update exp for vldb

2025-08-22 14:29:36 -07:00
98 changed files with 7635 additions and 16585 deletions
--- a/.github/ISSUE_TEMPLATE/bug_report.yml
+++ b/.github/ISSUE_TEMPLATE/bug_report.yml
@@ -1,50 +0,0 @@
-name: Bug Report
-description: Report a bug in LEANN
-labels: ["bug"]
-
-body:
-  - type: textarea
-    id: description
-    attributes:
-      label: What happened?
-      description: A clear description of the bug
-    validations:
-      required: true
-
-  - type: textarea
-    id: reproduce
-    attributes:
-      label: How to reproduce
-      placeholder: |
-        1. Install with...
-        2. Run command...
-        3. See error
-    validations:
-      required: true
-
-  - type: textarea
-    id: error
-    attributes:
-      label: Error message
-      description: Paste any error messages
-      render: shell
-
-  - type: input
-    id: version
-    attributes:
-      label: LEANN Version
-      placeholder: "0.1.0"
-    validations:
-      required: true
-
-  - type: dropdown
-    id: os
-    attributes:
-      label: Operating System
-      options:
-        - macOS
-        - Linux
-        - Windows
-        - Docker
-    validations:
-      required: true
--- a/.github/ISSUE_TEMPLATE/config.yml
+++ b/.github/ISSUE_TEMPLATE/config.yml
@@ -1,8 +0,0 @@
-blank_issues_enabled: true
-contact_links:
-  - name: Documentation
-    url: https://github.com/LEANN-RAG/LEANN-RAG/tree/main/docs
-    about: Read the docs first
-  - name: Discussions
-    url: https://github.com/LEANN-RAG/LEANN-RAG/discussions
-    about: Ask questions and share ideas
--- a/.github/ISSUE_TEMPLATE/feature_request.yml
+++ b/.github/ISSUE_TEMPLATE/feature_request.yml
@@ -1,27 +0,0 @@
-name: Feature Request
-description: Suggest a new feature for LEANN
-labels: ["enhancement"]
-
-body:
-  - type: textarea
-    id: problem
-    attributes:
-      label: What problem does this solve?
-      description: Describe the problem or need
-    validations:
-      required: true
-
-  - type: textarea
-    id: solution
-    attributes:
-      label: Proposed solution
-      description: How would you like this to work?
-    validations:
-      required: true
-
-  - type: textarea
-    id: example
-    attributes:
-      label: Example usage
-      description: Show how the API might look
-      render: python
--- a/.github/pull_request_template.md
+++ b/.github/pull_request_template.md
@@ -1,13 +0,0 @@
-## What does this PR do?
-
-<!-- Brief description of your changes -->
-
-## Related Issues
-
-Fixes #
-
-## Checklist
-
- [ ] Tests pass (`uv run pytest`)
- [ ] Code formatted (`ruff format` and `ruff check`)
- [ ] Pre-commit hooks pass (`pre-commit run --all-files`)
--- a/.github/workflows/build-reusable.yml
+++ b/.github/workflows/build-reusable.yml
@@ -17,17 +17,26 @@ jobs:
      - uses: actions/checkout@v4
        with:
          ref: ${{ inputs.ref }}
-          submodules: recursive

-      - name: Install uv and Python
-        uses: astral-sh/setup-uv@v6
+      - name: Setup Python
+        uses: actions/setup-python@v5
        with:
          python-version: '3.11'

-      - name: Run pre-commit with only lint group (no project deps)
-        run: |
-          uv run --only-group lint pre-commit run --all-files --show-diff-on-failure
+      - name: Install uv
+        uses: astral-sh/setup-uv@v4

+      - name: Install ruff
+        run: |
+          uv tool install ruff
+
+      - name: Run ruff check
+        run: |
+          ruff check .
+
+      - name: Run ruff format check
+        run: |
+          ruff format --check .

  build:
    needs: lint
@@ -45,17 +54,6 @@ jobs:
            python: '3.12'
          - os: ubuntu-22.04
            python: '3.13'
-          # ARM64 Linux builds
-          - os: ubuntu-24.04-arm
-            python: '3.9'
-          - os: ubuntu-24.04-arm
-            python: '3.10'
-          - os: ubuntu-24.04-arm
-            python: '3.11'
-          - os: ubuntu-24.04-arm
-            python: '3.12'
-          - os: ubuntu-24.04-arm
-            python: '3.13'
          - os: macos-14
            python: '3.9'
          - os: macos-14
@@ -94,11 +92,14 @@ jobs:
          ref: ${{ inputs.ref }}
          submodules: recursive

-      - name: Install uv and Python
-        uses: astral-sh/setup-uv@v6
+      - name: Setup Python
+        uses: actions/setup-python@v5
        with:
          python-version: ${{ matrix.python }}

+      - name: Install uv
+        uses: astral-sh/setup-uv@v6
+
      - name: Install system dependencies (Ubuntu)
        if: runner.os == 'Linux'
        run: |
@@ -107,46 +108,13 @@ jobs:
            pkg-config libabsl-dev libaio-dev libprotobuf-dev \
            patchelf

-          # Debug: Show system information
-          echo "🔍 System Information:"
-          echo "Architecture: $(uname -m)"
-          echo "OS: $(uname -a)"
-          echo "CPU info: $(lscpu | head -5)"
-
-          # Install math library based on architecture
-          ARCH=$(uname -m)
-          echo "🔍 Setting up math library for architecture: $ARCH"
-
-          if [[ "$ARCH" == "x86_64" ]]; then
-            # Install Intel MKL for DiskANN on x86_64
-            echo "📦 Installing Intel MKL for x86_64..."
-            wget -q https://registrationcenter-download.intel.com/akdlm/IRC_NAS/79153e0f-74d7-45af-b8c2-258941adf58a/intel-onemkl-2025.0.0.940.sh
-            sudo sh intel-onemkl-2025.0.0.940.sh -a --components intel.oneapi.lin.mkl.devel --action install --eula accept -s
-            source /opt/intel/oneapi/setvars.sh
-            echo "MKLROOT=/opt/intel/oneapi/mkl/latest" >> $GITHUB_ENV
-            echo "LD_LIBRARY_PATH=/opt/intel/oneapi/compiler/latest/linux/compiler/lib/intel64_lin" >> $GITHUB_ENV
-            echo "LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/opt/intel/oneapi/mkl/latest/lib/intel64" >> $GITHUB_ENV
-            echo "✅ Intel MKL installed for x86_64"
-
-            # Debug: Check MKL installation
-            echo "🔍 MKL Installation Check:"
-            ls -la /opt/intel/oneapi/mkl/latest/ || echo "MKL directory not found"
-            ls -la /opt/intel/oneapi/mkl/latest/lib/ || echo "MKL lib directory not found"
-
-          elif [[ "$ARCH" == "aarch64" ]]; then
-            # Use OpenBLAS for ARM64 (MKL installer not compatible with ARM64)
-            echo "📦 Installing OpenBLAS for ARM64..."
-            sudo apt-get install -y libopenblas-dev liblapack-dev liblapacke-dev
-            echo "✅ OpenBLAS installed for ARM64"
-
-            # Debug: Check OpenBLAS installation
-            echo "🔍 OpenBLAS Installation Check:"
-            dpkg -l | grep openblas || echo "OpenBLAS package not found"
-            ls -la /usr/lib/aarch64-linux-gnu/openblas/ || echo "OpenBLAS directory not found"
-          fi
-
-          # Debug: Show final library paths
-          echo "🔍 Final LD_LIBRARY_PATH: $LD_LIBRARY_PATH"
+          # Install Intel MKL for DiskANN
+          wget -q https://registrationcenter-download.intel.com/akdlm/IRC_NAS/79153e0f-74d7-45af-b8c2-258941adf58a/intel-onemkl-2025.0.0.940.sh
+          sudo sh intel-onemkl-2025.0.0.940.sh -a --components intel.oneapi.lin.mkl.devel --action install --eula accept -s
+          source /opt/intel/oneapi/setvars.sh
+          echo "MKLROOT=/opt/intel/oneapi/mkl/latest" >> $GITHUB_ENV
+          echo "LD_LIBRARY_PATH=/opt/intel/oneapi/compiler/latest/linux/compiler/lib/intel64_lin" >> $GITHUB_ENV
+          echo "LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/opt/intel/oneapi/mkl/latest/lib/intel64" >> $GITHUB_ENV

      - name: Install system dependencies (macOS)
        if: runner.os == 'macOS'
@@ -156,24 +124,11 @@ jobs:

      - name: Install build dependencies
        run: |
-          uv python install ${{ matrix.python }}
-          uv venv --python ${{ matrix.python }} .uv-build
-          if [[ "$RUNNER_OS" == "Windows" ]]; then
-            BUILD_PY=".uv-build\\Scripts\\python.exe"
-          else
-            BUILD_PY=".uv-build/bin/python"
-          fi
-          uv pip install --python "$BUILD_PY" scikit-build-core numpy swig Cython pybind11
+          uv pip install --system scikit-build-core numpy swig Cython pybind11
          if [[ "$RUNNER_OS" == "Linux" ]]; then
-            uv pip install --python "$BUILD_PY" auditwheel
+            uv pip install --system auditwheel
          else
-            uv pip install --python "$BUILD_PY" delocate
-          fi
-
-          if [[ "$RUNNER_OS" == "Windows" ]]; then
-            echo "$(pwd)\\.uv-build\\Scripts" >> $GITHUB_PATH
-          else
-            echo "$(pwd)/.uv-build/bin" >> $GITHUB_PATH
+            uv pip install --system delocate
          fi

      - name: Set macOS environment variables
@@ -309,66 +264,18 @@ jobs:

      - name: Install built packages for testing
        run: |
-          # Create uv-managed virtual environment with the requested interpreter
-          uv python install ${{ matrix.python }}
+          # Create a virtual environment with the correct Python version
          uv venv --python ${{ matrix.python }}
          source .venv/bin/activate || source .venv/Scripts/activate

-          if [[ "$RUNNER_OS" == "Windows" ]]; then
-            UV_PY=".venv\\Scripts\\python.exe"
-          else
-            UV_PY=".venv/bin/python"
-          fi
+          # Install packages using --find-links to prioritize local builds
+          uv pip install --find-links packages/leann-core/dist --find-links packages/leann-backend-hnsw/dist --find-links packages/leann-backend-diskann/dist packages/leann-core/dist/*.whl || uv pip install --find-links packages/leann-core/dist packages/leann-core/dist/*.tar.gz
+          uv pip install --find-links packages/leann-core/dist packages/leann-backend-hnsw/dist/*.whl
+          uv pip install --find-links packages/leann-core/dist packages/leann-backend-diskann/dist/*.whl
+          uv pip install packages/leann/dist/*.whl || uv pip install packages/leann/dist/*.tar.gz

-          # Install test dependency group only (avoids reinstalling project package)
-          uv pip install --python "$UV_PY" --group test
-
-          # Install core wheel built in this job
-          CORE_WHL=$(find packages/leann-core/dist -maxdepth 1 -name "*.whl" -print -quit)
-          if [[ -n "$CORE_WHL" ]]; then
-            uv pip install --python "$UV_PY" "$CORE_WHL"
-          else
-            uv pip install --python "$UV_PY" packages/leann-core/dist/*.tar.gz
-          fi
-
-          PY_TAG=$($UV_PY -c "import sys; print(f'cp{sys.version_info[0]}{sys.version_info[1]}')")
-
-          if [[ "$RUNNER_OS" == "macOS" ]]; then
-            if [[ "${{ matrix.os }}" == "macos-13" ]]; then
-              export MACOSX_DEPLOYMENT_TARGET=13.3
-            elif [[ "${{ matrix.os }}" == "macos-14" ]]; then
-              export MACOSX_DEPLOYMENT_TARGET=14.0
-            elif [[ "${{ matrix.os }}" == "macos-15" ]]; then
-              export MACOSX_DEPLOYMENT_TARGET=15.0
-            fi
-          fi
-
-          HNSW_WHL=$(find packages/leann-backend-hnsw/dist -maxdepth 1 -name "*-${PY_TAG}-*.whl" -print -quit)
-          if [[ -z "$HNSW_WHL" ]]; then
-            HNSW_WHL=$(find packages/leann-backend-hnsw/dist -maxdepth 1 -name "*-py3-*.whl" -print -quit)
-          fi
-          if [[ -n "$HNSW_WHL" ]]; then
-            uv pip install --python "$UV_PY" "$HNSW_WHL"
-          else
-            uv pip install --python "$UV_PY" ./packages/leann-backend-hnsw
-          fi
-
-          DISKANN_WHL=$(find packages/leann-backend-diskann/dist -maxdepth 1 -name "*-${PY_TAG}-*.whl" -print -quit)
-          if [[ -z "$DISKANN_WHL" ]]; then
-            DISKANN_WHL=$(find packages/leann-backend-diskann/dist -maxdepth 1 -name "*-py3-*.whl" -print -quit)
-          fi
-          if [[ -n "$DISKANN_WHL" ]]; then
-            uv pip install --python "$UV_PY" "$DISKANN_WHL"
-          else
-            uv pip install --python "$UV_PY" ./packages/leann-backend-diskann
-          fi
-
-          LEANN_WHL=$(find packages/leann/dist -maxdepth 1 -name "*.whl" -print -quit)
-          if [[ -n "$LEANN_WHL" ]]; then
-            uv pip install --python "$UV_PY" "$LEANN_WHL"
-          else
-            uv pip install --python "$UV_PY" packages/leann/dist/*.tar.gz
-          fi
+          # Install test dependencies using extras
+          uv pip install -e ".[test]"

      - name: Run tests with pytest
        env:
--- a/.gitignore
+++ b/.gitignore
@@ -18,12 +18,10 @@ demo/experiment_results/**/*.json
 *.eml
 *.emlx
 *.json
-*.png
 !.vscode/*.json
 *.sh
 *.txt
 !CMakeLists.txt
-!llms.txt
 latency_breakdown*.json
 experiment_results/eval_results/diskann/*.json
 aws/
@@ -95,13 +93,18 @@ packages/leann-backend-diskann/third_party/DiskANN/_deps/
 batchtest.py
 tests/__pytest_cache__/
 tests/__pycache__/
+paru-bin/
+
+CLAUDE.md
+CLAUDE.local.md
+.claude/*.local.*
+.claude/local/*
+
 benchmarks/data/
-
-## multi vector
-apps/multimodal/vision-based-pdf-multi-vector/multi-vector-colpali-native-weaviate.py
-
-# Ignore all PDFs (keep data exceptions above) and do not track demo PDFs
-# If you need to commit a specific demo PDF, remove this negation locally.
-# The following line used to force-add a large demo PDF; remove it to satisfy pre-commit:
-# !apps/multimodal/vision-based-pdf-multi-vector/pdfs/2004.12832v2.pdf
-!apps/multimodal/vision-based-pdf-multi-vector/fig/*
+!benchmarks/data/prompts_g5/*.txt
+!benchmarks/run_all.sh
+!benchmarks/run_speed_bench_all.sh
+!benchmarks/simple_mac_tpt_test.py
+!benchmarks/run_speed_bench_all.sh
+!benchmarks/run_speed_bench_all.sh
+!benchmarks/run_speed_bench_all.sh
--- a/.gitmodules
+++ b/.gitmodules
@@ -14,6 +14,3 @@
 [submodule "packages/leann-backend-hnsw/third_party/libzmq"]
 	path = packages/leann-backend-hnsw/third_party/libzmq
 	url = https://github.com/zeromq/libzmq.git
-[submodule "packages/astchunk-leann"]
-	path = packages/astchunk-leann
-	url = https://github.com/yichuan-w/astchunk-leann.git
--- a/README.md
+++ b/README.md
@@ -8,8 +8,6 @@
  <img src="https://img.shields.io/badge/Platform-Ubuntu%20%26%20Arch%20%26%20WSL%20%7C%20macOS%20(ARM64%2FIntel)-lightgrey" alt="Platform">
  <img src="https://img.shields.io/badge/License-MIT-green.svg" alt="MIT License">
  <img src="https://img.shields.io/badge/MCP-Native%20Integration-blue" alt="MCP Integration">
-  <a href="https://join.slack.com/t/leann-e2u9779/shared_invite/zt-3ckd2f6w1-OX08~NN4gkWhh10PRVBj1Q"><img src="https://img.shields.io/badge/Slack-Join-4A154B?logo=slack&logoColor=white" alt="Join Slack">
-  <a href="assets/wechat_user_group.JPG" title="Join WeChat group"><img src="https://img.shields.io/badge/WeChat-Join-2DC100?logo=wechat&logoColor=white" alt="Join WeChat group"></a>
 </p>

 <h2 align="center" tabindex="-1" class="heading-element" dir="auto">
@@ -20,7 +18,7 @@ LEANN is an innovative vector database that democratizes personal AI. Transform

 LEANN achieves this through *graph-based selective recomputation* with *high-degree preserving pruning*, computing embeddings on-demand instead of storing them all. [Illustration Fig →](#️-architecture--how-it-works) | [Paper →](https://arxiv.org/abs/2506.08276)

-**Ready to RAG Everything?** Transform your laptop into a personal AI assistant that can semantic search your **[file system](#-personal-data-manager-process-any-documents-pdf-txt-md)**, **[emails](#-your-personal-email-secretary-rag-on-apple-mail)**, **[browser history](#-time-machine-for-the-web-rag-your-entire-browser-history)**, **[chat history](#-wechat-detective-unlock-your-golden-memories)** ([WeChat](#-wechat-detective-unlock-your-golden-memories), [iMessage](#-imessage-history-your-personal-conversation-archive)), **[agent memory](#-chatgpt-chat-history-your-personal-ai-conversation-archive)** ([ChatGPT](#-chatgpt-chat-history-your-personal-ai-conversation-archive), [Claude](#-claude-chat-history-your-personal-ai-conversation-archive)), **[live data](#mcp-integration-rag-on-live-data-from-any-platform)** ([Slack](#slack-messages-search-your-team-conversations), [Twitter](#twitter-bookmarks-your-personal-tweet-library)), **[codebase](#-claude-code-integration-transform-your-development-workflow)**\* , or external knowledge bases (i.e., 60M documents) - all on your laptop, with zero cloud costs and complete privacy.
+**Ready to RAG Everything?** Transform your laptop into a personal AI assistant that can semantic search your **[file system](#-personal-data-manager-process-any-documents-pdf-txt-md)**, **[emails](#-your-personal-email-secretary-rag-on-apple-mail)**, **[browser history](#-time-machine-for-the-web-rag-your-entire-browser-history)**, **[chat history](#-wechat-detective-unlock-your-golden-memories)**, **[codebase](#-claude-code-integration-transform-your-development-workflow)**\* , or external knowledge bases (i.e., 60M documents) - all on your laptop, with zero cloud costs and complete privacy.


 \* Claude Code only supports basic `grep`-style keyword search. **LEANN** is a drop-in **semantic search MCP service fully compatible with Claude Code**, unlocking intelligent retrieval without changing your workflow. 🔥 Check out [the easy setup →](packages/leann-mcp/README.md)
@@ -72,9 +70,8 @@ uv venv
 source .venv/bin/activate
 uv pip install leann
 ```
-
 <!--
-> Low-resource? See "Low-resource setups" in the [Configuration Guide](docs/configuration-guide.md#low-resource-setups). -->
+> Low-resource? See “Low-resource setups” in the [Configuration Guide](docs/configuration-guide.md#low-resource-setups). -->

 <details>
 <summary>
@@ -177,16 +174,13 @@ response = chat.ask("How much storage does LEANN save?", top_k=1)

 ## RAG on Everything!

-LEANN supports RAG on various data sources including documents (`.pdf`, `.txt`, `.md`), Apple Mail, Google Search History, WeChat, ChatGPT conversations, Claude conversations, iMessage conversations, and **live data from any platform through MCP (Model Context Protocol) servers** - including Slack, Twitter, and more.
+LEANN supports RAG on various data sources including documents (`.pdf`, `.txt`, `.md`), Apple Mail, Google Search History, WeChat, and more.



 ### Generation Model Setup

-#### LLM Backend
-
-LEANN supports many LLM providers for text generation (HuggingFace, Ollama, and Any OpenAI compatible API).
-
+LEANN supports multiple LLM providers for text generation (OpenAI API, HuggingFace, Ollama).

 <details>
 <summary><strong>🔑 OpenAI API Setup (Default)</strong></summary>
@@ -197,68 +191,6 @@ Set your OpenAI API key as an environment variable:
 export OPENAI_API_KEY="your-api-key-here"
 ```

-Make sure to use `--llm openai` flag when using the CLI.
-You can also specify the model name with `--llm-model <model-name>` flag.
-
-</details>
-
-<details>
-<summary><strong>🛠️ Supported LLM & Embedding Providers (via OpenAI Compatibility)</strong></summary>
-
-Thanks to the widespread adoption of the OpenAI API format, LEANN is compatible out-of-the-box with a vast array of LLM and embedding providers. Simply set the `OPENAI_BASE_URL` and `OPENAI_API_KEY` environment variables to connect to your preferred service.
-
-```sh
-export OPENAI_API_KEY="xxx"
-export OPENAI_BASE_URL="http://localhost:1234/v1" # base url of the provider
-```
-
-To use OpenAI compatible endpoint with the CLI interface:
-
-If you are using it for text generation, make sure to use `--llm openai` flag and specify the model name with `--llm-model <model-name>` flag.
-
-If you are using it for embedding, set the `--embedding-mode openai` flag and specify the model name with `--embedding-model <MODEL>`.
-
-----
-
-
-Below is a list of base URLs for common providers to get you started.
-
-
-### 🖥️ Local Inference Engines (Recommended for full privacy)
-
-| Provider         | Sample Base URL             |
-| ---------------- | --------------------------- |
-| **Ollama** | `http://localhost:11434/v1` |
-| **LM Studio** | `http://localhost:1234/v1`  |
-| **vLLM** | `http://localhost:8000/v1`  |
-| **llama.cpp** | `http://localhost:8080/v1`  |
-| **SGLang** | `http://localhost:30000/v1` |
-| **LiteLLM** | `http://localhost:4000`     |
-
-----
-
-### ☁️ Cloud Providers
-
-> **🚨 A Note on Privacy:** Before choosing a cloud provider, carefully review their privacy and data retention policies. Depending on their terms, your data may be used for their own purposes, including but not limited to human reviews and model training, which can lead to serious consequences if not handled properly.
-
-
-| Provider         | Base URL                                                   |
-| ---------------- | ---------------------------------------------------------- |
-| **OpenAI** | `https://api.openai.com/v1`                                |
-| **OpenRouter** | `https://openrouter.ai/api/v1`                             |
-| **Gemini** | `https://generativelanguage.googleapis.com/v1beta/openai/` |
-| **x.AI (Grok)** | `https://api.x.ai/v1`                                      |
-| **Groq AI** | `https://api.groq.com/openai/v1`                           |
-| **DeepSeek** | `https://api.deepseek.com/v1`                              |
-| **SiliconFlow** | `https://api.siliconflow.cn/v1`                            |
-| **Zhipu (BigModel)** | `https://open.bigmodel.cn/api/paas/v4/`                |
-| **Mistral AI** | `https://api.mistral.ai/v1`                                |
-
-
-
-
-If your provider isn't on this list, don't worry! Check their documentation for an OpenAI-compatible endpoint—chances are, it's OpenAI Compatible too!
-
 </details>

 <details>
@@ -543,387 +475,6 @@ Once the index is built, you can ask questions like:

 </details>

-### 🤖 ChatGPT Chat History: Your Personal AI Conversation Archive!
-
-Transform your ChatGPT conversations into a searchable knowledge base! Search through all your ChatGPT discussions about coding, research, brainstorming, and more.
-
-```bash
-python -m apps.chatgpt_rag --export-path chatgpt_export.html --query "How do I create a list in Python?"
-```
-
-**Unlock your AI conversation history.** Never lose track of valuable insights from your ChatGPT discussions again.
-
-<details>
-<summary><strong>📋 Click to expand: How to Export ChatGPT Data</strong></summary>
-
-**Step-by-step export process:**
-
-1. **Sign in to ChatGPT**
-2. **Click your profile icon** in the top right corner
-3. **Navigate to Settings** → **Data Controls**
-4. **Click "Export"** under Export Data
-5. **Confirm the export** request
-6. **Download the ZIP file** from the email link (expires in 24 hours)
-7. **Extract or use directly** with LEANN
-
-**Supported formats:**
- `.html` files from ChatGPT exports
- `.zip` archives from ChatGPT
- Directories with multiple export files
-
-</details>
-
-<details>
-<summary><strong>📋 Click to expand: ChatGPT-Specific Arguments</strong></summary>
-
-#### Parameters
-```bash
--export-path PATH           # Path to ChatGPT export file (.html/.zip) or directory (default: ./chatgpt_export)
--separate-messages         # Process each message separately instead of concatenated conversations
--chunk-size N              # Text chunk size (default: 512)
--chunk-overlap N           # Overlap between chunks (default: 128)
-```
-
-#### Example Commands
-```bash
-# Basic usage with HTML export
-python -m apps.chatgpt_rag --export-path conversations.html
-
-# Process ZIP archive from ChatGPT
-python -m apps.chatgpt_rag --export-path chatgpt_export.zip
-
-# Search with specific query
-python -m apps.chatgpt_rag --export-path chatgpt_data.html --query "Python programming help"
-
-# Process individual messages for fine-grained search
-python -m apps.chatgpt_rag --separate-messages --export-path chatgpt_export.html
-
-# Process directory containing multiple exports
-python -m apps.chatgpt_rag --export-path ./chatgpt_exports/ --max-items 1000
-```
-
-</details>
-
-<details>
-<summary><strong>💡 Click to expand: Example queries you can try</strong></summary>
-
-Once your ChatGPT conversations are indexed, you can search with queries like:
- "What did I ask ChatGPT about Python programming?"
- "Show me conversations about machine learning algorithms"
- "Find discussions about web development frameworks"
- "What coding advice did ChatGPT give me?"
- "Search for conversations about debugging techniques"
- "Find ChatGPT's recommendations for learning resources"
-
-</details>
-
-### 🤖 Claude Chat History: Your Personal AI Conversation Archive!
-
-Transform your Claude conversations into a searchable knowledge base! Search through all your Claude discussions about coding, research, brainstorming, and more.
-
-```bash
-python -m apps.claude_rag --export-path claude_export.json --query "What did I ask about Python dictionaries?"
-```
-
-**Unlock your AI conversation history.** Never lose track of valuable insights from your Claude discussions again.
-
-<details>
-<summary><strong>📋 Click to expand: How to Export Claude Data</strong></summary>
-
-**Step-by-step export process:**
-
-1. **Open Claude** in your browser
-2. **Navigate to Settings** (look for gear icon or settings menu)
-3. **Find Export/Download** options in your account settings
-4. **Download conversation data** (usually in JSON format)
-5. **Place the file** in your project directory
-
-*Note: Claude export methods may vary depending on the interface you're using. Check Claude's help documentation for the most current export instructions.*
-
-**Supported formats:**
- `.json` files (recommended)
- `.zip` archives containing JSON data
- Directories with multiple export files
-
-</details>
-
-<details>
-<summary><strong>📋 Click to expand: Claude-Specific Arguments</strong></summary>
-
-#### Parameters
-```bash
--export-path PATH           # Path to Claude export file (.json/.zip) or directory (default: ./claude_export)
--separate-messages         # Process each message separately instead of concatenated conversations
--chunk-size N              # Text chunk size (default: 512)
--chunk-overlap N           # Overlap between chunks (default: 128)
-```
-
-#### Example Commands
-```bash
-# Basic usage with JSON export
-python -m apps.claude_rag --export-path my_claude_conversations.json
-
-# Process ZIP archive from Claude
-python -m apps.claude_rag --export-path claude_export.zip
-
-# Search with specific query
-python -m apps.claude_rag --export-path claude_data.json --query "machine learning advice"
-
-# Process individual messages for fine-grained search
-python -m apps.claude_rag --separate-messages --export-path claude_export.json
-
-# Process directory containing multiple exports
-python -m apps.claude_rag --export-path ./claude_exports/ --max-items 1000
-```
-
-</details>
-
-<details>
-<summary><strong>💡 Click to expand: Example queries you can try</strong></summary>
-
-Once your Claude conversations are indexed, you can search with queries like:
- "What did I ask Claude about Python programming?"
- "Show me conversations about machine learning algorithms"
- "Find discussions about software architecture patterns"
- "What debugging advice did Claude give me?"
- "Search for conversations about data structures"
- "Find Claude's recommendations for learning resources"
-
-</details>
-
-### 💬 iMessage History: Your Personal Conversation Archive!
-
-Transform your iMessage conversations into a searchable knowledge base! Search through all your text messages, group chats, and conversations with friends, family, and colleagues.
-
-```bash
-python -m apps.imessage_rag --query "What did we discuss about the weekend plans?"
-```
-
-**Unlock your message history.** Never lose track of important conversations, shared links, or memorable moments from your iMessage history.
-
-<details>
-<summary><strong>📋 Click to expand: How to Access iMessage Data</strong></summary>
-
-**iMessage data location:**
-
-iMessage conversations are stored in a SQLite database on your Mac at:
-```
-~/Library/Messages/chat.db
-```
-
-**Important setup requirements:**
-
-1. **Grant Full Disk Access** to your terminal or IDE:
-   - Open **System Preferences** → **Security & Privacy** → **Privacy**
-   - Select **Full Disk Access** from the left sidebar
-   - Click the **+** button and add your terminal app (Terminal, iTerm2) or IDE (VS Code, etc.)
-   - Restart your terminal/IDE after granting access
-
-2. **Alternative: Use a backup database**
-   - If you have Time Machine backups or manual copies of the database
-   - Use `--db-path` to specify a custom location
-
-**Supported formats:**
- Direct access to `~/Library/Messages/chat.db` (default)
- Custom database path with `--db-path`
- Works with backup copies of the database
-
-</details>
-
-<details>
-<summary><strong>📋 Click to expand: iMessage-Specific Arguments</strong></summary>
-
-#### Parameters
-```bash
--db-path PATH                    # Path to chat.db file (default: ~/Library/Messages/chat.db)
--concatenate-conversations       # Group messages by conversation (default: True)
--no-concatenate-conversations    # Process each message individually
--chunk-size N                    # Text chunk size (default: 1000)
--chunk-overlap N                 # Overlap between chunks (default: 200)
-```
-
-#### Example Commands
-```bash
-# Basic usage (requires Full Disk Access)
-python -m apps.imessage_rag
-
-# Search with specific query
-python -m apps.imessage_rag --query "family dinner plans"
-
-# Use custom database path
-python -m apps.imessage_rag --db-path /path/to/backup/chat.db
-
-# Process individual messages instead of conversations
-python -m apps.imessage_rag --no-concatenate-conversations
-
-# Limit processing for testing
-python -m apps.imessage_rag --max-items 100 --query "weekend"
-```
-
-</details>
-
-<details>
-<summary><strong>💡 Click to expand: Example queries you can try</strong></summary>
-
-Once your iMessage conversations are indexed, you can search with queries like:
- "What did we discuss about vacation plans?"
- "Find messages about restaurant recommendations"
- "Show me conversations with John about the project"
- "Search for shared links about technology"
- "Find group chat discussions about weekend events"
- "What did mom say about the family gathering?"
-
-</details>
-
-### MCP Integration: RAG on Live Data from Any Platform
-
-**NEW!** Connect to live data sources through the Model Context Protocol (MCP). LEANN now supports real-time RAG on platforms like Slack, Twitter, and more through standardized MCP servers.
-
-**Key Benefits:**
- **Live Data Access**: Fetch real-time data without manual exports
- **Standardized Protocol**: Use any MCP-compatible server
- **Easy Extension**: Add new platforms with minimal code
- **Secure Access**: MCP servers handle authentication
-
-<details>
-<summary><strong>Slack Messages: Search Your Team Conversations</strong></summary>
-
-Transform your Slack workspace into a searchable knowledge base! Find discussions, decisions, and shared knowledge across all your channels.
-
-```bash
-# Test MCP server connection
-python -m apps.slack_rag --mcp-server "slack-mcp-server" --test-connection
-
-# Index and search Slack messages
-python -m apps.slack_rag \
-  --mcp-server "slack-mcp-server" \
-  --workspace-name "my-team" \
-  --channels general dev-team random \
-  --query "What did we decide about the product launch?"
-```
-
-**Setup Requirements:**
-1. Install a Slack MCP server (e.g., `npm install -g slack-mcp-server`)
-2. Create a Slack App and get API credentials:
-   - Go to [api.slack.com/apps](https://api.slack.com/apps) and create a new app
-   - Under "OAuth & Permissions", add these Bot Token Scopes: `channels:read`, `channels:history`, `groups:read`, `groups:history`, `im:read`, `im:history`, `mpim:read`, `mpim:history`
-   - Install the app to your workspace and copy the "Bot User OAuth Token" (starts with `xoxb-`)
-   - Under "App-Level Tokens", create a token with `connections:write` scope (starts with `xapp-`)
-   ```bash
-   export SLACK_BOT_TOKEN="xoxb-your-bot-token"
-   export SLACK_APP_TOKEN="xapp-your-app-token"
-   ```
-3. Test connection with `--test-connection` flag
-
-**Arguments:**
- `--mcp-server`: Command to start the Slack MCP server
- `--workspace-name`: Slack workspace name for organization
- `--channels`: Specific channels to index (optional)
- `--concatenate-conversations`: Group messages by channel (default: true)
- `--max-messages-per-channel`: Limit messages per channel (default: 100)
-
-</details>
-
-<details>
-<summary><strong>Twitter Bookmarks: Your Personal Tweet Library</strong></summary>
-
-Search through your Twitter bookmarks! Find that perfect article, thread, or insight you saved for later.
-
-```bash
-# Test MCP server connection
-python -m apps.twitter_rag --mcp-server "twitter-mcp-server" --test-connection
-
-# Index and search Twitter bookmarks
-python -m apps.twitter_rag \
-  --mcp-server "twitter-mcp-server" \
-  --max-bookmarks 1000 \
-  --query "What AI articles did I bookmark about machine learning?"
-```
-
-**Setup Requirements:**
-1. Install a Twitter MCP server (e.g., `npm install -g twitter-mcp-server`)
-2. Get Twitter API credentials:
-   - Apply for a Twitter Developer Account at [developer.twitter.com](https://developer.twitter.com)
-   - Create a new app in the Twitter Developer Portal
-   - Generate API keys and access tokens with "Read" permissions
-   - For bookmarks access, you may need Twitter API v2 with appropriate scopes
-   ```bash
-   export TWITTER_API_KEY="your-api-key"
-   export TWITTER_API_SECRET="your-api-secret"
-   export TWITTER_ACCESS_TOKEN="your-access-token"
-   export TWITTER_ACCESS_TOKEN_SECRET="your-access-token-secret"
-   ```
-3. Test connection with `--test-connection` flag
-
-**Arguments:**
- `--mcp-server`: Command to start the Twitter MCP server
- `--username`: Filter bookmarks by username (optional)
- `--max-bookmarks`: Maximum bookmarks to fetch (default: 1000)
- `--no-tweet-content`: Exclude tweet content, only metadata
- `--no-metadata`: Exclude engagement metadata
-
-</details>
-
-<details>
-<summary><strong>💡 Click to expand: Example queries you can try</strong></summary>
-
-**Slack Queries:**
- "What did the team discuss about the project deadline?"
- "Find messages about the new feature launch"
- "Show me conversations about budget planning"
- "What decisions were made in the dev-team channel?"
-
-**Twitter Queries:**
- "What AI articles did I bookmark last month?"
- "Find tweets about machine learning techniques"
- "Show me bookmarked threads about startup advice"
- "What Python tutorials did I save?"
-
-</details>
-
-<details>
-<summary><strong>🔧 Using MCP with CLI Commands</strong></summary>
-
-**Want to use MCP data with regular LEANN CLI?** You can combine MCP apps with CLI commands:
-
-```bash
-# Step 1: Use MCP app to fetch and index data
-python -m apps.slack_rag --mcp-server "slack-mcp-server" --workspace-name "my-team"
-
-# Step 2: The data is now indexed and available via CLI
-leann search slack_messages "project deadline"
-leann ask slack_messages "What decisions were made about the product launch?"
-
-# Same for Twitter bookmarks
-python -m apps.twitter_rag --mcp-server "twitter-mcp-server"
-leann search twitter_bookmarks "machine learning articles"
-```
-
-**MCP vs Manual Export:**
- **MCP**: Live data, automatic updates, requires server setup
- **Manual Export**: One-time setup, works offline, requires manual data export
-
-</details>
-
-<details>
-<summary><strong>🔧 Adding New MCP Platforms</strong></summary>
-
-Want to add support for other platforms? LEANN's MCP integration is designed for easy extension:
-
-1. **Find or create an MCP server** for your platform
-2. **Create a reader class** following the pattern in `apps/slack_data/slack_mcp_reader.py`
-3. **Create a RAG application** following the pattern in `apps/slack_rag.py`
-4. **Test and contribute** back to the community!
-
-**Popular MCP servers to explore:**
- GitHub repositories and issues
- Discord messages
- Notion pages
- Google Drive documents
- And many more in the MCP ecosystem!
-
-</details>
-
 ### 🚀 Claude Code Integration: Transform Your Development Workflow!

 <details>
@@ -955,7 +506,7 @@ Try our fully agentic pipeline with auto query rewriting, semantic search planni

 **🔥 Ready to supercharge your coding?** [Complete Setup Guide →](packages/leann-mcp/README.md)

-## Command Line Interface
+## 🖥️ Command Line Interface

 LEANN includes a powerful CLI for document processing and search. Perfect for quick document indexing and interactive chat.

@@ -993,9 +544,6 @@ leann search my-docs "machine learning concepts"
 # Interactive chat with your documents
 leann ask my-docs --interactive

-# Ask a single question (non-interactive)
-leann ask my-docs "Where are prompts configured?"
-
 # List all your indexes
 leann list

@@ -1106,19 +654,6 @@ results = searcher.search(

 📖 **[Complete Metadata filtering guide →](docs/metadata_filtering.md)**

-### 🔍 Grep Search
-
-For exact text matching instead of semantic search, use the `use_grep` parameter:
-
-```python
-# Exact text search
-results = searcher.search("banana‑crocodile", use_grep=True, top_k=1)
-```
-
-**Use cases**: Finding specific code patterns, error messages, function names, or exact phrases where semantic similarity isn't needed.
-
-📖 **[Complete grep search guide →](docs/grep_search.md)**
-
 ## 🏗️ Architecture & How It Works

 <p align="center">
@@ -1156,8 +691,9 @@ results = searcher.search("banana‑crocodile", use_grep=True, top_k=1)
 ## Reproduce Our Results

 ```bash
-uv run benchmarks/run_evaluation.py    # Will auto-download evaluation data and run benchmarks
-uv run benchmarks/run_evaluation.py benchmarks/data/indices/rpj_wiki/rpj_wiki --num-queries 2000    # After downloading data, you can run the benchmark with our biggest index
+uv pip install -e ".[dev]"  # Install dev dependencies
+python benchmarks/run_evaluation.py    # Will auto-download evaluation data and run benchmarks
+python benchmarks/run_evaluation.py benchmarks/data/indices/rpj_wiki/rpj_wiki --num-queries 2000    # After downloading data, you can run the benchmark with our biggest index
 ```

 The evaluation script downloads data automatically on first run. The last three results were tested with partial personal data, and you can reproduce them with your own data!
@@ -1197,7 +733,7 @@ MIT License - see [LICENSE](LICENSE) for details.

 Core Contributors: [Yichuan Wang](https://yichuan-w.github.io/) & [Zhifei Li](https://github.com/andylizf).

-Active Contributors: [Gabriel Dehan](https://github.com/gabriel-dehan), [Aakash Suresh](https://github.com/ASuresh0524)
+Active Contributors: [Gabriel Dehan](https://github.com/gabriel-dehan)


 We welcome more contributors! Feel free to open issues or submit PRs.
--- a/apps/base_rag_example.py
+++ b/apps/base_rag_example.py
@@ -11,7 +11,6 @@ from typing import Any
 import dotenv
 from leann.api import LeannBuilder, LeannChat
 from leann.registry import register_project_directory
-from leann.settings import resolve_ollama_host, resolve_openai_api_key, resolve_openai_base_url

 dotenv.load_dotenv()

@@ -79,24 +78,6 @@ class BaseRAGExample(ABC):
            choices=["sentence-transformers", "openai", "mlx", "ollama"],
            help="Embedding backend mode (default: sentence-transformers), we provide sentence-transformers, openai, mlx, or ollama",
        )
-        embedding_group.add_argument(
-            "--embedding-host",
-            type=str,
-            default=None,
-            help="Override Ollama-compatible embedding host",
-        )
-        embedding_group.add_argument(
-            "--embedding-api-base",
-            type=str,
-            default=None,
-            help="Base URL for OpenAI-compatible embedding services",
-        )
-        embedding_group.add_argument(
-            "--embedding-api-key",
-            type=str,
-            default=None,
-            help="API key for embedding service (defaults to OPENAI_API_KEY)",
-        )

        # LLM parameters
        llm_group = parser.add_argument_group("LLM Parameters")
@@ -116,8 +97,8 @@ class BaseRAGExample(ABC):
        llm_group.add_argument(
            "--llm-host",
            type=str,
-            default=None,
-            help="Host for Ollama-compatible APIs (defaults to LEANN_OLLAMA_HOST/OLLAMA_HOST)",
+            default="http://localhost:11434",
+            help="Host for Ollama API (default: http://localhost:11434)",
        )
        llm_group.add_argument(
            "--thinking-budget",
@@ -126,18 +107,6 @@ class BaseRAGExample(ABC):
            default=None,
            help="Thinking budget for reasoning models (low/medium/high). Supported by GPT-Oss:20b and other reasoning models.",
        )
-        llm_group.add_argument(
-            "--llm-api-base",
-            type=str,
-            default=None,
-            help="Base URL for OpenAI-compatible APIs",
-        )
-        llm_group.add_argument(
-            "--llm-api-key",
-            type=str,
-            default=None,
-            help="API key for OpenAI-compatible APIs (defaults to OPENAI_API_KEY)",
-        )

        # AST Chunking parameters
        ast_group = parser.add_argument_group("AST Chunking Parameters")
@@ -236,13 +205,9 @@ class BaseRAGExample(ABC):

        if args.llm == "openai":
            config["model"] = args.llm_model or "gpt-4o"
-            config["base_url"] = resolve_openai_base_url(args.llm_api_base)
-            resolved_key = resolve_openai_api_key(args.llm_api_key)
-            if resolved_key:
-                config["api_key"] = resolved_key
        elif args.llm == "ollama":
            config["model"] = args.llm_model or "llama3.2:1b"
-            config["host"] = resolve_ollama_host(args.llm_host)
+            config["host"] = args.llm_host
        elif args.llm == "hf":
            config["model"] = args.llm_model or "Qwen/Qwen2.5-1.5B-Instruct"
        elif args.llm == "simulated":
@@ -258,20 +223,10 @@ class BaseRAGExample(ABC):
        print(f"\n[Building Index] Creating {self.name} index...")
        print(f"Total text chunks: {len(texts)}")

-        embedding_options: dict[str, Any] = {}
-        if args.embedding_mode == "ollama":
-            embedding_options["host"] = resolve_ollama_host(args.embedding_host)
-        elif args.embedding_mode == "openai":
-            embedding_options["base_url"] = resolve_openai_base_url(args.embedding_api_base)
-            resolved_embedding_key = resolve_openai_api_key(args.embedding_api_key)
-            if resolved_embedding_key:
-                embedding_options["api_key"] = resolved_embedding_key
-
        builder = LeannBuilder(
            backend_name=args.backend_name,
            embedding_model=args.embedding_model,
            embedding_mode=args.embedding_mode,
-            embedding_options=embedding_options or None,
            graph_degree=args.graph_degree,
            complexity=args.build_complexity,
            is_compact=not args.no_compact,
--- a/apps/browser_rag.py
+++ b/apps/browser_rag.py
@@ -10,8 +10,7 @@ from pathlib import Path
 # Add parent directory to path for imports
 sys.path.insert(0, str(Path(__file__).parent))

-from base_rag_example import BaseRAGExample
-from chunking import create_text_chunks
+from base_rag_example import BaseRAGExample, create_text_chunks

 from .history_data.history import ChromeHistoryReader

--- a/apps/chatgpt_data/chatgpt_reader.py
+++ b/apps/chatgpt_data/chatgpt_reader.py
@@ -1,413 +0,0 @@
-"""
-ChatGPT export data reader.
-
-Reads and processes ChatGPT export data from chat.html files.
-"""
-
-import re
-from pathlib import Path
-from typing import Any
-from zipfile import ZipFile
-
-from bs4 import BeautifulSoup
-from llama_index.core import Document
-from llama_index.core.readers.base import BaseReader
-
-
-class ChatGPTReader(BaseReader):
-    """
-    ChatGPT export data reader.
-
-    Reads ChatGPT conversation data from exported chat.html files or zip archives.
-    Processes conversations into structured documents with metadata.
-    """
-
-    def __init__(self, concatenate_conversations: bool = True) -> None:
-        """
-        Initialize.
-
-        Args:
-            concatenate_conversations: Whether to concatenate messages within conversations for better context
-        """
-        try:
-            from bs4 import BeautifulSoup  # noqa
-        except ImportError:
-            raise ImportError("`beautifulsoup4` package not found: `pip install beautifulsoup4`")
-
-        self.concatenate_conversations = concatenate_conversations
-
-    def _extract_html_from_zip(self, zip_path: Path) -> str | None:
-        """
-        Extract chat.html from ChatGPT export zip file.
-
-        Args:
-            zip_path: Path to the ChatGPT export zip file
-
-        Returns:
-            HTML content as string, or None if not found
-        """
-        try:
-            with ZipFile(zip_path, "r") as zip_file:
-                # Look for chat.html or conversations.html
-                html_files = [
-                    f
-                    for f in zip_file.namelist()
-                    if f.endswith(".html") and ("chat" in f.lower() or "conversation" in f.lower())
-                ]
-
-                if not html_files:
-                    print(f"No HTML chat file found in {zip_path}")
-                    return None
-
-                # Use the first HTML file found
-                html_file = html_files[0]
-                print(f"Found HTML file: {html_file}")
-
-                with zip_file.open(html_file) as f:
-                    return f.read().decode("utf-8", errors="ignore")
-
-        except Exception as e:
-            print(f"Error extracting HTML from zip {zip_path}: {e}")
-            return None
-
-    def _parse_chatgpt_html(self, html_content: str) -> list[dict]:
-        """
-        Parse ChatGPT HTML export to extract conversations.
-
-        Args:
-            html_content: HTML content from ChatGPT export
-
-        Returns:
-            List of conversation dictionaries
-        """
-        soup = BeautifulSoup(html_content, "html.parser")
-        conversations = []
-
-        # Try different possible structures for ChatGPT exports
-        # Structure 1: Look for conversation containers
-        conversation_containers = soup.find_all(
-            ["div", "section"], class_=re.compile(r"conversation|chat", re.I)
-        )
-
-        if not conversation_containers:
-            # Structure 2: Look for message containers directly
-            conversation_containers = [soup]  # Use the entire document as one conversation
-
-        for container in conversation_containers:
-            conversation = self._extract_conversation_from_container(container)
-            if conversation and conversation.get("messages"):
-                conversations.append(conversation)
-
-        # If no structured conversations found, try to extract all text as one conversation
-        if not conversations:
-            all_text = soup.get_text(separator="\n", strip=True)
-            if all_text:
-                conversations.append(
-                    {
-                        "title": "ChatGPT Conversation",
-                        "messages": [{"role": "mixed", "content": all_text, "timestamp": None}],
-                        "timestamp": None,
-                    }
-                )
-
-        return conversations
-
-    def _extract_conversation_from_container(self, container) -> dict | None:
-        """
-        Extract conversation data from a container element.
-
-        Args:
-            container: BeautifulSoup element containing conversation
-
-        Returns:
-            Dictionary with conversation data or None
-        """
-        messages = []
-
-        # Look for message elements with various possible structures
-        message_selectors = ['[class*="message"]', '[class*="chat"]', "[data-message]", "p", "div"]
-
-        for selector in message_selectors:
-            message_elements = container.select(selector)
-            if message_elements:
-                break
-        else:
-            message_elements = []
-
-        # If no structured messages found, treat the entire container as one message
-        if not message_elements:
-            text_content = container.get_text(separator="\n", strip=True)
-            if text_content:
-                messages.append({"role": "mixed", "content": text_content, "timestamp": None})
-        else:
-            for element in message_elements:
-                message = self._extract_message_from_element(element)
-                if message:
-                    messages.append(message)
-
-        if not messages:
-            return None
-
-        # Try to extract conversation title
-        title_element = container.find(["h1", "h2", "h3", "title"])
-        title = title_element.get_text(strip=True) if title_element else "ChatGPT Conversation"
-
-        # Try to extract timestamp from various possible locations
-        timestamp = self._extract_timestamp_from_container(container)
-
-        return {"title": title, "messages": messages, "timestamp": timestamp}
-
-    def _extract_message_from_element(self, element) -> dict | None:
-        """
-        Extract message data from an element.
-
-        Args:
-            element: BeautifulSoup element containing message
-
-        Returns:
-            Dictionary with message data or None
-        """
-        text_content = element.get_text(separator=" ", strip=True)
-
-        # Skip empty or very short messages
-        if not text_content or len(text_content.strip()) < 3:
-            return None
-
-        # Try to determine role (user/assistant) from class names or content
-        role = "mixed"  # Default role
-
-        class_names = " ".join(element.get("class", [])).lower()
-        if "user" in class_names or "human" in class_names:
-            role = "user"
-        elif "assistant" in class_names or "ai" in class_names or "gpt" in class_names:
-            role = "assistant"
-        elif text_content.lower().startswith(("you:", "user:", "me:")):
-            role = "user"
-            text_content = re.sub(r"^(you|user|me):\s*", "", text_content, flags=re.IGNORECASE)
-        elif text_content.lower().startswith(("chatgpt:", "assistant:", "ai:")):
-            role = "assistant"
-            text_content = re.sub(
-                r"^(chatgpt|assistant|ai):\s*", "", text_content, flags=re.IGNORECASE
-            )
-
-        # Try to extract timestamp
-        timestamp = self._extract_timestamp_from_element(element)
-
-        return {"role": role, "content": text_content, "timestamp": timestamp}
-
-    def _extract_timestamp_from_element(self, element) -> str | None:
-        """Extract timestamp from element."""
-        # Look for timestamp in various attributes and child elements
-        timestamp_attrs = ["data-timestamp", "timestamp", "datetime"]
-        for attr in timestamp_attrs:
-            if element.get(attr):
-                return element.get(attr)
-
-        # Look for time elements
-        time_element = element.find("time")
-        if time_element:
-            return time_element.get("datetime") or time_element.get_text(strip=True)
-
-        # Look for date-like text patterns
-        text = element.get_text()
-        date_patterns = [r"\d{4}-\d{2}-\d{2}", r"\d{1,2}/\d{1,2}/\d{4}", r"\w+ \d{1,2}, \d{4}"]
-
-        for pattern in date_patterns:
-            match = re.search(pattern, text)
-            if match:
-                return match.group()
-
-        return None
-
-    def _extract_timestamp_from_container(self, container) -> str | None:
-        """Extract timestamp from conversation container."""
-        return self._extract_timestamp_from_element(container)
-
-    def _create_concatenated_content(self, conversation: dict) -> str:
-        """
-        Create concatenated content from conversation messages.
-
-        Args:
-            conversation: Dictionary containing conversation data
-
-        Returns:
-            Formatted concatenated content
-        """
-        title = conversation.get("title", "ChatGPT Conversation")
-        messages = conversation.get("messages", [])
-        timestamp = conversation.get("timestamp", "Unknown")
-
-        # Build message content
-        message_parts = []
-        for message in messages:
-            role = message.get("role", "mixed")
-            content = message.get("content", "")
-            msg_timestamp = message.get("timestamp", "")
-
-            if role == "user":
-                prefix = "[You]"
-            elif role == "assistant":
-                prefix = "[ChatGPT]"
-            else:
-                prefix = "[Message]"
-
-            # Add timestamp if available
-            if msg_timestamp:
-                prefix += f" ({msg_timestamp})"
-
-            message_parts.append(f"{prefix}: {content}")
-
-        concatenated_text = "\n\n".join(message_parts)
-
-        # Create final document content
-        doc_content = f"""Conversation: {title}
-Date: {timestamp}
-Messages ({len(messages)} messages):
-
-{concatenated_text}
-"""
-        return doc_content
-
-    def load_data(self, input_dir: str | None = None, **load_kwargs: Any) -> list[Document]:
-        """
-        Load ChatGPT export data.
-
-        Args:
-            input_dir: Directory containing ChatGPT export files or path to specific file
-            **load_kwargs:
-                max_count (int): Maximum number of conversations to process
-                chatgpt_export_path (str): Specific path to ChatGPT export file/directory
-                include_metadata (bool): Whether to include metadata in documents
-        """
-        docs: list[Document] = []
-        max_count = load_kwargs.get("max_count", -1)
-        chatgpt_export_path = load_kwargs.get("chatgpt_export_path", input_dir)
-        include_metadata = load_kwargs.get("include_metadata", True)
-
-        if not chatgpt_export_path:
-            print("No ChatGPT export path provided")
-            return docs
-
-        export_path = Path(chatgpt_export_path)
-
-        if not export_path.exists():
-            print(f"ChatGPT export path not found: {export_path}")
-            return docs
-
-        html_content = None
-
-        # Handle different input types
-        if export_path.is_file():
-            if export_path.suffix.lower() == ".zip":
-                # Extract HTML from zip file
-                html_content = self._extract_html_from_zip(export_path)
-            elif export_path.suffix.lower() == ".html":
-                # Read HTML file directly
-                try:
-                    with open(export_path, encoding="utf-8", errors="ignore") as f:
-                        html_content = f.read()
-                except Exception as e:
-                    print(f"Error reading HTML file {export_path}: {e}")
-                    return docs
-            else:
-                print(f"Unsupported file type: {export_path.suffix}")
-                return docs
-
-        elif export_path.is_dir():
-            # Look for HTML files in directory
-            html_files = list(export_path.glob("*.html"))
-            zip_files = list(export_path.glob("*.zip"))
-
-            if html_files:
-                # Use first HTML file found
-                html_file = html_files[0]
-                print(f"Found HTML file: {html_file}")
-                try:
-                    with open(html_file, encoding="utf-8", errors="ignore") as f:
-                        html_content = f.read()
-                except Exception as e:
-                    print(f"Error reading HTML file {html_file}: {e}")
-                    return docs
-
-            elif zip_files:
-                # Use first zip file found
-                zip_file = zip_files[0]
-                print(f"Found zip file: {zip_file}")
-                html_content = self._extract_html_from_zip(zip_file)
-
-            else:
-                print(f"No HTML or zip files found in {export_path}")
-                return docs
-
-        if not html_content:
-            print("No HTML content found to process")
-            return docs
-
-        # Parse conversations from HTML
-        print("Parsing ChatGPT conversations from HTML...")
-        conversations = self._parse_chatgpt_html(html_content)
-
-        if not conversations:
-            print("No conversations found in HTML content")
-            return docs
-
-        print(f"Found {len(conversations)} conversations")
-
-        # Process conversations into documents
-        count = 0
-        for conversation in conversations:
-            if max_count > 0 and count >= max_count:
-                break
-
-            if self.concatenate_conversations:
-                # Create one document per conversation with concatenated messages
-                doc_content = self._create_concatenated_content(conversation)
-
-                metadata = {}
-                if include_metadata:
-                    metadata = {
-                        "title": conversation.get("title", "ChatGPT Conversation"),
-                        "timestamp": conversation.get("timestamp", "Unknown"),
-                        "message_count": len(conversation.get("messages", [])),
-                        "source": "ChatGPT Export",
-                    }
-
-                doc = Document(text=doc_content, metadata=metadata)
-                docs.append(doc)
-                count += 1
-
-            else:
-                # Create separate documents for each message
-                for message in conversation.get("messages", []):
-                    if max_count > 0 and count >= max_count:
-                        break
-
-                    role = message.get("role", "mixed")
-                    content = message.get("content", "")
-                    msg_timestamp = message.get("timestamp", "")
-
-                    if not content.strip():
-                        continue
-
-                    # Create document content with context
-                    doc_content = f"""Conversation: {conversation.get("title", "ChatGPT Conversation")}
-Role: {role}
-Timestamp: {msg_timestamp or conversation.get("timestamp", "Unknown")}
-Message: {content}
-"""
-
-                    metadata = {}
-                    if include_metadata:
-                        metadata = {
-                            "conversation_title": conversation.get("title", "ChatGPT Conversation"),
-                            "role": role,
-                            "timestamp": msg_timestamp or conversation.get("timestamp", "Unknown"),
-                            "source": "ChatGPT Export",
-                        }
-
-                    doc = Document(text=doc_content, metadata=metadata)
-                    docs.append(doc)
-                    count += 1
-
-        print(f"Created {len(docs)} documents from ChatGPT export")
-        return docs
--- a/apps/chatgpt_rag.py
+++ b/apps/chatgpt_rag.py
@@ -1,186 +0,0 @@
-"""
-ChatGPT RAG example using the unified interface.
-Supports ChatGPT export data from chat.html files.
-"""
-
-import sys
-from pathlib import Path
-
-# Add parent directory to path for imports
-sys.path.insert(0, str(Path(__file__).parent))
-
-from base_rag_example import BaseRAGExample
-from chunking import create_text_chunks
-
-from .chatgpt_data.chatgpt_reader import ChatGPTReader
-
-
-class ChatGPTRAG(BaseRAGExample):
-    """RAG example for ChatGPT conversation data."""
-
-    def __init__(self):
-        # Set default values BEFORE calling super().__init__
-        self.max_items_default = -1  # Process all conversations by default
-        self.embedding_model_default = (
-            "sentence-transformers/all-MiniLM-L6-v2"  # Fast 384-dim model
-        )
-
-        super().__init__(
-            name="ChatGPT",
-            description="Process and query ChatGPT conversation exports with LEANN",
-            default_index_name="chatgpt_conversations_index",
-        )
-
-    def _add_specific_arguments(self, parser):
-        """Add ChatGPT-specific arguments."""
-        chatgpt_group = parser.add_argument_group("ChatGPT Parameters")
-        chatgpt_group.add_argument(
-            "--export-path",
-            type=str,
-            default="./chatgpt_export",
-            help="Path to ChatGPT export file (.zip or .html) or directory containing exports (default: ./chatgpt_export)",
-        )
-        chatgpt_group.add_argument(
-            "--concatenate-conversations",
-            action="store_true",
-            default=True,
-            help="Concatenate messages within conversations for better context (default: True)",
-        )
-        chatgpt_group.add_argument(
-            "--separate-messages",
-            action="store_true",
-            help="Process each message as a separate document (overrides --concatenate-conversations)",
-        )
-        chatgpt_group.add_argument(
-            "--chunk-size", type=int, default=512, help="Text chunk size (default: 512)"
-        )
-        chatgpt_group.add_argument(
-            "--chunk-overlap", type=int, default=128, help="Text chunk overlap (default: 128)"
-        )
-
-    def _find_chatgpt_exports(self, export_path: Path) -> list[Path]:
-        """
-        Find ChatGPT export files in the given path.
-
-        Args:
-            export_path: Path to search for exports
-
-        Returns:
-            List of paths to ChatGPT export files
-        """
-        export_files = []
-
-        if export_path.is_file():
-            if export_path.suffix.lower() in [".zip", ".html"]:
-                export_files.append(export_path)
-        elif export_path.is_dir():
-            # Look for zip and html files
-            export_files.extend(export_path.glob("*.zip"))
-            export_files.extend(export_path.glob("*.html"))
-
-        return export_files
-
-    async def load_data(self, args) -> list[str]:
-        """Load ChatGPT export data and convert to text chunks."""
-        export_path = Path(args.export_path)
-
-        if not export_path.exists():
-            print(f"ChatGPT export path not found: {export_path}")
-            print(
-                "Please ensure you have exported your ChatGPT data and placed it in the correct location."
-            )
-            print("\nTo export your ChatGPT data:")
-            print("1. Sign in to ChatGPT")
-            print("2. Click on your profile icon → Settings → Data Controls")
-            print("3. Click 'Export' under Export Data")
-            print("4. Download the zip file from the email link")
-            print("5. Extract or place the file/directory at the specified path")
-            return []
-
-        # Find export files
-        export_files = self._find_chatgpt_exports(export_path)
-
-        if not export_files:
-            print(f"No ChatGPT export files (.zip or .html) found in: {export_path}")
-            return []
-
-        print(f"Found {len(export_files)} ChatGPT export files")
-
-        # Create reader with appropriate settings
-        concatenate = args.concatenate_conversations and not args.separate_messages
-        reader = ChatGPTReader(concatenate_conversations=concatenate)
-
-        # Process each export file
-        all_documents = []
-        total_processed = 0
-
-        for i, export_file in enumerate(export_files):
-            print(f"\nProcessing export file {i + 1}/{len(export_files)}: {export_file.name}")
-
-            try:
-                # Apply max_items limit per file
-                max_per_file = -1
-                if args.max_items > 0:
-                    remaining = args.max_items - total_processed
-                    if remaining <= 0:
-                        break
-                    max_per_file = remaining
-
-                # Load conversations
-                documents = reader.load_data(
-                    chatgpt_export_path=str(export_file),
-                    max_count=max_per_file,
-                    include_metadata=True,
-                )
-
-                if documents:
-                    all_documents.extend(documents)
-                    total_processed += len(documents)
-                    print(f"Processed {len(documents)} conversations from this file")
-                else:
-                    print(f"No conversations loaded from {export_file}")
-
-            except Exception as e:
-                print(f"Error processing {export_file}: {e}")
-                continue
-
-        if not all_documents:
-            print("No conversations found to process!")
-            print("\nTroubleshooting:")
-            print("- Ensure the export file is a valid ChatGPT export")
-            print("- Check that the HTML file contains conversation data")
-            print("- Try extracting the zip file and pointing to the HTML file directly")
-            return []
-
-        print(f"\nTotal conversations processed: {len(all_documents)}")
-        print("Now starting to split into text chunks... this may take some time")
-
-        # Convert to text chunks
-        all_texts = create_text_chunks(
-            all_documents, chunk_size=args.chunk_size, chunk_overlap=args.chunk_overlap
-        )
-
-        print(f"Created {len(all_texts)} text chunks from {len(all_documents)} conversations")
-        return all_texts
-
-
-if __name__ == "__main__":
-    import asyncio
-
-    # Example queries for ChatGPT RAG
-    print("\n🤖 ChatGPT RAG Example")
-    print("=" * 50)
-    print("\nExample queries you can try:")
-    print("- 'What did I ask about Python programming?'")
-    print("- 'Show me conversations about machine learning'")
-    print("- 'Find discussions about travel planning'")
-    print("- 'What advice did ChatGPT give me about career development?'")
-    print("- 'Search for conversations about cooking recipes'")
-    print("\nTo get started:")
-    print("1. Export your ChatGPT data from Settings → Data Controls → Export")
-    print("2. Place the downloaded zip file or extracted HTML in ./chatgpt_export/")
-    print("3. Run this script to build your personal ChatGPT knowledge base!")
-    print("\nOr run without --query for interactive mode\n")
-
-    rag = ChatGPTRAG()
-    asyncio.run(rag.run())
--- a/apps/chunking/init.py
+++ b/apps/chunking/init.py
@@ -1,38 +1,16 @@
-"""Unified chunking utilities facade.
-
-This module re-exports the packaged utilities from `leann.chunking_utils` so
-that both repo apps (importing `chunking`) and installed wheels share one
-single implementation. When running from the repo without installation, it
-adds the `packages/leann-core/src` directory to `sys.path` as a fallback.
+"""
+Chunking utilities for LEANN RAG applications.
+Provides AST-aware and traditional text chunking functionality.
 """

-import sys
-from pathlib import Path
-
-try:
-    from leann.chunking_utils import (
-        CODE_EXTENSIONS,
-        create_ast_chunks,
-        create_text_chunks,
-        create_traditional_chunks,
-        detect_code_files,
-        get_language_from_extension,
-    )
-except Exception:  # pragma: no cover - best-effort fallback for dev environment
-    repo_root = Path(__file__).resolve().parents[2]
-    leann_src = repo_root / "packages" / "leann-core" / "src"
-    if leann_src.exists():
-        sys.path.insert(0, str(leann_src))
-        from leann.chunking_utils import (
-            CODE_EXTENSIONS,
-            create_ast_chunks,
-            create_text_chunks,
-            create_traditional_chunks,
-            detect_code_files,
-            get_language_from_extension,
-        )
-    else:
-        raise
+from .utils import (
+    CODE_EXTENSIONS,
+    create_ast_chunks,
+    create_text_chunks,
+    create_traditional_chunks,
+    detect_code_files,
+    get_language_from_extension,
+)

 __all__ = [
    "CODE_EXTENSIONS",
--- a/packages/leann-core/src/leann/chunking_utils.py
+++ b/packages/leann-core/src/leann/chunking_utils.py
@@ -1,6 +1,6 @@
 """
 Enhanced chunking utilities with AST-aware code chunking support.
-Packaged within leann-core so installed wheels can import it reliably.
+Provides unified interface for both traditional and AST-based text chunking.
 """

 import logging
@@ -22,9 +22,30 @@ CODE_EXTENSIONS = {
    ".jsx": "typescript",
 }

+# Default chunk parameters for different content types
+DEFAULT_CHUNK_PARAMS = {
+    "code": {
+        "max_chunk_size": 512,
+        "chunk_overlap": 64,
+    },
+    "text": {
+        "chunk_size": 256,
+        "chunk_overlap": 128,
+    },
+}
+

 def detect_code_files(documents, code_extensions=None) -> tuple[list, list]:
-    """Separate documents into code files and regular text files."""
+    """
+    Separate documents into code files and regular text files.
+
+    Args:
+        documents: List of LlamaIndex Document objects
+        code_extensions: Dict mapping file extensions to languages (defaults to CODE_EXTENSIONS)
+
+    Returns:
+        Tuple of (code_documents, text_documents)
+    """
    if code_extensions is None:
        code_extensions = CODE_EXTENSIONS

@@ -32,10 +53,16 @@ def detect_code_files(documents, code_extensions=None) -> tuple[list, list]:
    text_docs = []

    for doc in documents:
-        file_path = doc.metadata.get("file_path", "") or doc.metadata.get("file_name", "")
+        # Get file path from metadata
+        file_path = doc.metadata.get("file_path", "")
+        if not file_path:
+            # Fallback to file_name
+            file_path = doc.metadata.get("file_name", "")
+
        if file_path:
            file_ext = Path(file_path).suffix.lower()
            if file_ext in code_extensions:
+                # Add language info to metadata
                doc.metadata["language"] = code_extensions[file_ext]
                doc.metadata["is_code"] = True
                code_docs.append(doc)
@@ -43,6 +70,7 @@ def detect_code_files(documents, code_extensions=None) -> tuple[list, list]:
                doc.metadata["is_code"] = False
                text_docs.append(doc)
        else:
+            # If no file path, treat as text
            doc.metadata["is_code"] = False
            text_docs.append(doc)

@@ -51,7 +79,7 @@ def detect_code_files(documents, code_extensions=None) -> tuple[list, list]:


 def get_language_from_extension(file_path: str) -> Optional[str]:
-    """Return language string from a filename/extension using CODE_EXTENSIONS."""
+    """Get the programming language from file extension."""
    ext = Path(file_path).suffix.lower()
    return CODE_EXTENSIONS.get(ext)

@@ -62,26 +90,40 @@ def create_ast_chunks(
    chunk_overlap: int = 64,
    metadata_template: str = "default",
 ) -> list[str]:
-    """Create AST-aware chunks from code documents using astchunk.
+    """
+    Create AST-aware chunks from code documents using astchunk.

