chore: release v0.1.15

* fix: auto-detect normalized embeddings and use cosine distance

- Add automatic detection for normalized embedding models (OpenAI, Voyage AI, Cohere)
- Automatically set distance_metric='cosine' for normalized embeddings
- Add warnings when using non-optimal distance metrics
- Implement manual L2 normalization in HNSW backend (custom Faiss build lacks normalize_L2)
- Fix DiskANN zmq_port compatibility with lazy loading strategy
- Add documentation for normalized embeddings feature

This fixes the low accuracy issue when using OpenAI text-embedding-3-small model with default MIPS metric.

* style: format

.github/workflows/build-and-publish.yml

@@ -8,4 +8,4 @@ on:
 
 jobs:
   build:
-    uses: ./.github/workflows/build-reusable.yml 
+    uses: ./.github/workflows/build-reusable.yml

.github/workflows/build-reusable.yml

@@ -10,7 +10,36 @@ on:
         default: ''
 
 jobs:
+  lint:
+    name: Lint and Format Check
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          ref: ${{ inputs.ref }}
+
+      - name: Setup Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.11'
+
+      - 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
     name: Build ${{ matrix.os }} Python ${{ matrix.python }}
     strategy:
       matrix:
@@ -36,40 +65,40 @@ jobs:
           - os: macos-latest
             python: '3.13'
     runs-on: ${{ matrix.os }}
-    
+
     steps:
       - uses: actions/checkout@v4
         with:
           ref: ${{ inputs.ref }}
           submodules: recursive
-      
+
       - name: Setup Python
         uses: actions/setup-python@v5
         with:
           python-version: ${{ matrix.python }}
-      
+
       - name: Install uv
         uses: astral-sh/setup-uv@v4
-      
+
       - name: Install system dependencies (Ubuntu)
         if: runner.os == 'Linux'
         run: |
           sudo apt-get update
           sudo apt-get install -y libomp-dev libboost-all-dev protobuf-compiler libzmq3-dev \
             pkg-config libopenblas-dev patchelf libabsl-dev libaio-dev libprotobuf-dev
-          
+
           # 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" >> $GITHUB_ENV
           echo "LD_LIBRARY_PATH=/opt/intel/oneapi/mkl/latest/lib/intel64:$LD_LIBRARY_PATH" >> $GITHUB_ENV
-      
+
       - name: Install system dependencies (macOS)
         if: runner.os == 'macOS'
         run: |
           brew install llvm libomp boost protobuf zeromq
-      
+
       - name: Install build dependencies
         run: |
           uv pip install --system scikit-build-core numpy swig Cython pybind11
@@ -78,7 +107,7 @@ jobs:
           else
             uv pip install --system delocate
           fi
-      
+
       - name: Build packages
         run: |
           # Build core (platform independent)
@@ -87,7 +116,7 @@ jobs:
             uv build
             cd ../..
           fi
-          
+
           # Build HNSW backend
           cd packages/leann-backend-hnsw
           if [ "${{ matrix.os }}" == "macos-latest" ]; then
@@ -96,7 +125,7 @@ jobs:
             uv build --wheel --python python
           fi
           cd ../..
-          
+
           # Build DiskANN backend
           cd packages/leann-backend-diskann
           if [ "${{ matrix.os }}" == "macos-latest" ]; then
@@ -105,14 +134,14 @@ jobs:
             uv build --wheel --python python
           fi
           cd ../..
-          
+
           # Build meta package (platform independent)
           if [[ "${{ matrix.os }}" == ubuntu-* ]]; then
             cd packages/leann
             uv build
             cd ../..
           fi
-      
+
       - name: Repair wheels (Linux)
         if: runner.os == 'Linux'
         run: |
@@ -124,7 +153,7 @@ jobs:
             mv dist_repaired dist
           fi
           cd ../..
-          
+
           # Repair DiskANN wheel
           cd packages/leann-backend-diskann
           if [ -d dist ]; then
@@ -133,7 +162,7 @@ jobs:
             mv dist_repaired dist
           fi
           cd ../..
-      
+
       - name: Repair wheels (macOS)
         if: runner.os == 'macOS'
         run: |
@@ -145,7 +174,7 @@ jobs:
             mv dist_repaired dist
           fi
           cd ../..
-          
+
           # Repair DiskANN wheel
           cd packages/leann-backend-diskann
           if [ -d dist ]; then
@@ -154,14 +183,14 @@ jobs:
             mv dist_repaired dist
           fi
           cd ../..
-      
+
       - name: List built packages
         run: |
           echo "📦 Built packages:"
           find packages/*/dist -name "*.whl" -o -name "*.tar.gz" | sort
-      
+
       - name: Upload artifacts
         uses: actions/upload-artifact@v4
         with:
           name: packages-${{ matrix.os }}-py${{ matrix.python }}
-          path: packages/*/dist/ 
+          path: packages/*/dist/

.github/workflows/release-manual.yml

@@ -16,18 +16,21 @@ jobs:
       contents: write
     outputs:
       commit-sha: ${{ steps.push.outputs.commit-sha }}
-    
+
     steps:
       - uses: actions/checkout@v4
-      
+
       - name: Validate version
         run: |
-          if ! [[ "${{ inputs.version }}" =~ ^[0-9]+\.[0-9]+\.[0-9]+$ ]]; then
-            echo "❌ Invalid version format"
+          # Remove 'v' prefix if present for validation
+          VERSION_CLEAN="${{ inputs.version }}"
+          VERSION_CLEAN="${VERSION_CLEAN#v}"
+          if ! [[ "$VERSION_CLEAN" =~ ^[0-9]+\.[0-9]+\.[0-9]+$ ]]; then
+            echo "❌ Invalid version format. Expected format: X.Y.Z or vX.Y.Z"
             exit 1
           fi
-          echo "✅ Version format valid"
-      
+          echo "✅ Version format valid: ${{ inputs.version }}"
+
       - name: Update versions and push
         id: push
         run: |
@@ -35,7 +38,7 @@ jobs:
           CURRENT_VERSION=$(grep "^version" packages/leann-core/pyproject.toml | cut -d'"' -f2)
           echo "Current version: $CURRENT_VERSION"
           echo "Target version: ${{ inputs.version }}"
-          
+
           if [ "$CURRENT_VERSION" = "${{ inputs.version }}" ]; then
             echo "⚠️  Version is already ${{ inputs.version }}, skipping update"
             COMMIT_SHA=$(git rev-parse HEAD)
@@ -49,7 +52,7 @@ jobs:
             COMMIT_SHA=$(git rev-parse HEAD)
             echo "✅ Pushed version update: $COMMIT_SHA"
           fi
-          
+
           echo "commit-sha=$COMMIT_SHA" >> $GITHUB_OUTPUT
 