-    Falls back to traditional chunking if astchunk is unavailable.
+    Args:
+        documents: List of code documents
+        max_chunk_size: Maximum characters per chunk
+        chunk_overlap: Number of AST nodes to overlap between chunks
+        metadata_template: Template for chunk metadata
+
+    Returns:
+        List of text chunks with preserved code structure
    """
    try:
-        from astchunk import ASTChunkBuilder  # optional dependency
+        from astchunk import ASTChunkBuilder
    except ImportError as e:
        logger.error(f"astchunk not available: {e}")
        logger.info("Falling back to traditional chunking for code files")
        return create_traditional_chunks(documents, max_chunk_size, chunk_overlap)

    all_chunks = []
+
    for doc in documents:
+        # Get language from metadata (set by detect_code_files)
        language = doc.metadata.get("language")
        if not language:
-            logger.warning("No language detected; falling back to traditional chunking")
-            all_chunks.extend(create_traditional_chunks([doc], max_chunk_size, chunk_overlap))
+            logger.warning(
+                "No language detected for document, falling back to traditional chunking"
+            )
+            traditional_chunks = create_traditional_chunks([doc], max_chunk_size, chunk_overlap)
+            all_chunks.extend(traditional_chunks)
            continue

        try:
+            # Configure astchunk
            configs = {
                "max_chunk_size": max_chunk_size,
                "language": language,
@@ -89,6 +131,7 @@ def create_ast_chunks(
                "chunk_overlap": chunk_overlap if chunk_overlap > 0 else 0,
            }

+            # Add repository-level metadata if available
            repo_metadata = {
                "file_path": doc.metadata.get("file_path", ""),
                "file_name": doc.metadata.get("file_name", ""),
@@ -97,13 +140,17 @@ def create_ast_chunks(
            }
            configs["repo_level_metadata"] = repo_metadata

+            # Create chunk builder and process
            chunk_builder = ASTChunkBuilder(**configs)
            code_content = doc.get_content()
+
            if not code_content or not code_content.strip():
                logger.warning("Empty code content, skipping")
                continue

            chunks = chunk_builder.chunkify(code_content)
+
+            # Extract text content from chunks
            for chunk in chunks:
                if hasattr(chunk, "text"):
                    chunk_text = chunk.text
@@ -112,6 +159,7 @@ def create_ast_chunks(
                elif isinstance(chunk, str):
                    chunk_text = chunk
                else:
+                    # Try to convert to string
                    chunk_text = str(chunk)

                if chunk_text and chunk_text.strip():
@@ -120,10 +168,12 @@ def create_ast_chunks(
            logger.info(
                f"Created {len(chunks)} AST chunks from {language} file: {doc.metadata.get('file_name', 'unknown')}"
            )
+
        except Exception as e:
            logger.warning(f"AST chunking failed for {language} file: {e}")
            logger.info("Falling back to traditional chunking")
-            all_chunks.extend(create_traditional_chunks([doc], max_chunk_size, chunk_overlap))
+            traditional_chunks = create_traditional_chunks([doc], max_chunk_size, chunk_overlap)
+            all_chunks.extend(traditional_chunks)

    return all_chunks

@@ -131,10 +181,23 @@ def create_ast_chunks(
 def create_traditional_chunks(
    documents, chunk_size: int = 256, chunk_overlap: int = 128
 ) -> list[str]:
-    """Create traditional text chunks using LlamaIndex SentenceSplitter."""
+    """
+    Create traditional text chunks using LlamaIndex SentenceSplitter.
+
+    Args:
+        documents: List of documents to chunk
+        chunk_size: Size of each chunk in characters
+        chunk_overlap: Overlap between chunks
+
+    Returns:
+        List of text chunks
+    """
+    # Handle invalid chunk_size values
    if chunk_size <= 0:
        logger.warning(f"Invalid chunk_size={chunk_size}, using default value of 256")
        chunk_size = 256
+
+    # Ensure chunk_overlap is not negative and not larger than chunk_size
    if chunk_overlap < 0:
        chunk_overlap = 0
    if chunk_overlap >= chunk_size:
@@ -152,9 +215,12 @@ def create_traditional_chunks(
        try:
            nodes = node_parser.get_nodes_from_documents([doc])
            if nodes:
-                all_texts.extend(node.get_content() for node in nodes)
+                chunk_texts = [node.get_content() for node in nodes]
+                all_texts.extend(chunk_texts)
+                logger.debug(f"Created {len(chunk_texts)} traditional chunks from document")
        except Exception as e:
            logger.error(f"Traditional chunking failed for document: {e}")
+            # As last resort, add the raw content
            content = doc.get_content()
            if content and content.strip():
                all_texts.append(content.strip())
@@ -172,13 +238,32 @@ def create_text_chunks(
    code_file_extensions: Optional[list[str]] = None,
    ast_fallback_traditional: bool = True,
 ) -> list[str]:
-    """Create text chunks from documents with optional AST support for code files."""
+    """
+    Create text chunks from documents with optional AST support for code files.
+
+    Args:
+        documents: List of LlamaIndex Document objects
+        chunk_size: Size for traditional text chunks
+        chunk_overlap: Overlap for traditional text chunks
+        use_ast_chunking: Whether to use AST chunking for code files
+        ast_chunk_size: Size for AST chunks
+        ast_chunk_overlap: Overlap for AST chunks
+        code_file_extensions: Custom list of code file extensions
+        ast_fallback_traditional: Fall back to traditional chunking on AST errors
+
+    Returns:
+        List of text chunks
+    """
    if not documents:
        logger.warning("No documents provided for chunking")
        return []

+    # Create a local copy of supported extensions for this function call
    local_code_extensions = CODE_EXTENSIONS.copy()
+
+    # Update supported extensions if provided
    if code_file_extensions:
+        # Map extensions to languages (simplified mapping)
        ext_mapping = {
            ".py": "python",
            ".java": "java",
@@ -188,32 +273,47 @@ def create_text_chunks(
        }
        for ext in code_file_extensions:
            if ext.lower() not in local_code_extensions:
+                # Try to guess language from extension
                if ext.lower() in ext_mapping:
                    local_code_extensions[ext.lower()] = ext_mapping[ext.lower()]
                else:
                    logger.warning(f"Unsupported extension {ext}, will use traditional chunking")

    all_chunks = []
+
    if use_ast_chunking:
+        # Separate code and text documents using local extensions
        code_docs, text_docs = detect_code_files(documents, local_code_extensions)
+
+        # Process code files with AST chunking
        if code_docs:
+            logger.info(f"Processing {len(code_docs)} code files with AST chunking")
            try:
-                all_chunks.extend(
-                    create_ast_chunks(
-                        code_docs, max_chunk_size=ast_chunk_size, chunk_overlap=ast_chunk_overlap
-                    )
+                ast_chunks = create_ast_chunks(
+                    code_docs, max_chunk_size=ast_chunk_size, chunk_overlap=ast_chunk_overlap
                )
+                all_chunks.extend(ast_chunks)
+                logger.info(f"Created {len(ast_chunks)} AST chunks from code files")
            except Exception as e:
                logger.error(f"AST chunking failed: {e}")
                if ast_fallback_traditional:
-                    all_chunks.extend(
-                        create_traditional_chunks(code_docs, chunk_size, chunk_overlap)
+                    logger.info("Falling back to traditional chunking for code files")
+                    traditional_code_chunks = create_traditional_chunks(
+                        code_docs, chunk_size, chunk_overlap
                    )
+                    all_chunks.extend(traditional_code_chunks)
                else:
                    raise
+
+        # Process text files with traditional chunking
        if text_docs:
-            all_chunks.extend(create_traditional_chunks(text_docs, chunk_size, chunk_overlap))
+            logger.info(f"Processing {len(text_docs)} text files with traditional chunking")
+            text_chunks = create_traditional_chunks(text_docs, chunk_size, chunk_overlap)
+            all_chunks.extend(text_chunks)
+            logger.info(f"Created {len(text_chunks)} traditional chunks from text files")
    else:
+        # Use traditional chunking for all files
+        logger.info(f"Processing {len(documents)} documents with traditional chunking")
        all_chunks = create_traditional_chunks(documents, chunk_size, chunk_overlap)

    logger.info(f"Total chunks created: {len(all_chunks)}")
--- a/apps/claude_data/init.py
+++ b/apps/claude_data/init.py
--- a/apps/claude_data/claude_reader.py
+++ b/apps/claude_data/claude_reader.py
@@ -1,420 +0,0 @@
-"""
-Claude export data reader.
-
-Reads and processes Claude conversation data from exported JSON files.
-"""
-
-import json
-from pathlib import Path
-from typing import Any
-from zipfile import ZipFile
-
-from llama_index.core import Document
-from llama_index.core.readers.base import BaseReader
-
-
-class ClaudeReader(BaseReader):
-    """
-    Claude export data reader.
-
-    Reads Claude conversation data from exported JSON files or zip archives.
-    Processes conversations into structured documents with metadata.
-    """
-
-    def __init__(self, concatenate_conversations: bool = True) -> None:
-        """
-        Initialize.
-
-        Args:
-            concatenate_conversations: Whether to concatenate messages within conversations for better context
-        """
-        self.concatenate_conversations = concatenate_conversations
-
-    def _extract_json_from_zip(self, zip_path: Path) -> list[str]:
-        """
-        Extract JSON files from Claude export zip file.
-
-        Args:
-            zip_path: Path to the Claude export zip file
-
-        Returns:
-            List of JSON content strings, or empty list if not found
-        """
-        json_contents = []
-        try:
-            with ZipFile(zip_path, "r") as zip_file:
-                # Look for JSON files
-                json_files = [f for f in zip_file.namelist() if f.endswith(".json")]
-
-                if not json_files:
-                    print(f"No JSON files found in {zip_path}")
-                    return []
-
-                print(f"Found {len(json_files)} JSON files in archive")
-
-                for json_file in json_files:
-                    with zip_file.open(json_file) as f:
-                        content = f.read().decode("utf-8", errors="ignore")
-                        json_contents.append(content)
-
-        except Exception as e:
-            print(f"Error extracting JSON from zip {zip_path}: {e}")
-
-        return json_contents
-
-    def _parse_claude_json(self, json_content: str) -> list[dict]:
-        """
-        Parse Claude JSON export to extract conversations.
-
-        Args:
-            json_content: JSON content from Claude export
-
-        Returns:
-            List of conversation dictionaries
-        """
-        try:
-            data = json.loads(json_content)
-        except json.JSONDecodeError as e:
-            print(f"Error parsing JSON: {e}")
-            return []
-
-        conversations = []
-
-        # Handle different possible JSON structures
-        if isinstance(data, list):
-            # If data is a list of conversations
-            for item in data:
-                conversation = self._extract_conversation_from_json(item)
-                if conversation:
-                    conversations.append(conversation)
-        elif isinstance(data, dict):
-            # Check for common structures
-            if "conversations" in data:
-                # Structure: {"conversations": [...]}
-                for item in data["conversations"]:
-                    conversation = self._extract_conversation_from_json(item)
-                    if conversation:
-                        conversations.append(conversation)
-            elif "messages" in data:
-                # Single conversation with messages
-                conversation = self._extract_conversation_from_json(data)
-                if conversation:
-                    conversations.append(conversation)
-            else:
-                # Try to treat the whole object as a conversation
-                conversation = self._extract_conversation_from_json(data)
-                if conversation:
-                    conversations.append(conversation)
-
-        return conversations
-
-    def _extract_conversation_from_json(self, conv_data: dict) -> dict | None:
-        """
-        Extract conversation data from a JSON object.
-
-        Args:
-            conv_data: Dictionary containing conversation data
-
-        Returns:
-            Dictionary with conversation data or None
-        """
-        if not isinstance(conv_data, dict):
-            return None
-
-        messages = []
-
-        # Look for messages in various possible structures
-        message_sources = []
-        if "messages" in conv_data:
-            message_sources = conv_data["messages"]
-        elif "chat" in conv_data:
-            message_sources = conv_data["chat"]
-        elif "conversation" in conv_data:
-            message_sources = conv_data["conversation"]
-        else:
-            # If no clear message structure, try to extract from the object itself
-            if "content" in conv_data and "role" in conv_data:
-                message_sources = [conv_data]
-
-        for msg_data in message_sources:
-            message = self._extract_message_from_json(msg_data)
-            if message:
-                messages.append(message)
-
-        if not messages:
-            return None
-
-        # Extract conversation metadata
-        title = self._extract_title_from_conversation(conv_data, messages)
-        timestamp = self._extract_timestamp_from_conversation(conv_data)
-
-        return {"title": title, "messages": messages, "timestamp": timestamp}
-
-    def _extract_message_from_json(self, msg_data: dict) -> dict | None:
-        """
-        Extract message data from a JSON message object.
-
-        Args:
-            msg_data: Dictionary containing message data
-
-        Returns:
-            Dictionary with message data or None
-        """
-        if not isinstance(msg_data, dict):
-            return None
-
-        # Extract content from various possible fields
-        content = ""
-        content_fields = ["content", "text", "message", "body"]
-        for field in content_fields:
-            if msg_data.get(field):
-                content = str(msg_data[field])
-                break
-
-        if not content or len(content.strip()) < 3:
-            return None
-
-        # Extract role (user/assistant/human/ai/claude)
-        role = "mixed"  # Default role
-        role_fields = ["role", "sender", "from", "author", "type"]
-        for field in role_fields:
-            if msg_data.get(field):
-                role_value = str(msg_data[field]).lower()
-                if role_value in ["user", "human", "person"]:
-                    role = "user"
-                elif role_value in ["assistant", "ai", "claude", "bot"]:
-                    role = "assistant"
-                break
-
-        # Extract timestamp
-        timestamp = self._extract_timestamp_from_message(msg_data)
-
-        return {"role": role, "content": content, "timestamp": timestamp}
-
-    def _extract_timestamp_from_message(self, msg_data: dict) -> str | None:
-        """Extract timestamp from message data."""
-        timestamp_fields = ["timestamp", "created_at", "date", "time"]
-        for field in timestamp_fields:
-            if msg_data.get(field):
-                return str(msg_data[field])
-        return None
-
-    def _extract_timestamp_from_conversation(self, conv_data: dict) -> str | None:
-        """Extract timestamp from conversation data."""
-        timestamp_fields = ["timestamp", "created_at", "date", "updated_at", "last_updated"]
-        for field in timestamp_fields:
-            if conv_data.get(field):
-                return str(conv_data[field])
-        return None
-
-    def _extract_title_from_conversation(self, conv_data: dict, messages: list) -> str:
-        """Extract or generate title for conversation."""
-        # Try to find explicit title
-        title_fields = ["title", "name", "subject", "topic"]
-        for field in title_fields:
-            if conv_data.get(field):
-                return str(conv_data[field])
-
-        # Generate title from first user message
-        for message in messages:
-            if message.get("role") == "user":
-                content = message.get("content", "")
-                if content:
-                    # Use first 50 characters as title
-                    title = content[:50].strip()
-                    if len(content) > 50:
-                        title += "..."
-                    return title
-
-        return "Claude Conversation"
-
-    def _create_concatenated_content(self, conversation: dict) -> str:
-        """
-        Create concatenated content from conversation messages.
-
-        Args:
-            conversation: Dictionary containing conversation data
-
-        Returns:
-            Formatted concatenated content
-        """
-        title = conversation.get("title", "Claude Conversation")
-        messages = conversation.get("messages", [])
-        timestamp = conversation.get("timestamp", "Unknown")
-
-        # Build message content
-        message_parts = []
-        for message in messages:
-            role = message.get("role", "mixed")
-            content = message.get("content", "")
-            msg_timestamp = message.get("timestamp", "")
-
-            if role == "user":
-                prefix = "[You]"
-            elif role == "assistant":
-                prefix = "[Claude]"
-            else:
-                prefix = "[Message]"
-
-            # Add timestamp if available
-            if msg_timestamp:
-                prefix += f" ({msg_timestamp})"
-
-            message_parts.append(f"{prefix}: {content}")
-
-        concatenated_text = "\n\n".join(message_parts)
-
-        # Create final document content
-        doc_content = f"""Conversation: {title}
-Date: {timestamp}
-Messages ({len(messages)} messages):
-
-{concatenated_text}
-"""
-        return doc_content
-
-    def load_data(self, input_dir: str | None = None, **load_kwargs: Any) -> list[Document]:
-        """
-        Load Claude export data.
-
-        Args:
-            input_dir: Directory containing Claude export files or path to specific file
-            **load_kwargs:
-                max_count (int): Maximum number of conversations to process
-                claude_export_path (str): Specific path to Claude export file/directory
-                include_metadata (bool): Whether to include metadata in documents
-        """
-        docs: list[Document] = []
-        max_count = load_kwargs.get("max_count", -1)
-        claude_export_path = load_kwargs.get("claude_export_path", input_dir)
-        include_metadata = load_kwargs.get("include_metadata", True)
-
-        if not claude_export_path:
-            print("No Claude export path provided")
-            return docs
-
-        export_path = Path(claude_export_path)
-
-        if not export_path.exists():
-            print(f"Claude export path not found: {export_path}")
-            return docs
-
-        json_contents = []
-
-        # Handle different input types
-        if export_path.is_file():
-            if export_path.suffix.lower() == ".zip":
-                # Extract JSON from zip file
-                json_contents = self._extract_json_from_zip(export_path)
-            elif export_path.suffix.lower() == ".json":
-                # Read JSON file directly
-                try:
-                    with open(export_path, encoding="utf-8", errors="ignore") as f:
-                        json_contents.append(f.read())
-                except Exception as e:
-                    print(f"Error reading JSON file {export_path}: {e}")
-                    return docs
-            else:
-                print(f"Unsupported file type: {export_path.suffix}")
-                return docs
-
-        elif export_path.is_dir():
-            # Look for JSON files in directory
-            json_files = list(export_path.glob("*.json"))
-            zip_files = list(export_path.glob("*.zip"))
-
-            if json_files:
-                print(f"Found {len(json_files)} JSON files in directory")
-                for json_file in json_files:
-                    try:
-                        with open(json_file, encoding="utf-8", errors="ignore") as f:
-                            json_contents.append(f.read())
-                    except Exception as e:
-                        print(f"Error reading JSON file {json_file}: {e}")
-                        continue
-
-            if zip_files:
-                print(f"Found {len(zip_files)} ZIP files in directory")
-                for zip_file in zip_files:
-                    zip_contents = self._extract_json_from_zip(zip_file)
-                    json_contents.extend(zip_contents)
-
-            if not json_files and not zip_files:
-                print(f"No JSON or ZIP files found in {export_path}")
-                return docs
-
-        if not json_contents:
-            print("No JSON content found to process")
-            return docs
-
-        # Parse conversations from JSON content
-        print("Parsing Claude conversations from JSON...")
-        all_conversations = []
-        for json_content in json_contents:
-            conversations = self._parse_claude_json(json_content)
-            all_conversations.extend(conversations)
-
-        if not all_conversations:
-            print("No conversations found in JSON content")
-            return docs
-
-        print(f"Found {len(all_conversations)} conversations")
-
-        # Process conversations into documents
-        count = 0
-        for conversation in all_conversations:
-            if max_count > 0 and count >= max_count:
-                break
-
-            if self.concatenate_conversations:
-                # Create one document per conversation with concatenated messages
-                doc_content = self._create_concatenated_content(conversation)
-
-                metadata = {}
-                if include_metadata:
-                    metadata = {
-                        "title": conversation.get("title", "Claude Conversation"),
-                        "timestamp": conversation.get("timestamp", "Unknown"),
-                        "message_count": len(conversation.get("messages", [])),
-                        "source": "Claude Export",
-                    }
-
-                doc = Document(text=doc_content, metadata=metadata)
-                docs.append(doc)
-                count += 1
-
-            else:
-                # Create separate documents for each message
-                for message in conversation.get("messages", []):
-                    if max_count > 0 and count >= max_count:
-                        break
-
-                    role = message.get("role", "mixed")
-                    content = message.get("content", "")
-                    msg_timestamp = message.get("timestamp", "")
-
-                    if not content.strip():
-                        continue
-
-                    # Create document content with context
-                    doc_content = f"""Conversation: {conversation.get("title", "Claude Conversation")}
-Role: {role}
-Timestamp: {msg_timestamp or conversation.get("timestamp", "Unknown")}
-Message: {content}
-"""
-
-                    metadata = {}
-                    if include_metadata:
-                        metadata = {
-                            "conversation_title": conversation.get("title", "Claude Conversation"),
-                            "role": role,
-                            "timestamp": msg_timestamp or conversation.get("timestamp", "Unknown"),
-                            "source": "Claude Export",
-                        }
-
-                    doc = Document(text=doc_content, metadata=metadata)
-                    docs.append(doc)
-                    count += 1
-
-        print(f"Created {len(docs)} documents from Claude export")
-        return docs
--- a/apps/claude_rag.py
+++ b/apps/claude_rag.py
@@ -1,189 +0,0 @@
-"""
-Claude RAG example using the unified interface.
-Supports Claude export data from JSON files.
-"""
-
-import sys
-from pathlib import Path
-
-# Add parent directory to path for imports
-sys.path.insert(0, str(Path(__file__).parent))
-
-from base_rag_example import BaseRAGExample
-from chunking import create_text_chunks
-
-from .claude_data.claude_reader import ClaudeReader
-
-
-class ClaudeRAG(BaseRAGExample):
-    """RAG example for Claude conversation data."""
-
-    def __init__(self):
-        # Set default values BEFORE calling super().__init__
-        self.max_items_default = -1  # Process all conversations by default
-        self.embedding_model_default = (
-            "sentence-transformers/all-MiniLM-L6-v2"  # Fast 384-dim model
-        )
-
-        super().__init__(
-            name="Claude",
-            description="Process and query Claude conversation exports with LEANN",
-            default_index_name="claude_conversations_index",
-        )
-
-    def _add_specific_arguments(self, parser):
-        """Add Claude-specific arguments."""
-        claude_group = parser.add_argument_group("Claude Parameters")
-        claude_group.add_argument(
-            "--export-path",
-            type=str,
-            default="./claude_export",
-            help="Path to Claude export file (.json or .zip) or directory containing exports (default: ./claude_export)",
-        )
-        claude_group.add_argument(
-            "--concatenate-conversations",
-            action="store_true",
-            default=True,
-            help="Concatenate messages within conversations for better context (default: True)",
-        )
-        claude_group.add_argument(
-            "--separate-messages",
-            action="store_true",
-            help="Process each message as a separate document (overrides --concatenate-conversations)",
-        )
-        claude_group.add_argument(
-            "--chunk-size", type=int, default=512, help="Text chunk size (default: 512)"
-        )
-        claude_group.add_argument(
-            "--chunk-overlap", type=int, default=128, help="Text chunk overlap (default: 128)"
-        )
-
-    def _find_claude_exports(self, export_path: Path) -> list[Path]:
-        """
-        Find Claude export files in the given path.
-
-        Args:
-            export_path: Path to search for exports
-
-        Returns:
-            List of paths to Claude export files
-        """
-        export_files = []
-
-        if export_path.is_file():
-            if export_path.suffix.lower() in [".zip", ".json"]:
-                export_files.append(export_path)
-        elif export_path.is_dir():
-            # Look for zip and json files
-            export_files.extend(export_path.glob("*.zip"))
-            export_files.extend(export_path.glob("*.json"))
-
-        return export_files
-
-    async def load_data(self, args) -> list[str]:
-        """Load Claude export data and convert to text chunks."""
-        export_path = Path(args.export_path)
-
-        if not export_path.exists():
-            print(f"Claude export path not found: {export_path}")
-            print(
-                "Please ensure you have exported your Claude data and placed it in the correct location."
-            )
-            print("\nTo export your Claude data:")
-            print("1. Open Claude in your browser")
-            print("2. Look for export/download options in settings or conversation menu")
-            print("3. Download the conversation data (usually in JSON format)")
-            print("4. Place the file/directory at the specified path")
-            print(
-                "\nNote: Claude export methods may vary. Check Claude's help documentation for current instructions."
-            )
-            return []
-
-        # Find export files
-        export_files = self._find_claude_exports(export_path)
-
-        if not export_files:
-            print(f"No Claude export files (.json or .zip) found in: {export_path}")
-            return []
-
-        print(f"Found {len(export_files)} Claude export files")
-
-        # Create reader with appropriate settings
-        concatenate = args.concatenate_conversations and not args.separate_messages
-        reader = ClaudeReader(concatenate_conversations=concatenate)
-
-        # Process each export file
-        all_documents = []
-        total_processed = 0
-
-        for i, export_file in enumerate(export_files):
-            print(f"\nProcessing export file {i + 1}/{len(export_files)}: {export_file.name}")
-
-            try:
-                # Apply max_items limit per file
-                max_per_file = -1
-                if args.max_items > 0:
-                    remaining = args.max_items - total_processed
-                    if remaining <= 0:
-                        break
-                    max_per_file = remaining
-
-                # Load conversations
-                documents = reader.load_data(
-                    claude_export_path=str(export_file),
-                    max_count=max_per_file,
-                    include_metadata=True,
-                )
-
-                if documents:
-                    all_documents.extend(documents)
-                    total_processed += len(documents)
-                    print(f"Processed {len(documents)} conversations from this file")
-                else:
-                    print(f"No conversations loaded from {export_file}")
-
-            except Exception as e:
-                print(f"Error processing {export_file}: {e}")
-                continue
-
-        if not all_documents:
-            print("No conversations found to process!")
-            print("\nTroubleshooting:")
-            print("- Ensure the export file is a valid Claude export")
-            print("- Check that the JSON file contains conversation data")
-            print("- Try using a different export format or method")
-            print("- Check Claude's documentation for current export procedures")
-            return []
-
-        print(f"\nTotal conversations processed: {len(all_documents)}")
-        print("Now starting to split into text chunks... this may take some time")
-
-        # Convert to text chunks
-        all_texts = create_text_chunks(
-            all_documents, chunk_size=args.chunk_size, chunk_overlap=args.chunk_overlap
-        )
-
-        print(f"Created {len(all_texts)} text chunks from {len(all_documents)} conversations")
-        return all_texts
-
-
-if __name__ == "__main__":
-    import asyncio
-
-    # Example queries for Claude RAG
-    print("\n🤖 Claude RAG Example")
-    print("=" * 50)
-    print("\nExample queries you can try:")
-    print("- 'What did I ask Claude about Python programming?'")
-    print("- 'Show me conversations about machine learning'")
-    print("- 'Find discussions about code optimization'")
-    print("- 'What advice did Claude give me about software design?'")
-    print("- 'Search for conversations about debugging techniques'")
-    print("\nTo get started:")
-    print("1. Export your Claude conversation data")
-    print("2. Place the JSON/ZIP file in ./claude_export/")
-    print("3. Run this script to build your personal Claude knowledge base!")
-    print("\nOr run without --query for interactive mode\n")
-
-    rag = ClaudeRAG()
-    asyncio.run(rag.run())
--- a/apps/email_rag.py
+++ b/apps/email_rag.py
@@ -9,8 +9,7 @@ from pathlib import Path
 # Add parent directory to path for imports
 sys.path.insert(0, str(Path(__file__).parent))

-from base_rag_example import BaseRAGExample
-from chunking import create_text_chunks
+from base_rag_example import BaseRAGExample, create_text_chunks

 from .email_data.LEANN_email_reader import EmlxReader

--- a/apps/history_data/history.py
+++ b/apps/history_data/history.py
@@ -74,7 +74,7 @@ class ChromeHistoryReader(BaseReader):
                if count >= max_count and max_count > 0:
                    break

-                last_visit, url, title, visit_count, typed_count, _hidden = row
+                last_visit, url, title, visit_count, typed_count, hidden = row

                # Create document content with metadata embedded in text
                doc_content = f"""
--- a/apps/imessage_data/init.py
+++ b/apps/imessage_data/init.py
@@ -1 +0,0 @@
-"""iMessage data processing module."""
--- a/apps/imessage_data/imessage_reader.py
+++ b/apps/imessage_data/imessage_reader.py
@@ -1,342 +0,0 @@
-"""
-iMessage data reader.
-
-Reads and processes iMessage conversation data from the macOS Messages database.
-"""
-
-import sqlite3
-from datetime import datetime
-from pathlib import Path
-from typing import Any
-
-from llama_index.core import Document
-from llama_index.core.readers.base import BaseReader
-
-
-class IMessageReader(BaseReader):
-    """
-    iMessage data reader.
-
-    Reads iMessage conversation data from the macOS Messages database (chat.db).
-    Processes conversations into structured documents with metadata.
-    """
-
-    def __init__(self, concatenate_conversations: bool = True) -> None:
-        """
-        Initialize.
-
-        Args:
-            concatenate_conversations: Whether to concatenate messages within conversations for better context
-        """
-        self.concatenate_conversations = concatenate_conversations
-
-    def _get_default_chat_db_path(self) -> Path:
-        """
-        Get the default path to the iMessage chat database.
-
-        Returns:
-            Path to the chat.db file
-        """
-        home = Path.home()
-        return home / "Library" / "Messages" / "chat.db"
-
-    def _convert_cocoa_timestamp(self, cocoa_timestamp: int) -> str:
-        """
-        Convert Cocoa timestamp to readable format.
-
-        Args:
-            cocoa_timestamp: Timestamp in Cocoa format (nanoseconds since 2001-01-01)
-
-        Returns:
-            Formatted timestamp string
-        """
-        if cocoa_timestamp == 0:
-            return "Unknown"
-
-        try:
-            # Cocoa timestamp is nanoseconds since 2001-01-01 00:00:00 UTC
-            # Convert to seconds and add to Unix epoch
-            cocoa_epoch = datetime(2001, 1, 1)
-            unix_timestamp = cocoa_timestamp / 1_000_000_000  # Convert nanoseconds to seconds
-            message_time = cocoa_epoch.timestamp() + unix_timestamp
-            return datetime.fromtimestamp(message_time).strftime("%Y-%m-%d %H:%M:%S")
-        except (ValueError, OSError):
-            return "Unknown"
-
-    def _get_contact_name(self, handle_id: str) -> str:
-        """
-        Get a readable contact name from handle ID.
-
-        Args:
-            handle_id: The handle ID (phone number or email)
-
-        Returns:
-            Formatted contact name
-        """
-        if not handle_id:
-            return "Unknown"
-
-        # Clean up phone numbers and emails for display
-        if "@" in handle_id:
-            return handle_id  # Email address
-        elif handle_id.startswith("+"):
-            return handle_id  # International phone number
-        else:
-            # Try to format as phone number
-            digits = "".join(filter(str.isdigit, handle_id))
-            if len(digits) == 10:
-                return f"({digits[:3]}) {digits[3:6]}-{digits[6:]}"
-            elif len(digits) == 11 and digits[0] == "1":
-                return f"+1 ({digits[1:4]}) {digits[4:7]}-{digits[7:]}"
-            else:
-                return handle_id
-
-    def _read_messages_from_db(self, db_path: Path) -> list[dict]:
-        """
-        Read messages from the iMessage database.
-
-        Args:
-            db_path: Path to the chat.db file
-
-        Returns:
-            List of message dictionaries
-        """
-        if not db_path.exists():
-            print(f"iMessage database not found at: {db_path}")
-            return []
-
-        try:
-            # Connect to the database
-            conn = sqlite3.connect(str(db_path))
-            cursor = conn.cursor()
-
-            # Query to get messages with chat and handle information
-            query = """
-            SELECT
-                m.ROWID as message_id,
-                m.text,
-                m.date,
-                m.is_from_me,
-                m.service,
-                c.chat_identifier,
-                c.display_name as chat_display_name,
-                h.id as handle_id,
-                c.ROWID as chat_id
-            FROM message m
-            LEFT JOIN chat_message_join cmj ON m.ROWID = cmj.message_id
-            LEFT JOIN chat c ON cmj.chat_id = c.ROWID
-            LEFT JOIN handle h ON m.handle_id = h.ROWID
-            WHERE m.text IS NOT NULL AND m.text != ''
-            ORDER BY c.ROWID, m.date
-            """
-
-            cursor.execute(query)
-            rows = cursor.fetchall()
-
-            messages = []
-            for row in rows:
-                (
-                    message_id,
-                    text,
-                    date,
-                    is_from_me,
-                    service,
-                    chat_identifier,
-                    chat_display_name,
-                    handle_id,
-                    chat_id,
-                ) = row
-
-                message = {
-                    "message_id": message_id,
-                    "text": text,
-                    "timestamp": self._convert_cocoa_timestamp(date),
-                    "is_from_me": bool(is_from_me),
-                    "service": service or "iMessage",
-                    "chat_identifier": chat_identifier or "Unknown",
-                    "chat_display_name": chat_display_name or "Unknown Chat",
-                    "handle_id": handle_id or "Unknown",
-                    "contact_name": self._get_contact_name(handle_id or ""),
-                    "chat_id": chat_id,
-                }
-                messages.append(message)
-
-            conn.close()
-            print(f"Found {len(messages)} messages in database")
-            return messages
-
-        except sqlite3.Error as e:
-            print(f"Error reading iMessage database: {e}")
-            return []
-        except Exception as e:
-            print(f"Unexpected error reading iMessage database: {e}")
-            return []
-
-    def _group_messages_by_chat(self, messages: list[dict]) -> dict[int, list[dict]]:
-        """
-        Group messages by chat ID.
-
-        Args:
-            messages: List of message dictionaries
-
-        Returns:
-            Dictionary mapping chat_id to list of messages
-        """
-        chats = {}
-        for message in messages:
-            chat_id = message["chat_id"]
-            if chat_id not in chats:
-                chats[chat_id] = []
-            chats[chat_id].append(message)
-
-        return chats
-
-    def _create_concatenated_content(self, chat_id: int, messages: list[dict]) -> str:
-        """
-        Create concatenated content from chat messages.
-
-        Args:
-            chat_id: The chat ID
-            messages: List of messages in the chat
-
-        Returns:
-            Concatenated text content
-        """
-        if not messages:
-            return ""
-
-        # Get chat info from first message
-        first_msg = messages[0]
-        chat_name = first_msg["chat_display_name"]
-        chat_identifier = first_msg["chat_identifier"]
-
-        # Build message content
-        message_parts = []
-        for message in messages:
-            timestamp = message["timestamp"]
-            is_from_me = message["is_from_me"]
-            text = message["text"]
-            contact_name = message["contact_name"]
-
-            if is_from_me:
-                prefix = "[You]"
-            else:
-                prefix = f"[{contact_name}]"
-
-            if timestamp != "Unknown":
-                prefix += f" ({timestamp})"
-
-            message_parts.append(f"{prefix}: {text}")
-
-        concatenated_text = "\n\n".join(message_parts)
-
-        doc_content = f"""Chat: {chat_name}
-Identifier: {chat_identifier}
-Messages ({len(messages)} messages):
-
-{concatenated_text}
-"""
-        return doc_content
-
-    def _create_individual_content(self, message: dict) -> str:
-        """
-        Create content for individual message.
-
-        Args:
-            message: Message dictionary
-
-        Returns:
-            Formatted message content
-        """
-        timestamp = message["timestamp"]
-        is_from_me = message["is_from_me"]
-        text = message["text"]
-        contact_name = message["contact_name"]
-        chat_name = message["chat_display_name"]
-
-        sender = "You" if is_from_me else contact_name
-
-        return f"""Message from {sender} in chat "{chat_name}"
-Time: {timestamp}
-Content: {text}
-"""
-
-    def load_data(self, input_dir: str | None = None, **load_kwargs: Any) -> list[Document]:
-        """
-        Load iMessage data and return as documents.
-
-        Args:
-            input_dir: Optional path to directory containing chat.db file.
-                      If not provided, uses default macOS location.
-            **load_kwargs: Additional arguments (unused)
-
-        Returns:
-            List of Document objects containing iMessage data
-        """
-        docs = []
-
-        # Determine database path
-        if input_dir:
-            db_path = Path(input_dir) / "chat.db"
-        else:
-            db_path = self._get_default_chat_db_path()
-
-        print(f"Reading iMessage database from: {db_path}")
-
-        # Read messages from database
-        messages = self._read_messages_from_db(db_path)
-        if not messages:
-            return docs
-
-        if self.concatenate_conversations:
-            # Group messages by chat and create concatenated documents
-            chats = self._group_messages_by_chat(messages)
-
-            for chat_id, chat_messages in chats.items():
-                if not chat_messages:
-                    continue
-
-                content = self._create_concatenated_content(chat_id, chat_messages)
-
-                # Create metadata
-                first_msg = chat_messages[0]
-                last_msg = chat_messages[-1]
-
-                metadata = {
-                    "source": "iMessage",
-                    "chat_id": chat_id,
-                    "chat_name": first_msg["chat_display_name"],
-                    "chat_identifier": first_msg["chat_identifier"],
-                    "message_count": len(chat_messages),
-                    "first_message_date": first_msg["timestamp"],
-                    "last_message_date": last_msg["timestamp"],
-                    "participants": list(
-                        {msg["contact_name"] for msg in chat_messages if not msg["is_from_me"]}
-                    ),
-                }
-
-                doc = Document(text=content, metadata=metadata)
-                docs.append(doc)
-
-        else:
-            # Create individual documents for each message
-            for message in messages:
-                content = self._create_individual_content(message)
-
-                metadata = {
-                    "source": "iMessage",
-                    "message_id": message["message_id"],
-                    "chat_id": message["chat_id"],
-                    "chat_name": message["chat_display_name"],
-                    "chat_identifier": message["chat_identifier"],
-                    "timestamp": message["timestamp"],
-                    "is_from_me": message["is_from_me"],
-                    "contact_name": message["contact_name"],
-                    "service": message["service"],
-                }
-
-                doc = Document(text=content, metadata=metadata)
-                docs.append(doc)
-
-        print(f"Created {len(docs)} documents from iMessage data")
-        return docs
--- a/apps/imessage_rag.py
+++ b/apps/imessage_rag.py
@@ -1,125 +0,0 @@
-"""
-iMessage RAG Example.
-
-This example demonstrates how to build a RAG system on your iMessage conversation history.
-"""
-
-import asyncio
-from pathlib import Path
-
-from leann.chunking_utils import create_text_chunks
-
-from apps.base_rag_example import BaseRAGExample
-from apps.imessage_data.imessage_reader import IMessageReader
-
-
-class IMessageRAG(BaseRAGExample):
-    """RAG example for iMessage conversation history."""
-
-    def __init__(self):
-        super().__init__(
-            name="iMessage",
-            description="RAG on your iMessage conversation history",
-            default_index_name="imessage_index",
-        )
-
-    def _add_specific_arguments(self, parser):
-        """Add iMessage-specific arguments."""
-        imessage_group = parser.add_argument_group("iMessage Parameters")
-        imessage_group.add_argument(
-            "--db-path",
-            type=str,
-            default=None,
-            help="Path to iMessage chat.db file (default: ~/Library/Messages/chat.db)",
-        )
-        imessage_group.add_argument(
-            "--concatenate-conversations",
-            action="store_true",
-            default=True,
-            help="Concatenate messages within conversations for better context (default: True)",
-        )
-        imessage_group.add_argument(
-            "--no-concatenate-conversations",
-            action="store_true",
-            help="Process each message individually instead of concatenating by conversation",
-        )
-        imessage_group.add_argument(
-            "--chunk-size",
-            type=int,
-            default=1000,
-            help="Maximum characters per text chunk (default: 1000)",
-        )
-        imessage_group.add_argument(
-            "--chunk-overlap",
-            type=int,
-            default=200,
-            help="Overlap between text chunks (default: 200)",
-        )
-
-    async def load_data(self, args) -> list[str]:
-        """Load iMessage history and convert to text chunks."""
-        print("Loading iMessage conversation history...")
-
-        # Determine concatenation setting
-        concatenate = args.concatenate_conversations and not args.no_concatenate_conversations
-
-        # Initialize iMessage reader
-        reader = IMessageReader(concatenate_conversations=concatenate)
-
-        # Load documents
-        try:
-            if args.db_path:
-                # Use custom database path
-                db_dir = str(Path(args.db_path).parent)
-                documents = reader.load_data(input_dir=db_dir)
-            else:
-                # Use default macOS location
-                documents = reader.load_data()
-
-        except Exception as e:
-            print(f"Error loading iMessage data: {e}")
-            print("\nTroubleshooting tips:")
-            print("1. Make sure you have granted Full Disk Access to your terminal/IDE")
-            print("2. Check that the iMessage database exists at ~/Library/Messages/chat.db")
-            print("3. Try specifying a custom path with --db-path if you have a backup")
-            return []
-
-        if not documents:
-            print("No iMessage conversations found!")
-            return []
-
-        print(f"Loaded {len(documents)} iMessage documents")
-
-        # Show some statistics
-        total_messages = sum(doc.metadata.get("message_count", 1) for doc in documents)
-        print(f"Total messages: {total_messages}")
-
-        if concatenate:
-            # Show chat statistics
-            chat_names = [doc.metadata.get("chat_name", "Unknown") for doc in documents]
-            unique_chats = len(set(chat_names))
-            print(f"Unique conversations: {unique_chats}")
-
-        # Convert to text chunks
-        all_texts = create_text_chunks(
-            documents,
-            chunk_size=args.chunk_size,
-            chunk_overlap=args.chunk_overlap,
-        )
-
-        # Apply max_items limit if specified
-        if args.max_items > 0:
-            all_texts = all_texts[: args.max_items]
-            print(f"Limited to {len(all_texts)} text chunks (max_items={args.max_items})")
-
-        return all_texts
-
-
-async def main():
-    """Main entry point."""
-    app = IMessageRAG()
-    await app.run()
-
-
-if __name__ == "__main__":
-    asyncio.run(main())
--- a/apps/multimodal/vision-based-pdf-multi-vector/README.md
+++ b/apps/multimodal/vision-based-pdf-multi-vector/README.md
@@ -1,113 +0,0 @@
-## Vision-based PDF Multi-Vector Demos (macOS/MPS)
-
-This folder contains two demos to index PDF pages as images and run multi-vector retrieval with ColPali/ColQwen2, plus optional similarity map visualization and answer generation.
-
-### What you’ll run
- `multi-vector-leann-paper-example.py`: local PDF → pages → embed → build HNSW index → search.
- `multi-vector-leann-similarity-map.py`: HF dataset (default) or local pages → embed → index → retrieve → similarity maps → optional Qwen-VL answer.
-
-## Prerequisites (macOS)
-
-### 1) Homebrew poppler (for pdf2image)
-```bash
-brew install poppler
-which pdfinfo && pdfinfo -v
-```
-
-### 2) Python environment
-Use uv (recommended) or pip. Python 3.9+.
-
-Using uv:
-```bash
-uv pip install \
-  colpali_engine \
-  pdf2image \
-  pillow \
-  matplotlib qwen_vl_utils \
-  einops \
-  seaborn
-```
-
-Notes:
- On first run, models download from Hugging Face. Login/config if needed.
- The scripts auto-select device: CUDA > MPS > CPU. Verify MPS:
-```bash
-python -c "import torch; print('MPS available:', bool(getattr(torch.backends, 'mps', None) and torch.backends.mps.is_available()))"
-```
-
-## Run the demos
-
-### A) Local PDF example
-Converts a local PDF into page images, embeds them, builds an index, and searches.
-
-```bash
-cd apps/multimodal/vision-based-pdf-multi-vector
-# If you don't have the sample PDF locally, download it (ignored by Git)
-mkdir -p pdfs
-curl -L -o pdfs/2004.12832v2.pdf https://arxiv.org/pdf/2004.12832.pdf
-ls pdfs/2004.12832v2.pdf
-# Ensure output dir exists
-mkdir -p pages
-python multi-vector-leann-paper-example.py
-```
-Expected:
- Page images in `pages/`.
- Console prints like `Using device=mps, dtype=...` and retrieved file paths for queries.
-
-To use your own PDF: edit `pdf_path` near the top of the script.
-
-### B) Similarity map + answer demo
-Uses HF dataset `weaviate/arXiv-AI-papers-multi-vector` by default; can switch to local pages.
-
-```bash
-cd apps/multimodal/vision-based-pdf-multi-vector
-python multi-vector-leann-similarity-map.py
-```
-Artifacts (when enabled):
- Retrieved pages: `./figures/retrieved_page_rank{K}.png`
- Similarity maps: `./figures/similarity_map_rank{K}.png`
-
-Key knobs in the script (top of file):
- `QUERY`: your question
- `MODEL`: `"colqwen2"` or `"colpali"`
- `USE_HF_DATASET`: set `False` to use local pages
- `PDF`, `PAGES_DIR`: for local mode
- `INDEX_PATH`, `TOPK`, `FIRST_STAGE_K`, `REBUILD_INDEX`
- `SIMILARITY_MAP`, `SIM_TOKEN_IDX`, `SIM_OUTPUT`
- `ANSWER`, `MAX_NEW_TOKENS` (Qwen-VL)
-
-## Troubleshooting
- pdf2image errors on macOS: ensure `brew install poppler` and `pdfinfo` works in terminal.
- Slow or OOM on MPS: reduce dataset size (e.g., set `MAX_DOCS`) or switch to CPU.
- NaNs on MPS: keep fp32 on MPS (default in similarity-map script); avoid fp16 there.
- First-run model downloads can be large; ensure network access (HF mirrors if needed).
-
-## Notes
- Index files are under `./indexes/`. Delete or set `REBUILD_INDEX=True` to rebuild.
- For local PDFs, page images go to `./pages/`.
-
-
-### Retrieval and Visualization Example
-
-Example settings in `multi-vector-leann-similarity-map.py`:
- `QUERY = "How does DeepSeek-V2 compare against the LLaMA family of LLMs?"`
- `SIMILARITY_MAP = True` (to generate heatmaps)
- `TOPK = 1` (save the top retrieved page and its similarity map)
-
-Run:
-```bash
-cd apps/multimodal/vision-based-pdf-multi-vector
-python multi-vector-leann-similarity-map.py
-```
-
-Outputs (by default):
- Retrieved page: `./figures/retrieved_page_rank1.png`
- Similarity map: `./figures/similarity_map_rank1.png`
-
-Sample visualization (example result, and the query is "QUERY = "How does Vim model performance and efficiency compared to other models?"
-"):
-![Similarity map example](fig/image.png)
-
-Notes:
- Set `SIM_TOKEN_IDX` to visualize a specific token index; set `-1` to auto-select the most salient token.
- If you change `SIM_OUTPUT` to a file path (e.g., `./figures/my_map.png`), multiple ranks are saved as `my_map_rank{K}.png`.
--- a/apps/multimodal/vision-based-pdf-multi-vector/fig/image.png
+++ b/apps/multimodal/vision-based-pdf-multi-vector/fig/image.png
--- a/apps/multimodal/vision-based-pdf-multi-vector/leann_multi_vector.py
+++ b/apps/multimodal/vision-based-pdf-multi-vector/leann_multi_vector.py
@@ -1,182 +0,0 @@
-from __future__ import annotations
-
-import sys
-from pathlib import Path
-
-import numpy as np
-
-
-def _ensure_repo_paths_importable(current_file: str) -> None:
-    _repo_root = Path(current_file).resolve().parents[3]
-    _leann_core_src = _repo_root / "packages" / "leann-core" / "src"
-    _leann_hnsw_pkg = _repo_root / "packages" / "leann-backend-hnsw"
-    if str(_leann_core_src) not in sys.path:
-        sys.path.append(str(_leann_core_src))
-    if str(_leann_hnsw_pkg) not in sys.path:
-        sys.path.append(str(_leann_hnsw_pkg))
-
-
-_ensure_repo_paths_importable(__file__)
-
-from leann_backend_hnsw.hnsw_backend import HNSWBuilder, HNSWSearcher  # noqa: E402
-
-
-class LeannMultiVector:
-    def __init__(
-        self,
-        index_path: str,
-        dim: int = 128,
-        distance_metric: str = "mips",
-        m: int = 16,
-        ef_construction: int = 500,
-        is_compact: bool = False,
-        is_recompute: bool = False,
-        embedding_model_name: str = "colvision",
-    ) -> None:
-        self.index_path = index_path
-        self.dim = dim
-        self.embedding_model_name = embedding_model_name
-        self._pending_items: list[dict] = []
-        self._backend_kwargs = {
-            "distance_metric": distance_metric,
-            "M": m,
-            "efConstruction": ef_construction,
-            "is_compact": is_compact,
-            "is_recompute": is_recompute,
-        }
-        self._labels_meta: list[dict] = []
-
-    def _meta_dict(self) -> dict:
-        return {
-            "version": "1.0",
-            "backend_name": "hnsw",
-            "embedding_model": self.embedding_model_name,
-            "embedding_mode": "custom",
-            "dimensions": self.dim,
-            "backend_kwargs": self._backend_kwargs,
-            "is_compact": self._backend_kwargs.get("is_compact", True),
-            "is_pruned": self._backend_kwargs.get("is_compact", True)
-            and self._backend_kwargs.get("is_recompute", True),
-        }
-
-    def create_collection(self) -> None:
-        path = Path(self.index_path)
-        path.parent.mkdir(parents=True, exist_ok=True)
-
-    def insert(self, data: dict) -> None:
-        self._pending_items.append(
-            {
-                "doc_id": int(data["doc_id"]),
-                "filepath": data.get("filepath", ""),
-                "colbert_vecs": [np.asarray(v, dtype=np.float32) for v in data["colbert_vecs"]],
-            }
-        )
-
-    def _labels_path(self) -> Path:
-        index_path_obj = Path(self.index_path)
-        return index_path_obj.parent / f"{index_path_obj.name}.labels.json"
-
-    def _meta_path(self) -> Path:
-        index_path_obj = Path(self.index_path)
-        return index_path_obj.parent / f"{index_path_obj.name}.meta.json"
-
-    def create_index(self) -> None:
-        if not self._pending_items:
-            return
-
-        embeddings: list[np.ndarray] = []
-        labels_meta: list[dict] = []
-
-        for item in self._pending_items:
-            doc_id = int(item["doc_id"])
-            filepath = item.get("filepath", "")
-            colbert_vecs = item["colbert_vecs"]
-            for seq_id, vec in enumerate(colbert_vecs):
-                vec_np = np.asarray(vec, dtype=np.float32)
-                embeddings.append(vec_np)
-                labels_meta.append(
-                    {
-                        "id": f"{doc_id}:{seq_id}",
-                        "doc_id": doc_id,
-                        "seq_id": int(seq_id),
-                        "filepath": filepath,
-                    }
-                )
-
-        if not embeddings:
-            return
-
-        embeddings_np = np.vstack(embeddings).astype(np.float32)
-        # print shape of embeddings_np
-        print(embeddings_np.shape)
-
-        builder = HNSWBuilder(**{**self._backend_kwargs, "dimensions": self.dim})
-        ids = [str(i) for i in range(embeddings_np.shape[0])]
-        builder.build(embeddings_np, ids, self.index_path)
-
-        import json as _json
-
-        with open(self._meta_path(), "w", encoding="utf-8") as f:
-            _json.dump(self._meta_dict(), f, indent=2)
-        with open(self._labels_path(), "w", encoding="utf-8") as f:
-            _json.dump(labels_meta, f)
-
-        self._labels_meta = labels_meta
-
-    def _load_labels_meta_if_needed(self) -> None:
-        if self._labels_meta:
-            return
-        labels_path = self._labels_path()
-        if labels_path.exists():
-            import json as _json
-
-            with open(labels_path, encoding="utf-8") as f:
-                self._labels_meta = _json.load(f)
-
-    def search(
-        self, data: np.ndarray, topk: int, first_stage_k: int = 50
-    ) -> list[tuple[float, int]]:
-        if data.ndim == 1:
-            data = data.reshape(1, -1)
-        if data.dtype != np.float32:
-            data = data.astype(np.float32)
-
-        self._load_labels_meta_if_needed()
-
-        searcher = HNSWSearcher(self.index_path, meta=self._meta_dict())
-        raw = searcher.search(
-            data,
-            first_stage_k,
-            recompute_embeddings=False,
-            complexity=128,
-            beam_width=1,
-            prune_ratio=0.0,
-            batch_size=0,
-        )
-
-        labels = raw.get("labels")
-        distances = raw.get("distances")
-        if labels is None or distances is None:
-            return []
-
-        doc_scores: dict[int, float] = {}
-        B = len(labels)
-        for b in range(B):
-            per_doc_best: dict[int, float] = {}
-            for k, sid in enumerate(labels[b]):
-                try:
-                    idx = int(sid)
-                except Exception:
-                    continue
-                if 0 <= idx < len(self._labels_meta):
-                    doc_id = int(self._labels_meta[idx]["doc_id"])  # type: ignore[index]
-                else:
-                    continue
-                score = float(distances[b][k])
-                if (doc_id not in per_doc_best) or (score > per_doc_best[doc_id]):
-                    per_doc_best[doc_id] = score
-            for doc_id, best_score in per_doc_best.items():
-                doc_scores[doc_id] = doc_scores.get(doc_id, 0.0) + best_score
-
-        scores = sorted(((v, k) for k, v in doc_scores.items()), key=lambda x: x[0], reverse=True)
-        return scores[:topk] if len(scores) >= topk else scores
--- a/apps/multimodal/vision-based-pdf-multi-vector/multi-vector-leann-paper-example.py
+++ b/apps/multimodal/vision-based-pdf-multi-vector/multi-vector-leann-paper-example.py
@@ -1,112 +0,0 @@
-# pip install pdf2image
-# pip install pymilvus
-# pip install colpali_engine
-# pip install tqdm
-# pip install pillow
-
-import os
-import re
-import sys
-from pathlib import Path
-from typing import cast
-
-from PIL import Image
-from tqdm import tqdm
-
-# Ensure local leann packages are importable before importing them
-_repo_root = Path(__file__).resolve().parents[3]
-_leann_core_src = _repo_root / "packages" / "leann-core" / "src"
-_leann_hnsw_pkg = _repo_root / "packages" / "leann-backend-hnsw"
-if str(_leann_core_src) not in sys.path:
-    sys.path.append(str(_leann_core_src))
-if str(_leann_hnsw_pkg) not in sys.path:
-    sys.path.append(str(_leann_hnsw_pkg))
-
-
-import torch
-from colpali_engine.models import ColPali
-from colpali_engine.models.paligemma.colpali.processing_colpali import ColPaliProcessor
-from colpali_engine.utils.torch_utils import ListDataset, get_torch_device
-from torch.utils.data import DataLoader
-
-# Auto-select device: CUDA > MPS (mac) > CPU
-_device_str = (
-    "cuda"
-    if torch.cuda.is_available()
-    else (
-        "mps"
-        if getattr(torch.backends, "mps", None) and torch.backends.mps.is_available()
-        else "cpu"
-    )
-)
-device = get_torch_device(_device_str)
-# Prefer fp16 on GPU/MPS, bfloat16 on CPU
-_dtype = torch.float16 if _device_str in ("cuda", "mps") else torch.bfloat16
-model_name = "vidore/colpali-v1.2"
-
-model = ColPali.from_pretrained(
-    model_name,
-    torch_dtype=_dtype,
-    device_map=device,
-).eval()
-print(f"Using device={_device_str}, dtype={_dtype}")
-
-queries = [
-    "How to end-to-end retrieval with ColBert",
-    "Where is ColBERT performance Table, including text representation results?",
-]
-
-processor = cast(ColPaliProcessor, ColPaliProcessor.from_pretrained(model_name))
-
-dataloader = DataLoader(
-    dataset=ListDataset[str](queries),
-    batch_size=1,
-    shuffle=False,
-    collate_fn=lambda x: processor.process_queries(x),
-)
-
-qs: list[torch.Tensor] = []
-for batch_query in dataloader:
-    with torch.no_grad():
-        batch_query = {k: v.to(model.device) for k, v in batch_query.items()}
-        embeddings_query = model(**batch_query)
-    qs.extend(list(torch.unbind(embeddings_query.to("cpu"))))
-print(qs[0].shape)
-# %%
-page_filenames = sorted(os.listdir("./pages"), key=lambda n: int(re.search(r"\d+", n).group()))
-images = [Image.open(os.path.join("./pages", name)) for name in page_filenames]
-
-dataloader = DataLoader(
-    dataset=ListDataset[str](images),
-    batch_size=1,
-    shuffle=False,
-    collate_fn=lambda x: processor.process_images(x),
-)
-
-ds: list[torch.Tensor] = []
-for batch_doc in tqdm(dataloader):
-    with torch.no_grad():
-        batch_doc = {k: v.to(model.device) for k, v in batch_doc.items()}
-        embeddings_doc = model(**batch_doc)
-    ds.extend(list(torch.unbind(embeddings_doc.to("cpu"))))
-
-print(ds[0].shape)
-
-# %%
-# Build HNSW index via LeannRetriever primitives and run search
-index_path = "./indexes/colpali.leann"
-retriever = LeannRetriever(index_path=index_path, dim=int(ds[0].shape[-1]))
-retriever.create_collection()
-filepaths = [os.path.join("./pages", name) for name in page_filenames]
-for i in range(len(filepaths)):
-    data = {
-        "colbert_vecs": ds[i].float().numpy(),
-        "doc_id": i,
-        "filepath": filepaths[i],
-    }
-    retriever.insert(data)
-retriever.create_index()
-for query in qs:
-    query_np = query.float().numpy()
-    result = retriever.search(query_np, topk=1)
-    print(filepaths[result[0][1]])
--- a/apps/multimodal/vision-based-pdf-multi-vector/multi-vector-leann-similarity-map.py
+++ b/apps/multimodal/vision-based-pdf-multi-vector/multi-vector-leann-similarity-map.py
@@ -1,477 +0,0 @@
-## Jupyter-style notebook script
-# %%
-# uv pip install matplotlib qwen_vl_utils
-import os
-import re
-import sys
-from pathlib import Path
-from typing import Any, Optional, cast
-
-from PIL import Image
-from tqdm import tqdm
-
-
-def _ensure_repo_paths_importable(current_file: str) -> None:
-    """Make local leann packages importable without installing (mirrors multi-vector-leann.py)."""
-    _repo_root = Path(current_file).resolve().parents[3]
-    _leann_core_src = _repo_root / "packages" / "leann-core" / "src"
-    _leann_hnsw_pkg = _repo_root / "packages" / "leann-backend-hnsw"
-    if str(_leann_core_src) not in sys.path:
-        sys.path.append(str(_leann_core_src))
-    if str(_leann_hnsw_pkg) not in sys.path:
-        sys.path.append(str(_leann_hnsw_pkg))
-
-
-_ensure_repo_paths_importable(__file__)
-
-from leann_multi_vector import LeannMultiVector  # noqa: E402
-
-# %%
-# Config
-os.environ["TOKENIZERS_PARALLELISM"] = "false"
-QUERY = "How does DeepSeek-V2 compare against the LLaMA family of LLMs?"
-MODEL: str = "colqwen2"  # "colpali" or "colqwen2"
-
-# Data source: set to True to use the Hugging Face dataset example (recommended)
-USE_HF_DATASET: bool = True
-DATASET_NAME: str = "weaviate/arXiv-AI-papers-multi-vector"
-DATASET_SPLIT: str = "train"
-MAX_DOCS: Optional[int] = None  # limit number of pages to index; None = all
-
-# Local pages (used when USE_HF_DATASET == False)
-PDF: Optional[str] = None  # e.g., "./pdfs/2004.12832v2.pdf"
-PAGES_DIR: str = "./pages"
-
-# Index + retrieval settings
-INDEX_PATH: str = "./indexes/colvision.leann"
-TOPK: int = 1
-FIRST_STAGE_K: int = 500
-REBUILD_INDEX: bool = False
-
-# Artifacts
-SAVE_TOP_IMAGE: Optional[str] = "./figures/retrieved_page.png"
-SIMILARITY_MAP: bool = True
-SIM_TOKEN_IDX: int = 13  # -1 means auto-select the most salient token
-SIM_OUTPUT: str = "./figures/similarity_map.png"
-ANSWER: bool = True
-MAX_NEW_TOKENS: int = 128
-
-
-# %%
-# Helpers
-def _natural_sort_key(name: str) -> int:
-    m = re.search(r"\d+", name)
-    return int(m.group()) if m else 0
-
-
-def _load_images_from_dir(pages_dir: str) -> tuple[list[str], list[Image.Image]]:
-    filenames = [n for n in os.listdir(pages_dir) if n.lower().endswith((".png", ".jpg", ".jpeg"))]
-    filenames = sorted(filenames, key=_natural_sort_key)
-    filepaths = [os.path.join(pages_dir, n) for n in filenames]
-    images = [Image.open(p) for p in filepaths]
-    return filepaths, images
-
-
-def _maybe_convert_pdf_to_images(pdf_path: Optional[str], pages_dir: str, dpi: int = 200) -> None:
-    if not pdf_path:
-        return
-    os.makedirs(pages_dir, exist_ok=True)
-    try:
-        from pdf2image import convert_from_path
-    except Exception as e:
-        raise RuntimeError(
-            "pdf2image is required to convert PDF to images. Install via pip install pdf2image"
-        ) from e
-    images = convert_from_path(pdf_path, dpi=dpi)
-    for i, image in enumerate(images):
-        image.save(os.path.join(pages_dir, f"page_{i + 1}.png"), "PNG")
-
-
-def _select_device_and_dtype():
-    import torch
-    from colpali_engine.utils.torch_utils import get_torch_device
-
-    device_str = (
-        "cuda"
-        if torch.cuda.is_available()
-        else (
-            "mps"
-            if getattr(torch.backends, "mps", None) and torch.backends.mps.is_available()
-            else "cpu"
-        )
-    )
-    device = get_torch_device(device_str)
-    # Stable dtype selection to avoid NaNs:
-    # - CUDA: prefer bfloat16 if supported, else float16
-    # - MPS: use float32 (fp16 on MPS can produce NaNs in some ops)
-    # - CPU: float32
-    if device_str == "cuda":
-        dtype = torch.bfloat16 if torch.cuda.is_bf16_supported() else torch.float16
-        try:
-            torch.backends.cuda.matmul.allow_tf32 = True  # Better stability/perf on Ampere+
-        except Exception:
-            pass
-    elif device_str == "mps":
-        dtype = torch.float32
-    else:
-        dtype = torch.float32
-    return device_str, device, dtype
-
-
-def _load_colvision(model_choice: str):
-    import torch
-    from colpali_engine.models import ColPali, ColQwen2, ColQwen2Processor
-    from colpali_engine.models.paligemma.colpali.processing_colpali import ColPaliProcessor
-    from transformers.utils.import_utils import is_flash_attn_2_available
-
-    device_str, device, dtype = _select_device_and_dtype()
-
-    if model_choice == "colqwen2":
-        model_name = "vidore/colqwen2-v1.0"
-        # On CPU/MPS we must avoid flash-attn and stay eager; on CUDA prefer flash-attn if available
-        attn_implementation = (
-            "flash_attention_2"
-            if (device_str == "cuda" and is_flash_attn_2_available())
-            else "eager"
-        )
-        model = ColQwen2.from_pretrained(
-            model_name,
-            torch_dtype=torch.bfloat16,
-            device_map=device,
-            attn_implementation=attn_implementation,
-        ).eval()
-        processor = ColQwen2Processor.from_pretrained(model_name)
-    else:
-        model_name = "vidore/colpali-v1.2"
-        model = ColPali.from_pretrained(
-            model_name,
-            torch_dtype=torch.bfloat16,
-            device_map=device,
-        ).eval()
-        processor = cast(ColPaliProcessor, ColPaliProcessor.from_pretrained(model_name))
-
-    return model_name, model, processor, device_str, device, dtype
-
-
-def _embed_images(model, processor, images: list[Image.Image]) -> list[Any]:
-    import torch
-    from colpali_engine.utils.torch_utils import ListDataset
-    from torch.utils.data import DataLoader
-
-    # Ensure deterministic eval and autocast for stability
-    model.eval()
-
-    dataloader = DataLoader(
-        dataset=ListDataset[Image.Image](images),
-        batch_size=1,
-        shuffle=False,
-        collate_fn=lambda x: processor.process_images(x),
-    )
-
-    doc_vecs: list[Any] = []
-    for batch_doc in tqdm(dataloader, desc="Embedding images"):
-        with torch.no_grad():
-            batch_doc = {k: v.to(model.device) for k, v in batch_doc.items()}
-            # autocast on CUDA for bf16/fp16; on CPU/MPS stay in fp32
-            if model.device.type == "cuda":
-                with torch.autocast(
-                    device_type="cuda",
-                    dtype=model.dtype if model.dtype.is_floating_point else torch.bfloat16,
-                ):
-                    embeddings_doc = model(**batch_doc)
-            else:
-                embeddings_doc = model(**batch_doc)
-        doc_vecs.extend(list(torch.unbind(embeddings_doc.to("cpu"))))
-    return doc_vecs
-
-
-def _embed_queries(model, processor, queries: list[str]) -> list[Any]:
-    import torch
-    from colpali_engine.utils.torch_utils import ListDataset
-    from torch.utils.data import DataLoader
-
-    model.eval()
-
-    dataloader = DataLoader(
-        dataset=ListDataset[str](queries),
-        batch_size=1,
-        shuffle=False,
-        collate_fn=lambda x: processor.process_queries(x),
-    )
-
-    q_vecs: list[Any] = []
-    for batch_query in tqdm(dataloader, desc="Embedding queries"):
-        with torch.no_grad():
-            batch_query = {k: v.to(model.device) for k, v in batch_query.items()}
-            if model.device.type == "cuda":
-                with torch.autocast(
-                    device_type="cuda",
-                    dtype=model.dtype if model.dtype.is_floating_point else torch.bfloat16,
-                ):
-                    embeddings_query = model(**batch_query)
-            else:
-                embeddings_query = model(**batch_query)
-        q_vecs.extend(list(torch.unbind(embeddings_query.to("cpu"))))
-    return q_vecs
-
-
-def _build_index(index_path: str, doc_vecs: list[Any], filepaths: list[str]) -> LeannMultiVector:
-    dim = int(doc_vecs[0].shape[-1])
-    retriever = LeannMultiVector(index_path=index_path, dim=dim)
-    retriever.create_collection()
-    for i, vec in enumerate(doc_vecs):
-        data = {
-            "colbert_vecs": vec.float().numpy(),
-            "doc_id": i,
-            "filepath": filepaths[i],
-        }
-        retriever.insert(data)
-    retriever.create_index()
-    return retriever
-
-
-def _load_retriever_if_index_exists(index_path: str, dim: int) -> Optional[LeannMultiVector]:
-    index_base = Path(index_path)
-    # Rough heuristic: index dir exists AND meta+labels files exist
-    meta = index_base.parent / f"{index_base.name}.meta.json"
-    labels = index_base.parent / f"{index_base.name}.labels.json"
-    if index_base.exists() and meta.exists() and labels.exists():
-        return LeannMultiVector(index_path=index_path, dim=dim)
-    return None
-
-
-def _generate_similarity_map(
-    model,
-    processor,
-    image: Image.Image,
-    query: str,
-    token_idx: Optional[int] = None,
-    output_path: Optional[str] = None,
-) -> tuple[int, float]:
-    import torch
-    from colpali_engine.interpretability import (
-        get_similarity_maps_from_embeddings,
-        plot_similarity_map,
-    )
-
-    batch_images = processor.process_images([image]).to(model.device)
-    batch_queries = processor.process_queries([query]).to(model.device)
-
-    with torch.no_grad():
-        image_embeddings = model.forward(**batch_images)
-        query_embeddings = model.forward(**batch_queries)
-
-    n_patches = processor.get_n_patches(
-        image_size=image.size,
-        spatial_merge_size=getattr(model, "spatial_merge_size", None),
-    )
-    image_mask = processor.get_image_mask(batch_images)
-
-    batched_similarity_maps = get_similarity_maps_from_embeddings(
-        image_embeddings=image_embeddings,
-        query_embeddings=query_embeddings,
-        n_patches=n_patches,
-        image_mask=image_mask,
-    )
-
-    similarity_maps = batched_similarity_maps[0]
-
-    # Determine token index if not provided: choose the token with highest max score
-    if token_idx is None:
-        per_token_max = similarity_maps.view(similarity_maps.shape[0], -1).max(dim=1).values
-        token_idx = int(per_token_max.argmax().item())
-
-    max_sim_score = similarity_maps[token_idx, :, :].max().item()
-
-    if output_path:
-        import matplotlib.pyplot as plt
-
-        fig, ax = plot_similarity_map(
-            image=image,
-            similarity_map=similarity_maps[token_idx],
-            figsize=(14, 14),
-            show_colorbar=False,
-        )
-        ax.set_title(f"Token #{token_idx}. MaxSim score: {max_sim_score:.2f}", fontsize=12)
-        os.makedirs(os.path.dirname(output_path), exist_ok=True)
-        plt.savefig(output_path, bbox_inches="tight")
-        plt.close(fig)
-
-    return token_idx, float(max_sim_score)
-
-
-class QwenVL:
-    def __init__(self, device: str):
-        from transformers import AutoProcessor, Qwen2_5_VLForConditionalGeneration
-        from transformers.utils.import_utils import is_flash_attn_2_available
-
-        attn_implementation = "flash_attention_2" if is_flash_attn_2_available() else "eager"
-        self.model = Qwen2_5_VLForConditionalGeneration.from_pretrained(
-            "Qwen/Qwen2.5-VL-3B-Instruct",
-            torch_dtype="auto",
-            device_map=device,
-            attn_implementation=attn_implementation,
-        )
-
-        min_pixels = 256 * 28 * 28
-        max_pixels = 1280 * 28 * 28
-        self.processor = AutoProcessor.from_pretrained(
-            "Qwen/Qwen2.5-VL-3B-Instruct", min_pixels=min_pixels, max_pixels=max_pixels
-        )
-
-    def answer(self, query: str, images: list[Image.Image], max_new_tokens: int = 128) -> str:
-        import base64
-        from io import BytesIO
-
-        from qwen_vl_utils import process_vision_info
-
-        content = []
-        for img in images:
-            buffer = BytesIO()
-            img.save(buffer, format="jpeg")
-            img_base64 = base64.b64encode(buffer.getvalue()).decode("utf-8")
-            content.append({"type": "image", "image": f"data:image;base64,{img_base64}"})
-        content.append({"type": "text", "text": query})
-        messages = [{"role": "user", "content": content}]
-
-        text = self.processor.apply_chat_template(
-            messages, tokenize=False, add_generation_prompt=True
-        )
-        image_inputs, video_inputs = process_vision_info(messages)
-        inputs = self.processor(
-            text=[text], images=image_inputs, videos=video_inputs, padding=True, return_tensors="pt"
-        )
-        inputs = inputs.to(self.model.device)
-
-        generated_ids = self.model.generate(**inputs, max_new_tokens=max_new_tokens)
-        generated_ids_trimmed = [
-            out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
-        ]
-        return self.processor.batch_decode(
-            generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
-        )[0]
-
-
-# %%
-
-# Step 1: Prepare data
-if USE_HF_DATASET:
-    from datasets import load_dataset
-
-    dataset = load_dataset(DATASET_NAME, split=DATASET_SPLIT)
-    N = len(dataset) if MAX_DOCS is None else min(MAX_DOCS, len(dataset))
-    filepaths: list[str] = []
-    images: list[Image.Image] = []
-    for i in tqdm(range(N), desc="Loading dataset", total=N ):
-        p = dataset[i]
-        # Compose a descriptive identifier for printing later
-        identifier = f"arXiv:{p['paper_arxiv_id']}|title:{p['paper_title']}|page:{int(p['page_number'])}|id:{p['page_id']}"
-        print(identifier)
-        filepaths.append(identifier)
-        images.append(p["page_image"])  # PIL Image
-else:
-    _maybe_convert_pdf_to_images(PDF, PAGES_DIR)
-    filepaths, images = _load_images_from_dir(PAGES_DIR)
-    if not images:
-        raise RuntimeError(
-            f"No images found in {PAGES_DIR}. Provide PDF path in PDF variable or ensure images exist."
-        )
-
-
-# %%
-# Step 2: Load model and processor
-model_name, model, processor, device_str, device, dtype = _load_colvision(MODEL)
-print(f"Using model={model_name}, device={device_str}, dtype={dtype}")
-
-
-# %%
-
-# %%
-# Step 3: Build or load index
-retriever: Optional[LeannMultiVector] = None
-if not REBUILD_INDEX:
-    try:
-        one_vec = _embed_images(model, processor, [images[0]])[0]
-        retriever = _load_retriever_if_index_exists(INDEX_PATH, dim=int(one_vec.shape[-1]))
-    except Exception:
-        retriever = None
-
-if retriever is None:
-    doc_vecs = _embed_images(model, processor, images)
-    retriever = _build_index(INDEX_PATH, doc_vecs, filepaths)
-
-
-# %%
-# Step 4: Embed query and search
-q_vec = _embed_queries(model, processor, [QUERY])[0]
-results = retriever.search(q_vec.float().numpy(), topk=TOPK, first_stage_k=FIRST_STAGE_K)
-if not results:
-    print("No results found.")
-else:
-    print(f'Top {len(results)} results for query: "{QUERY}"')
-    top_images: list[Image.Image] = []
-    for rank, (score, doc_id) in enumerate(results, start=1):
-        path = filepaths[doc_id]
-        # For HF dataset, path is a descriptive identifier, not a real file path
-        print(f"{rank}) MaxSim: {score:.4f}, Page: {path}")
-        top_images.append(images[doc_id])
-
-    if SAVE_TOP_IMAGE:
-        from pathlib import Path as _Path
-
-        base = _Path(SAVE_TOP_IMAGE)
-        base.parent.mkdir(parents=True, exist_ok=True)
-        for rank, img in enumerate(top_images[:TOPK], start=1):
-            if base.suffix:
-                out_path = base.parent / f"{base.stem}_rank{rank}{base.suffix}"
-            else:
-                out_path = base / f"retrieved_page_rank{rank}.png"
-            img.save(str(out_path))
-            print(f"Saved retrieved page (rank {rank}) to: {out_path}")
-
-## TODO stange results of second page of DeepSeek-V2 rather than the first page
-
-# %%
-# Step 5: Similarity maps for top-K results
-if results and SIMILARITY_MAP:
-    token_idx = None if SIM_TOKEN_IDX < 0 else int(SIM_TOKEN_IDX)
-    from pathlib import Path as _Path
-
-    output_base = _Path(SIM_OUTPUT) if SIM_OUTPUT else None
-    for rank, img in enumerate(top_images[:TOPK], start=1):
-        if output_base:
-            if output_base.suffix:
-                out_dir = output_base.parent
-                out_name = f"{output_base.stem}_rank{rank}{output_base.suffix}"
-                out_path = str(out_dir / out_name)
-            else:
-                out_dir = output_base
-                out_dir.mkdir(parents=True, exist_ok=True)
-                out_path = str(out_dir / f"similarity_map_rank{rank}.png")
-        else:
-            out_path = None
-        chosen_idx, max_sim = _generate_similarity_map(
-            model=model,
-            processor=processor,
-            image=img,
-            query=QUERY,
-            token_idx=token_idx,
-            output_path=out_path,
-        )
-        if out_path:
-            print(
-                f"Saved similarity map for rank {rank}, token #{chosen_idx} (max={max_sim:.2f}) to: {out_path}"
-            )
-        else:
-            print(
-                f"Computed similarity map for rank {rank}, token #{chosen_idx} (max={max_sim:.2f})"
-            )
-
-
-# %%
-# Step 6: Optional answer generation
-if results and ANSWER:
-    qwen = QwenVL(device=device_str)
-    response = qwen.answer(QUERY, top_images[:TOPK], max_new_tokens=MAX_NEW_TOKENS)
-    print("\nAnswer:")
-    print(response)
--- a/apps/slack_data/init.py
+++ b/apps/slack_data/init.py
@@ -1 +0,0 @@
-# Slack MCP data integration for LEANN
--- a/apps/slack_data/slack_mcp_reader.py
+++ b/apps/slack_data/slack_mcp_reader.py
@@ -1,334 +0,0 @@
-#!/usr/bin/env python3
-"""
-Slack MCP Reader for LEANN
-
-This module provides functionality to connect to Slack MCP servers and fetch message data
-for indexing in LEANN. It supports various Slack MCP server implementations and provides
-flexible message processing options.
-"""
-
-import asyncio
-import json
-import logging
-from typing import Any, Optional
-
-logger = logging.getLogger(__name__)
-
-
-class SlackMCPReader:
-    """
-    Reader for Slack data via MCP (Model Context Protocol) servers.
-
-    This class connects to Slack MCP servers to fetch message data and convert it
-    into a format suitable for LEANN indexing.
-    """
-
-    def __init__(
-        self,
-        mcp_server_command: str,
-        workspace_name: Optional[str] = None,
-        concatenate_conversations: bool = True,
-        max_messages_per_conversation: int = 100,
-    ):
-        """
-        Initialize the Slack MCP Reader.
-
-        Args:
-            mcp_server_command: Command to start the MCP server (e.g., 'slack-mcp-server')
-            workspace_name: Optional workspace name to filter messages
-            concatenate_conversations: Whether to group messages by channel/thread
-            max_messages_per_conversation: Maximum messages to include per conversation
-        """
-        self.mcp_server_command = mcp_server_command
-        self.workspace_name = workspace_name
-        self.concatenate_conversations = concatenate_conversations
-        self.max_messages_per_conversation = max_messages_per_conversation
-        self.mcp_process = None
-
-    async def start_mcp_server(self):
-        """Start the MCP server process."""
-        try:
-            self.mcp_process = await asyncio.create_subprocess_exec(
-                *self.mcp_server_command.split(),
-                stdin=asyncio.subprocess.PIPE,
-                stdout=asyncio.subprocess.PIPE,
-                stderr=asyncio.subprocess.PIPE,
-            )
-            logger.info(f"Started MCP server: {self.mcp_server_command}")
-        except Exception as e:
-            logger.error(f"Failed to start MCP server: {e}")
-            raise
-
-    async def stop_mcp_server(self):
-        """Stop the MCP server process."""
-        if self.mcp_process:
-            self.mcp_process.terminate()
-            await self.mcp_process.wait()
-            logger.info("Stopped MCP server")
-
-    async def send_mcp_request(self, request: dict[str, Any]) -> dict[str, Any]:
-        """Send a request to the MCP server and get response."""
-        if not self.mcp_process:
-            raise RuntimeError("MCP server not started")
-
-        request_json = json.dumps(request) + "\n"
-        self.mcp_process.stdin.write(request_json.encode())
-        await self.mcp_process.stdin.drain()
-
-        response_line = await self.mcp_process.stdout.readline()
-        if not response_line:
-            raise RuntimeError("No response from MCP server")
-
-        return json.loads(response_line.decode().strip())
-
-    async def initialize_mcp_connection(self):
-        """Initialize the MCP connection."""
-        init_request = {
-            "jsonrpc": "2.0",
-            "id": 1,
-            "method": "initialize",
-            "params": {
-                "protocolVersion": "2024-11-05",
-                "capabilities": {},
-                "clientInfo": {"name": "leann-slack-reader", "version": "1.0.0"},
-            },
-        }
-
-        response = await self.send_mcp_request(init_request)
-        if "error" in response:
-            raise RuntimeError(f"MCP initialization failed: {response['error']}")
-
-        logger.info("MCP connection initialized successfully")
-
-    async def list_available_tools(self) -> list[dict[str, Any]]:
-        """List available tools from the MCP server."""
-        list_request = {"jsonrpc": "2.0", "id": 2, "method": "tools/list", "params": {}}
-
-        response = await self.send_mcp_request(list_request)
-        if "error" in response:
-            raise RuntimeError(f"Failed to list tools: {response['error']}")
-
-        return response.get("result", {}).get("tools", [])
-
-    async def fetch_slack_messages(
-        self, channel: Optional[str] = None, limit: int = 100
-    ) -> list[dict[str, Any]]:
-        """
-        Fetch Slack messages using MCP tools.
-
-        Args:
-            channel: Optional channel name to filter messages
-            limit: Maximum number of messages to fetch
-
-        Returns:
-            List of message dictionaries
-        """
-        # This is a generic implementation - specific MCP servers may have different tool names
-        # Common tool names might be: 'get_messages', 'list_messages', 'fetch_channel_history'
-
-        tools = await self.list_available_tools()
-        message_tool = None
-
-        # Look for a tool that can fetch messages
-        for tool in tools:
-            tool_name = tool.get("name", "").lower()
-            if any(
-                keyword in tool_name
-                for keyword in ["message", "history", "channel", "conversation"]
-            ):
-                message_tool = tool
-                break
-
-        if not message_tool:
-            raise RuntimeError("No message fetching tool found in MCP server")
-
-        # Prepare tool call parameters
-        tool_params = {"limit": limit}
-        if channel:
-            # Try common parameter names for channel specification
-            for param_name in ["channel", "channel_id", "channel_name"]:
-                tool_params[param_name] = channel
-                break
-
-        fetch_request = {
-            "jsonrpc": "2.0",
-            "id": 3,
-            "method": "tools/call",
-            "params": {"name": message_tool["name"], "arguments": tool_params},
-        }
-
-        response = await self.send_mcp_request(fetch_request)
-        if "error" in response:
-            raise RuntimeError(f"Failed to fetch messages: {response['error']}")
-
-        # Extract messages from response - format may vary by MCP server
-        result = response.get("result", {})
-        if "content" in result and isinstance(result["content"], list):
-            # Some MCP servers return content as a list
-            content = result["content"][0] if result["content"] else {}
-            if "text" in content:
-                try:
-                    messages = json.loads(content["text"])
-                except json.JSONDecodeError:
-                    # If not JSON, treat as plain text
-                    messages = [{"text": content["text"], "channel": channel or "unknown"}]
-            else:
-                messages = result["content"]
-        else:
-            # Direct message format
-            messages = result.get("messages", [result])
-
-        return messages if isinstance(messages, list) else [messages]
-
-    def _format_message(self, message: dict[str, Any]) -> str:
-        """Format a single message for indexing."""
-        text = message.get("text", "")
-        user = message.get("user", message.get("username", "Unknown"))
-        channel = message.get("channel", message.get("channel_name", "Unknown"))
-        timestamp = message.get("ts", message.get("timestamp", ""))
-
-        # Format timestamp if available
-        formatted_time = ""
-        if timestamp:
-            try:
-                import datetime
-
-                if isinstance(timestamp, str) and "." in timestamp:
-                    dt = datetime.datetime.fromtimestamp(float(timestamp))
-                    formatted_time = dt.strftime("%Y-%m-%d %H:%M:%S")
-                elif isinstance(timestamp, (int, float)):
-                    dt = datetime.datetime.fromtimestamp(timestamp)
-                    formatted_time = dt.strftime("%Y-%m-%d %H:%M:%S")
-                else:
-                    formatted_time = str(timestamp)
-            except (ValueError, TypeError):
-                formatted_time = str(timestamp)
-
-        # Build formatted message
-        parts = []
-        if channel:
-            parts.append(f"Channel: #{channel}")
-        if user:
-            parts.append(f"User: {user}")
-        if formatted_time:
-            parts.append(f"Time: {formatted_time}")
-        if text:
-            parts.append(f"Message: {text}")
-
-        return "\n".join(parts)
-
-    def _create_concatenated_content(self, messages: list[dict[str, Any]], channel: str) -> str:
-        """Create concatenated content from multiple messages in a channel."""
-        if not messages:
-            return ""
-
-        # Sort messages by timestamp if available
-        try:
-            messages.sort(key=lambda x: float(x.get("ts", x.get("timestamp", 0))))
-        except (ValueError, TypeError):
-            pass  # Keep original order if timestamps aren't numeric
-
-        # Limit messages per conversation
-        if len(messages) > self.max_messages_per_conversation:
-            messages = messages[-self.max_messages_per_conversation :]
-
-        # Create header
-        content_parts = [
-            f"Slack Channel: #{channel}",
-            f"Message Count: {len(messages)}",
-            f"Workspace: {self.workspace_name or 'Unknown'}",
-            "=" * 50,
-            "",
-        ]
-
-        # Add messages
-        for message in messages:
-            formatted_msg = self._format_message(message)
-            if formatted_msg.strip():
-                content_parts.append(formatted_msg)
-                content_parts.append("-" * 30)
-                content_parts.append("")
-
-        return "\n".join(content_parts)
-
-    async def read_slack_data(self, channels: Optional[list[str]] = None) -> list[str]:
-        """
-        Read Slack data and return formatted text chunks.
-
-        Args:
-            channels: Optional list of channel names to fetch. If None, fetches from all available channels.
-
-        Returns:
-            List of formatted text chunks ready for LEANN indexing
-        """
-        try:
-            await self.start_mcp_server()
-            await self.initialize_mcp_connection()
-
-            all_texts = []
-
-            if channels:
-                # Fetch specific channels
-                for channel in channels:
-                    try:
-                        messages = await self.fetch_slack_messages(channel=channel, limit=1000)
-                        if messages:
-                            if self.concatenate_conversations:
-                                text_content = self._create_concatenated_content(messages, channel)
-                                if text_content.strip():
-                                    all_texts.append(text_content)
-                            else:
-                                # Process individual messages
-                                for message in messages:
-                                    formatted_msg = self._format_message(message)
-                                    if formatted_msg.strip():
-                                        all_texts.append(formatted_msg)
-                    except Exception as e:
-                        logger.warning(f"Failed to fetch messages from channel {channel}: {e}")
-                        continue
-            else:
-                # Fetch from all available channels/conversations
-                # This is a simplified approach - real implementation would need to
-                # discover available channels first
-                try:
-                    messages = await self.fetch_slack_messages(limit=1000)
-                    if messages:
-                        # Group messages by channel if concatenating
-                        if self.concatenate_conversations:
-                            channel_messages = {}
-                            for message in messages:
-                                channel = message.get(
-                                    "channel", message.get("channel_name", "general")
-                                )
-                                if channel not in channel_messages:
-                                    channel_messages[channel] = []
-                                channel_messages[channel].append(message)
-
-                            # Create concatenated content for each channel
-                            for channel, msgs in channel_messages.items():
-                                text_content = self._create_concatenated_content(msgs, channel)
-                                if text_content.strip():
-                                    all_texts.append(text_content)
-                        else:
-                            # Process individual messages
-                            for message in messages:
-                                formatted_msg = self._format_message(message)
-                                if formatted_msg.strip():
-                                    all_texts.append(formatted_msg)
-                except Exception as e:
-                    logger.error(f"Failed to fetch messages: {e}")
-
-            return all_texts
-
-        finally:
-            await self.stop_mcp_server()
-
-    async def __aenter__(self):
-        """Async context manager entry."""
-        await self.start_mcp_server()
-        await self.initialize_mcp_connection()
-        return self
-
-    async def __aexit__(self, exc_type, exc_val, exc_tb):
-        """Async context manager exit."""
-        await self.stop_mcp_server()
--- a/apps/slack_rag.py
+++ b/apps/slack_rag.py
@@ -1,206 +0,0 @@
-#!/usr/bin/env python3
-"""
-Slack RAG Application with MCP Support
-
-This application enables RAG (Retrieval-Augmented Generation) on Slack messages
-by connecting to Slack MCP servers to fetch live data and index it in LEANN.
-
-Usage:
-    python -m apps.slack_rag --mcp-server "slack-mcp-server" --query "What did the team discuss about the project?"
-"""
-
-import argparse
-import asyncio
-
-from apps.base_rag_example import BaseRAGExample
-from apps.slack_data.slack_mcp_reader import SlackMCPReader
-
-
-class SlackMCPRAG(BaseRAGExample):
-    """
-    RAG application for Slack messages via MCP servers.
-
-    This class provides a complete RAG pipeline for Slack data, including
-    MCP server connection, data fetching, indexing, and interactive chat.
-    """
-
-    def __init__(self):
-        super().__init__(
-            name="Slack MCP RAG",
-            description="RAG application for Slack messages via MCP servers",
-            default_index_name="slack_messages",
-        )
-
-    def _add_specific_arguments(self, parser: argparse.ArgumentParser):
-        """Add Slack MCP-specific arguments."""
-        parser.add_argument(
-            "--mcp-server",
-            type=str,
-            required=True,
-            help="Command to start the Slack MCP server (e.g., 'slack-mcp-server' or 'npx slack-mcp-server')",
-        )
-
-        parser.add_argument(
-            "--workspace-name",
-            type=str,
-            help="Slack workspace name for better organization and filtering",
-        )
-
-        parser.add_argument(
-            "--channels",
-            nargs="+",
-            help="Specific Slack channels to index (e.g., general random). If not specified, fetches from all available channels",
-        )
-
-        parser.add_argument(
-            "--concatenate-conversations",
-            action="store_true",
-            default=True,
-            help="Group messages by channel/thread for better context (default: True)",
-        )
-
-        parser.add_argument(
-            "--no-concatenate-conversations",
-            action="store_true",
-            help="Process individual messages instead of grouping by channel",
-        )
-
-        parser.add_argument(
-            "--max-messages-per-channel",
-            type=int,
-            default=100,
-            help="Maximum number of messages to include per channel (default: 100)",
-        )
-
-        parser.add_argument(
-            "--test-connection",
-            action="store_true",
-            help="Test MCP server connection and list available tools without indexing",
-        )
-
-    async def test_mcp_connection(self, args) -> bool:
-        """Test the MCP server connection and display available tools."""
-        print(f"Testing connection to MCP server: {args.mcp_server}")
-
-        try:
-            reader = SlackMCPReader(
-                mcp_server_command=args.mcp_server,
-                workspace_name=args.workspace_name,
-                concatenate_conversations=not args.no_concatenate_conversations,
-                max_messages_per_conversation=args.max_messages_per_channel,
-            )
-
-            async with reader:
-                tools = await reader.list_available_tools()
-
-                print("\n✅ Successfully connected to MCP server!")
-                print(f"Available tools ({len(tools)}):")
-
-                for i, tool in enumerate(tools, 1):
-                    name = tool.get("name", "Unknown")
-                    description = tool.get("description", "No description available")
-                    print(f"\n{i}. {name}")
-                    print(
-                        f"   Description: {description[:100]}{'...' if len(description) > 100 else ''}"
-                    )
-
-                    # Show input schema if available
-                    schema = tool.get("inputSchema", {})
-                    if schema.get("properties"):
-                        props = list(schema["properties"].keys())[:3]  # Show first 3 properties
-                        print(
-                            f"   Parameters: {', '.join(props)}{'...' if len(schema['properties']) > 3 else ''}"
-                        )
-
-                return True
-
-        except Exception as e:
-            print(f"\n❌ Failed to connect to MCP server: {e}")
-            print("\nTroubleshooting tips:")
-            print("1. Make sure the MCP server is installed and accessible")
-            print("2. Check if the server command is correct")
-            print("3. Ensure you have proper authentication/credentials configured")
-            print("4. Try running the MCP server command directly to test it")
-            return False
-
-    async def load_data(self, args) -> list[str]:
-        """Load Slack messages via MCP server."""
-        print(f"Connecting to Slack MCP server: {args.mcp_server}")
-
-        if args.workspace_name:
-            print(f"Workspace: {args.workspace_name}")
-
-        if args.channels:
-            print(f"Channels: {', '.join(args.channels)}")
-        else:
-            print("Fetching from all available channels")
-
-        concatenate = not args.no_concatenate_conversations
-        print(
-            f"Processing mode: {'Concatenated conversations' if concatenate else 'Individual messages'}"
-        )
-
-        try:
-            reader = SlackMCPReader(
-                mcp_server_command=args.mcp_server,
-                workspace_name=args.workspace_name,
-                concatenate_conversations=concatenate,
-                max_messages_per_conversation=args.max_messages_per_channel,
-            )
-
-            texts = await reader.read_slack_data(channels=args.channels)
-
-            if not texts:
-                print("❌ No messages found! This could mean:")
-                print("- The MCP server couldn't fetch messages")
-                print("- The specified channels don't exist or are empty")
-                print("- Authentication issues with the Slack workspace")
-                return []
-
-            print(f"✅ Successfully loaded {len(texts)} text chunks from Slack")
-
-            # Show sample of what was loaded
-            if texts:
-                sample_text = texts[0][:200] + "..." if len(texts[0]) > 200 else texts[0]
-                print("\nSample content:")
-                print("-" * 40)
-                print(sample_text)
-                print("-" * 40)
-
-            return texts
-
-        except Exception as e:
-            print(f"❌ Error loading Slack data: {e}")
-            print("\nThis might be due to:")
-            print("- MCP server connection issues")
-            print("- Authentication problems")
-            print("- Network connectivity issues")
-            print("- Incorrect channel names")
-            raise
-
-    async def run(self):
-        """Main entry point with MCP connection testing."""
-        args = self.parser.parse_args()
-
-        # Test connection if requested
-        if args.test_connection:
-            success = await self.test_mcp_connection(args)
-            if not success:
-                return
-            print(
-                "\n🎉 MCP server is working! You can now run without --test-connection to start indexing."
-            )
-            return
-
-        # Run the standard RAG pipeline
-        await super().run()
-
-
-async def main():
-    """Main entry point for the Slack MCP RAG application."""
-    app = SlackMCPRAG()
-    await app.run()
-
-
-if __name__ == "__main__":
-    asyncio.run(main())
--- a/apps/twitter_data/init.py
+++ b/apps/twitter_data/init.py
@@ -1 +0,0 @@
-# Twitter MCP data integration for LEANN
--- a/apps/twitter_data/twitter_mcp_reader.py
+++ b/apps/twitter_data/twitter_mcp_reader.py
@@ -1,295 +0,0 @@
-#!/usr/bin/env python3
-"""
-Twitter MCP Reader for LEANN
-
-This module provides functionality to connect to Twitter MCP servers and fetch bookmark data
-for indexing in LEANN. It supports various Twitter MCP server implementations and provides
-flexible bookmark processing options.
-"""
-
-import asyncio
-import json
-import logging
-from typing import Any, Optional
-
-logger = logging.getLogger(__name__)
-
-
-class TwitterMCPReader:
-    """
-    Reader for Twitter bookmark data via MCP (Model Context Protocol) servers.
-
-    This class connects to Twitter MCP servers to fetch bookmark data and convert it
-    into a format suitable for LEANN indexing.
-    """
-
-    def __init__(
-        self,
-        mcp_server_command: str,
-        username: Optional[str] = None,
-        include_tweet_content: bool = True,
-        include_metadata: bool = True,
-        max_bookmarks: int = 1000,
-    ):
-        """
-        Initialize the Twitter MCP Reader.
-
-        Args:
-            mcp_server_command: Command to start the MCP server (e.g., 'twitter-mcp-server')
-            username: Optional Twitter username to filter bookmarks
-            include_tweet_content: Whether to include full tweet content
-            include_metadata: Whether to include tweet metadata (likes, retweets, etc.)
-            max_bookmarks: Maximum number of bookmarks to fetch
-        """
-        self.mcp_server_command = mcp_server_command
-        self.username = username
-        self.include_tweet_content = include_tweet_content
-        self.include_metadata = include_metadata
-        self.max_bookmarks = max_bookmarks
-        self.mcp_process = None
-
-    async def start_mcp_server(self):
-        """Start the MCP server process."""
-        try:
-            self.mcp_process = await asyncio.create_subprocess_exec(
-                *self.mcp_server_command.split(),
-                stdin=asyncio.subprocess.PIPE,
-                stdout=asyncio.subprocess.PIPE,
-                stderr=asyncio.subprocess.PIPE,
-            )
-            logger.info(f"Started MCP server: {self.mcp_server_command}")
-        except Exception as e:
-            logger.error(f"Failed to start MCP server: {e}")
-            raise
-
-    async def stop_mcp_server(self):
-        """Stop the MCP server process."""
-        if self.mcp_process:
-            self.mcp_process.terminate()
-            await self.mcp_process.wait()
-            logger.info("Stopped MCP server")
-
-    async def send_mcp_request(self, request: dict[str, Any]) -> dict[str, Any]:
-        """Send a request to the MCP server and get response."""
-        if not self.mcp_process:
-            raise RuntimeError("MCP server not started")
-
-        request_json = json.dumps(request) + "\n"
-        self.mcp_process.stdin.write(request_json.encode())
-        await self.mcp_process.stdin.drain()
-
-        response_line = await self.mcp_process.stdout.readline()
-        if not response_line:
-            raise RuntimeError("No response from MCP server")
-
-        return json.loads(response_line.decode().strip())
-
-    async def initialize_mcp_connection(self):
-        """Initialize the MCP connection."""
-        init_request = {
-            "jsonrpc": "2.0",
-            "id": 1,
-            "method": "initialize",
-            "params": {
-                "protocolVersion": "2024-11-05",
-                "capabilities": {},
-                "clientInfo": {"name": "leann-twitter-reader", "version": "1.0.0"},
-            },
-        }
-
-        response = await self.send_mcp_request(init_request)
-        if "error" in response:
-            raise RuntimeError(f"MCP initialization failed: {response['error']}")
-
-        logger.info("MCP connection initialized successfully")
-
-    async def list_available_tools(self) -> list[dict[str, Any]]:
-        """List available tools from the MCP server."""
-        list_request = {"jsonrpc": "2.0", "id": 2, "method": "tools/list", "params": {}}
-
-        response = await self.send_mcp_request(list_request)
-        if "error" in response:
-            raise RuntimeError(f"Failed to list tools: {response['error']}")
-
-        return response.get("result", {}).get("tools", [])
-
-    async def fetch_twitter_bookmarks(self, limit: Optional[int] = None) -> list[dict[str, Any]]:
-        """
-        Fetch Twitter bookmarks using MCP tools.
-
-        Args:
-            limit: Maximum number of bookmarks to fetch
-
-        Returns:
-            List of bookmark dictionaries
-        """
-        tools = await self.list_available_tools()
-        bookmark_tool = None
-
-        # Look for a tool that can fetch bookmarks
-        for tool in tools:
-            tool_name = tool.get("name", "").lower()
-            if any(keyword in tool_name for keyword in ["bookmark", "saved", "favorite"]):
-                bookmark_tool = tool
-                break
-
-        if not bookmark_tool:
-            raise RuntimeError("No bookmark fetching tool found in MCP server")
-
-        # Prepare tool call parameters
-        tool_params = {}
-        if limit or self.max_bookmarks:
-            tool_params["limit"] = limit or self.max_bookmarks
-        if self.username:
-            tool_params["username"] = self.username
-
-        fetch_request = {
-            "jsonrpc": "2.0",
-            "id": 3,
-            "method": "tools/call",
-            "params": {"name": bookmark_tool["name"], "arguments": tool_params},
-        }
-
-        response = await self.send_mcp_request(fetch_request)
-        if "error" in response:
-            raise RuntimeError(f"Failed to fetch bookmarks: {response['error']}")
-
-        # Extract bookmarks from response
-        result = response.get("result", {})
-        if "content" in result and isinstance(result["content"], list):
-            content = result["content"][0] if result["content"] else {}
-            if "text" in content:
-                try:
-                    bookmarks = json.loads(content["text"])
-                except json.JSONDecodeError:
-                    # If not JSON, treat as plain text
-                    bookmarks = [{"text": content["text"], "source": "twitter"}]
-            else:
-                bookmarks = result["content"]
-        else:
-            bookmarks = result.get("bookmarks", result.get("tweets", [result]))
-
-        return bookmarks if isinstance(bookmarks, list) else [bookmarks]
-
-    def _format_bookmark(self, bookmark: dict[str, Any]) -> str:
-        """Format a single bookmark for indexing."""
-        # Extract tweet information
-        text = bookmark.get("text", bookmark.get("content", ""))
-        author = bookmark.get(
-            "author", bookmark.get("username", bookmark.get("user", {}).get("username", "Unknown"))
-        )
-        timestamp = bookmark.get("created_at", bookmark.get("timestamp", ""))
-        url = bookmark.get("url", bookmark.get("tweet_url", ""))
-
-        # Extract metadata if available
-        likes = bookmark.get("likes", bookmark.get("favorite_count", 0))
-        retweets = bookmark.get("retweets", bookmark.get("retweet_count", 0))
-        replies = bookmark.get("replies", bookmark.get("reply_count", 0))
-
-        # Build formatted bookmark
-        parts = []
-
-        # Header
-        parts.append("=== Twitter Bookmark ===")
-
-        if author:
-            parts.append(f"Author: @{author}")
-
-        if timestamp:
-            # Format timestamp if it's a standard format
-            try:
-                import datetime
-
-                if "T" in str(timestamp):  # ISO format
-                    dt = datetime.datetime.fromisoformat(timestamp.replace("Z", "+00:00"))
-                    formatted_time = dt.strftime("%Y-%m-%d %H:%M:%S")
-                else:
-                    formatted_time = str(timestamp)
-                parts.append(f"Date: {formatted_time}")
-            except (ValueError, TypeError):
-                parts.append(f"Date: {timestamp}")
-
-        if url:
-            parts.append(f"URL: {url}")
-
-        # Tweet content
-        if text and self.include_tweet_content:
-            parts.append("")
-            parts.append("Content:")
-            parts.append(text)
-
-        # Metadata
-        if self.include_metadata and any([likes, retweets, replies]):
-            parts.append("")
-            parts.append("Engagement:")
-            if likes:
-                parts.append(f"  Likes: {likes}")
-            if retweets:
-                parts.append(f"  Retweets: {retweets}")
-            if replies:
-                parts.append(f"  Replies: {replies}")
-
-        # Extract hashtags and mentions if available
-        hashtags = bookmark.get("hashtags", [])
-        mentions = bookmark.get("mentions", [])
-
-        if hashtags or mentions:
-            parts.append("")
-            if hashtags:
-                parts.append(f"Hashtags: {', '.join(hashtags)}")
-            if mentions:
-                parts.append(f"Mentions: {', '.join(mentions)}")
-
-        return "\n".join(parts)
-
-    async def read_twitter_bookmarks(self) -> list[str]:
-        """
-        Read Twitter bookmark data and return formatted text chunks.
-
-        Returns:
-            List of formatted text chunks ready for LEANN indexing
-        """
-        try:
-            await self.start_mcp_server()
-            await self.initialize_mcp_connection()
-
-            print(f"Fetching up to {self.max_bookmarks} bookmarks...")
-            if self.username:
-                print(f"Filtering for user: @{self.username}")
-
-            bookmarks = await self.fetch_twitter_bookmarks()
-
-            if not bookmarks:
-                print("No bookmarks found")
-                return []
-
-            print(f"Processing {len(bookmarks)} bookmarks...")
-
-            all_texts = []
-            processed_count = 0
-
-            for bookmark in bookmarks:
-                try:
-                    formatted_bookmark = self._format_bookmark(bookmark)
-                    if formatted_bookmark.strip():
-                        all_texts.append(formatted_bookmark)
-                        processed_count += 1
-                except Exception as e:
-                    logger.warning(f"Failed to format bookmark: {e}")
-                    continue
-
-            print(f"Successfully processed {processed_count} bookmarks")
-            return all_texts
-
-        finally:
-            await self.stop_mcp_server()
-
-    async def __aenter__(self):
-        """Async context manager entry."""
-        await self.start_mcp_server()
-        await self.initialize_mcp_connection()
-        return self
-
-    async def __aexit__(self, exc_type, exc_val, exc_tb):
-        """Async context manager exit."""
-        await self.stop_mcp_server()
--- a/apps/twitter_rag.py
+++ b/apps/twitter_rag.py
@@ -1,195 +0,0 @@
-#!/usr/bin/env python3
-"""
-Twitter RAG Application with MCP Support
-
-This application enables RAG (Retrieval-Augmented Generation) on Twitter bookmarks
-by connecting to Twitter MCP servers to fetch live data and index it in LEANN.
-
-Usage:
-    python -m apps.twitter_rag --mcp-server "twitter-mcp-server" --query "What articles did I bookmark about AI?"
-"""
-
-import argparse
-import asyncio
-
-from apps.base_rag_example import BaseRAGExample
-from apps.twitter_data.twitter_mcp_reader import TwitterMCPReader
-
-
-class TwitterMCPRAG(BaseRAGExample):
-    """
-    RAG application for Twitter bookmarks via MCP servers.
-
-    This class provides a complete RAG pipeline for Twitter bookmark data, including
-    MCP server connection, data fetching, indexing, and interactive chat.
-    """
-
-    def __init__(self):
-        super().__init__(
-            name="Twitter MCP RAG",
-            description="RAG application for Twitter bookmarks via MCP servers",
-            default_index_name="twitter_bookmarks",
-        )
-
-    def _add_specific_arguments(self, parser: argparse.ArgumentParser):
-        """Add Twitter MCP-specific arguments."""
-        parser.add_argument(
-            "--mcp-server",
-            type=str,
-            required=True,
-            help="Command to start the Twitter MCP server (e.g., 'twitter-mcp-server' or 'npx twitter-mcp-server')",
-        )
-
-        parser.add_argument(
-            "--username", type=str, help="Twitter username to filter bookmarks (without @)"
-        )
-
-        parser.add_argument(
-            "--max-bookmarks",
-            type=int,
-            default=1000,
-            help="Maximum number of bookmarks to fetch (default: 1000)",
-        )
-
-        parser.add_argument(
-            "--no-tweet-content",
-            action="store_true",
-            help="Exclude tweet content, only include metadata",
-        )
-
-        parser.add_argument(
-            "--no-metadata",
-            action="store_true",
-            help="Exclude engagement metadata (likes, retweets, etc.)",
-        )
-
-        parser.add_argument(
-            "--test-connection",
-            action="store_true",
-            help="Test MCP server connection and list available tools without indexing",
-        )
-
-    async def test_mcp_connection(self, args) -> bool:
-        """Test the MCP server connection and display available tools."""
-        print(f"Testing connection to MCP server: {args.mcp_server}")
-
-        try:
-            reader = TwitterMCPReader(
-                mcp_server_command=args.mcp_server,
-                username=args.username,
-                include_tweet_content=not args.no_tweet_content,
-                include_metadata=not args.no_metadata,
-                max_bookmarks=args.max_bookmarks,
-            )
-
-            async with reader:
-                tools = await reader.list_available_tools()
-
-                print("\n✅ Successfully connected to MCP server!")
-                print(f"Available tools ({len(tools)}):")
-
-                for i, tool in enumerate(tools, 1):
-                    name = tool.get("name", "Unknown")
-                    description = tool.get("description", "No description available")
-                    print(f"\n{i}. {name}")
-                    print(
-                        f"   Description: {description[:100]}{'...' if len(description) > 100 else ''}"
-                    )
-
-                    # Show input schema if available
-                    schema = tool.get("inputSchema", {})
-                    if schema.get("properties"):
-                        props = list(schema["properties"].keys())[:3]  # Show first 3 properties
-                        print(
-                            f"   Parameters: {', '.join(props)}{'...' if len(schema['properties']) > 3 else ''}"
-                        )
-
-                return True
-
-        except Exception as e:
-            print(f"\n❌ Failed to connect to MCP server: {e}")
-            print("\nTroubleshooting tips:")
-            print("1. Make sure the Twitter MCP server is installed and accessible")
-            print("2. Check if the server command is correct")
-            print("3. Ensure you have proper Twitter API credentials configured")
-            print("4. Verify your Twitter account has bookmarks to fetch")
-            print("5. Try running the MCP server command directly to test it")
-            return False
-
-    async def load_data(self, args) -> list[str]:
-        """Load Twitter bookmarks via MCP server."""
-        print(f"Connecting to Twitter MCP server: {args.mcp_server}")
-
-        if args.username:
-            print(f"Username filter: @{args.username}")
-
-        print(f"Max bookmarks: {args.max_bookmarks}")
-        print(f"Include tweet content: {not args.no_tweet_content}")
-        print(f"Include metadata: {not args.no_metadata}")
-
-        try:
-            reader = TwitterMCPReader(
-                mcp_server_command=args.mcp_server,
-                username=args.username,
-                include_tweet_content=not args.no_tweet_content,
-                include_metadata=not args.no_metadata,
-                max_bookmarks=args.max_bookmarks,
-            )
-
-            texts = await reader.read_twitter_bookmarks()
-
-            if not texts:
-                print("❌ No bookmarks found! This could mean:")
-                print("- You don't have any bookmarks on Twitter")
-                print("- The MCP server couldn't access your bookmarks")
-                print("- Authentication issues with Twitter API")
-                print("- The username filter didn't match any bookmarks")
-                return []
-
-            print(f"✅ Successfully loaded {len(texts)} bookmarks from Twitter")
-
-            # Show sample of what was loaded
-            if texts:
-                sample_text = texts[0][:300] + "..." if len(texts[0]) > 300 else texts[0]
-                print("\nSample bookmark:")
-                print("-" * 50)
-                print(sample_text)
-                print("-" * 50)
-
-            return texts
-
-        except Exception as e:
-            print(f"❌ Error loading Twitter bookmarks: {e}")
-            print("\nThis might be due to:")
-            print("- MCP server connection issues")
-            print("- Twitter API authentication problems")
-            print("- Network connectivity issues")
-            print("- Rate limiting from Twitter API")
-            raise
-
-    async def run(self):
-        """Main entry point with MCP connection testing."""
-        args = self.parser.parse_args()
-
-        # Test connection if requested
-        if args.test_connection:
-            success = await self.test_mcp_connection(args)
-            if not success:
-                return
-            print(
-                "\n🎉 MCP server is working! You can now run without --test-connection to start indexing."
-            )
-            return
-
-        # Run the standard RAG pipeline
-        await super().run()
-
-
-async def main():
-    """Main entry point for the Twitter MCP RAG application."""
-    app = TwitterMCPRAG()
-    await app.run()
-
-
-if __name__ == "__main__":
-    asyncio.run(main())
--- a/assets/wechat_user_group.JPG
+++ b/assets/wechat_user_group.JPG
--- a/benchmarks/init.py
+++ b/benchmarks/init.py
--- a/benchmarks/bm25_diskann_baselines/README.md
+++ b/benchmarks/bm25_diskann_baselines/README.md
@@ -1,23 +0,0 @@
-BM25 vs DiskANN Baselines
-
-```bash
-aws s3 sync s3://powerrag-diskann-rpj-wiki-20250824-224037-194d640c/bm25_rpj_wiki/index_en_only/ benchmarks/data/indices/bm25_index/
-aws s3 sync s3://powerrag-diskann-rpj-wiki-20250824-224037-194d640c/diskann_rpj_wiki/ benchmarks/data/indices/diskann_rpj_wiki/
-```
-
- Dataset: `benchmarks/data/queries/nq_open.jsonl` (Natural Questions)
- Machine-specific; results measured locally with the current repo.
-
-DiskANN (NQ queries, search-only)
- Command: `uv run --script benchmarks/bm25_diskann_baselines/run_diskann.py`
- Settings: `recompute_embeddings=False`, embeddings precomputed (excluded from timing), batching off, caching off (`cache_mechanism=2`, `num_nodes_to_cache=0`)
- Result: avg 0.011093 s/query, QPS 90.15 (p50 0.010731 s, p95 0.015000 s)
-
-BM25
- Command: `uv run --script benchmarks/bm25_diskann_baselines/run_bm25.py`
- Settings: `k=10`, `k1=0.9`, `b=0.4`, queries=100
- Result: avg 0.028589 s/query, QPS 34.97 (p50 0.026060 s, p90 0.043695 s, p95 0.053260 s, p99 0.055257 s)
-
-Notes
- DiskANN measures search-only latency on real NQ queries (embeddings computed beforehand and excluded from timing).
- Use `benchmarks/bm25_diskann_baselines/run_diskann.py` for DiskANN; `benchmarks/bm25_diskann_baselines/run_bm25.py` for BM25.
--- a/benchmarks/bm25_diskann_baselines/run_bm25.py
+++ b/benchmarks/bm25_diskann_baselines/run_bm25.py
@@ -1,183 +0,0 @@
-# /// script
-# dependencies = [
-#   "pyserini"
-# ]
-# ///
-# sudo pacman -S jdk21-openjdk
-# export JAVA_HOME=/usr/lib/jvm/java-21-openjdk
-# sudo archlinux-java status
-# sudo archlinux-java set java-21-openjdk
-# set -Ux JAVA_HOME /usr/lib/jvm/java-21-openjdk
-# fish_add_path --global $JAVA_HOME/bin
-# set -Ux LD_LIBRARY_PATH $JAVA_HOME/lib/server $LD_LIBRARY_PATH
-# which javac # Should be /usr/lib/jvm/java-21-openjdk/bin/javac
-
-import argparse
-import json
-import os
-import sys
-import time
-from statistics import mean
-
-
-def load_queries(path: str, limit: int | None) -> list[str]:
-    queries: list[str] = []
-    # Try JSONL with a 'query' or 'text' field; fallback to plain text (one query per line)
-    _, ext = os.path.splitext(path)
-    if ext.lower() in {".jsonl", ".json"}:
-        with open(path, encoding="utf-8") as f:
-            for line in f:
-                line = line.strip()
-                if not line:
-                    continue
-                try:
-                    obj = json.loads(line)
-                except json.JSONDecodeError:
-                    # Not strict JSONL? treat the whole line as the query
-                    queries.append(line)
-                    continue
-                q = obj.get("query") or obj.get("text") or obj.get("question")
-                if q:
-                    queries.append(str(q))
-    else:
-        with open(path, encoding="utf-8") as f:
-            for line in f:
-                s = line.strip()
-                if s:
-                    queries.append(s)
-
-    if limit is not None and limit > 0:
-        queries = queries[:limit]
-    return queries
-
-
-def percentile(values: list[float], p: float) -> float:
-    if not values:
-        return 0.0
-    s = sorted(values)
-    k = (len(s) - 1) * (p / 100.0)
-    f = int(k)
-    c = min(f + 1, len(s) - 1)
-    if f == c:
-        return s[f]
-    return s[f] + (s[c] - s[f]) * (k - f)
-
-
-def main():
-    ap = argparse.ArgumentParser(description="Standalone BM25 latency benchmark (Pyserini)")
-    ap.add_argument(
-        "--bm25-index",
-        default="benchmarks/data/indices/bm25_index",
-        help="Path to Pyserini Lucene index directory",
-    )
-    ap.add_argument(
-        "--queries",
-        default="benchmarks/data/queries/nq_open.jsonl",
-        help="Path to queries file (JSONL with 'query'/'text' or plain txt one-per-line)",
-    )
-    ap.add_argument("--k", type=int, default=10, help="Top-k to retrieve (default: 10)")
-    ap.add_argument("--k1", type=float, default=0.9, help="BM25 k1 (default: 0.9)")
-    ap.add_argument("--b", type=float, default=0.4, help="BM25 b (default: 0.4)")
-    ap.add_argument("--limit", type=int, default=100, help="Max queries to run (default: 100)")
-    ap.add_argument(
-        "--warmup", type=int, default=5, help="Warmup queries not counted in latency (default: 5)"
-    )
-    ap.add_argument(
-        "--fetch-docs", action="store_true", help="Also fetch doc contents (slower; default: off)"
-    )
-    ap.add_argument("--report", type=str, default=None, help="Optional JSON report path")
-    args = ap.parse_args()
-
-    try:
-        from pyserini.search.lucene import LuceneSearcher
-    except Exception:
-        print("Pyserini not found. Install with: pip install pyserini", file=sys.stderr)
-        raise
-
-    if not os.path.isdir(args.bm25_index):
-        print(f"Index directory not found: {args.bm25_index}", file=sys.stderr)
-        sys.exit(1)
-
-    queries = load_queries(args.queries, args.limit)
-    if not queries:
-        print("No queries loaded.", file=sys.stderr)
-        sys.exit(1)
-
-    print(f"Loaded {len(queries)} queries from {args.queries}")
-    print(f"Opening BM25 index: {args.bm25_index}")
-    searcher = LuceneSearcher(args.bm25_index)
-    # Some builds of pyserini require explicit set_bm25; others ignore
-    try:
-        searcher.set_bm25(k1=args.k1, b=args.b)
-    except Exception:
-        pass
-
-    latencies: list[float] = []
-    total_searches = 0
-
-    # Warmup
-    for i in range(min(args.warmup, len(queries))):
-        _ = searcher.search(queries[i], k=args.k)
-
-    t0 = time.time()
-    for i, q in enumerate(queries):
-        t1 = time.time()
-        hits = searcher.search(q, k=args.k)
-        t2 = time.time()
-        latencies.append(t2 - t1)
-        total_searches += 1
-
-        if args.fetch_docs:
-            # Optional doc fetch to include I/O time
-            for h in hits:
-                try:
-                    _ = searcher.doc(h.docid)
-                except Exception:
-                    pass
-
-        if (i + 1) % 50 == 0:
-            print(f"Processed {i + 1}/{len(queries)} queries")
-
-    t1 = time.time()
-    total_time = t1 - t0
-
-    if latencies:
-        avg = mean(latencies)
-        p50 = percentile(latencies, 50)
-        p90 = percentile(latencies, 90)
-        p95 = percentile(latencies, 95)
-        p99 = percentile(latencies, 99)
-        qps = total_searches / total_time if total_time > 0 else 0.0
-    else:
-        avg = p50 = p90 = p95 = p99 = qps = 0.0
-
-    print("BM25 Latency Report")
-    print(f"  queries: {total_searches}")
-    print(f"  k: {args.k}, k1: {args.k1}, b: {args.b}")
-    print(f"  avg per query: {avg:.6f} s")
-    print(f"  p50/p90/p95/p99: {p50:.6f}/{p90:.6f}/{p95:.6f}/{p99:.6f} s")
-    print(f"  total time: {total_time:.3f} s, qps: {qps:.2f}")
-
-    if args.report:
-        payload = {
-            "queries": total_searches,
-            "k": args.k,
-            "k1": args.k1,
-            "b": args.b,
-            "avg_s": avg,
-            "p50_s": p50,
-            "p90_s": p90,
-            "p95_s": p95,
-            "p99_s": p99,
-            "total_time_s": total_time,
-            "qps": qps,
-            "index_dir": os.path.abspath(args.bm25_index),
-            "fetch_docs": bool(args.fetch_docs),
-        }
-        with open(args.report, "w", encoding="utf-8") as f:
-            json.dump(payload, f, indent=2)
-        print(f"Saved report to {args.report}")
-
-
-if __name__ == "__main__":
-    main()
--- a/benchmarks/bm25_diskann_baselines/run_diskann.py
+++ b/benchmarks/bm25_diskann_baselines/run_diskann.py
@@ -1,124 +0,0 @@
-# /// script
-# dependencies = [
-#   "leann-backend-diskann"
-# ]
-# ///
-
-import argparse
-import json
-import time
-from pathlib import Path
-
-import numpy as np
-
-
-def load_queries(path: Path, limit: int | None) -> list[str]:
-    out: list[str] = []
-    with open(path, encoding="utf-8") as f:
-        for line in f:
-            obj = json.loads(line)
-            out.append(obj["query"])
-            if limit and len(out) >= limit:
-                break
-    return out
-
-
-def main() -> None:
-    ap = argparse.ArgumentParser(
-        description="DiskANN baseline on real NQ queries (search-only timing)"
-    )
-    ap.add_argument(
-        "--index-dir",
-        default="benchmarks/data/indices/diskann_rpj_wiki",
-        help="Directory containing DiskANN files",
-    )
-    ap.add_argument("--index-prefix", default="ann")
-    ap.add_argument("--queries-file", default="benchmarks/data/queries/nq_open.jsonl")
-    ap.add_argument("--num-queries", type=int, default=200)
-    ap.add_argument("--top-k", type=int, default=10)
-    ap.add_argument("--complexity", type=int, default=62)
-    ap.add_argument("--threads", type=int, default=1)
-    ap.add_argument("--beam-width", type=int, default=1)
-    ap.add_argument("--cache-mechanism", type=int, default=2)
-    ap.add_argument("--num-nodes-to-cache", type=int, default=0)
-    args = ap.parse_args()
-
-    index_dir = Path(args.index_dir).resolve()
-    if not index_dir.is_dir():
-        raise SystemExit(f"Index dir not found: {index_dir}")
-
-    qpath = Path(args.queries_file).resolve()
-    if not qpath.exists():
-        raise SystemExit(f"Queries file not found: {qpath}")
-
-    queries = load_queries(qpath, args.num_queries)
-    print(f"Loaded {len(queries)} queries from {qpath}")
-
-    # Compute embeddings once (exclude from timing)
-    from leann.api import compute_embeddings as _compute
-
-    embs = _compute(
-        queries,
-        model_name="facebook/contriever-msmarco",
-        mode="sentence-transformers",
-        use_server=False,
-    ).astype(np.float32)
-    if embs.ndim != 2:
-        raise SystemExit("Embedding compute failed or returned wrong shape")
-
-    # Build searcher
-    from leann_backend_diskann.diskann_backend import DiskannSearcher as _DiskannSearcher
-
-    index_prefix_path = str(index_dir / args.index_prefix)
-    searcher = _DiskannSearcher(
-        index_prefix_path,
-        num_threads=int(args.threads),
-        cache_mechanism=int(args.cache_mechanism),
-        num_nodes_to_cache=int(args.num_nodes_to_cache),
-    )
-
-    # Warmup (not timed)
-    _ = searcher.search(
-        embs[0:1],
-        top_k=args.top_k,
-        complexity=args.complexity,
-        beam_width=args.beam_width,
-        prune_ratio=0.0,
-        recompute_embeddings=False,
-        batch_recompute=False,
-        dedup_node_dis=False,
-    )
-
-    # Timed loop
-    times: list[float] = []
-    for i in range(embs.shape[0]):
-        t0 = time.time()
-        _ = searcher.search(
-            embs[i : i + 1],
-            top_k=args.top_k,
-            complexity=args.complexity,
-            beam_width=args.beam_width,
-            prune_ratio=0.0,
-            recompute_embeddings=False,
-            batch_recompute=False,
-            dedup_node_dis=False,
-        )
-        times.append(time.time() - t0)
-
-    times_sorted = sorted(times)
-    avg = float(sum(times) / len(times))
-    p50 = times_sorted[len(times) // 2]
-    p95 = times_sorted[max(0, int(len(times) * 0.95) - 1)]
-
-    print("\nDiskANN (NQ, search-only) Report")
-    print(f"  queries: {len(times)}")
-    print(
-        f"  k: {args.top_k}, complexity: {args.complexity}, beam_width: {args.beam_width}, threads: {args.threads}"
-    )
-    print(f"  avg per query: {avg:.6f} s")
-    print(f"  p50/p95: {p50:.6f}/{p95:.6f} s")
-    print(f"  QPS: {1.0 / avg:.2f}")
-
-
-if __name__ == "__main__":
-    main()
--- a/benchmarks/data/prompts_g5/prompt_dump_gpqa_hnsw.txt
+++ b/benchmarks/data/prompts_g5/prompt_dump_gpqa_hnsw.txt
--- a/benchmarks/data/prompts_g5/prompt_dump_hotpot_hnsw.txt
+++ b/benchmarks/data/prompts_g5/prompt_dump_hotpot_hnsw.txt
--- a/benchmarks/data/prompts_g5/prompt_dump_nq_hnsw.txt
+++ b/benchmarks/data/prompts_g5/prompt_dump_nq_hnsw.txt
--- a/benchmarks/data/prompts_g5/prompt_dump_trivia_hnsw.txt
+++ b/benchmarks/data/prompts_g5/prompt_dump_trivia_hnsw.txt
@@ -0,0 +1,484 @@
+=== Prompt Dump for TRIVIA + HNSW ===
+Total prompts: 50
+Showing first 20 prompts:
+
+==================================================
+PROMPT #1:
+==================================================
+Jason Lee also portrays David Seville in live action/CGI films starring Alvin and the Chipmunks, which use a combination of live-action acting and computer animation. While Ross Bagdasarian Jr. does not do any voices for the film series, the films are all produced in association with Bagdasarian Productions, which owns the rights to all of the characters. Portrayed by Filmography Films Television See also References Fictional characters introduced in 1958 Alter egos Alvin and the Chipmunks Fictional managers Fictional producers American male characters in televisionRoss Dickran Bagdasarian (born May 6, 1949) is an American actor, animator and producer, known for his work on the Alvin and the Chipmunks franchise. He is the son of the franchise's creator, Ross Bagdasarian. Early life Bagdasarian was born in Fresno, California, the son of Armenian-American parents Armenuhi Bagdasarian (née Kulhanjian) and Ross Bagdasarian (1919–1972). As a child, he worked with his father on The Alvin Show by helping edit and coordinate the soundtracks and falsetto voice-overs of the Chipmunks. Career Bagdasarian graduated from law school. He succeeded his father as president of Bagdasarian Productions in 1972 after the death of the elder Bagdasarian. The company had fallen into obscurity after significant success between 1958 and the late 1960s. Bagdasarian was also admitted to the California bar as an attorney in 1975. Under Bagdasarian's supervision, new Chipmunks records were created shortly after his marriage to Karman, including Chipmunk Punk. In 1981, the Chipmunks returned to television in the cartoon special A Chipmunk Christmas. Two years later, Ruby-Spears Productions' Alvin and the Chipmunks Saturday morning cartoon series debuted on NBC. Based on that series, a feature film, The Chipmunk Adventure was released in 1987. Bagdasarian voices Alvin, Simon, and Dave Seville, and Karman voices Theodore and the Chipettes (Brittany, Jeanette, and Eleanor). Bagdasarian and Karman hold tight creative and financial control over the Chipmunk franchise, reviewing each and every business contract in great detail. In the mid-90s, Bagdasarian bought out his brother's and sister's portions of the Chipmunk rights, to take complete control of the franchise.Alvin and the Chipmunks, originally David Seville and the Chipmunks or simply The Chipmunks, are an American animated virtual band and media franchise first created by Ross Bagdasarian for novelty records in 1958. The group consists of three singing animated anthropomorphic chipmunks named Alvin, Simon, and Theodore who are originally managed by their human adoptive father, David "Dave" Seville. Bagdasarian provided the group's voices by producing sped-up recordings of his own, a technique pioneered on the successful "Witch Doctor". Later in 1958, Bagdasarian released the similarly-engineered "The Chipmunk Song" for which he came up with the chipmunk characters and their human father, attributing the track to them. David Seville and the Chipmunks released several more records over the following decade until Bagdasarian's death in 1972. The franchise was revived in 1979 with the characters' voices provided by his son Ross Bagdasarian Jr. and the latter's wife Janice Karman. Through the successful franchise, the Chipmunks have become one of the most successful children's artists of all time. It has garnered two number-one singles on the Billboard Hot 100 and won five Grammy Awards, having four Top 10 albums on the Billboard 200 and three certified platinum albums. "The Chipmunk Song" became one of the best-selling singles of all time at 5 million physical copies sold. The Chipmunks were first depicted in animated form in The Alvin Show (1961). The characters have since featured in several television series and films, as well as other media. In 2019, The Chipmunks received a star on the Hollywood Walk of Fame.
+Think hard, but answer shortly and concisely. Only give direct answers to the questions. No additional explanations. Directly answer these questions:
+Q: Rita Coolidge sang the title song for which Bond film??
+A: Octopussy
+
+Q: Which Lloyd Webber musical premiered in the US on 10th December 1993??
+A: Sunset Boulevard
+
+Q: Who was the next British Prime Minister after Arthur Balfour??
+A: Campbell-Bannerman
+
+Q: Who had a 70s No 1 hit with Kiss You All Over??
+A: Exile
+
+Q: What claimed the life of singer Kathleen Ferrier??
+A: Cancer
+
+Q: Who was the man behind The Chipmunks?
+A: 
+==================================================
+
+==================================================
+PROMPT #2:
+==================================================
+and the drum set. Their film counterparts are Michelle and Eleni. Production history Broadway (2015-2019) Auditions began on January 19, 2015 for children ages nine through fifteen. Some recruiting was done through the School of Rock after-school educational program (which predated the film by several years) and open calls were held in New York at the Winter Garden, in Chicago and in Los Angeles. The production closed on January 20, 2019, after 1,309 performances. West End (2016–2020) On 7 December 2015, following the show's Broadway opening, it was announced by Andrew Lloyd Webber that the show would transfer to London's West End in autumn 2016, with the intention to open at the London Palladium. On 20 May 2016, the musical was confirmed at the Gillian Lynne Theatre instead of the Palladium with previews starting on 24 October 2016, opening night on 14 November 2016, and public booking opening on 25 May 2016. Lloyd Webber revealed that the production was able to open several months earlier than anticipated due to finding the child musician actors easily. Anna Louizos' scenery has been modified to fit the architecture of the Gillian Lynne Theatre from the traditional proscenium arch stage at Winter Garden Theatre. Changes include the removal of the pre-show curtain, the use of a revolving stage and action taking place in the aisles of the stalls. While the show remains to be set in America, the script has been adapted to include some minor references for a British audience. The original London cast includes David Fynn as DeweyThe Sound of Music, Camelot and Fiddler on the Roof played at the theatre in the early 1980s. In 1984, the interior was extensively modified by the introduction of a 'race track' that ran through the audience, for the show Starlight Express with performers on roller skates. The show premièred on 27 March, composed by Andrew Lloyd Webber and directed by Trevor Nunn and ran for 7,406 performances, over 18 years. With the removal of the 'tracks', the interior was extensively restored by architects Jaques Muir and Partners. This included the removal of 3,500 incandescent lamps that had become difficult to maintain and consumed a considerable amount of power. These were replaced by 88,000 low power LEDs specially designed for the theatre, creating the first auditorium completely lit in this way. Another Lloyd Webber production followed, Bombay Dreams premièred on 19 June 2002. It was created by A. R. Rahman with lyrics by Don Black and was directed by Steven Pimlott, closing after 1,500 performances on 13 June 2004. This was followed by the return to the West End of the Bee Gee's musical Saturday Night Fever on 6 July 2004, closing 22 October 2005 to tour. This was followed on 10 April 2006 by the jukebox musical Movin' Out, featuring the music of Billy Joel. This starred James Fox but ran for only two months. The Broadway musical Wicked received its London première at the venue on 27 September 2006 with a cast featuring Idina Menzel as Elphaba, Helen Dallimore as Glinda, Nigel Planer asand also starred comedian Tim Minchin as Judas Iscariot, former Spice Girl Melanie C as Mary Magdalene and BBC Radio 1 DJ Chris Moyles as King Herod. Tickets for most venues went on sale on 18 May 2012. In 2013, Lloyd Webber reunited with Christopher Hampton and Don Black on Stephen Ward the Musical. For his next project, a 2015 musical adaptation of the 2003 film School of Rock, auditions were held for children aged nine to fifteen in cooperation with the School of Rock music education program, which predated the film by several years. In April 2016, the English National Opera staged a revival of Sunset Boulevard at the London Coliseum. The limited run, semi-staged production directed by Lonny Price brought Glenn Close to reprise her star turn as "Norma Desmond", which was her first time performing the role in London; she had originated the role in Los Angeles in December 1993 and then on Broadway in November 1994 (which won her the 1995 Tony Award for Best Actress in a Musical). The 2016 London revival was so well-received that the production transferred to the Palace Theatre on Broadway in February 2017, making Lloyd Webber the first musical-theatre composer since 1953 to have four musicals running simultaneously on Broadway – a feat that his heroes Rodgers and Hammerstein had previously achieved. Lloyd Webber's memoir, Unmasked, was published in 2018. On 9 September 2018, Lloyd Webber, along with Tim Rice and John Legend each won an Emmy for Jesus Christ Superstar Live in Concert. With this
+Think hard, but answer shortly and concisely. Only give direct answers to the questions. No additional explanations. Directly answer these questions:
+Q: Who was the man behind The Chipmunks??
+A: David Seville
+
+Q: Rita Coolidge sang the title song for which Bond film??
+A: Octopussy
+
+Q: Who was the next British Prime Minister after Arthur Balfour??
+A: Campbell-Bannerman
+
+Q: Who had a 70s No 1 hit with Kiss You All Over??
+A: Exile
+
+Q: What claimed the life of singer Kathleen Ferrier??
+A: Cancer
+
+Q: Which Lloyd Webber musical premiered in the US on 10th December 1993?
+A: 
+==================================================
+
+==================================================
+PROMPT #3:
+==================================================
+Cabinet Louis Botha, Prime Minister of the Union of South Africa (1910–1919) Behind Churchill are: George Barnes, leader of the National Democratic and Labour Party Sir Robert Borden, Prime Minister of Canada (1911–1920) To their right are: Arthur Balfour, 1st Earl of Balfour, former Prime Minister of the United Kingdom (1902–1905); First Lord of the Admiralty (1915–1916) and Foreign Secretary (1916–1919) (standing adlocutio in a black suit) H. H. Asquith, 1st Earl of Oxford and Asquith, Prime Minister of the United Kingdom (1908–1916) (sitting in front) Sir Eric Geddes, First Lord of the Admiralty (1917–1919) (behind, cleanshaven) Bonar Law, Leader of the Opposition (United Kingdom) (1911–1915), Secretary of State for the Colonies (1915–1916), Chancellor of the Exchequer (1916–1919) (later Prime Minister of the United Kingdom, 1922–1923) (dark moustache) Edward Morris, 1st Baron Morris, Prime Minister of Newfoundland (1909–1917) (white moustache, in the shadows) Herbert Kitchener, 1st Earl Kitchener, Secretary of State for War (1914–1916) (in the shadows) Bailey decided that the painting should include British and Dominion civilian leaders in office at the beginning and the end of the First World War. It includes Prime Ministers of Australia, Canada, Newfoundland, and New Zealand, and the Prime Ministers, Foreign Secretaries, Secretaries of War, and First Lords of the Admiralty of the United Kingdom, together with two leaders of the British Conservative and Labour parties. The Maharaja of Bikaner, a member of the Imperial War Cabinet and the Indian delegate to the Versailles Peace Conference, stands to the left next to Botha, both in military uniform. Kitchener standsArthur James Balfour, 1st Earl of Balfour, (, ; 25 July 184819 March 1930), also known as Lord Balfour, was a British Conservative statesman who served as Prime Minister of the United Kingdom from 1902 to 1905. As foreign secretary in the Lloyd George ministry, he issued the Balfour Declaration of 1917 on behalf of the cabinet, which supported a "home for the Jewish people" in Palestine. Entering Parliament in 1874, Balfour achieved prominence as Chief Secretary for Ireland, in which position he suppressed agrarian unrest whilst taking measures against absentee landlords. He opposed Irish Home Rule, saying there could be no half-way house between Ireland remaining within the United Kingdom or becoming independent. From 1891 he led the Conservative Party in the House of Commons, serving under his uncle, Lord Salisbury, whose government won large majorities in 1895 and 1900. An esteemed debater, he was bored by the mundane tasks of party management. In July 1902, he succeeded his uncle as prime minister. In domestic policy he passed the Land Purchase (Ireland) Act 1903, which bought out most of the Anglo-Irish land owners. The Education Act 1902 had a major long-term impact in modernising the school system in England and Wales and provided financial support for schools operated by the Church of England and by the Catholic Church. Nonconformists were outraged and mobilised their voters, but were unable to reverse it. In foreign and defence policy, he oversaw reform of British defence policy and supported Jackie Fisher's naval innovations. He secured the Entente Cordiale withthe county of Haddington. In October 1922 he, with most of the Conservative leadership, resigned with Lloyd George's government following the Carlton Club meeting, a Conservative back-bench revolt against continuance of the coalition. Bonar Law became prime minister. Like many Coalition leaders, he did not hold office in the Conservative governments of 1922–1924, but as an elder statesman, he was consulted by the King in the choice of Stanley Baldwin as Bonar Law's successor as Conservative leader in May 1923. His advice was strongly in favour of Baldwin, ostensibly due to Baldwin's being an MP but in reality motivated by his personal dislike of Curzon. Later that evening, he met a mutual friend who asked 'Will dear George be chosen?' to which he replied with 'feline Balfourian satisfaction,' 'No, dear George will not.' His hostess replied, 'Oh, I am so sorry to hear that. He will be terribly disappointed.' Balfour retorted, 'Oh, I don't know. After all, even if he has lost the hope of glory he still possesses the means of Grace.' Balfour was not initially included in Baldwin's second government in 1924, but in 1925, he returned to the Cabinet, in place of the late Lord Curzon as Lord President of the Council, until the government ended in 1929. With 28 years of government service, Balfour had one of the longest ministerial careers in modern British politics, second only to Winston Churchill . Last years Lord Balfour had generally good health until 1928 and remained until then a regular tennis player. Four years previously
+Think hard, but answer shortly and concisely. Only give direct answers to the questions. No additional explanations. Directly answer these questions:
+Q: Who was the man behind The Chipmunks??
+A: David Seville
+
+Q: Which Lloyd Webber musical premiered in the US on 10th December 1993??
+A: Sunset Boulevard
+
+Q: Rita Coolidge sang the title song for which Bond film??
+A: Octopussy
+
+Q: Who had a 70s No 1 hit with Kiss You All Over??
+A: Exile
+
+Q: What claimed the life of singer Kathleen Ferrier??
+A: Cancer
+
+Q: Who was the next British Prime Minister after Arthur Balfour?
+A: 
+==================================================
+
+==================================================
+PROMPT #4:
+==================================================
+classic '70s pop song." In 1992, Mexican trio Pandora released a cover version titled "Pierdo el Control" on their album Ilegal. In 1979 Ginger Rogers sang this song on The Love Boat in the episode "Critical Success / The Love Lamp Is Lit / Take My Boyfriend, Please / Rent a Family / The Man in Her Life: Parts 1 & 2" In 2001, the film Get Over It featured a dance to this song at the beginning by some of the cast. References 1973 songs 1975 debut singles Songs written by Neil Sedaka Songs with lyrics by Howard Greenfield Neil Sedaka songs Captain & Tennille songs Andy Williams songs Number-one singles in Australia Billboard Hot 100 number-one singles Cashbox number-one singles RPM Top Singles number-one singles Grammy Award for Record of the Year A&M Records singles Juno Award for Best Selling Single singlesMusic Week rated the song four out of five, concluding, "A third huge hit for the boys." Tracklisting CD single "Kiss You All Over" (Radio Edit) - 4:31 "Kiss You All Over" (Club Mix) - 5:53 "Bonita" (Radio Edit) - 3:54 "Bonita" (Club Mix) - 7:08 Charts Release history References 1978 songs 1978 singles 1997 singles 1998 singles Billboard Hot 100 number-one singles Cashbox number-one singles Exile (American band) songs Number-one singles in New Zealand Number-one singles in South Africa Number-one singles in Australia Songs written by Mike Chapman Song recordings produced by Frank Farian Song recordings produced by Mike Chapman Songs written by Nicky Chinn RAK Records singles Curb Records singles Hilltak Records singles Warner Records singles Arista Records singles No Mercy (pop band) songs Songs about kissing Phyllis Hyman songs"Kiss You All Over" is a 1978 song performed by American group Exile, written by Mike Chapman and Nicky Chinn. It was included on the band's third album, Mixed Emotions (1978), and featured lead vocalist Jimmy Stokley and guitarist J.P. Pennington on vocals. On the American Top 40 broadcast of May 26, 1979, Casey Kasem reported that Chapman stated his source of inspiration for "Kiss You All Over" was "It's Ecstasy When You Lay Down Next to Me" by Barry White. The song was a number one single in the United States, but proved to be Exile's only big hit in the pop market (they would later have great success on the country music charts). It held the number one spot on the Billboard Hot 100 for four weeks (starting September 30), and Billboard ranked it as the No. 5 song for 1978. The track also reached number-one in at least three other nations. In the United Kingdom, the song was released on Mickie Most's RAK Records, and peaked at number 6 on the UK Singles Chart. The strings are played with a synthesizer in a backing track. In 2010, Billboard ranked the song tenth on its list of "The 50 Sexiest Songs of All Time". Lead vocalist on the number, Stokley was ousted from the band in 1979, his health declining thereafter until he died at the age of 41 in 1985. After the success of soft rock singles from the albums Mixed Emotions and All There Is, the band moved into country music in
+Think hard, but answer shortly and concisely. Only give direct answers to the questions. No additional explanations. Directly answer these questions:
+Q: Who was the man behind The Chipmunks??
+A: David Seville
+
+Q: Which Lloyd Webber musical premiered in the US on 10th December 1993??
+A: Sunset Boulevard
+
+Q: Who was the next British Prime Minister after Arthur Balfour??
+A: Campbell-Bannerman
+
+Q: Rita Coolidge sang the title song for which Bond film??
+A: Octopussy
+
+Q: What claimed the life of singer Kathleen Ferrier??
+A: Cancer
+
+Q: Who had a 70s No 1 hit with Kiss You All Over?
+A: 
+==================================================
+
+==================================================
+PROMPT #5:
+==================================================
+21st century world: "We dislike low-lying voices, for one thing— contraltos now sound freakish and headmistressy, and even the majority of mezzo-sopranos should more accurately be categorised as almost-sopranos". However, she was "a singer of, and for, her time — a time of grief and weariness, national self-respect and a belief in human nobility". In this context "her artistry stands upright, austere, unfussy, fundamental and sincere". Shortly after Ferrier's death an appeal was launched by Barbirolli, Walter, Myra Hess and others, to establish a cancer research fund in Ferrier's name. Donations were received from all over the world. To publicise the fund a special concert was given at the Royal Festival Hall on 7 May 1954, at which Barbirolli and Walter shared the conducting duties without payment. Among the items was a rendition of Purcell's When I am laid in earth, which Ferrier had often sung; on this occasion the vocal part was played by a solo cor anglais. The Kathleen Ferrier Cancer Research Fund helped establish the Kathleen Ferrier Chair of Clinical Oncology at University College Hospital, in 1984. , it was continuing to fund oncology research. As the result of a separate appeal, augmented by the sales proceeds of a memoir edited by Neville Cardus, the Kathleen Ferrier Memorial Scholarship Fund was created to encourage young British and Commonwealth singers of either sex. The Fund, which has operated from 1956 under the auspices of the Royal Philharmonic Society, initially provided an annual award covering the cost of a year's study to a single prizewinner.In the course of her professional life the English contralto Kathleen Ferrier made a large number of recordings. In the summer of 1944 she signed a contract with Columbia, which lasted until February 1946. She then transferred to Decca, and remained with them until her death in October 1953. Apart from her studio recordings, many of her live performances and broadcast recitals were recorded, sometimes privately. Some of these were later issued as commercial recordings; others are held by individuals or in the archives of broadcasting companies. The following list is neither up to date nor entirely accurate, particularly in regard to a CD issue, entitled 'Kathleen Ferrier Remembered', released in June 2017, on SOMM264, comprising 26 tracks, 19 of which have never previously been issued. Most of these 19 are not listed below. They include Lieder by Schubert, Brahms, Wolf and Mahler and songs by Stanford, Parry, Jacobson and Rubbra, all taken from BBC broadcasts between 1947 and 1952. In April 2019, a recording of Ferrier singing in Bach's 'Magnificat' during the 1950 Vienna International Bach Festival was issued for the first time. The CD catalogue number is SOMM Ariadne 5004 and it also features Irmgard Seefried and Friedl Riegler (sopranos), Hugo Meyer-Welfing (tenor) and Otto Edelmann (bass). The Vienna Philharmonic Orchestra and Chorus of the Vienna State Opera are conducted by Volkmar Andreae. The existence of this recording was not known until a vinyl disc was offered for sale on an internet auction site in 2018. In superb recorded sound, this discovery is aKathleen Mary Ferrier, CBE (22 April 19128 October 1953) was an English contralto singer who achieved an international reputation as a stage, concert and recording artist, with a repertoire extending from folksong and popular ballads to the classical works of Bach, Brahms, Mahler and Elgar. Her death from cancer, at the height of her fame, was a shock to the musical world and particularly to the general public, which was kept in ignorance of the nature of her illness until after her death. The daughter of a Lancashire village schoolmaster, Ferrier showed early talent as a pianist, and won numerous amateur piano competitions while working as a telephonist with the General Post Office. She did not take up singing seriously until 1937, when after winning a prestigious singing competition at the Carlisle Festival she began to receive offers of professional engagements as a vocalist. Thereafter she took singing lessons, first with J.E. Hutchinson and later with Roy Henderson. After the outbreak of the Second World War Ferrier was recruited by the Council for the Encouragement of Music and the Arts (CEMA), and in the following years sang at concerts and recitals throughout the UK. In 1942 her career was boosted when she met the conductor Malcolm Sargent, who recommended her to the influential Ibbs and Tillett concert management agency. She became a regular performer at leading London and provincial venues, and made numerous BBC radio broadcasts. In 1946, Ferrier made her stage debut, in the Glyndebourne Festival premiere of Benjamin Britten's opera The Rape of Lucretia.
+Think hard, but answer shortly and concisely. Only give direct answers to the questions. No additional explanations. Directly answer these questions:
+Q: Who was the man behind The Chipmunks??
+A: David Seville
+
+Q: Which Lloyd Webber musical premiered in the US on 10th December 1993??
+A: Sunset Boulevard
+
+Q: Who was the next British Prime Minister after Arthur Balfour??
+A: Campbell-Bannerman
+
+Q: Who had a 70s No 1 hit with Kiss You All Over??
+A: Exile
+
+Q: Rita Coolidge sang the title song for which Bond film??
+A: Octopussy
+
+Q: What claimed the life of singer Kathleen Ferrier?
+A: 
+==================================================
+
+==================================================
+PROMPT #6:
+==================================================
+"You Only Live Twice", performed by Nancy Sinatra, is the theme song to the 1967 James Bond film of the same name. The music was by veteran Bond film composer John Barry, with lyrics by Leslie Bricusse. The song is widely recognized for its striking opening bars, featuring a simple 2-bar theme in the high octaves of the violins and lush harmonies from French horns. It is considered by some to be among the best James Bond theme songs, and has become one of Nancy Sinatra's best known hits. Shortly after Barry's production, Sinatra's producer Lee Hazlewood released a more guitar-based single version. The song has been covered by many artists including Coldplay, Soft Cell, Björk and Shirley Bassey. In 1998, Robbie Williams re-recorded portions of the song (including the opening strings) for use in his UK number-one single "Millennium". Background James Bond veteran John Barry returned to the franchise to produce the score. The lyrics were by Leslie Bricusse, who had previously cowritten the lyrics for the theme to Goldfinger. An initial version of the song was performed by Julie Rogers and recorded with a 50 or 60 piece orchestra at CTS Studios. However, this version was not used since Barry decided to re-write and re-record the song: "It was usually the producers that said 'this isn't working, there's a certain something that it needed'. If that energy wasn't there, if that mysterioso kind of thing wasn't there, then it wasn't going to work for the movie." The Rogers song shares only two lines withBassey belting out the fantastic title song." He added that the remastered edition's sound quality was "impeccable". Chart positions Track listing Credits Project manager: Herb Agner Creative director: Michelle Azzopardi Composer, conductor, primary artist: John Barry Primary artist, vocals: Shirley Bassey Liner notes: Jeff Bond Composer, lyricist: Leslie Bricusse Project manager: Wendy Brueder Producer, reissue producer: Frank Collura Remastering: Bob Fisher Guitar, soloist: Vic Flick Art direction, design: Peter Grant Orchestra contractor: Sid Margo Lyricist: Anthony Newley A&R: Gregg Ogorzelec Engineer: John Richards Saxophone, soloist: John Scott Source: Aftermath Following the success of her performance on the title track, Shirley Bassey sang the title songs for two later Bond films, Diamonds Are Forever and Moonraker. John Barry used the Goldfinger theme on his 1965 John Barry Plays Goldfinger album that featured Robert Brownjohn artwork. References Footnotes Citations Bibliography Soundtrack albums from James Bond films Soundtrack 1964 soundtrack albums EMI Records soundtracks John Barry (composer) soundtracksJames Bond (Roger Moore), and the title evidently refers to the key aerial sequences featured in the movie. Prior to Rita Coolidge being assigned the Octopussy theme, Mari Wilson was a contender, a British singer whose retro-image evoked the mid-'60s when the Bond series originated; but Wilson's lack of a US-profile led to a negative decision. In January 1983, the producer of Octopussy: Cubby Broccoli, stated that he hoped to have current hitmaker Laura Branigan sing the movie's theme song, an artist choice which both Barry and Rice have stated would have pleased them. However, on March 29, 1983 Rita Coolidge was revealed as the singer, a seemingly surprising choice in that Coolidge's career peak had occurred some six years previously. Coolidge recalls that Barbara Broccoli, daughter of Cubby Broccoli and herself the assistant director of Octopussy, was a fan of Coolidge and made a point of playing Coolidge records around her father until "one day [he said], "Who is that? That's the voice I want for the movie." Rice still had to complete his contribution as the singer arrived in the studio, with Coolidge stating that "we were waiting for the lyrics as the instrumental track had already been done." The chorus of "All Time High" features a lyric similar to that of Coolidge's #2 hit "(Your Love Has Lifted Me) Higher and Higher" whose lyric "When you wrap your loving arms around me I can stand up and face the world again" is echoed by the "All Time High" lyric "We'll take on the
+Think hard, but answer shortly and concisely. Only give direct answers to the questions. No additional explanations. Directly answer these questions:
+Q: Who was the man behind The Chipmunks??
+A: David Seville
+
+Q: Which Lloyd Webber musical premiered in the US on 10th December 1993??
+A: Sunset Boulevard
+
+Q: Who was the next British Prime Minister after Arthur Balfour??
+A: Campbell-Bannerman
+
+Q: Who had a 70s No 1 hit with Kiss You All Over??
+A: Exile
+
+Q: What claimed the life of singer Kathleen Ferrier??
+A: Cancer
+
+Q: Rita Coolidge sang the title song for which Bond film?
+A: 
+==================================================
+
+==================================================
+PROMPT #7:
+==================================================
+which allowed the first legal beer sales since the beginning of Prohibition on January 16, 1920. In 1933 state conventions ratified the Twenty-first Amendment, which repealed Prohibition. The Amendment was fully ratified on December 5, 1933. Federal laws enforcing Prohibition were then repealed. Dry counties Following repeal some states continued prohibition within their own jurisdictions. Almost two-thirds of the states adopted some form of local option which enabled residents in political subdivisions to vote for or against local prohibition. For a time, 38 percent of Americans lived in areas with Prohibition. By 1966, however, all states had repealed their statewide prohibition laws, with Mississippi the last state to do so. Notes Sources Walker, Robert S. and Samuel C. Patterson, Oklahoma Goes Wet: The Repeal of Prohibiton, Eagleton Institute, Rutgers University, (1961). External links Repeal Day is December Fifth See more related images by selecting the "Alcohol" subject at the Persuasive Cartography, The PJ Mode Collection, Cornell University Library Prohibition in the United States Economic history of the United States 1933 in the United States Articles containing video clipsimportation of alcoholic beverages in the United States. The resolution was sent to the states for ratification and became the Eighteenth Amendment to the U.S. Constitution. On January 8, 1918, Mississippi became the first state to ratify the amendment and on January 16, 1919, Nebraska became the 36th state to do so, securing its passage with the required three-fourths of the states. By the end of February 1919, only three states remained as hold-outs to ratification: New Jersey, Connecticut and Rhode Island. The National Prohibition Act, also known as the Volstead Act, was enacted on October 18, 1919. Prohibition in the United States went into effect on January 17, 1920. Nationwide prohibition was repealed in 1933 with the passage of the Twenty-first Amendment on February 20 and its ratification on December 5. List of formerly dry states This table lists the effective dates each state went dry and any dates of repeal that do not coincide with the end of national prohibition in 1933. See also Dry county Alcoholic beverage control state List of alcohol laws of the United States by state Notes Alcohol law in the United States Prohibition in the United StatesAugust 19. PPS functionals were completed August 21. GATV 5006 was then transferred to complex 14 for mating with the Atlas. July 27, 1966 (Wednesday) Following the announcement of his austerity programme, British Prime Minister Harold Wilson survived a vote of censure in the House of Commons, as members of his Labour Party (with an 88-seat majority) supported him. The final result was 246 votes in favor, and 325 against. On the same day, the nation's chief labor union, the Trades Union Congress, voted 20 to 12 in support of a resolution pledging to halt strikes that had been threatened during the six-month freeze against raising wages. For the first time in 58 years, liquor was legally served in Mississippi, the last of the United States to have repealed its prohibition laws. Effective July 1, individual local governments were allowed to hold referendum elections on whether to allow the sale of liquor at state-approved resorts, and Harrison County voters had endorsed the measure. At 6:55 p.m., after police cars escorted a liquor delivery truck into Biloxi. The first drink in the state was poured at the Broadwater Beach Hotel, and Louis Cobb, the first legal bartender in Mississippi, sold a glass of scotch whiskey to hotel manager T.M. Dorsett. Biloxi Mayor Dan Guice then cut the ribbon to open the entrance to the hotel's bar.Died: Brenda Sue Brown, 11, was beaten to death after walking with her sister to summer school in Shelby, North Carolina. Police were unable to charge a suspect with the crime, until
+Think hard, but answer shortly and concisely. Only give direct answers to the questions. No additional explanations. Directly answer these questions:
+Q: Who was the man behind The Chipmunks??
+A: David Seville
+
+Q: Which Lloyd Webber musical premiered in the US on 10th December 1993??
+A: Sunset Boulevard
+
+Q: Who was the next British Prime Minister after Arthur Balfour??
+A: Campbell-Bannerman
+
+Q: Who had a 70s No 1 hit with Kiss You All Over??
+A: Exile
+
+Q: What claimed the life of singer Kathleen Ferrier??
+A: Cancer
+
+Q: What was the last US state to reintroduce alcohol after prohibition?
+A: 
+==================================================
+
+==================================================
+PROMPT #8:
+==================================================
+to New York City for work in summer stock theatre shortly before winning a supporting role in MGM's These Glamour Girls (1939) opposite Lana Turner and Lew Ayres. The role of Betty was said to have been written especially with Hunt in mind. Other roles in major studio productions soon followed, including supporting roles as Mary Bennet in MGM's version of Pride and Prejudice (1940) with Laurence Olivier, and as Martha Scott's surrogate child Hope Thompson in Cheers for Miss Bishop (1941). Years at MGM In 1941, Hunt signed a contract with MGM, where she remained for the next six years. While filming Blossoms in the Dust, film director Mervyn LeRoy lauded Hunt for her heartfelt and genuine acting ability. During this period she had starring roles in 21 films, including The Penalty (1941) opposite Lionel Barrymore, Panama Hattie (1942) opposite Ann Sothern and Red Skelton, and the war drama Pilot No. 5 (1943) in which she was cast as the love interest of Franchot Tone, and The Valley of Decision (1945). In 1944 she polled seventh in a list by exhibitors of "Stars of Tomorrow". She previously did a screen test to play Melanie Hamilton in Gone with the Wind (1939) and was told by David O. Selznick she would play the role, but to "keep it a secret for now." Three days later, it was announced that Olivia de Havilland was cast. In 1944, she appeared in None Shall Escape, a film that is now regarded as the first about the Holocaust. She playedMiss America 1941, the 15th Miss America pageant, was held at the Boardwalk Hall in Atlantic City, New Jersey on September 6, 1941. Shortly after the crowning of Miss California, Rosemary LaPlanche, who had been first runner-up in 1940, the pageant committee adopted this rule: "No contestant can compete in Atlantic City for the title of Miss America more than once", thus eliminating future state winners with more than one attempt at the national title. LaPlanche became a film actress, as did her sister, Louise LaPlanche. 1941 was also the first year that the special award, “Miss Congeniality” was created. It went to Mifaunwy Shunatona, a member of the Otoe and Pawnee tribes — she was also the first American Indian contestant in the pageant’s history. Results Awards Preliminary awards Other awards Contestants References Secondary sources External links Miss America official website 1941 1941 in the United States 1941 in New Jersey September 1941 events Events in Atlantic City, New JerseyMiss America 1942, the 16th Miss America pageant, was held at the Warner Theater in Atlantic City, New Jersey on September 12, 1942. Miss Texas, Jo-Carroll Dennison won the title after winning the swimsuit and talent categories. She was the first Miss Texas to win the Miss America title. Dennison became an actress and had roles in films such as Winged Victory. She was married at one time to comedian Phil Silvers. Results Awards Preliminary awards Other awards Contestants References Secondary sources External links Miss America (1942) 1942 1942 in the United States 1942 in New Jersey September 1942 events Events in Atlantic City, New Jersey
+Think hard, but answer shortly and concisely. Only give direct answers to the questions. No additional explanations. Directly answer these questions:
+Q: Who was the man behind The Chipmunks??
+A: David Seville
+
+Q: Which Lloyd Webber musical premiered in the US on 10th December 1993??
+A: Sunset Boulevard
+
+Q: Who was the next British Prime Minister after Arthur Balfour??
+A: Campbell-Bannerman
+
+Q: Who had a 70s No 1 hit with Kiss You All Over??
+A: Exile
+
+Q: What claimed the life of singer Kathleen Ferrier??
+A: Cancer
+
+Q: Which actress was voted Miss Greenwich Village in 1942?
+A: 
+==================================================
+
+==================================================
+PROMPT #9:
+==================================================
+De Tokyo Stock Price Index (Japans: 東証株価指数) of TOPIX is een belangrijke aandelenindex van de Tokyo Stock Exchange. Berekening In deze index zijn alle bedrijven opgenomen die op de beurs van Tokio staan genoteerd in de First Section. Dit zijn de grootste en meest liquide aandelen die op de beurs worden verhandeld. Tot medio 2006 werd het gewicht van de individuele bedrijven in de index bepaald op basis van de marktkapitalisatie, hierna wordt ook de free float in de berekening meegenomen. Het effect van deze verandering was significant, daar veel Japanse bedrijven aandelen houden in andere Japanse bedrijven, ook wel bekend als crossholdings, om daarmee de langdurige zakenrelatie te onderstrepen. Deze belangen worden voor lange tijd gehouden en worden niet tot de free float gerekend. De index heeft 4 januari 1968 als startdatum, maar ging op 1 juli 1969 daadwerkelijk van start. Een andere belangrijke beursindex in Japan is de Nikkei 225. In deze index zijn 225 bedrijven opgenomen en dit is een prijsgewogen index. Samenstelling Eind maart 2021 bestond de index uit 2187 aandelen. Door het grote aantal aandelen is het gewicht van de individuele namen zeer klein. De top 10 aandelen hebben een gezamenlijk gewicht in de index van slechts 18,4% en de lijst zag er als volgt uit, met de gewichten tussen de haakjes: De belangrijkste drie sectoren zijn: elektronische apparatuur, informatie technologie en chemie. Deze drie vertegenwoordigen tezamen zo'n 34% van de index, waarvan de sector elektronische apparatuur het grootst is met een gewicht van 17,5%. Koershistorie De hoogste stand van deTOPIX steht für Tōkyō Stock Price Index (jap. , Tōshō kabuka shisū) und ist neben dem Nikkei 225 ein Kursindex der Tokioter Börse. Berechnet wird der TOPIX seit dem 1. Juli 1969. Die Index-Basis liegt bei 100 Punkten per 4. Januar 1968. Er enthält alle japanischen Aktien, welche im amtlichen Handel zugelassen sind. Die Gewichtung der einzelnen Unternehmen im Index erfolgt anhand der Marktkapitalisierung. Gegenwärtig (8. September 2021) setzt sich der Index aus 2.189 Aktien zusammen. Wegen dieser hohen Zahl an vertretenen Unternehmen wird der TOPIX als aussagekräftiger für den Zustand der japanischen Wirtschaft angesehen als der Nikkei 225. Weblinks Beschreibung des TOPIX (engl.) TOPIX in Echtzeit Jährliche Entwicklung des TOPIX seit 1949 (Daten vor 1969 – dem Einführungsjahr des TOPIX – sind rückgerechnet; XLS-Format, 31,5 KB; abgerufen am 12. Oktober 2017) Einzelnachweise Aktienindex Wirtschaft (Japan) Abkürzung, commonly known as TOPIX, along with the Nikkei 225, is an important stock market index for the Tokyo Stock Exchange (TSE) in Japan, tracking all domestic companies of the exchange's Prime market division. It is calculated and published by the TSE. , there were 1,669 companies listed on the First Section of the TSE, and the market value for the index was ¥197.4 trillion. The index transitioned from a system where a company's weighting is based on the total number of shares outstanding to a weighting based on the number of shares available for trading (called the free float). This transition took place in three phases starting in October 2005 and was completed in June 2006. Although the change is a technicality, it had a significant effect on the weighting of many companies in the index, because many companies in Japan hold a significant number of shares of their business partners as a part of intricate business alliances, and such shares are no longer included in calculating the weight of companies in the index. The TOPIX index is traded as a future on the Osaka Exchange under the ticker symbol JTPX. The CQG contract specifications for the TOPIX Index are listed below. TSE currently calculates and distributes TOPIX every second and further plans to launch a new High-Speed Index dissemination service provided at the millisecond level starting from February 28, 2011. History of TOPIX 1969-07-01 TSE to begin calculating and publishing “TOPIX” and “TOPIX Sector Indices” 1969-08-18 TSE to begin calculating and publishing “Tokyo Stock
+Think hard, but answer shortly and concisely. Only give direct answers to the questions. No additional explanations. Directly answer these questions:
+Q: Who was the man behind The Chipmunks??
+A: David Seville
+
+Q: Which Lloyd Webber musical premiered in the US on 10th December 1993??
+A: Sunset Boulevard
+
+Q: Who was the next British Prime Minister after Arthur Balfour??
+A: Campbell-Bannerman
+
+Q: Who had a 70s No 1 hit with Kiss You All Over??
+A: Exile
+
+Q: What claimed the life of singer Kathleen Ferrier??
+A: Cancer
+
+Q: What is the Japanese share index called?
+A: 
+==================================================
+
+==================================================
+PROMPT #10:
+==================================================
+Man in the Music: The Creative Life and Work of Michael Jackson is a non-fiction book written by Joseph Vogel, published in June 2011 by the Sterling Publishing. Reception Man in the Music: The Creative Life and Work of Michael Jackson, was described by the Associated Press as "a fascinating read and really a must have for any fan of Jackson." Filmmaker Spike Lee characterized it as having "brilliantly cracked the DNA, the code, the artistry of Michael Joseph Jackson." References Works about Michael Jackson 2011 non-fiction books Sterling Publishing booksMoonwalk is a 1988 autobiography written by American recording artist Michael Jackson. The book was first published by Doubleday on February 1, 1988, five months after the release of Jackson's 1987 Bad album, and named after Jackson's signature dance move, the moonwalk. The book contains a foreword by Jacqueline Onassis. It reached number one on the New York Times Best Seller list. The book was reissued by Doubleday on October 13, 2009, following Jackson's death on June 25, 2009. Production Jacqueline Onassis, who was an editor at Doubleday, secured the book deal and paid Jackson a $300,000 advance. As part of the deal Jackson wanted Onassis to write a foreword, which she initially refused not wanting her name on any books she worked on but agreed to three paragraphs. She also edited the book. The first manuscript of the book was written by Robert Hilburn and was refused by the publishers, Doubleday, because it lacked "juicy details". A second manuscript was written by Stephen Davis, which Jackson drastically edited. Jackson finally decided to write the book himself, with help from Shaye Areheart. Due to the public interest in Jackson, Moonwalk was prepared for publication in secret. Relatives of Doubleday employees were hired as couriers, to deliver portions of the book from the company's head office in Manhattan to the printing plant in Fairfield, Pennsylvania. At the printing plant, the book was given the code name "Neil Armstrong", after the first "moonwalker". Narrative Dedicated to Fred Astaire, the book discusses Jackson's show business friends, girlfriends and hisMichael Jackson: Unauthorized in a 1994 biography of the late pop star Michael Jackson, written by celebrity biographer Christopher Andersen. Development According to Andersen, work started on the book in early 1991 when he received a call from a fellow journalist, who told him that two workers at Jackson's Neverland Ranch allegedly witnessed Jackson fondling a young celebrity. Andersen tried to interview Jackson several times, but was turned down. When Michael was publicly accused of child molestation in 1993, Andersen was told that he was under surveillance from investigators. Reception The book was largely overlooked by the public. Dana Kennedy of Entertainment Weekly felt that, with its "killer material", Anderson "probably could have retired from the celebrity-bio grind for good" had it been released five years before. People magazine found it to be a "sad book", considering its dark revelations about Jackson's behaviour. References 1994 non-fiction books Unauthorized biographies Works about the Michael Jackson sexual abuse allegations Biographies about musicians
+Think hard, but answer shortly and concisely. Only give direct answers to the questions. No additional explanations. Directly answer these questions:
+Q: Who was the man behind The Chipmunks??
+A: David Seville
+
+Q: Which Lloyd Webber musical premiered in the US on 10th December 1993??
+A: Sunset Boulevard
+
+Q: Who was the next British Prime Minister after Arthur Balfour??
+A: Campbell-Bannerman
+
+Q: Who had a 70s No 1 hit with Kiss You All Over??
+A: Exile
+
+Q: What claimed the life of singer Kathleen Ferrier??
+A: Cancer
+
+Q: What was the name of Michael Jackson's autobiography written in 1988?
+A: 
+==================================================
+
+==================================================
+PROMPT #11:
+==================================================
+including popular titles by Sérgio Mendes and Herb Alpert were released with this audio process starting in September 1968. Other record labels soon followed suit, and an estimated 10% of all stereophonic albums released during the late 1960s and early 1970s employed the system. Other labels known to have used the system include Warner Bros. Records and Reprise Records. One of the biggest selling albums using the process is The Association's Greatest Hits, released in 1968. This recording has sold more than 2 million copies in the United States. The process was also used on the 1968 Frank Sinatra album Cycles as well as on most of the studio recordings on Wheels of Fire by Cream. Early 1968 copies of Neil Young's self-titled debut album also used the system. Use of Haeco-CSG in promotional recordings for radio The original intention of using Haeco-CSG on commercial LP releases was rather short lived, however, use of the process continued well into the mid-1970s on promotional records sent to radio stations. Many commercial FM Rock stations did not transition from mono to stereo broadcasting until the mid to late 1970s. AM Pop music stations continued to broadcast in mono, as AM stereo broadcasting was not introduced until 1982 and was never widely adopted. Many promotional singles and some commercial singles from the Warner/Reprise/Atlantic label group from this era had "CSG Mono Process" or "CSG Process" printed on the labels. Artists included Frank Sinatra, Gordon Lightfoot, James Taylor, Seals and Crofts. Warner subsidiary labels such as Atlantic issued a serieswas introduced to the public on December 13, 1957, at the Times Auditorium in New York City. 500 copies of this initial demonstration record were pressed. On December 16, 1957, Frey advertised in the trade magazine Billboard that he would send a free copy to anyone in the industry who wrote to him on company letterhead. Frey became known as "Mr. Stereo" during that era. Stereophonic sound was not entirely new to the public. In 1952 sound engineer Emory Cook developed a "Binaural" disk that used two separate grooves and playback needles to produce stereophonic sound; the following year he had a catalog of about 25 disks available for audiophiles. Multi-channel sound was integral to the widescreen motion picture processes Cinerama (1952) and CinemaScope (1953). Stereophonic audio tapes had been commercially available to audiophiles, although expensive, since the early-1950s. After the release of the Audio Fidelity demonstration disks, the other spur to the popularity of stereo disks was the reduction in price of a stereo magnetic cartridge, for playing the disks, from $250 to $29.95 in June 1958. The first four stereo discs available to the general public were released by Audio Fidelity in March, 1958--Johnny Puleo and his Harmonica Gang Volume 1 (AFSD 5830), Railroad - Sounds of a Vanishing Era (AFSD 5843), Lionel - Lionel Hampton and his Orchestra (AFSD 5849) and Marching Along with the Dukes of Dixieland Volume 3 (AFSD 5851). By the end of March the company had four more stereo LPs available. In the summer of 1958, Audio Fidelity recordedin 1957, with his Essex Records office manager George Phillips, he founded Somerset Records and Somerset Stereo Fidelity Records budget albums. His greatest claim to fame was selling large amounts of cheaply priced albums, with Somerset claiming to have manufactured the first stereo budget albums. The name of Somerset high fidelity albums was suggested by Miller International's West Coast distributor, Jimmy Warren, with the name of Stereo Fidelity (stereo albums) thought of by Wally Hill to capitalize on the public's interest in both high fidelity and stereophonic sound. The economy came from Miller starting his own record factory in Swarthmore, Pennsylvania, using public domain music and non union musicians from outside the United States to record cover versions of hit songs of the time. Many original tunes were written by Monty Kelly, Robert Lowden, and Joseph Kuhn with the music published by Miller's own music publisher, Chesdel Music created in 1962. Miller had his own distribution channels of his records in supermarkets and drugstores with the cheap albums being sold in metal racks similar to those holding paperback books or cardboard record holders called "dumps" that could be placed anywhere. Miller's record albums were sold wholesale for 93 cents to salesmen who sold them to merchants who sold them to the public for $1.98. Somerset Records used artist Anthony "Chic" Laganella to create attractive eye catching album covers. Miller used the name 101 Strings for several German orchestras; their first album appearing in September 1957. In 1958 Somerset released 24 101 Strings titles. Miller International's philosophy
+Think hard, but answer shortly and concisely. Only give direct answers to the questions. No additional explanations. Directly answer these questions:
+Q: Who was the man behind The Chipmunks??
+A: David Seville
+
+Q: Which Lloyd Webber musical premiered in the US on 10th December 1993??
+A: Sunset Boulevard
+
+Q: Who was the next British Prime Minister after Arthur Balfour??
+A: Campbell-Bannerman
+
+Q: Who had a 70s No 1 hit with Kiss You All Over??
+A: Exile
+
+Q: What claimed the life of singer Kathleen Ferrier??
+A: Cancer
+
+Q: In which decade did stereo records first go on sale?
+A: 
+==================================================
+
+==================================================
+PROMPT #12:
+==================================================
+Flack in 1896) to win gold medals in both the 800 m and 1500 m in the same Olympics. Billy Mills, an unfancied runner, became the only American to win the gold in the men's 10,000 m. Bob Hayes won the 100 metre title in a time of 10.06 seconds, equaling the world record, and set the current record for the fastest relay leg in the 4×100 m. Joe Frazier, future heavyweight champion of the world, won a gold medal in heavyweight boxing while competing with a broken thumb. This was the last Summer Olympics to use a cinder running track for athletic events, and the first to use fiberglass poles for pole vaulting. Zambia declared its independence on the day of the closing ceremony of the 1964 Summer Olympics, thereby becoming the first country ever to have entered an Olympic games as one country, and left it as another. This was celebrated in the ceremony itself by the team using a placard with "Zambia" instead of the "Northern Rhodesia" placard from the opening ceremony. Zambia was the only team to use a placard in the closing ceremony. The start of operations for the first Japanese "bullet train" (the Tōkaidō Shinkansen) between Tokyo Station and Shin-Ōsaka Station was scheduled to coincide with the Olympic games. The first regularly scheduled train ran on 1 October 1964, just nine days before the opening of the games, transporting passengers in about four hours, and connecting the three major metropolitan areas of Tokyo, Nagoya, and Osaka. Ranatunge Karunananda who representedsystems were used: official hand timing, hand started photo-finish times, and the Gustavus Town Kirby timing device, which was designed by Kirby to determine the correct order of finish in horse races. The official report for 1932 Olympics states: "In addition to hand timing, two auxiliary electrical timing devices were used. Both were started by an attachment to the starters gun. One was stopped by hand at the time the runners hit the tape. The other was provided with a motion picture camera which photographed the runner at the tape and the dial of the time indicator simultaneously." Kirby's system was also used at the 1932 US. Olympic Trials, where Ralph Metcalfe's winning time of 10.62 in the 100 meters is considered possibly the first automatically timed world record. FAT was also used in 1936, but very few times have been found. In 1948, Bulova began developing the Phototimer, a unique combination of photo-finish camera and precision electronic timing instrument. The Phototimer was the first automatic timing device to be used in competitive sports. It was used extensively in North America, including at the 1948 US Olympic trials. The Bulova device was activated by the sound of the starting gun firing, rather than by a direct connection, which means that the times were around 0.02 seconds faster than reality. The 1948 Olympics, however, continued to use Omega timing with a device called the 'Magic Eye', developed by British Race Finish Recording Co. Ltd. The automatic times produced in the 1948 Olympics have never been released, butWhile the most notable story coming out of 1968 was socio-political, politics involved with the Olympics was not something unique to this year. However, the year marked the beginning of several emerging elements of contemporary track and field. Automatic timing While timing to the 100th of a second had been experimented with for many years, the 1968 Summer Olympics were the first to use Fully Automatic Timing, in not only athletics, but in canoeing, rowing, cycling, equestrian and swimming competitions. Subsequently, systems to record such times became more common and thus the accuracy of Fully Automatic Timing became mandated for World Record acceptance. While this rule was officially put into place in 1977, many 1968 records still stood as the first Automatically timed record. All weather tracks This technology too had been developing, but Tartan tracks were used as the competition surface for the first time at an Olympics. Since then an all-weather running track was required for all top-level competition. Subsequently, the inconsistency of the running surface became a significantly smaller factor in athletic performance. Altitude With the Olympics happening in Mexico City, at high altitude, the effect of the thin air on athletic performance became a factor on world records. This was already a known phenomenon, and the American team was selected by holding the Olympic Trials at high altitude at Echo Summit, California. In 1955, Lou Jones set the world record in the 400 meters at altitude in Mexico City. Following the 1968 Summer Olympics the: Men's 100 meters record, set by Jim
+Think hard, but answer shortly and concisely. Only give direct answers to the questions. No additional explanations. Directly answer these questions:
+Q: Who was the man behind The Chipmunks??
+A: David Seville
+
+Q: Which Lloyd Webber musical premiered in the US on 10th December 1993??
+A: Sunset Boulevard
+
+Q: Who was the next British Prime Minister after Arthur Balfour??
+A: Campbell-Bannerman
+
+Q: Who had a 70s No 1 hit with Kiss You All Over??
+A: Exile
+
+Q: What claimed the life of singer Kathleen Ferrier??
+A: Cancer
+
+Q: In what year's Olympics were electric timing devices and a public-address system used for the first time?
+A: 
+==================================================
+
+==================================================
+PROMPT #13:
+==================================================
+A list of stratovolcanoes follows below. Africa Cameroon Mount Cameroon Democratic Republic of Congo Mount Nyiragongo, Goma; designated as a Decade Volcano It contains an active lava lake inside its crater which overflowed due to cracks in 2002. Mount Mikeno Eritrea Alid Volcano Dubbi Volcano Nabro Volcano Ethiopia Adwa Borawli, Afar Region Dabbahu Volcano Mount Fentale Kenya Mount Kenya, which contains several volcanic plugs on its peak. Mount Longonot Rwanda Mount Bisoke, on the border between Rwanda and the Democratic Republic of the Congo. Mount Gahinga, on the border between Rwanda and Uganda. Mount Karisimbi, on the border between Rwanda and the Democratic Republic of the Congo. Mount Muhabura, on the border between Rwanda and Uganda. Mount Sabyinyo, marks the border between Rwanda, Uganda, and the Democratic Republic of the Congo. Tanzania Ol Doinyo Lengai, the Earth's only active carbonatite lava-producing volcano. Mount Kilimanjaro, a dormant stratovolcano. It is the highest point of Africa. Mount Meru Mid-Atlantic Ridge Mount Pico in Pico Island, Azores, Portugal Teide in Tenerife, Canary Islands, Spain; designated as a Decade Volcano Cumbre Vieja in La Palma, Canary Islands, Spain Mount Fogo in Fogo, Cape Verde Green Mountain, Ascension Island Pico de las Nieves in Gran Canaria, Canary Islands, Spain Americas Caribbean La Grande Soufrière on Basse-Terre Island, Guadeloupe Soufriere Hills on the island Montserrat Its 1995 eruptions resulted in the abandonment of its capital city, Plymouth. Soufrière on the island Saint Vincent Mount Pelée on the island Martinique Its devastating eruption on 8 May 1902 resulted in the complete destruction ofMount Kilimanjaro is a volcano in Tanzania and the highest mountain in Africa. Kilimanjaro may also refer to: Tanzania Kilimanjaro National Park comprises the whole of Mount Kilimanjaro above the tree line and six forest corridors stretching down Kilimanjaro Region, a region in Tanzania Kilimanjaro (ward), a ward in the Moshi Urban district of Kilimanjaro Region, Tanzania Kilimanjaro International Airport in Tanzania a Tanzanian beer, see Beer in Africa#Eastern Africa a Tanzanite jewellery brand owned by F. Hinds Music Killamanjaro, a Jamaican reggae sound system Albums Kilimanjaro, an album by German artist Superpitcher Kilimanjaro (The Rippingtons album), a 1988 album by The Rippingtons Kilimanjaro (The Teardrop Explodes album), an album by The Teardrop Explodes Songs "Kilimanjaro", song by The Del Vikings 1962 "Kilimanjaro", song by Manhattan Brothers 1955 "Kilimanjaro", song by The Teardrop Explodes 1980 "Kilimanjaro", song by Juluka 1984 "Kilimandjaro" (song), a 1966 French-language song by French singer Pascal Danel "Kilimanjaro" (song), a 2010 song by A.R. Rahman from the film Enthiran "Kilimanjaro", a song by KSI from the 2016 extended play Keep Up Film Kilimanjaro (film), a 2013 American film Nigeria Kilimanjaro restaurant, a fast-food chain in Nigeria. See also The Snows of Kilimanjaro (disambiguation)Mount Kilimanjaro () is a dormant volcano located in Kilimanjaro Region of Tanzania. It has three volcanic cones: Kibo, Mawenzi, and Shira. It is the highest mountain in Africa and the highest single free-standing mountain above sea level in the world: above sea level and about above its plateau base. It is the highest volcano in Africa and the Eastern Hemisphere. Kilimanjaro is the fourth most topographically prominent peak on Earth. It is part of Kilimanjaro National Park and is a major hiking and climbing destination. Because of its shrinking glaciers and ice fields, which are projected to disappear between 2025 and 2035, it has been the subject of many scientific studies. Toponymy The origin of the name Kilimanjaro is not known, but a number of theories exist. European explorers had adopted the name by 1860 and reported that Kilimanjaro was the mountain's Kiswahili name. The 1907 edition of The Nuttall Encyclopædia also records the name of the mountain as Kilima-Njaro. Johann Ludwig Krapf wrote in 1860 that Swahilis along the coast called the mountain Kilimanjaro. Although he did not offer any support, he claimed that Kilimanjaro meant either mountain of greatness or mountain of caravans. Under the latter meaning, kilima meant mountain and jaro meant caravans. Jim Thompson claimed in 1885, again without support, that the term Kilima-Njaro "has generally been understood to mean" the mountain (kilima) of greatness (njaro). He also suggested "though not improbably it may mean" the white mountain. Njaro is an ancient Kiswahili word for shining. Similarly, Krapf wrote that a
+Think hard, but answer shortly and concisely. Only give direct answers to the questions. No additional explanations. Directly answer these questions:
+Q: Who was the man behind The Chipmunks??
+A: David Seville
+
+Q: Which Lloyd Webber musical premiered in the US on 10th December 1993??
+A: Sunset Boulevard
+
+Q: Who was the next British Prime Minister after Arthur Balfour??
+A: Campbell-Bannerman
+
+Q: Who had a 70s No 1 hit with Kiss You All Over??
+A: Exile
+
+Q: What claimed the life of singer Kathleen Ferrier??
+A: Cancer
+
+Q: Which volcano in Tanzania is the highest mountain in Africa?
+A: 
+==================================================
+
+==================================================
+PROMPT #14:
+==================================================
+of the Libyan Draft Constitutional Charter for the Transitional Stage: The national flag shall have the following shape and dimensions: Its length shall be double its width, its shall be divided into three parallel coloured stripes, the uppermost being red, the centre black and lowest green, the black stripe shall be equal in area to the other two stripes together and shall bear in its centre a white crescent, between the two extremities of which there shall be a five-pointed white star. On 10 March 2011, France was the first country to recognise the council as the official government of Libya, as well as the first to allow the Libyan embassy staff to raise the flag. On 21 March, the flag was flown by the Permanent Mission of Libya to the United Nations and appeared on their official website, and thereafter in late August by the Arab League and by Libya's own telecommunications authority, the Libya Telecom & Technology, on its own website. In the following months many other Libyan embassies replaced the green flag of Gaddafi with the tricolour flag. This original flag of Libya is now the only flag used by the United Nations to represent Libya, according to the following UN statement: "Following the adoption by the General Assembly of resolution 66/1, the Permanent Mission of Libya to the United Nations formally notified the United Nations of a Declaration by the National Transitional Council of 3 August 2011 changing the official name of the Libyan Arab Jamahiriya to 'Libya' as well as athe flag's colours and symbols. According to Omar Faiek Shennib, "red was selected for the blood sacrificed for the freedom of Libya, black to remember the dark days that Libyans lived under the occupation of the Italians and green to represent its primary wealth, agriculture, [Libya once being referred to as the 'agricultural basket' or 'breadbasket' of the Ottoman Empire] and the future prosperity of the country. The star and crescent were placed within the black central strip of the flag as a reference to the Senussi flag and the role of King Idris in leading the country to independence". The flag's colours also echo the colours of the flags of the three regions of Libya: Fezzan (red), Cyrenaica (black), and Tripolitania (green). Under Muammar Gaddafi's dictatorship, Libya had a red-white-black flag from 1969 to 1977, and it was replaced by the all-green flag from 1977 to 2011, during which it was the only flag in the world to have one color and no design. During the Libyan Civil War against the rule of Muammar Gaddafi, the 1951–69 flag – as well as various makeshift versions without the crescent and star symbol, or without the green stripe – came back into use in areas held by the Libyan opposition and by protesters at several Libyan diplomatic missions abroad. The National Transitional Council, formed on 27 February 2011, adopted the flag previously used in the Kingdom of Libya between 1951 and 1969 as the "emblem of the Libyan Republic". The flag was officially defined in article threeThe flag of Libya from 1977 to 2011 was used by the Socialist People's Libyan Arab Jamahiriya from 1977 to 1986 and later the Great Socialist People's Libyan Arab Jamahiriya until 2011. The design is a green field in 1:2 ratio and was considered the only solid colour national flag in the world during its time. In 2011, after the collapse of Gaddafi's government, the 1951–1969 flag from the Kingdom of Libya was re-adopted but the flag introduced by Gaddafi remained in use by Pro-Gaddafists and Gaddafi loyalists. Before 1977, the country was called the Libyan Arab Republic from 1969 to 1977 and used a red-white-black flag similar to most traditional Arab national flags bearing a resemblance to the modern flag of Yemen. in 1977 after the Egyptian-Libyan War, the blank green flag was introduced to replace the red-white-black flag to avoid similarities with Egypt. History of Libya under Muammar Gaddafi Flags introduced in 1977 1977 establishments in Libya 2011 disestablishments in Libya
+Think hard, but answer shortly and concisely. Only give direct answers to the questions. No additional explanations. Directly answer these questions:
+Q: Who was the man behind The Chipmunks??
+A: David Seville
+
+Q: Which Lloyd Webber musical premiered in the US on 10th December 1993??
+A: Sunset Boulevard
+
+Q: Who was the next British Prime Minister after Arthur Balfour??
+A: Campbell-Bannerman
+
+Q: Who had a 70s No 1 hit with Kiss You All Over??
+A: Exile
+
+Q: What claimed the life of singer Kathleen Ferrier??
+A: Cancer
+
+Q: The flag of Libya is a plain rectangle of which color?
+A: 
+==================================================
+
+==================================================
+PROMPT #15:
+==================================================
+la Francophonie. Places of worship Niger being a predominantly Muslim country, mosques are the most common places of worship, with the Grande Mosquée being the largest in the city. There are also various Christian churches, most notably Our Lady of Perpetual Help Cathedral and the Cathedral de Maourey. Governance Administration Niamey makes up a special capital district of Niger, which is surrounded by the Region of Tillabéri. The city of Niamey itself is governed as an autonomous first-level administrative block, the Niamey Urban Community (Fr. Communauté Urbaine de Niamey, or CUN). It includes five Urban Communes, divided into 44 "Districts" and 99 "Quartiers", including formerly independent towns. It is a co-equal first division subdivision with the seven Regions of Niger. The Niamey Urban Community includes an administration and Governor appointed by national leaders. Like the rest of Niger, Niamey has seen a decentralisation of governance since 2000. Government Ordinance n°2010–56 and Presidential Decree n°2010-679 of September 2010 mandated an elected City Council for the city of Niamey, subsumed under the CUN. This excludes some outlying areas of the CUN. Forty-five councillors are popularly elected and in turn elect the Mayor of the City of Niamey. In July 2011, the first Mayor under the new system, Oumarou Dogari Moumouni, was installed by the Governor of the CUN Mrs. Aïchatou Boulama Kané and the City Council. The City Council and Mayor have limited roles compared to the CUN Governor. Niamey has a third layer of government in the Commune system. Each Commune elects its own council, and outsidein Niger Niamey NigerNiamey () is the capital and largest city of Niger. Niamey lies on the Niger River, primarily situated on the east bank. Niamey's population was counted as 1,026,848 as of the 2012 census. As of 2017, population projections show the capital district growing at a slower rate than the country as a whole, which has the world's highest fertility rate. The city is located in a pearl millet growing region, while manufacturing industries include bricks, ceramic goods, cement, and weaving. History Niamey was probably founded in the 18th century and originated as a cluster of small villages (Gaweye, Kalley, Maourey, Zongo and Foulani Koira). Niamey was of little importance until the French developed it as a colonial centre in the late 1890s. The town, then with an estimated population of some 1,800, was chosen as the capital of the newly created Military Territory of Niger in 1905, however, the capital was shifted to the more established city of Zinder in 1912. Zinder's proximity to the Nigerian border and distance from French-controlled ports prompted the French to move the capital back to Niamey in 1926, by which time the city had some 3,000 inhabitants. A series of devastating droughts prompted significant population growth during this period, and by 1945 the population was about 8,000. Prior to 1926-27 the Upper Volta-Niger border ran along the Niger river, meaning that Niamey lay directly on the boundary. At the time of independence in 1960 the population had grown to around 30,000. The period from 1970 to 1988 was one in
+Think hard, but answer shortly and concisely. Only give direct answers to the questions. No additional explanations. Directly answer these questions:
+Q: Who was the man behind The Chipmunks??
+A: David Seville
+
+Q: Which Lloyd Webber musical premiered in the US on 10th December 1993??
+A: Sunset Boulevard
+
+Q: Who was the next British Prime Minister after Arthur Balfour??
+A: Campbell-Bannerman
+
+Q: Who had a 70s No 1 hit with Kiss You All Over??
+A: Exile
+
+Q: What claimed the life of singer Kathleen Ferrier??
+A: Cancer
+
+Q: Of which African country is Niamey the capital?
+A: 
+==================================================
+
+==================================================
+PROMPT #16:
+==================================================
+James Walter McCord Jr. (January 26, 1924 – June 15, 2017) was an American CIA officer, later head of security for President Richard Nixon's 1972 reelection campaign. He was involved as an electronics expert in the burglaries which precipitated the Watergate scandal. Career McCord was born in Waurika, Oklahoma. He served as a bombardier with the rank of second lieutenant in the Army Air Forces during World War II. He briefly attended Baylor University before receiving a B.B.A. from the University of Texas at Austin in 1949. In 1965, he received an M.S. in international affairs from George Washington University. After beginning his career at the Federal Bureau of Investigation (FBI), McCord worked for the Central Intelligence Agency (CIA), ultimately ascending to the GS-15 directorship of the Agency's Office of Security. For a period of time, he was in charge of physical security at the Agency's Langley headquarters. L. Fletcher Prouty, a former colonel in the United States Air Force, claimed then-Director of Central Intelligence Allen Dulles introduced McCord to him as "my top man.". In 1961, under his direction, a counter-intelligence program was launched against the Fair Play for Cuba Committee. He also held the rank of lieutenant colonel in the United States Air Force Reserve. Watergate scandal Shortly after resigning from the CIA, McCord was interviewed and then hired by Jack Caulfield in January 1972 "for strict, solely defensive security work at the Republican National Committee (RNC) and the Committee to Re-Elect the President (CRP)." Some of the money from this contract came fromadministration as assistant director of the Bureau of the Budget, devoting most of his time to Defense matters. In 1971, President Nixon appointed Schlesinger a member of the Atomic Energy Commission (AEC) and designated him as chairman. Serving in this position for about a year and a half, Schlesinger instituted extensive organizational and management changes in an effort to improve the AEC's regulatory performance. CIA Director Schlesinger was CIA Director from February 2, 1973, to July 2, 1973. He was succeeded by William Colby. Schlesinger was extremely unpopular with CIA staff, as he reduced CIA staff by 7%, and was considered a Nixon loyalist seeking to make the agency more obedient to Nixon. He had a CCTV camera installed near his official portrait at the CIA headquarters in Langley, Va., as it was believed that vandalism of the portrait by disgruntled staff was likely. Secretary of Defense (1973–1975) Schlesinger left the CIA to become Secretary of Defense on July 2, aged 44. As a university professor, researcher at Rand, and government official in three agencies, he had acquired an impressive resume in national security affairs. Nuclear strategy Shortly after assuming office, Schlesinger outlined the basic objectives that would guide his administration: maintain a "strong defense establishment"; "assure the military balance so necessary to deterrence and a more enduring peace"; obtain for members of the military "the respect, dignity and support that are their due"; assume "an . . . obligation to use our citizens' resources wisely"; and "become increasingly competitive with potential adversaries.... [W]e must nota conventional North Vietnamese assault in 1975. The CORDS model and its approach influenced U.S. strategy and thinking on counterinsurgency in the 2000s in Iraq and Afghanistan. CIA HQ: Director Colby returned to Washington in July 1971 and became executive director of CIA. After long-time DCI Richard Helms was dismissed by President Nixon in 1973, James Schlesinger assumed the helm at the Agency. A strong believer in reform of the CIA and the intelligence community more broadly, Schlesinger had written a 1971 Bureau of the Budget report outlining his views on the subject. Colby, who had had a somewhat unorthodox career in the CIA focused on political action and counterinsurgency, agreed with Schlesinger's reformist approach. Schlesinger appointed him head of the clandestine branch in early 1973. When Nixon reshuffled his agency heads and made Schlesinger secretary of defense, Colby emerged as a natural candidate for DCI—apparently on the basis of the recommendation that he was a professional who would not make waves. Colby was known as a media-friendly CIA director. His tenure as DCI, which lasted two and a half tumultuous years, was overshadowed by the Church and Pike congressional investigations into alleged U.S. intelligence malfeasance over the preceding 25 years, including 1975, the so-called Year of Intelligence. Colby's time as DCI was also eventful on the world stage. Shortly after he assumed leadership, the Yom Kippur War broke out, an event that surprised not only the American intelligence agencies but also the Israelis. This intelligence surprise reportedly affected Colby's credibility with the Nixon administration. Colby
+Think hard, but answer shortly and concisely. Only give direct answers to the questions. No additional explanations. Directly answer these questions:
+Q: Who was the man behind The Chipmunks??
+A: David Seville
+
+Q: Which Lloyd Webber musical premiered in the US on 10th December 1993??
+A: Sunset Boulevard
+
+Q: Who was the next British Prime Minister after Arthur Balfour??
+A: Campbell-Bannerman
+
+Q: Who had a 70s No 1 hit with Kiss You All Over??
+A: Exile
+
+Q: What claimed the life of singer Kathleen Ferrier??
+A: Cancer
+
+Q: Who was the director of the CIA from 1976-81?
+A: 
+==================================================
+
+==================================================
+PROMPT #17:
+==================================================
+"On the Street Where You Live" is a song with music by Frederick Loewe and lyrics by Alan Jay Lerner from the 1956 Broadway musical My Fair Lady. It is sung in the musical by the character Freddy Eynsford-Hill, who was portrayed by John Michael King in the original production. In the 1964 film version, it was sung by Bill Shirley, dubbing for actor Jeremy Brett. Recorded versions The most popular single of the song was recorded by Vic Damone in 1956 for Columbia Records. It reached No. 4 on the Billboard chart and No. 6 on Cashbox magazine's chart. It was a No. 1 hit in the UK Singles Chart in 1958. Eddie Fisher also had a top 20 Billboard hit with the song in 1956, reaching No. 18. Lawrence Welk and His Orchestra released a version that went to No. 96 in 1956. Andy Williams' recording appeared in the Billboard top 40 in 1964, reaching No. 3 on the adult contemporary chart and No. 28 on the Billboard Hot 100. The song has been recorded by a wide variety of other performers, including Ray Conniff and Bing Crosby, who recorded the song in 1956 for use on his radio show and it was subsequently included in the boxed set The Bing Crosby CBS Radio Recordings (1954–56) issued by Mosaic Records (catalog MD7-245) in 2009, Lawrence Welk (whose band also performed it on his weekly TV series numerous times), Shirley Horn, Doris Day, George Shearing, Frank Chacksfield, Alfie Boe, Bobby Darin, Dean Martin, Mario Lanza,The Times praised it as "Alan Jay Lerner's terrific autobiography". The Street Where I Live was reissued in 1989 by Columbus Books and in 1994 by the Da Capo Press. In 2000, BBC radio broadcast a serialization of the book, read by Henry Goodman, which The Times called "one of the delights of the evening schedule". References Sources Non-fiction books about musical theatre"On the Street Where You Live" is a song from the 1956 Broadway musical My Fair Lady. On the Street Where You Live may also refer to: On the Street Where You Live (TV series), an Irish documentary television series On The Street Where You Live, a 2001 novel by Mary Higgins Clark
+Think hard, but answer shortly and concisely. Only give direct answers to the questions. No additional explanations. Directly answer these questions:
+Q: Who was the man behind The Chipmunks??
+A: David Seville
+
+Q: Which Lloyd Webber musical premiered in the US on 10th December 1993??
+A: Sunset Boulevard
+
+Q: Who was the next British Prime Minister after Arthur Balfour??
+A: Campbell-Bannerman
+
+Q: Who had a 70s No 1 hit with Kiss You All Over??
+A: Exile
+
+Q: What claimed the life of singer Kathleen Ferrier??
+A: Cancer
+
+Q: Which musical featured the song The Street Where You Live?
+A: 
+==================================================
+
+==================================================
+PROMPT #18:
+==================================================
+engineers were ordered to end construction work. The Allies were unaware of this and mounted further attacks on the site as part of the United States Army Air Forces experimental Operation Aphrodite, involving radio-controlled B-24 Liberators packed with explosives. Two such attacks were mounted but failed; in the second such attack, on 12 August, Lt Joseph P. Kennedy, Jr. – the elder brother of future US President John F. Kennedy – was killed when the drone aircraft exploded prematurely. By the end of the bombing campaign, over 4,100 tons of bombs had been dropped on Mimoyecques, more than on any other V-weapons site. The Mimoyecques site was never formally abandoned, but German forces left it at the start of September 1944 as the Allies advanced northeast from Normandy towards the Pas de Calais. It was captured on 5 September by the Canadian 3rd Infantry Division. Subsequent investigations and attempted demolition In September 1944, Duncan Sandys ordered the constitution of a Technical Inter-Services Mission under Colonel T.R.B. Sanders. It was given the task of investigating the V-weapons sites at Mimoyecques, Siracourt, Watten, and Wizernes, collectively known to the Allies as the "Heavy Crossbow" sites. Sanders' report was submitted to the War Cabinet on 19 March 1945. Even at this stage the true purpose of the site was unclear. Claims that it had been intended to be used for "electro-magnetic projectors" (railguns), firing huge shells at London, were debunked by Lord Cherwell, Winston Churchill's scientific adviser, who calculated that it would take sixty times the output of Battersearesearched at a facility in Peenemünde along with the V-1 flying bomb. The V-2's first target was Paris on 8 September 1944. The program while advanced proved to be an impediment to the war economy. The large capital investment was not repaid in military effectiveness. The rockets were built at an underground factory at Mittelwerk. Labor to build the A4 rockets came from the Mittelbau-Dora concentration camp. Of the 60,000 people who ended up at the camp 20,000 died, due to the appalling conditions. On 14 April 1944, Speer lost control of Organisation Todt to his Deputy, Franz Xaver Dorsch. He opposed the assassination attempt against Hitler on 20 July 1944. He was not involved in the plot, and played a minor role in the regime's efforts to regain control over Berlin after Hitler survived. After the plot Speer's rivals attacked some of his closest allies and his management system fell out of favor with radicals in the party. He lost yet more authority. Defeat of Nazi Germany Losses of territory and a dramatic expansion of the Allied strategic bombing campaign caused the collapse of the German economy from late 1944. Air attacks on the transport network were particularly effective, as they cut the main centres of production off from essential coal supplies. In January 1945, Speer told Goebbels that armaments production could be sustained for at least a year. However, he concluded that the war was lost after Soviet forces captured the important Silesian industrial region later that month. Nevertheless, Speer believed that Germany shouldof 1944 the Allies continued their gains in the Mediterranean Theatre and massed men and materiel for a European invasion along the French channel coastline. The conspirators began to organize for another attempt to assassinate Hitler and take over both German civil government and its military. The von Stauffenberg bomb attempt and aftermath By the summer of 1944 unrest in the German military and diplomatic ranks was widespread. The Allied landing at Normandy in June and failed German response raised the specter of doom among the upper ranks even of German field marshals. The Schwarze Kapelle responded by organizing a deadly attempt on Hitler's life at his Wolf's Lair compound in East Prussia. Undertaken by an aristocratic member of a hereditarily military family, Colonel Claus von Stauffenberg, the July 20 Plot nearly succeeded. Although surrounded by fatalities from the bomb Hitler escaped with a concussion and various injuries. In the aftermath he was determined to get vengeance upon the plotters. The Gestapo rounded up the members of the Schwarze Kapelle and many, many more it believed were either implicated in or sympathetic to it; according to its records it put 7,000 of them to death. Stauffenberg and three others were summarily shot that night. Most of the conspirators were put on trial in the Volksgerichtshof (People's Court) between August 1944 to February 1945. Many were executed the day after their convictions by hanging from meat hooks at Plötzensee Prison. Architect of the 1943 bomb plot on Hitler's plane Fabian von Schlabrendorff only escaped death because an
+Think hard, but answer shortly and concisely. Only give direct answers to the questions. No additional explanations. Directly answer these questions:
+Q: Who was the man behind The Chipmunks??
+A: David Seville
+
+Q: Which Lloyd Webber musical premiered in the US on 10th December 1993??
+A: Sunset Boulevard
+
+Q: Who was the next British Prime Minister after Arthur Balfour??
+A: Campbell-Bannerman
+
+Q: Who had a 70s No 1 hit with Kiss You All Over??
+A: Exile
+
+Q: What claimed the life of singer Kathleen Ferrier??
+A: Cancer
+
+Q: "Who was the target of the failed ""Bomb Plot"" of 1944?"
+A: 
+==================================================
+
+==================================================
+PROMPT #19:
+==================================================
+propelling him into the first rank of international superstars. The album contained the number-one hit "All Night Long", a Caribbean-flavored dance number that was promoted by a colorful music video produced by former Monkee Michael Nesmith. In 1984, he performed "All Night Long" at the ending ceremony of the XXIII Olympic Games in Los Angeles. Several more Top 10 hits followed, the most successful of which was the ballad "Hello" (1984), a sentimental love song that showed how far he had moved from his R&B roots. Richie had three more top ten hits in 1984, "Stuck on You" (No. 3), "Running with the Night" (No. 7) and "Penny Lover" (No. 8), as well as writing and producing "Missing You" for former labelmate and duet partner Diana Ross (No. 10 Pop, No. 1 R&B). In 1985, he wrote and performed "Say You, Say Me" for the film White Nights. The song won an Academy Award and reached No. 1 on the U.S. charts, staying there for four weeks, making it the number-two song of 1986 according to Billboards Year-End Hot 100 chart, behind the charity single "That's What Friends Are For" by Dionne and Friends. He also collaborated with Michael Jackson on the charity single "We Are the World" by USA for Africa, another number-one hit. In 1986, Richie released Dancing on the Ceiling, his last widely popular album, which produced a run of five US and UK hits, "Say You, Say Me" (U.S. No. 1), "Dancing on the Ceiling" (U.S. No. 2), "Love Will Conquer All"top 20 US R&B chart hit in 1972. Their first few recordings were released on Buddah Records, including "Hold Back the Night", which was a hit on the Billboard R&B chart in 1973, before a re-release saw it climb in the UK two years later. Several R&B hits followed during a stay with Philadelphia International subsidiary Golden Fleece (run by Baker-Harris-Young) before they signed to Atlantic Records. Their single "Disco Inferno" (1976), which was included on the Grammy Award-winning Saturday Night Fever: The Original Movie Sound Track in 1977, reached No. 11 on the Billboard Hot 100 chart in May 1978. Other major hits included "Hold Back the Night" (1975) (UK No. 5) and "That's Where the Happy People Go" (1976). In late 1977, the Trammps released the song "The Night the Lights Went Out" to commemorate the electrical blackout that affected New York City on July 13–14, 1977. Their signature song "Disco Inferno" has been covered by Tina Turner and Cyndi Lauper. In addition, Graham Parker covered "Hold Back the Night" on "The Pink Parker EP" in 1977, and reached No. 24 in the UK Singles Chart, and top 60 in the US. In 2021, "Disco Inferno" was certified Silver by the British Phonographic Industry, together with "Can We Come Together" (from the album Where the Happy People Go). Dissolution and aftermath On September 19, 2005, the group's "Disco Inferno" was inducted into the Dance Music Hall of Fame at a ceremony held in New York. The song was part-written by Ron Kersey, a producer-arranger"Hold On to the Nights" is a power ballad written and performed by American rock singer/songwriter/musician Richard Marx. This was the fourth and final single released from his self-titled debut album, and his first to reach number one on the US Billboard Hot 100 chart. The song has been re-released on numerous albums and is included on Marx's live performance DVD A Night Out with Friends (2012). Release "Hold On to the Nights" reached the Billboard Hot 100 number 1 position on July 23, 1988, preventing Def Leppard's "Pour Some Sugar on Me" from reaching the top spot that same week. The song was on the chart for twenty-one weeks, and left the chart at number 91. The song also reached at number three on the Billboard Adult Contemporary chart. Chart performance Charts Personnel Richard Marx – vocals, keyboards, acoustic piano Michael Landau – guitars Patrick O'Hearn – bass Tris Imboden – drums Paulinho da Costa – percussion Other performances Marx appeared as lounge singer/piano player Buddy Daquiri in the "Poison Fire Teats Universe" episode of the TV series Life in Pieces in 2017, in which he played the song on the piano while whistling. References 1987 songs 1988 singles Richard Marx songs Billboard Hot 100 number-one singles Songs written by Richard Marx Pop ballads Rock ballads EMI Records singles Songs about nights
+Think hard, but answer shortly and concisely. Only give direct answers to the questions. No additional explanations. Directly answer these questions:
+Q: Who was the man behind The Chipmunks??
+A: David Seville
+
+Q: Which Lloyd Webber musical premiered in the US on 10th December 1993??
+A: Sunset Boulevard
+
+Q: Who was the next British Prime Minister after Arthur Balfour??
+A: Campbell-Bannerman
+
+Q: Who had a 70s No 1 hit with Kiss You All Over??
+A: Exile
+
+Q: What claimed the life of singer Kathleen Ferrier??
+A: Cancer
+
+Q: Who had an 80s No 1 hit with Hold On To The Nights?
+A: 
+==================================================
+
+==================================================
+PROMPT #20:
+==================================================
+Turner Classic Movies in November 2006 features directors Steven Spielberg, Clint Eastwood, and Martin Scorsese, who suggest that the string of classic films Ford directed during 1936 to 1941 was due in part to an intense six-month extramarital affair with Katharine Hepburn, the star of Mary of Scotland (1936), an Elizabethan costume drama. 1939–1941 Stagecoach (1939) was Ford's first western since 3 Bad Men in 1926, and it was his first with sound. Orson Welles claimed that he watched Stagecoach forty times in preparation for making Citizen Kane. It remains one of the most admired and imitated of all Hollywood movies, not least for its climactic stagecoach chase and the hair-raising horse-jumping scene, performed by the stuntman Yakima Canutt. The Dudley Nichols–Ben Hecht screenplay was based on an Ernest Haycox story that Ford had spotted in Collier's magazine and he purchased the screen rights for just $2500. Production chief Walter Wanger urged Ford to hire Gary Cooper and Marlene Dietrich for the lead roles, but eventually accepted Ford's decision to cast Claire Trevor as Dallas and a virtual unknown, his friend John Wayne, as Ringo; Wanger reportedly had little further influence over the production. In making Stagecoach, Ford faced entrenched industry prejudice about the now-hackneyed genre which he had helped to make so popular. Although low-budget western features and serials were still being churned out in large numbers by "Poverty Row" studios, the genre had fallen out of favor with the big studios during the 1930s and they were regarded as B-grade "pulp" movies at best.Stagecoach is a 1986 American made-for-television Western action drama film and remake of the classic 1939 film Stagecoach, directed by Ted Post and starring Kris Kristofferson as the Ringo Kid, the role originally played by John Wayne. Willie Nelson portrays famous gunslinger and dentist Doc Holliday, Johnny Cash portrays Marshal Curly Wilcox and Waylon Jennings plays the gambler Hatfield. The four main stars of the film (Nelson, Kristofferson, Cash and Jennings) were associated as members of the country music supergroup The Highwaymen. The supporting cast features Elizabeth Ashley, Anthony Newley, Tony Franciosa, Mary Crosby, June Carter Cash and Jessi Colter. Plot In 1880, a group of strangers boards the east-bound stagecoach from Tonto, Arizona Territory, to Lordsburg, New Mexico Territory. The travelers seem ordinary, but many have secrets from which they are running. Among them are Dallas, a prostitute, who is being driven out of town; an alcoholic dentist, Doc Holliday; pregnant Lucy Mallory, who is meeting her cavalry officer husband; and whiskey salesman Trevor Peacock. As the stage sets out, U.S. Cavalry Lieutenant Blanchard announces that Geronimo and his Apaches are on the warpath; his small troop will provide an escort to Dry Fork. Cast Willie Nelson as Doc Holliday Kris Kristofferson as Ringo / Ringo Kid / Bill Williams Johnny Cash as Marshal Curly Wilcox Waylon Jennings as Hatfield (Gambler) John Schneider as Buck (Overland Stage Driver) Elizabeth Ashley as Dallas Anthony Newley as Trevor Peacock (Old John's Whiskey Salesman) Tony Franciosa as Henry Gatewood (Tonto Banker) Merritt Butrick as Lieutenant Blanchard Mary CrosbyStagecoach is a 1939 American Western film directed by John Ford and starring Claire Trevor and John Wayne in his breakthrough role. The screenplay by Dudley Nichols is an adaptation of "The Stage to Lordsburg", a 1937 short story by Ernest Haycox. The film follows a group of strangers riding on a stagecoach through dangerous Apache territory. The film has long been recognized as an important work that transcends the Western genre. Philosopher Robert B. Pippin has observed that both the collection of characters and their journey "are archetypal rather than merely individual" and that the film is a "mythic representation of the American aspiration toward a form of politically meaningful equality." In 1995, the film was deemed "culturally, historically, or aesthetically significant" by the United States Library of Congress and selected for preservation in their National Film Registry. Still, Stagecoach has not avoided controversy. Like most Westerns of the era, its depiction of Native Americans as simplistic savages has been criticized. Stagecoach was the first of many Westerns that Ford shot in Monument Valley, on the Arizona–Utah border in the American Southwest. Many of the movies Ford shot there also starred John Wayne. Scenes from Stagecoach, including a sequence introducing John Wayne's character the Ringo Kid, blended shots of Monument Valley with shots filmed on the Iverson Movie Ranch in Chatsworth, California, RKO Encino Movie Ranch, and other locations. Geographic incongruities are visible throughout the film, including the closing scene where Ringo (Wayne) and Dallas (Trevor) depart Lordsburg, in southwestern New Mexico, by way of