   build-packages:
@@ -57,7 +60,7 @@ jobs:
     needs: update-version
     uses: ./.github/workflows/build-reusable.yml
     with:
-      ref: 'main' 
+      ref: 'main'
 
   publish:
     name: Publish and Release
@@ -66,26 +69,26 @@ jobs:
     runs-on: ubuntu-latest
     permissions:
       contents: write
-    
+
     steps:
       - uses: actions/checkout@v4
         with:
-          ref: 'main' 
-      
+          ref: 'main'
+
       - name: Download all artifacts
         uses: actions/download-artifact@v4
         with:
           path: dist-artifacts
-      
+
       - name: Collect packages
         run: |
           mkdir -p dist
           find dist-artifacts -name "*.whl" -exec cp {} dist/ \;
           find dist-artifacts -name "*.tar.gz" -exec cp {} dist/ \;
-          
+
           echo "📦 Packages to publish:"
           ls -la dist/
-      
+
       - name: Publish to PyPI
         env:
           TWINE_USERNAME: __token__
@@ -95,12 +98,12 @@ jobs:
             echo "❌ PYPI_API_TOKEN not configured!"
             exit 1
           fi
-          
+
           pip install twine
           twine upload dist/* --skip-existing --verbose
-          
+
           echo "✅ Published to PyPI!"
-      
+
       - name: Create release
         run: |
           # Check if tag already exists
@@ -111,7 +114,7 @@ jobs:
             git push origin "v${{ inputs.version }}"
             echo "✅ Created and pushed tag v${{ inputs.version }}"
           fi
-          
+
           # Check if release already exists
           if gh release view "v${{ inputs.version }}" >/dev/null 2>&1; then
             echo "⚠️  Release v${{ inputs.version }} already exists, skipping release creation"
@@ -123,4 +126,4 @@ jobs:
             echo "✅ Created GitHub release v${{ inputs.version }}"
           fi
         env:
-          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}

.gitignore

@@ -9,7 +9,7 @@ demo/indices/
 outputs/
 *.pkl
 *.pdf
-*.idx 
+*.idx
 *.map
 .history/
 lm_eval.egg-info/
@@ -85,4 +85,4 @@ packages/leann-backend-diskann/third_party/DiskANN/_deps/
 *.meta.json
 *.passages.json
 
-batchtest.py
+batchtest.py

.pre-commit-config.yaml

@@ -0,0 +1,16 @@
+repos:
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v4.5.0
+    hooks:
+      - id: trailing-whitespace
+      - id: end-of-file-fixer
+      - id: check-yaml
+      - id: check-added-large-files
+      - id: check-merge-conflict
+      - id: debug-statements
+
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.2.1
+    hooks:
+      - id: ruff
+      - id: ruff-format

README.md

@@ -12,7 +12,7 @@
     The smallest vector index in the world. RAG Everything with LEANN!
 </h2>
 
-LEANN is a revolutionary vector database that democratizes personal AI. Transform your laptop into a powerful RAG system that can index and search through millions of documents while using **97% less storage** than traditional solutions **without accuracy loss**.
+LEANN is an innovative vector database that democratizes personal AI. Transform your laptop into a powerful RAG system that can index and search through millions of documents while using **97% less storage** than traditional solutions **without accuracy loss**.
 
 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)
 
@@ -33,12 +33,46 @@ LEANN achieves this through *graph-based selective recomputation* with *high-deg
 
 🪶 **Lightweight:** Graph-based recomputation eliminates heavy embedding storage, while smart graph pruning and CSR format minimize graph storage overhead. Always less storage, less memory usage!
 
+📦 **Portable:** Transfer your entire knowledge base between devices (even with others) with minimal cost - your personal AI memory travels with you.
+
 📈 **Scalability:** Handle messy personal data that would crash traditional vector DBs, easily managing your growing personalized data and agent generated memory!
 
 ✨ **No Accuracy Loss:** Maintain the same search quality as heavyweight solutions while using 97% less storage.
 
 ## Installation
-> `pip leann` coming soon!
+
+<details>
+<summary><strong>📦 Prerequisites: Install uv (if you don't have it)</strong></summary>
+
+Install uv first if you don't have it:
+
+```bash
+curl -LsSf https://astral.sh/uv/install.sh | sh
+```
+
+📖 [Detailed uv installation methods →](https://docs.astral.sh/uv/getting-started/installation/#installation-methods)
+
+</details>
+
+
+LEANN provides two installation methods: **pip install** (quick and easy) and **build from source** (recommended for development).
+
+
+
+### 🚀 Quick Install (Recommended for most users)
+
+Clone the repository to access all examples and install LEANN from [PyPI](https://pypi.org/project/leann/) to run them immediately:
+
+```bash
+git clone git@github.com:yichuan-w/LEANN.git leann
+cd leann
+uv venv
+source .venv/bin/activate
+uv pip install leann
+```
+
+### 🔧 Build from Source (Recommended for development)
+
 ```bash
 git clone git@github.com:yichuan-w/LEANN.git leann
 cd leann
@@ -48,27 +82,65 @@ git submodule update --init --recursive
 **macOS:**
 ```bash
 brew install llvm libomp boost protobuf zeromq pkgconf
-
-# Install with HNSW backend (default, recommended for most users)
-# Install uv first if you don't have it:
-# curl -LsSf https://astral.sh/uv/install.sh | sh
-# See: https://docs.astral.sh/uv/getting-started/installation/#installation-methods
 CC=$(brew --prefix llvm)/bin/clang CXX=$(brew --prefix llvm)/bin/clang++ uv sync
 ```
 
 **Linux:**
 ```bash
 sudo apt-get install libomp-dev libboost-all-dev protobuf-compiler libabsl-dev libmkl-full-dev libaio-dev libzmq3-dev
-
-# Install with HNSW backend (default, recommended for most users)
 uv sync
 ```
 
 
-**Ollama Setup (Recommended for full privacy):**
 
-> *You can skip this installation if you only want to use OpenAI API for generation.*
 
+## Quick Star
+
+Our declarative API makes RAG as easy as writing a config file.
+
+[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/yichuan-w/LEANN/blob/main/demo.ipynb) [Try in this ipynb file →](demo.ipynb)
+
+```python
+from leann import LeannBuilder, LeannSearcher, LeannCha
+from pathlib import Path
+INDEX_PATH = str(Path("./").resolve() / "demo.leann")
+
+# Build an index
+builder = LeannBuilder(backend_name="hnsw")
+builder.add_text("LEANN saves 97% storage compared to traditional vector databases.")
+builder.add_text("Tung Tung Tung Sahur called—they need their banana‑crocodile hybrid back")
+builder.build_index(INDEX_PATH)
+
+# Search
+searcher = LeannSearcher(INDEX_PATH)
+results = searcher.search("fantastical AI-generated creatures", top_k=1)
+
+# Chat with your data
+chat = LeannChat(INDEX_PATH, llm_config={"type": "hf", "model": "Qwen/Qwen3-0.6B"})
+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, and more.
+
+
+> **Generation Model Setup**
+> LEANN supports multiple LLM providers for text generation (OpenAI API, HuggingFace, Ollama).
+
+<details>
+<summary><strong>🔑 OpenAI API Setup (Default)</strong></summary>
+
+Set your OpenAI API key as an environment variable:
+
+```bash
+export OPENAI_API_KEY="your-api-key-here"
+```
+
+</details>
+
+<details>
+<summary><strong>🔧 Ollama Setup (Recommended for full privacy)</strong></summary>
 
 **macOS:**
 
@@ -80,6 +152,7 @@ ollama pull llama3.2:1b
 ```
 