+Think hard, but answer shortly and concisely. Only give direct answers to the questions. No additional explanations. Directly answer these questions:
+Q: Who was the man behind The Chipmunks??
+A: David Seville
+
+Q: Which Lloyd Webber musical premiered in the US on 10th December 1993??
+A: Sunset Boulevard
+
+Q: Who was the next British Prime Minister after Arthur Balfour??
+A: Campbell-Bannerman
+
+Q: Who had a 70s No 1 hit with Kiss You All Over??
+A: Exile
+
+Q: What claimed the life of singer Kathleen Ferrier??
+A: Cancer
+
+Q: Who directed the classic 30s western Stagecoach?
+A: 
+==================================================
+
--- a/benchmarks/enron_emails/README.md
+++ b/benchmarks/enron_emails/README.md
@@ -1,141 +0,0 @@
-# Enron Emails Benchmark
-
-A comprehensive RAG benchmark for evaluating LEANN search and generation on the Enron email corpus. It mirrors the structure and CLI of the existing FinanceBench and LAION benches, using stage-based evaluation with Recall@3 and generation timing.
-
- Dataset: Enron email CSV (e.g., Kaggle wcukierski/enron-email-dataset) for passages
- Queries: corbt/enron_emails_sample_questions (filtered for realistic questions)
- Metrics: Recall@3 vs FAISS Flat baseline + Generation evaluation with Qwen3-8B
-
-## Layout
-
-benchmarks/enron_emails/
- setup_enron_emails.py: Prepare passages, build LEANN index, build FAISS baseline
- evaluate_enron_emails.py: Evaluate retrieval recall (Stages 2-5) + generation with Qwen3-8B
- data/: Generated passages, queries, embeddings-related files
- baseline/: FAISS Flat baseline files
- llm_utils.py: LLM utilities for Qwen3-8B generation (in parent directory)
-
-## Quickstart
-
-1) Prepare the data and index
-
-cd benchmarks/enron_emails
-python setup_enron_emails.py --data-dir data
-
-Notes:
- If `--emails-csv` is omitted, the script attempts to download from Kaggle dataset `wcukierski/enron-email-dataset` using Kaggle API (requires `KAGGLE_USERNAME` and `KAGGLE_KEY`).
-  Alternatively, pass a local path to `--emails-csv`.
-
-Notes:
- The script parses emails, chunks header/body into passages, builds a compact LEANN index, and then builds a FAISS Flat baseline from the same passages and embedding model.
- Optionally, it will also create evaluation queries from HuggingFace dataset `corbt/enron_emails_sample_questions`.
-
-2) Run recall evaluation (Stage 2)
-
-python evaluate_enron_emails.py --index data/enron_index_hnsw.leann --stage 2
-
-3) Complexity sweep (Stage 3)
-
-python evaluate_enron_emails.py --index data/enron_index_hnsw.leann --stage 3 --target-recall 0.90 --max-queries 200
-
-Stage 3 uses binary search over complexity to find the minimal value achieving the target Recall@3 (assumes recall is non-decreasing with complexity). The search expands the upper bound as needed and snaps complexity to multiples of 8.
-
-4) Index comparison (Stage 4)
-
-python evaluate_enron_emails.py --index data/enron_index_hnsw.leann --stage 4 --complexity 88 --max-queries 100 --output results.json
-
-5) Generation evaluation (Stage 5)
-
-python evaluate_enron_emails.py --index data/enron_index_hnsw.leann --stage 5 --complexity 88 --llm-backend hf --model-name Qwen/Qwen3-8B
-
-6) Combined index + generation evaluation (Stages 4+5, recommended)
-
-python evaluate_enron_emails.py --index data/enron_index_hnsw.leann --stage 45 --complexity 88 --llm-backend hf
-
-Notes:
- Minimal CLI: you can run from repo root with only `--index`, defaults match financebench/laion patterns:
-  - `--stage` defaults to `all` (runs 2, 3, 4, 5)
-  - `--baseline-dir` defaults to `baseline`
-  - `--queries` defaults to `data/evaluation_queries.jsonl` (or falls back to the index directory)
-  - `--llm-backend` defaults to `hf` (HuggingFace), can use `vllm`
-  - `--model-name` defaults to `Qwen/Qwen3-8B`
- Fail-fast behavior: no silent fallbacks. If compact index cannot run with recompute, it errors out.
- Stage 5 requires Stage 4 retrieval results. Use `--stage 45` to run both efficiently.
-
-Optional flags:
- --queries data/evaluation_queries.jsonl (custom queries file)
- --baseline-dir baseline (where FAISS baseline lives)
- --complexity 88 (LEANN complexity parameter, optimal for 90% recall)
- --llm-backend hf|vllm (LLM backend for generation)
- --model-name Qwen/Qwen3-8B (LLM model for generation)
- --max-queries 1000 (limit number of queries for evaluation)
-
-## Files Produced
- data/enron_passages_preview.jsonl: Small preview of passages used (for inspection)
- data/enron_index_hnsw.leann.*: LEANN index files
- baseline/faiss_flat.index + baseline/metadata.pkl: FAISS baseline with passage IDs
- data/evaluation_queries.jsonl: Query file (id + query; includes GT IDs for reference)
-
-## Notes
- Evaluates both retrieval Recall@3 and generation timing with Qwen3-8B thinking model.
- The emails CSV must contain a column named "message" (raw RFC822 email) and a column named "file" for source identifier. Message-ID headers are parsed as canonical message IDs when present.
- Qwen3-8B requires special handling for thinking models with chat templates and <think></think> tag processing.
-
-## Stages Summary
-
- Stage 2 (Recall@3):
-  - Compares LEANN vs FAISS Flat baseline on Recall@3.
-  - Compact index runs with `recompute_embeddings=True`.
-
- Stage 3 (Binary Search for Complexity):
-  - Builds a non-compact index (`<index>_noncompact.leann`) and runs binary search with `recompute_embeddings=False` to find the minimal complexity achieving target Recall@3 (default 90%).
-
- Stage 4 (Index Comparison):
-  - Reports .index-only sizes for compact vs non-compact.
-  - Measures timings on queries by default: non-compact (no recompute) vs compact (with recompute).
-  - Stores retrieval results for Stage 5 generation evaluation.
-  - Fails fast if compact recompute cannot run.
-  - If `--complexity` is not provided, the script tries to use the best complexity from Stage 3:
-    - First from the current run (when running `--stage all`), otherwise
-    - From `enron_stage3_results.json` saved next to the index during the last Stage 3 run.
-    - If neither exists, Stage 4 will error and ask you to run Stage 3 or pass `--complexity`.
-
- Stage 5 (Generation Evaluation):
-  - Uses Qwen3-8B thinking model for RAG generation on retrieved documents from Stage 4.
-  - Supports HuggingFace (`hf`) and vLLM (`vllm`) backends.
-  - Measures generation timing separately from search timing.
-  - Requires Stage 4 results (no additional searching performed).
-
-## Example Results
-
-These are sample results obtained on Enron data using all-mpnet-base-v2 and Qwen3-8B.
-
- Stage 3 (Binary Search):
-  - Minimal complexity achieving 90% Recall@3: 88
-  - Sampled points:
-    - C=8 → 59.9% Recall@3
-    - C=72 → 89.4% Recall@3
-    - C=88 → 90.2% Recall@3
-    - C=96 → 90.7% Recall@3
-    - C=112 → 91.1% Recall@3
-    - C=136 → 91.3% Recall@3
-    - C=256 → 92.0% Recall@3
-
- Stage 4 (Index Sizes, .index only):
-  - Compact: ~2.2 MB
-  - Non-compact: ~82.0 MB
-  - Storage saving by compact: ~97.3%
-
- Stage 4 (Search Timing, 988 queries, complexity=88):
-  - Non-compact (no recompute): ~0.0075 s avg per query
-  - Compact (with recompute): ~1.981 s avg per query
-  - Speed ratio (non-compact/compact): ~0.0038x
-
- Stage 5 (RAG Generation, 988 queries, Qwen3-8B):
-  - Average generation time: ~22.302 s per query
-  - Total queries processed: 988
-  - LLM backend: HuggingFace transformers
-  - Model: Qwen/Qwen3-8B (thinking model with <think></think> processing)
-
-Full JSON output is saved by the script (see `--output`), e.g.:
-`benchmarks/enron_emails/results_enron_stage45.json`.
--- a/benchmarks/enron_emails/data/.gitignore
+++ b/benchmarks/enron_emails/data/.gitignore
@@ -1 +0,0 @@
-downloads/
--- a/benchmarks/enron_emails/evaluate_enron_emails.py
+++ b/benchmarks/enron_emails/evaluate_enron_emails.py
@@ -1,614 +0,0 @@
-"""
-Enron Emails Benchmark Evaluation - Retrieval Recall@3 (Stages 2/3/4)
-Follows the style of FinanceBench/LAION: Stage 2 recall vs FAISS baseline,
-Stage 3 complexity sweep to target recall, Stage 4 index comparison.
-On errors, fail fast without fallbacks.
-"""
-
-import argparse
-import json
-import logging
-import os
-import pickle
-from pathlib import Path
-
-import numpy as np
-from leann import LeannBuilder, LeannSearcher
-from leann_backend_hnsw import faiss
-
-from ..llm_utils import generate_hf, generate_vllm, load_hf_model, load_vllm_model
-
-# Setup logging to reduce verbose output
-logging.basicConfig(level=logging.WARNING)
-logging.getLogger("leann.api").setLevel(logging.WARNING)
-logging.getLogger("leann_backend_hnsw").setLevel(logging.WARNING)
-
-
-class RecallEvaluator:
-    """Stage 2: Evaluate Recall@3 (LEANN vs FAISS)"""
-
-    def __init__(self, index_path: str, baseline_dir: str):
-        self.index_path = index_path
-        self.baseline_dir = baseline_dir
-        self.searcher = LeannSearcher(index_path)
-
-        baseline_index_path = os.path.join(baseline_dir, "faiss_flat.index")
-        metadata_path = os.path.join(baseline_dir, "metadata.pkl")
-
-        self.faiss_index = faiss.read_index(baseline_index_path)
-        with open(metadata_path, "rb") as f:
-            self.passage_ids = pickle.load(f)
-
-        print(f"📚 Loaded FAISS flat baseline with {self.faiss_index.ntotal} vectors")
-
-        # No fallbacks here; if embedding server is needed but fails, the caller will see the error.
-
-    def evaluate_recall_at_3(
-        self, queries: list[str], complexity: int = 64, recompute_embeddings: bool = True
-    ) -> float:
-        """Evaluate recall@3 using FAISS Flat as ground truth"""
-        from leann.api import compute_embeddings
-
-        recompute_str = "with recompute" if recompute_embeddings else "no recompute"
-        print(f"🔍 Evaluating recall@3 with complexity={complexity} ({recompute_str})...")
-
-        total_recall = 0.0
-        for i, query in enumerate(queries):
-            # Compute query embedding with the same model/mode as the index
-            q_emb = compute_embeddings(
-                [query],
-                self.searcher.embedding_model,
-                mode=self.searcher.embedding_mode,
-                use_server=False,
-            ).astype(np.float32)
-
-            # Search FAISS Flat ground truth
-            n = q_emb.shape[0]
-            k = 3
-            distances = np.zeros((n, k), dtype=np.float32)
-            labels = np.zeros((n, k), dtype=np.int64)
-            self.faiss_index.search(
-                n,
-                faiss.swig_ptr(q_emb),
-                k,
-                faiss.swig_ptr(distances),
-                faiss.swig_ptr(labels),
-            )
-
-            baseline_ids = {self.passage_ids[idx] for idx in labels[0]}
-
-            # Search with LEANN (may require embedding server depending on index configuration)
-            results = self.searcher.search(
-                query,
-                top_k=3,
-                complexity=complexity,
-                recompute_embeddings=recompute_embeddings,
-            )
-            test_ids = {r.id for r in results}
-
-            intersection = test_ids.intersection(baseline_ids)
-            recall = len(intersection) / 3.0
-            total_recall += recall
-
-            if i < 3:
-                print(f"  Q{i + 1}: '{query[:60]}...' -> Recall@3: {recall:.3f}")
-                print(f"    FAISS: {list(baseline_ids)}")
-                print(f"    LEANN: {list(test_ids)}")
-                print(f"    ∩: {list(intersection)}")
-
-        avg = total_recall / max(1, len(queries))
-        print(f"📊 Average Recall@3: {avg:.3f} ({avg * 100:.1f}%)")
-        return avg
-
-    def cleanup(self):
-        if hasattr(self, "searcher"):
-            self.searcher.cleanup()
-
-
-class EnronEvaluator:
-    def __init__(self, index_path: str):
-        self.index_path = index_path
-        self.searcher = LeannSearcher(index_path)
-
-    def load_queries(self, queries_file: str) -> list[str]:
-        queries: list[str] = []
-        with open(queries_file, encoding="utf-8") as f:
-            for line in f:
-                if not line.strip():
-                    continue
-                data = json.loads(line)
-                if "query" in data:
-                    queries.append(data["query"])
-        print(f"📊 Loaded {len(queries)} queries from {queries_file}")
-        return queries
-
-    def cleanup(self):
-        if self.searcher:
-            self.searcher.cleanup()
-
-    def analyze_index_sizes(self) -> dict:
-        """Analyze index sizes (.index only), similar to LAION bench."""
-
-        print("📏 Analyzing index sizes (.index only)...")
-        index_path = Path(self.index_path)
-        index_dir = index_path.parent
-        index_name = index_path.stem
-
-        sizes: dict[str, float] = {}
-        index_file = index_dir / f"{index_name}.index"
-        meta_file = index_dir / f"{index_path.name}.meta.json"
-        passages_file = index_dir / f"{index_path.name}.passages.jsonl"
-        passages_idx_file = index_dir / f"{index_path.name}.passages.idx"
-
-        sizes["index_only_mb"] = (
-            index_file.stat().st_size / (1024 * 1024) if index_file.exists() else 0.0
-        )
-        sizes["metadata_mb"] = (
-            meta_file.stat().st_size / (1024 * 1024) if meta_file.exists() else 0.0
-        )
-        sizes["passages_text_mb"] = (
-            passages_file.stat().st_size / (1024 * 1024) if passages_file.exists() else 0.0
-        )
-        sizes["passages_index_mb"] = (
-            passages_idx_file.stat().st_size / (1024 * 1024) if passages_idx_file.exists() else 0.0
-        )
-
-        print(f"  📁 .index size: {sizes['index_only_mb']:.1f} MB")
-        return sizes
-
-    def create_non_compact_index_for_comparison(self, non_compact_index_path: str) -> dict:
-        """Create a non-compact index for comparison using current passages and embeddings."""
-
-        current_index_path = Path(self.index_path)
-        current_index_dir = current_index_path.parent
-        current_index_name = current_index_path.name
-
-        # Read metadata to get passage source and embedding model
-        meta_path = current_index_dir / f"{current_index_name}.meta.json"
-        with open(meta_path, encoding="utf-8") as f:
-            meta = json.load(f)
-
-        passage_source = meta["passage_sources"][0]
-        passage_file = passage_source["path"]
-
-        # Convert relative path to absolute
-        if not Path(passage_file).is_absolute():
-            passage_file = current_index_dir / Path(passage_file).name
-
-        # Load all passages and ids
-        ids: list[str] = []
-        texts: list[str] = []
-        with open(passage_file, encoding="utf-8") as f:
-            for line in f:
-                if line.strip():
-                    data = json.loads(line)
-                    ids.append(str(data["id"]))
-                    texts.append(data["text"])
-
-        # Compute embeddings using the same method as LEANN
-        from leann.api import compute_embeddings
-
-        embeddings = compute_embeddings(
-            texts,
-            meta["embedding_model"],
-            mode=meta.get("embedding_mode", "sentence-transformers"),
-            use_server=False,
-        ).astype(np.float32)
-
-        # Build non-compact index with same passages and embeddings
-        builder = LeannBuilder(
-            backend_name="hnsw",
-            embedding_model=meta["embedding_model"],
-            embedding_mode=meta.get("embedding_mode", "sentence-transformers"),
-            is_recompute=False,
-            is_compact=False,
-            **{
-                k: v
-                for k, v in meta.get("backend_kwargs", {}).items()
-                if k not in ["is_recompute", "is_compact"]
-            },
-        )
-
-        # Persist a pickle for build_index_from_embeddings
-        pkl_path = current_index_dir / f"{Path(non_compact_index_path).stem}_embeddings.pkl"
-        with open(pkl_path, "wb") as pf:
-            pickle.dump((ids, embeddings), pf)
-
-        print(
-            f"🔨 Building non-compact index at {non_compact_index_path} from precomputed embeddings..."
-        )
-        builder.build_index_from_embeddings(non_compact_index_path, str(pkl_path))
-
-        # Analyze the non-compact index size
-        temp_evaluator = EnronEvaluator(non_compact_index_path)
-        non_compact_sizes = temp_evaluator.analyze_index_sizes()
-        non_compact_sizes["index_type"] = "non_compact"
-
-        return non_compact_sizes
-
-    def compare_index_performance(
-        self, non_compact_path: str, compact_path: str, test_queries: list[str], complexity: int
-    ) -> dict:
-        """Compare search speed for non-compact vs compact indexes."""
-        import time
-
-        results: dict = {
-            "non_compact": {"search_times": []},
-            "compact": {"search_times": []},
-            "avg_search_times": {},
-            "speed_ratio": 0.0,
-            "retrieval_results": [],  # Store retrieval results for Stage 5
-        }
-
-        print("⚡ Comparing search performance between indexes...")
-        # Non-compact (no recompute)
-        print("  🔍 Testing non-compact index (no recompute)...")
-        non_compact_searcher = LeannSearcher(non_compact_path)
-        for q in test_queries:
-            t0 = time.time()
-            _ = non_compact_searcher.search(
-                q, top_k=3, complexity=complexity, recompute_embeddings=False
-            )
-            results["non_compact"]["search_times"].append(time.time() - t0)
-
-        # Compact (with recompute). Fail fast if it cannot run.
-        print("  🔍 Testing compact index (with recompute)...")
-        compact_searcher = LeannSearcher(compact_path)
-        for q in test_queries:
-            t0 = time.time()
-            docs = compact_searcher.search(
-                q, top_k=3, complexity=complexity, recompute_embeddings=True
-            )
-            results["compact"]["search_times"].append(time.time() - t0)
-
-            # Store retrieval results for Stage 5
-            results["retrieval_results"].append(
-                {"query": q, "retrieved_docs": [{"id": doc.id, "text": doc.text} for doc in docs]}
-            )
-        compact_searcher.cleanup()
-
-        if results["non_compact"]["search_times"]:
-            results["avg_search_times"]["non_compact"] = sum(
-                results["non_compact"]["search_times"]
-            ) / len(results["non_compact"]["search_times"])
-        if results["compact"]["search_times"]:
-            results["avg_search_times"]["compact"] = sum(results["compact"]["search_times"]) / len(
-                results["compact"]["search_times"]
-            )
-        if results["avg_search_times"].get("compact", 0) > 0:
-            results["speed_ratio"] = (
-                results["avg_search_times"]["non_compact"] / results["avg_search_times"]["compact"]
-            )
-        else:
-            results["speed_ratio"] = 0.0
-
-        non_compact_searcher.cleanup()
-        return results
-
-    def evaluate_complexity(
-        self,
-        recall_eval: "RecallEvaluator",
-        queries: list[str],
-        target: float = 0.90,
-        c_min: int = 8,
-        c_max: int = 256,
-        max_iters: int = 10,
-        recompute: bool = False,
-    ) -> dict:
-        """Binary search minimal complexity achieving target recall (monotonic assumption)."""
-
-        def round_c(x: int) -> int:
-            # snap to multiple of 8 like other benches typically do
-            return max(1, int((x + 7) // 8) * 8)
-
-        metrics: list[dict] = []
-
-        lo = round_c(c_min)
-        hi = round_c(c_max)
-
-        print(
-            f"🧪 Binary search complexity in [{lo}, {hi}] for target Recall@3>={int(target * 100)}%..."
-        )
-
-        # Ensure upper bound can reach target; expand if needed (up to a cap)
-        r_lo = recall_eval.evaluate_recall_at_3(
-            queries, complexity=lo, recompute_embeddings=recompute
-        )
-        metrics.append({"complexity": lo, "recall_at_3": r_lo})
-        r_hi = recall_eval.evaluate_recall_at_3(
-            queries, complexity=hi, recompute_embeddings=recompute
-        )
-        metrics.append({"complexity": hi, "recall_at_3": r_hi})
-
-        cap = 1024
-        while r_hi < target and hi < cap:
-            lo = hi
-            r_lo = r_hi
-            hi = round_c(hi * 2)
-            r_hi = recall_eval.evaluate_recall_at_3(
-                queries, complexity=hi, recompute_embeddings=recompute
-            )
-            metrics.append({"complexity": hi, "recall_at_3": r_hi})
-
-        if r_hi < target:
-            print(f"⚠️ Max complexity {hi} did not reach target recall {target:.2f}.")
-            print("📈 Observations:")
-            for m in metrics:
-                print(f"  C={m['complexity']:>4} -> Recall@3={m['recall_at_3'] * 100:.1f}%")
-            return {"metrics": metrics, "best_complexity": None, "target_recall": target}
-
-        # Binary search within [lo, hi]
-        best = hi
-        iters = 0
-        while lo < hi and iters < max_iters:
-            mid = round_c((lo + hi) // 2)
-            r_mid = recall_eval.evaluate_recall_at_3(
-                queries, complexity=mid, recompute_embeddings=recompute
-            )
-            metrics.append({"complexity": mid, "recall_at_3": r_mid})
-            if r_mid >= target:
-                best = mid
-                hi = mid
-            else:
-                lo = mid + 8  # move past mid, respecting multiple-of-8 step
-            iters += 1
-
-        print("📈 Binary search results (sampled points):")
-        # Print unique complexity entries ordered by complexity
-        for m in sorted(
-            {m["complexity"]: m for m in metrics}.values(), key=lambda x: x["complexity"]
-        ):
-            print(f"  C={m['complexity']:>4} -> Recall@3={m['recall_at_3'] * 100:.1f}%")
-        print(f"✅ Minimal complexity achieving {int(target * 100)}% recall: {best}")
-        return {"metrics": metrics, "best_complexity": best, "target_recall": target}
-
-
-def main():
-    parser = argparse.ArgumentParser(description="Enron Emails Benchmark Evaluation")
-    parser.add_argument("--index", required=True, help="Path to LEANN index")
-    parser.add_argument(
-        "--queries", default="data/evaluation_queries.jsonl", help="Path to evaluation queries"
-    )
-    parser.add_argument(
-        "--stage",
-        choices=["2", "3", "4", "5", "all", "45"],
-        default="all",
-        help="Which stage to run (2=recall, 3=complexity, 4=index comparison, 5=generation)",
-    )
-    parser.add_argument("--complexity", type=int, default=None, help="LEANN search complexity")
-    parser.add_argument("--baseline-dir", default="baseline", help="Baseline output directory")
-    parser.add_argument(
-        "--max-queries", type=int, help="Limit number of queries to evaluate", default=1000
-    )
-    parser.add_argument(
-        "--target-recall", type=float, default=0.90, help="Target Recall@3 for Stage 3"
-    )
-    parser.add_argument("--output", help="Save results to JSON file")
-    parser.add_argument("--llm-backend", choices=["hf", "vllm"], default="hf", help="LLM backend")
-    parser.add_argument("--model-name", default="Qwen/Qwen3-8B", help="Model name")
-
-    args = parser.parse_args()
-
-    # Resolve queries file: if default path not found, fall back to index's directory
-    if not os.path.exists(args.queries):
-        from pathlib import Path
-
-        idx_dir = Path(args.index).parent
-        fallback_q = idx_dir / "evaluation_queries.jsonl"
-        if fallback_q.exists():
-            args.queries = str(fallback_q)
-
-    baseline_index_path = os.path.join(args.baseline_dir, "faiss_flat.index")
-    if not os.path.exists(baseline_index_path):
-        print(f"❌ FAISS baseline not found at {baseline_index_path}")
-        print("💡 Please run setup_enron_emails.py first to build the baseline")
-        raise SystemExit(1)
-
-    results_out: dict = {}
-
-    if args.stage in ("2", "all"):
-        print("🚀 Starting Stage 2: Recall@3 evaluation")
-        evaluator = RecallEvaluator(args.index, args.baseline_dir)
-
-        enron_eval = EnronEvaluator(args.index)
-        queries = enron_eval.load_queries(args.queries)
-        queries = queries[:10]
-        print(f"🧪 Using first {len(queries)} queries")
-
-        complexity = args.complexity or 64
-        r = evaluator.evaluate_recall_at_3(queries, complexity)
-        results_out["stage2"] = {"complexity": complexity, "recall_at_3": r}
-        evaluator.cleanup()
-        enron_eval.cleanup()
-        print("✅ Stage 2 completed!\n")
-
-    if args.stage in ("3", "all"):
-        print("🚀 Starting Stage 3: Binary search for target recall (no recompute)")
-        enron_eval = EnronEvaluator(args.index)
-        queries = enron_eval.load_queries(args.queries)
-        queries = queries[: args.max_queries]
-        print(f"🧪 Using first {len(queries)} queries")
-
-        # Build non-compact index for fast binary search (recompute_embeddings=False)
-        from pathlib import Path
-
-        index_path = Path(args.index)
-        non_compact_index_path = str(index_path.parent / f"{index_path.stem}_noncompact.leann")
-        enron_eval.create_non_compact_index_for_comparison(non_compact_index_path)
-
-        # Use non-compact evaluator for binary search with recompute=False
-        evaluator_nc = RecallEvaluator(non_compact_index_path, args.baseline_dir)
-        sweep = enron_eval.evaluate_complexity(
-            evaluator_nc, queries, target=args.target_recall, recompute=False
-        )
-        results_out["stage3"] = sweep
-        # Persist default stage 3 results near the index for Stage 4 auto-pickup
-        from pathlib import Path
-
-        default_stage3_path = Path(args.index).parent / "enron_stage3_results.json"
-        with open(default_stage3_path, "w", encoding="utf-8") as f:
-            json.dump({"stage3": sweep}, f, indent=2)
-        print(f"📝 Saved Stage 3 summary to {default_stage3_path}")
-        evaluator_nc.cleanup()
-        enron_eval.cleanup()
-        print("✅ Stage 3 completed!\n")
-
-    if args.stage in ("4", "all", "45"):
-        print("🚀 Starting Stage 4: Index size + performance comparison")
-        evaluator = RecallEvaluator(args.index, args.baseline_dir)
-        enron_eval = EnronEvaluator(args.index)
-        queries = enron_eval.load_queries(args.queries)
-        test_q = queries[: min(args.max_queries, len(queries))]
-
-        current_sizes = enron_eval.analyze_index_sizes()
-        # Build non-compact index for comparison (no fallback)
-        from pathlib import Path
-
-        index_path = Path(args.index)
-        non_compact_path = str(index_path.parent / f"{index_path.stem}_noncompact.leann")
-        non_compact_sizes = enron_eval.create_non_compact_index_for_comparison(non_compact_path)
-        nc_eval = EnronEvaluator(non_compact_path)
-
-        if (
-            current_sizes.get("index_only_mb", 0) > 0
-            and non_compact_sizes.get("index_only_mb", 0) > 0
-        ):
-            storage_saving_percent = max(
-                0.0,
-                100.0 * (1.0 - current_sizes["index_only_mb"] / non_compact_sizes["index_only_mb"]),
-            )
-        else:
-            storage_saving_percent = 0.0
-
-        if args.complexity is None:
-            # Prefer in-session Stage 3 result
-            if "stage3" in results_out and results_out["stage3"].get("best_complexity") is not None:
-                complexity = results_out["stage3"]["best_complexity"]
-                print(f"📥 Using best complexity from Stage 3 in-session: {complexity}")
-            else:
-                # Try to load last saved Stage 3 result near index
-                default_stage3_path = Path(args.index).parent / "enron_stage3_results.json"
-                if default_stage3_path.exists():
-                    with open(default_stage3_path, encoding="utf-8") as f:
-                        prev = json.load(f)
-                    complexity = prev.get("stage3", {}).get("best_complexity")
-                    if complexity is None:
-                        raise SystemExit(
-                            "❌ Stage 4: No --complexity and no best_complexity found in saved Stage 3 results"
-                        )
-                    print(f"📥 Using best complexity from saved Stage 3: {complexity}")
-                else:
-                    raise SystemExit(
-                        "❌ Stage 4 requires --complexity if Stage 3 hasn't been run. Run stage 3 first or pass --complexity."
-                    )
-        else:
-            complexity = args.complexity
-
-        comp = enron_eval.compare_index_performance(
-            non_compact_path, args.index, test_q, complexity=complexity
-        )
-        results_out["stage4"] = {
-            "current_index": current_sizes,
-            "non_compact_index": non_compact_sizes,
-            "storage_saving_percent": storage_saving_percent,
-            "performance_comparison": comp,
-        }
-        nc_eval.cleanup()
-        evaluator.cleanup()
-        enron_eval.cleanup()
-        print("✅ Stage 4 completed!\n")
-
-    if args.stage in ("5", "all"):
-        print("🚀 Starting Stage 5: Generation evaluation with Qwen3-8B")
-
-        # Check if Stage 4 results exist
-        if "stage4" not in results_out or "performance_comparison" not in results_out["stage4"]:
-            print("❌ Stage 5 requires Stage 4 retrieval results")
-            print("💡 Run Stage 4 first or use --stage all")
-            raise SystemExit(1)
-
-        retrieval_results = results_out["stage4"]["performance_comparison"]["retrieval_results"]
-        if not retrieval_results:
-            print("❌ No retrieval results found from Stage 4")
-            raise SystemExit(1)
-
-        print(f"📁 Using {len(retrieval_results)} retrieval results from Stage 4")
-
-        # Load LLM
-        try:
-            if args.llm_backend == "hf":
-                tokenizer, model = load_hf_model(args.model_name)
-
-                def llm_func(prompt):
-                    return generate_hf(tokenizer, model, prompt)
-            else:  # vllm
-                llm, sampling_params = load_vllm_model(args.model_name)
-
-                def llm_func(prompt):
-                    return generate_vllm(llm, sampling_params, prompt)
-
-            # Run generation using stored retrieval results
-            import time
-
-            from llm_utils import create_prompt
-
-            generation_times = []
-            responses = []
-
-            print("🤖 Running generation on pre-retrieved results...")
-            for i, item in enumerate(retrieval_results):
-                query = item["query"]
-                retrieved_docs = item["retrieved_docs"]
-
-                # Prepare context from retrieved docs
-                context = "\n\n".join([doc["text"] for doc in retrieved_docs])
-                prompt = create_prompt(context, query, "emails")
-
-                # Time generation only
-                gen_start = time.time()
-                response = llm_func(prompt)
-                gen_time = time.time() - gen_start
-
-                generation_times.append(gen_time)
-                responses.append(response)
-
-                if i < 3:
-                    print(f"  Q{i + 1}: Gen={gen_time:.3f}s")
-
-            avg_gen_time = sum(generation_times) / len(generation_times)
-
-            print("\n📊 Generation Results:")
-            print(f"  Total Queries: {len(retrieval_results)}")
-            print(f"  Avg Generation Time: {avg_gen_time:.3f}s")
-            print("  (Search time from Stage 4)")
-
-            results_out["stage5"] = {
-                "total_queries": len(retrieval_results),
-                "avg_generation_time": avg_gen_time,
-                "generation_times": generation_times,
-                "responses": responses,
-            }
-
-            # Show sample results
-            print("\n📝 Sample Results:")
-            for i in range(min(3, len(retrieval_results))):
-                query = retrieval_results[i]["query"]
-                response = responses[i]
-                print(f"  Q{i + 1}: {query[:60]}...")
-                print(f"  A{i + 1}: {response[:100]}...")
-                print()
-
-        except Exception as e:
-            print(f"❌ Generation evaluation failed: {e}")
-            print("💡 Make sure transformers/vllm is installed and model is available")
-
-        print("✅ Stage 5 completed!\n")
-
-    if args.output and results_out:
-        with open(args.output, "w", encoding="utf-8") as f:
-            json.dump(results_out, f, indent=2)
-        print(f"📝 Saved results to {args.output}")
-
-
-if __name__ == "__main__":
-    main()
--- a/benchmarks/enron_emails/setup_enron_emails.py
+++ b/benchmarks/enron_emails/setup_enron_emails.py
@@ -1,359 +0,0 @@
-"""
-Enron Emails Benchmark Setup Script
-Prepares passages from emails.csv, builds LEANN index, and FAISS Flat baseline
-"""
-
-import argparse
-import csv
-import json
-import os
-import re
-from collections.abc import Iterable
-from email import message_from_string
-from email.policy import default
-from pathlib import Path
-from typing import Optional
-
-from leann import LeannBuilder
-
-
-class EnronSetup:
-    def __init__(self, data_dir: str = "data"):
-        self.data_dir = Path(data_dir)
-        self.data_dir.mkdir(parents=True, exist_ok=True)
-
-        self.passages_preview = self.data_dir / "enron_passages_preview.jsonl"
-        self.index_path = self.data_dir / "enron_index_hnsw.leann"
-        self.queries_file = self.data_dir / "evaluation_queries.jsonl"
-        self.downloads_dir = self.data_dir / "downloads"
-        self.downloads_dir.mkdir(parents=True, exist_ok=True)
-
-    # ----------------------------
-    # Dataset acquisition
-    # ----------------------------
-    def ensure_emails_csv(self, emails_csv: Optional[str]) -> str:
-        """Return a path to emails.csv, downloading from Kaggle if needed."""
-        if emails_csv:
-            p = Path(emails_csv)
-            if not p.exists():
-                raise FileNotFoundError(f"emails.csv not found: {emails_csv}")
-            return str(p)
-
-        print(
-            "📥 Trying to download Enron emails.csv from Kaggle (wcukierski/enron-email-dataset)..."
-        )
-        try:
-            from kaggle.api.kaggle_api_extended import KaggleApi
-
-            api = KaggleApi()
-            api.authenticate()
-            api.dataset_download_files(
-                "wcukierski/enron-email-dataset", path=str(self.downloads_dir), unzip=True
-            )
-            candidate = self.downloads_dir / "emails.csv"
-            if candidate.exists():
-                print(f"✅ Downloaded emails.csv: {candidate}")
-                return str(candidate)
-            else:
-                raise FileNotFoundError(
-                    f"emails.csv was not found in {self.downloads_dir} after Kaggle download"
-                )
-        except Exception as e:
-            print(
-                "❌ Could not download via Kaggle automatically. Provide --emails-csv or configure Kaggle API."
-            )
-            print(
-                "   Set KAGGLE_USERNAME and KAGGLE_KEY env vars, or place emails.csv locally and pass --emails-csv."
-            )
-            raise e
-
-    # ----------------------------
-    # Data preparation
-    # ----------------------------
-    @staticmethod
-    def _extract_message_id(raw_email: str) -> str:
-        msg = message_from_string(raw_email, policy=default)
-        val = msg.get("Message-ID", "")
-        if val.startswith("<") and val.endswith(">"):
-            val = val[1:-1]
-        return val or ""
-
-    @staticmethod
-    def _split_header_body(raw_email: str) -> tuple[str, str]:
-        parts = raw_email.split("\n\n", 1)
-        if len(parts) == 2:
-            return parts[0].strip(), parts[1].strip()
-        # Heuristic fallback
-        first_lines = raw_email.splitlines()
-        if first_lines and ":" in first_lines[0]:
-            return raw_email.strip(), ""
-        return "", raw_email.strip()
-
-    @staticmethod
-    def _split_fixed_words(text: str, chunk_words: int, keep_last: bool) -> list[str]:
-        text = (text or "").strip()
-        if not text:
-            return []
-        if chunk_words <= 0:
-            return [text]
-        words = text.split()
-        if not words:
-            return []
-        limit = len(words)
-        if not keep_last:
-            limit = (len(words) // chunk_words) * chunk_words
-        if limit == 0:
-            return []
-        chunks = [" ".join(words[i : i + chunk_words]) for i in range(0, limit, chunk_words)]
-        return [c for c in (s.strip() for s in chunks) if c]
-
-    def _iter_passages_from_csv(
-        self,
-        emails_csv: Path,
-        chunk_words: int = 256,
-        keep_last_header: bool = True,
-        keep_last_body: bool = True,
-        max_emails: int | None = None,
-    ) -> Iterable[dict]:
-        with open(emails_csv, encoding="utf-8") as f:
-            reader = csv.DictReader(f)
-            count = 0
-            for i, row in enumerate(reader):
-                if max_emails is not None and count >= max_emails:
-                    break
-
-                raw_message = row.get("message", "")
-                email_file_id = row.get("file", "")
-
-                if not raw_message.strip():
-                    continue
-
-                message_id = self._extract_message_id(raw_message)
-                if not message_id:
-                    # Fallback ID based on CSV position and file path
-                    safe_file = re.sub(r"[^A-Za-z0-9_.-]", "_", email_file_id)
-                    message_id = f"enron_{i}_{safe_file}"
-
-                header, body = self._split_header_body(raw_message)
-
-                # Header chunks
-                for chunk in self._split_fixed_words(header, chunk_words, keep_last_header):
-                    yield {
-                        "text": chunk,
-                        "metadata": {
-                            "message_id": message_id,
-                            "is_header": True,
-                            "email_file_id": email_file_id,
-                        },
-                    }
-
-                # Body chunks
-                for chunk in self._split_fixed_words(body, chunk_words, keep_last_body):
-                    yield {
-                        "text": chunk,
-                        "metadata": {
-                            "message_id": message_id,
-                            "is_header": False,
-                            "email_file_id": email_file_id,
-                        },
-                    }
-
-                count += 1
-
-    # ----------------------------
-    # Build LEANN index and FAISS baseline
-    # ----------------------------
-    def build_leann_index(
-        self,
-        emails_csv: Optional[str],
-        backend: str = "hnsw",
-        embedding_model: str = "sentence-transformers/all-mpnet-base-v2",
-        chunk_words: int = 256,
-        max_emails: int | None = None,
-    ) -> str:
-        emails_csv_path = self.ensure_emails_csv(emails_csv)
-        print(f"🏗️ Building LEANN index from {emails_csv_path}...")
-
-        builder = LeannBuilder(
-            backend_name=backend,
-            embedding_model=embedding_model,
-            embedding_mode="sentence-transformers",
-            graph_degree=32,
-            complexity=64,
-            is_recompute=True,
-            is_compact=True,
-            num_threads=4,
-        )
-
-        # Stream passages and add to builder
-        preview_written = 0
-        with open(self.passages_preview, "w", encoding="utf-8") as preview_out:
-            for p in self._iter_passages_from_csv(
-                Path(emails_csv_path), chunk_words=chunk_words, max_emails=max_emails
-            ):
-                builder.add_text(p["text"], metadata=p["metadata"])
-                if preview_written < 200:
-                    preview_out.write(json.dumps({"text": p["text"][:200], **p["metadata"]}) + "\n")
-                    preview_written += 1
-
-        print(f"🔨 Building index at {self.index_path}...")
-        builder.build_index(str(self.index_path))
-        print("✅ LEANN index built!")
-        return str(self.index_path)
-
-    def build_faiss_flat_baseline(self, index_path: str, output_dir: str = "baseline") -> str:
-        print("🔨 Building FAISS Flat baseline from LEANN passages...")
-
-        import pickle
-
-        import numpy as np
-        from leann.api import compute_embeddings
-        from leann_backend_hnsw import faiss
-
-        os.makedirs(output_dir, exist_ok=True)
-        baseline_path = os.path.join(output_dir, "faiss_flat.index")
-        metadata_path = os.path.join(output_dir, "metadata.pkl")
-
-        if os.path.exists(baseline_path) and os.path.exists(metadata_path):
-            print(f"✅ Baseline already exists at {baseline_path}")
-            return baseline_path
-
-        # Read meta for passage source and embedding model
-        meta_path = f"{index_path}.meta.json"
-        with open(meta_path, encoding="utf-8") as f:
-            meta = json.load(f)
-
-        embedding_model = meta["embedding_model"]
-        passage_source = meta["passage_sources"][0]
-        passage_file = passage_source["path"]
-
-        if not os.path.isabs(passage_file):
-            index_dir = os.path.dirname(index_path)
-            passage_file = os.path.join(index_dir, os.path.basename(passage_file))
-
-        # Load passages from builder output so IDs match LEANN
-        passages: list[str] = []
-        passage_ids: list[str] = []
-        with open(passage_file, encoding="utf-8") as f:
-            for line in f:
-                if not line.strip():
-                    continue
-                data = json.loads(line)
-                passages.append(data["text"])
-                passage_ids.append(data["id"])  # builder-assigned ID
-
-        print(f"📄 Loaded {len(passages)} passages for baseline")
-        print(f"🤖 Embedding model: {embedding_model}")
-
-        embeddings = compute_embeddings(
-            passages,
-            embedding_model,
-            mode="sentence-transformers",
-            use_server=False,
-        )
-
-        # Build FAISS IndexFlatIP
-        dim = embeddings.shape[1]
-        index = faiss.IndexFlatIP(dim)
-        emb_f32 = embeddings.astype(np.float32)
-        index.add(emb_f32.shape[0], faiss.swig_ptr(emb_f32))
-
-        faiss.write_index(index, baseline_path)
-        with open(metadata_path, "wb") as pf:
-            pickle.dump(passage_ids, pf)
-
-        print(f"✅ FAISS baseline saved: {baseline_path}")
-        print(f"✅ Metadata saved: {metadata_path}")
-        print(f"📊 Total vectors: {index.ntotal}")
-        return baseline_path
-
-    # ----------------------------
-    # Queries (optional): prepare evaluation queries file
-    # ----------------------------
-    def prepare_queries(self, min_realism: float = 0.85) -> Path:
-        print(
-            "📝 Preparing evaluation queries from HuggingFace dataset corbt/enron_emails_sample_questions ..."
-        )
-        try:
-            from datasets import load_dataset
-
-            ds = load_dataset("corbt/enron_emails_sample_questions", split="train")
-        except Exception as e:
-            print(f"⚠️  Failed to load dataset: {e}")
-            return self.queries_file
-
-        kept = 0
-        with open(self.queries_file, "w", encoding="utf-8") as out:
-            for i, item in enumerate(ds):
-                how_realistic = float(item.get("how_realistic", 0.0))
-                if how_realistic < min_realism:
-                    continue
-                qid = str(item.get("id", f"enron_q_{i}"))
-                query = item.get("question", "")
-                if not query:
-                    continue
-                record = {
-                    "id": qid,
-                    "query": query,
-                    # For reference only, not used in recall metric below
-                    "gt_message_ids": item.get("message_ids", []),
-                }
-                out.write(json.dumps(record) + "\n")
-                kept += 1
-        print(f"✅ Wrote {kept} queries to {self.queries_file}")
-        return self.queries_file
-
-
-def main():
-    parser = argparse.ArgumentParser(description="Setup Enron Emails Benchmark")
-    parser.add_argument(
-        "--emails-csv",
-        help="Path to emails.csv (Enron dataset). If omitted, attempt Kaggle download.",
-    )
-    parser.add_argument("--data-dir", default="data", help="Data directory")
-    parser.add_argument("--backend", choices=["hnsw", "diskann"], default="hnsw")
-    parser.add_argument(
-        "--embedding-model",
-        default="sentence-transformers/all-mpnet-base-v2",
-        help="Embedding model for LEANN",
-    )
-    parser.add_argument("--chunk-words", type=int, default=256, help="Fixed word chunk size")
-    parser.add_argument("--max-emails", type=int, help="Limit number of emails to process")
-    parser.add_argument("--skip-queries", action="store_true", help="Skip creating queries file")
-    parser.add_argument("--skip-build", action="store_true", help="Skip building LEANN index")
-
-    args = parser.parse_args()
-
-    setup = EnronSetup(args.data_dir)
-
-    # Build index
-    if not args.skip_build:
-        index_path = setup.build_leann_index(
-            emails_csv=args.emails_csv,
-            backend=args.backend,
-            embedding_model=args.embedding_model,
-            chunk_words=args.chunk_words,
-            max_emails=args.max_emails,
-        )
-
-        # Build FAISS baseline from the same passages & embeddings
-        setup.build_faiss_flat_baseline(index_path)
-    else:
-        print("⏭️  Skipping LEANN index build and baseline")
-
-    # Queries file (optional)
-    if not args.skip_queries:
-        setup.prepare_queries()
-    else:
-        print("⏭️  Skipping query preparation")
-
-    print("\n🎉 Enron Emails setup completed!")
-    print(f"📁 Data directory: {setup.data_dir.absolute()}")
-    print("Next steps:")
-    print(
-        "1) Evaluate recall: python evaluate_enron_emails.py --index data/enron_index_hnsw.leann --stage 2"
-    )
-
-
-if __name__ == "__main__":
-    main()
--- a/benchmarks/financebench/README.md
+++ b/benchmarks/financebench/README.md
@@ -1,115 +0,0 @@
-# FinanceBench Benchmark for LEANN-RAG
-
-FinanceBench is a benchmark for evaluating retrieval-augmented generation (RAG) systems on financial document question-answering tasks.
-
-## Dataset
-
- **Source**: [PatronusAI/financebench](https://huggingface.co/datasets/PatronusAI/financebench)
- **Questions**: 150 financial Q&A examples
- **Documents**: 368 PDF files (10-K, 10-Q, 8-K, earnings reports)
- **Companies**: Major public companies (3M, Apple, Microsoft, Amazon, etc.)
- **Paper**: [FinanceBench: A New Benchmark for Financial Question Answering](https://arxiv.org/abs/2311.11944)
-
-## Structure
-
-```
-benchmarks/financebench/
-├── setup_financebench.py        # Downloads PDFs and builds index
-├── evaluate_financebench.py     # Intelligent evaluation script
-├── data/
-│   ├── financebench_merged.jsonl     # Q&A dataset
-│   ├── pdfs/                         # Downloaded financial documents
-│   └── index/                        # LEANN indexes
-│       └── financebench_full_hnsw.leann
-└── README.md
-```
-
-## Usage
-
-### 1. Setup (Download & Build Index)
-
-```bash
-cd benchmarks/financebench
-python setup_financebench.py
-```
-
-This will:
- Download the 150 Q&A examples
- Download all 368 PDF documents (parallel processing)
- Build a LEANN index from 53K+ text chunks
- Verify setup with test query
-
-### 2. Evaluation
-
-```bash
-# Basic retrieval evaluation
-python evaluate_financebench.py --index data/index/financebench_full_hnsw.leann
-
-
-# RAG generation evaluation with Qwen3-8B
-python evaluate_financebench.py --index data/index/financebench_full_hnsw.leann --stage 4 --complexity 64 --llm-backend hf --model-name Qwen/Qwen3-8B --output results_qwen3.json
-```
-
-## Evaluation Methods
-
-### Retrieval Evaluation
-Uses intelligent matching with three strategies:
-1. **Exact text overlap** - Direct substring matches
-2. **Number matching** - Key financial figures ($1,577, 1.2B, etc.)
-3. **Semantic similarity** - Word overlap with 20% threshold
-
-### QA Evaluation
-LLM-based answer evaluation using GPT-4o:
- Handles numerical rounding and equivalent representations
- Considers fractions, percentages, and decimal equivalents
- Evaluates semantic meaning rather than exact text match
-
-## Benchmark Results
-
-### LEANN-RAG Performance (sentence-transformers/all-mpnet-base-v2)
-
-**Retrieval Metrics:**
- **Question Coverage**: 100.0% (all questions retrieve relevant docs)
- **Exact Match Rate**: 0.7% (substring overlap with evidence)
- **Number Match Rate**: 120.7% (key financial figures matched)*
- **Semantic Match Rate**: 4.7% (word overlap ≥20%)
- **Average Search Time**: 0.097s
-
-**QA Metrics:**
- **Accuracy**: 42.7% (LLM-evaluated answer correctness)
- **Average QA Time**: 4.71s (end-to-end response time)
-
-**System Performance:**
- **Index Size**: 53,985 chunks from 368 PDFs
- **Build Time**: ~5-10 minutes with sentence-transformers/all-mpnet-base-v2
-
-*Note: Number match rate >100% indicates multiple retrieved documents contain the same financial figures, which is expected behavior for financial data appearing across multiple document sections.
-
-### LEANN-RAG Generation Performance (Qwen3-8B)
-
- **Stage 4 (Index Comparison):**
-  - Compact Index: 5.0 MB
-  - Non-compact Index: 172.2 MB
-  - **Storage Saving**: 97.1%
- **Search Performance**:
-  - Non-compact (no recompute): 0.009s avg per query
-  - Compact (with recompute): 2.203s avg per query
-  - Speed ratio: 0.004x
-
-**Generation Evaluation (20 queries, complexity=64):**
- **Average Search Time**: 1.638s per query
- **Average Generation Time**: 45.957s per query
- **LLM Backend**: HuggingFace transformers
- **Model**: Qwen/Qwen3-8B (thinking model with <think></think> processing)
- **Total Questions Processed**: 20
-
-## Options
-
-```bash
-# Use different backends
-python setup_financebench.py --backend diskann
-python evaluate_financebench.py --index data/index/financebench_full_diskann.leann
-
-# Use different embedding models
-python setup_financebench.py --embedding-model facebook/contriever
-```
--- a/benchmarks/financebench/evaluate_financebench.py
+++ b/benchmarks/financebench/evaluate_financebench.py
@@ -1,923 +0,0 @@
-"""
-FinanceBench Evaluation Script - Modular Recall-based Evaluation
-"""
-
-import argparse
-import json
-import logging
-import os
-import pickle
-import time
-from pathlib import Path
-from typing import Optional
-
-import numpy as np
-import openai
-from leann import LeannChat, LeannSearcher
-from leann_backend_hnsw import faiss
-
-from ..llm_utils import evaluate_rag, generate_hf, generate_vllm, load_hf_model, load_vllm_model
-
-# Setup logging to reduce verbose output
-logging.basicConfig(level=logging.WARNING)
-logging.getLogger("leann.api").setLevel(logging.WARNING)
-logging.getLogger("leann_backend_hnsw").setLevel(logging.WARNING)
-
-
-class RecallEvaluator:
-    """Stage 2: Evaluate Recall@3 (searcher vs baseline)"""
-
-    def __init__(self, index_path: str, baseline_dir: str):
-        self.index_path = index_path
-        self.baseline_dir = baseline_dir
-        self.searcher = LeannSearcher(index_path)
-
-        # Load FAISS flat baseline
-        baseline_index_path = os.path.join(baseline_dir, "faiss_flat.index")
-        metadata_path = os.path.join(baseline_dir, "metadata.pkl")
-
-        self.faiss_index = faiss.read_index(baseline_index_path)
-        with open(metadata_path, "rb") as f:
-            self.passage_ids = pickle.load(f)
-        print(f"📚 Loaded FAISS flat baseline with {self.faiss_index.ntotal} vectors")
-
-    def evaluate_recall_at_3(
-        self, queries: list[str], complexity: int = 64, recompute_embeddings: bool = True
-    ) -> float:
-        """Evaluate recall@3 for given queries at specified complexity"""
-        recompute_str = "with recompute" if recompute_embeddings else "no recompute"
-        print(f"🔍 Evaluating recall@3 with complexity={complexity} ({recompute_str})...")
-
-        total_recall = 0.0
-        num_queries = len(queries)
-
-        for i, query in enumerate(queries):
-            # Get ground truth: search with FAISS flat
-            from leann.api import compute_embeddings
-
-            query_embedding = compute_embeddings(
-                [query],
-                self.searcher.embedding_model,
-                mode=self.searcher.embedding_mode,
-                use_server=False,
-            ).astype(np.float32)
-
-            # Search FAISS flat for ground truth using LEANN's modified faiss API
-            n = query_embedding.shape[0]  # Number of queries
-            k = 3  # Number of nearest neighbors
-            distances = np.zeros((n, k), dtype=np.float32)
-            labels = np.zeros((n, k), dtype=np.int64)
-
-            self.faiss_index.search(
-                n,
-                faiss.swig_ptr(query_embedding),
-                k,
-                faiss.swig_ptr(distances),
-                faiss.swig_ptr(labels),
-            )
-
-            # Extract the results
-            baseline_ids = {self.passage_ids[idx] for idx in labels[0]}
-
-            # Search with LEANN at specified complexity
-            test_results = self.searcher.search(
-                query,
-                top_k=3,
-                complexity=complexity,
-                recompute_embeddings=recompute_embeddings,
-            )
-            test_ids = {result.id for result in test_results}
-
-            # Calculate recall@3 = |intersection| / |ground_truth|
-            intersection = test_ids.intersection(baseline_ids)
-            recall = len(intersection) / 3.0  # Ground truth size is 3
-            total_recall += recall
-
-            if i < 3:  # Show first few examples
-                print(f"  Query {i + 1}: '{query[:50]}...' -> Recall@3: {recall:.3f}")
-                print(f"    FAISS ground truth: {list(baseline_ids)}")
-                print(f"    LEANN results (C={complexity}, {recompute_str}): {list(test_ids)}")
-                print(f"    Intersection: {list(intersection)}")
-
-        avg_recall = total_recall / num_queries
-        print(f"📊 Average Recall@3: {avg_recall:.3f} ({avg_recall * 100:.1f}%)")
-        return avg_recall
-
-    def cleanup(self):
-        """Cleanup resources"""
-        if hasattr(self, "searcher"):
-            self.searcher.cleanup()
-
-
-class FinanceBenchEvaluator:
-    def __init__(self, index_path: str, openai_api_key: Optional[str] = None):
-        self.index_path = index_path
-        self.openai_client = openai.OpenAI(api_key=openai_api_key) if openai_api_key else None
-
-        self.searcher = LeannSearcher(index_path)
-        self.chat = LeannChat(index_path) if openai_api_key else None
-
-    def load_dataset(self, dataset_path: str = "data/financebench_merged.jsonl"):
-        """Load FinanceBench dataset"""
-        data = []
-        with open(dataset_path, encoding="utf-8") as f:
-            for line in f:
-                if line.strip():
-                    data.append(json.loads(line))
-
-        print(f"📊 Loaded {len(data)} FinanceBench examples")
-        return data
-
-    def analyze_index_sizes(self) -> dict:
-        """Analyze index sizes with and without embeddings"""
-
-        print("📏 Analyzing index sizes...")
-
-        # Get all index-related files
-        index_path = Path(self.index_path)
-        index_dir = index_path.parent
-        index_name = index_path.stem  # Remove .leann extension
-
-        sizes = {}
-        total_with_embeddings = 0
-
-        # Core index files
-        index_file = index_dir / f"{index_name}.index"
-        meta_file = index_dir / f"{index_path.name}.meta.json"  # Keep .leann for meta file
-        passages_file = index_dir / f"{index_path.name}.passages.jsonl"  # Keep .leann for passages
-        passages_idx_file = index_dir / f"{index_path.name}.passages.idx"  # Keep .leann for idx
-
-        for file_path, name in [
-            (index_file, "index"),
-            (meta_file, "metadata"),
-            (passages_file, "passages_text"),
-            (passages_idx_file, "passages_index"),
-        ]:
-            if file_path.exists():
-                size_mb = file_path.stat().st_size / (1024 * 1024)
-                sizes[name] = size_mb
-                total_with_embeddings += size_mb
-
-            else:
-                sizes[name] = 0
-
-        sizes["total_with_embeddings"] = total_with_embeddings
-        sizes["index_only_mb"] = sizes["index"]  # Just the .index file for fair comparison
-
-        print(f"  📁 Total index size: {total_with_embeddings:.1f} MB")
-        print(f"  📁 Index file only: {sizes['index']:.1f} MB")
-
-        return sizes
-
-    def create_compact_index_for_comparison(self, compact_index_path: str) -> dict:
-        """Create a compact index for comparison purposes"""
-        print("🏗️ Building compact index from existing passages...")
-
-        # Load existing passages from current index
-
-        from leann import LeannBuilder
-
-        current_index_path = Path(self.index_path)
-        current_index_dir = current_index_path.parent
-        current_index_name = current_index_path.name
-
-        # Read metadata to get passage source
-        meta_path = current_index_dir / f"{current_index_name}.meta.json"
-        with open(meta_path) as f:
-            import json
-
-            meta = json.load(f)
-
-        passage_source = meta["passage_sources"][0]
-        passage_file = passage_source["path"]
-
-        # Convert relative path to absolute
-        if not Path(passage_file).is_absolute():
-            passage_file = current_index_dir / Path(passage_file).name
-
-        print(f"📄 Loading passages from {passage_file}...")
-
-        # Build compact index with same passages
-        builder = LeannBuilder(
-            backend_name="hnsw",
-            embedding_model=meta["embedding_model"],
-            embedding_mode=meta.get("embedding_mode", "sentence-transformers"),
-            is_recompute=True,  # Enable recompute (no stored embeddings)
-            is_compact=True,  # Enable compact storage
-            **meta.get("backend_kwargs", {}),
-        )
-
-        # Load all passages
-        with open(passage_file, encoding="utf-8") as f:
-            for line in f:
-                if line.strip():
-                    data = json.loads(line)
-                    builder.add_text(data["text"], metadata=data.get("metadata", {}))
-
-        print(f"🔨 Building compact index at {compact_index_path}...")
-        builder.build_index(compact_index_path)
-
-        # Analyze the compact index size
-        temp_evaluator = FinanceBenchEvaluator(compact_index_path)
-        compact_sizes = temp_evaluator.analyze_index_sizes()
-        compact_sizes["index_type"] = "compact"
-
-        return compact_sizes
-
-    def create_non_compact_index_for_comparison(self, non_compact_index_path: str) -> dict:
-        """Create a non-compact index for comparison purposes"""
-        print("🏗️ Building non-compact index from existing passages...")
-
-        # Load existing passages from current index
-
-        from leann import LeannBuilder
-
-        current_index_path = Path(self.index_path)
-        current_index_dir = current_index_path.parent
-        current_index_name = current_index_path.name
-
-        # Read metadata to get passage source
-        meta_path = current_index_dir / f"{current_index_name}.meta.json"
-        with open(meta_path) as f:
-            import json
-
-            meta = json.load(f)
-
-        passage_source = meta["passage_sources"][0]
-        passage_file = passage_source["path"]
-
-        # Convert relative path to absolute
-        if not Path(passage_file).is_absolute():
-            passage_file = current_index_dir / Path(passage_file).name
-
-        print(f"📄 Loading passages from {passage_file}...")
-
-        # Build non-compact index with same passages
-        builder = LeannBuilder(
-            backend_name="hnsw",
-            embedding_model=meta["embedding_model"],
-            embedding_mode=meta.get("embedding_mode", "sentence-transformers"),
-            is_recompute=False,  # Disable recompute (store embeddings)
-            is_compact=False,  # Disable compact storage
-            **{
-                k: v
-                for k, v in meta.get("backend_kwargs", {}).items()
-                if k not in ["is_recompute", "is_compact"]
-            },
-        )
-
-        # Load all passages
-        with open(passage_file, encoding="utf-8") as f:
-            for line in f:
-                if line.strip():
-                    data = json.loads(line)
-                    builder.add_text(data["text"], metadata=data.get("metadata", {}))
-
-        print(f"🔨 Building non-compact index at {non_compact_index_path}...")
-        builder.build_index(non_compact_index_path)
-
-        # Analyze the non-compact index size
-        temp_evaluator = FinanceBenchEvaluator(non_compact_index_path)
-        non_compact_sizes = temp_evaluator.analyze_index_sizes()
-        non_compact_sizes["index_type"] = "non_compact"
-
-        return non_compact_sizes
-
-    def compare_index_performance(
-        self, non_compact_path: str, compact_path: str, test_data: list, complexity: int
-    ) -> dict:
-        """Compare performance between non-compact and compact indexes"""
-        print("⚡ Comparing search performance between indexes...")
-
-        import time
-
-        from leann import LeannSearcher
-
-        # Test queries
-        test_queries = [item["question"] for item in test_data[:5]]
-
-        results = {
-            "non_compact": {"search_times": []},
-            "compact": {"search_times": []},
-            "avg_search_times": {},
-            "speed_ratio": 0.0,
-        }
-
-        # Test non-compact index (no recompute)
-        print("  🔍 Testing non-compact index (no recompute)...")
-        non_compact_searcher = LeannSearcher(non_compact_path)
-
-        for query in test_queries:
-            start_time = time.time()
-            _ = non_compact_searcher.search(
-                query, top_k=3, complexity=complexity, recompute_embeddings=False
-            )
-            search_time = time.time() - start_time
-            results["non_compact"]["search_times"].append(search_time)
-
-        # Test compact index (with recompute)
-        print("  🔍 Testing compact index (with recompute)...")
-        compact_searcher = LeannSearcher(compact_path)
-
-        for query in test_queries:
-            start_time = time.time()
-            _ = compact_searcher.search(
-                query, top_k=3, complexity=complexity, recompute_embeddings=True
-            )
-            search_time = time.time() - start_time
-            results["compact"]["search_times"].append(search_time)
-
-        # Calculate averages
-        results["avg_search_times"]["non_compact"] = sum(
-            results["non_compact"]["search_times"]
-        ) / len(results["non_compact"]["search_times"])
-        results["avg_search_times"]["compact"] = sum(results["compact"]["search_times"]) / len(
-            results["compact"]["search_times"]
-        )
-
-        # Performance ratio
-        if results["avg_search_times"]["compact"] > 0:
-            results["speed_ratio"] = (
-                results["avg_search_times"]["non_compact"] / results["avg_search_times"]["compact"]
-            )
-        else:
-            results["speed_ratio"] = float("inf")
-
-        print(
-            f"    Non-compact (no recompute): {results['avg_search_times']['non_compact']:.3f}s avg"
-        )
-        print(f"    Compact (with recompute): {results['avg_search_times']['compact']:.3f}s avg")
-        print(f"    Speed ratio: {results['speed_ratio']:.2f}x")
-
-        # Cleanup
-        non_compact_searcher.cleanup()
-        compact_searcher.cleanup()
-
-        return results
-
-    def evaluate_timing_breakdown(
-        self, data: list[dict], max_samples: Optional[int] = None
-    ) -> dict:
-        """Evaluate timing breakdown and accuracy by hacking LeannChat.ask() for separated timing"""
-        if not self.chat or not self.openai_client:
-            print("⚠️  Skipping timing evaluation (no OpenAI API key provided)")
-            return {
-                "total_questions": 0,
-                "avg_search_time": 0.0,
-                "avg_generation_time": 0.0,
-                "avg_total_time": 0.0,
-                "accuracy": 0.0,
-            }
-
-        print("🔍🤖 Evaluating timing breakdown and accuracy (search + generation)...")
-
-        if max_samples:
-            data = data[:max_samples]
-            print(f"📝 Using first {max_samples} samples for timing evaluation")
-
-        search_times = []
-        generation_times = []
-        total_times = []
-        correct_answers = 0
-
-        for i, item in enumerate(data):
-            question = item["question"]
-            ground_truth = item["answer"]
-
-            try:
-                # Hack: Monkey-patch the ask method to capture internal timing
-                original_ask = self.chat.ask
-                captured_search_time = None
-                captured_generation_time = None
-
-                def patched_ask(*args, **kwargs):
-                    nonlocal captured_search_time, captured_generation_time
-
-                    # Time the search part
-                    search_start = time.time()
-                    results = self.chat.searcher.search(args[0], top_k=3, complexity=64)
-                    captured_search_time = time.time() - search_start
-
-                    # Time the generation part
-                    context = "\n\n".join([r.text for r in results])
-                    prompt = (
-                        "Here is some retrieved context that might help answer your question:\n\n"
-                        f"{context}\n\n"
-                        f"Question: {args[0]}\n\n"
-                        "Please provide the best answer you can based on this context and your knowledge."
-                    )
-
-                    generation_start = time.time()
-                    answer = self.chat.llm.ask(prompt)
-                    captured_generation_time = time.time() - generation_start
-
-                    return answer
-
-                # Apply the patch
-                self.chat.ask = patched_ask
-
-                # Time the total QA
-                total_start = time.time()
-                generated_answer = self.chat.ask(question)
-                total_time = time.time() - total_start
-
-                # Restore original method
-                self.chat.ask = original_ask
-
-                # Store the timings
-                search_times.append(captured_search_time)
-                generation_times.append(captured_generation_time)
-                total_times.append(total_time)
-
-                # Check accuracy using LLM as judge
-                is_correct = self._check_answer_accuracy(generated_answer, ground_truth, question)
-                if is_correct:
-                    correct_answers += 1
-
-                status = "✅" if is_correct else "❌"
-                print(
-                    f"Question {i + 1}/{len(data)}: {status} Search={captured_search_time:.3f}s, Gen={captured_generation_time:.3f}s, Total={total_time:.3f}s"
-                )
-                print(f"  GT: {ground_truth}")
-                print(f"  Gen: {generated_answer[:100]}...")
-
-            except Exception as e:
-                print(f"  ❌ Error: {e}")
-                search_times.append(0.0)
-                generation_times.append(0.0)
-                total_times.append(0.0)
-
-        accuracy = correct_answers / len(data) if data else 0.0
-
-        metrics = {
-            "total_questions": len(data),
-            "avg_search_time": sum(search_times) / len(search_times) if search_times else 0.0,
-            "avg_generation_time": sum(generation_times) / len(generation_times)
-            if generation_times
-            else 0.0,
-            "avg_total_time": sum(total_times) / len(total_times) if total_times else 0.0,
-            "accuracy": accuracy,
-            "correct_answers": correct_answers,
-            "search_times": search_times,
-            "generation_times": generation_times,
-            "total_times": total_times,
-        }
-
-        return metrics
-
-    def _check_answer_accuracy(
-        self, generated_answer: str, ground_truth: str, question: str
-    ) -> bool:
-        """Check if generated answer matches ground truth using LLM as judge"""
-        judge_prompt = f"""You are an expert judge evaluating financial question answering.
-
-Question: {question}
-
-Ground Truth Answer: {ground_truth}
-
-Generated Answer: {generated_answer}
-
-Task: Determine if the generated answer is factually correct compared to the ground truth. Focus on:
-1. Numerical accuracy (exact values, units, currency)
-2. Key financial concepts and terminology
-3. Overall factual correctness
-
-For financial data, small formatting differences are OK (e.g., "$1,577" vs "1577 million" vs "$1.577 billion"), but the core numerical value must match.
-
-Respond with exactly one word: "CORRECT" if the generated answer is factually accurate, or "INCORRECT" if it's wrong or significantly different."""
-
-        try:
-            judge_response = self.openai_client.chat.completions.create(
-                model="gpt-4o-mini",
-                messages=[{"role": "user", "content": judge_prompt}],
-                max_tokens=10,
-                temperature=0,
-            )
-            judgment = judge_response.choices[0].message.content.strip().upper()
-            return judgment == "CORRECT"
-        except Exception as e:
-            print(f"  ⚠️  Judge error: {e}, falling back to string matching")
-            # Fallback to simple string matching
-            gen_clean = generated_answer.strip().lower().replace("$", "").replace(",", "")
-            gt_clean = ground_truth.strip().lower().replace("$", "").replace(",", "")
-            return gt_clean in gen_clean
-
-    def _print_results(self, timing_metrics: dict):
-        """Print evaluation results"""
-        print("\n🎯 EVALUATION RESULTS")
-        print("=" * 50)
-
-        # Index comparison analysis
-        if "current_index" in timing_metrics and "non_compact_index" in timing_metrics:
-            print("\n📏 Index Comparison Analysis:")
-            current = timing_metrics["current_index"]
-            non_compact = timing_metrics["non_compact_index"]
-
-            print(f"  Compact index (current): {current.get('total_with_embeddings', 0):.1f} MB")
-            print(
-                f"  Non-compact index (with embeddings): {non_compact.get('total_with_embeddings', 0):.1f} MB"
-            )
-            print(
-                f"  Storage saving by compact: {timing_metrics.get('storage_saving_percent', 0):.1f}%"
-            )
-
-            print("  Component breakdown (non-compact):")
-            print(f"    - Main index: {non_compact.get('index', 0):.1f} MB")
-            print(f"    - Passages text: {non_compact.get('passages_text', 0):.1f} MB")
-            print(f"    - Passages index: {non_compact.get('passages_index', 0):.1f} MB")
-            print(f"    - Metadata: {non_compact.get('metadata', 0):.1f} MB")
-
-        # Performance comparison
-        if "performance_comparison" in timing_metrics:
-            perf = timing_metrics["performance_comparison"]
-            print("\n⚡ Performance Comparison:")
-            print(
-                f"  Non-compact (no recompute): {perf.get('avg_search_times', {}).get('non_compact', 0):.3f}s avg"
-            )
-            print(
-                f"  Compact (with recompute): {perf.get('avg_search_times', {}).get('compact', 0):.3f}s avg"
-            )
-            print(f"  Speed ratio: {perf.get('speed_ratio', 0):.2f}x")
-
-        # Legacy single index analysis (fallback)
-        if "total_with_embeddings" in timing_metrics and "current_index" not in timing_metrics:
-            print("\n📏 Index Size Analysis:")
-            print(f"  Total index size: {timing_metrics.get('total_with_embeddings', 0):.1f} MB")
-
-        print("\n📊 Accuracy:")
-        print(f"  Accuracy: {timing_metrics.get('accuracy', 0) * 100:.1f}%")
-        print(
-            f"  Correct Answers: {timing_metrics.get('correct_answers', 0)}/{timing_metrics.get('total_questions', 0)}"
-        )
-
-        print("\n📊 Timing Breakdown:")
-        print(f"  Total Questions: {timing_metrics.get('total_questions', 0)}")
-        print(f"  Avg Search Time: {timing_metrics.get('avg_search_time', 0):.3f}s")
-        print(f"  Avg Generation Time: {timing_metrics.get('avg_generation_time', 0):.3f}s")
-        print(f"  Avg Total Time: {timing_metrics.get('avg_total_time', 0):.3f}s")
-
-        if timing_metrics.get("avg_total_time", 0) > 0:
-            search_pct = (
-                timing_metrics.get("avg_search_time", 0)
-                / timing_metrics.get("avg_total_time", 1)
-                * 100
-            )
-            gen_pct = (
-                timing_metrics.get("avg_generation_time", 0)
-                / timing_metrics.get("avg_total_time", 1)
-                * 100
-            )
-            print("\n📈 Time Distribution:")
-            print(f"  Search: {search_pct:.1f}%")
-            print(f"  Generation: {gen_pct:.1f}%")
-
-    def cleanup(self):
-        """Cleanup resources"""
-        if self.searcher:
-            self.searcher.cleanup()
-
-
-def main():
-    parser = argparse.ArgumentParser(description="Modular FinanceBench Evaluation")
-    parser.add_argument("--index", required=True, help="Path to LEANN index")
-    parser.add_argument("--dataset", default="data/financebench_merged.jsonl", help="Dataset path")
-    parser.add_argument(
-        "--stage",
-        choices=["2", "3", "4", "all"],
-        default="all",
-        help="Which stage to run (2=recall, 3=complexity, 4=generation)",
-    )
-    parser.add_argument("--complexity", type=int, default=None, help="Complexity for search")
-    parser.add_argument("--baseline-dir", default="baseline", help="Baseline output directory")
-    parser.add_argument("--openai-api-key", help="OpenAI API key for generation evaluation")
-    parser.add_argument("--output", help="Save results to JSON file")
-    parser.add_argument(
-        "--llm-backend", choices=["openai", "hf", "vllm"], default="openai", help="LLM backend"
-    )
-    parser.add_argument("--model-name", default="Qwen3-8B", help="Model name for HF/vLLM")
-
-    args = parser.parse_args()
-
-    try:
-        # Check if baseline exists
-        baseline_index_path = os.path.join(args.baseline_dir, "faiss_flat.index")
-        if not os.path.exists(baseline_index_path):
-            print(f"❌ FAISS baseline not found at {baseline_index_path}")
-            print("💡 Please run setup_financebench.py first to build the baseline")
-            exit(1)
-
-        if args.stage == "2" or args.stage == "all":
-            # Stage 2: Recall@3 evaluation
-            print("🚀 Starting Stage 2: Recall@3 evaluation")
-
-            evaluator = RecallEvaluator(args.index, args.baseline_dir)
-
-            # Load FinanceBench queries for testing
-            print("📖 Loading FinanceBench dataset...")
-            queries = []
-            with open(args.dataset, encoding="utf-8") as f:
-                for line in f:
-                    if line.strip():
-                        data = json.loads(line)
-                        queries.append(data["question"])
-
-            # Test with more queries for robust measurement
-            test_queries = queries[:2000]
-            print(f"🧪 Testing with {len(test_queries)} queries")
-
-            # Test with complexity 64
-            complexity = 64
-            recall = evaluator.evaluate_recall_at_3(test_queries, complexity)
-            print(f"📈 Recall@3 at complexity {complexity}: {recall * 100:.1f}%")
-
-            evaluator.cleanup()
-            print("✅ Stage 2 completed!\n")
-
-        # Shared non-compact index path for Stage 3 and 4
-        non_compact_index_path = args.index.replace(".leann", "_noncompact.leann")
-        complexity = args.complexity
-
-        if args.stage == "3" or args.stage == "all":
-            # Stage 3: Binary search for 90% recall complexity (using non-compact index for speed)
-            print("🚀 Starting Stage 3: Binary search for 90% recall complexity")
-            print(
-                "💡 Creating non-compact index for fast binary search with recompute_embeddings=False"
-            )
-
-            # Create non-compact index for binary search (will be reused in Stage 4)
-            print("🏗️ Creating non-compact index for binary search...")
-            evaluator = FinanceBenchEvaluator(args.index)
-            evaluator.create_non_compact_index_for_comparison(non_compact_index_path)
-
-            # Use non-compact index for binary search
-            binary_search_evaluator = RecallEvaluator(non_compact_index_path, args.baseline_dir)
-
-            # Load queries for testing
-            print("📖 Loading FinanceBench dataset...")
-            queries = []
-            with open(args.dataset, encoding="utf-8") as f:
-                for line in f:
-                    if line.strip():
-                        data = json.loads(line)
-                        queries.append(data["question"])
-
-            # Use more queries for robust measurement
-            test_queries = queries[:200]
-            print(f"🧪 Testing with {len(test_queries)} queries")
-
-            # Binary search for 90% recall complexity (without recompute for speed)
-            target_recall = 0.9
-            min_complexity, max_complexity = 1, 32
-
-            print(f"🔍 Binary search for {target_recall * 100}% recall complexity...")
-            print(f"Search range: {min_complexity} to {max_complexity}")
-
-            best_complexity = None
-            best_recall = 0.0
-
-            while min_complexity <= max_complexity:
-                mid_complexity = (min_complexity + max_complexity) // 2
-
-                print(
-                    f"\n🧪 Testing complexity {mid_complexity} (no recompute, non-compact index)..."
-                )
-                # Use recompute_embeddings=False on non-compact index for fast binary search
-                recall = binary_search_evaluator.evaluate_recall_at_3(
-                    test_queries, mid_complexity, recompute_embeddings=False
-                )
-
-                print(
-                    f"  Complexity {mid_complexity}: Recall@3 = {recall:.3f} ({recall * 100:.1f}%)"
-                )
-
-                if recall >= target_recall:
-                    best_complexity = mid_complexity
-                    best_recall = recall
-                    max_complexity = mid_complexity - 1
-                    print("  ✅ Target reached! Searching for lower complexity...")
-                else:
-                    min_complexity = mid_complexity + 1
-                    print("  ❌ Below target. Searching for higher complexity...")
-
-            if best_complexity is not None:
-                print("\n🎯 Optimal complexity found!")
-                print(f"  Complexity: {best_complexity}")
-                print(f"  Recall@3: {best_recall:.3f} ({best_recall * 100:.1f}%)")
-
-                # Test a few complexities around the optimal one for verification
-                print("\n🔬 Verification test around optimal complexity:")
-                verification_complexities = [
-                    max(1, best_complexity - 2),
-                    max(1, best_complexity - 1),
-                    best_complexity,
-                    best_complexity + 1,
-                    best_complexity + 2,
-                ]
-
-                for complexity in verification_complexities:
-                    if complexity <= 512:  # reasonable upper bound
-                        recall = binary_search_evaluator.evaluate_recall_at_3(
-                            test_queries, complexity, recompute_embeddings=False
-                        )
-                        status = "✅" if recall >= target_recall else "❌"
-                        print(f"  {status} Complexity {complexity:3d}: {recall * 100:5.1f}%")
-
-                # Now test the optimal complexity with compact index and recompute for comparison
-                print(
-                    f"\n🔄 Testing optimal complexity {best_complexity} on compact index WITH recompute..."
-                )
-                compact_evaluator = RecallEvaluator(args.index, args.baseline_dir)
-                recall_with_recompute = compact_evaluator.evaluate_recall_at_3(
-                    test_queries[:10], best_complexity, recompute_embeddings=True
-                )
-                print(
-                    f"  ✅ Complexity {best_complexity} (compact index with recompute): {recall_with_recompute * 100:.1f}%"
-                )
-                complexity = best_complexity
-                print(
-                    f"  📊 Recall difference: {abs(best_recall - recall_with_recompute) * 100:.2f}%"
-                )
-                compact_evaluator.cleanup()
-            else:
-                print(f"\n❌ Could not find complexity achieving {target_recall * 100}% recall")
-                print("All tested complexities were below target.")
-
-            # Cleanup evaluators (keep non-compact index for Stage 4)
-            binary_search_evaluator.cleanup()
-            evaluator.cleanup()
-
-            print("✅ Stage 3 completed! Non-compact index saved for Stage 4.\n")
-
-        if args.stage == "4" or args.stage == "all":
-            # Stage 4: Comprehensive evaluation with dual index comparison
-            print("🚀 Starting Stage 4: Comprehensive evaluation with dual index comparison")
-
-            # Use FinanceBench evaluator for QA evaluation
-            evaluator = FinanceBenchEvaluator(
-                args.index, args.openai_api_key if args.llm_backend == "openai" else None
-            )
-
-            print("📖 Loading FinanceBench dataset...")
-            data = evaluator.load_dataset(args.dataset)
-
-            # Step 1: Analyze current (compact) index
-            print("\n📏 Analyzing current index (compact, pruned)...")
-            compact_size_metrics = evaluator.analyze_index_sizes()
-            compact_size_metrics["index_type"] = "compact"
-
-            # Step 2: Use existing non-compact index or create if needed
-            from pathlib import Path
-
-            if Path(non_compact_index_path).exists():
-                print(
-                    f"\n📁 Using existing non-compact index from Stage 3: {non_compact_index_path}"
-                )
-                temp_evaluator = FinanceBenchEvaluator(non_compact_index_path)
-                non_compact_size_metrics = temp_evaluator.analyze_index_sizes()
-                non_compact_size_metrics["index_type"] = "non_compact"
-            else:
-                print("\n🏗️ Creating non-compact index (with embeddings) for comparison...")
-                non_compact_size_metrics = evaluator.create_non_compact_index_for_comparison(
-                    non_compact_index_path
-                )
-
-            # Step 3: Compare index sizes
-            print("\n📊 Index size comparison:")
-            print(
-                f"  Compact index (current): {compact_size_metrics['total_with_embeddings']:.1f} MB"
-            )
-            print(
-                f"  Non-compact index: {non_compact_size_metrics['total_with_embeddings']:.1f} MB"
-            )
-            print("\n📊 Index-only size comparison (.index file only):")
-            print(f"  Compact index: {compact_size_metrics['index_only_mb']:.1f} MB")
-            print(f"  Non-compact index: {non_compact_size_metrics['index_only_mb']:.1f} MB")
-            # Use index-only size for fair comparison (same as Enron emails)
-            storage_saving = (
-                (non_compact_size_metrics["index_only_mb"] - compact_size_metrics["index_only_mb"])
-                / non_compact_size_metrics["index_only_mb"]
-                * 100
-            )
-            print(f"  Storage saving by compact: {storage_saving:.1f}%")
-
-            # Step 4: Performance comparison between the two indexes
-            if complexity is None:
-                raise ValueError("Complexity is required for performance comparison")
-
-            print("\n⚡ Performance comparison between indexes...")
-            performance_metrics = evaluator.compare_index_performance(
-                non_compact_index_path, args.index, data[:10], complexity=complexity
-            )
-
-            # Step 5: Generation evaluation
-            test_samples = 20
-            print(f"\n🧪 Testing with first {test_samples} samples for generation analysis")
-
-            if args.llm_backend == "openai" and args.openai_api_key:
-                print("🔍🤖 Running OpenAI-based generation evaluation...")
-                evaluation_start = time.time()
-                timing_metrics = evaluator.evaluate_timing_breakdown(data[:test_samples])
-                evaluation_time = time.time() - evaluation_start
-            else:
-                print(
-                    f"🔍🤖 Running {args.llm_backend} generation evaluation with {args.model_name}..."
-                )
-                try:
-                    # Load LLM
-                    if args.llm_backend == "hf":
-                        tokenizer, model = load_hf_model(args.model_name)
-
-                        def llm_func(prompt):
-                            return generate_hf(tokenizer, model, prompt)
-                    else:  # vllm
-                        llm, sampling_params = load_vllm_model(args.model_name)
-
-                        def llm_func(prompt):
-                            return generate_vllm(llm, sampling_params, prompt)
-
-                    # Simple generation evaluation
-                    queries = [item["question"] for item in data[:test_samples]]
-                    gen_results = evaluate_rag(
-                        evaluator.searcher,
-                        llm_func,
-                        queries,
-                        domain="finance",
-                        complexity=complexity,
-                    )
-
-                    timing_metrics = {
-                        "total_questions": len(queries),
-                        "avg_search_time": gen_results["avg_search_time"],
-                        "avg_generation_time": gen_results["avg_generation_time"],
-                        "results": gen_results["results"],
-                    }
-                    evaluation_time = time.time()
-
-                except Exception as e:
-                    print(f"❌ Generation evaluation failed: {e}")
-                    timing_metrics = {
-                        "total_questions": 0,
-                        "avg_search_time": 0,
-                        "avg_generation_time": 0,
-                    }
-                    evaluation_time = 0
-
-            # Combine all metrics
-            combined_metrics = {
-                **timing_metrics,
-                "total_evaluation_time": evaluation_time,
-                "current_index": compact_size_metrics,
-                "non_compact_index": non_compact_size_metrics,
-                "performance_comparison": performance_metrics,
-                "storage_saving_percent": storage_saving,
-            }
-
-            # Print results
-            print("\n📊 Generation Results:")
-            print(f"  Total Questions: {timing_metrics.get('total_questions', 0)}")
-            print(f"  Avg Search Time: {timing_metrics.get('avg_search_time', 0):.3f}s")
-            print(f"  Avg Generation Time: {timing_metrics.get('avg_generation_time', 0):.3f}s")
-
-            # Save results if requested
-            if args.output:
-                print(f"\n💾 Saving results to {args.output}...")
-                with open(args.output, "w") as f:
-                    json.dump(combined_metrics, f, indent=2, default=str)
-                print(f"✅ Results saved to {args.output}")
-
-            evaluator.cleanup()
-            print("✅ Stage 4 completed!\n")
-
-        if args.stage == "all":
-            print("🎉 All evaluation stages completed successfully!")
-            print("\n📋 Summary:")
-            print("  Stage 2: ✅ Recall@3 evaluation completed")
-            print("  Stage 3: ✅ Optimal complexity found")
-            print("  Stage 4: ✅ Generation accuracy & timing evaluation completed")
-            print("\n🔧 Recommended next steps:")
-            print("  - Use optimal complexity for best speed/accuracy balance")
-            print("  - Review accuracy and timing breakdown for performance optimization")
-            print("  - Run full evaluation on complete dataset if needed")
-
-            # Clean up non-compact index after all stages complete
-            print("\n🧹 Cleaning up temporary non-compact index...")
-            from pathlib import Path
-
-            if Path(non_compact_index_path).exists():
-                temp_index_dir = Path(non_compact_index_path).parent
-                temp_index_name = Path(non_compact_index_path).name
-                for temp_file in temp_index_dir.glob(f"{temp_index_name}*"):
-                    temp_file.unlink()
-                print(f"✅ Cleaned up {non_compact_index_path}")
-            else:
-                print("📝 No temporary index to clean up")
-    except KeyboardInterrupt:
-        print("\n⚠️  Evaluation interrupted by user")
-        exit(1)
-    except Exception as e:
-        print(f"\n❌ Stage {args.stage} failed: {e}")
-        exit(1)
-
-
-if __name__ == "__main__":
-    main()
--- a/benchmarks/financebench/setup_financebench.py
+++ b/benchmarks/financebench/setup_financebench.py
@@ -1,462 +0,0 @@
-#!/usr/bin/env python3
-"""
-FinanceBench Complete Setup Script
-Downloads all PDFs and builds full LEANN datastore
-"""
-
-import argparse
-import os
-import re
-import time
-from concurrent.futures import ThreadPoolExecutor, as_completed
-from pathlib import Path
-from threading import Lock
-
-import pymupdf
-import requests
-from leann import LeannBuilder, LeannSearcher
-from tqdm import tqdm
-
-
-class FinanceBenchSetup:
-    def __init__(self, data_dir: str = "data"):
-        self.base_dir = Path(__file__).parent  # benchmarks/financebench/
-        self.data_dir = self.base_dir / data_dir
-        self.pdf_dir = self.data_dir / "pdfs"
-        self.dataset_file = self.data_dir / "financebench_merged.jsonl"
-        self.index_dir = self.data_dir / "index"
-        self.download_lock = Lock()
-
-    def download_dataset(self):
-        """Download the main FinanceBench dataset"""
-        print("📊 Downloading FinanceBench dataset...")
-        self.data_dir.mkdir(parents=True, exist_ok=True)
-
-        if self.dataset_file.exists():
-            print(f"✅ Dataset already exists: {self.dataset_file}")
-            return
-
-        url = "https://huggingface.co/datasets/PatronusAI/financebench/raw/main/financebench_merged.jsonl"
-        response = requests.get(url, stream=True)
-        response.raise_for_status()
-
-        with open(self.dataset_file, "wb") as f:
-            for chunk in response.iter_content(chunk_size=8192):
-                f.write(chunk)
-
-        print(f"✅ Dataset downloaded: {self.dataset_file}")
-
-    def get_pdf_list(self):
-        """Get list of all PDF files from GitHub"""
-        print("📋 Fetching PDF list from GitHub...")
-
-        response = requests.get(
-            "https://api.github.com/repos/patronus-ai/financebench/contents/pdfs"
-        )
-        response.raise_for_status()
-        pdf_files = response.json()
-
-        print(f"Found {len(pdf_files)} PDF files")
-        return pdf_files
-
-    def download_single_pdf(self, pdf_info, position):
-        """Download a single PDF file"""
-        pdf_name = pdf_info["name"]
-        pdf_path = self.pdf_dir / pdf_name
-
-        # Skip if already downloaded
-        if pdf_path.exists() and pdf_path.stat().st_size > 0:
-            return f"✅ {pdf_name} (cached)"
-
-        try:
-            # Download PDF
-            response = requests.get(pdf_info["download_url"], timeout=60)
-            response.raise_for_status()
-
-            # Write to file
-            with self.download_lock:
-                with open(pdf_path, "wb") as f:
-                    f.write(response.content)
-
-            return f"✅ {pdf_name} ({len(response.content) // 1024}KB)"
-
-        except Exception as e:
-            return f"❌ {pdf_name}: {e!s}"
-
-    def download_all_pdfs(self, max_workers: int = 5):
-        """Download all PDF files with parallel processing"""
-        self.pdf_dir.mkdir(parents=True, exist_ok=True)
-
-        pdf_files = self.get_pdf_list()
-
-        print(f"📥 Downloading {len(pdf_files)} PDFs with {max_workers} workers...")
-
-        with ThreadPoolExecutor(max_workers=max_workers) as executor:
-            # Submit all download tasks
-            future_to_pdf = {
-                executor.submit(self.download_single_pdf, pdf_info, i): pdf_info["name"]
-                for i, pdf_info in enumerate(pdf_files)
-            }
-
-            # Process completed downloads with progress bar
-            with tqdm(total=len(pdf_files), desc="Downloading PDFs") as pbar:
-                for future in as_completed(future_to_pdf):
-                    result = future.result()
-                    pbar.set_postfix_str(result.split()[-1] if "✅" in result else "Error")
-                    pbar.update(1)
-
-        # Verify downloads
-        downloaded_pdfs = list(self.pdf_dir.glob("*.pdf"))
-        print(f"✅ Successfully downloaded {len(downloaded_pdfs)}/{len(pdf_files)} PDFs")
-
-        # Show any failures
-        missing_pdfs = []
-        for pdf_info in pdf_files:
-            pdf_path = self.pdf_dir / pdf_info["name"]
-            if not pdf_path.exists() or pdf_path.stat().st_size == 0:
-                missing_pdfs.append(pdf_info["name"])
-
-        if missing_pdfs:
-            print(f"⚠️  Failed to download {len(missing_pdfs)} PDFs:")
-            for pdf in missing_pdfs[:5]:  # Show first 5
-                print(f"   - {pdf}")
-            if len(missing_pdfs) > 5:
-                print(f"   ... and {len(missing_pdfs) - 5} more")
-
-    def build_leann_index(
-        self,
-        backend: str = "hnsw",
-        embedding_model: str = "sentence-transformers/all-mpnet-base-v2",
-    ):
-        """Build LEANN index from all PDFs"""
-        print(f"🏗️  Building LEANN index with {backend} backend...")
-
-        # Check if we have PDFs
-        pdf_files = list(self.pdf_dir.glob("*.pdf"))
-        if not pdf_files:
-            raise RuntimeError("No PDF files found! Run download first.")
-
-        print(f"Found {len(pdf_files)} PDF files to process")
-
-        start_time = time.time()
-
-        # Initialize builder with standard compact configuration
-        builder = LeannBuilder(
-            backend_name=backend,
-            embedding_model=embedding_model,
-            embedding_mode="sentence-transformers",
-            graph_degree=32,
-            complexity=64,
-            is_recompute=True,  # Enable recompute (no stored embeddings)
-            is_compact=True,  # Enable compact storage (pruned)
-            num_threads=4,
-        )
-
-        # Process PDFs and extract text
-        total_chunks = 0
-        failed_pdfs = []
-
-        for pdf_path in tqdm(pdf_files, desc="Processing PDFs"):
-            try:
-                chunks = self.extract_pdf_text(pdf_path)
-                for chunk in chunks:
-                    builder.add_text(chunk["text"], metadata=chunk["metadata"])
-                    total_chunks += 1
-
-            except Exception as e:
-                print(f"❌ Failed to process {pdf_path.name}: {e}")
-                failed_pdfs.append(pdf_path.name)
-                continue
-
-        # Build index in index directory
-        self.index_dir.mkdir(parents=True, exist_ok=True)
-        index_path = self.index_dir / f"financebench_full_{backend}.leann"
-        print(f"🔨 Building index: {index_path}")
-        builder.build_index(str(index_path))
-
-        build_time = time.time() - start_time
-
-        print("✅ Index built successfully!")
-        print(f"   📁 Index path: {index_path}")
-        print(f"   📊 Total chunks: {total_chunks:,}")
-        print(f"   📄 Processed PDFs: {len(pdf_files) - len(failed_pdfs)}/{len(pdf_files)}")
-        print(f"   ⏱️  Build time: {build_time:.1f}s")
-
-        if failed_pdfs:
-            print(f"   ⚠️  Failed PDFs: {failed_pdfs}")
-
-        return str(index_path)
-
-    def build_faiss_flat_baseline(self, index_path: str, output_dir: str = "baseline"):
-        """Build FAISS flat baseline using the same embeddings as LEANN index"""
-        print("🔨 Building FAISS Flat baseline...")
-
-        import os
-        import pickle
-
-        import numpy as np
-        from leann.api import compute_embeddings
-        from leann_backend_hnsw import faiss
-
-        os.makedirs(output_dir, exist_ok=True)
-        baseline_path = os.path.join(output_dir, "faiss_flat.index")
-        metadata_path = os.path.join(output_dir, "metadata.pkl")
-
-        if os.path.exists(baseline_path) and os.path.exists(metadata_path):
-            print(f"✅ Baseline already exists at {baseline_path}")
-            return baseline_path
-
-        # Read metadata from the built index
-        meta_path = f"{index_path}.meta.json"
-        with open(meta_path) as f:
-            import json
-
-            meta = json.loads(f.read())
-
-        embedding_model = meta["embedding_model"]
-        passage_source = meta["passage_sources"][0]
-        passage_file = passage_source["path"]
-
-        # Convert relative path to absolute
-        if not os.path.isabs(passage_file):
-            index_dir = os.path.dirname(index_path)
-            passage_file = os.path.join(index_dir, os.path.basename(passage_file))
-
-        print(f"📊 Loading passages from {passage_file}...")
-        print(f"🤖 Using embedding model: {embedding_model}")
-
-        # Load all passages for baseline
-        passages = []
-        passage_ids = []
-        with open(passage_file, encoding="utf-8") as f:
-            for line in f:
-                if line.strip():
-                    data = json.loads(line)
-                    passages.append(data["text"])
-                    passage_ids.append(data["id"])
-
-        print(f"📄 Loaded {len(passages)} passages")
-
-        # Compute embeddings using the same method as LEANN
-        print("🧮 Computing embeddings...")
-        embeddings = compute_embeddings(
-            passages,
-            embedding_model,
-            mode="sentence-transformers",
-            use_server=False,
-        )
-
-        print(f"📐 Embedding shape: {embeddings.shape}")
-
-        # Build FAISS flat index
-        print("🏗️  Building FAISS IndexFlatIP...")
-        dimension = embeddings.shape[1]
-        index = faiss.IndexFlatIP(dimension)
-
-        # Add embeddings to flat index
-        embeddings_f32 = embeddings.astype(np.float32)
-        index.add(embeddings_f32.shape[0], faiss.swig_ptr(embeddings_f32))
-
-        # Save index and metadata
-        faiss.write_index(index, baseline_path)
-        with open(metadata_path, "wb") as f:
-            pickle.dump(passage_ids, f)
-
-        print(f"✅ FAISS baseline saved to {baseline_path}")
-        print(f"✅ Metadata saved to {metadata_path}")
-        print(f"📊 Total vectors: {index.ntotal}")
-
-        return baseline_path
-
-    def extract_pdf_text(self, pdf_path: Path) -> list[dict]:
-        """Extract and chunk text from a PDF file"""
-        chunks = []
-        doc = pymupdf.open(pdf_path)
-
-        for page_num in range(len(doc)):
-            page = doc[page_num]
-            text = page.get_text()  # type: ignore
-
-            if not text.strip():
-                continue
-
-            # Create metadata
-            metadata = {
-                "source_file": pdf_path.name,
-                "page_number": page_num + 1,
-                "document_type": "10K" if "10K" in pdf_path.name else "10Q",
-                "company": pdf_path.name.split("_")[0],
-                "doc_period": self.extract_year_from_filename(pdf_path.name),
-            }
-
-            # Use recursive character splitting like LangChain
-            if len(text.split()) > 500:
-                # Split by double newlines (paragraphs)
-                paragraphs = [p.strip() for p in text.split("\n\n") if p.strip()]
-
-                current_chunk = ""
-                for para in paragraphs:
-                    # If adding this paragraph would make chunk too long, save current chunk
-                    if current_chunk and len((current_chunk + " " + para).split()) > 300:
-                        if current_chunk.strip():
-                            chunks.append(
-                                {
-                                    "text": current_chunk.strip(),
-                                    "metadata": {
-                                        **metadata,
-                                        "chunk_id": f"page_{page_num + 1}_chunk_{len(chunks)}",
-                                    },
-                                }
-                            )
-                        current_chunk = para
-                    else:
-                        current_chunk = (current_chunk + " " + para).strip()
-
-                # Add the last chunk
-                if current_chunk.strip():
-                    chunks.append(
-                        {
-                            "text": current_chunk.strip(),
-                            "metadata": {
-                                **metadata,
-                                "chunk_id": f"page_{page_num + 1}_chunk_{len(chunks)}",
-                            },
-                        }
-                    )
-            else:
-                # Page is short enough, use as single chunk
-                chunks.append(
-                    {
-                        "text": text.strip(),
-                        "metadata": {**metadata, "chunk_id": f"page_{page_num + 1}"},
-                    }
-                )
-
-        doc.close()
-        return chunks
-
-    def extract_year_from_filename(self, filename: str) -> str:
-        """Extract year from PDF filename"""
-        # Try to find 4-digit year in filename
-
-        match = re.search(r"(\d{4})", filename)
-        return match.group(1) if match else "unknown"
-
-    def verify_setup(self, index_path: str):
-        """Verify the setup by testing a simple query"""
-        print("🧪 Verifying setup with test query...")
-
-        try:
-            searcher = LeannSearcher(index_path)
-
-            # Test query
-            test_query = "What is the capital expenditure for 3M in 2018?"
-            results = searcher.search(test_query, top_k=3)
-
-            print(f"✅ Test query successful! Found {len(results)} results:")
-            for i, result in enumerate(results, 1):
-                company = result.metadata.get("company", "Unknown")
-                year = result.metadata.get("doc_period", "Unknown")
-                page = result.metadata.get("page_number", "Unknown")
-                print(f"   {i}. {company} {year} (page {page}) - Score: {result.score:.3f}")
-                print(f"      {result.text[:100]}...")
-
-            searcher.cleanup()
-            print("✅ Setup verification completed successfully!")
-
-        except Exception as e:
-            print(f"❌ Setup verification failed: {e}")
-            raise
-
-
-def main():
-    parser = argparse.ArgumentParser(description="Setup FinanceBench with full PDF datastore")
-    parser.add_argument("--data-dir", default="data", help="Data directory")
-    parser.add_argument(
-        "--backend", choices=["hnsw", "diskann"], default="hnsw", help="LEANN backend"
-    )
-    parser.add_argument(
-        "--embedding-model",
-        default="sentence-transformers/all-mpnet-base-v2",
-        help="Embedding model",
-    )
-    parser.add_argument("--max-workers", type=int, default=5, help="Parallel download workers")
-    parser.add_argument("--skip-download", action="store_true", help="Skip PDF download")
-    parser.add_argument("--skip-build", action="store_true", help="Skip index building")
-    parser.add_argument(
-        "--build-baseline-only",
-        action="store_true",
-        help="Only build FAISS baseline from existing index",
-    )
-
-    args = parser.parse_args()
-
-    print("🏦 FinanceBench Complete Setup")
-    print("=" * 50)
-
-    setup = FinanceBenchSetup(args.data_dir)
-
-    try:
-        if args.build_baseline_only:
-            # Only build baseline from existing index
-            index_path = setup.index_dir / f"financebench_full_{args.backend}"
-            index_file = f"{index_path}.index"
-            meta_file = f"{index_path}.leann.meta.json"
-
-            if not os.path.exists(index_file) or not os.path.exists(meta_file):
-                print("❌ Index files not found:")
-                print(f"   Index: {index_file}")
-                print(f"   Meta: {meta_file}")
-                print("💡 Run without --build-baseline-only to build the index first")
-                exit(1)
-
-            print(f"🔨 Building baseline from existing index: {index_path}")
-            baseline_path = setup.build_faiss_flat_baseline(str(index_path))
-            print(f"✅ Baseline built at {baseline_path}")
-            return
-
-        # Step 1: Download dataset
-        setup.download_dataset()
-
-        # Step 2: Download PDFs
-        if not args.skip_download:
-            setup.download_all_pdfs(max_workers=args.max_workers)
-        else:
-            print("⏭️  Skipping PDF download")
-
-        # Step 3: Build LEANN index
-        if not args.skip_build:
-            index_path = setup.build_leann_index(
-                backend=args.backend, embedding_model=args.embedding_model
-            )
-
-            # Step 4: Build FAISS flat baseline
-            print("\n🔨 Building FAISS flat baseline...")
-            baseline_path = setup.build_faiss_flat_baseline(index_path)
-            print(f"✅ Baseline built at {baseline_path}")
-
-            # Step 5: Verify setup
-            setup.verify_setup(index_path)
-        else:
-            print("⏭️  Skipping index building")
-
-        print("\n🎉 FinanceBench setup completed!")
-        print(f"📁 Data directory: {setup.data_dir.absolute()}")
-        print("\nNext steps:")
-        print(
-            "1. Run evaluation: python evaluate_financebench.py --index data/index/financebench_full_hnsw.leann"
-        )
-        print(
-            "2. Or test manually: python -c \"from leann import LeannSearcher; s = LeannSearcher('data/index/financebench_full_hnsw.leann'); print(s.search('3M capital expenditure 2018'))\""
-        )
-
-    except KeyboardInterrupt:
-        print("\n⚠️  Setup interrupted by user")
-        exit(1)
-    except Exception as e:
-        print(f"\n❌ Setup failed: {e}")
-        exit(1)
-
-
-if __name__ == "__main__":
-    main()
--- a/benchmarks/financebench/verify_recall.py
+++ b/benchmarks/financebench/verify_recall.py
@@ -1,214 +0,0 @@
-#!/usr/bin/env python3
-# /// script
-# requires-python = ">=3.9"
-# dependencies = [
-#     "faiss-cpu",
-#     "numpy",
-#     "sentence-transformers",
-#     "torch",
-#     "tqdm",
-# ]
-# ///
-
-"""
-Independent recall verification script using standard FAISS.
-Creates two indexes (HNSW and Flat) and compares recall@3 at different complexities.
-"""
-
-import json
-import time
-from pathlib import Path
-
-import faiss
-import numpy as np
-from sentence_transformers import SentenceTransformer
-from tqdm import tqdm
-
-
-def compute_embeddings_direct(chunks: list[str], model_name: str) -> np.ndarray:
-    """
-    Direct embedding computation using sentence-transformers.
-    Copied logic to avoid dependency issues.
-    """
-    print(f"Loading model: {model_name}")
-    model = SentenceTransformer(model_name)
-
-    print(f"Computing embeddings for {len(chunks)} chunks...")
-    embeddings = model.encode(
-        chunks,
-        show_progress_bar=True,
-        batch_size=32,
-        convert_to_numpy=True,
-        normalize_embeddings=False,
-    )
-
-    return embeddings.astype(np.float32)
-
-
-def load_financebench_queries(dataset_path: str, max_queries: int = 200) -> list[str]:
-    """Load FinanceBench queries from dataset"""
-    queries = []
-    with open(dataset_path, encoding="utf-8") as f:
-        for line in f:
-            if line.strip():
-                data = json.loads(line)
-                queries.append(data["question"])
-                if len(queries) >= max_queries:
-                    break
-    return queries
-
-
-def load_passages_from_leann_index(index_path: str) -> tuple[list[str], list[str]]:
-    """Load passages from LEANN index structure"""
-    meta_path = f"{index_path}.meta.json"
-    with open(meta_path) as f:
-        meta = json.load(f)
-
-    passage_source = meta["passage_sources"][0]
-    passage_file = passage_source["path"]
-
-    # Convert relative path to absolute
-    if not Path(passage_file).is_absolute():
-        index_dir = Path(index_path).parent
-        passage_file = index_dir / Path(passage_file).name
-
-    print(f"Loading passages from {passage_file}")
-
-    passages = []
-    passage_ids = []
-    with open(passage_file, encoding="utf-8") as f:
-        for line in tqdm(f, desc="Loading passages"):
-            if line.strip():
-                data = json.loads(line)
-                passages.append(data["text"])
-                passage_ids.append(data["id"])
-
-    print(f"Loaded {len(passages)} passages")
-    return passages, passage_ids
-
-
-def build_faiss_indexes(embeddings: np.ndarray) -> tuple[faiss.Index, faiss.Index]:
-    """Build FAISS indexes: Flat (ground truth) and HNSW"""
-    dimension = embeddings.shape[1]
-
-    # Build Flat index (ground truth)
-    print("Building FAISS IndexFlatIP (ground truth)...")
-    flat_index = faiss.IndexFlatIP(dimension)
-    flat_index.add(embeddings)
-
-    # Build HNSW index
-    print("Building FAISS IndexHNSWFlat...")
-    M = 32  # Same as LEANN default
-    hnsw_index = faiss.IndexHNSWFlat(dimension, M, faiss.METRIC_INNER_PRODUCT)
-    hnsw_index.hnsw.efConstruction = 200  # Same as LEANN default
-    hnsw_index.add(embeddings)
-
-    print(f"Built indexes with {flat_index.ntotal} vectors, dimension {dimension}")
-    return flat_index, hnsw_index
-
-
-def evaluate_recall_at_k(
-    query_embeddings: np.ndarray,
-    flat_index: faiss.Index,
-    hnsw_index: faiss.Index,
-    passage_ids: list[str],
-    k: int = 3,
-    ef_search: int = 64,
-) -> float:
-    """Evaluate recall@k comparing HNSW vs Flat"""
-
-    # Set search parameters for HNSW
-    hnsw_index.hnsw.efSearch = ef_search
-
-    total_recall = 0.0
-    num_queries = query_embeddings.shape[0]
-
-    for i in range(num_queries):
-        query = query_embeddings[i : i + 1]  # Keep 2D shape
-
-        # Get ground truth from Flat index (standard FAISS API)
-        flat_distances, flat_indices = flat_index.search(query, k)
-        ground_truth_ids = {passage_ids[idx] for idx in flat_indices[0]}
-
-        # Get results from HNSW index (standard FAISS API)
-        hnsw_distances, hnsw_indices = hnsw_index.search(query, k)
-        hnsw_ids = {passage_ids[idx] for idx in hnsw_indices[0]}
-
-        # Calculate recall
-        intersection = ground_truth_ids.intersection(hnsw_ids)
-        recall = len(intersection) / k
-        total_recall += recall
-
-        if i < 3:  # Show first few examples
-            print(f"  Query {i + 1}: Recall@{k} = {recall:.3f}")
-            print(f"    Flat: {list(ground_truth_ids)}")
-            print(f"    HNSW: {list(hnsw_ids)}")
-            print(f"    Intersection: {list(intersection)}")
-
-    avg_recall = total_recall / num_queries
-    return avg_recall
-
-
-def main():
-    # Configuration
-    dataset_path = "data/financebench_merged.jsonl"
-    index_path = "data/index/financebench_full_hnsw.leann"
-    embedding_model = "sentence-transformers/all-mpnet-base-v2"
-
-    print("🔍 FAISS Recall Verification")
-    print("=" * 50)
-
-    # Check if files exist
-    if not Path(dataset_path).exists():
-        print(f"❌ Dataset not found: {dataset_path}")
-        return
-    if not Path(f"{index_path}.meta.json").exists():
-        print(f"❌ Index metadata not found: {index_path}.meta.json")
-        return
-
-    # Load data
-    print("📖 Loading FinanceBench queries...")
-    queries = load_financebench_queries(dataset_path, max_queries=50)
-    print(f"Loaded {len(queries)} queries")
-
-    print("📄 Loading passages from LEANN index...")
-    passages, passage_ids = load_passages_from_leann_index(index_path)
-
-    # Compute embeddings
-    print("🧮 Computing passage embeddings...")
-    passage_embeddings = compute_embeddings_direct(passages, embedding_model)
-
-    print("🧮 Computing query embeddings...")
-    query_embeddings = compute_embeddings_direct(queries, embedding_model)
-
-    # Build FAISS indexes
-    print("🏗️ Building FAISS indexes...")
-    flat_index, hnsw_index = build_faiss_indexes(passage_embeddings)
-
-    # Test different efSearch values (equivalent to LEANN complexity)
-    print("\n📊 Evaluating Recall@3 at different efSearch values...")
-    ef_search_values = [16, 32, 64, 128, 256]
-
-    for ef_search in ef_search_values:
-        print(f"\n🧪 Testing efSearch = {ef_search}")
-        start_time = time.time()
-
-        recall = evaluate_recall_at_k(
-            query_embeddings, flat_index, hnsw_index, passage_ids, k=3, ef_search=ef_search
-        )
-
-        elapsed = time.time() - start_time
-        print(
-            f"📈 efSearch {ef_search}: Recall@3 = {recall:.3f} ({recall * 100:.1f}%) in {elapsed:.2f}s"
-        )
-
-    print("\n✅ Verification completed!")
-    print("\n📋 Summary:")
-    print("  - Built independent FAISS Flat and HNSW indexes")
-    print("  - Compared recall@3 at different efSearch values")
-    print("  - Used same embedding model as LEANN")
-    print("  - This validates LEANN's recall measurements")
-
-
-if __name__ == "__main__":
-    main()
--- a/benchmarks/generation_speed_bench.py
+++ b/benchmarks/generation_speed_bench.py
@@ -0,0 +1,114 @@
+import argparse
+import re
+import sys
+import time
+from pathlib import Path
+from statistics import mean
+
+from leann.chat import get_llm
+
+
+def parse_prompts_from_file(file_path: str) -> list[str]:
+    """
+    Parse a prompt dump file into individual prompt strings.
+
+    Splits by lines that look like: "PROMPT #<n>:".
+    Keeps the content from each marker up to the next marker (or EOF).
+    """
+    with open(file_path, "r", encoding="utf-8") as f:
+        text = f.read()
+
+    matches = list(re.finditer(r"^PROMPT\s+#\d+:\s*$", text, flags=re.MULTILINE))
+    if not matches:
+        # Fallback: try a more permissive pattern
+        matches = list(
+            re.finditer(r"^=+\nPROMPT\s+#\d+:\n=+\s*$", text, flags=re.MULTILINE)
+        )
+
+    prompts: list[str] = []
+    if not matches:
+        # No explicit markers; treat the whole file as a single prompt
+        return [text]
+
+    for i, m in enumerate(matches):
+        start = m.end()
+        end = matches[i + 1].start() if i + 1 < len(matches) else len(text)
+        block = text[start:end].strip()
+        # Reattach the marker line content above the block for full context
+        header_line_start = text.rfind("\n", 0, m.start()) + 1
+        header = text[header_line_start : m.end()].strip()
+        prompts.append(f"{header}\n{block}".strip())
+
+    return prompts
+
+
+def main():
+    parser = argparse.ArgumentParser(
+        description=(
+            "Iterate prompts in a dump file, time generations, print outputs, and report last-10 average time."
+        )
+    )
+    parser.add_argument(
+        "--path",
+        default="benchmarks/data/prompts_g5/prompt_dump_nq_hnsw.txt",
+        help="Path to the prompt dump file",
+    )
+    parser.add_argument(
+        "--type",
+        default="ollama",
+        choices=["hf", "openai", "ollama", "gemini", "simulated"],
+        help="LLM backend type",
+    )
+    parser.add_argument(
+        "--model",
+        default="Qwen/Qwen3-4B",
+        help="Model identifier (depends on backend)",
+    )
+    parser.add_argument(
+        "--max_tokens",
+        type=int,
+        default=512,
+        help="Max new tokens to generate per prompt",
+    )
+    args = parser.parse_args()
+
+    llm_config = {"type": args.type, "model": args.model}
+    chat = get_llm(llm_config)
+
+    prompts = parse_prompts_from_file(args.path)
+    print(f"Found {len(prompts)} prompts in {args.path}")
+
+    times: list[float] = []
+    for idx, prompt in enumerate(prompts, start=1):
+        print("\n" + "=" * 80)
+        print(f"PROMPT {idx}/{len(prompts)}")
+        print("-" * 80)
+        start = time.perf_counter()
+        try:
+            output = chat.ask(prompt, max_tokens=args.max_tokens)
+        except Exception as e:
+            output = f"<error: {e}>"
+        elapsed = time.perf_counter() - start
+        times.append(elapsed)
+        print(f"Time: {elapsed:.3f}s")
+        print("-" * 80)
+        print(output)
+        print("=" * 80)
+
+    if times:
+        window = times[-10:] if len(times) >= 10 else times
+        avg_last_10 = mean(window)
+        print(
+            f"\nAverage time over last {len(window)} prompts: {avg_last_10:.3f}s"
+        )
+    else:
+        print("No prompts processed.")
+
+
+if __name__ == "__main__":
+    main()
+
+
+
+
+
--- a/benchmarks/laion/.gitignore
+++ b/benchmarks/laion/.gitignore
@@ -1 +0,0 @@
-data/
--- a/benchmarks/laion/README.md
+++ b/benchmarks/laion/README.md
@@ -1,199 +0,0 @@
-# LAION Multimodal Benchmark
-
-A multimodal benchmark for evaluating image retrieval and generation performance using LEANN with CLIP embeddings and Qwen2.5-VL for multimodal generation on LAION dataset subset.
-
-## Overview
-
-This benchmark evaluates:
- **Image retrieval timing** using caption-based queries
- **Recall@K performance** for image search
- **Complexity analysis** across different search parameters
- **Index size and storage efficiency**
- **Multimodal generation** with Qwen2.5-VL for image understanding and description
-
-## Dataset Configuration
-
- **Dataset**: LAION-400M subset (10,000 images)
- **Embeddings**: Pre-computed CLIP ViT-B/32 (512 dimensions)
- **Queries**: 200 random captions from the dataset
- **Ground Truth**: Self-recall (query caption → original image)
-
-## Quick Start
-
-### 1. Setup the benchmark
-
-```bash
-cd benchmarks/laion
-python setup_laion.py --num-samples 10000 --num-queries 200
-```
-
-This will:
- Create dummy LAION data (10K samples)
- Generate CLIP embeddings (512-dim)
- Build LEANN index with HNSW backend
- Create 200 evaluation queries
-
-### 2. Run evaluation
-
-```bash
-# Run all evaluation stages
-python evaluate_laion.py --index data/laion_index.leann
-
-# Run specific stages
-python evaluate_laion.py --index data/laion_index.leann --stage 2  # Recall evaluation
-python evaluate_laion.py --index data/laion_index.leann --stage 3  # Complexity analysis
-python evaluate_laion.py --index data/laion_index.leann --stage 4  # Index comparison
-python evaluate_laion.py --index data/laion_index.leann --stage 5  # Multimodal generation
-
-# Multimodal generation with Qwen2.5-VL
-python evaluate_laion.py --index data/laion_index.leann --stage 5 --model-name Qwen/Qwen2.5-VL-7B-Instruct
-```
-
-### 3. Save results
-
-```bash
-python evaluate_laion.py --index data/laion_index.leann --output results.json
-```
-
-## Configuration Options
-
-### Setup Options
-```bash
-python setup_laion.py \
-  --num-samples 10000 \
-  --num-queries 200 \
-  --index-path data/laion_index.leann \
-  --backend hnsw
-```
-
-### Evaluation Options
-```bash
-python evaluate_laion.py \
-  --index data/laion_index.leann \
-  --queries data/evaluation_queries.jsonl \
-  --complexity 64 \
-  --top-k 3 \
-  --num-samples 100 \
-  --stage all
-```
-
-## Evaluation Stages
-
-### Stage 2: Recall Evaluation
- Evaluates Recall@3 for multimodal retrieval
- Compares LEANN vs FAISS baseline performance
- Self-recall: query caption should retrieve original image
-
-### Stage 3: Complexity Analysis
- Binary search for optimal complexity (90% recall target)
- Tests performance across different complexity levels
- Analyzes speed vs. accuracy tradeoffs
-
-### Stage 4: Index Comparison
- Compares compact vs non-compact index sizes
- Measures search performance differences
- Reports storage efficiency and speed ratios
-
-### Stage 5: Multimodal Generation
- Uses Qwen2.5-VL for image understanding and description
- Retrieval-Augmented Generation (RAG) with multimodal context
- Measures both search and generation timing
-
-## Output Metrics
-
-### Timing Metrics
- Average/median/min/max search time
- Standard deviation
- Searches per second
- Latency in milliseconds
-
-### Recall Metrics
- Recall@3 percentage for image retrieval
- Number of queries with ground truth
-
-### Index Metrics
- Total index size (MB)
- Component breakdown (index, passages, metadata)
- Storage savings (compact vs non-compact)
- Backend and embedding model info
-
-### Generation Metrics (Stage 5)
- Average search time per query
- Average generation time per query
- Time distribution (search vs generation)
- Sample multimodal responses
- Model: Qwen2.5-VL performance
-
-## Benchmark Results
-
-### LEANN-RAG Performance (CLIP ViT-L/14 + Qwen2.5-VL)
-
-**Stage 3: Optimal Complexity Analysis**
- **Optimal Complexity**: 85 (achieving 90% Recall@3)
- **Binary Search Range**: 1-128
- **Target Recall**: 90%
- **Index Type**: Non-compact (for fast binary search)
-
-**Stage 5: Multimodal Generation Performance (Qwen2.5-VL)**
- **Total Queries**: 20
- **Average Search Time**: 1.200s per query
- **Average Generation Time**: 6.558s per query
- **Time Distribution**: Search 15.5%, Generation 84.5%
- **LLM Backend**: HuggingFace transformers
- **Model**: Qwen/Qwen2.5-VL-7B-Instruct
- **Optimal Complexity**: 85
-
-**System Performance:**
- **Index Size**: ~10,000 image embeddings from LAION subset
- **Embedding Model**: CLIP ViT-L/14 (768 dimensions)
- **Backend**: HNSW with cosine distance
-
-### Example Results
-
-```
-🎯 LAION MULTIMODAL BENCHMARK RESULTS
-============================================================
-
-📊 Multimodal Generation Results:
-  Total Queries: 20
-  Avg Search Time: 1.200s
-  Avg Generation Time: 6.558s
-  Time Distribution: Search 15.5%, Generation 84.5%
-  LLM Backend: HuggingFace transformers
-  Model: Qwen/Qwen2.5-VL-7B-Instruct
-
-⚙️ Optimal Complexity Analysis:
-  Target Recall: 90%
-  Optimal Complexity: 85
-  Binary Search Range: 1-128
-  Non-compact Index (fast search, no recompute)
-
-🚀 Performance Summary:
-  Multimodal RAG: 7.758s total per query
-  Search: 15.5% of total time
-  Generation: 84.5% of total time
-```
-
-## Directory Structure
-
-```
-benchmarks/laion/
-├── setup_laion.py           # Setup script
-├── evaluate_laion.py        # Evaluation script
-├── README.md               # This file
-└── data/                   # Generated data
-    ├── laion_images/       # Image files (placeholder)
-    ├── laion_metadata.jsonl # Image metadata
-    ├── laion_passages.jsonl # LEANN passages
-    ├── laion_embeddings.npy # CLIP embeddings
-    ├── evaluation_queries.jsonl # Evaluation queries
-    └── laion_index.leann/  # LEANN index files
-```
-
-## Notes
-
- Current implementation uses dummy data for demonstration
- For real LAION data, implement actual download logic in `setup_laion.py`
- CLIP embeddings are randomly generated - replace with real CLIP model for production
- Adjust `num_samples` and `num_queries` based on available resources
- Consider using `--num-samples` during evaluation for faster testing
--- a/benchmarks/laion/evaluate_laion.py
+++ b/benchmarks/laion/evaluate_laion.py
@@ -1,725 +0,0 @@
-"""
-LAION Multimodal Benchmark Evaluation Script - Modular Recall-based Evaluation
-"""
-
-import argparse
-import json
-import logging
-import os
-import pickle
-import time
-from pathlib import Path
-
-import numpy as np
-from leann import LeannSearcher
-from leann_backend_hnsw import faiss
-from sentence_transformers import SentenceTransformer
-
-from ..llm_utils import evaluate_multimodal_rag, load_qwen_vl_model
-
-# Setup logging to reduce verbose output
-logging.basicConfig(level=logging.WARNING)
-logging.getLogger("leann.api").setLevel(logging.WARNING)
-logging.getLogger("leann_backend_hnsw").setLevel(logging.WARNING)
-
-
-class RecallEvaluator:
-    """Stage 2: Evaluate Recall@3 (LEANN vs FAISS baseline for multimodal retrieval)"""
-
-    def __init__(self, index_path: str, baseline_dir: str):
-        self.index_path = index_path
-        self.baseline_dir = baseline_dir
-        self.searcher = LeannSearcher(index_path)
-
-        # Load FAISS flat baseline (image embeddings)
-        baseline_index_path = os.path.join(baseline_dir, "faiss_flat.index")
-        metadata_path = os.path.join(baseline_dir, "metadata.pkl")
-
-        self.faiss_index = faiss.read_index(baseline_index_path)
-        with open(metadata_path, "rb") as f:
-            self.image_ids = pickle.load(f)
-        print(f"📚 Loaded FAISS flat baseline with {self.faiss_index.ntotal} image vectors")
-
-        # Load sentence-transformers CLIP for text embedding (ViT-L/14)
-        self.st_clip = SentenceTransformer("clip-ViT-L-14")
-
-    def evaluate_recall_at_3(
-        self, captions: list[str], complexity: int = 64, recompute_embeddings: bool = True
-    ) -> float:
-        """Evaluate recall@3 for multimodal retrieval: caption queries -> image results"""
-        recompute_str = "with recompute" if recompute_embeddings else "no recompute"
-        print(f"🔍 Evaluating recall@3 with complexity={complexity} ({recompute_str})...")
-
-        total_recall = 0.0
-        num_queries = len(captions)
-
-        for i, caption in enumerate(captions):
-            # Get ground truth: search with FAISS flat using caption text embedding
-            # Generate CLIP text embedding for caption via sentence-transformers (normalized)
-            query_embedding = self.st_clip.encode(
-                [caption], convert_to_numpy=True, normalize_embeddings=True, show_progress_bar=False
-            ).astype(np.float32)
-
-            # Search FAISS flat for ground truth using LEANN's modified faiss API
-            n = query_embedding.shape[0]  # Number of queries
-            k = 3  # Number of nearest neighbors
-            distances = np.zeros((n, k), dtype=np.float32)
-            labels = np.zeros((n, k), dtype=np.int64)
-
-            self.faiss_index.search(
-                n,
-                faiss.swig_ptr(query_embedding),
-                k,
-                faiss.swig_ptr(distances),
-                faiss.swig_ptr(labels),
-            )
-
-            # Extract the results (image IDs from FAISS)
-            baseline_ids = {self.image_ids[idx] for idx in labels[0]}
-
-            # Search with LEANN at specified complexity (using caption as text query)
-            test_results = self.searcher.search(
-                caption,
-                top_k=3,
-                complexity=complexity,
-                recompute_embeddings=recompute_embeddings,
-            )
-            test_ids = {result.id for result in test_results}
-
-            # Calculate recall@3 = |intersection| / |ground_truth|
-            intersection = test_ids.intersection(baseline_ids)
-            recall = len(intersection) / 3.0  # Ground truth size is 3
-            total_recall += recall
-
-            if i < 3:  # Show first few examples
-                print(f"  Query {i + 1}: '{caption[:50]}...' -> Recall@3: {recall:.3f}")
-                print(f"    FAISS ground truth: {list(baseline_ids)}")
-                print(f"    LEANN results (C={complexity}, {recompute_str}): {list(test_ids)}")
-                print(f"    Intersection: {list(intersection)}")
-
-        avg_recall = total_recall / num_queries
-        print(f"📊 Average Recall@3: {avg_recall:.3f} ({avg_recall * 100:.1f}%)")
-        return avg_recall
-
-    def cleanup(self):
-        """Cleanup resources"""
-        if hasattr(self, "searcher"):
-            self.searcher.cleanup()
-
-
-class LAIONEvaluator:
-    def __init__(self, index_path: str):
-        self.index_path = index_path
-        self.searcher = LeannSearcher(index_path)
-
-    def load_queries(self, queries_file: str) -> list[str]:
-        """Load caption queries from evaluation file"""
-        captions = []
-        with open(queries_file, encoding="utf-8") as f:
-            for line in f:
-                if line.strip():
-                    query_data = json.loads(line)
-                    captions.append(query_data["query"])
-
-        print(f"📊 Loaded {len(captions)} caption queries")
-        return captions
-
-    def analyze_index_sizes(self) -> dict:
-        """Analyze index sizes, emphasizing .index only (exclude passages)."""
-        print("📏 Analyzing index sizes (.index only)...")
-
-        # Get all index-related files
-        index_path = Path(self.index_path)
-        index_dir = index_path.parent
-        index_name = index_path.stem  # Remove .leann extension
-
-        sizes: dict[str, float] = {}
-
-        # Core index files
-        index_file = index_dir / f"{index_name}.index"
-        meta_file = index_dir / f"{index_path.name}.meta.json"  # Keep .leann for meta file
-        passages_file = index_dir / f"{index_path.name}.passages.jsonl"  # Keep .leann for passages
-        passages_idx_file = index_dir / f"{index_path.name}.passages.idx"  # Keep .leann for idx
-
-        # Core index size (.index only)
-        index_mb = index_file.stat().st_size / (1024 * 1024) if index_file.exists() else 0.0
-        sizes["index_only_mb"] = index_mb
-
-        # Other files for reference (not counted in index_only_mb)
-        sizes["metadata_mb"] = (
-            meta_file.stat().st_size / (1024 * 1024) if meta_file.exists() else 0.0
-        )
-        sizes["passages_text_mb"] = (
-            passages_file.stat().st_size / (1024 * 1024) if passages_file.exists() else 0.0
-        )
-        sizes["passages_index_mb"] = (
-            passages_idx_file.stat().st_size / (1024 * 1024) if passages_idx_file.exists() else 0.0
-        )
-
-        print(f"  📁 .index size: {index_mb:.1f} MB")
-        if sizes["metadata_mb"]:
-            print(f"  🧾 metadata: {sizes['metadata_mb']:.3f} MB")
-        if sizes["passages_text_mb"] or sizes["passages_index_mb"]:
-            print(
-                f"  (passages excluded) text: {sizes['passages_text_mb']:.1f} MB, idx: {sizes['passages_index_mb']:.1f} MB"
-            )
-
-        return sizes
-
-    def create_non_compact_index_for_comparison(self, non_compact_index_path: str) -> dict:
-        """Create a non-compact index for comparison purposes"""
-        print("🏗️ Building non-compact index from existing passages...")
-
-        # Load existing passages from current index
-        from leann import LeannBuilder
-
-        current_index_path = Path(self.index_path)
-        current_index_dir = current_index_path.parent
-        current_index_name = current_index_path.name
-
-        # Read metadata to get passage source
-        meta_path = current_index_dir / f"{current_index_name}.meta.json"
-        with open(meta_path) as f:
-            meta = json.load(f)
-
-        passage_source = meta["passage_sources"][0]
-        passage_file = passage_source["path"]
-
-        # Convert relative path to absolute
-        if not Path(passage_file).is_absolute():
-            passage_file = current_index_dir / Path(passage_file).name
-
-        print(f"📄 Loading passages from {passage_file}...")
-
-        # Load CLIP embeddings
-        embeddings_file = current_index_dir / "clip_image_embeddings.npy"
-        embeddings = np.load(embeddings_file)
-        print(f"📐 Loaded embeddings shape: {embeddings.shape}")
-
-        # Build non-compact index with same passages and embeddings
-        builder = LeannBuilder(
-            backend_name="hnsw",
-            # Use CLIP text encoder (ViT-L/14) to match image embeddings (768-dim)
-            embedding_model="clip-ViT-L-14",
-            embedding_mode="sentence-transformers",
-            is_recompute=False,  # Disable recompute (store embeddings)
-            is_compact=False,  # Disable compact storage
-            distance_metric="cosine",
-            **{
-                k: v
-                for k, v in meta.get("backend_kwargs", {}).items()
-                if k not in ["is_recompute", "is_compact", "distance_metric"]
-            },
-        )
-
-        # Prepare ids and add passages
-        ids: list[str] = []
-        with open(passage_file, encoding="utf-8") as f:
-            for line in f:
-                if line.strip():
-                    data = json.loads(line)
-                    ids.append(str(data["id"]))
-                    # Ensure metadata contains the id used by the vector index
-                    metadata = {**data.get("metadata", {}), "id": data["id"]}
-                    builder.add_text(text=data["text"], metadata=metadata)
-
-        if len(ids) != embeddings.shape[0]:
-            raise ValueError(
-                f"IDs count ({len(ids)}) does not match embeddings ({embeddings.shape[0]})."
-            )
-
-        # Persist a pickle for build_index_from_embeddings
-        pkl_path = current_index_dir / "clip_image_embeddings.pkl"
-        with open(pkl_path, "wb") as pf:
-            pickle.dump((ids, embeddings.astype(np.float32)), pf)
-
-        print(
-            f"🔨 Building non-compact index at {non_compact_index_path} from precomputed embeddings..."
-        )
-        builder.build_index_from_embeddings(non_compact_index_path, str(pkl_path))
-
-        # Analyze the non-compact index size
-        temp_evaluator = LAIONEvaluator(non_compact_index_path)
-        non_compact_sizes = temp_evaluator.analyze_index_sizes()
-        non_compact_sizes["index_type"] = "non_compact"
-
-        return non_compact_sizes
-
-    def compare_index_performance(
-        self, non_compact_path: str, compact_path: str, test_captions: list, complexity: int
-    ) -> dict:
-        """Compare performance between non-compact and compact indexes"""
-        print("⚡ Comparing search performance between indexes...")
-
-        # Test queries
-        test_queries = test_captions[:5]
-
-        results = {
-            "non_compact": {"search_times": []},
-            "compact": {"search_times": []},
-            "avg_search_times": {},
-            "speed_ratio": 0.0,
-        }
-
-        # Test non-compact index (no recompute)
-        print("  🔍 Testing non-compact index (no recompute)...")
-        non_compact_searcher = LeannSearcher(non_compact_path)
-
-        for caption in test_queries:
-            start_time = time.time()
-            _ = non_compact_searcher.search(
-                caption, top_k=3, complexity=complexity, recompute_embeddings=False
-            )
-            search_time = time.time() - start_time
-            results["non_compact"]["search_times"].append(search_time)
-
-        # Test compact index (with recompute)
-        print("  🔍 Testing compact index (with recompute)...")
-        compact_searcher = LeannSearcher(compact_path)
-
-        for caption in test_queries:
-            start_time = time.time()
-            _ = compact_searcher.search(
-                caption, top_k=3, complexity=complexity, recompute_embeddings=True
-            )
-            search_time = time.time() - start_time
-            results["compact"]["search_times"].append(search_time)
-
-        # Calculate averages
-        results["avg_search_times"]["non_compact"] = sum(
-            results["non_compact"]["search_times"]
-        ) / len(results["non_compact"]["search_times"])
-        results["avg_search_times"]["compact"] = sum(results["compact"]["search_times"]) / len(
-            results["compact"]["search_times"]
-        )
-
-        # Performance ratio
-        if results["avg_search_times"]["compact"] > 0:
-            results["speed_ratio"] = (
-                results["avg_search_times"]["non_compact"] / results["avg_search_times"]["compact"]
-            )
-        else:
-            results["speed_ratio"] = float("inf")
-
-        print(
-            f"    Non-compact (no recompute): {results['avg_search_times']['non_compact']:.3f}s avg"
-        )
-        print(f"    Compact (with recompute): {results['avg_search_times']['compact']:.3f}s avg")
-        print(f"    Speed ratio: {results['speed_ratio']:.2f}x")
-
-        # Cleanup
-        non_compact_searcher.cleanup()
-        compact_searcher.cleanup()
-
-        return results
-
-    def _print_results(self, timing_metrics: dict):
-        """Print evaluation results"""
-        print("\n🎯 LAION MULTIMODAL BENCHMARK RESULTS")
-        print("=" * 60)
-
-        # Index comparison analysis (prefer .index-only view if present)
-        if "current_index" in timing_metrics and "non_compact_index" in timing_metrics:
-            current = timing_metrics["current_index"]
-            non_compact = timing_metrics["non_compact_index"]
-
-            if "index_only_mb" in current and "index_only_mb" in non_compact:
-                print("\n📏 Index Comparison Analysis (.index only):")
-                print(f"  Compact index (current): {current.get('index_only_mb', 0):.1f} MB")
-                print(f"  Non-compact index: {non_compact.get('index_only_mb', 0):.1f} MB")
-                print(
-                    f"  Storage saving by compact: {timing_metrics.get('storage_saving_percent', 0):.1f}%"
-                )
-                # Show excluded components for reference if available
-                if any(
-                    k in non_compact
-                    for k in ("passages_text_mb", "passages_index_mb", "metadata_mb")
-                ):
-                    print("  (passages excluded in totals, shown for reference):")
-                    print(
-                        f"    - Passages text: {non_compact.get('passages_text_mb', 0):.1f} MB, "
-                        f"Passages index: {non_compact.get('passages_index_mb', 0):.1f} MB, "
-                        f"Metadata: {non_compact.get('metadata_mb', 0):.3f} MB"
-                    )
-            else:
-                # Fallback to legacy totals if running with older metrics
-                print("\n📏 Index Comparison Analysis:")
-                print(
-                    f"  Compact index (current): {current.get('total_with_embeddings', 0):.1f} MB"
-                )
-                print(
-                    f"  Non-compact index (with embeddings): {non_compact.get('total_with_embeddings', 0):.1f} MB"
-                )
-                print(
-                    f"  Storage saving by compact: {timing_metrics.get('storage_saving_percent', 0):.1f}%"
-                )
-                print("  Component breakdown (non-compact):")
-                print(f"    - Main index: {non_compact.get('index', 0):.1f} MB")
-                print(f"    - Passages text: {non_compact.get('passages_text', 0):.1f} MB")
-                print(f"    - Passages index: {non_compact.get('passages_index', 0):.1f} MB")
-                print(f"    - Metadata: {non_compact.get('metadata', 0):.1f} MB")
-
-        # Performance comparison
-        if "performance_comparison" in timing_metrics:
-            perf = timing_metrics["performance_comparison"]
-            print("\n⚡ Performance Comparison:")
-            print(
-                f"  Non-compact (no recompute): {perf.get('avg_search_times', {}).get('non_compact', 0):.3f}s avg"
-            )
-            print(
-                f"  Compact (with recompute): {perf.get('avg_search_times', {}).get('compact', 0):.3f}s avg"
-            )
-            print(f"  Speed ratio: {perf.get('speed_ratio', 0):.2f}x")
-
-        # Legacy single index analysis (fallback)
-        if "total_with_embeddings" in timing_metrics and "current_index" not in timing_metrics:
-            print("\n📏 Index Size Analysis:")
-            print(
-                f"  Index with embeddings: {timing_metrics.get('total_with_embeddings', 0):.1f} MB"
-            )
-            print(
-                f"  Estimated pruned index: {timing_metrics.get('total_without_embeddings', 0):.1f} MB"
-            )
-            print(f"  Compression ratio: {timing_metrics.get('compression_ratio', 0):.2f}x")
-
-    def cleanup(self):
-        """Cleanup resources"""
-        if self.searcher:
-            self.searcher.cleanup()
-
-
-def main():
-    parser = argparse.ArgumentParser(description="LAION Multimodal Benchmark Evaluation")
-    parser.add_argument("--index", required=True, help="Path to LEANN index")
-    parser.add_argument(
-        "--queries", default="data/evaluation_queries.jsonl", help="Path to evaluation queries"
-    )
-    parser.add_argument(
-        "--stage",
-        choices=["2", "3", "4", "5", "all"],
-        default="all",
-        help="Which stage to run (2=recall, 3=complexity, 4=index comparison, 5=generation)",
-    )
-    parser.add_argument("--complexity", type=int, default=None, help="Complexity for search")
-    parser.add_argument("--baseline-dir", default="baseline", help="Baseline output directory")
-    parser.add_argument("--output", help="Save results to JSON file")
-    parser.add_argument(
-        "--llm-backend",
-        choices=["hf"],
-        default="hf",
-        help="LLM backend (Qwen2.5-VL only supports HF)",
-    )
-    parser.add_argument(
-        "--model-name", default="Qwen/Qwen2.5-VL-7B-Instruct", help="Multimodal model name"
-    )
-
-    args = parser.parse_args()
-
-    try:
-        # Check if baseline exists
-        baseline_index_path = os.path.join(args.baseline_dir, "faiss_flat.index")
-        if not os.path.exists(baseline_index_path):
-            print(f"❌ FAISS baseline not found at {baseline_index_path}")
-            print("💡 Please run setup_laion.py first to build the baseline")
-            exit(1)
-
-        if args.stage == "2" or args.stage == "all":
-            # Stage 2: Recall@3 evaluation
-            print("🚀 Starting Stage 2: Recall@3 evaluation for multimodal retrieval")
-
-            evaluator = RecallEvaluator(args.index, args.baseline_dir)
-
-            # Load caption queries for testing
-            laion_evaluator = LAIONEvaluator(args.index)
-            captions = laion_evaluator.load_queries(args.queries)
-
-            # Test with queries for robust measurement
-            test_captions = captions[:100]  # Use subset for speed
-            print(f"🧪 Testing with {len(test_captions)} caption queries")
-
-            # Test with complexity 64
-            complexity = 64
-            recall = evaluator.evaluate_recall_at_3(test_captions, complexity)
-            print(f"📈 Recall@3 at complexity {complexity}: {recall * 100:.1f}%")
-
-            evaluator.cleanup()
-            print("✅ Stage 2 completed!\n")
-
-        # Shared non-compact index path for Stage 3 and 4
-        non_compact_index_path = args.index.replace(".leann", "_noncompact.leann")
-        complexity = args.complexity
-
-        if args.stage == "3" or args.stage == "all":
-            # Stage 3: Binary search for 90% recall complexity
-            print("🚀 Starting Stage 3: Binary search for 90% recall complexity")
-            print(
-                "💡 Creating non-compact index for fast binary search with recompute_embeddings=False"
-            )
-
-            # Create non-compact index for binary search
-            print("🏗️ Creating non-compact index for binary search...")
-            evaluator = LAIONEvaluator(args.index)
-            evaluator.create_non_compact_index_for_comparison(non_compact_index_path)
-
-            # Use non-compact index for binary search
-            binary_search_evaluator = RecallEvaluator(non_compact_index_path, args.baseline_dir)
-
-            # Load caption queries for testing
-            captions = evaluator.load_queries(args.queries)
-
-            # Use subset for robust measurement
-            test_captions = captions[:50]  # Smaller subset for binary search speed
-            print(f"🧪 Testing with {len(test_captions)} caption queries")
-
-            # Binary search for 90% recall complexity
-            target_recall = 0.9
-            min_complexity, max_complexity = 1, 128
-
-            print(f"🔍 Binary search for {target_recall * 100}% recall complexity...")
-            print(f"Search range: {min_complexity} to {max_complexity}")
-
-            best_complexity = None
-            best_recall = 0.0
-
-            while min_complexity <= max_complexity:
-                mid_complexity = (min_complexity + max_complexity) // 2
-
-                print(
-                    f"\n🧪 Testing complexity {mid_complexity} (no recompute, non-compact index)..."
-                )
-                # Use recompute_embeddings=False on non-compact index for fast binary search
-                recall = binary_search_evaluator.evaluate_recall_at_3(
-                    test_captions, mid_complexity, recompute_embeddings=False
-                )
-
-                print(
-                    f"  Complexity {mid_complexity}: Recall@3 = {recall:.3f} ({recall * 100:.1f}%)"
-                )
-
-                if recall >= target_recall:
-                    best_complexity = mid_complexity
-                    best_recall = recall
-                    max_complexity = mid_complexity - 1
-                    print("  ✅ Target reached! Searching for lower complexity...")
-                else:
-                    min_complexity = mid_complexity + 1
-                    print("  ❌ Below target. Searching for higher complexity...")
-
-            if best_complexity is not None:
-                print("\n🎯 Optimal complexity found!")
-                print(f"  Complexity: {best_complexity}")
-                print(f"  Recall@3: {best_recall:.3f} ({best_recall * 100:.1f}%)")
-
-                # Test a few complexities around the optimal one for verification
-                print("\n🔬 Verification test around optimal complexity:")
-                verification_complexities = [
-                    max(1, best_complexity - 2),
-                    max(1, best_complexity - 1),
-                    best_complexity,
-                    best_complexity + 1,
-                    best_complexity + 2,
-                ]
-
-                for complexity in verification_complexities:
-                    if complexity <= 512:  # reasonable upper bound
-                        recall = binary_search_evaluator.evaluate_recall_at_3(
-                            test_captions, complexity, recompute_embeddings=False
-                        )
-                        status = "✅" if recall >= target_recall else "❌"
-                        print(f"  {status} Complexity {complexity:3d}: {recall * 100:5.1f}%")
-
-                # Now test the optimal complexity with compact index and recompute for comparison
-                print(
-                    f"\n🔄 Testing optimal complexity {best_complexity} on compact index WITH recompute..."
-                )
-                compact_evaluator = RecallEvaluator(args.index, args.baseline_dir)
-                recall_with_recompute = compact_evaluator.evaluate_recall_at_3(
-                    test_captions[:10], best_complexity, recompute_embeddings=True
-                )
-                print(
-                    f"  ✅ Complexity {best_complexity} (compact index with recompute): {recall_with_recompute * 100:.1f}%"
-                )
-                complexity = best_complexity
-                print(
-                    f"  📊 Recall difference: {abs(best_recall - recall_with_recompute) * 100:.2f}%"
-                )
-                compact_evaluator.cleanup()
-            else:
-                print(f"\n❌ Could not find complexity achieving {target_recall * 100}% recall")
-                print("All tested complexities were below target.")
-
-            # Cleanup evaluators (keep non-compact index for Stage 4)
-            binary_search_evaluator.cleanup()
-            evaluator.cleanup()
-
-            print("✅ Stage 3 completed! Non-compact index saved for Stage 4.\n")
-
-        if args.stage == "4" or args.stage == "all":
-            # Stage 4: Index comparison (without LLM generation)
-            print("🚀 Starting Stage 4: Index comparison analysis")
-
-            # Use LAION evaluator for index comparison
-            evaluator = LAIONEvaluator(args.index)
-
-            # Load caption queries
-            captions = evaluator.load_queries(args.queries)
-
-            # Step 1: Analyze current (compact) index
-            print("\n📏 Analyzing current index (compact, pruned)...")
-            compact_size_metrics = evaluator.analyze_index_sizes()
-            compact_size_metrics["index_type"] = "compact"
-
-            # Step 2: Use existing non-compact index or create if needed
-            if Path(non_compact_index_path).exists():
-                print(
-                    f"\n📁 Using existing non-compact index from Stage 3: {non_compact_index_path}"
-                )
-                temp_evaluator = LAIONEvaluator(non_compact_index_path)
-                non_compact_size_metrics = temp_evaluator.analyze_index_sizes()
-                non_compact_size_metrics["index_type"] = "non_compact"
-            else:
-                print("\n🏗️ Creating non-compact index (with embeddings) for comparison...")
-                non_compact_size_metrics = evaluator.create_non_compact_index_for_comparison(
-                    non_compact_index_path
-                )
-
-            # Step 3: Compare index sizes (.index only)
-            print("\n📊 Index size comparison (.index only):")
-            print(
-                f"  Compact index (current): {compact_size_metrics.get('index_only_mb', 0):.1f} MB"
-            )
-            print(f"  Non-compact index: {non_compact_size_metrics.get('index_only_mb', 0):.1f} MB")
-
-            storage_saving = 0.0
-            if non_compact_size_metrics.get("index_only_mb", 0) > 0:
-                storage_saving = (
-                    (
-                        non_compact_size_metrics.get("index_only_mb", 0)
-                        - compact_size_metrics.get("index_only_mb", 0)
-                    )
-                    / non_compact_size_metrics.get("index_only_mb", 1)
-                    * 100
-                )
-            print(f"  Storage saving by compact: {storage_saving:.1f}%")
-
-            # Step 4: Performance comparison between the two indexes
-            if complexity is None:
-                raise ValueError("Complexity is required for index comparison")
-
-            print("\n⚡ Performance comparison between indexes...")
-            performance_metrics = evaluator.compare_index_performance(
-                non_compact_index_path, args.index, captions[:10], complexity=complexity
-            )
-
-            # Combine all metrics
-            combined_metrics = {
-                "current_index": compact_size_metrics,
-                "non_compact_index": non_compact_size_metrics,
-                "performance_comparison": performance_metrics,
-                "storage_saving_percent": storage_saving,
-            }
-
-            # Print comprehensive results
-            evaluator._print_results(combined_metrics)
-
-            # Save results if requested
-            if args.output:
-                print(f"\n💾 Saving results to {args.output}...")
-                with open(args.output, "w") as f:
-                    json.dump(combined_metrics, f, indent=2, default=str)
-                print(f"✅ Results saved to {args.output}")
-
-            evaluator.cleanup()
-            print("✅ Stage 4 completed!\n")
-
-        if args.stage in ("5", "all"):
-            print("🚀 Starting Stage 5: Multimodal generation with Qwen2.5-VL")
-            evaluator = LAIONEvaluator(args.index)
-            captions = evaluator.load_queries(args.queries)
-            test_captions = captions[: min(20, len(captions))]  # Use subset for generation
-
-            print(f"🧪 Testing multimodal generation with {len(test_captions)} queries")
-
-            # Load Qwen2.5-VL model
-            try:
-                print("Loading Qwen2.5-VL model...")
-                processor, model = load_qwen_vl_model(args.model_name)
-
-                # Run multimodal generation evaluation
-                complexity = args.complexity or 64
-                gen_results = evaluate_multimodal_rag(
-                    evaluator.searcher,
-                    test_captions,
-                    processor=processor,
-                    model=model,
-                    complexity=complexity,
-                )
-
-                print("\n📊 Multimodal Generation Results:")
-                print(f"  Total Queries: {len(test_captions)}")
-                print(f"  Avg Search Time: {gen_results['avg_search_time']:.3f}s")
-                print(f"  Avg Generation Time: {gen_results['avg_generation_time']:.3f}s")
-                total_time = gen_results["avg_search_time"] + gen_results["avg_generation_time"]
-                search_pct = (gen_results["avg_search_time"] / total_time) * 100
-                gen_pct = (gen_results["avg_generation_time"] / total_time) * 100
-                print(f"  Time Distribution: Search {search_pct:.1f}%, Generation {gen_pct:.1f}%")
-                print("  LLM Backend: HuggingFace transformers")
-                print(f"  Model: {args.model_name}")
-
-                # Show sample results
-                print("\n📝 Sample Multimodal Generations:")
-                for i, response in enumerate(gen_results["results"][:3]):
-                    # Handle both string and dict formats for captions
-                    if isinstance(test_captions[i], dict):
-                        caption_text = test_captions[i].get("query", str(test_captions[i]))
-                    else:
-                        caption_text = str(test_captions[i])
-                    print(f"  Query {i + 1}: {caption_text[:60]}...")
-                    print(f"  Response {i + 1}: {response[:100]}...")
-                    print()
-
-            except Exception as e:
-                print(f"❌ Multimodal generation evaluation failed: {e}")
-                print("💡 Make sure transformers and Qwen2.5-VL are installed")
-                import traceback
-
-                traceback.print_exc()
-
-            evaluator.cleanup()
-            print("✅ Stage 5 completed!\n")
-
-        if args.stage == "all":
-            print("🎉 All evaluation stages completed successfully!")
-            print("\n📋 Summary:")
-            print("  Stage 2: ✅ Multimodal Recall@3 evaluation completed")
-            print("  Stage 3: ✅ Optimal complexity found")
-            print("  Stage 4: ✅ Index comparison analysis completed")
-            print("  Stage 5: ✅ Multimodal generation evaluation completed")
-            print("\n🔧 Recommended next steps:")
-            print("  - Use optimal complexity for best speed/accuracy balance")
-            print("  - Review index comparison for storage vs performance tradeoffs")
-
-            # Clean up non-compact index after all stages complete
-            print("\n🧹 Cleaning up temporary non-compact index...")
-            if Path(non_compact_index_path).exists():
-                temp_index_dir = Path(non_compact_index_path).parent
-                temp_index_name = Path(non_compact_index_path).name
-                for temp_file in temp_index_dir.glob(f"{temp_index_name}*"):
-                    temp_file.unlink()
-                print(f"✅ Cleaned up {non_compact_index_path}")
-            else:
-                print("📝 No temporary index to clean up")
-
-    except KeyboardInterrupt:
-        print("\n⚠️  Evaluation interrupted by user")
-        exit(1)
-    except Exception as e:
-        print(f"\n❌ Stage {args.stage} failed: {e}")
-        import traceback
-
-        traceback.print_exc()
-        exit(1)
-
-
-if __name__ == "__main__":
-    main()
--- a/benchmarks/laion/setup_laion.py
+++ b/benchmarks/laion/setup_laion.py
@@ -1,576 +0,0 @@
-"""
-LAION Multimodal Benchmark Setup Script
-Downloads LAION subset and builds LEANN index with sentence embeddings
-"""
-
-import argparse
-import asyncio
-import io
-import json
-import os
-import pickle
-import time
-from pathlib import Path
-
-import aiohttp
-import numpy as np
-from datasets import load_dataset
-from leann import LeannBuilder
-from PIL import Image
-from sentence_transformers import SentenceTransformer
-from tqdm import tqdm
-
-
-class LAIONSetup:
-    def __init__(self, data_dir: str = "data"):
-        self.data_dir = Path(data_dir)
-        self.images_dir = self.data_dir / "laion_images"
-        self.metadata_file = self.data_dir / "laion_metadata.jsonl"
-
-        # Create directories
-        self.data_dir.mkdir(exist_ok=True)
-        self.images_dir.mkdir(exist_ok=True)
-
-    async def download_single_image(self, session, sample_data, semaphore, progress_bar):
-        """Download a single image asynchronously"""
-        async with semaphore:  # Limit concurrent downloads
-            try:
-                image_url = sample_data["url"]
-                image_path = sample_data["image_path"]
-
-                # Skip if already exists
-                if os.path.exists(image_path):
-                    progress_bar.update(1)
-                    return sample_data
-
-                async with session.get(image_url, timeout=10) as response:
-                    if response.status == 200:
-                        content = await response.read()
-
-                        # Verify it's a valid image
-                        try:
-                            img = Image.open(io.BytesIO(content))
-                            img = img.convert("RGB")
-                            img.save(image_path, "JPEG")
-                            progress_bar.update(1)
-                            return sample_data
-                        except Exception:
-                            progress_bar.update(1)
-                            return None  # Skip invalid images
-                    else:
-                        progress_bar.update(1)
-                        return None
-
-            except Exception:
-                progress_bar.update(1)
-                return None
-
-    def download_laion_subset(self, num_samples: int = 1000):
-        """Download LAION subset from HuggingFace datasets with async parallel downloading"""
-        print(f"📥 Downloading LAION subset ({num_samples} samples)...")
-
-        # Load LAION-400M subset from HuggingFace
-        print("🤗 Loading from HuggingFace datasets...")
-        dataset = load_dataset("laion/laion400m", split="train", streaming=True)
-
-        # Collect sample metadata first (fast)
-        print("📋 Collecting sample metadata...")
-        candidates = []
-        for sample in dataset:
-            if len(candidates) >= num_samples * 3:  # Get 3x more candidates in case some fail
-                break
-
-            image_url = sample.get("url", "")
-            caption = sample.get("caption", "")
-
-            if not image_url or not caption:
-                continue
-
-            image_filename = f"laion_{len(candidates):06d}.jpg"
-            image_path = self.images_dir / image_filename
-
-            candidate = {
-                "id": f"laion_{len(candidates):06d}",
-                "url": image_url,
-                "caption": caption,
-                "image_path": str(image_path),
-                "width": sample.get("original_width", 512),
-                "height": sample.get("original_height", 512),
-                "similarity": sample.get("similarity", 0.0),
-            }
-            candidates.append(candidate)
-
-        print(
-            f"📊 Collected {len(candidates)} candidates, downloading {num_samples} in parallel..."
-        )
-
-        # Download images in parallel
-        async def download_batch():
-            semaphore = asyncio.Semaphore(20)  # Limit to 20 concurrent downloads
-            connector = aiohttp.TCPConnector(limit=100, limit_per_host=20)
-            timeout = aiohttp.ClientTimeout(total=30)
-
-            progress_bar = tqdm(total=len(candidates[: num_samples * 2]), desc="Downloading images")
-
-            async with aiohttp.ClientSession(connector=connector, timeout=timeout) as session:
-                tasks = []
-                for candidate in candidates[: num_samples * 2]:  # Try 2x more than needed
-                    task = self.download_single_image(session, candidate, semaphore, progress_bar)
-                    tasks.append(task)
-
-                # Wait for all downloads
-                results = await asyncio.gather(*tasks, return_exceptions=True)
-                progress_bar.close()
-
-                # Filter successful downloads
-                successful = [r for r in results if r is not None and not isinstance(r, Exception)]
-                return successful[:num_samples]
-
-        # Run async download
-        loop = asyncio.new_event_loop()
-        asyncio.set_event_loop(loop)
-        try:
-            samples = loop.run_until_complete(download_batch())
-        finally:
-            loop.close()
-
-        # Save metadata
-        with open(self.metadata_file, "w", encoding="utf-8") as f:
-            for sample in samples:
-                f.write(json.dumps(sample) + "\n")
-
-        print(f"✅ Downloaded {len(samples)} real LAION samples with async parallel downloading")
-        return samples
-
-    def generate_clip_image_embeddings(self, samples: list[dict]):
-        """Generate CLIP image embeddings for downloaded images"""
-        print("🔍 Generating CLIP image embeddings...")
-
-        # Load sentence-transformers CLIP (ViT-L/14, 768-dim) for image embeddings
-        # This single model can encode both images and text.
-        model = SentenceTransformer("clip-ViT-L-14")
-
-        embeddings = []
-        valid_samples = []
-
-        for sample in tqdm(samples, desc="Processing images"):
-            try:
-                # Load image
-                image_path = sample["image_path"]
-                image = Image.open(image_path).convert("RGB")
-
-                # Encode image to 768-dim embedding via sentence-transformers (normalized)
-                vec = model.encode(
-                    [image],
-                    convert_to_numpy=True,
-                    normalize_embeddings=True,
-                    batch_size=1,
-                    show_progress_bar=False,
-                )[0]
-                embeddings.append(vec.astype(np.float32))
-                valid_samples.append(sample)
-
-            except Exception as e:
-                print(f"  ⚠️ Failed to process {sample['id']}: {e}")
-                # Skip invalid images
-
-        embeddings = np.array(embeddings, dtype=np.float32)
-
-        # Save embeddings
-        embeddings_file = self.data_dir / "clip_image_embeddings.npy"
-        np.save(embeddings_file, embeddings)
-        print(f"✅ Generated {len(embeddings)} image embeddings, shape: {embeddings.shape}")
-
-        return embeddings, valid_samples
-
-    def build_faiss_baseline(
-        self, embeddings: np.ndarray, samples: list[dict], output_dir: str = "baseline"
-    ):
-        """Build FAISS flat baseline using CLIP image embeddings"""
-        print("🔨 Building FAISS Flat baseline...")
-
-        from leann_backend_hnsw import faiss
-
-        os.makedirs(output_dir, exist_ok=True)
-        baseline_path = os.path.join(output_dir, "faiss_flat.index")
-        metadata_path = os.path.join(output_dir, "metadata.pkl")
-
-        if os.path.exists(baseline_path) and os.path.exists(metadata_path):
-            print(f"✅ Baseline already exists at {baseline_path}")
-            return baseline_path
-
-        # Extract image IDs (must be present)
-        if not samples or "id" not in samples[0]:
-            raise KeyError("samples missing 'id' field for FAISS baseline")
-        image_ids: list[str] = [str(sample["id"]) for sample in samples]
-
-        print(f"📐 Embedding shape: {embeddings.shape}")
-        print(f"📄 Processing {len(image_ids)} images")
-
-        # Build FAISS flat index
-        print("🏗️ Building FAISS IndexFlatIP...")
-        dimension = embeddings.shape[1]
-        index = faiss.IndexFlatIP(dimension)
-
-        # Add embeddings to flat index
-        embeddings_f32 = embeddings.astype(np.float32)
-        index.add(embeddings_f32.shape[0], faiss.swig_ptr(embeddings_f32))
-
-        # Save index and metadata
-        faiss.write_index(index, baseline_path)
-        with open(metadata_path, "wb") as f:
-            pickle.dump(image_ids, f)
-
-        print(f"✅ FAISS baseline saved to {baseline_path}")
-        print(f"✅ Metadata saved to {metadata_path}")
-        print(f"📊 Total vectors: {index.ntotal}")
-
-        return baseline_path
-
-    def create_leann_passages(self, samples: list[dict]):
-        """Create LEANN-compatible passages from LAION data"""
-        print("📝 Creating LEANN passages...")
-
-        passages_file = self.data_dir / "laion_passages.jsonl"
-
-        with open(passages_file, "w", encoding="utf-8") as f:
-            for i, sample in enumerate(samples):
-                passage = {
-                    "id": sample["id"],
-                    "text": sample["caption"],  # Use caption as searchable text
-                    "metadata": {
-                        "image_url": sample["url"],
-                        "image_path": sample.get("image_path", ""),
-                        "width": sample["width"],
-                        "height": sample["height"],
-                        "similarity": sample["similarity"],
-                        "image_index": i,  # Index for embedding lookup
-                    },
-                }
-                f.write(json.dumps(passage) + "\n")
-
-        print(f"✅ Created {len(samples)} passages")
-        return passages_file
-
-    def build_compact_index(
-        self, passages_file: Path, embeddings: np.ndarray, index_path: str, backend: str = "hnsw"
-    ):
-        """Build compact LEANN index with CLIP embeddings (recompute=True, compact=True)"""
-        print(f"🏗️ Building compact LEANN index with {backend} backend...")
-
-        start_time = time.time()
-
-        # Save CLIP embeddings (npy) and also a pickle with (ids, embeddings)
-        npy_path = self.data_dir / "clip_image_embeddings.npy"
-        np.save(npy_path, embeddings)
-        print(f"💾 Saved CLIP embeddings to {npy_path}")
-
-        # Prepare ids in the same order as passages_file (matches embeddings order)
-        ids: list[str] = []
-        with open(passages_file, encoding="utf-8") as f:
-            for line in f:
-                if line.strip():
-                    rec = json.loads(line)
-                    ids.append(str(rec["id"]))
-
-        if len(ids) != embeddings.shape[0]:
-            raise ValueError(
-                f"IDs count ({len(ids)}) does not match embeddings ({embeddings.shape[0]})."
-            )
-
-        pkl_path = self.data_dir / "clip_image_embeddings.pkl"
-        with open(pkl_path, "wb") as pf:
-            pickle.dump((ids, embeddings.astype(np.float32)), pf)
-        print(f"💾 Saved (ids, embeddings) pickle to {pkl_path}")
-
-        # Initialize builder - compact with recompute
-        # Note: For multimodal case, we need to handle embeddings differently
-        # Let's try using sentence-transformers mode but with custom embeddings
-        builder = LeannBuilder(
-            backend_name=backend,
-            # Use CLIP text encoder (ViT-L/14) to match image space (768-dim)
-            embedding_model="clip-ViT-L-14",
-            embedding_mode="sentence-transformers",
-            # HNSW params (or forwarded to chosen backend)
-            graph_degree=32,
-            complexity=64,
-            # Compact/pruned with recompute at query time
-            is_recompute=True,
-            is_compact=True,
-            distance_metric="cosine",  # CLIP uses normalized vectors; cosine is appropriate
-            num_threads=4,
-        )
-
-        # Add passages (text + metadata)
-        print("📚 Adding passages...")
-        self._add_passages_with_embeddings(builder, passages_file, embeddings)
-
-        print(f"🔨 Building compact index at {index_path} from precomputed embeddings...")
-        builder.build_index_from_embeddings(index_path, str(pkl_path))
-
-        build_time = time.time() - start_time
-        print(f"✅ Compact index built in {build_time:.2f}s")
-
-        # Analyze index size
-        self._analyze_index_size(index_path)
-
-        return index_path
-
-    def build_non_compact_index(
-        self, passages_file: Path, embeddings: np.ndarray, index_path: str, backend: str = "hnsw"
-    ):
-        """Build non-compact LEANN index with CLIP embeddings (recompute=False, compact=False)"""
-        print(f"🏗️ Building non-compact LEANN index with {backend} backend...")
-
-        start_time = time.time()
-
-        # Ensure embeddings are saved (npy + pickle)
-        npy_path = self.data_dir / "clip_image_embeddings.npy"
-        if not npy_path.exists():
-            np.save(npy_path, embeddings)
-            print(f"💾 Saved CLIP embeddings to {npy_path}")
-        # Prepare ids in same order as passages_file
-        ids: list[str] = []
-        with open(passages_file, encoding="utf-8") as f:
-            for line in f:
-                if line.strip():
-                    rec = json.loads(line)
-                    ids.append(str(rec["id"]))
-        if len(ids) != embeddings.shape[0]:
-            raise ValueError(
-                f"IDs count ({len(ids)}) does not match embeddings ({embeddings.shape[0]})."
-            )
-        pkl_path = self.data_dir / "clip_image_embeddings.pkl"
-        if not pkl_path.exists():
-            with open(pkl_path, "wb") as pf:
-                pickle.dump((ids, embeddings.astype(np.float32)), pf)
-            print(f"💾 Saved (ids, embeddings) pickle to {pkl_path}")
-
-        # Initialize builder - non-compact without recompute
-        builder = LeannBuilder(
-            backend_name=backend,
-            embedding_model="clip-ViT-L-14",
-            embedding_mode="sentence-transformers",
-            graph_degree=32,
-            complexity=64,
-            is_recompute=False,  # Store embeddings (no recompute needed)
-            is_compact=False,  # Store full index (not pruned)
-            distance_metric="cosine",
-            num_threads=4,
-        )
-
-        # Add passages - embeddings will be loaded from file
-        print("📚 Adding passages...")
-        self._add_passages_with_embeddings(builder, passages_file, embeddings)
-
-        print(f"🔨 Building non-compact index at {index_path} from precomputed embeddings...")
-        builder.build_index_from_embeddings(index_path, str(pkl_path))
-
-        build_time = time.time() - start_time
-        print(f"✅ Non-compact index built in {build_time:.2f}s")
-
-        # Analyze index size
-        self._analyze_index_size(index_path)
-
-        return index_path
-
-    def _add_passages_with_embeddings(self, builder, passages_file: Path, embeddings: np.ndarray):
-        """Helper to add passages with pre-computed CLIP embeddings"""
-        with open(passages_file, encoding="utf-8") as f:
-            for line in tqdm(f, desc="Adding passages"):
-                if line.strip():
-                    passage = json.loads(line)
-
-                    # Add image metadata - LEANN will handle embeddings separately
-                    # Note: We store image metadata and caption text for searchability
-                    # Important: ensure passage ID in metadata matches vector ID
-                    builder.add_text(
-                        text=passage["text"],  # Image caption for searchability
-                        metadata={**passage["metadata"], "id": passage["id"]},
-                    )
-
-    def _analyze_index_size(self, index_path: str):
-        """Analyze index file sizes"""
-        print("📏 Analyzing index sizes...")
-
-        index_path = Path(index_path)
-        index_dir = index_path.parent
-        index_name = index_path.name  # e.g., laion_index.leann
-        index_prefix = index_path.stem  # e.g., laion_index
-
-        files = [
-            (f"{index_prefix}.index", ".index", "core"),
-            (f"{index_name}.meta.json", ".meta.json", "core"),
-            (f"{index_name}.ids.txt", ".ids.txt", "core"),
-            (f"{index_name}.passages.jsonl", ".passages.jsonl", "passages"),
-            (f"{index_name}.passages.idx", ".passages.idx", "passages"),
-        ]
-
-        def _fmt_size(bytes_val: int) -> str:
-            if bytes_val < 1024:
-                return f"{bytes_val} B"
-            kb = bytes_val / 1024
-            if kb < 1024:
-                return f"{kb:.1f} KB"
-            mb = kb / 1024
-            if mb < 1024:
-                return f"{mb:.2f} MB"
-            gb = mb / 1024
-            return f"{gb:.2f} GB"
-
-        total_index_only_mb = 0.0
-        total_all_mb = 0.0
-        for filename, label, group in files:
-            file_path = index_dir / filename
-            if file_path.exists():
-                size_bytes = file_path.stat().st_size
-                print(f"  {label}: {_fmt_size(size_bytes)}")
-                size_mb = size_bytes / (1024 * 1024)
-                total_all_mb += size_mb
-                if group == "core":
-                    total_index_only_mb += size_mb
-            else:
-                print(f"  {label}: (missing)")
-        print(f"  Total (index only, exclude passages): {total_index_only_mb:.2f} MB")
-        print(f"  Total (including passages): {total_all_mb:.2f} MB")
-
-    def create_evaluation_queries(self, samples: list[dict], num_queries: int = 200):
-        """Create evaluation queries from captions"""
-        print(f"📝 Creating {num_queries} evaluation queries...")
-
-        # Sample random captions as queries
-        import random
-
-        random.seed(42)  # For reproducibility
-
-        query_samples = random.sample(samples, min(num_queries, len(samples)))
-
-        queries_file = self.data_dir / "evaluation_queries.jsonl"
-        with open(queries_file, "w", encoding="utf-8") as f:
-            for sample in query_samples:
-                query = {
-                    "id": sample["id"],
-                    "query": sample["caption"],
-                    "ground_truth_id": sample["id"],  # For potential recall evaluation
-                }
-                f.write(json.dumps(query) + "\n")
-
-        print(f"✅ Created {len(query_samples)} evaluation queries")
-        return queries_file
-
-
-def main():
-    parser = argparse.ArgumentParser(description="Setup LAION Multimodal Benchmark")
-    parser.add_argument("--data-dir", default="data", help="Data directory")
-    parser.add_argument("--num-samples", type=int, default=1000, help="Number of LAION samples")
-    parser.add_argument("--num-queries", type=int, default=50, help="Number of evaluation queries")
-    parser.add_argument("--index-path", default="data/laion_index.leann", help="Output index path")
-    parser.add_argument(
-        "--backend", default="hnsw", choices=["hnsw", "diskann"], help="LEANN backend"
-    )
-    parser.add_argument("--skip-download", action="store_true", help="Skip LAION dataset download")
-    parser.add_argument("--skip-build", action="store_true", help="Skip index building")
-
-    args = parser.parse_args()
-
-    print("🚀 Setting up LAION Multimodal Benchmark")
-    print("=" * 50)
-
-    try:
-        # Initialize setup
-        setup = LAIONSetup(args.data_dir)
-
-        # Step 1: Download LAION subset
-        if not args.skip_download:
-            print("\n📦 Step 1: Download LAION subset")
-            samples = setup.download_laion_subset(args.num_samples)
-
-            # Step 2: Generate CLIP image embeddings
-            print("\n🔍 Step 2: Generate CLIP image embeddings")
-            embeddings, valid_samples = setup.generate_clip_image_embeddings(samples)
-
-            # Step 3: Create LEANN passages (image metadata with embeddings)
-            print("\n📝 Step 3: Create LEANN passages")
-            passages_file = setup.create_leann_passages(valid_samples)
-        else:
-            print("⏭️  Skipping LAION dataset download")
-            # Load existing data
-            passages_file = setup.data_dir / "laion_passages.jsonl"
-            embeddings_file = setup.data_dir / "clip_image_embeddings.npy"
-
-            if not passages_file.exists() or not embeddings_file.exists():
-                raise FileNotFoundError(
-                    "Passages or embeddings file not found. Run without --skip-download first."
-                )
-
-            embeddings = np.load(embeddings_file)
-            print(f"📊 Loaded {len(embeddings)} embeddings from {embeddings_file}")
-
-        # Step 4: Build LEANN indexes (both compact and non-compact)
-        if not args.skip_build:
-            print("\n🏗️ Step 4: Build LEANN indexes with CLIP image embeddings")
-
-            # Build compact index (production mode - small, recompute required)
-            compact_index_path = args.index_path
-            print(f"Building compact index: {compact_index_path}")
-            setup.build_compact_index(passages_file, embeddings, compact_index_path, args.backend)
-
-            # Build non-compact index (comparison mode - large, fast search)
-            non_compact_index_path = args.index_path.replace(".leann", "_noncompact.leann")
-            print(f"Building non-compact index: {non_compact_index_path}")
-            setup.build_non_compact_index(
-                passages_file, embeddings, non_compact_index_path, args.backend
-            )
-
-            # Step 5: Build FAISS flat baseline
-            print("\n🔨 Step 5: Build FAISS flat baseline")
-            if not args.skip_download:
-                baseline_path = setup.build_faiss_baseline(embeddings, valid_samples)
-            else:
-                # Load valid_samples from passages file for FAISS baseline
-                valid_samples = []
-                with open(passages_file, encoding="utf-8") as f:
-                    for line in f:
-                        if line.strip():
-                            passage = json.loads(line)
-                            valid_samples.append({"id": passage["id"], "caption": passage["text"]})
-                baseline_path = setup.build_faiss_baseline(embeddings, valid_samples)
-
-            # Step 6: Create evaluation queries
-            print("\n📝 Step 6: Create evaluation queries")
-            queries_file = setup.create_evaluation_queries(valid_samples, args.num_queries)
-        else:
-            print("⏭️  Skipping index building")
-            baseline_path = "data/baseline/faiss_index.bin"
-            queries_file = setup.data_dir / "evaluation_queries.jsonl"
-
-        print("\n🎉 Setup completed successfully!")
-        print("📊 Summary:")
-        if not args.skip_download:
-            print(f"  Downloaded samples: {len(samples)}")
-            print(f"  Valid samples with embeddings: {len(valid_samples)}")
-        else:
-            print(f"  Loaded {len(embeddings)} embeddings")
-
-        if not args.skip_build:
-            print(f"  Compact index: {compact_index_path}")
-            print(f"  Non-compact index: {non_compact_index_path}")
-            print(f"  FAISS baseline: {baseline_path}")
-            print(f"  Queries: {queries_file}")
-
-            print("\n🔧 Next steps:")
-            print(f"  Run evaluation: python evaluate_laion.py --index {compact_index_path}")
-            print(f"  Or compare with: python evaluate_laion.py --index {non_compact_index_path}")
-        else:
-            print("  Skipped building indexes")
-
-    except KeyboardInterrupt:
-        print("\n⚠️  Setup interrupted by user")
-        exit(1)
-    except Exception as e:
-        print(f"\n❌ Setup failed: {e}")
-        exit(1)
-
-
-if __name__ == "__main__":
-    main()
--- a/benchmarks/llm_utils.py
+++ b/benchmarks/llm_utils.py
@@ -1,301 +0,0 @@
-"""
-LLM utils for RAG benchmarks with Qwen3-8B and Qwen2.5-VL (multimodal)
-"""
-
-import time
-
-try:
-    import torch
-    from transformers import AutoModelForCausalLM, AutoTokenizer
-
-    HF_AVAILABLE = True
-except ImportError:
-    HF_AVAILABLE = False
-
-try:
-    from vllm import LLM, SamplingParams
-
-    VLLM_AVAILABLE = True
-except ImportError:
-    VLLM_AVAILABLE = False
-
-
-def is_qwen3_model(model_name):
-    """Check if model is Qwen3"""
-    return "Qwen3" in model_name or "qwen3" in model_name.lower()
-
-
-def is_qwen_vl_model(model_name):
-    """Check if model is Qwen2.5-VL"""
-    return "Qwen2.5-VL" in model_name or "qwen2.5-vl" in model_name.lower()
-
-
-def apply_qwen3_chat_template(tokenizer, prompt):
-    """Apply Qwen3 chat template with thinking enabled"""
-    messages = [{"role": "user", "content": prompt}]
-    return tokenizer.apply_chat_template(
-        messages,
-        tokenize=False,
-        add_generation_prompt=True,
-        enable_thinking=True,
-    )
-
-
-def extract_thinking_answer(response):
-    """Extract final answer from Qwen3 thinking model response"""
-    if "<think>" in response and "</think>" in response:
-        try:
-            think_end = response.index("</think>") + len("</think>")
-            final_answer = response[think_end:].strip()
-            return final_answer
-        except (ValueError, IndexError):
-            pass
-
-    return response.strip()
-
-
-def load_hf_model(model_name="Qwen/Qwen3-8B"):
-    """Load HuggingFace model"""
-    if not HF_AVAILABLE:
-        raise ImportError("transformers not available")
-
-    print(f"Loading HF: {model_name}")
-    tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
-    model = AutoModelForCausalLM.from_pretrained(
-        model_name,
-        torch_dtype=torch.float16 if torch.cuda.is_available() else torch.float32,
-        device_map="auto",
-        trust_remote_code=True,
-    )
-    return tokenizer, model
-
-
-def load_vllm_model(model_name="Qwen/Qwen3-8B"):
-    """Load vLLM model"""
-    if not VLLM_AVAILABLE:
-        raise ImportError("vllm not available")
-
-    print(f"Loading vLLM: {model_name}")
-    llm = LLM(model=model_name, trust_remote_code=True)
-
-    # Qwen3 specific config
-    if is_qwen3_model(model_name):
-        stop_tokens = ["<|im_end|>", "<|end_of_text|>"]
-        max_tokens = 2048
-    else:
-        stop_tokens = None
-        max_tokens = 1024
-
-    sampling_params = SamplingParams(temperature=0.7, max_tokens=max_tokens, stop=stop_tokens)
-    return llm, sampling_params
-
-
-def generate_hf(tokenizer, model, prompt, max_tokens=None):
-    """Generate with HF - supports Qwen3 thinking models"""
-    model_name = getattr(model, "name_or_path", "unknown")
-    is_qwen3 = is_qwen3_model(model_name)
-
-    # Apply chat template for Qwen3
-    if is_qwen3:
-        prompt = apply_qwen3_chat_template(tokenizer, prompt)
-        max_tokens = max_tokens or 2048
-    else:
-        max_tokens = max_tokens or 1024
-
-    inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
-    with torch.no_grad():
-        outputs = model.generate(
-            **inputs,
-            max_new_tokens=max_tokens,
-            temperature=0.7,
-            do_sample=True,
-            pad_token_id=tokenizer.eos_token_id,
-        )
-    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
-    response = response[len(prompt) :].strip()
-
-    # Extract final answer for thinking models
-    if is_qwen3:
-        return extract_thinking_answer(response)
-    return response
-
-
-def generate_vllm(llm, sampling_params, prompt):
-    """Generate with vLLM - supports Qwen3 thinking models"""
-    outputs = llm.generate([prompt], sampling_params)
-    response = outputs[0].outputs[0].text.strip()
-
-    # Extract final answer for Qwen3 thinking models
-    model_name = str(llm.llm_engine.model_config.model)
-    if is_qwen3_model(model_name):
-        return extract_thinking_answer(response)
-    return response
-
-
-def create_prompt(context, query, domain="default"):
-    """Create RAG prompt"""
-    if domain == "emails":
-        return f"Email content:\n{context}\n\nQuestion: {query}\n\nAnswer:"
-    elif domain == "finance":
-        return f"Financial content:\n{context}\n\nQuestion: {query}\n\nAnswer:"
-    elif domain == "multimodal":
-        return f"Image context:\n{context}\n\nQuestion: {query}\n\nAnswer:"
-    else:
-        return f"Context: {context}\n\nQuestion: {query}\n\nAnswer:"
-
-
-def evaluate_rag(searcher, llm_func, queries, domain="default", top_k=3, complexity=64):
-    """Simple RAG evaluation with timing"""
-    search_times = []
-    gen_times = []
-    results = []
-
-    for i, query in enumerate(queries):
-        # Search
-        start = time.time()
-        docs = searcher.search(query, top_k=top_k, complexity=complexity)
-        search_time = time.time() - start
-
-        # Generate
-        context = "\n\n".join([doc.text for doc in docs])
-        prompt = create_prompt(context, query, domain)
-
-        start = time.time()
-        response = llm_func(prompt)
-        gen_time = time.time() - start
-
-        search_times.append(search_time)
-        gen_times.append(gen_time)
-        results.append(response)
-
-        if i < 3:
-            print(f"Q{i + 1}: Search={search_time:.3f}s, Gen={gen_time:.3f}s")
-
-    return {
-        "avg_search_time": sum(search_times) / len(search_times),
-        "avg_generation_time": sum(gen_times) / len(gen_times),
-        "results": results,
-    }
-
-
-def load_qwen_vl_model(model_name="Qwen/Qwen2.5-VL-7B-Instruct"):
-    """Load Qwen2.5-VL multimodal model"""
-    if not HF_AVAILABLE:
-        raise ImportError("transformers not available")
-
-    print(f"Loading Qwen2.5-VL: {model_name}")
-
-    try:
-        from transformers import AutoModelForVision2Seq, AutoProcessor
-
-        processor = AutoProcessor.from_pretrained(model_name, trust_remote_code=True)
-        model = AutoModelForVision2Seq.from_pretrained(
-            model_name, torch_dtype=torch.bfloat16, device_map="auto", trust_remote_code=True
-        )
-
-        return processor, model
-
-    except Exception as e:
-        print(f"Failed to load with AutoModelForVision2Seq, trying specific class: {e}")
-
-        # Fallback to specific class
-        try:
-            from transformers import AutoProcessor, Qwen2VLForConditionalGeneration
-
-            processor = AutoProcessor.from_pretrained(model_name, trust_remote_code=True)
-            model = Qwen2VLForConditionalGeneration.from_pretrained(
-                model_name, torch_dtype=torch.bfloat16, device_map="auto", trust_remote_code=True
-            )
-
-            return processor, model
-
-        except Exception as e2:
-            raise ImportError(f"Failed to load Qwen2.5-VL model: {e2}")
-
-
-def generate_qwen_vl(processor, model, prompt, image_path=None, max_tokens=512):
-    """Generate with Qwen2.5-VL multimodal model"""
-    from PIL import Image
-
-    # Prepare inputs
-    if image_path:
-        image = Image.open(image_path)
-        inputs = processor(text=prompt, images=image, return_tensors="pt").to(model.device)
-    else:
-        inputs = processor(text=prompt, return_tensors="pt").to(model.device)
-
-    # Generate
-    with torch.no_grad():
-        generated_ids = model.generate(
-            **inputs, max_new_tokens=max_tokens, do_sample=False, temperature=0.1
-        )
-
-    # Decode response
-    generated_ids = generated_ids[:, inputs["input_ids"].shape[1] :]
-    response = processor.decode(generated_ids[0], skip_special_tokens=True)
-
-    return response
-
-
-def create_multimodal_prompt(context, query, image_descriptions, task_type="images"):
-    """Create prompt for multimodal RAG"""
-    if task_type == "images":
-        return f"""Based on the retrieved images and their descriptions, answer the following question.
-
-Retrieved Image Descriptions:
-{context}
-
-Question: {query}
-
-Provide a detailed answer based on the visual content described above."""
-
-    return f"Context: {context}\nQuestion: {query}\nAnswer:"
-
-
-def evaluate_multimodal_rag(searcher, queries, processor=None, model=None, complexity=64):
-    """Evaluate multimodal RAG with Qwen2.5-VL"""
-    search_times = []
-    gen_times = []
-    results = []
-
-    for i, query_item in enumerate(queries):
-        # Handle both string and dict formats for queries
-        if isinstance(query_item, dict):
-            query = query_item.get("query", "")
-            image_path = query_item.get("image_path")  # Optional reference image
-        else:
-            query = str(query_item)
-            image_path = None
-
-        # Search
-        start_time = time.time()
-        search_results = searcher.search(query, top_k=3, complexity=complexity)
-        search_time = time.time() - start_time
-        search_times.append(search_time)
-
-        # Prepare context from search results
-        context_parts = []
-        for result in search_results:
-            context_parts.append(f"- {result.text}")
-        context = "\n".join(context_parts)
-
-        # Generate with multimodal model
-        start_time = time.time()
-        if processor and model:
-            prompt = create_multimodal_prompt(context, query, context_parts)
-            response = generate_qwen_vl(processor, model, prompt, image_path)
-        else:
-            response = f"Context: {context}"
-        gen_time = time.time() - start_time
-
-        gen_times.append(gen_time)
-        results.append(response)
-
-        if i < 3:
-            print(f"Q{i + 1}: Search={search_time:.3f}s, Gen={gen_time:.3f}s")
-
-    return {
-        "avg_search_time": sum(search_times) / len(search_times),
-        "avg_generation_time": sum(gen_times) / len(gen_times),
-        "results": results,
-    }
--- a/benchmarks/run_all.sh
+++ b/benchmarks/run_all.sh
@@ -0,0 +1,49 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+# 公共参数
+INDEX_PATH="benchmarks/data/indices/rpj_wiki/rpj_wiki"
+NUM_QUERIES=20
+BATCH_SIZE=128
+LLM_MODEL="qwen3:4b"
+TOP_K=3
+
+# 日志目录（带时间戳）
+LOG_DIR="logs/eval_runs_$(date +%Y%m%d_%H%M%S)"
+mkdir -p "$LOG_DIR"
+
+# dataset -> ef 列表
+declare -A EF_MAP=(
+  [nq_open.jsonl]="32 62 190"
+  [trivia_qa.jsonl]="77 150 249"
+  [gpqa.jsonl]="41 72 124"
+  [hotpot_qa.jsonl]="137 299 1199"
+)
+
+# 按指定顺序遍历
+ORDERED_DATASETS=(nq_open.jsonl trivia_qa.jsonl gpqa.jsonl hotpot_qa.jsonl)
+
+for dataset in "${ORDERED_DATASETS[@]}"; do
+  for ef in ${EF_MAP[$dataset]}; do
+    log_file="${LOG_DIR}/${dataset%.jsonl}_ef${ef}.log"
+
+    # 展示并记录将要执行的命令
+    cmd=(python benchmarks/run_evaluation.py "$INDEX_PATH" \
+      --num-queries "$NUM_QUERIES" \
+      --ef "$ef" \
+      --batch-size "$BATCH_SIZE" \
+      --llm-model "$LLM_MODEL" \
+      --top-k "$TOP_K" \
+      --queries-file "$dataset")
+
+    echo "=== Running dataset=${dataset} ef=${ef} ===" | tee -a "$log_file"
+    printf 'CMD: '; printf '%q ' "${cmd[@]}" | tee -a "$log_file"; echo | tee -a "$log_file"
+
+    # 同时输出到命令行和日志文件
+    "${cmd[@]}" 2>&1 | tee -a "$log_file"
+
+    echo | tee -a "$log_file"
+  done
+done
+
+echo "All runs completed. Logs in: $LOG_DIR"
--- a/benchmarks/run_evaluation.py
+++ b/benchmarks/run_evaluation.py
@@ -53,7 +53,7 @@ def download_data_if_needed(data_root: Path, download_embeddings: bool = False):
            print(
                "Error: huggingface_hub is not installed. Please install it to download the data:"
            )
-            print("uv sync --only-group dev")
+            print("uv pip install -e '.[dev]'")
            sys.exit(1)
        except Exception as e:
            print(f"An error occurred during data download: {e}")
@@ -203,6 +203,15 @@ def main():
        default=0,
        help="Batch size for HNSW batched search (0 disables batching)",
    )
+    parser.add_argument(
+        "--queries-file",
+        type=str,
+        default="nq_open.jsonl",
+        help=(
+            "Queries file to use. Provide a filename under benchmarks/data/queries "
+            "or an absolute path to a .jsonl file (default: nq_open.jsonl)."
+        ),
+    )
    parser.add_argument(
        "--llm-type",
        type=str,
@@ -314,8 +323,52 @@ def main():
        dataset_type = Path(args.index_path).name
        print(f"WARNING: Could not detect dataset type from path, inferred '{dataset_type}'.")