 **Linux:**
+
 ```bash
 # Install Ollama
 curl -fsSL https://ollama.ai/install.sh | sh
@@ -91,43 +164,7 @@ ollama serve &
 ollama pull llama3.2:1b
 ```
 
-## Quick Start in 30s
-
-Our declarative API makes RAG as easy as writing a config file.
-[Try in this ipynb file →](demo.ipynb) [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/yichuan-w/LEANN/blob/main/demo.ipynb)
-
-```python
-from leann.api import LeannBuilder, LeannSearcher, LeannChat
-
-# 1. Build the index (no embeddings stored!)
-builder = LeannBuilder(backend_name="hnsw")
-builder.add_text("C# is a powerful programming language")
-builder.add_text("Python is a powerful programming language and it is very popular")
-builder.add_text("Machine learning transforms industries")
-builder.add_text("Neural networks process complex data")
-builder.add_text("Leann is a great storage saving engine for RAG on your MacBook")
-builder.build_index("knowledge.leann")
-
-# 2. Search with real-time embeddings
-searcher = LeannSearcher("knowledge.leann")
-results = searcher.search("programming languages", top_k=2)
-
-# 3. Chat with LEANN using retrieved results
-llm_config = {
-    "type": "ollama",
-    "model": "llama3.2:1b"
-}
-
-chat = LeannChat(index_path="knowledge.leann", llm_config=llm_config)
-response = chat.ask(
-    "Compare the two retrieved programming languages and say which one is more popular today.",
-    top_k=2,
-)
-```
-
-## RAG on Everything!
-
-LEANN supports RAG on various data sources including documents (.pdf, .txt, .md), Apple Mail, Google Search History, WeChat, and more.
+</details>
 
 ### 📄 Personal Data Manager: Process Any Documents (.pdf, .txt, .md)!
 
@@ -139,11 +176,6 @@ Ask questions directly about your personal PDFs, documents, and any directory co
 
 The example below asks a question about summarizing two papers (uses default data in `examples/data`):
 
-```bash
-# Drop your PDFs, .txt, .md files into examples/data/
-uv run ./examples/main_cli_example.py
-```
-
 ```
 # Or use python directly
 source .venv/bin/activate
@@ -154,6 +186,9 @@ python ./examples/main_cli_example.py
 
 ### 📧 Your Personal Email Secretary: RAG on Apple Mail!
 
+> **Note:** The examples below currently support macOS only. Windows support coming soon.
+
+
 <p align="center">
   <img src="videos/mail_clear.gif" alt="LEANN Email Search Demo" width="600">
 </p>
@@ -233,7 +268,7 @@ The default Chrome profile path is configured for a typical macOS setup. If you
 1. Open Terminal
 2. Run: `ls ~/Library/Application\ Support/Google/Chrome/`
 3. Look for folders like "Default", "Profile 1", "Profile 2", etc.
-4. Use the full path as your `--chrome-profile` argument
+4. Use the full path as your `--chrome-profile` argumen
 
 **Common Chrome profile locations:**
 - macOS: `~/Library/Application Support/Google/Chrome/Default`
@@ -276,7 +311,7 @@ sudo packages/wechat-exporter/wechattweak-cli install
 
 **Troubleshooting:**
 - **Installation issues**: Check the [WeChatTweak-CLI issues page](https://github.com/sunnyyoung/WeChatTweak-CLI/issues/41)
-- **Export errors**: If you encounter the error below, try restarting WeChat
+- **Export errors**: If you encounter the error below, try restarting WeCha
 ```
 Failed to export WeChat data. Please ensure WeChat is running and WeChatTweak is installed.
 Failed to find or export WeChat data. Exiting.
@@ -324,14 +359,14 @@ LEANN includes a powerful CLI for document processing and search. Perfect for qu
 # Build an index from documents
 leann build my-docs --docs ./documents
 
-# Search your documents  
+# Search your documents
 leann search my-docs "machine learning concepts"
 
 # Interactive chat with your documents
 leann ask my-docs --interactive
 
 # List all your indexes
-leann list
+leann lis
 ```
 
 **Key CLI features:**
@@ -392,7 +427,7 @@ Options:
 
 **Core techniques:**
 - **Graph-based selective recomputation:** Only compute embeddings for nodes in the search path
-- **High-degree preserving pruning:** Keep important "hub" nodes while removing redundant connections  
+- **High-degree preserving pruning:** Keep important "hub" nodes while removing redundant connections
 - **Dynamic batching:** Efficiently batch embedding computations for GPU utilization
 - **Two-level search:** Smart graph traversal that prioritizes promising nodes
 
@@ -416,7 +451,7 @@ Options:
 
 ```bash
 uv pip install -e ".[dev]"  # Install dev dependencies
-python examples/run_evaluation.py data/indices/dpr/dpr_diskann      # DPR dataset
+python examples/run_evaluation.py data/indices/dpr/dpr_diskann      # DPR datase
 python examples/run_evaluation.py data/indices/rpj_wiki/rpj_wiki.index  # Wikipedia
 ```
 
@@ -429,22 +464,22 @@ If you find Leann useful, please cite:
 
 ```bibtex
 @misc{wang2025leannlowstoragevectorindex,
-      title={LEANN: A Low-Storage Vector Index}, 
+      title={LEANN: A Low-Storage Vector Index},
       author={Yichuan Wang and Shu Liu and Zhifei Li and Yongji Wu and Ziming Mao and Yilong Zhao and Xiao Yan and Zhiying Xu and Yang Zhou and Ion Stoica and Sewon Min and Matei Zaharia and Joseph E. Gonzalez},
       year={2025},
       eprint={2506.08276},
       archivePrefix={arXiv},
       primaryClass={cs.DB},
-      url={https://arxiv.org/abs/2506.08276}, 
+      url={https://arxiv.org/abs/2506.08276},
 }
 ```
 
 ## ✨ [Detailed Features →](docs/features.md)
 
-## 🤝 [Contributing →](docs/contributing.md)
+## 🤝 [CONTRIBUTING →](docs/CONTRIBUTING.md)
 
 
-## [FAQ →](docs/faq.md)
+## ❓ [FAQ →](docs/faq.md)
 
 
 ## 📈 [Roadmap →](docs/roadmap.md)
@@ -465,4 +500,3 @@ This work is done at [**Berkeley Sky Computing Lab**](https://sky.cs.berkeley.e
 <p align="center">
   Made with ❤️ by the Leann team
 </p>
-

demo.ipynb

@@ -4,7 +4,11 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "# Quick Start in 30s"
+    "# Quick Start \n",
+    "\n",
+    "**Home GitHub Repository:** [LEANN on GitHub](https://github.com/yichuan-w/LEANN)\n",
+    "\n",
+    "**Important for Colab users:** Set your runtime type to T4 GPU for optimal performance. Go to Runtime → Change runtime type → Hardware accelerator → T4 GPU."
    ]
   },
   {
@@ -14,11 +18,24 @@
    "outputs": [],
    "source": [
     "# install this if you are using colab\n",
-    "! pip install leann\n",
-    "\n",
+    "! uv pip install leann-core leann-backend-hnsw --no-deps\n",
+    "! uv pip install leann --no-deps\n",
     "# For Colab environment, we need to set some environment variables\n",
     "import os\n",
-    "os.environ['LEANN_LOG_LEVEL'] = 'INFO'  # Enable more detailed logging"
+    "\n",
+    "os.environ[\"LEANN_LOG_LEVEL\"] = \"INFO\"  # Enable more detailed logging"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from pathlib import Path\n",
+    "\n",
+    "INDEX_DIR = Path(\"./\").resolve()\n",
+    "INDEX_PATH = str(INDEX_DIR / \"demo.leann\")"
    ]
   },
   {
@@ -38,11 +55,13 @@
     "\n",
     "builder = LeannBuilder(backend_name=\"hnsw\")\n",
     "builder.add_text(\"C# is a powerful programming language and it is good at game development\")\n",
-    "builder.add_text(\"Python is a powerful programming language and it is good at machine learning tasks\")\n",
+    "builder.add_text(\n",
+    "    \"Python is a powerful programming language and it is good at machine learning tasks\"\n",
+    ")\n",
     "builder.add_text(\"Machine learning transforms industries\")\n",
     "builder.add_text(\"Neural networks process complex data\")\n",
     "builder.add_text(\"Leann is a great storage saving engine for RAG on your MacBook\")\n",
-    "builder.build_index(\"knowledge.leann\")"
+    "builder.build_index(INDEX_PATH)"
    ]
   },
   {
@@ -60,7 +79,7 @@
    "source": [
     "from leann.api import LeannSearcher\n",
     "\n",
-    "searcher = LeannSearcher(\"knowledge.leann\")\n",
+    "searcher = LeannSearcher(INDEX_PATH)\n",
     "results = searcher.search(\"programming languages\", top_k=2)\n",
     "results"
    ]
@@ -85,11 +104,11 @@
     "    \"model\": \"Qwen/Qwen3-0.6B\",\n",
     "}\n",
     "\n",
-    "chat = LeannChat(index_path=\"knowledge.leann\", llm_config=llm_config)\n",
+    "chat = LeannChat(index_path=INDEX_PATH, llm_config=llm_config)\n",
     "response = chat.ask(\n",
     "    \"Compare the two retrieved programming languages and tell me their advantages.\",\n",
     "    top_k=2,\n",
-    "    llm_kwargs={\"max_tokens\": 128}\n",
+    "    llm_kwargs={\"max_tokens\": 128},\n",
     ")\n",
     "response"
    ]

docs/CONTRIBUTING.md

@@ -0,0 +1,220 @@
+# 🤝 Contributing
+
+We welcome contributions! Leann is built by the community, for the community.
+
+## Ways to Contribute
+
+- 🐛 **Bug Reports**: Found an issue? Let us know!
+- 💡 **Feature Requests**: Have an idea? We'd love to hear it!
+- 🔧 **Code Contributions**: PRs welcome for all skill levels
+- 📖 **Documentation**: Help make Leann more accessible
+- 🧪 **Benchmarks**: Share your performance results
+
+## 🚀 Development Setup
+
+### Prerequisites
+
+1. **Install uv** (fast Python package installer):
+   ```bash
+   curl -LsSf https://astral.sh/uv/install.sh | sh
+   ```
+
+2. **Clone the repository**:
+   ```bash
+   git clone https://github.com/LEANN-RAG/LEANN-RAG.git
+   cd LEANN-RAG
+   ```
+
+3. **Install system dependencies**:
+
+   **macOS:**
+   ```bash
+   brew install llvm libomp boost protobuf zeromq pkgconf
+   ```
+
+   **Ubuntu/Debian:**
+   ```bash
+   sudo apt-get install libomp-dev libboost-all-dev protobuf-compiler \
+                        libabsl-dev libmkl-full-dev libaio-dev libzmq3-dev
+   ```
+
+4. **Build from source**:
+   ```bash
+   # macOS
+   CC=$(brew --prefix llvm)/bin/clang CXX=$(brew --prefix llvm)/bin/clang++ uv sync
+
+   # Ubuntu/Debian
+   uv sync
+   ```
+
+## 🔨 Pre-commit Hooks
+
+We use pre-commit hooks to ensure code quality and consistency. This runs automatically before each commit.
+
+### Setup Pre-commit
+
+1. **Install pre-commit** (already included when you run `uv sync`):
+   ```bash
+   uv pip install pre-commit
+   ```
+
+2. **Install the git hooks**:
+   ```bash
+   pre-commit install
+   ```
+
+3. **Run pre-commit manually** (optional):
+   ```bash
+   pre-commit run --all-files
+   ```
+
+### Pre-commit Checks
+
+Our pre-commit configuration includes:
+- **Trailing whitespace removal**
+- **End-of-file fixing**
+- **YAML validation**
+- **Large file prevention**
+- **Merge conflict detection**
+- **Debug statement detection**
+- **Code formatting with ruff**
+- **Code linting with ruff**
+
+## 🧪 Testing
+
+### Running Tests
+
+```bash
+# Run all tests
+uv run pytest
+
+# Run specific test file
+uv run pytest test/test_filename.py
+
+# Run with coverage
+uv run pytest --cov=leann
+```
+
+### Writing Tests
+
+- Place tests in the `test/` directory
+- Follow the naming convention `test_*.py`
+- Use descriptive test names that explain what's being tested
+- Include both positive and negative test cases
+
+## 📝 Code Style
+
+We use `ruff` for both linting and formatting to ensure consistent code style.
+
+### Format Your Code
+
+```bash
+# Format all files
+ruff format
+
+# Check formatting without changing files
+ruff format --check
+```
+
+### Lint Your Code
+
+```bash
+# Run linter with auto-fix
+ruff check --fix
+
+# Just check without fixing
+ruff check
+```
+
+### Style Guidelines
+
+- Follow PEP 8 conventions
+- Use descriptive variable names
+- Add type hints where appropriate
+- Write docstrings for all public functions and classes
+- Keep functions focused and single-purpose
+
+## 🚦 CI/CD
+
+Our CI pipeline runs automatically on all pull requests. It includes:
+
+1. **Linting and Formatting**: Ensures code follows our style guidelines
+2. **Multi-platform builds**: Tests on Ubuntu and macOS
+3. **Python version matrix**: Tests on Python 3.9-3.13
+4. **Wheel building**: Ensures packages can be built and distributed
+
+### CI Commands
+
+The CI uses the same commands as pre-commit to ensure consistency:
+```bash
+# Linting
+ruff check .
+
+# Format checking
+ruff format --check .
+```
+
+Make sure your code passes these checks locally before pushing!
+
+## 🔄 Pull Request Process
+
+1. **Fork the repository** and create your branch from `main`:
+   ```bash
+   git checkout -b feature/your-feature-name
+   ```
+
+2. **Make your changes**:
+   - Write clean, documented code
+   - Add tests for new functionality
+   - Update documentation as needed
+
+3. **Run pre-commit checks**:
+   ```bash
+   pre-commit run --all-files
+   ```
+
+4. **Test your changes**:
+   ```bash
+   uv run pytest
+   ```
+
+5. **Commit with descriptive messages**:
+   ```bash
+   git commit -m "feat: add new search algorithm"
+   ```
+
+   Follow [Conventional Commits](https://www.conventionalcommits.org/):
+   - `feat:` for new features
+   - `fix:` for bug fixes
+   - `docs:` for documentation changes
+   - `test:` for test additions/changes
+   - `refactor:` for code refactoring
+   - `perf:` for performance improvements
+
+6. **Push and create a pull request**:
+   - Provide a clear description of your changes
+   - Reference any related issues
+   - Include examples or screenshots if applicable
+
+## 📚 Documentation
+
+When adding new features or making significant changes:
+
+1. Update relevant documentation in `/docs`
+2. Add docstrings to new functions/classes
+3. Update README.md if needed
+4. Include usage examples
+
+## 🤔 Getting Help
+
+- **Discord**: Join our community for discussions
+- **Issues**: Check existing issues or create a new one
+- **Discussions**: For general questions and ideas
+
+## 📄 License
+
+By contributing, you agree that your contributions will be licensed under the same license as the project (MIT).
+
+---
+
+Thank you for contributing to LEANN! Every contribution, no matter how small, helps make the project better for everyone. 🌟

docs/RELEASE.md

@@ -19,4 +19,4 @@ That's it! The workflow will automatically:
 - ✅ Publish to PyPI
 - ✅ Create GitHub tag and release
 
-Check progress: https://github.com/yichuan-w/LEANN/actions 
+Check progress: https://github.com/yichuan-w/LEANN/actions

docs/contributing.md

@@ -1,11 +0,0 @@
-# 🤝 Contributing
-
-We welcome contributions! Leann is built by the community, for the community.
-
-## Ways to Contribute
-
-- 🐛 **Bug Reports**: Found an issue? Let us know!
-- 💡 **Feature Requests**: Have an idea? We'd love to hear it!
-- 🔧 **Code Contributions**: PRs welcome for all skill levels
-- 📖 **Documentation**: Help make Leann more accessible
-- 🧪 **Benchmarks**: Share your performance results 

docs/faq.md

@@ -7,4 +7,4 @@ You can speed up the process by using a lightweight embedding model. Add this to
 ```bash
 --embedding-model sentence-transformers/all-MiniLM-L6-v2
 ```
-**Model sizes:** `all-MiniLM-L6-v2` (30M parameters), `facebook/contriever` (~100M parameters), `Qwen3-0.6B` (600M parameters) 
+**Model sizes:** `all-MiniLM-L6-v2` (30M parameters), `facebook/contriever` (~100M parameters), `Qwen3-0.6B` (600M parameters)

docs/features.md

@@ -19,4 +19,4 @@
 
 - **Simple Python API** - Get started in minutes
 - **Extensible backend system** - Easy to add new algorithms
-- **Comprehensive examples** - From basic usage to production deployment 
+- **Comprehensive examples** - From basic usage to production deployment

docs/normalized_embeddings.md

@@ -0,0 +1,75 @@
+# Normalized Embeddings Support in LEANN
+
+LEANN now automatically detects normalized embedding models and sets the appropriate distance metric for optimal performance.
+
+## What are Normalized Embeddings?
+
+Normalized embeddings are vectors with L2 norm = 1 (unit vectors). These embeddings are optimized for cosine similarity rather than Maximum Inner Product Search (MIPS).
+
+## Automatic Detection
+
+When you create a `LeannBuilder` instance with a normalized embedding model, LEANN will:
+
+1. **Automatically set `distance_metric="cosine"`** if not specified
+2. **Show a warning** if you manually specify a different distance metric
+3. **Provide optimal search performance** with the correct metric
+
+## Supported Normalized Embedding Models
+
+### OpenAI
+All OpenAI text embedding models are normalized:
+- `text-embedding-ada-002`
+- `text-embedding-3-small`
+- `text-embedding-3-large`
+
+### Voyage AI
+All Voyage AI embedding models are normalized:
+- `voyage-2`
+- `voyage-3`
+- `voyage-large-2`
+- `voyage-multilingual-2`
+- `voyage-code-2`
+
+### Cohere
+All Cohere embedding models are normalized:
+- `embed-english-v3.0`
+- `embed-multilingual-v3.0`
+- `embed-english-light-v3.0`
+- `embed-multilingual-light-v3.0`
+
+## Example Usage
+
+```python
+from leann.api import LeannBuilder
+
+# Automatic detection - will use cosine distance
+builder = LeannBuilder(
+    backend_name="hnsw",
+    embedding_model="text-embedding-3-small",
+    embedding_mode="openai"
+)
+# Warning: Detected normalized embeddings model 'text-embedding-3-small'...
+# Automatically setting distance_metric='cosine'
+
+# Manual override (not recommended)
+builder = LeannBuilder(
+    backend_name="hnsw",
+    embedding_model="text-embedding-3-small",
+    embedding_mode="openai",
+    distance_metric="mips"  # Will show warning
+)
+# Warning: Using 'mips' distance metric with normalized embeddings...
+```
+
+## Non-Normalized Embeddings
+
+Models like `facebook/contriever` and other sentence-transformers models that are not normalized will continue to use MIPS by default, which is optimal for them.
+
+## Why This Matters
+
+Using the wrong distance metric with normalized embeddings can lead to:
+- **Poor search quality** due to HNSW's early termination with narrow score ranges
+- **Incorrect ranking** of search results
+- **Suboptimal performance** compared to using the correct metric
+
+For more details on why this happens, see our analysis of [OpenAI embeddings with MIPS](../examples/main_cli_example.py).

docs/roadmap.md

@@ -18,4 +18,4 @@
 
 - [ ] Integration with LangChain/LlamaIndex
 - [ ] Visual similarity search
-- [ ] Query rewrtiting, rerank and expansion 
+- [ ] Query rewrtiting, rerank and expansion

examples/compare_faiss_vs_leann.py

@@ -3,14 +3,15 @@
 Memory comparison between Faiss HNSW and LEANN HNSW backend
 """
 
+import gc
 import logging
 import os
+import subprocess
 import sys
 import time
-import psutil
-import gc
-import subprocess
 from pathlib import Path
+
+import psutil
 from llama_index.core.node_parser import SentenceSplitter
 