-    queries_file = data_root / "queries" / "nq_open.jsonl"
-    golden_results_file = data_root / "ground_truth" / dataset_type / "flat_results_nq_k3.json"
+    # Resolve queries file (supports absolute path or name under data/queries)
+    queries_file_candidate = Path(args.queries_file)
+    if queries_file_candidate.is_absolute():
+        queries_file = queries_file_candidate
+    else:
+        queries_file = data_root / "queries" / args.queries_file
+
+    if not queries_file.exists():
+        print(f"Error: Queries file not found: {queries_file}")
+        print("Tip: Use --queries-file with a filename under benchmarks/data/queries or an absolute path.")
+        sys.exit(1)
+
+    # Infer ground-truth file from the queries filename
+    qname = queries_file.name.lower()
+    if "hotpot" in qname:
+        task_key = "hotpot"
+    elif "trivia" in qname:
+        task_key = "trivia"
+    elif "gpqa" in qname:
+        task_key = "gpqa"
+    elif "nq" in qname:
+        task_key = "nq"
+    else:
+        print(
+            "Error: Could not infer task from queries filename. Supported names include 'nq', 'hotpot', 'trivia', 'gpqa'."
+        )
+        print(f"Filename was: {queries_file.name}")
+        sys.exit(1)
+
+    golden_results_file = data_root / "ground_truth" / dataset_type / f"flat_results_{task_key}_k3.json"
+    if not golden_results_file.exists():
+        gt_dir = data_root / "ground_truth" / dataset_type
+        try:
+            available = sorted(p.name for p in gt_dir.glob("flat_results_*_k3.json"))
+        except Exception:
+            available = []
+        print(
+            f"Error: Ground truth file not found for task '{task_key}' under dataset '{dataset_type}': {golden_results_file}"
+        )
+        if available:
+            print("Available ground truth files:")
+            for name in available:
+                print(f"  - {name}")
+        else:
+            print(f"No ground truth files found in {gt_dir}")
+        sys.exit(1)

    print(f"INFO: Detected dataset type: {dataset_type}")
    print(f"INFO: Using queries file: {queries_file}")
@@ -346,15 +399,15 @@ def main():
            search_times.append(time.time() - start_time)

            # Optional: also call the LLM with configurable backend/model (does not affect recall)
-            llm_config = {"type": args.llm_type, "model": args.llm_model}
-            chat = LeannChat(args.index_path, llm_config=llm_config, searcher=searcher)
-            answer = chat.ask(
-                queries[i],
-                top_k=args.top_k,
-                complexity=args.ef_search,
-                batch_size=args.batch_size,
-            )
-            print(f"Answer: {answer}")
+            # llm_config = {"type": args.llm_type, "model": args.llm_model}
+            # chat = LeannChat(args.index_path, llm_config=llm_config, searcher=searcher)
+            # answer = chat.ask(
+            #     queries[i],
+            #     top_k=args.top_k,
+            #     complexity=args.ef_search,
+            #     batch_size=args.batch_size,
+            # )
+            # print(f"Answer: {answer}")
            # Correct Recall Calculation: Based on TEXT content
            new_texts = {result.text for result in new_results}

@@ -378,10 +431,16 @@ def main():
        avg_recall = np.mean(recall_scores) if recall_scores else 0
        avg_time = np.mean(search_times) if search_times else 0

+        print(f"search time: {search_times}")
+
        print("\n🎉 --- Evaluation Complete ---")
        print(f"Avg. Recall@{args.top_k} (efSearch={args.ef_search}): {avg_recall:.4f}")
        print(f"Avg. Search Time: {avg_time:.4f}s")

+        # avg last 10 search times
+        avg_last_10_search_times = np.mean(search_times[-10:])
+        print(f"Avg. Last 10 Search Times: {avg_last_10_search_times:.4f}s")
+
    except Exception as e:
        print(f"\n❌ An error occurred during evaluation: {e}")
        import traceback
--- a/benchmarks/run_speed_bench_all.sh
+++ b/benchmarks/run_speed_bench_all.sh
@@ -0,0 +1,55 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+# Absolute paths (adjust if needed)
+PROMPTS_DIR="/home/tony/yichuan/leann/benchmarks/data/prompts_g5"
+SCRIPT_PATH="/home/tony/yichuan/leann/benchmarks/generation_speed_bench.py"
+
+# Common args
+MAX_TOKENS=2048
+OLLAMA_MODEL="qwen3:4b"
+HF_MODEL="Qwen/Qwen3-4B"
+
+# Logs
+LOG_DIR="/home/tony/yichuan/leann/logs/speed_bench_$(date +%Y%m%d_%H%M%S)"
+mkdir -p "$LOG_DIR"
+
+echo "Scanning: $PROMPTS_DIR"
+
+# Iterate all .txt files under PROMPTS_DIR
+while IFS= read -r -d '' file; do
+  base_name=$(basename "$file")
+  stem_name="${base_name%.*}"
+
+  # 1) Ollama
+  log_ollama="${LOG_DIR}/${stem_name}_ollama.log"
+  cmd_ollama=(python "$SCRIPT_PATH" \
+    --path "$file" \
+    --type ollama \
+    --model "$OLLAMA_MODEL" \
+    --max_tokens "$MAX_TOKENS")
+
+  echo "=== Running (ollama) file=${file} model=${OLLAMA_MODEL} ===" | tee -a "$log_ollama"
+  printf 'CMD: '; printf '%q ' "${cmd_ollama[@]}" | tee -a "$log_ollama"; echo | tee -a "$log_ollama"
+  "${cmd_ollama[@]}" 2>&1 | tee -a "$log_ollama"
+  echo | tee -a "$log_ollama"
+
+  # 2) HF
+  log_hf="${LOG_DIR}/${stem_name}_hf.log"
+  cmd_hf=(python "$SCRIPT_PATH" \
+    --path "$file" \
+    --type hf \
+    --model "$HF_MODEL" \
+    --max_tokens "$MAX_TOKENS")
+
+  echo "=== Running (hf) file=${file} model=${HF_MODEL} ===" | tee -a "$log_hf"
+  printf 'CMD: '; printf '%q ' "${cmd_hf[@]}" | tee -a "$log_hf"; echo | tee -a "$log_hf"
+  "${cmd_hf[@]}" 2>&1 | tee -a "$log_hf"
+  echo | tee -a "$log_hf"
+
+done < <(find "$PROMPTS_DIR" -type f -name '*.txt' -print0)
+
+
+echo "All runs completed. Logs in: $LOG_DIR"
+
+
--- a/docs/CONTRIBUTING.md
+++ b/docs/CONTRIBUTING.md
@@ -53,9 +53,9 @@ We use pre-commit hooks to ensure code quality and consistency. This runs automa

 ### Setup Pre-commit

-1. **Install pre-commit tools**:
+1. **Install pre-commit** (already included when you run `uv sync`):
   ```bash
-   uv sync lint
+   uv pip install pre-commit
   ```

 2. **Install the git hooks**:
@@ -65,7 +65,7 @@ We use pre-commit hooks to ensure code quality and consistency. This runs automa

 3. **Run pre-commit manually** (optional):
   ```bash
-   uv run pre-commit run --all-files
+   pre-commit run --all-files
   ```

 ### Pre-commit Checks
@@ -85,9 +85,6 @@ Our pre-commit configuration includes:
 ### Running Tests

 ```bash
-# Install test tools only (no project runtime)
-uv sync --group test
-
 # Run all tests
 uv run pytest

--- a/docs/ast_chunking_guide.md
+++ b/docs/ast_chunking_guide.md
@@ -26,21 +26,6 @@ leann build my-code-index --docs ./src --use-ast-chunking
 uv pip install -e "."
 ```

-#### For normal users (PyPI install)
- Use `pip install leann` or `uv pip install leann`.
- `astchunk` is pulled automatically from PyPI as a dependency; no extra steps.
-
-#### For developers (from source, editable)
-```bash
-git clone https://github.com/yichuan-w/LEANN.git leann
-cd leann
-git submodule update --init --recursive
-uv sync
-```
- This repo vendors `astchunk` as a git submodule at `packages/astchunk-leann` (our fork).
- `[tool.uv.sources]` maps the `astchunk` package to that path in editable mode.
- You can edit code under `packages/astchunk-leann` and Python will use your changes immediately (no separate `pip install astchunk` needed).
-
 ## Best Practices

 ### When to Use AST Chunking
--- a/docs/configuration-guide.md
+++ b/docs/configuration-guide.md
@@ -83,81 +83,6 @@ ollama pull nomic-embed-text

 </details>

-## Local & Remote Inference Endpoints
-
-> Applies to both LLMs (`leann ask`) and embeddings (`leann build`).
-
-LEANN now treats Ollama, LM Studio, and other OpenAI-compatible runtimes as first-class providers. You can point LEANN at any compatible endpoint – either on the same machine or across the network – with a couple of flags or environment variables.
-
-### One-Time Environment Setup
-
-```bash
-# Works for OpenAI-compatible runtimes such as LM Studio, vLLM, SGLang, llamafile, etc.
-export OPENAI_API_KEY="your-key"            # or leave unset for local servers that do not check keys
-export OPENAI_BASE_URL="http://localhost:1234/v1"
-
-# Ollama-compatible runtimes (Ollama, Ollama on another host, llamacpp-server, etc.)
-export LEANN_OLLAMA_HOST="http://localhost:11434"   # falls back to OLLAMA_HOST or LOCAL_LLM_ENDPOINT
-```
-
-LEANN also recognises `LEANN_LOCAL_LLM_HOST` (highest priority), `LEANN_OPENAI_BASE_URL`, and `LOCAL_OPENAI_BASE_URL`, so existing scripts continue to work.
-
-### Passing Hosts Per Command
-
-```bash
-# Build an index with a remote embedding server
-leann build my-notes \
-  --docs ./notes \
-  --embedding-mode openai \
-  --embedding-model text-embedding-qwen3-embedding-0.6b \
-  --embedding-api-base http://192.168.1.50:1234/v1 \
-  --embedding-api-key local-dev-key
-
-# Query using a local LM Studio instance via OpenAI-compatible API
-leann ask my-notes \
-  --llm openai \
-  --llm-model qwen3-8b \
-  --api-base http://localhost:1234/v1 \
-  --api-key local-dev-key
-
-# Query an Ollama instance running on another box
-leann ask my-notes \
-  --llm ollama \
-  --llm-model qwen3:14b \
-  --host http://192.168.1.101:11434
-```
-
-⚠️ **Make sure the endpoint is reachable**: when your inference server runs on a home/workstation and the index/search job runs in the cloud, the server must be able to reach the host you configured. Typical options include:
-
- Expose a public IP (and open the relevant port) on the machine that hosts LM Studio/Ollama.
- Configure router or cloud provider port forwarding.
- Tunnel traffic through tools like `tailscale`, `cloudflared`, or `ssh -R`.
-
-When you set these options while building an index, LEANN stores them in `meta.json`. Any subsequent `leann ask` or searcher process automatically reuses the same provider settings – even when we spawn background embedding servers. This makes the “server without GPU talking to my local workstation” workflow from [issue #80](https://github.com/yichuan-w/LEANN/issues/80#issuecomment-2287230548) work out-of-the-box.
-
-**Tip:** If your runtime does not require an API key (many local stacks don’t), leave `--api-key` unset. LEANN will skip injecting credentials.
-
-### Python API Usage
-
-You can pass the same configuration from Python:
-
-```python
-from leann.api import LeannBuilder
-
-builder = LeannBuilder(
-    backend_name="hnsw",
-    embedding_mode="openai",
-    embedding_model="text-embedding-qwen3-embedding-0.6b",
-    embedding_options={
-        "base_url": "http://192.168.1.50:1234/v1",
-        "api_key": "local-dev-key",
-    },
-)
-builder.build_index("./indexes/my-notes", chunks)
-```
-
-`embedding_options` is persisted to the index `meta.json`, so subsequent `LeannSearcher` or `LeannChat` sessions automatically reuse the same provider settings (the embedding server manager forwards them to the provider for you).
-
 ## Index Selection: Matching Your Scale