 # Setup logging
@@ -83,9 +84,7 @@ def test_faiss_hnsw():
 
         for line in lines:
             if "Peak Memory:" in line:
-                peak_memory = float(
-                    line.split("Peak Memory:")[1].split("MB")[0].strip()
-                )
+                peak_memory = float(line.split("Peak Memory:")[1].split("MB")[0].strip())
 
         return {"peak_memory": peak_memory}
 
@@ -111,9 +110,8 @@ def test_leann_hnsw():
 
     tracker.checkpoint("After imports")
 
+    from leann.api import LeannBuilder
     from llama_index.core import SimpleDirectoryReader
-    from leann.api import LeannBuilder, LeannSearcher
-
 
     # Load and parse documents
     documents = SimpleDirectoryReader(
@@ -197,16 +195,14 @@ def test_leann_hnsw():
     runtime_start_mem = get_memory_usage()
     print(f"Before load memory: {runtime_start_mem:.1f} MB")
     tracker.checkpoint("Before load memory")
-    
+
     # Load searcher
     searcher = LeannSearcher(index_path)
     tracker.checkpoint("After searcher loading")
 
-
-
     print("Running search queries...")
     queries = [
-        "什么是盘古大模型以及盘古开发过程中遇到了什么阴暗面，任务令一般在什么城市颁发",
+        "什么是盘古大模型以及盘古开发过程中遇到了什么阴暗面,任务令一般在什么城市颁发",
         "What is LEANN and how does it work?",
         "华为诺亚方舟实验室的主要研究内容",
     ]
@@ -304,21 +300,15 @@ def main():
 
         print("\nLEANN vs Faiss Performance:")
         memory_saving = faiss_results["peak_memory"] - leann_results["peak_memory"]
-        print(
-            f"  Search Memory: {memory_ratio:.1f}x less ({memory_saving:.1f} MB saved)"
-        )
+        print(f"  Search Memory: {memory_ratio:.1f}x less ({memory_saving:.1f} MB saved)")
 
         # Storage comparison
         if leann_storage_size > faiss_storage_size:
             storage_ratio = leann_storage_size / faiss_storage_size
-            print(
-                f"  Storage Size: {storage_ratio:.1f}x larger (LEANN uses more storage)"
-            )
+            print(f"  Storage Size: {storage_ratio:.1f}x larger (LEANN uses more storage)")
         elif faiss_storage_size > leann_storage_size:
             storage_ratio = faiss_storage_size / leann_storage_size
-            print(
-                f"  Storage Size: {storage_ratio:.1f}x smaller (LEANN uses less storage)"
-            )
+            print(f"  Storage Size: {storage_ratio:.1f}x smaller (LEANN uses less storage)")
         else:
             print("  Storage Size: similar")
     else:

examples/data/PrideandPrejudice.txt

@@ -1,5 +1,5 @@
 The Project Gutenberg eBook of Pride and Prejudice
-    
+
 This ebook is for the use of anyone anywhere in the United States and
 most other parts of the world at no cost and with almost no restrictions
 whatsoever. You may copy it, give it away or re-use it under the terms
@@ -14557,7 +14557,7 @@ her into Derbyshire, had been the means of uniting them.
 *** END OF THE PROJECT GUTENBERG EBOOK PRIDE AND PREJUDICE ***
 
 
-    
+
 
 Updated editions will replace the previous one—the old editions will
 be renamed.
@@ -14662,7 +14662,7 @@ performed, viewed, copied or distributed:
     at www.gutenberg.org. If you
     are not located in the United States, you will have to check the laws
     of the country where you are located before using this eBook.
-  
+
 1.E.2. If an individual Project Gutenberg™ electronic work is
 derived from texts not protected by U.S. copyright law (does not
 contain a notice indicating that it is posted with permission of the
@@ -14724,7 +14724,7 @@ provided that:
         Gutenberg Literary Archive Foundation at the address specified in
         Section 4, “Information about donations to the Project Gutenberg
         Literary Archive Foundation.”
-    
+
     • You provide a full refund of any money paid by a user who notifies
         you in writing (or by e-mail) within 30 days of receipt that s/he
         does not agree to the terms of the full Project Gutenberg™
@@ -14732,15 +14732,15 @@ provided that:
         copies of the works possessed in a physical medium and discontinue
         all use of and all access to other copies of Project Gutenberg™
         works.
-    
+
     • You provide, in accordance with paragraph 1.F.3, a full refund of
         any money paid for a work or a replacement copy, if a defect in the
         electronic work is discovered and reported to you within 90 days of
         receipt of the work.
-    
+
     • You comply with all other terms of this agreement for free
         distribution of Project Gutenberg™ works.
-    
+
 
 1.E.9. If you wish to charge a fee or distribute a Project
 Gutenberg™ electronic work or group of works on different terms than
@@ -14903,5 +14903,3 @@ This website includes information about Project Gutenberg™,
 including how to make donations to the Project Gutenberg Literary
 Archive Foundation, how to help produce our new eBooks, and how to
 subscribe to our email newsletter to hear about new eBooks.
-
-

examples/document_search.py

@@ -3,37 +3,47 @@
 Document search demo with recompute mode
 """
 
-import os
-from pathlib import Path
 import shutil
 import time
+from pathlib import Path
 
 # Import backend packages to trigger plugin registration
 try:
-    import leann_backend_diskann
-    import leann_backend_hnsw
+    import leann_backend_diskann  # noqa: F401
+    import leann_backend_hnsw  # noqa: F401
+
     print("INFO: Backend packages imported successfully.")
 except ImportError as e:
     print(f"WARNING: Could not import backend packages. Error: {e}")
 
 # Import upper-level API from leann-core
-from leann.api import LeannBuilder, LeannSearcher, LeannChat
+from leann.api import LeannBuilder, LeannChat, LeannSearcher
 
 
 def load_sample_documents():
     """Create sample documents for demonstration"""
     docs = [
-        {"title": "Intro to Python", "content": "Python is a high-level, interpreted language known for simplicity."},
-        {"title": "ML Basics", "content": "Machine learning builds systems that learn from data."},
-        {"title": "Data Structures", "content": "Data structures like arrays, lists, and graphs organize data."},
+        {
+            "title": "Intro to Python",
+            "content": "Python is a high-level, interpreted language known for simplicity.",
+        },
+        {
+            "title": "ML Basics",
+            "content": "Machine learning builds systems that learn from data.",
+        },
+        {
+            "title": "Data Structures",
+            "content": "Data structures like arrays, lists, and graphs organize data.",
+        },
     ]
     return docs
 
+
 def main():
     print("==========================================================")
     print("=== Leann Document Search Demo (DiskANN + Recompute) ===")
     print("==========================================================")
-    
+
     INDEX_DIR = Path("./test_indices")