 ### HNSW (Hierarchical Navigable Small World)
--- a/docs/grep_search.md
+++ b/docs/grep_search.md
@@ -1,149 +0,0 @@
-# LEANN Grep Search Usage Guide
-
-## Overview
-
-LEANN's grep search functionality provides exact text matching for finding specific code patterns, error messages, function names, or exact phrases in your indexed documents.
-
-## Basic Usage
-
-### Simple Grep Search
-
-```python
-from leann.api import LeannSearcher
-
-searcher = LeannSearcher("your_index_path")
-
-# Exact text search
-results = searcher.search("def authenticate_user", use_grep=True, top_k=5)
-
-for result in results:
-    print(f"Score: {result.score}")
-    print(f"Text: {result.text[:100]}...")
-    print("-" * 40)
-```
-
-### Comparison: Semantic vs Grep Search
-
-```python
-# Semantic search - finds conceptually similar content
-semantic_results = searcher.search("machine learning algorithms", top_k=3)
-
-# Grep search - finds exact text matches
-grep_results = searcher.search("def train_model", use_grep=True, top_k=3)
-```
-
-## When to Use Grep Search
-
-### Use Cases
-
- **Code Search**: Finding specific function definitions, class names, or variable references
- **Error Debugging**: Locating exact error messages or stack traces
- **Documentation**: Finding specific API endpoints or exact terminology
-
-### Examples
-
-```python
-# Find function definitions
-functions = searcher.search("def __init__", use_grep=True)
-
-# Find import statements
-imports = searcher.search("from sklearn import", use_grep=True)
-
-# Find specific error types
-errors = searcher.search("FileNotFoundError", use_grep=True)
-
-# Find TODO comments
-todos = searcher.search("TODO:", use_grep=True)
-
-# Find configuration entries
-configs = searcher.search("server_port=", use_grep=True)
-```
-
-## Technical Details
-
-### How It Works
-
-1. **File Location**: Grep search operates on the raw text stored in `.jsonl` files
-2. **Command Execution**: Uses the system `grep` command with case-insensitive search
-3. **Result Processing**: Parses JSON lines and extracts text and metadata
-4. **Scoring**: Simple frequency-based scoring based on query term occurrences
-
-### Search Process
-
-```
-Query: "def train_model"
-  ↓
-grep -i -n "def train_model" documents.leann.passages.jsonl
-  ↓
-Parse matching JSON lines
-  ↓
-Calculate scores based on term frequency
-  ↓
-Return top_k results
-```
-
-### Scoring Algorithm
-
-```python
-# Term frequency in document
-score = text.lower().count(query.lower())
-```
-
-Results are ranked by score (highest first), with higher scores indicating more occurrences of the search term.
-
-## Error Handling
-
-### Common Issues
-
-#### Grep Command Not Found
-```
-RuntimeError: grep command not found. Please install grep or use semantic search.
-```
-
-**Solution**: Install grep on your system:
- **Ubuntu/Debian**: `sudo apt-get install grep`
- **macOS**: grep is pre-installed
- **Windows**: Use WSL or install grep via Git Bash/MSYS2
-
-#### No Results Found
-```python
-# Check if your query exists in the raw data
-results = searcher.search("your_query", use_grep=True)
-if not results:
-    print("No exact matches found. Try:")
-    print("1. Check spelling and case")
-    print("2. Use partial terms")
-    print("3. Switch to semantic search")
-```
-
-## Complete Example
-
-```python
-#!/usr/bin/env python3
-"""
-Grep Search Example
-Demonstrates grep search for exact text matching.
-"""
-
-from leann.api import LeannSearcher
-
-def demonstrate_grep_search():
-    # Initialize searcher
-    searcher = LeannSearcher("my_index")
-
-    print("=== Function Search ===")
-    functions = searcher.search("def __init__", use_grep=True, top_k=5)
-    for i, result in enumerate(functions, 1):
-        print(f"{i}. Score: {result.score}")
-        print(f"   Preview: {result.text[:60]}...")
-        print()
-
-    print("=== Error Search ===")
-    errors = searcher.search("FileNotFoundError", use_grep=True, top_k=3)
-    for result in errors:
-        print(f"Content: {result.text.strip()}")
-        print("-" * 40)
-
-if __name__ == "__main__":
-    demonstrate_grep_search()
-```
--- a/examples/init.py
+++ b/examples/init.py
--- a/examples/dynamic_update_no_recompute.py
+++ b/examples/dynamic_update_no_recompute.py
@@ -1,429 +0,0 @@
-"""Dynamic HNSW update demo without compact storage.
-
-This script reproduces the minimal scenario we used while debugging on-the-fly
-recompute:
-
-1. Build a non-compact HNSW index from the first few paragraphs of a text file.
-2. Print the top results with `recompute_embeddings=True`.
-3. Append additional paragraphs with :meth:`LeannBuilder.update_index`.
-4. Run the same query again to show the newly inserted passages.
-
-Run it with ``uv`` (optionally pointing LEANN_HNSW_LOG_PATH at a file to inspect
-ZMQ activity)::
-
-    LEANN_HNSW_LOG_PATH=embedding_fetch.log \
-    uv run -m examples.dynamic_update_no_recompute \
-      --index-path .leann/examples/leann-demo.leann
-
-By default the script builds an index from ``data/2501.14312v1 (1).pdf`` and
-then updates it with LEANN-related material from ``data/2506.08276v1.pdf``.
-It issues the query "What's LEANN?" before and after the update to show how the
-new passages become immediately searchable. The script uses the
-``sentence-transformers/all-MiniLM-L6-v2`` model with ``is_recompute=True`` so
-Faiss pulls existing vectors on demand via the ZMQ embedding server, while
-freshly added passages are embedded locally just like the initial build.
-
-To make storage comparisons easy, the script can also build a matching
-``is_recompute=False`` baseline (enabled by default) and report the index size
-delta after the update. Disable the baseline run with
-``--skip-compare-no-recompute`` if you only need the recompute flow.
-"""
-
-import argparse
-import json
-from collections.abc import Iterable
-from pathlib import Path
-from typing import Any
-
-from leann.api import LeannBuilder, LeannSearcher
-from leann.registry import register_project_directory
-
-from apps.chunking import create_text_chunks
-
-REPO_ROOT = Path(__file__).resolve().parents[1]
-
-DEFAULT_QUERY = "What's LEANN?"
-DEFAULT_INITIAL_FILES = [
-    REPO_ROOT / "data" / "2501.14312v1 (1).pdf",
-    REPO_ROOT / "data" / "huawei_pangu.md",
-    REPO_ROOT / "data" / "PrideandPrejudice.txt",
-]
-DEFAULT_UPDATE_FILES = [REPO_ROOT / "data" / "2506.08276v1.pdf"]
-
-
-def load_chunks_from_files(paths: list[Path]) -> list[str]:
-    from llama_index.core import SimpleDirectoryReader
-
-    documents = []
-    for path in paths:
-        p = path.expanduser().resolve()
-        if not p.exists():
-            raise FileNotFoundError(f"Input path not found: {p}")
-        if p.is_dir():
-            reader = SimpleDirectoryReader(str(p), recursive=False)
-            documents.extend(reader.load_data(show_progress=True))
-        else:
-            reader = SimpleDirectoryReader(input_files=[str(p)])
-            documents.extend(reader.load_data(show_progress=True))
-
-    if not documents:
-        return []
-
-    chunks = create_text_chunks(
-        documents,
-        chunk_size=512,
-        chunk_overlap=128,
-        use_ast_chunking=False,
-    )
-    return [c for c in chunks if isinstance(c, str) and c.strip()]
-
-
-def run_search(index_path: Path, query: str, top_k: int, *, recompute_embeddings: bool) -> list:
-    searcher = LeannSearcher(str(index_path))
-    try:
-        return searcher.search(
-            query=query,
-            top_k=top_k,
-            recompute_embeddings=recompute_embeddings,
-            batch_size=16,
-        )
-    finally:
-        searcher.cleanup()
-
-
-def print_results(title: str, results: Iterable) -> None:
-    print(f"\n=== {title} ===")
-    res_list = list(results)
-    print(f"results count: {len(res_list)}")
-    print("passages:")
-    if not res_list:
-        print("  (no passages returned)")
-    for res in res_list:
-        snippet = res.text.replace("\n", " ")[:120]
-        print(f"  - {res.id}: {snippet}... (score={res.score:.4f})")
-
-
-def build_initial_index(
-    index_path: Path,
-    paragraphs: list[str],
-    model_name: str,
-    embedding_mode: str,
-    is_recompute: bool,
-) -> None:
-    builder = LeannBuilder(
-        backend_name="hnsw",
-        embedding_model=model_name,
-        embedding_mode=embedding_mode,
-        is_compact=False,
-        is_recompute=is_recompute,
-    )
-    for idx, passage in enumerate(paragraphs):
-        builder.add_text(passage, metadata={"id": str(idx)})
-    builder.build_index(str(index_path))
-
-
-def update_index(
-    index_path: Path,
-    start_id: int,
-    paragraphs: list[str],
-    model_name: str,
-    embedding_mode: str,
-    is_recompute: bool,
-) -> None:
-    updater = LeannBuilder(
-        backend_name="hnsw",
-        embedding_model=model_name,
-        embedding_mode=embedding_mode,
-        is_compact=False,
-        is_recompute=is_recompute,
-    )
-    for offset, passage in enumerate(paragraphs, start=start_id):
-        updater.add_text(passage, metadata={"id": str(offset)})
-    updater.update_index(str(index_path))
-
-
-def ensure_index_dir(index_path: Path) -> None:
-    index_path.parent.mkdir(parents=True, exist_ok=True)
-
-
-def cleanup_index_files(index_path: Path) -> None:
-    """Remove leftover index artifacts for a clean rebuild."""
-
-    parent = index_path.parent
-    if not parent.exists():
-        return
-    stem = index_path.stem
-    for file in parent.glob(f"{stem}*"):
-        if file.is_file():
-            file.unlink()
-
-
-def index_file_size(index_path: Path) -> int:
-    """Return the size of the primary .index file for the given index path."""
-
-    index_file = index_path.parent / f"{index_path.stem}.index"
-    return index_file.stat().st_size if index_file.exists() else 0
-
-
-def load_metadata_snapshot(index_path: Path) -> dict[str, Any] | None:
-    meta_path = index_path.parent / f"{index_path.name}.meta.json"
-    if not meta_path.exists():
-        return None
-    try:
-        return json.loads(meta_path.read_text())
-    except json.JSONDecodeError:
-        return None
-
-
-def run_workflow(
-    *,
-    label: str,
-    index_path: Path,
-    initial_paragraphs: list[str],
-    update_paragraphs: list[str],
-    model_name: str,
-    embedding_mode: str,
-    is_recompute: bool,
-    query: str,
-    top_k: int,
-    skip_search: bool,
-) -> dict[str, Any]:
-    prefix = f"[{label}] " if label else ""
-
-    ensure_index_dir(index_path)
-    cleanup_index_files(index_path)
-
-    print(f"{prefix}Building initial index...")
-    build_initial_index(
-        index_path,
-        initial_paragraphs,
-        model_name,
-        embedding_mode,
-        is_recompute=is_recompute,
-    )
-
-    initial_size = index_file_size(index_path)
-    if not skip_search:
-        before_results = run_search(
-            index_path,
-            query,
-            top_k,
-            recompute_embeddings=is_recompute,
-        )
-    else:
-        before_results = None
-
-    print(f"\n{prefix}Updating index with additional passages...")
-    update_index(
-        index_path,
-        start_id=len(initial_paragraphs),
-        paragraphs=update_paragraphs,
-        model_name=model_name,
-        embedding_mode=embedding_mode,
-        is_recompute=is_recompute,
-    )
-
-    if not skip_search:
-        after_results = run_search(
-            index_path,
-            query,
-            top_k,
-            recompute_embeddings=is_recompute,
-        )
-    else:
-        after_results = None
-    updated_size = index_file_size(index_path)
-
-    return {
-        "initial_size": initial_size,
-        "updated_size": updated_size,
-        "delta": updated_size - initial_size,
-        "before_results": before_results if not skip_search else None,
-        "after_results": after_results if not skip_search else None,
-        "metadata": load_metadata_snapshot(index_path),
-    }
-
-
-def main() -> None:
-    parser = argparse.ArgumentParser(description=__doc__)
-    parser.add_argument(
-        "--initial-files",
-        type=Path,
-        nargs="+",
-        default=DEFAULT_INITIAL_FILES,
-        help="Initial document files (PDF/TXT) used to build the base index",
-    )
-    parser.add_argument(
-        "--index-path",
-        type=Path,
-        default=Path(".leann/examples/leann-demo.leann"),
-        help="Destination index path (default: .leann/examples/leann-demo.leann)",
-    )
-    parser.add_argument(
-        "--initial-count",
-        type=int,
-        default=8,
-        help="Number of chunks to use from the initial documents (default: 8)",
-    )
-    parser.add_argument(
-        "--update-files",
-        type=Path,
-        nargs="*",
-        default=DEFAULT_UPDATE_FILES,
-        help="Additional documents to add during update (PDF/TXT)",
-    )
-    parser.add_argument(
-        "--update-count",
-        type=int,
-        default=4,
-        help="Number of chunks to append from update documents (default: 4)",
-    )
-    parser.add_argument(
-        "--update-text",
-        type=str,
-        default=(
-            "LEANN (Lightweight Embedding ANN) is an indexing toolkit focused on "
-            "recompute-aware HNSW graphs, allowing embeddings to be regenerated "
-            "on demand to keep disk usage minimal."
-        ),
-        help="Fallback text to append if --update-files is omitted",
-    )
-    parser.add_argument(
-        "--top-k",
-        type=int,
-        default=4,
-        help="Number of results to show for each search (default: 4)",
-    )
-    parser.add_argument(
-        "--query",
-        type=str,
-        default=DEFAULT_QUERY,
-        help="Query to run before/after the update",
-    )
-    parser.add_argument(
-        "--embedding-model",
-        type=str,
-        default="sentence-transformers/all-MiniLM-L6-v2",
-        help="Embedding model name",
-    )
-    parser.add_argument(
-        "--embedding-mode",
-        type=str,
-        default="sentence-transformers",
-        choices=["sentence-transformers", "openai", "mlx", "ollama"],
-        help="Embedding backend mode",
-    )
-    parser.add_argument(
-        "--compare-no-recompute",
-        dest="compare_no_recompute",
-        action="store_true",
-        help="Also run a baseline with is_recompute=False and report its index growth.",
-    )
-    parser.add_argument(
-        "--skip-compare-no-recompute",
-        dest="compare_no_recompute",
-        action="store_false",
-        help="Skip building the no-recompute baseline.",
-    )
-    parser.add_argument(
-        "--skip-search",
-        dest="skip_search",
-        action="store_true",
-        help="Skip the search step.",
-    )
-    parser.set_defaults(compare_no_recompute=True)
-    args = parser.parse_args()
-
-    ensure_index_dir(args.index_path)
-    register_project_directory(REPO_ROOT)
-
-    initial_chunks = load_chunks_from_files(list(args.initial_files))
-    if not initial_chunks:
-        raise ValueError("No text chunks extracted from the initial files.")
-
-    initial = initial_chunks[: args.initial_count]
-    if not initial:
-        raise ValueError("Initial chunk set is empty after applying --initial-count.")
-
-    if args.update_files:
-        update_chunks = load_chunks_from_files(list(args.update_files))
-        if not update_chunks:
-            raise ValueError("No text chunks extracted from the update files.")
-        to_add = update_chunks[: args.update_count]
-    else:
-        if not args.update_text:
-            raise ValueError("Provide --update-files or --update-text for the update step.")
-        to_add = [args.update_text]
-    if not to_add:
-        raise ValueError("Update chunk set is empty after applying --update-count.")
-
-    recompute_stats = run_workflow(
-        label="recompute",
-        index_path=args.index_path,
-        initial_paragraphs=initial,
-        update_paragraphs=to_add,
-        model_name=args.embedding_model,
-        embedding_mode=args.embedding_mode,
-        is_recompute=True,
-        query=args.query,
-        top_k=args.top_k,
-        skip_search=args.skip_search,
-    )
-
-    if not args.skip_search:
-        print_results("initial search", recompute_stats["before_results"])
-    if not args.skip_search:
-        print_results("after update", recompute_stats["after_results"])
-    print(
-        f"\n[recompute] Index file size change: {recompute_stats['initial_size']} -> {recompute_stats['updated_size']} bytes"
-        f" (Δ {recompute_stats['delta']})"
-    )
-
-    if recompute_stats["metadata"]:
-        meta_view = {k: recompute_stats["metadata"].get(k) for k in ("is_compact", "is_pruned")}
-        print("[recompute] metadata snapshot:")
-        print(json.dumps(meta_view, indent=2))
-
-    if args.compare_no_recompute:
-        baseline_path = (
-            args.index_path.parent / f"{args.index_path.stem}-norecompute{args.index_path.suffix}"
-        )
-        baseline_stats = run_workflow(
-            label="no-recompute",
-            index_path=baseline_path,
-            initial_paragraphs=initial,
-            update_paragraphs=to_add,
-            model_name=args.embedding_model,
-            embedding_mode=args.embedding_mode,
-            is_recompute=False,
-            query=args.query,
-            top_k=args.top_k,
-            skip_search=args.skip_search,
-        )
-
-        print(
-            f"\n[no-recompute] Index file size change: {baseline_stats['initial_size']} -> {baseline_stats['updated_size']} bytes"
-            f" (Δ {baseline_stats['delta']})"
-        )
-
-        after_texts = (
-            [res.text for res in recompute_stats["after_results"]] if not args.skip_search else None
-        )
-        baseline_after_texts = (
-            [res.text for res in baseline_stats["after_results"]] if not args.skip_search else None
-        )
-        if after_texts == baseline_after_texts:
-            print(
-                "[no-recompute] Search results match recompute baseline; see above for the shared output."
-            )
-        else:
-            print("[no-recompute] WARNING: search results differ from recompute baseline.")
-
-        if baseline_stats["metadata"]:
-            meta_view = {k: baseline_stats["metadata"].get(k) for k in ("is_compact", "is_pruned")}
-            print("[no-recompute] metadata snapshot:")
-            print(json.dumps(meta_view, indent=2))
-
-
-if __name__ == "__main__":
-    main()
--- a/examples/grep_search_example.py
+++ b/examples/grep_search_example.py
@@ -1,35 +0,0 @@
-"""
-Grep Search Example
-
-Shows how to use grep-based text search instead of semantic search.
-Useful when you need exact text matches rather than meaning-based results.
-"""
-
-from leann import LeannSearcher
-
-# Load your index
-searcher = LeannSearcher("my-documents.leann")
-
-# Regular semantic search
-print("=== Semantic Search ===")
-results = searcher.search("machine learning algorithms", top_k=3)
-for result in results:
-    print(f"Score: {result.score:.3f}")
-    print(f"Text: {result.text[:80]}...")
-    print()
-
-# Grep-based search for exact text matches
-print("=== Grep Search ===")
-results = searcher.search("def train_model", top_k=3, use_grep=True)
-for result in results:
-    print(f"Score: {result.score}")
-    print(f"Text: {result.text[:80]}...")
-    print()
-
-# Find specific error messages
-error_results = searcher.search("FileNotFoundError", use_grep=True)
-print(f"Found {len(error_results)} files mentioning FileNotFoundError")
-
-# Search for function definitions
-func_results = searcher.search("class SearchResult", use_grep=True, top_k=5)
-print(f"Found {len(func_results)} class definitions")
--- a/examples/mcp_integration_demo.py
+++ b/examples/mcp_integration_demo.py
@@ -1,178 +0,0 @@
-#!/usr/bin/env python3
-"""
-MCP Integration Examples for LEANN
-
-This script demonstrates how to use LEANN with different MCP servers for
-RAG on various platforms like Slack and Twitter.
-
-Examples:
-1. Slack message RAG via MCP
-2. Twitter bookmark RAG via MCP
-3. Testing MCP server connections
-"""
-
-import asyncio
-import sys
-from pathlib import Path
-
-# Add the parent directory to the path so we can import from apps
-sys.path.append(str(Path(__file__).parent.parent))
-
-
-async def demo_slack_mcp():
-    """Demonstrate Slack MCP integration."""
-    print("=" * 60)
-    print("🔥 Slack MCP RAG Demo")
-    print("=" * 60)
-
-    print("\n1. Testing Slack MCP server connection...")
-
-    # This would typically use a real MCP server command
-    # For demo purposes, we show what the command would look like
-    # slack_app = SlackMCPRAG()  # Would be used for actual testing
-
-    # Simulate command line arguments for testing
-    class MockArgs:
-        mcp_server = "slack-mcp-server"  # This would be the actual MCP server command
-        workspace_name = "my-workspace"
-        channels = ["general", "random", "dev-team"]
-        no_concatenate_conversations = False
-        max_messages_per_channel = 50
-        test_connection = True
-
-    print(f"MCP Server Command: {MockArgs.mcp_server}")
-    print(f"Workspace: {MockArgs.workspace_name}")
-    print(f"Channels: {', '.join(MockArgs.channels)}")
-
-    # In a real scenario, you would run:
-    # success = await slack_app.test_mcp_connection(MockArgs)
-
-    print("\n📝 Example usage:")
-    print("python -m apps.slack_rag \\")
-    print("  --mcp-server 'slack-mcp-server' \\")
-    print("  --workspace-name 'my-team' \\")
-    print("  --channels general dev-team \\")
-    print("  --test-connection")
-
-    print("\n🔍 After indexing, you could query:")
-    print("- 'What did the team discuss about the project deadline?'")
-    print("- 'Find messages about the new feature launch'")
-    print("- 'Show me conversations about budget planning'")
-
-
-async def demo_twitter_mcp():
-    """Demonstrate Twitter MCP integration."""
-    print("\n" + "=" * 60)
-    print("🐦 Twitter MCP RAG Demo")
-    print("=" * 60)
-
-    print("\n1. Testing Twitter MCP server connection...")
-
-    # twitter_app = TwitterMCPRAG()  # Would be used for actual testing
-
-    class MockArgs:
-        mcp_server = "twitter-mcp-server"
-        username = None  # Fetch all bookmarks
-        max_bookmarks = 500
-        no_tweet_content = False
-        no_metadata = False
-        test_connection = True
-
-    print(f"MCP Server Command: {MockArgs.mcp_server}")
-    print(f"Max Bookmarks: {MockArgs.max_bookmarks}")
-    print(f"Include Content: {not MockArgs.no_tweet_content}")
-    print(f"Include Metadata: {not MockArgs.no_metadata}")
-
-    print("\n📝 Example usage:")
-    print("python -m apps.twitter_rag \\")
-    print("  --mcp-server 'twitter-mcp-server' \\")
-    print("  --max-bookmarks 1000 \\")
-    print("  --test-connection")
-
-    print("\n🔍 After indexing, you could query:")
-    print("- 'What AI articles did I bookmark last month?'")
-    print("- 'Find tweets about machine learning techniques'")
-    print("- 'Show me bookmarked threads about startup advice'")
-
-
-async def show_mcp_server_setup():
-    """Show how to set up MCP servers."""
-    print("\n" + "=" * 60)
-    print("⚙️  MCP Server Setup Guide")
-    print("=" * 60)
-
-    print("\n🔧 Setting up Slack MCP Server:")
-    print("1. Install a Slack MCP server (example commands):")
-    print("   npm install -g slack-mcp-server")
-    print("   # OR")
-    print("   pip install slack-mcp-server")
-
-    print("\n2. Configure Slack credentials:")
-    print("   export SLACK_BOT_TOKEN='xoxb-your-bot-token'")
-    print("   export SLACK_APP_TOKEN='xapp-your-app-token'")
-
-    print("\n3. Test the server:")
-    print("   slack-mcp-server --help")
-
-    print("\n🔧 Setting up Twitter MCP Server:")
-    print("1. Install a Twitter MCP server:")
-    print("   npm install -g twitter-mcp-server")
-    print("   # OR")
-    print("   pip install twitter-mcp-server")
-
-    print("\n2. Configure Twitter API credentials:")
-    print("   export TWITTER_API_KEY='your-api-key'")
-    print("   export TWITTER_API_SECRET='your-api-secret'")
-    print("   export TWITTER_ACCESS_TOKEN='your-access-token'")
-    print("   export TWITTER_ACCESS_TOKEN_SECRET='your-access-token-secret'")
-
-    print("\n3. Test the server:")
-    print("   twitter-mcp-server --help")
-
-
-async def show_integration_benefits():
-    """Show the benefits of MCP integration."""
-    print("\n" + "=" * 60)
-    print("🌟 Benefits of MCP Integration")
-    print("=" * 60)
-
-    benefits = [
-        ("🔄 Live Data Access", "Fetch real-time data from platforms without manual exports"),
-        ("🔌 Standardized Protocol", "Use any MCP-compatible server with minimal code changes"),
-        ("🚀 Easy Extension", "Add new platforms by implementing MCP readers"),
-        ("🔒 Secure Access", "MCP servers handle authentication and API management"),
-        ("📊 Rich Metadata", "Access full platform metadata (timestamps, engagement, etc.)"),
-        ("⚡ Efficient Processing", "Stream data directly into LEANN without intermediate files"),
-    ]
-
-    for title, description in benefits:
-        print(f"\n{title}")
-        print(f"   {description}")
-
-
-async def main():
-    """Main demo function."""
-    print("🎯 LEANN MCP Integration Examples")
-    print("This demo shows how to integrate LEANN with MCP servers for various platforms.")
-
-    await demo_slack_mcp()
-    await demo_twitter_mcp()
-    await show_mcp_server_setup()
-    await show_integration_benefits()
-
-    print("\n" + "=" * 60)
-    print("✨ Next Steps")
-    print("=" * 60)
-    print("1. Install and configure MCP servers for your platforms")
-    print("2. Test connections using --test-connection flag")
-    print("3. Run indexing to build your RAG knowledge base")
-    print("4. Start querying your personal data!")
-
-    print("\n📚 For more information:")
-    print("- Check the README for detailed setup instructions")
-    print("- Look at the apps/slack_rag.py and apps/twitter_rag.py for implementation details")
-    print("- Explore other MCP servers for additional platforms")
-
-
-if __name__ == "__main__":
-    asyncio.run(main())
--- a/llms.txt
+++ b/llms.txt
@@ -1,28 +0,0 @@
-# llms.txt — LEANN MCP and Agent Integration
-product: LEANN
-homepage: https://github.com/yichuan-w/LEANN
-contact: https://github.com/yichuan-w/LEANN/issues
-
-# Installation
-install: uv tool install leann-core --with leann
-
-# MCP Server Entry Point
-mcp.server: leann_mcp
-mcp.protocol_version: 2024-11-05
-
-# Tools
-mcp.tools: leann_list, leann_search
-
-mcp.tool.leann_list.description: List available LEANN indexes
-mcp.tool.leann_list.input: {}
-
-mcp.tool.leann_search.description: Semantic search across a named LEANN index
-mcp.tool.leann_search.input.index_name: string, required
-mcp.tool.leann_search.input.query: string, required
-mcp.tool.leann_search.input.top_k: integer, optional, default=5, min=1, max=20
-mcp.tool.leann_search.input.complexity: integer, optional, default=32, min=16, max=128
-
-# Notes
-note: Build indexes with `leann build <name> --docs <files...>` before searching.
-example.add: claude mcp add --scope user leann-server -- leann_mcp
-example.verify: claude mcp list | cat
--- a/packages/astchunk-leann
+++ b/packages/astchunk-leann
--- a/packages/leann-backend-diskann/leann_backend_diskann/diskann_backend.py
+++ b/packages/leann-backend-diskann/leann_backend_diskann/diskann_backend.py
@@ -343,8 +343,7 @@ class DiskannSearcher(BaseSearcher):
                "full_index_prefix": full_index_prefix,
                "num_threads": self.num_threads,
                "num_nodes_to_cache": kwargs.get("num_nodes_to_cache", 0),
-                # 1 -> initialize cache using sample_data; 2 -> ready cache without init; others disable cache
-                "cache_mechanism": kwargs.get("cache_mechanism", 1),
+                "cache_mechanism": 1,
                "pq_prefix": "",
                "partition_prefix": partition_prefix,
            }
--- a/packages/leann-backend-diskann/leann_backend_diskann/diskann_embedding_server.py
+++ b/packages/leann-backend-diskann/leann_backend_diskann/diskann_embedding_server.py
@@ -10,7 +10,7 @@ import sys
 import threading
 import time
 from pathlib import Path
-from typing import Any, Optional
+from typing import Optional

 import numpy as np
 import zmq
@@ -32,16 +32,6 @@ if not logger.handlers:
    logger.propagate = False


-_RAW_PROVIDER_OPTIONS = os.getenv("LEANN_EMBEDDING_OPTIONS")
-try:
-    PROVIDER_OPTIONS: dict[str, Any] = (
-        json.loads(_RAW_PROVIDER_OPTIONS) if _RAW_PROVIDER_OPTIONS else {}
-    )
-except json.JSONDecodeError:
-    logger.warning("Failed to parse LEANN_EMBEDDING_OPTIONS; ignoring provider options")
-    PROVIDER_OPTIONS = {}
-
-
 def create_diskann_embedding_server(
    passages_file: Optional[str] = None,
    zmq_port: int = 5555,
@@ -191,12 +181,7 @@ def create_diskann_embedding_server(
                    logger.debug(f"Text lengths: {[len(t) for t in texts[:5]]}")  # Show first 5

                # Process embeddings using unified computation
-                embeddings = compute_embeddings(
-                    texts,
-                    model_name,
-                    mode=embedding_mode,
-                    provider_options=PROVIDER_OPTIONS,
-                )
+                embeddings = compute_embeddings(texts, model_name, mode=embedding_mode)
                logger.info(
                    f"Computed embeddings for {len(texts)} texts, shape: {embeddings.shape}"
                )
@@ -311,12 +296,7 @@ def create_diskann_embedding_server(
                            continue

                    # Process the request
-                    embeddings = compute_embeddings(
-                        texts,
-                        model_name,
-                        mode=embedding_mode,
-                        provider_options=PROVIDER_OPTIONS,
-                    )
+                    embeddings = compute_embeddings(texts, model_name, mode=embedding_mode)
                    logger.info(f"Computed embeddings shape: {embeddings.shape}")

                    # Validation
--- a/packages/leann-backend-diskann/pyproject.toml
+++ b/packages/leann-backend-diskann/pyproject.toml
@@ -1,11 +1,11 @@
 [build-system]
-requires = ["scikit-build-core>=0.10", "pybind11>=2.12.0", "numpy", "cmake>=3.30"]
+requires = ["scikit-build-core>=0.10", "pybind11>=2.12.0", "numpy"]
 build-backend = "scikit_build_core.build"

 [project]
 name = "leann-backend-diskann"
-version = "0.3.4"
-dependencies = ["leann-core==0.3.4", "numpy", "protobuf>=3.19.0"]
+version = "0.3.2"
+dependencies = ["leann-core==0.3.2", "numpy", "protobuf>=3.19.0"]

 [tool.scikit-build]
 # Key: simplified CMake path
--- a/packages/leann-backend-diskann/third_party/DiskANN
+++ b/packages/leann-backend-diskann/third_party/DiskANN
--- a/packages/leann-backend-hnsw/CMakeLists.txt
+++ b/packages/leann-backend-hnsw/CMakeLists.txt
@@ -49,28 +49,9 @@ set(BUILD_TESTING OFF CACHE BOOL "" FORCE)
 set(FAISS_ENABLE_C_API OFF CACHE BOOL "" FORCE)
 set(FAISS_OPT_LEVEL "generic" CACHE STRING "" FORCE)

-# Disable x86-specific SIMD optimizations (important for ARM64 compatibility)
+# Disable additional SIMD versions to speed up compilation
 set(FAISS_ENABLE_AVX2 OFF CACHE BOOL "" FORCE)
 set(FAISS_ENABLE_AVX512 OFF CACHE BOOL "" FORCE)
-set(FAISS_ENABLE_SSE4_1 OFF CACHE BOOL "" FORCE)
-
-# ARM64-specific configuration
-if(CMAKE_SYSTEM_PROCESSOR MATCHES "aarch64|arm64")
-    message(STATUS "Configuring Faiss for ARM64 architecture")
-
-    if(CMAKE_SYSTEM_NAME STREQUAL "Linux")
-        # Use SVE optimization level for ARM64 Linux (as seen in Faiss conda build)
-        set(FAISS_OPT_LEVEL "sve" CACHE STRING "" FORCE)
-        message(STATUS "Setting FAISS_OPT_LEVEL to 'sve' for ARM64 Linux")
-    else()
-        # Use generic optimization for other ARM64 platforms (like macOS)
-        set(FAISS_OPT_LEVEL "generic" CACHE STRING "" FORCE)
-        message(STATUS "Setting FAISS_OPT_LEVEL to 'generic' for ARM64 ${CMAKE_SYSTEM_NAME}")
-    endif()
-
-    # ARM64 compatibility: Faiss submodule has been modified to fix x86 header inclusion
-    message(STATUS "Using ARM64-compatible Faiss submodule")
-endif()

 # Additional optimization options from INSTALL.md
 set(CMAKE_BUILD_TYPE "Release" CACHE STRING "" FORCE)
--- a/packages/leann-backend-hnsw/leann_backend_hnsw/convert_to_csr.py
+++ b/packages/leann-backend-hnsw/leann_backend_hnsw/convert_to_csr.py
@@ -5,8 +5,6 @@ import os
 import struct
 import sys
 import time
-from dataclasses import dataclass
-from typing import Any, Optional

 import numpy as np

@@ -239,288 +237,6 @@ def write_compact_format(
        f_out.write(storage_data)


-@dataclass
-class HNSWComponents:
-    original_hnsw_data: dict[str, Any]
-    assign_probas_np: np.ndarray
-    cum_nneighbor_per_level_np: np.ndarray
-    levels_np: np.ndarray
-    is_compact: bool
-    compact_level_ptr: Optional[np.ndarray] = None
-    compact_node_offsets_np: Optional[np.ndarray] = None
-    compact_neighbors_data: Optional[list[int]] = None
-    offsets_np: Optional[np.ndarray] = None
-    neighbors_np: Optional[np.ndarray] = None
-    storage_fourcc: int = NULL_INDEX_FOURCC
-    storage_data: bytes = b""
-
-
-def _read_hnsw_structure(f) -> HNSWComponents:
-    original_hnsw_data: dict[str, Any] = {}
-
-    hnsw_index_fourcc = read_struct(f, "<I")
-    if hnsw_index_fourcc not in EXPECTED_HNSW_FOURCCS:
-        raise ValueError(
-            f"Unexpected HNSW FourCC: {hnsw_index_fourcc:08x}. Expected one of {EXPECTED_HNSW_FOURCCS}."
-        )
-
-    original_hnsw_data["index_fourcc"] = hnsw_index_fourcc
-    original_hnsw_data["d"] = read_struct(f, "<i")
-    original_hnsw_data["ntotal"] = read_struct(f, "<q")
-    original_hnsw_data["dummy1"] = read_struct(f, "<q")
-    original_hnsw_data["dummy2"] = read_struct(f, "<q")
-    original_hnsw_data["is_trained"] = read_struct(f, "?")
-    original_hnsw_data["metric_type"] = read_struct(f, "<i")
-    original_hnsw_data["metric_arg"] = 0.0
-    if original_hnsw_data["metric_type"] > 1:
-        original_hnsw_data["metric_arg"] = read_struct(f, "<f")
-
-    assign_probas_np = read_numpy_vector(f, np.float64, "d")
-    cum_nneighbor_per_level_np = read_numpy_vector(f, np.int32, "i")
-    levels_np = read_numpy_vector(f, np.int32, "i")
-
-    ntotal = len(levels_np)
-    if ntotal != original_hnsw_data["ntotal"]:
-        original_hnsw_data["ntotal"] = ntotal
-
-    pos_before_compact = f.tell()
-    is_compact_flag = None
-    try:
-        is_compact_flag = read_struct(f, "<?")
-    except EOFError:
-        is_compact_flag = None
-
-    if is_compact_flag:
-        compact_level_ptr = read_numpy_vector(f, np.uint64, "Q")
-        compact_node_offsets_np = read_numpy_vector(f, np.uint64, "Q")
-
-        original_hnsw_data["entry_point"] = read_struct(f, "<i")
-        original_hnsw_data["max_level"] = read_struct(f, "<i")
-        original_hnsw_data["efConstruction"] = read_struct(f, "<i")
-        original_hnsw_data["efSearch"] = read_struct(f, "<i")
-        original_hnsw_data["dummy_upper_beam"] = read_struct(f, "<i")
-
-        storage_fourcc = read_struct(f, "<I")
-        compact_neighbors_data_np = read_numpy_vector(f, np.int32, "i")
-        compact_neighbors_data = compact_neighbors_data_np.tolist()
-        storage_data = f.read()
-
-        return HNSWComponents(
-            original_hnsw_data=original_hnsw_data,
-            assign_probas_np=assign_probas_np,
-            cum_nneighbor_per_level_np=cum_nneighbor_per_level_np,
-            levels_np=levels_np,
-            is_compact=True,
-            compact_level_ptr=compact_level_ptr,
-            compact_node_offsets_np=compact_node_offsets_np,
-            compact_neighbors_data=compact_neighbors_data,
-            storage_fourcc=storage_fourcc,
-            storage_data=storage_data,
-        )
-
-    # Non-compact case
-    f.seek(pos_before_compact)
-
-    pos_before_probe = f.tell()
-    try:
-        suspected_flag = read_struct(f, "<B")
-        if suspected_flag != 0x00:
-            f.seek(pos_before_probe)
-    except EOFError:
-        f.seek(pos_before_probe)
-
-    offsets_np = read_numpy_vector(f, np.uint64, "Q")
-    neighbors_np = read_numpy_vector(f, np.int32, "i")
-
-    original_hnsw_data["entry_point"] = read_struct(f, "<i")
-    original_hnsw_data["max_level"] = read_struct(f, "<i")
-    original_hnsw_data["efConstruction"] = read_struct(f, "<i")
-    original_hnsw_data["efSearch"] = read_struct(f, "<i")
-    original_hnsw_data["dummy_upper_beam"] = read_struct(f, "<i")
-
-    storage_fourcc = NULL_INDEX_FOURCC
-    storage_data = b""
-    try:
-        storage_fourcc = read_struct(f, "<I")
-        storage_data = f.read()
-    except EOFError:
-        storage_fourcc = NULL_INDEX_FOURCC
-
-    return HNSWComponents(
-        original_hnsw_data=original_hnsw_data,
-        assign_probas_np=assign_probas_np,
-        cum_nneighbor_per_level_np=cum_nneighbor_per_level_np,
-        levels_np=levels_np,
-        is_compact=False,
-        offsets_np=offsets_np,
-        neighbors_np=neighbors_np,
-        storage_fourcc=storage_fourcc,
-        storage_data=storage_data,
-    )
-
-
-def _read_hnsw_structure_from_file(path: str) -> HNSWComponents:
-    with open(path, "rb") as f:
-        return _read_hnsw_structure(f)
-
-
-def write_original_format(
-    f_out,
-    original_hnsw_data,
-    assign_probas_np,
-    cum_nneighbor_per_level_np,
-    levels_np,
-    offsets_np,
-    neighbors_np,
-    storage_fourcc,
-    storage_data,
-):
-    """Write non-compact HNSW data in original FAISS order."""
-
-    f_out.write(struct.pack("<I", original_hnsw_data["index_fourcc"]))
-    f_out.write(struct.pack("<i", original_hnsw_data["d"]))
-    f_out.write(struct.pack("<q", original_hnsw_data["ntotal"]))
-    f_out.write(struct.pack("<q", original_hnsw_data["dummy1"]))
-    f_out.write(struct.pack("<q", original_hnsw_data["dummy2"]))
-    f_out.write(struct.pack("<?", original_hnsw_data["is_trained"]))
-    f_out.write(struct.pack("<i", original_hnsw_data["metric_type"]))
-    if original_hnsw_data["metric_type"] > 1:
-        f_out.write(struct.pack("<f", original_hnsw_data["metric_arg"]))
-
-    write_numpy_vector(f_out, assign_probas_np, "d")
-    write_numpy_vector(f_out, cum_nneighbor_per_level_np, "i")
-    write_numpy_vector(f_out, levels_np, "i")
-
-    write_numpy_vector(f_out, offsets_np, "Q")
-    write_numpy_vector(f_out, neighbors_np, "i")
-
-    f_out.write(struct.pack("<i", original_hnsw_data["entry_point"]))
-    f_out.write(struct.pack("<i", original_hnsw_data["max_level"]))
-    f_out.write(struct.pack("<i", original_hnsw_data["efConstruction"]))
-    f_out.write(struct.pack("<i", original_hnsw_data["efSearch"]))
-    f_out.write(struct.pack("<i", original_hnsw_data["dummy_upper_beam"]))
-
-    f_out.write(struct.pack("<I", storage_fourcc))
-    if storage_fourcc != NULL_INDEX_FOURCC and storage_data:
-        f_out.write(storage_data)
-
-
-def prune_hnsw_embeddings(input_filename: str, output_filename: str) -> bool:
-    """Rewrite an HNSW index while dropping the embedded storage section."""
-
-    start_time = time.time()
-    try:
-        with open(input_filename, "rb") as f_in, open(output_filename, "wb") as f_out:
-            original_hnsw_data: dict[str, Any] = {}
-
-            hnsw_index_fourcc = read_struct(f_in, "<I")
-            if hnsw_index_fourcc not in EXPECTED_HNSW_FOURCCS:
-                print(
-                    f"Error: Expected HNSW Index FourCC ({list(EXPECTED_HNSW_FOURCCS)}), got {hnsw_index_fourcc:08x}.",
-                    file=sys.stderr,
-                )
-                return False
-
-            original_hnsw_data["index_fourcc"] = hnsw_index_fourcc
-            original_hnsw_data["d"] = read_struct(f_in, "<i")
-            original_hnsw_data["ntotal"] = read_struct(f_in, "<q")
-            original_hnsw_data["dummy1"] = read_struct(f_in, "<q")
-            original_hnsw_data["dummy2"] = read_struct(f_in, "<q")
-            original_hnsw_data["is_trained"] = read_struct(f_in, "?")
-            original_hnsw_data["metric_type"] = read_struct(f_in, "<i")
-            original_hnsw_data["metric_arg"] = 0.0
-            if original_hnsw_data["metric_type"] > 1:
-                original_hnsw_data["metric_arg"] = read_struct(f_in, "<f")
-
-            assign_probas_np = read_numpy_vector(f_in, np.float64, "d")
-            cum_nneighbor_per_level_np = read_numpy_vector(f_in, np.int32, "i")
-            levels_np = read_numpy_vector(f_in, np.int32, "i")
-
-            ntotal = len(levels_np)
-            if ntotal != original_hnsw_data["ntotal"]:
-                original_hnsw_data["ntotal"] = ntotal
-
-            pos_before_compact = f_in.tell()
-            is_compact_flag = None
-            try:
-                is_compact_flag = read_struct(f_in, "<?")
-            except EOFError:
-                is_compact_flag = None
-
-            if is_compact_flag:
-                compact_level_ptr = read_numpy_vector(f_in, np.uint64, "Q")
-                compact_node_offsets_np = read_numpy_vector(f_in, np.uint64, "Q")
-
-                original_hnsw_data["entry_point"] = read_struct(f_in, "<i")
-                original_hnsw_data["max_level"] = read_struct(f_in, "<i")
-                original_hnsw_data["efConstruction"] = read_struct(f_in, "<i")
-                original_hnsw_data["efSearch"] = read_struct(f_in, "<i")
-                original_hnsw_data["dummy_upper_beam"] = read_struct(f_in, "<i")
-
-                _storage_fourcc = read_struct(f_in, "<I")
-                compact_neighbors_data_np = read_numpy_vector(f_in, np.int32, "i")
-                compact_neighbors_data = compact_neighbors_data_np.tolist()
-                _storage_data = f_in.read()
-
-                write_compact_format(
-                    f_out,
-                    original_hnsw_data,
-                    assign_probas_np,
-                    cum_nneighbor_per_level_np,
-                    levels_np,
-                    compact_level_ptr,
-                    compact_node_offsets_np,
-                    compact_neighbors_data,
-                    NULL_INDEX_FOURCC,
-                    b"",
-                )
-            else:
-                f_in.seek(pos_before_compact)
-
-                pos_before_probe = f_in.tell()
-                try:
-                    suspected_flag = read_struct(f_in, "<B")
-                    if suspected_flag != 0x00:
-                        f_in.seek(pos_before_probe)
-                except EOFError:
-                    f_in.seek(pos_before_probe)
-
-                offsets_np = read_numpy_vector(f_in, np.uint64, "Q")
-                neighbors_np = read_numpy_vector(f_in, np.int32, "i")
-
-                original_hnsw_data["entry_point"] = read_struct(f_in, "<i")
-                original_hnsw_data["max_level"] = read_struct(f_in, "<i")
-                original_hnsw_data["efConstruction"] = read_struct(f_in, "<i")
-                original_hnsw_data["efSearch"] = read_struct(f_in, "<i")
-                original_hnsw_data["dummy_upper_beam"] = read_struct(f_in, "<i")
-
-                _storage_fourcc = None
-                _storage_data = b""
-                try:
-                    _storage_fourcc = read_struct(f_in, "<I")
-                    _storage_data = f_in.read()
-                except EOFError:
-                    _storage_fourcc = NULL_INDEX_FOURCC
-
-                write_original_format(
-                    f_out,
-                    original_hnsw_data,
-                    assign_probas_np,
-                    cum_nneighbor_per_level_np,
-                    levels_np,
-                    offsets_np,
-                    neighbors_np,
-                    NULL_INDEX_FOURCC,
-                    b"",
-                )
-
-        print(f"[{time.time() - start_time:.2f}s] Pruned embeddings from {input_filename}")
-        return True
-    except Exception as exc:
-        print(f"Failed to prune embeddings: {exc}", file=sys.stderr)
-        return False
-
-
 # --- Main Conversion Logic ---


@@ -984,29 +700,6 @@ def convert_hnsw_graph_to_csr(input_filename, output_filename, prune_embeddings=
            pass


-def prune_hnsw_embeddings_inplace(index_filename: str) -> bool:
-    """Convenience wrapper to prune embeddings in-place."""
-
-    temp_path = f"{index_filename}.prune.tmp"
-    success = prune_hnsw_embeddings(index_filename, temp_path)
-    if success:
-        try:
-            os.replace(temp_path, index_filename)
-        except Exception as exc:  # pragma: no cover - defensive
-            logger.error(f"Failed to replace original index with pruned version: {exc}")
-            try:
-                os.remove(temp_path)
-            except OSError:
-                pass
-            return False
-    else:
-        try:
-            os.remove(temp_path)
-        except OSError:
-            pass
-    return success
-
-
 # --- Script Execution ---
 if __name__ == "__main__":
    parser = argparse.ArgumentParser(
--- a/packages/leann-backend-hnsw/leann_backend_hnsw/hnsw_backend.py
+++ b/packages/leann-backend-hnsw/leann_backend_hnsw/hnsw_backend.py
@@ -14,7 +14,7 @@ from leann.interface import (
 from leann.registry import register_backend
 from leann.searcher_base import BaseSearcher

-from .convert_to_csr import convert_hnsw_graph_to_csr, prune_hnsw_embeddings_inplace
+from .convert_to_csr import convert_hnsw_graph_to_csr

 logger = logging.getLogger(__name__)

@@ -90,19 +90,8 @@ class HNSWBuilder(LeannBackendBuilderInterface):
        index_file = index_dir / f"{index_prefix}.index"
        faiss.write_index(index, str(index_file))

-        # Persist ID map so searcher can map FAISS integer labels back to passage IDs
-        try:
-            idmap_file = index_dir / f"{index_prefix}.ids.txt"
-            with open(idmap_file, "w", encoding="utf-8") as f:
-                for id_str in ids:
-                    f.write(str(id_str) + "\n")
-        except Exception as e:
-            logger.warning(f"Failed to write ID map: {e}")
-
        if self.is_compact:
            self._convert_to_csr(index_file)
-        elif self.is_recompute:
-            prune_hnsw_embeddings_inplace(str(index_file))

    def _convert_to_csr(self, index_file: Path):
        """Convert built index to CSR format"""
@@ -144,10 +133,10 @@ class HNSWSearcher(BaseSearcher):
        if metric_enum is None:
            raise ValueError(f"Unsupported distance_metric '{self.distance_metric}'.")

-        backend_meta_kwargs = self.meta.get("backend_kwargs", {})
-        self.is_compact = self.meta.get("is_compact", backend_meta_kwargs.get("is_compact", True))
-        default_pruned = backend_meta_kwargs.get("is_recompute", self.is_compact)
-        self.is_pruned = bool(self.meta.get("is_pruned", default_pruned))
+        self.is_compact, self.is_pruned = (
+            self.meta.get("is_compact", True),
+            self.meta.get("is_pruned", True),
+        )

        index_file = self.index_dir / f"{self.index_path.stem}.index"
        if not index_file.exists():
@@ -161,16 +150,6 @@ class HNSWSearcher(BaseSearcher):

        self._index = faiss.read_index(str(index_file), faiss.IO_FLAG_MMAP, hnsw_config)

-        # Load ID map if available
-        self._id_map: list[str] = []
-        try:
-            idmap_file = self.index_dir / f"{self.index_path.stem}.ids.txt"
-            if idmap_file.exists():
-                with open(idmap_file, encoding="utf-8") as f:
-                    self._id_map = [line.rstrip("\n") for line in f]
-        except Exception as e:
-            logger.warning(f"Failed to load ID map: {e}")
-
    def search(
        self,
        query: np.ndarray,
@@ -269,19 +248,6 @@ class HNSWSearcher(BaseSearcher):
        )
        search_time = time.time() - search_time
        logger.info(f"  Search time in HNSWSearcher.search() backend: {search_time} seconds")
-        if self._id_map:
-
-            def map_label(x: int) -> str:
-                if 0 <= x < len(self._id_map):
-                    return self._id_map[x]
-                return str(x)
-
-            string_labels = [
-                [map_label(int(label)) for label in batch_labels] for batch_labels in labels
-            ]
-        else:
-            string_labels = [
-                [str(int_label) for int_label in batch_labels] for batch_labels in labels
-            ]
+        string_labels = [[str(int_label) for int_label in batch_labels] for batch_labels in labels]

        return {"labels": string_labels, "distances": distances}
--- a/packages/leann-backend-hnsw/leann_backend_hnsw/hnsw_embedding_server.py
+++ b/packages/leann-backend-hnsw/leann_backend_hnsw/hnsw_embedding_server.py
@@ -10,7 +10,7 @@ import sys
 import threading
 import time
 from pathlib import Path
-from typing import Any, Optional
+from typing import Optional

 import msgpack
 import numpy as np
@@ -24,35 +24,13 @@ logger = logging.getLogger(__name__)
 log_level = getattr(logging, LOG_LEVEL, logging.WARNING)
 logger.setLevel(log_level)

-# Ensure we have handlers if none exist
+# Ensure we have a handler if none exists
 if not logger.handlers:
-    stream_handler = logging.StreamHandler()
+    handler = logging.StreamHandler()
    formatter = logging.Formatter("%(asctime)s - %(levelname)s - %(message)s")
-    stream_handler.setFormatter(formatter)
-    logger.addHandler(stream_handler)
-
-log_path = os.getenv("LEANN_HNSW_LOG_PATH")
-if log_path:
-    try:
-        file_handler = logging.FileHandler(log_path, mode="a", encoding="utf-8")
-        file_formatter = logging.Formatter(
-            "%(asctime)s - %(levelname)s - [pid=%(process)d] %(message)s"
-        )
-        file_handler.setFormatter(file_formatter)
-        logger.addHandler(file_handler)
-    except Exception as exc:  # pragma: no cover - best effort logging
-        logger.warning(f"Failed to attach file handler for log path {log_path}: {exc}")
-
-logger.propagate = False
-
-_RAW_PROVIDER_OPTIONS = os.getenv("LEANN_EMBEDDING_OPTIONS")
-try:
-    PROVIDER_OPTIONS: dict[str, Any] = (
-        json.loads(_RAW_PROVIDER_OPTIONS) if _RAW_PROVIDER_OPTIONS else {}
-    )
-except json.JSONDecodeError:
-    logger.warning("Failed to parse LEANN_EMBEDDING_OPTIONS; ignoring provider options")
-    PROVIDER_OPTIONS = {}
+    handler.setFormatter(formatter)
+    logger.addHandler(handler)
+    logger.propagate = False


 def create_hnsw_embedding_server(
@@ -114,35 +92,6 @@ def create_hnsw_embedding_server(
        embedding_dim = 0
    logger.info(f"Loaded PassageManager with {len(passages)} passages from metadata")

-    # Attempt to load ID map (maps FAISS integer labels -> passage IDs)
-    id_map: list[str] = []
-    try:
-        meta_path = Path(passages_file)
-        base = meta_path.name
-        if base.endswith(".meta.json"):
-            base = base[: -len(".meta.json")]  # e.g., laion_index.leann
-        if base.endswith(".leann"):
-            base = base[: -len(".leann")]  # e.g., laion_index
-        idmap_file = meta_path.parent / f"{base}.ids.txt"
-        if idmap_file.exists():
-            with open(idmap_file, encoding="utf-8") as f:
-                id_map = [line.rstrip("\n") for line in f]
-            logger.info(f"Loaded ID map with {len(id_map)} entries from {idmap_file}")
-        else:
-            logger.warning(f"ID map file not found at {idmap_file}; will use raw labels")
-    except Exception as e:
-        logger.warning(f"Failed to load ID map: {e}")
-
-    def _map_node_id(nid) -> str:
-        try:
-            if id_map is not None and len(id_map) > 0 and isinstance(nid, (int, np.integer)):
-                idx = int(nid)
-                if 0 <= idx < len(id_map):
-                    return id_map[idx]
-        except Exception:
-            pass
-        return str(nid)
-
    # (legacy ZMQ thread removed; using shutdown-capable server only)

    def zmq_server_thread_with_shutdown(shutdown_event):
@@ -189,12 +138,7 @@ def create_hnsw_embedding_server(
                    ):
                        last_request_type = "text"
                        last_request_length = len(request)
-                        embeddings = compute_embeddings(
-                            request,
-                            model_name,
-                            mode=embedding_mode,
-                            provider_options=PROVIDER_OPTIONS,
-                        )
+                        embeddings = compute_embeddings(request, model_name, mode=embedding_mode)
                        rep_socket.send(msgpack.packb(embeddings.tolist()))
                        e2e_end = time.time()
                        logger.info(f"⏱️  Text embedding E2E time: {e2e_end - e2e_start:.6f}s")
@@ -224,14 +168,13 @@ def create_hnsw_embedding_server(
                        found_indices: list[int] = []
                        for idx, nid in enumerate(node_ids):
                            try:
-                                passage_id = _map_node_id(nid)
-                                passage_data = passages.get_passage(passage_id)
+                                passage_data = passages.get_passage(str(nid))
                                txt = passage_data.get("text", "")
                                if isinstance(txt, str) and len(txt) > 0:
                                    texts.append(txt)
                                    found_indices.append(idx)
                                else:
-                                    logger.error(f"Empty text for passage ID {passage_id}")
+                                    logger.error(f"Empty text for passage ID {nid}")
                            except KeyError:
                                logger.error(f"Passage ID {nid} not found")
                            except Exception as e:
@@ -244,10 +187,7 @@ def create_hnsw_embedding_server(
                        if texts:
                            try:
                                embeddings = compute_embeddings(
-                                    texts,
-                                    model_name,
-                                    mode=embedding_mode,
-                                    provider_options=PROVIDER_OPTIONS,
+                                    texts, model_name, mode=embedding_mode
                                )
                                logger.info(
                                    f"Computed embeddings for {len(texts)} texts, shape: {embeddings.shape}"
@@ -298,14 +238,13 @@ def create_hnsw_embedding_server(
                    found_indices: list[int] = []
                    for idx, nid in enumerate(node_ids):
                        try:
-                            passage_id = _map_node_id(nid)
-                            passage_data = passages.get_passage(passage_id)
+                            passage_data = passages.get_passage(str(nid))
                            txt = passage_data.get("text", "")
                            if isinstance(txt, str) and len(txt) > 0:
                                texts.append(txt)
                                found_indices.append(idx)
                            else:
-                                logger.error(f"Empty text for passage ID {passage_id}")
+                                logger.error(f"Empty text for passage ID {nid}")
                        except KeyError:
                            logger.error(f"Passage with ID {nid} not found")
                        except Exception as e:
@@ -313,12 +252,7 @@ def create_hnsw_embedding_server(

                    if texts:
                        try:
-                            embeddings = compute_embeddings(
-                                texts,
-                                model_name,
-                                mode=embedding_mode,
-                                provider_options=PROVIDER_OPTIONS,
-                            )
+                            embeddings = compute_embeddings(texts, model_name, mode=embedding_mode)
                            logger.info(
                                f"Computed embeddings for {len(texts)} texts, shape: {embeddings.shape}"
                            )
--- a/packages/leann-backend-hnsw/pyproject.toml
+++ b/packages/leann-backend-hnsw/pyproject.toml
@@ -6,10 +6,10 @@ build-backend = "scikit_build_core.build"

 [project]
 name = "leann-backend-hnsw"
-version = "0.3.4"
+version = "0.3.2"
 description = "Custom-built HNSW (Faiss) backend for the Leann toolkit."
 dependencies = [
-    "leann-core==0.3.4",
+    "leann-core==0.3.2",
    "numpy",
    "pyzmq>=23.0.0",
    "msgpack>=1.0.0",
--- a/packages/leann-backend-hnsw/third_party/faiss
+++ b/packages/leann-backend-hnsw/third_party/faiss
--- a/packages/leann-core/pyproject.toml
+++ b/packages/leann-core/pyproject.toml
@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"

 [project]
 name = "leann-core"
-version = "0.3.4"
+version = "0.3.2"
 description = "Core API and plugin system for LEANN"
 readme = "README.md"
 requires-python = ">=3.9"
--- a/packages/leann-core/src/leann/api.py
+++ b/packages/leann-core/src/leann/api.py
@@ -5,10 +5,7 @@ with the correct, original embedding logic from the user's reference code.

 import json
 import logging
-import os
 import pickle
-import re
-import subprocess
 import time
 import warnings
 from dataclasses import dataclass, field
@@ -16,12 +13,10 @@ from pathlib import Path
 from typing import Any, Literal, Optional, Union

 import numpy as np
-from leann_backend_hnsw.convert_to_csr import prune_hnsw_embeddings_inplace

 from leann.interface import LeannBackendSearcherInterface

 from .chat import get_llm
-from .embedding_server_manager import EmbeddingServerManager
 from .interface import LeannBackendFactoryInterface
 from .metadata_filter import MetadataFilterEngine
 from .registry import BACKEND_REGISTRY
@@ -41,7 +36,6 @@ def compute_embeddings(
    use_server: bool = True,
    port: Optional[int] = None,
    is_build=False,
-    provider_options: Optional[dict[str, Any]] = None,
 ) -> np.ndarray:
    """
    Computes embeddings using different backends.
@@ -75,7 +69,6 @@ def compute_embeddings(
            model_name,
            mode=mode,
            is_build=is_build,
-            provider_options=provider_options,
        )


@@ -282,7 +275,6 @@ class LeannBuilder:
        embedding_model: str = "facebook/contriever",
        dimensions: Optional[int] = None,
        embedding_mode: str = "sentence-transformers",
-        embedding_options: Optional[dict[str, Any]] = None,
        **backend_kwargs,
    ):
        self.backend_name = backend_name
@@ -305,7 +297,6 @@ class LeannBuilder:
        self.embedding_model = embedding_model
        self.dimensions = dimensions
        self.embedding_mode = embedding_mode
-        self.embedding_options = embedding_options or {}

        # Check if we need to use cosine distance for normalized embeddings
        normalized_embeddings_models = {
@@ -413,7 +404,6 @@ class LeannBuilder:
                    self.embedding_model,
                    self.embedding_mode,
                    use_server=False,
-                    provider_options=self.embedding_options,
                )[0]
            )
        path = Path(index_path)
@@ -453,20 +443,8 @@ class LeannBuilder:
            self.embedding_mode,
            use_server=False,
            is_build=True,
-            provider_options=self.embedding_options,
        )
        string_ids = [chunk["id"] for chunk in self.chunks]
-        # Persist ID map alongside index so backends that return integer labels can remap to passage IDs
-        try:
-            idmap_file = (
-                index_dir
-                / f"{index_name[: -len('.leann')] if index_name.endswith('.leann') else index_name}.ids.txt"
-            )
-            with open(idmap_file, "w", encoding="utf-8") as f:
-                for sid in string_ids:
-                    f.write(str(sid) + "\n")
-        except Exception:
-            pass
        current_backend_kwargs = {**self.backend_kwargs, "dimensions": self.dimensions}
        builder_instance = self.backend_factory.builder(**current_backend_kwargs)
        builder_instance.build(embeddings, string_ids, index_path, **current_backend_kwargs)
@@ -491,15 +469,14 @@ class LeannBuilder:
            ],
        }

-        if self.embedding_options:
-            meta_data["embedding_options"] = self.embedding_options
-
        # Add storage status flags for HNSW backend
        if self.backend_name == "hnsw":
            is_compact = self.backend_kwargs.get("is_compact", True)
            is_recompute = self.backend_kwargs.get("is_recompute", True)
            meta_data["is_compact"] = is_compact
-            meta_data["is_pruned"] = bool(is_recompute)
+            meta_data["is_pruned"] = (
+                is_compact and is_recompute
+            )  # Pruned only if compact and recompute
        with open(leann_meta_path, "w", encoding="utf-8") as f:
            json.dump(meta_data, f, indent=2)

@@ -586,17 +563,6 @@ class LeannBuilder:

        # Build the vector index using precomputed embeddings
        string_ids = [str(id_val) for id_val in ids]
-        # Persist ID map (order == embeddings order)
-        try:
-            idmap_file = (
-                index_dir
-                / f"{index_name[: -len('.leann')] if index_name.endswith('.leann') else index_name}.ids.txt"
-            )
-            with open(idmap_file, "w", encoding="utf-8") as f:
-                for sid in string_ids:
-                    f.write(str(sid) + "\n")
-        except Exception:
-            pass
        current_backend_kwargs = {**self.backend_kwargs, "dimensions": self.dimensions}
        builder_instance = self.backend_factory.builder(**current_backend_kwargs)
        builder_instance.build(embeddings, string_ids, index_path)
@@ -625,242 +591,18 @@ class LeannBuilder:
            "embeddings_source": str(embeddings_file),
        }

-        if self.embedding_options:
-            meta_data["embedding_options"] = self.embedding_options
-
        # Add storage status flags for HNSW backend
        if self.backend_name == "hnsw":
            is_compact = self.backend_kwargs.get("is_compact", True)
            is_recompute = self.backend_kwargs.get("is_recompute", True)
            meta_data["is_compact"] = is_compact
-            meta_data["is_pruned"] = bool(is_recompute)
+            meta_data["is_pruned"] = is_compact and is_recompute

        with open(leann_meta_path, "w", encoding="utf-8") as f:
            json.dump(meta_data, f, indent=2)

        logger.info(f"Index built successfully from precomputed embeddings: {index_path}")

-    def update_index(self, index_path: str):
-        """Append new passages and vectors to an existing HNSW index."""
-        if not self.chunks:
-            raise ValueError("No new chunks provided for update.")
-
-        path = Path(index_path)
-        index_dir = path.parent
-        index_name = path.name
-        index_prefix = path.stem
-
-        meta_path = index_dir / f"{index_name}.meta.json"
-        passages_file = index_dir / f"{index_name}.passages.jsonl"
-        offset_file = index_dir / f"{index_name}.passages.idx"
-        index_file = index_dir / f"{index_prefix}.index"
-
-        if not meta_path.exists() or not passages_file.exists() or not offset_file.exists():
-            raise FileNotFoundError("Index metadata or passage files are missing; cannot update.")
-        if not index_file.exists():
-            raise FileNotFoundError(f"HNSW index file not found: {index_file}")
-
-        with open(meta_path, encoding="utf-8") as f:
-            meta = json.load(f)
-        backend_name = meta.get("backend_name")
-        if backend_name != self.backend_name:
-            raise ValueError(
-                f"Index was built with backend '{backend_name}', cannot update with '{self.backend_name}'."
-            )
-
-        meta_backend_kwargs = meta.get("backend_kwargs", {})
-        index_is_compact = meta.get("is_compact", meta_backend_kwargs.get("is_compact", True))
-        if index_is_compact:
-            raise ValueError(
-                "Compact HNSW indices do not support in-place updates. Rebuild required."
-            )
-
-        distance_metric = meta_backend_kwargs.get(
-            "distance_metric", self.backend_kwargs.get("distance_metric", "mips")
-        ).lower()
-        needs_recompute = bool(
-            meta.get("is_pruned")
-            or meta_backend_kwargs.get("is_recompute")
-            or self.backend_kwargs.get("is_recompute")
-        )
-
-        with open(offset_file, "rb") as f:
-            offset_map: dict[str, int] = pickle.load(f)
-        existing_ids = set(offset_map.keys())
-
-        valid_chunks: list[dict[str, Any]] = []
-        for chunk in self.chunks:
-            text = chunk.get("text", "")
-            if not isinstance(text, str) or not text.strip():
-                continue
-            metadata = chunk.setdefault("metadata", {})
-            passage_id = chunk.get("id") or metadata.get("id")
-            if passage_id and passage_id in existing_ids:
-                raise ValueError(f"Passage ID '{passage_id}' already exists in the index.")
-            valid_chunks.append(chunk)
-
-        if not valid_chunks:
-            raise ValueError("No valid chunks to append.")
-
-        texts_to_embed = [chunk["text"] for chunk in valid_chunks]
-        embeddings = compute_embeddings(
-            texts_to_embed,
-            self.embedding_model,
-            self.embedding_mode,
-            use_server=False,
-            is_build=True,
-            provider_options=self.embedding_options,
-        )
-
-        embedding_dim = embeddings.shape[1]
-        expected_dim = meta.get("dimensions")
-        if expected_dim is not None and expected_dim != embedding_dim:
-            raise ValueError(
-                f"Dimension mismatch during update: existing index uses {expected_dim}, got {embedding_dim}."
-            )
-
-        from leann_backend_hnsw import faiss  # type: ignore
-
-        embeddings = np.ascontiguousarray(embeddings, dtype=np.float32)
-        if distance_metric == "cosine":
-            norms = np.linalg.norm(embeddings, axis=1, keepdims=True)
-            norms[norms == 0] = 1
-            embeddings = embeddings / norms
-
-        index = faiss.read_index(str(index_file))
-        if hasattr(index, "is_recompute"):
-            index.is_recompute = needs_recompute
-            print(f"index.is_recompute: {index.is_recompute}")
-        if getattr(index, "storage", None) is None:
-            if index.metric_type == faiss.METRIC_INNER_PRODUCT:
-                storage_index = faiss.IndexFlatIP(index.d)
-            else:
-                storage_index = faiss.IndexFlatL2(index.d)
-            index.storage = storage_index
-            index.own_fields = True
-            # Faiss expects storage.ntotal to reflect the existing graph's
-            # population (even if the vectors themselves were pruned from disk
-            # for recompute mode).  When we attach a fresh IndexFlat here its
-            # ntotal starts at zero, which later causes IndexHNSW::add to
-            # believe new "preset" levels were provided and trips the
-            # `n0 + n == levels.size()` assertion.  Seed the temporary storage
-            # with the current ntotal so Faiss maintains the proper offset for
-            # incoming vectors.
-            try:
-                storage_index.ntotal = index.ntotal
-            except AttributeError:
-                # Older Faiss builds may not expose ntotal as a writable
-                # attribute; in that case we fall back to the default behaviour.
-                pass
-        if index.d != embedding_dim:
-            raise ValueError(
-                f"Existing index dimension ({index.d}) does not match new embeddings ({embedding_dim})."
-            )
-
-        passage_meta_mode = meta.get("embedding_mode", self.embedding_mode)
-        passage_provider_options = meta.get("embedding_options", self.embedding_options)
-
-        base_id = index.ntotal
-        for offset, chunk in enumerate(valid_chunks):
-            new_id = str(base_id + offset)
-            chunk.setdefault("metadata", {})["id"] = new_id
-            chunk["id"] = new_id
-
-        # Append passages/offsets before we attempt index.add so the ZMQ server
-        # can resolve newly assigned IDs during recompute. Keep rollback hooks
-        # so we can restore files if the update fails mid-way.
-        rollback_passages_size = passages_file.stat().st_size if passages_file.exists() else 0
-        offset_map_backup = offset_map.copy()
-
-        try:
-            with open(passages_file, "a", encoding="utf-8") as f:
-                for chunk in valid_chunks:
-                    offset = f.tell()
-                    json.dump(
-                        {
-                            "id": chunk["id"],
-                            "text": chunk["text"],
-                            "metadata": chunk.get("metadata", {}),
-                        },
-                        f,
-                        ensure_ascii=False,
-                    )
-                    f.write("\n")
-                    offset_map[chunk["id"]] = offset
-
-            with open(offset_file, "wb") as f:
-                pickle.dump(offset_map, f)
-
-            server_manager: Optional[EmbeddingServerManager] = None
-            server_started = False
-            requested_zmq_port = int(os.getenv("LEANN_UPDATE_ZMQ_PORT", "5557"))
-
-            try:
-                if needs_recompute:
-                    server_manager = EmbeddingServerManager(
-                        backend_module_name="leann_backend_hnsw.hnsw_embedding_server"
-                    )
-                    server_started, actual_port = server_manager.start_server(
-                        port=requested_zmq_port,
-                        model_name=self.embedding_model,
-                        embedding_mode=passage_meta_mode,
-                        passages_file=str(meta_path),
-                        distance_metric=distance_metric,
-                        provider_options=passage_provider_options,
-                    )
-                    if not server_started:
-                        raise RuntimeError(
-                            "Failed to start HNSW embedding server for recompute update."
-                        )
-                    if actual_port != requested_zmq_port:
-                        logger.warning(
-                            "Embedding server started on port %s instead of requested %s. "
-                            "Using reassigned port.",
-                            actual_port,
-                            requested_zmq_port,
-                        )
-                    try:
-                        index.hnsw.zmq_port = actual_port
-                    except AttributeError:
-                        pass
-
-                if needs_recompute:
-                    for i in range(embeddings.shape[0]):
-                        print(f"add {i} embeddings")
-                        index.add(1, faiss.swig_ptr(embeddings[i : i + 1]))
-                else:
-                    index.add(embeddings.shape[0], faiss.swig_ptr(embeddings))
-                faiss.write_index(index, str(index_file))
-            finally:
-                if server_started and server_manager is not None:
-                    server_manager.stop_server()
-
-        except Exception:
-            # Roll back appended passages/offset map to keep files consistent.
-            if passages_file.exists():
-                with open(passages_file, "rb+") as f:
-                    f.truncate(rollback_passages_size)
-            offset_map = offset_map_backup
-            with open(offset_file, "wb") as f:
-                pickle.dump(offset_map, f)
-            raise
-
-        meta["total_passages"] = len(offset_map)
-        with open(meta_path, "w", encoding="utf-8") as f:
-            json.dump(meta, f, indent=2)
-
-        logger.info(
-            "Appended %d passages to index '%s'. New total: %d",
-            len(valid_chunks),
-            index_path,
-            len(offset_map),
-        )
-
-        self.chunks.clear()
-
-        if needs_recompute:
-            prune_hnsw_embeddings_inplace(str(index_file))
-

 class LeannSearcher:
    def __init__(self, index_path: str, enable_warmup: bool = False, **backend_kwargs):
@@ -884,7 +626,6 @@ class LeannSearcher:
        self.embedding_model = self.meta_data["embedding_model"]
        # Support both old and new format
        self.embedding_mode = self.meta_data.get("embedding_mode", "sentence-transformers")
-        self.embedding_options = self.meta_data.get("embedding_options", {})
        # Delegate portability handling to PassageManager
        self.passage_manager = PassageManager(
            self.meta_data.get("passage_sources", []), metadata_file_path=self.meta_path_str
@@ -896,8 +637,6 @@ class LeannSearcher:
            raise ValueError(f"Backend '{backend_name}' not found.")
        final_kwargs = {**self.meta_data.get("backend_kwargs", {}), **backend_kwargs}
        final_kwargs["enable_warmup"] = enable_warmup
-        if self.embedding_options:
-            final_kwargs.setdefault("embedding_options", self.embedding_options)
        self.backend_impl: LeannBackendSearcherInterface = backend_factory.searcher(
            index_path, **final_kwargs
        )
@@ -914,7 +653,6 @@ class LeannSearcher:
        expected_zmq_port: int = 5557,
        metadata_filters: Optional[dict[str, dict[str, Union[str, int, float, bool, list]]]] = None,
        batch_size: int = 0,
-        use_grep: bool = False,
        **kwargs,
    ) -> list[SearchResult]:
        """
@@ -941,10 +679,6 @@ class LeannSearcher:
        Returns:
            List of SearchResult objects with text, metadata, and similarity scores
        """
-        # Handle grep search
-        if use_grep:
-            return self._grep_search(query, top_k)
-
        logger.info("🔍 LeannSearcher.search() called:")
        logger.info(f"  Query: '{query}'")
        logger.info(f"  Top_k: {top_k}")
@@ -1061,96 +795,9 @@ class LeannSearcher:
        logger.info(f"  {GREEN}✓ Final enriched results: {len(enriched_results)} passages{RESET}")
        return enriched_results

-    def _find_jsonl_file(self) -> Optional[str]:
-        """Find the .jsonl file containing raw passages for grep search"""
-        index_path = Path(self.meta_path_str).parent
-        potential_files = [
-            index_path / "documents.leann.passages.jsonl",
-            index_path.parent / "documents.leann.passages.jsonl",
-        ]
-
-        for file_path in potential_files:
-            if file_path.exists():
-                return str(file_path)
-        return None
-
-    def _grep_search(self, query: str, top_k: int = 5) -> list[SearchResult]:
-        """Perform grep-based search on raw passages"""
-        jsonl_file = self._find_jsonl_file()
-        if not jsonl_file:
-            raise FileNotFoundError("No .jsonl passages file found for grep search")
-
-        try:
-            cmd = ["grep", "-i", "-n", query, jsonl_file]
-            result = subprocess.run(cmd, capture_output=True, text=True, check=False)
-
-            if result.returncode == 1:
-                return []
-            elif result.returncode != 0:
-                raise RuntimeError(f"Grep failed: {result.stderr}")
-
-            matches = []
-            for line in result.stdout.strip().split("\n"):
-                if not line:
-                    continue
-                parts = line.split(":", 1)
-                if len(parts) != 2:
-                    continue
-
-                try:
-                    data = json.loads(parts[1])
-                    text = data.get("text", "")
-                    score = text.lower().count(query.lower())
-
-                    matches.append(
-                        SearchResult(
-                            id=data.get("id", parts[0]),
-                            text=text,
-                            metadata=data.get("metadata", {}),
-                            score=float(score),
-                        )
-                    )
-                except json.JSONDecodeError:
-                    continue
-
-            matches.sort(key=lambda x: x.score, reverse=True)
-            return matches[:top_k]
-
-        except FileNotFoundError:
-            raise RuntimeError(
-                "grep command not found. Please install grep or use semantic search."
-            )
-
-    def _python_regex_search(self, query: str, top_k: int = 5) -> list[SearchResult]:
-        """Fallback regex search"""
-        jsonl_file = self._find_jsonl_file()
-        if not jsonl_file:
-            raise FileNotFoundError("No .jsonl file found")
-
-        pattern = re.compile(re.escape(query), re.IGNORECASE)
-        matches = []
-
-        with open(jsonl_file, encoding="utf-8") as f:
-            for line_num, line in enumerate(f, 1):
-                if pattern.search(line):
-                    try:
-                        data = json.loads(line.strip())
-                        matches.append(
-                            SearchResult(
-                                id=data.get("id", str(line_num)),
-                                text=data.get("text", ""),
-                                metadata=data.get("metadata", {}),
-                                score=float(len(pattern.findall(data.get("text", "")))),
-                            )
-                        )
-                    except json.JSONDecodeError:
-                        continue
-
-        matches.sort(key=lambda x: x.score, reverse=True)
-        return matches[:top_k]
-
    def cleanup(self):
        """Explicitly cleanup embedding server resources.
+
        This method should be called after you're done using the searcher,
        especially in test environments or batch processing scenarios.
        """
@@ -1206,7 +853,6 @@ class LeannChat:
        expected_zmq_port: int = 5557,
        metadata_filters: Optional[dict[str, dict[str, Union[str, int, float, bool, list]]]] = None,
        batch_size: int = 0,
-        use_grep: bool = False,
        **search_kwargs,
    ):
        if llm_kwargs is None:
--- a/packages/leann-core/src/leann/chat.py
+++ b/packages/leann-core/src/leann/chat.py
@@ -12,8 +12,6 @@ from typing import Any, Optional

 import torch

-from .settings import resolve_ollama_host, resolve_openai_api_key, resolve_openai_base_url
-
 # Configure logging
 logging.basicConfig(level=logging.INFO)
 logger = logging.getLogger(__name__)
@@ -312,12 +310,11 @@ def search_hf_models(query: str, limit: int = 10) -> list[str]:


 def validate_model_and_suggest(
-    model_name: str, llm_type: str, host: Optional[str] = None
+    model_name: str, llm_type: str, host: str = "http://localhost:11434"
 ) -> Optional[str]:
    """Validate model name and provide suggestions if invalid"""
    if llm_type == "ollama":
-        resolved_host = resolve_ollama_host(host)
-        available_models = check_ollama_models(resolved_host)
+        available_models = check_ollama_models(host)
        if available_models and model_name not in available_models:
            error_msg = f"Model '{model_name}' not found in your local Ollama installation."

@@ -460,19 +457,19 @@ class LLMInterface(ABC):
 class OllamaChat(LLMInterface):
    """LLM interface for Ollama models."""

-    def __init__(self, model: str = "llama3:8b", host: Optional[str] = None):
+    def __init__(self, model: str = "llama3:8b", host: str = "http://localhost:11434"):
        self.model = model
-        self.host = resolve_ollama_host(host)
-        logger.info(f"Initializing OllamaChat with model='{model}' and host='{self.host}'")
+        self.host = host
+        logger.info(f"Initializing OllamaChat with model='{model}' and host='{host}'")
        try:
            import requests

            # Check if the Ollama server is responsive
-            if self.host:
-                requests.get(self.host)
+            if host:
+                requests.get(host)

            # Pre-check model availability with helpful suggestions
-            model_error = validate_model_and_suggest(model, "ollama", self.host)
+            model_error = validate_model_and_suggest(model, "ollama", host)
            if model_error:
                raise ValueError(model_error)

@@ -481,11 +478,9 @@ class OllamaChat(LLMInterface):
                "The 'requests' library is required for Ollama. Please install it with 'pip install requests'."
            )
        except requests.exceptions.ConnectionError:
-            logger.error(
-                f"Could not connect to Ollama at {self.host}. Please ensure Ollama is running."
-            )
+            logger.error(f"Could not connect to Ollama at {host}. Please ensure Ollama is running.")
            raise ConnectionError(
-                f"Could not connect to Ollama at {self.host}. Please ensure Ollama is running."
+                f"Could not connect to Ollama at {host}. Please ensure Ollama is running."
            )

    def ask(self, prompt: str, **kwargs) -> str:
@@ -527,6 +522,8 @@ class OllamaChat(LLMInterface):
        logger.debug(f"Sending request to Ollama: {payload}")
        try:
            logger.info("Sending request to Ollama and waiting for response...")
+            max_tokens = kwargs.get("max_tokens", 1000)
+            payload["options"]["max_tokens"] = max_tokens
            response = requests.post(full_url, data=json.dumps(payload))
            response.raise_for_status()

@@ -625,8 +622,8 @@ class HFChat(LLMInterface):
        is_qwen_model = "qwen" in self.model.config._name_or_path.lower()

        # For Qwen models, automatically add /no_think to the prompt
-        if is_qwen_model and "/no_think" not in prompt and "/think" not in prompt:
-            prompt = prompt + " /no_think"
+        # if is_qwen_model and "/no_think" not in prompt and "/think" not in prompt:
+        #     prompt = prompt + " /no_think"

        # Prepare chat template
        messages = [{"role": "user", "content": prompt}]
@@ -742,31 +739,21 @@ class GeminiChat(LLMInterface):
 class OpenAIChat(LLMInterface):
    """LLM interface for OpenAI models."""

-    def __init__(
-        self,
-        model: str = "gpt-4o",
-        api_key: Optional[str] = None,
-        base_url: Optional[str] = None,
-    ):
+    def __init__(self, model: str = "gpt-4o", api_key: Optional[str] = None):
        self.model = model
-        self.base_url = resolve_openai_base_url(base_url)
-        self.api_key = resolve_openai_api_key(api_key)
+        self.api_key = api_key or os.getenv("OPENAI_API_KEY")

        if not self.api_key:
            raise ValueError(
                "OpenAI API key is required. Set OPENAI_API_KEY environment variable or pass api_key parameter."
            )

-        logger.info(
-            "Initializing OpenAI Chat with model='%s' and base_url='%s'",
-            model,
-            self.base_url,
-        )
+        logger.info(f"Initializing OpenAI Chat with model='{model}'")

        try:
            import openai

-            self.client = openai.OpenAI(api_key=self.api_key, base_url=self.base_url)
+            self.client = openai.OpenAI(api_key=self.api_key)
        except ImportError:
            raise ImportError(
                "The 'openai' library is required for OpenAI models. Please install it with 'pip install openai'."
@@ -856,16 +843,12 @@ def get_llm(llm_config: Optional[dict[str, Any]] = None) -> LLMInterface:
    if llm_type == "ollama":
        return OllamaChat(
            model=model or "llama3:8b",
-            host=llm_config.get("host"),
+            host=llm_config.get("host", "http://localhost:11434"),
        )
    elif llm_type == "hf":
        return HFChat(model_name=model or "deepseek-ai/deepseek-llm-7b-chat")
    elif llm_type == "openai":
-        return OpenAIChat(
-            model=model or "gpt-4o",
-            api_key=llm_config.get("api_key"),
-            base_url=llm_config.get("base_url"),
-        )
+        return OpenAIChat(model=model or "gpt-4o", api_key=llm_config.get("api_key"))
    elif llm_type == "gemini":
        return GeminiChat(model=model or "gemini-2.5-flash", api_key=llm_config.get("api_key"))
    elif llm_type == "simulated":
--- a/packages/leann-core/src/leann/cli.py
+++ b/packages/leann-core/src/leann/cli.py
@@ -1,5 +1,6 @@
 import argparse
 import asyncio
+import sys
 from pathlib import Path
 from typing import Any, Optional, Union

@@ -9,7 +10,6 @@ from tqdm import tqdm

 from .api import LeannBuilder, LeannChat, LeannSearcher
 from .registry import register_project_directory
-from .settings import resolve_ollama_host, resolve_openai_api_key, resolve_openai_base_url


 def extract_pdf_text_with_pymupdf(file_path: str) -> str:
@@ -124,24 +124,6 @@ Examples:
            choices=["sentence-transformers", "openai", "mlx", "ollama"],
            help="Embedding backend mode (default: sentence-transformers)",
        )
-        build_parser.add_argument(
-            "--embedding-host",
-            type=str,
-            default=None,
-            help="Override Ollama-compatible embedding host",
-        )
-        build_parser.add_argument(
-            "--embedding-api-base",
-            type=str,
-            default=None,
-            help="Base URL for OpenAI-compatible embedding services",
-        )
-        build_parser.add_argument(
-            "--embedding-api-key",
-            type=str,
-            default=None,
-            help="API key for embedding service (defaults to OPENAI_API_KEY)",
-        )
        build_parser.add_argument(
            "--force", "-f", action="store_true", help="Force rebuild existing index"
        )
@@ -257,11 +239,6 @@ Examples:
        # Ask command
        ask_parser = subparsers.add_parser("ask", help="Ask questions")
        ask_parser.add_argument("index_name", help="Index name")
-        ask_parser.add_argument(
-            "query",
-            nargs="?",
-            help="Question to ask (omit for prompt or when using --interactive)",
-        )
        ask_parser.add_argument(
            "--llm",
            type=str,
@@ -272,12 +249,7 @@ Examples:
        ask_parser.add_argument(
            "--model", type=str, default="qwen3:8b", help="Model name (default: qwen3:8b)"
        )
-        ask_parser.add_argument(
-            "--host",
-            type=str,
-            default=None,
-            help="Override Ollama-compatible host (defaults to LEANN_OLLAMA_HOST/OLLAMA_HOST)",
-        )
+        ask_parser.add_argument("--host", type=str, default="http://localhost:11434")
        ask_parser.add_argument(
            "--interactive", "-i", action="store_true", help="Interactive chat mode"
        )
@@ -306,18 +278,6 @@ Examples:
            default=None,
            help="Thinking budget for reasoning models (low/medium/high). Supported by GPT-Oss:20b and other reasoning models.",
        )
-        ask_parser.add_argument(
-            "--api-base",
-            type=str,
-            default=None,
-            help="Base URL for OpenAI-compatible APIs (e.g., http://localhost:10000/v1)",
-        )
-        ask_parser.add_argument(
-            "--api-key",
-            type=str,
-            default=None,
-            help="API key for OpenAI-compatible APIs (defaults to OPENAI_API_KEY)",
-        )

        # List command
        subparsers.add_parser("list", help="List all indexes")
@@ -362,17 +322,9 @@ Examples:

        return basic_matches

-    def _should_exclude_file(self, file_path: Path, gitignore_matches) -> bool:
-        """Check if a file should be excluded using gitignore parser.
-
-        Always match against absolute, posix-style paths for consistency with
-        gitignore_parser expectations.
-        """
-        try:
-            absolute_path = file_path.resolve()
-        except Exception:
-            absolute_path = Path(str(file_path))
-        return gitignore_matches(absolute_path.as_posix())
+    def _should_exclude_file(self, relative_path: Path, gitignore_matches) -> bool:
+        """Check if a file should be excluded using gitignore parser."""
+        return gitignore_matches(str(relative_path))

    def _is_git_submodule(self, path: Path) -> bool:
        """Check if a path is a git submodule."""
@@ -444,9 +396,7 @@ Examples:
        print(f"   {current_path}")
        print("   " + "─" * 45)

-        current_indexes = self._discover_indexes_in_project(
-            current_path, exclude_dirs=other_projects
-        )
+        current_indexes = self._discover_indexes_in_project(current_path)
        if current_indexes:
            for idx in current_indexes:
                total_indexes += 1
@@ -485,14 +435,9 @@ Examples:
            print("   leann build my-docs --docs ./documents")
        else:
            # Count only projects that have at least one discoverable index
-            projects_count = 0
-            for p in valid_projects:
-                if p == current_path:
-                    discovered = self._discover_indexes_in_project(p, exclude_dirs=other_projects)
-                else:
-                    discovered = self._discover_indexes_in_project(p)
-                if len(discovered) > 0:
-                    projects_count += 1
+            projects_count = sum(
+                1 for p in valid_projects if len(self._discover_indexes_in_project(p)) > 0
+            )
            print(f"📊 Total: {total_indexes} indexes across {projects_count} projects")

            if current_indexes_count > 0:
@@ -509,22 +454,9 @@ Examples:
                print("\n💡 Create your first index:")
                print("   leann build my-docs --docs ./documents")

-    def _discover_indexes_in_project(
-        self, project_path: Path, exclude_dirs: Optional[list[Path]] = None
-    ):
-        """Discover all indexes in a project directory (both CLI and apps formats)
-
-        exclude_dirs: when provided, skip any APP-format index files that are
-        located under these directories. This prevents duplicates when the
-        current project is a parent directory of other registered projects.
-        """
+    def _discover_indexes_in_project(self, project_path: Path):
+        """Discover all indexes in a project directory (both CLI and apps formats)"""
        indexes = []
-        exclude_dirs = exclude_dirs or []
-        # normalize to resolved paths once for comparison
-        try:
-            exclude_dirs_resolved = [p.resolve() for p in exclude_dirs]
-        except Exception:
-            exclude_dirs_resolved = exclude_dirs

        # 1. CLI format: .leann/indexes/index_name/
        cli_indexes_dir = project_path / ".leann" / "indexes"
@@ -563,17 +495,6 @@ Examples:
                        continue
                except Exception:
                    pass
-                # Skip meta files that live under excluded directories
-                try:
-                    meta_parent_resolved = meta_file.parent.resolve()
-                    if any(
-                        meta_parent_resolved.is_relative_to(ex_dir)
-                        for ex_dir in exclude_dirs_resolved
-                    ):
-                        continue
-                except Exception:
-                    # best effort; if resolve or comparison fails, do not exclude
-                    pass
                # Use the parent directory name as the app index display name
                display_name = meta_file.parent.name
                # Extract file base used to store files
@@ -1101,8 +1022,7 @@ Examples:

            # Try to use better PDF parsers first, but only if PDFs are requested
            documents = []
-            # Use resolved absolute paths to avoid mismatches (symlinks, relative vs absolute)
-            docs_path = Path(docs_dir).resolve()
+            docs_path = Path(docs_dir)

            # Check if we should process PDFs
            should_process_pdfs = custom_file_types is None or ".pdf" in custom_file_types
@@ -1111,15 +1031,10 @@ Examples:
                for file_path in docs_path.rglob("*.pdf"):
                    # Check if file matches any exclude pattern
                    try:
-                        # Ensure both paths are resolved before computing relativity
-                        file_path_resolved = file_path.resolve()
-                        # Determine directory scope using the non-resolved path to avoid
-                        # misclassifying symlinked entries as outside the docs directory
                        relative_path = file_path.relative_to(docs_path)
                        if not include_hidden and _path_has_hidden_segment(relative_path):
                            continue
-                        # Use absolute path for gitignore matching
-                        if self._should_exclude_file(file_path_resolved, gitignore_matches):
+                        if self._should_exclude_file(relative_path, gitignore_matches):
                            continue
                    except ValueError:
                        # Skip files that can't be made relative to docs_path
@@ -1162,11 +1077,10 @@ Examples:
                ) -> bool:
                    """Return True if file should be included (not excluded)"""
                    try:
-                        docs_path_obj = Path(docs_dir).resolve()
-                        file_path_obj = Path(file_path).resolve()
-                        # Use absolute path for gitignore matching
-                        _ = file_path_obj.relative_to(docs_path_obj)  # validate scope
-                        return not self._should_exclude_file(file_path_obj, gitignore_matches)
+                        docs_path_obj = Path(docs_dir)
+                        file_path_obj = Path(file_path)
+                        relative_path = file_path_obj.relative_to(docs_path_obj)
+                        return not self._should_exclude_file(relative_path, gitignore_matches)
                    except (ValueError, OSError):
                        return True  # Include files that can't be processed

@@ -1256,8 +1170,13 @@ Examples:
        if use_ast:
            print("🧠 Using AST-aware chunking for code files")
            try:
-                # Import enhanced chunking utilities from packaged module
-                from .chunking_utils import create_text_chunks
+                # Import enhanced chunking utilities
+                # Add apps directory to path to import chunking utilities
+                apps_dir = Path(__file__).parent.parent.parent.parent.parent / "apps"
+                if apps_dir.exists():
+                    sys.path.insert(0, str(apps_dir))
+
+                from chunking import create_text_chunks

                # Use enhanced chunking with AST support
                all_texts = create_text_chunks(
@@ -1272,9 +1191,7 @@ Examples:
                )

            except ImportError as e:
-                print(
-                    f"⚠️  AST chunking utilities not available in package ({e}), falling back to traditional chunking"
-                )
+                print(f"⚠️  AST chunking not available ({e}), falling back to traditional chunking")
                use_ast = False

        if not use_ast:
@@ -1366,20 +1283,10 @@ Examples:

        print(f"Building index '{index_name}' with {args.backend} backend...")

-        embedding_options: dict[str, Any] = {}
-        if args.embedding_mode == "ollama":
-            embedding_options["host"] = resolve_ollama_host(args.embedding_host)
-        elif args.embedding_mode == "openai":
-            embedding_options["base_url"] = resolve_openai_base_url(args.embedding_api_base)
-            resolved_embedding_key = resolve_openai_api_key(args.embedding_api_key)
-            if resolved_embedding_key:
-                embedding_options["api_key"] = resolved_embedding_key
-
        builder = LeannBuilder(
            backend_name=args.backend,
            embedding_model=args.embedding_model,
            embedding_mode=args.embedding_mode,
-            embedding_options=embedding_options or None,
            graph_degree=args.graph_degree,
            complexity=args.complexity,
            is_compact=args.compact,
@@ -1527,38 +1434,11 @@ Examples:

        llm_config = {"type": args.llm, "model": args.model}
        if args.llm == "ollama":
-            llm_config["host"] = resolve_ollama_host(args.host)
-        elif args.llm == "openai":
-            llm_config["base_url"] = resolve_openai_base_url(args.api_base)
-            resolved_api_key = resolve_openai_api_key(args.api_key)
-            if resolved_api_key:
-                llm_config["api_key"] = resolved_api_key
+            llm_config["host"] = args.host

        chat = LeannChat(index_path=index_path, llm_config=llm_config)

-        llm_kwargs: dict[str, Any] = {}
-        if args.thinking_budget:
-            llm_kwargs["thinking_budget"] = args.thinking_budget
-
-        def _ask_once(prompt: str) -> None:
-            response = chat.ask(
-                prompt,
-                top_k=args.top_k,
-                complexity=args.complexity,
-                beam_width=args.beam_width,
-                prune_ratio=args.prune_ratio,
-                recompute_embeddings=args.recompute_embeddings,
-                pruning_strategy=args.pruning_strategy,
-                llm_kwargs=llm_kwargs,
-            )
-            print(f"LEANN: {response}")
-
-        initial_query = (args.query or "").strip()
-
        if args.interactive:
-            if initial_query:
-                _ask_once(initial_query)
-
            print("LEANN Assistant ready! Type 'quit' to exit")
            print("=" * 40)

@@ -1571,14 +1451,41 @@ Examples:
                if not user_input:
                    continue

-                _ask_once(user_input)
-        else:
-            query = initial_query or input("Enter your question: ").strip()
-            if not query:
-                print("No question provided. Exiting.")
-                return
+                # Prepare LLM kwargs with thinking budget if specified
+                llm_kwargs = {}
+                if args.thinking_budget:
+                    llm_kwargs["thinking_budget"] = args.thinking_budget

-            _ask_once(query)
+                response = chat.ask(
+                    user_input,
+                    top_k=args.top_k,
+                    complexity=args.complexity,
+                    beam_width=args.beam_width,
+                    prune_ratio=args.prune_ratio,
+                    recompute_embeddings=args.recompute_embeddings,
+                    pruning_strategy=args.pruning_strategy,
+                    llm_kwargs=llm_kwargs,
+                )
+                print(f"LEANN: {response}")
+        else:
+            query = input("Enter your question: ").strip()
+            if query:
+                # Prepare LLM kwargs with thinking budget if specified
+                llm_kwargs = {}
+                if args.thinking_budget:
+                    llm_kwargs["thinking_budget"] = args.thinking_budget
+
+                response = chat.ask(
+                    query,
+                    top_k=args.top_k,
+                    complexity=args.complexity,
+                    beam_width=args.beam_width,
+                    prune_ratio=args.prune_ratio,
+                    recompute_embeddings=args.recompute_embeddings,
+                    pruning_strategy=args.pruning_strategy,
+                    llm_kwargs=llm_kwargs,
+                )
+                print(f"LEANN: {response}")

    async def run(self, args=None):
        parser = self.create_parser()
--- a/packages/leann-core/src/leann/embedding_compute.py
+++ b/packages/leann-core/src/leann/embedding_compute.py
@@ -7,13 +7,11 @@ Preserves all optimization parameters to ensure performance
 import logging
 import os
 import time
-from typing import Any, Optional
+from typing import Any

 import numpy as np
 import torch

-from .settings import resolve_ollama_host, resolve_openai_api_key, resolve_openai_base_url
-
 # Set up logger with proper level
 logger = logging.getLogger(__name__)
 LOG_LEVEL = os.getenv("LEANN_LOG_LEVEL", "WARNING").upper()
@@ -23,6 +21,9 @@ logger.setLevel(log_level)
 # Global model cache to avoid repeated loading
 _model_cache: dict[str, Any] = {}

+# Enable fast tokenizer multithreading by default
+os.environ.setdefault("TOKENIZERS_PARALLELISM", "true")
+

 def compute_embeddings(
    texts: list[str],
@@ -32,8 +33,7 @@ def compute_embeddings(
    batch_size: int = 32,
    adaptive_optimization: bool = True,
    manual_tokenize: bool = False,
-    max_length: int = 512,
-    provider_options: Optional[dict[str, Any]] = None,
+    max_length: int = 256,
 ) -> np.ndarray:
    """
    Unified embedding computation entry point
@@ -49,8 +49,6 @@ def compute_embeddings(
    Returns:
        Normalized embeddings array, shape: (len(texts), embedding_dim)
    """
-    provider_options = provider_options or {}
-
    if mode == "sentence-transformers":
        return compute_embeddings_sentence_transformers(
            texts,
@@ -62,21 +60,11 @@ def compute_embeddings(
            max_length=max_length,
        )
    elif mode == "openai":
-        return compute_embeddings_openai(
-            texts,
-            model_name,
-            base_url=provider_options.get("base_url"),
-            api_key=provider_options.get("api_key"),
-        )
+        return compute_embeddings_openai(texts, model_name)
    elif mode == "mlx":
        return compute_embeddings_mlx(texts, model_name)
    elif mode == "ollama":
-        return compute_embeddings_ollama(
-            texts,
-            model_name,
-            is_build=is_build,
-            host=provider_options.get("host"),
-        )
+        return compute_embeddings_ollama(texts, model_name, is_build=is_build)
    elif mode == "gemini":
        return compute_embeddings_gemini(texts, model_name, is_build=is_build)
    else:
@@ -85,15 +73,18 @@ def compute_embeddings(

 def compute_embeddings_sentence_transformers(
    texts: list[str],
-    model_name: str,
+    model_name: str, 
    use_fp16: bool = True,
    device: str = "auto",
    batch_size: int = 32,
    is_build: bool = False,
    adaptive_optimization: bool = True,
    manual_tokenize: bool = False,
-    max_length: int = 512,
+    max_length: int = 256,
 ) -> np.ndarray:
+    manual_tokenize = False
+    batch_size = 512
+    
    """
    Compute embeddings using SentenceTransformer with model caching and adaptive optimization

@@ -134,7 +125,7 @@ def compute_embeddings_sentence_transformers(
        # Keep original batch_size for CPU

    # Create cache key
-    cache_key = f"sentence_transformers_{model_name}_{device}_{use_fp16}_optimized"
+    cache_key = f"sentence_transformers_{model_name}_{device}_{use_fp16}_optimized_len{max_length}"

    # Check if model is already cached
    if cache_key in _model_cache:
@@ -173,83 +164,47 @@ def compute_embeddings_sentence_transformers(
            "torch_dtype": torch.float16 if use_fp16 else torch.float32,
            "low_cpu_mem_usage": True,
            "_fast_init": True,
-            "attn_implementation": "eager",  # Use eager attention for speed
        }
+        # Prefer SDPA on CUDA; fall back to eager elsewhere
+        if device == "cuda":
+            model_kwargs["attn_implementation"] = "sdpa"
+        else:
+            model_kwargs["attn_implementation"] = "eager"

        tokenizer_kwargs = {
            "use_fast": True,
-            "padding": True,
+            "padding": "max_length",
            "truncation": True,
+            "max_length": max_length,
        }

        try:
-            # Try loading with advanced parameters first (newer versions)
-            local_model_kwargs = model_kwargs.copy()
-            local_tokenizer_kwargs = tokenizer_kwargs.copy()
-            local_model_kwargs["local_files_only"] = True
-            local_tokenizer_kwargs["local_files_only"] = True
+            # Try local loading first
+            model_kwargs["local_files_only"] = True
+            tokenizer_kwargs["local_files_only"] = True

            model = SentenceTransformer(
                model_name,
                device=device,
-                model_kwargs=local_model_kwargs,
-                tokenizer_kwargs=local_tokenizer_kwargs,
+                model_kwargs=model_kwargs,
+                tokenizer_kwargs=tokenizer_kwargs,
                local_files_only=True,
            )
            logger.info("Model loaded successfully! (local + optimized)")
-        except TypeError as e:
-            if "model_kwargs" in str(e) or "tokenizer_kwargs" in str(e):
-                logger.warning(
-                    f"Advanced parameters not supported ({e}), using basic initialization..."
-                )
-                # Fallback to basic initialization for older versions
-                try:
-                    model = SentenceTransformer(
-                        model_name,
-                        device=device,
-                        local_files_only=True,
-                    )
-                    logger.info("Model loaded successfully! (local + basic)")
-                except Exception as e2:
-                    logger.warning(f"Local loading failed ({e2}), trying network download...")
-                    model = SentenceTransformer(
-                        model_name,
-                        device=device,
-                        local_files_only=False,
-                    )
-                    logger.info("Model loaded successfully! (network + basic)")
-            else:
-                raise
        except Exception as e:
            logger.warning(f"Local loading failed ({e}), trying network download...")
-            # Fallback to network loading with advanced parameters
-            try:
-                network_model_kwargs = model_kwargs.copy()
-                network_tokenizer_kwargs = tokenizer_kwargs.copy()
-                network_model_kwargs["local_files_only"] = False
-                network_tokenizer_kwargs["local_files_only"] = False
+            # Fallback to network loading
+            model_kwargs["local_files_only"] = False
+            tokenizer_kwargs["local_files_only"] = False

-                model = SentenceTransformer(
-                    model_name,
-                    device=device,
-                    model_kwargs=network_model_kwargs,
-                    tokenizer_kwargs=network_tokenizer_kwargs,
-                    local_files_only=False,
-                )
-                logger.info("Model loaded successfully! (network + optimized)")
-            except TypeError as e2:
-                if "model_kwargs" in str(e2) or "tokenizer_kwargs" in str(e2):
-                    logger.warning(
-                        f"Advanced parameters not supported ({e2}), using basic network loading..."
-                    )
-                    model = SentenceTransformer(
-                        model_name,
-                        device=device,
-                        local_files_only=False,
-                    )
-                    logger.info("Model loaded successfully! (network + basic)")
-                else:
-                    raise
+            model = SentenceTransformer(
+                model_name,
+                device=device,
+                model_kwargs=model_kwargs,
+                tokenizer_kwargs=tokenizer_kwargs,
+                local_files_only=False,
+            )
+            logger.info("Model loaded successfully! (network + optimized)")

        # Apply additional optimizations based on mode
        if use_fp16 and device in ["cuda", "mps"]:
@@ -272,6 +227,13 @@ def compute_embeddings_sentence_transformers(
        for param in model.parameters():
            param.requires_grad_(False)

+        # Enforce max sequence length for encode path
+        try:
+            if hasattr(model, "max_seq_length"):
+                model.max_seq_length = max_length
+        except Exception:
+            pass
+
        # Cache the model
        _model_cache[cache_key] = model
        logger.info(f"Model cached: {cache_key}")
@@ -284,22 +246,43 @@ def compute_embeddings_sentence_transformers(
    start_time = time.time()
    if not manual_tokenize:
        # Use SentenceTransformer's optimized encode path (default)
+        # print text shapr
        with torch.inference_mode():
+            # print avg len of texts
+            avg_len = sum(len(text) for text in texts) / len(texts)
+            logger.info(f"Avg len of texts: {avg_len}")
+            # print the precision of the model
+            logger.info(f"Model precision: {model.dtype}")
+            time_start = time.time()
            embeddings = model.encode(
                texts,
                batch_size=batch_size,
                show_progress_bar=is_build,  # Don't show progress bar in server environment
-                convert_to_numpy=True,
+                convert_to_tensor=True,
                normalize_embeddings=False,
                device=device,
+                max_length=max_length,
            )
+
        # Synchronize if CUDA to measure accurate wall time
        try:
-            if torch.cuda.is_available():
-                torch.cuda.synchronize()
+            # if torch.cuda.is_available():
+            #     torch.cuda.synchronize()
+            time_end = time.time()
+            embedding_time, embedding_tpt = (
+                time_end - time_start,
+                embeddings.shape[0] / (time_end - time_start),
+            )
+            logger.info(
+                f"Time taken in embedding {batch_size} texts in embedding model: {embedding_time} seconds, embedding tpt: {embedding_tpt} seqs/s"
+            )
        except Exception:
            pass
+        # Single CPU copy after timing (avoid per-batch D2H sync)
+        if isinstance(embeddings, torch.Tensor):
+            embeddings = embeddings.float().cpu().numpy()
    else:
+        time_start = time.time()
        # Manual tokenization + forward pass using HF AutoTokenizer/AutoModel
        try:
            from transformers import AutoModel, AutoTokenizer  # type: ignore
@@ -307,8 +290,8 @@ def compute_embeddings_sentence_transformers(
            raise ImportError(f"transformers is required for manual_tokenize=True: {e}")

        # Cache tokenizer and model
-        tok_cache_key = f"hf_tokenizer_{model_name}"
-        mdl_cache_key = f"hf_model_{model_name}_{device}_{use_fp16}"
+        tok_cache_key = f"hf_tokenizer_{model_name}_len{max_length}_padmax"
+        mdl_cache_key = f"hf_model_{model_name}_{device}_{use_fp16}_len{max_length}"
        if tok_cache_key in _model_cache and mdl_cache_key in _model_cache:
            hf_tokenizer = _model_cache[tok_cache_key]
            hf_model = _model_cache[mdl_cache_key]
@@ -329,9 +312,10 @@ def compute_embeddings_sentence_transformers(
            _model_cache[tok_cache_key] = hf_tokenizer
            _model_cache[mdl_cache_key] = hf_model

-        all_embeddings: list[np.ndarray] = []
+        emb_list: list[torch.Tensor] = []
        # Progress bar when building or for large inputs
        show_progress = is_build or len(texts) > 32
+        show_progress = False
        try:
            if show_progress:
                from tqdm import tqdm  # type: ignore
@@ -354,28 +338,36 @@ def compute_embeddings_sentence_transformers(
                tokenize_start_time = time.time()
                inputs = hf_tokenizer(
                    batch_texts,
-                    padding=True,
+                    padding="max_length",
                    truncation=True,
                    max_length=max_length,
                    return_tensors="pt",
                )
                tokenize_end_time = time.time()
-                logger.info(
+                logger.debug(
                    f"Tokenize time taken: {tokenize_end_time - tokenize_start_time} seconds"
                )
-                # Print shapes of all input tensors for debugging
-                for k, v in inputs.items():
-                    print(f"inputs[{k!r}] shape: {getattr(v, 'shape', type(v))}")
                to_device_start_time = time.time()
-                inputs = {k: v.to(device) for k, v in inputs.items()}
+                # Pin CPU memory then transfer non-blocking to GPU when available
+                inputs = {
+                    k: (v.pin_memory() if (device == "cuda" and v.device.type == "cpu") else v)
+                    for k, v in inputs.items()
+                }
+                inputs = {
+                    k: v.to(device, non_blocking=(device == "cuda")) for k, v in inputs.items()
+                }
                to_device_end_time = time.time()
-                logger.info(
+                logger.debug(
                    f"To device time taken: {to_device_end_time - to_device_start_time} seconds"
                )
+                # if device == "cuda":
+                #     torch.cuda.synchronize()
                forward_start_time = time.time()
                outputs = hf_model(**inputs)
+                # if device == "cuda":
+                #     torch.cuda.synchronize()
                forward_end_time = time.time()
-                logger.info(f"Forward time taken: {forward_end_time - forward_start_time} seconds")
+                logger.debug(f"Forward time taken: {forward_end_time - forward_start_time} seconds")
                last_hidden_state = outputs.last_hidden_state  # (B, L, H)
                attention_mask = inputs.get("attention_mask")
                if attention_mask is None:
@@ -386,18 +378,27 @@ def compute_embeddings_sentence_transformers(
                    masked = last_hidden_state * mask
                    lengths = mask.sum(dim=1).clamp(min=1)
                    pooled = masked.sum(dim=1) / lengths
-                # Move to CPU float32
-                batch_embeddings = pooled.detach().to("cpu").float().numpy()
-                all_embeddings.append(batch_embeddings)
+                # Accumulate on-device; single D2H copy after loop
+                emb_list.append(pooled.detach())

-        embeddings = np.vstack(all_embeddings).astype(np.float32, copy=False)
-        try:
-            if torch.cuda.is_available():
-                torch.cuda.synchronize()
-        except Exception:
-            pass
+        # Concatenate and single-copy to CPU/NumPy
+        embeddings_tensor = torch.cat(emb_list, dim=0)
+        embeddings = embeddings_tensor.float().cpu().numpy()
+        # try:
+        #     if torch.cuda.is_available():
+        #         torch.cuda.synchronize()
+        # except Exception:
+        #     pass
        end_time = time.time()
        logger.info(f"Manual tokenize time taken: {end_time - start_time_manual} seconds")
+        time_end = time.time()
+        tokenize_time, tokenize_tpt = (
+            time_end - time_start,
+            embeddings.shape[0] / (time_end - time_start),
+        )
+        logger.info(
+            f"Tokenize time taken: {tokenize_time} seconds, tokenize tpt: {tokenize_tpt} seqs/s"
+        )
    end_time = time.time()
    logger.info(f"Generated {len(embeddings)} embeddings, dimension: {embeddings.shape[1]}")
    logger.info(f"Time taken: {end_time - start_time} seconds")
@@ -409,15 +410,12 @@ def compute_embeddings_sentence_transformers(
    return embeddings


-def compute_embeddings_openai(
-    texts: list[str],
-    model_name: str,
-    base_url: Optional[str] = None,
-    api_key: Optional[str] = None,
-) -> np.ndarray:
+def compute_embeddings_openai(texts: list[str], model_name: str) -> np.ndarray:
    # TODO: @yichuan-w add progress bar only in build mode
    """Compute embeddings using OpenAI API"""
    try:
+        import os
+
        import openai
    except ImportError as e:
        raise ImportError(f"OpenAI package not installed: {e}")
@@ -432,18 +430,16 @@ def compute_embeddings_openai(
            f"Found {invalid_count} empty/invalid text(s) in input. Upstream should filter before calling OpenAI."
        )

-    resolved_base_url = resolve_openai_base_url(base_url)
-    resolved_api_key = resolve_openai_api_key(api_key)
-
-    if not resolved_api_key:
+    api_key = os.getenv("OPENAI_API_KEY")
+    if not api_key:
        raise RuntimeError("OPENAI_API_KEY environment variable not set")

    # Cache OpenAI client
-    cache_key = f"openai_client::{resolved_base_url}"
+    cache_key = "openai_client"
    if cache_key in _model_cache:
        client = _model_cache[cache_key]
    else:
-        client = openai.OpenAI(api_key=resolved_api_key, base_url=resolved_base_url)
+        client = openai.OpenAI(api_key=api_key)
        _model_cache[cache_key] = client
        logger.info("OpenAI client cached")

@@ -568,10 +564,7 @@ def compute_embeddings_mlx(chunks: list[str], model_name: str, batch_size: int =


 def compute_embeddings_ollama(
-    texts: list[str],
-    model_name: str,
-    is_build: bool = False,
-    host: Optional[str] = None,
+    texts: list[str], model_name: str, is_build: bool = False, host: str = "http://localhost:11434"
 ) -> np.ndarray:
    """
    Compute embeddings using Ollama API with simplified batch processing.
@@ -582,7 +575,7 @@ def compute_embeddings_ollama(
        texts: List of texts to compute embeddings for
        model_name: Ollama model name (e.g., "nomic-embed-text", "mxbai-embed-large")
        is_build: Whether this is a build operation (shows progress bar)
-        host: Ollama host URL (defaults to environment or http://localhost:11434)
+        host: Ollama host URL (default: http://localhost:11434)

    Returns:
        Normalized embeddings array, shape: (len(texts), embedding_dim)
@@ -597,19 +590,17 @@ def compute_embeddings_ollama(
    if not texts:
        raise ValueError("Cannot compute embeddings for empty text list")

-    resolved_host = resolve_ollama_host(host)
-
    logger.info(
-        f"Computing embeddings for {len(texts)} texts using Ollama API, model: '{model_name}', host: '{resolved_host}'"
+        f"Computing embeddings for {len(texts)} texts using Ollama API, model: '{model_name}'"
    )

    # Check if Ollama is running
    try:
-        response = requests.get(f"{resolved_host}/api/version", timeout=5)
+        response = requests.get(f"{host}/api/version", timeout=5)
        response.raise_for_status()
    except requests.exceptions.ConnectionError:
        error_msg = (
-            f"❌ Could not connect to Ollama at {resolved_host}.\n\n"
+            f"❌ Could not connect to Ollama at {host}.\n\n"
            "Please ensure Ollama is running:\n"
            "  • macOS/Linux: ollama serve\n"
            "  • Windows: Make sure Ollama is running in the system tray\n\n"
@@ -621,7 +612,7 @@ def compute_embeddings_ollama(

    # Check if model exists and provide helpful suggestions
    try:
-        response = requests.get(f"{resolved_host}/api/tags", timeout=5)
+        response = requests.get(f"{host}/api/tags", timeout=5)
        response.raise_for_status()
        models = response.json()
        model_names = [model["name"] for model in models.get("models", [])]
@@ -684,9 +675,7 @@ def compute_embeddings_ollama(
        # Verify the model supports embeddings by testing it
        try:
            test_response = requests.post(
-                f"{resolved_host}/api/embeddings",
-                json={"model": model_name, "prompt": "test"},
-                timeout=10,
+                f"{host}/api/embeddings", json={"model": model_name, "prompt": "test"}, timeout=10
            )
            if test_response.status_code != 200:
                error_msg = (
@@ -733,7 +722,7 @@ def compute_embeddings_ollama(
            while retry_count < max_retries:
                try:
                    response = requests.post(
-                        f"{resolved_host}/api/embeddings",
+                        f"{host}/api/embeddings",
                        json={"model": model_name, "prompt": truncated_text},
                        timeout=30,
                    )
--- a/packages/leann-core/src/leann/embedding_server_manager.py
+++ b/packages/leann-core/src/leann/embedding_server_manager.py
@@ -1,5 +1,4 @@
 import atexit
-import json
 import logging
 import os
 import socket
@@ -9,8 +8,6 @@ import time
 from pathlib import Path
 from typing import Optional

-from .settings import encode_provider_options
-
 # Lightweight, self-contained server manager with no cross-process inspection

 # Set up logging based on environment variable
@@ -49,85 +46,6 @@ def _check_port(port: int) -> bool:
 # Note: All cross-process scanning helpers removed for simplicity


-def _safe_resolve(path: Path) -> str:
-    """Resolve paths safely even if the target does not yet exist."""
-    try:
-        return str(path.resolve(strict=False))
-    except Exception:
-        return str(path)
-
-
-def _safe_stat_signature(path: Path) -> dict:
-    """Return a lightweight signature describing the current state of a path."""
-    signature: dict[str, object] = {"path": _safe_resolve(path)}
-    try:
-        stat = path.stat()
-    except FileNotFoundError:
-        signature["missing"] = True
-    except Exception as exc:  # pragma: no cover - unexpected filesystem errors
-        signature["error"] = str(exc)
-    else:
-        signature["mtime_ns"] = stat.st_mtime_ns
-        signature["size"] = stat.st_size
-    return signature
-
-
-def _build_passages_signature(passages_file: Optional[str]) -> Optional[dict]:
-    """Collect modification signatures for metadata and referenced passage files."""
-    if not passages_file:
-        return None
-
-    meta_path = Path(passages_file)
-    signature: dict[str, object] = {"meta": _safe_stat_signature(meta_path)}
-
-    try:
-        with meta_path.open(encoding="utf-8") as fh:
-            meta = json.load(fh)
-    except FileNotFoundError:
-        signature["meta_missing"] = True
-        signature["sources"] = []
-        return signature
-    except json.JSONDecodeError as exc:
-        signature["meta_error"] = f"json_error:{exc}"
-        signature["sources"] = []
-        return signature
-    except Exception as exc:  # pragma: no cover - unexpected errors
-        signature["meta_error"] = str(exc)
-        signature["sources"] = []
-        return signature
-
-    base_dir = meta_path.parent
-    seen_paths: set[str] = set()
-    source_signatures: list[dict[str, object]] = []
-
-    for source in meta.get("passage_sources", []):
-        for key, kind in (
-            ("path", "passages"),
-            ("path_relative", "passages"),
-            ("index_path", "index"),
-            ("index_path_relative", "index"),
-        ):
-            raw_path = source.get(key)
-            if not raw_path:
-                continue
-            candidate = Path(raw_path)
-            if not candidate.is_absolute():
-                candidate = base_dir / candidate
-            resolved = _safe_resolve(candidate)
-            if resolved in seen_paths:
-                continue
-            seen_paths.add(resolved)
-            sig = _safe_stat_signature(candidate)
-            sig["kind"] = kind
-            source_signatures.append(sig)
-
-    signature["sources"] = source_signatures
-    return signature
-
-
-# Note: All cross-process scanning helpers removed for simplicity
-
-
 class EmbeddingServerManager:
    """
    A simplified manager for embedding server processes that avoids complex update mechanisms.
@@ -164,42 +82,16 @@ class EmbeddingServerManager:
    ) -> tuple[bool, int]:
        """Start the embedding server."""
        # passages_file may be present in kwargs for server CLI, but we don't need it here
-        provider_options = kwargs.pop("provider_options", None)
-        passages_file = kwargs.get("passages_file", "")
-
-        config_signature = self._build_config_signature(
-            model_name=model_name,
-            embedding_mode=embedding_mode,
-            provider_options=provider_options,
-            passages_file=passages_file,
-        )

        # If this manager already has a live server, just reuse it
-        if (
-            self.server_process
-            and self.server_process.poll() is None
-            and self.server_port
-            and self._server_config == config_signature
-        ):
+        if self.server_process and self.server_process.poll() is None and self.server_port:
            logger.info("Reusing in-process server")
            return True, self.server_port

-        # Configuration changed, stop existing server before starting a new one
-        if self.server_process and self.server_process.poll() is None:
-            logger.info("Existing server configuration differs; restarting embedding server")
-            self.stop_server()
-
        # For Colab environment, use a different strategy
        if _is_colab_environment():
            logger.info("Detected Colab environment, using alternative startup strategy")
-            return self._start_server_colab(
-                port,
-                model_name,
-                embedding_mode,
-                config_signature=config_signature,
-                provider_options=provider_options,
-                **kwargs,
-            )
+            return self._start_server_colab(port, model_name, embedding_mode, **kwargs)

        # Always pick a fresh available port
        try:
@@ -209,40 +101,13 @@ class EmbeddingServerManager:
            return False, port

        # Start a new server
-        return self._start_new_server(
-            actual_port,
-            model_name,
-            embedding_mode,
-            provider_options=provider_options,
-            config_signature=config_signature,
-            **kwargs,
-        )
-
-    def _build_config_signature(
-        self,
-        *,
-        model_name: str,
-        embedding_mode: str,
-        provider_options: Optional[dict],
-        passages_file: Optional[str],
-    ) -> dict:
-        """Create a signature describing the current server configuration."""
-        return {
-            "model_name": model_name,
-            "passages_file": passages_file or "",
-            "embedding_mode": embedding_mode,
-            "provider_options": provider_options or {},
-            "passages_signature": _build_passages_signature(passages_file),
-        }
+        return self._start_new_server(actual_port, model_name, embedding_mode, **kwargs)

    def _start_server_colab(
        self,
        port: int,
        model_name: str,
        embedding_mode: str = "sentence-transformers",
-        *,
-        config_signature: Optional[dict] = None,
-        provider_options: Optional[dict] = None,
        **kwargs,
    ) -> tuple[bool, int]:
        """Start server with Colab-specific configuration."""
@@ -260,21 +125,8 @@ class EmbeddingServerManager:

        try:
            # In Colab, we'll use a more direct approach
-            self._launch_server_process_colab(
-                command,
-                actual_port,
-                provider_options=provider_options,
-                config_signature=config_signature,
-            )
-            started, ready_port = self._wait_for_server_ready_colab(actual_port)
-            if started:
-                self._server_config = config_signature or {
-                    "model_name": model_name,
-                    "passages_file": kwargs.get("passages_file", ""),
-                    "embedding_mode": embedding_mode,
-                    "provider_options": provider_options or {},
-                }
-            return started, ready_port
+            self._launch_server_process_colab(command, actual_port)
+            return self._wait_for_server_ready_colab(actual_port)
        except Exception as e:
            logger.error(f"Failed to start embedding server in Colab: {e}")
            return False, actual_port
@@ -282,13 +134,7 @@ class EmbeddingServerManager:
    # Note: No compatibility check needed; manager is per-searcher and configs are stable per instance

    def _start_new_server(
-        self,
-        port: int,
-        model_name: str,
-        embedding_mode: str,
-        provider_options: Optional[dict] = None,
-        config_signature: Optional[dict] = None,
-        **kwargs,
+        self, port: int, model_name: str, embedding_mode: str, **kwargs
    ) -> tuple[bool, int]:
        """Start a new embedding server on the given port."""
        logger.info(f"Starting embedding server on port {port}...")
@@ -296,21 +142,8 @@ class EmbeddingServerManager:
        command = self._build_server_command(port, model_name, embedding_mode, **kwargs)

        try:
-            self._launch_server_process(
-                command,
-                port,
-                provider_options=provider_options,
-                config_signature=config_signature,
-            )
-            started, ready_port = self._wait_for_server_ready(port)
-            if started:
-                self._server_config = config_signature or {
-                    "model_name": model_name,
-                    "passages_file": kwargs.get("passages_file", ""),
-                    "embedding_mode": embedding_mode,
-                    "provider_options": provider_options or {},
-                }
-            return started, ready_port
+            self._launch_server_process(command, port)
+            return self._wait_for_server_ready(port)
        except Exception as e:
            logger.error(f"Failed to start embedding server: {e}")
            return False, port
@@ -340,14 +173,7 @@ class EmbeddingServerManager:

        return command

-    def _launch_server_process(
-        self,
-        command: list,
-        port: int,
-        *,
-        provider_options: Optional[dict] = None,
-        config_signature: Optional[dict] = None,
-    ) -> None:
+    def _launch_server_process(self, command: list, port: int) -> None:
        """Launch the server process."""
        project_root = Path(__file__).parent.parent.parent.parent.parent
        logger.info(f"Command: {' '.join(command)}")
@@ -367,43 +193,32 @@ class EmbeddingServerManager:

        # Start embedding server subprocess
        logger.info(f"Starting server process with command: {' '.join(command)}")
-        env = os.environ.copy()
-        encoded_options = encode_provider_options(provider_options)
-        if encoded_options:
-            env["LEANN_EMBEDDING_OPTIONS"] = encoded_options
-
        self.server_process = subprocess.Popen(
            command,
            cwd=project_root,
            stdout=stdout_target,
            stderr=stderr_target,
-            env=env,
        )
        self.server_port = port
-        # Record config for in-process reuse (best effort; refined later when ready)
-        if config_signature is not None:
-            self._server_config = config_signature
-        else:  # Fallback for unexpected code paths
-            try:
-                self._server_config = {
-                    "model_name": command[command.index("--model-name") + 1]
-                    if "--model-name" in command
-                    else "",
-                    "passages_file": command[command.index("--passages-file") + 1]
-                    if "--passages-file" in command
-                    else "",
-                    "embedding_mode": command[command.index("--embedding-mode") + 1]
-                    if "--embedding-mode" in command
-                    else "sentence-transformers",
-                    "provider_options": provider_options or {},
-                }
-            except Exception:
-                self._server_config = {
-                    "model_name": "",
-                    "passages_file": "",
-                    "embedding_mode": "sentence-transformers",
-                    "provider_options": provider_options or {},
-                }
+        # Record config for in-process reuse
+        try:
+            self._server_config = {
+                "model_name": command[command.index("--model-name") + 1]
+                if "--model-name" in command
+                else "",
+                "passages_file": command[command.index("--passages-file") + 1]
+                if "--passages-file" in command
+                else "",
+                "embedding_mode": command[command.index("--embedding-mode") + 1]
+                if "--embedding-mode" in command
+                else "sentence-transformers",
+            }
+        except Exception:
+            self._server_config = {
+                "model_name": "",
+                "passages_file": "",
+                "embedding_mode": "sentence-transformers",
+            }
        logger.info(f"Server process started with PID: {self.server_process.pid}")

        # Register atexit callback only when we actually start a process
@@ -507,29 +322,16 @@ class EmbeddingServerManager:
        # Removed: cross-process adoption no longer supported
        return

-    def _launch_server_process_colab(
-        self,
-        command: list,
-        port: int,
-        *,
-        provider_options: Optional[dict] = None,
-        config_signature: Optional[dict] = None,
-    ) -> None:
+    def _launch_server_process_colab(self, command: list, port: int) -> None:
        """Launch the server process with Colab-specific settings."""
        logger.info(f"Colab Command: {' '.join(command)}")

        # In Colab, we need to be more careful about process management
-        env = os.environ.copy()
-        encoded_options = encode_provider_options(provider_options)
-        if encoded_options:
-            env["LEANN_EMBEDDING_OPTIONS"] = encoded_options
-
        self.server_process = subprocess.Popen(
            command,
            stdout=subprocess.PIPE,
            stderr=subprocess.PIPE,
            text=True,
-            env=env,
        )
        self.server_port = port
        logger.info(f"Colab server process started with PID: {self.server_process.pid}")
@@ -539,15 +341,11 @@ class EmbeddingServerManager:
            atexit.register(self._finalize_process)
            self._atexit_registered = True
        # Record config for in-process reuse is best-effort in Colab mode
-        if config_signature is not None:
-            self._server_config = config_signature
-        else:
-            self._server_config = {
-                "model_name": "",
-                "passages_file": "",
-                "embedding_mode": "sentence-transformers",
-                "provider_options": provider_options or {},
-            }
+        self._server_config = {
+            "model_name": "",
+            "passages_file": "",
+            "embedding_mode": "sentence-transformers",
+        }

    def _wait_for_server_ready_colab(self, port: int) -> tuple[bool, int]:
        """Wait for the server to be ready with Colab-specific timeout."""
--- a/packages/leann-core/src/leann/searcher_base.py
+++ b/packages/leann-core/src/leann/searcher_base.py
@@ -41,7 +41,6 @@ class BaseSearcher(LeannBackendSearcherInterface, ABC):
            print("WARNING: embedding_model not found in meta.json. Recompute will fail.")

        self.embedding_mode = self.meta.get("embedding_mode", "sentence-transformers")
-        self.embedding_options = self.meta.get("embedding_options", {})

        self.embedding_server_manager = EmbeddingServerManager(
            backend_module_name=backend_module_name,
@@ -78,7 +77,6 @@ class BaseSearcher(LeannBackendSearcherInterface, ABC):
            passages_file=passages_source_file,
            distance_metric=distance_metric,
            enable_warmup=kwargs.get("enable_warmup", False),
-            provider_options=self.embedding_options,
        )
        if not server_started:
            raise RuntimeError(f"Failed to start embedding server on port {actual_port}")
@@ -127,12 +125,7 @@ class BaseSearcher(LeannBackendSearcherInterface, ABC):
        from .embedding_compute import compute_embeddings

        embedding_mode = self.meta.get("embedding_mode", "sentence-transformers")
-        return compute_embeddings(
-            [query],
-            self.embedding_model,
-            embedding_mode,
-            provider_options=self.embedding_options,
-        )
+        return compute_embeddings([query], self.embedding_model, embedding_mode)

    def _compute_embedding_via_server(self, chunks: list, zmq_port: int) -> np.ndarray:
        """Compute embeddings using the ZMQ embedding server."""
--- a/packages/leann-core/src/leann/settings.py
+++ b/packages/leann-core/src/leann/settings.py
@@ -1,74 +0,0 @@
-"""Runtime configuration helpers for LEANN."""
-
-from __future__ import annotations
-
-import json
-import os
-from typing import Any
-
-# Default fallbacks to preserve current behaviour while keeping them in one place.
-_DEFAULT_OLLAMA_HOST = "http://localhost:11434"
-_DEFAULT_OPENAI_BASE_URL = "https://api.openai.com/v1"
-
-
-def _clean_url(value: str) -> str:
-    """Normalize URL strings by stripping trailing slashes."""
-
-    return value.rstrip("/") if value else value
-
-
-def resolve_ollama_host(explicit: str | None = None) -> str:
-    """Resolve the Ollama-compatible endpoint to use."""
-
-    candidates = (
-        explicit,
-        os.getenv("LEANN_LOCAL_LLM_HOST"),
-        os.getenv("LEANN_OLLAMA_HOST"),
-        os.getenv("OLLAMA_HOST"),
-        os.getenv("LOCAL_LLM_ENDPOINT"),
-    )
-
-    for candidate in candidates:
-        if candidate:
-            return _clean_url(candidate)
-
-    return _clean_url(_DEFAULT_OLLAMA_HOST)
-
-
-def resolve_openai_base_url(explicit: str | None = None) -> str:
-    """Resolve the base URL for OpenAI-compatible services."""
-
-    candidates = (
-        explicit,
-        os.getenv("LEANN_OPENAI_BASE_URL"),
-        os.getenv("OPENAI_BASE_URL"),
-        os.getenv("LOCAL_OPENAI_BASE_URL"),
-    )
-
-    for candidate in candidates:
-        if candidate:
-            return _clean_url(candidate)
-
-    return _clean_url(_DEFAULT_OPENAI_BASE_URL)
-
-
-def resolve_openai_api_key(explicit: str | None = None) -> str | None:
-    """Resolve the API key for OpenAI-compatible services."""
-
-    if explicit:
-        return explicit
-
-    return os.getenv("OPENAI_API_KEY")
-
-
-def encode_provider_options(options: dict[str, Any] | None) -> str | None:
-    """Serialize provider options for child processes."""
-
-    if not options:
-        return None
-
-    try:
-        return json.dumps(options)
-    except (TypeError, ValueError):
-        # Fall back to empty payload if serialization fails
-        return None
--- a/packages/leann-mcp/README.md
+++ b/packages/leann-mcp/README.md
@@ -2,8 +2,6 @@

 Transform your development workflow with intelligent code assistance using LEANN's semantic search directly in Claude Code.

-For agent-facing discovery details, see `llms.txt` in the repository root.
-
 ## Prerequisites

 Install LEANN globally for MCP integration (with default backend):
--- a/packages/leann/pyproject.toml
+++ b/packages/leann/pyproject.toml
@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"

 [project]
 name = "leann"
-version = "0.3.4"
+version = "0.3.2"
 description = "LEANN - The smallest vector index in the world. RAG Everything with LEANN!"
 readme = "README.md"
 requires-python = ">=3.9"
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -53,10 +53,27 @@ dependencies = [
    "tree-sitter-java>=0.20.0",
    "tree-sitter-c-sharp>=0.20.0",
    "tree-sitter-typescript>=0.20.0",
-    "torchvision>=0.23.0",
 ]

 [project.optional-dependencies]
+dev = [
+    "pytest>=7.0",
+    "pytest-cov>=4.0",
+    "pytest-xdist>=3.0",  # For parallel test execution
+    "black>=23.0",
+    "ruff==0.12.7",  # Fixed version to ensure consistent formatting across all environments
+    "matplotlib",
+    "huggingface-hub>=0.20.0",
+    "pre-commit>=3.5.0",
+]
+
+test = [
+    "pytest>=7.0",
+    "pytest-timeout>=2.0",
+    "llama-index-core>=0.12.0",
+    "python-dotenv>=1.0.0",
+]
+
 diskann = [
    "leann-backend-diskann",
 ]
@@ -82,38 +99,11 @@ wechat-exporter = "wechat_exporter.main:main"
 leann-core = { path = "packages/leann-core", editable = true }
 leann-backend-diskann = { path = "packages/leann-backend-diskann", editable = true }
 leann-backend-hnsw = { path = "packages/leann-backend-hnsw", editable = true }
-astchunk = { path = "packages/astchunk-leann", editable = true }
-
-[dependency-groups]
-# Minimal lint toolchain for CI and local hooks
-lint = [
-    "pre-commit>=3.5.0",
-    "ruff==0.12.7",  # Fixed version to ensure consistent formatting across all environments
-]
-
-# Test toolchain (no heavy project runtime deps)
-test = [
-    "pytest>=7.0",
-    "pytest-cov>=4.0",
-    "pytest-xdist>=3.0",
-    "pytest-timeout>=2.0",
-    "python-dotenv>=1.0.0",
-]
-
-# dependencies by apps/ should list here
-dev = [
-    "matplotlib",
-    "huggingface-hub>=0.20.0",
-]

 [tool.ruff]
 target-version = "py39"
 line-length = 100
-extend-exclude = [
-    "third_party",
-    "apps/multimodal/vision-based-pdf-multi-vector/multi-vector-leann-paper-example.py",
-    "apps/multimodal/vision-based-pdf-multi-vector/multi-vector-leann-similarity-map.py"
-]
+extend-exclude = ["third_party"]


 [tool.ruff.lint]
--- a/run_eval_search_only2.logsource
+++ b/run_eval_search_only2.logsource
--- a/scripts/hf_upload.py
+++ b/scripts/hf_upload.py
@@ -1,121 +0,0 @@
-#!/usr/bin/env python3
-"""
-Upload local evaluation data to Hugging Face Hub, excluding diskann_rpj_wiki.
-
-Defaults:
- repo_id: LEANN-RAG/leann-rag-evaluation-data (dataset)
- folder_path: benchmarks/data
- ignore_patterns: diskann_rpj_wiki/** and .cache/**
-
-Requires authentication via `huggingface-cli login` or HF_TOKEN env var.
-"""
-
-from __future__ import annotations
-
-import argparse
-import os
-
-try:
-    from huggingface_hub import HfApi
-except Exception as e:
-    raise SystemExit(
-        "huggingface_hub is required. Install with: pip install huggingface_hub hf_transfer"
-    ) from e
-
-
-def _enable_transfer_accel_if_available() -> None:
-    """Best-effort enabling of accelerated transfers across hub versions.
-
-    Tries the public util if present; otherwise, falls back to env flag when
-    hf_transfer is installed. Silently no-ops if unavailable.
-    """
-    try:
-        # Newer huggingface_hub exposes this under utils
-        from huggingface_hub.utils import hf_hub_enable_hf_transfer  # type: ignore
-
-        hf_hub_enable_hf_transfer()
-        return
-    except Exception:
-        pass
-
-    try:
-        # If hf_transfer is installed, set env flag recognized by the hub
-        import hf_transfer  # noqa: F401
-
-        os.environ.setdefault("HF_HUB_ENABLE_HF_TRANSFER", "1")
-    except Exception:
-        # Acceleration not available; proceed without it
-        pass
-
-
-def parse_args() -> argparse.Namespace:
-    p = argparse.ArgumentParser(description="Upload local data to HF, excluding diskann_rpj_wiki")
-    p.add_argument(
-        "--repo-id",
-        default="LEANN-RAG/leann-rag-evaluation-data",
-        help="Target dataset repo id (namespace/name)",
-    )
-    p.add_argument(
-        "--folder-path",
-        default="benchmarks/data",
-        help="Local folder to upload (default: benchmarks/data)",
-    )
-    p.add_argument(
-        "--ignore",
-        default=["diskann_rpj_wiki/**", ".cache/**"],
-        nargs="+",
-        help="Glob patterns to ignore (space-separated)",
-    )
-    p.add_argument(
-        "--allow",
-        default=["**"],
-        nargs="+",
-        help="Glob patterns to allow (space-separated). Defaults to everything.",
-    )
-    p.add_argument(
-        "--message",
-        default="sync local data (exclude diskann_rpj_wiki)",
-        help="Commit message",
-    )
-    p.add_argument(
-        "--no-transfer-accel",
-        action="store_true",
-        help="Disable hf_transfer accelerated uploads",
-    )
-    return p.parse_args()
-
-
-def main() -> None:
-    args = parse_args()
-
-    if not args.no_transfer_accel:
-        _enable_transfer_accel_if_available()
-
-    if not os.path.isdir(args.folder_path):
-        raise SystemExit(f"Folder not found: {args.folder_path}")
-
-    print("Uploading to Hugging Face Hub:")
-    print(f"  repo_id:        {args.repo_id}")
-    print("  repo_type:      dataset")
-    print(f"  folder_path:    {args.folder_path}")
-    print(f"  allow_patterns: {args.allow}")
-    print(f"  ignore_patterns:{args.ignore}")
-
-    api = HfApi()
-
-    # Perform upload. This skips unchanged files by content hash.
-    api.upload_folder(
-        repo_id=args.repo_id,
-        repo_type="dataset",
-        folder_path=args.folder_path,
-        path_in_repo=".",
-        allow_patterns=args.allow,
-        ignore_patterns=args.ignore,
-        commit_message=args.message,
-    )
-
-    print("Upload completed (unchanged files were skipped by the Hub).")
-
-
-if __name__ == "__main__":
-    main()
--- a/tests/README.md
+++ b/tests/README.md
@@ -40,8 +40,8 @@ Tests DiskANN graph partitioning functionality:

 ### Install test dependencies:
 ```bash
-# Using uv dependency groups (tools only)
-uv sync --only-group test
+# Using extras
+uv pip install -e ".[test]"
 ```

 ### Run all tests:
--- a/tests/test_cli_ask.py
+++ b/tests/test_cli_ask.py
@@ -1,14 +0,0 @@
-from leann.cli import LeannCLI
-
-
-def test_cli_ask_accepts_positional_query(tmp_path, monkeypatch):
-    monkeypatch.chdir(tmp_path)
-
-    cli = LeannCLI()
-    parser = cli.create_parser()
-
-    args = parser.parse_args(["ask", "my-docs", "Where are prompts configured?"])
-
-    assert args.command == "ask"
-    assert args.index_name == "my-docs"
-    assert args.query == "Where are prompts configured?"
--- a/tests/test_embedding_server_manager.py
+++ b/tests/test_embedding_server_manager.py
@@ -1,137 +0,0 @@
-import json
-import time
-
-import pytest
-from leann.embedding_server_manager import EmbeddingServerManager
-
-
-class DummyProcess:
-    def __init__(self):
-        self.pid = 12345
-        self._terminated = False
-
-    def poll(self):
-        return 0 if self._terminated else None
-
-    def terminate(self):
-        self._terminated = True
-
-    def kill(self):
-        self._terminated = True
-
-    def wait(self, timeout=None):
-        self._terminated = True
-        return 0
-
-
-@pytest.fixture
-def embedding_manager(monkeypatch):
-    manager = EmbeddingServerManager("leann_backend_hnsw.hnsw_embedding_server")
-
-    def fake_get_available_port(start_port):
-        return start_port
-
-    monkeypatch.setattr(
-        "leann.embedding_server_manager._get_available_port",
-        fake_get_available_port,
-    )
-
-    start_calls = []
-
-    def fake_start_new_server(self, port, model_name, embedding_mode, **kwargs):
-        config_signature = kwargs.get("config_signature")
-        start_calls.append(config_signature)
-        self.server_process = DummyProcess()
-        self.server_port = port
-        self._server_config = config_signature
-        return True, port
-
-    monkeypatch.setattr(
-        EmbeddingServerManager,
-        "_start_new_server",
-        fake_start_new_server,
-    )
-
-    # Ensure stop_server doesn't try to operate on real subprocesses
-    def fake_stop_server(self):
-        self.server_process = None
-        self.server_port = None
-        self._server_config = None
-
-    monkeypatch.setattr(EmbeddingServerManager, "stop_server", fake_stop_server)
-
-    return manager, start_calls
-
-
-def _write_meta(meta_path, passages_name, index_name, total):
-    meta_path.write_text(
-        json.dumps(
-            {
-                "backend_name": "hnsw",
-                "embedding_model": "test-model",
-                "embedding_mode": "sentence-transformers",
-                "dimensions": 3,
-                "backend_kwargs": {},
-                "passage_sources": [
-                    {
-                        "type": "jsonl",
-                        "path": passages_name,
-                        "index_path": index_name,
-                    }
-                ],
-                "total_passages": total,
-            }
-        ),
-        encoding="utf-8",
-    )
-
-
-def test_server_restarts_when_metadata_changes(tmp_path, embedding_manager):
-    manager, start_calls = embedding_manager
-
-    meta_path = tmp_path / "example.meta.json"
-    passages_path = tmp_path / "example.passages.jsonl"
-    index_path = tmp_path / "example.passages.idx"
-
-    passages_path.write_text("first\n", encoding="utf-8")
-    index_path.write_bytes(b"index")
-    _write_meta(meta_path, passages_path.name, index_path.name, total=1)
-
-    # Initial start populates signature
-    ok, port = manager.start_server(
-        port=6000,
-        model_name="test-model",
-        passages_file=str(meta_path),
-    )
-    assert ok
-    assert port == 6000
-    assert len(start_calls) == 1
-
-    initial_signature = start_calls[0]["passages_signature"]
-
-    # No metadata change => reuse existing server
-    ok, port_again = manager.start_server(
-        port=6000,
-        model_name="test-model",
-        passages_file=str(meta_path),
-    )
-    assert ok
-    assert port_again == 6000
-    assert len(start_calls) == 1
-
-    # Modify passage data and metadata to force signature change
-    time.sleep(0.01)  # Ensure filesystem timestamps move forward
-    passages_path.write_text("second\n", encoding="utf-8")
-    _write_meta(meta_path, passages_path.name, index_path.name, total=2)
-
-    ok, port_third = manager.start_server(
-        port=6000,
-        model_name="test-model",
-        passages_file=str(meta_path),
-    )
-    assert ok
-    assert port_third == 6000
-    assert len(start_calls) == 2
-
-    updated_signature = start_calls[1]["passages_signature"]
-    assert updated_signature != initial_signature
--- a/tests/test_mcp_integration.py
+++ b/tests/test_mcp_integration.py
@@ -1,208 +0,0 @@
-#!/usr/bin/env python3
-"""
-Test script for MCP integration implementations.
-
-This script tests the basic functionality of the MCP readers and RAG applications
-without requiring actual MCP servers to be running.
-"""
-
-import sys
-from pathlib import Path
-
-# Add the parent directory to the path so we can import from apps
-sys.path.append(str(Path(__file__).parent.parent))
-
-from apps.slack_data.slack_mcp_reader import SlackMCPReader
-from apps.slack_rag import SlackMCPRAG
-from apps.twitter_data.twitter_mcp_reader import TwitterMCPReader
-from apps.twitter_rag import TwitterMCPRAG
-
-
-def test_slack_reader_initialization():
-    """Test that SlackMCPReader can be initialized with various parameters."""
-    print("Testing SlackMCPReader initialization...")
-
-    # Test basic initialization
-    reader = SlackMCPReader("slack-mcp-server")
-    assert reader.mcp_server_command == "slack-mcp-server"
-    assert reader.concatenate_conversations
-    assert reader.max_messages_per_conversation == 100
-
-    # Test with custom parameters
-    reader = SlackMCPReader(
-        "custom-slack-server",
-        workspace_name="test-workspace",
-        concatenate_conversations=False,
-        max_messages_per_conversation=50,
-    )
-    assert reader.workspace_name == "test-workspace"
-    assert not reader.concatenate_conversations
-    assert reader.max_messages_per_conversation == 50
-
-    print("✅ SlackMCPReader initialization tests passed")
-
-
-def test_twitter_reader_initialization():
-    """Test that TwitterMCPReader can be initialized with various parameters."""
-    print("Testing TwitterMCPReader initialization...")
-
-    # Test basic initialization
-    reader = TwitterMCPReader("twitter-mcp-server")
-    assert reader.mcp_server_command == "twitter-mcp-server"
-    assert reader.include_tweet_content
-    assert reader.include_metadata
-    assert reader.max_bookmarks == 1000
-
-    # Test with custom parameters
-    reader = TwitterMCPReader(
-        "custom-twitter-server",
-        username="testuser",
-        include_tweet_content=False,
-        include_metadata=False,
-        max_bookmarks=500,
-    )
-    assert reader.username == "testuser"
-    assert not reader.include_tweet_content
-    assert not reader.include_metadata
-    assert reader.max_bookmarks == 500
-
-    print("✅ TwitterMCPReader initialization tests passed")
-
-
-def test_slack_message_formatting():
-    """Test Slack message formatting functionality."""
-    print("Testing Slack message formatting...")
-
-    reader = SlackMCPReader("slack-mcp-server")
-
-    # Test basic message formatting
-    message = {
-        "text": "Hello, world!",
-        "user": "john_doe",
-        "channel": "general",
-        "ts": "1234567890.123456",
-    }
-
-    formatted = reader._format_message(message)
-    assert "Channel: #general" in formatted
-    assert "User: john_doe" in formatted
-    assert "Message: Hello, world!" in formatted
-    assert "Time:" in formatted
-
-    # Test with missing fields
-    message = {"text": "Simple message"}
-    formatted = reader._format_message(message)
-    assert "Message: Simple message" in formatted
-
-    print("✅ Slack message formatting tests passed")
-
-
-def test_twitter_bookmark_formatting():
-    """Test Twitter bookmark formatting functionality."""
-    print("Testing Twitter bookmark formatting...")
-
-    reader = TwitterMCPReader("twitter-mcp-server")
-
-    # Test basic bookmark formatting
-    bookmark = {
-        "text": "This is a great article about AI!",
-        "author": "ai_researcher",
-        "created_at": "2024-01-01T12:00:00Z",
-        "url": "https://twitter.com/ai_researcher/status/123456789",
-        "likes": 42,
-        "retweets": 15,
-    }
-
-    formatted = reader._format_bookmark(bookmark)
-    assert "=== Twitter Bookmark ===" in formatted
-    assert "Author: @ai_researcher" in formatted
-    assert "Content:" in formatted
-    assert "This is a great article about AI!" in formatted
-    assert "URL: https://twitter.com" in formatted
-    assert "Likes: 42" in formatted
-    assert "Retweets: 15" in formatted
-
-    # Test with minimal data
-    bookmark = {"text": "Simple tweet"}
-    formatted = reader._format_bookmark(bookmark)
-    assert "=== Twitter Bookmark ===" in formatted
-    assert "Simple tweet" in formatted
-
-    print("✅ Twitter bookmark formatting tests passed")
-
-
-def test_slack_rag_initialization():
-    """Test that SlackMCPRAG can be initialized."""
-    print("Testing SlackMCPRAG initialization...")
-
-    app = SlackMCPRAG()
-    assert app.default_index_name == "slack_messages"
-    assert hasattr(app, "parser")
-
-    print("✅ SlackMCPRAG initialization tests passed")
-
-
-def test_twitter_rag_initialization():
-    """Test that TwitterMCPRAG can be initialized."""
-    print("Testing TwitterMCPRAG initialization...")
-
-    app = TwitterMCPRAG()
-    assert app.default_index_name == "twitter_bookmarks"
-    assert hasattr(app, "parser")
-
-    print("✅ TwitterMCPRAG initialization tests passed")
-
-
-def test_concatenated_content_creation():
-    """Test creation of concatenated content from multiple messages."""
-    print("Testing concatenated content creation...")
-
-    reader = SlackMCPReader("slack-mcp-server", workspace_name="test-workspace")
-
-    messages = [
-        {"text": "First message", "user": "alice", "ts": "1000"},
-        {"text": "Second message", "user": "bob", "ts": "2000"},
-        {"text": "Third message", "user": "charlie", "ts": "3000"},
-    ]
-
-    content = reader._create_concatenated_content(messages, "general")
-
-    assert "Slack Channel: #general" in content
-    assert "Message Count: 3" in content
-    assert "Workspace: test-workspace" in content
-    assert "First message" in content
-    assert "Second message" in content
-    assert "Third message" in content
-
-    print("✅ Concatenated content creation tests passed")
-
-
-def main():
-    """Run all tests."""
-    print("🧪 Running MCP Integration Tests")
-    print("=" * 50)
-
-    try:
-        test_slack_reader_initialization()
-        test_twitter_reader_initialization()
-        test_slack_message_formatting()
-        test_twitter_bookmark_formatting()
-        test_slack_rag_initialization()
-        test_twitter_rag_initialization()
-        test_concatenated_content_creation()
-
-        print("\n" + "=" * 50)
-        print("🎉 All tests passed! MCP integration is working correctly.")
-        print("\nNext steps:")
-        print("1. Install actual MCP servers for Slack and Twitter")
-        print("2. Configure API credentials")
-        print("3. Test with --test-connection flag")
-        print("4. Start indexing your live data!")
-
-    except Exception as e:
-        print(f"\n❌ Test failed: {e}")
-        sys.exit(1)
-
-
-if __name__ == "__main__":
-    main()
--- a/tests/test_mcp_standalone.py
+++ b/tests/test_mcp_standalone.py
@@ -1,221 +0,0 @@
-#!/usr/bin/env python3
-"""
-Standalone test script for MCP integration implementations.
-
-This script tests the basic functionality of the MCP readers
-without requiring LEANN core dependencies.
-"""
-
-import json
-import sys
-from pathlib import Path
-
-# Add the parent directory to the path so we can import from apps
-sys.path.append(str(Path(__file__).parent.parent))
-
-
-def test_slack_reader_basic():
-    """Test basic SlackMCPReader functionality without async operations."""
-    print("Testing SlackMCPReader basic functionality...")
-
-    # Import and test initialization
-    from apps.slack_data.slack_mcp_reader import SlackMCPReader
-
-    reader = SlackMCPReader("slack-mcp-server")
-    assert reader.mcp_server_command == "slack-mcp-server"
-    assert reader.concatenate_conversations
-
-    # Test message formatting
-    message = {
-        "text": "Hello team! How's the project going?",
-        "user": "john_doe",
-        "channel": "general",
-        "ts": "1234567890.123456",
-    }
-
-    formatted = reader._format_message(message)
-    assert "Channel: #general" in formatted
-    assert "User: john_doe" in formatted
-    assert "Message: Hello team!" in formatted
-
-    # Test concatenated content creation
-    messages = [
-        {"text": "First message", "user": "alice", "ts": "1000"},
-        {"text": "Second message", "user": "bob", "ts": "2000"},
-    ]
-
-    content = reader._create_concatenated_content(messages, "dev-team")
-    assert "Slack Channel: #dev-team" in content
-    assert "Message Count: 2" in content
-    assert "First message" in content
-    assert "Second message" in content
-
-    print("✅ SlackMCPReader basic tests passed")
-
-
-def test_twitter_reader_basic():
-    """Test basic TwitterMCPReader functionality."""
-    print("Testing TwitterMCPReader basic functionality...")
-
-    from apps.twitter_data.twitter_mcp_reader import TwitterMCPReader
-
-    reader = TwitterMCPReader("twitter-mcp-server")
-    assert reader.mcp_server_command == "twitter-mcp-server"
-    assert reader.include_tweet_content
-    assert reader.max_bookmarks == 1000
-
-    # Test bookmark formatting
-    bookmark = {
-        "text": "Amazing article about the future of AI! Must read for everyone interested in tech.",
-        "author": "tech_guru",
-        "created_at": "2024-01-15T14:30:00Z",
-        "url": "https://twitter.com/tech_guru/status/123456789",
-        "likes": 156,
-        "retweets": 42,
-        "replies": 23,
-        "hashtags": ["AI", "tech", "future"],
-        "mentions": ["@openai", "@anthropic"],
-    }
-
-    formatted = reader._format_bookmark(bookmark)
-    assert "=== Twitter Bookmark ===" in formatted
-    assert "Author: @tech_guru" in formatted
-    assert "Amazing article about the future of AI!" in formatted
-    assert "Likes: 156" in formatted
-    assert "Retweets: 42" in formatted
-    assert "Hashtags: AI, tech, future" in formatted
-    assert "Mentions: @openai, @anthropic" in formatted
-
-    # Test with minimal data
-    simple_bookmark = {"text": "Short tweet", "author": "user123"}
-    formatted_simple = reader._format_bookmark(simple_bookmark)
-    assert "=== Twitter Bookmark ===" in formatted_simple
-    assert "Short tweet" in formatted_simple
-    assert "Author: @user123" in formatted_simple
-
-    print("✅ TwitterMCPReader basic tests passed")
-
-
-def test_mcp_request_format():
-    """Test MCP request formatting."""
-    print("Testing MCP request formatting...")
-
-    # Test initialization request format
-    init_request = {
-        "jsonrpc": "2.0",
-        "id": 1,
-        "method": "initialize",
-        "params": {
-            "protocolVersion": "2024-11-05",
-            "capabilities": {},
-            "clientInfo": {"name": "leann-slack-reader", "version": "1.0.0"},
-        },
-    }
-
-    # Verify it's valid JSON
-    json_str = json.dumps(init_request)
-    parsed = json.loads(json_str)
-    assert parsed["jsonrpc"] == "2.0"
-    assert parsed["method"] == "initialize"
-    assert parsed["params"]["protocolVersion"] == "2024-11-05"
-
-    # Test tools/list request
-    list_request = {"jsonrpc": "2.0", "id": 2, "method": "tools/list", "params": {}}
-
-    json_str = json.dumps(list_request)
-    parsed = json.loads(json_str)
-    assert parsed["method"] == "tools/list"
-
-    print("✅ MCP request formatting tests passed")
-
-
-def test_data_processing():
-    """Test data processing capabilities."""
-    print("Testing data processing capabilities...")
-
-    from apps.slack_data.slack_mcp_reader import SlackMCPReader
-    from apps.twitter_data.twitter_mcp_reader import TwitterMCPReader
-
-    # Test Slack message processing with various formats
-    slack_reader = SlackMCPReader("test-server")
-
-    messages_with_timestamps = [
-        {"text": "Meeting in 5 minutes", "user": "alice", "ts": "1000.123"},
-        {"text": "On my way!", "user": "bob", "ts": "1001.456"},
-        {"text": "Starting now", "user": "charlie", "ts": "1002.789"},
-    ]
-
-    content = slack_reader._create_concatenated_content(messages_with_timestamps, "meetings")
-    assert "Meeting in 5 minutes" in content
-    assert "On my way!" in content
-    assert "Starting now" in content
-
-    # Test Twitter bookmark processing with engagement data
-    twitter_reader = TwitterMCPReader("test-server", include_metadata=True)
-
-    high_engagement_bookmark = {
-        "text": "Thread about startup lessons learned 🧵",
-        "author": "startup_founder",
-        "likes": 1250,
-        "retweets": 340,
-        "replies": 89,
-    }
-
-    formatted = twitter_reader._format_bookmark(high_engagement_bookmark)
-    assert "Thread about startup lessons learned" in formatted
-    assert "Likes: 1250" in formatted
-    assert "Retweets: 340" in formatted
-    assert "Replies: 89" in formatted
-
-    # Test with metadata disabled
-    twitter_reader_no_meta = TwitterMCPReader("test-server", include_metadata=False)
-    formatted_no_meta = twitter_reader_no_meta._format_bookmark(high_engagement_bookmark)
-    assert "Thread about startup lessons learned" in formatted_no_meta
-    assert "Likes:" not in formatted_no_meta
-    assert "Retweets:" not in formatted_no_meta
-
-    print("✅ Data processing tests passed")
-
-
-def main():
-    """Run all standalone tests."""
-    print("🧪 Running MCP Integration Standalone Tests")
-    print("=" * 60)
-    print("Testing core functionality without LEANN dependencies...")
-    print()
-
-    try:
-        test_slack_reader_basic()
-        test_twitter_reader_basic()
-        test_mcp_request_format()
-        test_data_processing()
-
-        print("\n" + "=" * 60)
-        print("🎉 All standalone tests passed!")
-        print("\n✨ MCP Integration Summary:")
-        print("- SlackMCPReader: Ready for Slack message processing")
-        print("- TwitterMCPReader: Ready for Twitter bookmark processing")
-        print("- MCP Protocol: Properly formatted JSON-RPC requests")
-        print("- Data Processing: Handles various message/bookmark formats")
-
-        print("\n🚀 Next Steps:")
-        print("1. Install MCP servers: npm install -g slack-mcp-server twitter-mcp-server")
-        print("2. Configure API credentials for Slack and Twitter")
-        print("3. Test connections: python -m apps.slack_rag --test-connection")
-        print("4. Start indexing live data from your platforms!")
-
-        print("\n📖 Documentation:")
-        print("- Check README.md for detailed setup instructions")
-        print("- Run examples/mcp_integration_demo.py for usage examples")
-        print("- Explore apps/slack_rag.py and apps/twitter_rag.py for implementation details")
-
-    except Exception as e:
-        print(f"\n❌ Test failed: {e}")
-        import traceback
-
-        traceback.print_exc()
-        sys.exit(1)
-
-
-if __name__ == "__main__":
-    main()
--- a/uv.lock
+++ b/uv.lock