     INDEX_PATH = str(INDEX_DIR / "documents.diskann")
     BACKEND_TO_TEST = "diskann"
@@ -44,94 +54,96 @@ def main():
 
     # --- 1. Build index ---
     print(f"\n[PHASE 1] Building index using '{BACKEND_TO_TEST}' backend...")
-    
-    builder = LeannBuilder(
-        backend_name=BACKEND_TO_TEST, 
-        graph_degree=32, 
-        complexity=64
-    )
-    
+
+    builder = LeannBuilder(backend_name=BACKEND_TO_TEST, graph_degree=32, complexity=64)
+
     documents = load_sample_documents()
     print(f"Loaded {len(documents)} sample documents.")
     for doc in documents:
         builder.add_text(doc["content"], metadata={"title": doc["title"]})
-        
+
     builder.build_index(INDEX_PATH)
-    print(f"\nIndex built!")
+    print("\nIndex built!")
 
     # --- 2. Basic search demo ---
     print(f"\n[PHASE 2] Basic search using '{BACKEND_TO_TEST}' backend...")
     searcher = LeannSearcher(index_path=INDEX_PATH)
-    
+
     query = "What is machine learning?"
     print(f"\nQuery: '{query}'")
-    
+
     print("\n--- Basic search mode (PQ computation) ---")
     start_time = time.time()
     results = searcher.search(query, top_k=2)
     basic_time = time.time() - start_time
-    
+
     print(f"⏱️  Basic search time: {basic_time:.3f} seconds")
     print(">>> Basic search results <<<")
     for i, res in enumerate(results, 1):
-        print(f"  {i}. ID: {res.id}, Score: {res.score:.4f}, Text: '{res.text}', Metadata: {res.metadata}")
+        print(
+            f"  {i}. ID: {res.id}, Score: {res.score:.4f}, Text: '{res.text}', Metadata: {res.metadata}"
+        )
 
     # --- 3. Recompute search demo ---
-    print(f"\n[PHASE 3] Recompute search using embedding server...")
-    
+    print("\n[PHASE 3] Recompute search using embedding server...")
+
     print("\n--- Recompute search mode (get real embeddings via network) ---")
-    
+
     # Configure recompute parameters
     recompute_params = {
         "recompute_beighbor_embeddings": True,  # Enable network recomputation
-        "USE_DEFERRED_FETCH": False,           # Don't use deferred fetch
-        "skip_search_reorder": True,           # Skip search reordering
-        "dedup_node_dis": True,               # Enable node distance deduplication
-        "prune_ratio": 0.1,                   # Pruning ratio 10%
-        "batch_recompute": False,             # Don't use batch recomputation
-        "global_pruning": False,              # Don't use global pruning
-        "zmq_port": 5555,                     # ZMQ port
-        "embedding_model": "sentence-transformers/all-mpnet-base-v2"
+        "USE_DEFERRED_FETCH": False,  # Don't use deferred fetch
+        "skip_search_reorder": True,  # Skip search reordering
+        "dedup_node_dis": True,  # Enable node distance deduplication
+        "prune_ratio": 0.1,  # Pruning ratio 10%
+        "batch_recompute": False,  # Don't use batch recomputation
+        "global_pruning": False,  # Don't use global pruning
+        "zmq_port": 5555,  # ZMQ port
+        "embedding_model": "sentence-transformers/all-mpnet-base-v2",
     }
-    
+
     print("Recompute parameter configuration:")
     for key, value in recompute_params.items():
         print(f"  {key}: {value}")
-    
-    print(f"\n🔄 Executing Recompute search...")
+
+    print("\n🔄 Executing Recompute search...")
     try:
         start_time = time.time()
         recompute_results = searcher.search(query, top_k=2, **recompute_params)
         recompute_time = time.time() - start_time
-        
+
         print(f"⏱️  Recompute search time: {recompute_time:.3f} seconds")
         print(">>> Recompute search results <<<")
         for i, res in enumerate(recompute_results, 1):
-            print(f"  {i}. ID: {res.id}, Score: {res.score:.4f}, Text: '{res.text}', Metadata: {res.metadata}")
-        
+            print(
+                f"  {i}. ID: {res.id}, Score: {res.score:.4f}, Text: '{res.text}', Metadata: {res.metadata}"
+            )
+
         # Compare results
-        print(f"\n--- Result comparison ---")
+        print("\n--- Result comparison ---")
         print(f"Basic search time: {basic_time:.3f} seconds")
         print(f"Recompute time: {recompute_time:.3f} seconds")
-        
+
         print("\nBasic search vs Recompute results:")
         for i in range(min(len(results), len(recompute_results))):
             basic_score = results[i].score
             recompute_score = recompute_results[i].score
             score_diff = abs(basic_score - recompute_score)
-            print(f"  Position {i+1}: PQ={basic_score:.4f}, Recompute={recompute_score:.4f}, Difference={score_diff:.4f}")
-        
+            print(
+                f"  Position {i + 1}: PQ={basic_score:.4f}, Recompute={recompute_score:.4f}, Difference={score_diff:.4f}"
+            )
+
         if recompute_time > basic_time:
-            print(f"✅ Recompute mode working correctly (more accurate but slower)")
+            print("✅ Recompute mode working correctly (more accurate but slower)")
         else:
-            print(f"ℹ️  Recompute time is unusually fast, network recomputation may not be enabled")
-            
+            print("i️  Recompute time is unusually fast, network recomputation may not be enabled")
+
     except Exception as e:
         print(f"❌ Recompute search failed: {e}")
         print("This usually indicates an embedding server connection issue")
 
     # --- 4. Chat demo ---
-    print(f"\n[PHASE 4] Starting chat session...")
+    print("\n[PHASE 4] Starting chat session...")
     chat = LeannChat(index_path=INDEX_PATH)
     chat_response = chat.ask(query)
     print(f"You: {query}")
@@ -143,4 +155,4 @@ def main():
 
 
 if __name__ == "__main__":
-    main()
+    main()

examples/email_data/LEANN_email_reader.py

@@ -1,11 +1,13 @@
-import os
 import email
+import os
 from pathlib import Path
-from typing import List, Any
+from typing import Any
+
 from llama_index.core import Document
 from llama_index.core.readers.base import BaseReader
 
-def find_all_messages_directories(root: str = None) -> List[Path]:
+
+def find_all_messages_directories(root: str | None = None) -> list[Path]:
     """
     Recursively find all 'Messages' directories under the given root.
     Returns a list of Path objects.
@@ -14,86 +16,97 @@ def find_all_messages_directories(root: str = None) -> List[Path]:
         # Auto-detect user's mail path
         home_dir = os.path.expanduser("~")
         root = os.path.join(home_dir, "Library", "Mail")
-    
+
     messages_dirs = []
-    for dirpath, dirnames, filenames in os.walk(root):
+    for dirpath, _dirnames, _filenames in os.walk(root):
         if os.path.basename(dirpath) == "Messages":
             messages_dirs.append(Path(dirpath))
     return messages_dirs
 
+
 class EmlxReader(BaseReader):
     """
     Apple Mail .emlx file reader with embedded metadata.
-    
+
     Reads individual .emlx files from Apple Mail's storage format.
     """
-    
+
     def __init__(self, include_html: bool = False) -> None:
         """
         Initialize.
-        
+
         Args:
             include_html: Whether to include HTML content in the email body (default: False)
         """
         self.include_html = include_html
-    
-    def load_data(self, input_dir: str, **load_kwargs: Any) -> List[Document]:
+
+    def load_data(self, input_dir: str, **load_kwargs: Any) -> list[Document]:
         """
         Load data from the input directory containing .emlx files.
-        
+
         Args:
             input_dir: Directory containing .emlx files
             **load_kwargs:
                 max_count (int): Maximum amount of messages to read.
         """
-        docs: List[Document] = []
-        max_count = load_kwargs.get('max_count', 1000)
+        docs: list[Document] = []
+        max_count = load_kwargs.get("max_count", 1000)
         count = 0
-        
+
         # Walk through the directory recursively
         for dirpath, dirnames, filenames in os.walk(input_dir):
             # Skip hidden directories
             dirnames[:] = [d for d in dirnames if not d.startswith(".")]
-            
+
             for filename in filenames:
                 if count >= max_count:
                     break
-                    
+
                 if filename.endswith(".emlx"):
                     filepath = os.path.join(dirpath, filename)
                     try:
                         # Read the .emlx file
-                        with open(filepath, 'r', encoding='utf-8', errors='ignore') as f:
+                        with open(filepath, encoding="utf-8", errors="ignore") as f:
                             content = f.read()
-                        
+
                         # .emlx files have a length prefix followed by the email content
                         # The first line contains the length, followed by the email
-                        lines = content.split('\n', 1)
+                        lines = content.split("\n", 1)
                         if len(lines) >= 2:
                             email_content = lines[1]
-                            
+
                             # Parse the email using Python's email module
                             try:
                                 msg = email.message_from_string(email_content)
-                                
+
                                 # Extract email metadata
-                                subject = msg.get('Subject', 'No Subject')
-                                from_addr = msg.get('From', 'Unknown')
-                                to_addr = msg.get('To', 'Unknown')
-                                date = msg.get('Date', 'Unknown')
-                                
+                                subject = msg.get("Subject", "No Subject")
+                                from_addr = msg.get("From", "Unknown")
+                                to_addr = msg.get("To", "Unknown")
+                                date = msg.get("Date", "Unknown")
+
                                 # Extract email body
                                 body = ""
                                 if msg.is_multipart():
                                     for part in msg.walk():
-                                        if part.get_content_type() == "text/plain" or part.get_content_type() == "text/html":
-                                            if part.get_content_type() == "text/html" and not self.include_html:
+                                        if (
+                                            part.get_content_type() == "text/plain"
+                                            or part.get_content_type() == "text/html"
+                                        ):
+                                            if (
+                                                part.get_content_type() == "text/html"
+                                                and not self.include_html
+                                            ):
                                                 continue
-                                            body += part.get_payload(decode=True).decode('utf-8', errors='ignore')
+                                            body += part.get_payload(decode=True).decode(
+                                                "utf-8", errors="ignore"
+                                            )
                                             # break
                                 else:
-                                    body = msg.get_payload(decode=True).decode('utf-8', errors='ignore')
-                                
+                                    body = msg.get_payload(decode=True).decode(
+                                        "utf-8", errors="ignore"
+                                    )
+
                                 # Create document content with metadata embedded in text
                                 doc_content = f"""
 [File]: {filename}
@@ -104,19 +117,19 @@ class EmlxReader(BaseReader):
 [EMAIL BODY Start]:
 {body}
 """
-                                
+
                                 # No separate metadata - everything is in the text
                                 doc = Document(text=doc_content, metadata={})
                                 docs.append(doc)
                                 count += 1
-                                
+
                             except Exception as e:
                                 print(f"Error parsing email from {filepath}: {e}")
                                 continue
-                                
+
                     except Exception as e:
                         print(f"Error reading file {filepath}: {e}")
                         continue
-        
+
         print(f"Loaded {len(docs)} email documents")
-        return docs 
+        return docs

examples/email_data/email.py

@@ -7,9 +7,9 @@ Contains simple parser for mbox files.
 
 import logging
 from pathlib import Path
-from typing import Any, Dict, List, Optional
-from fsspec import AbstractFileSystem
+from typing import Any
 
+from fsspec import AbstractFileSystem
 from llama_index.core.readers.base import BaseReader
 from llama_index.core.schema import Document
 
@@ -27,11 +27,7 @@ class MboxReader(BaseReader):
     """
 
     DEFAULT_MESSAGE_FORMAT: str = (
-        "Date: {_date}\n"
-        "From: {_from}\n"
-        "To: {_to}\n"
-        "Subject: {_subject}\n"
-        "Content: {_content}"
+        "Date: {_date}\nFrom: {_from}\nTo: {_to}\nSubject: {_subject}\nContent: {_content}"
     )
 
     def __init__(
@@ -45,9 +41,7 @@ class MboxReader(BaseReader):
         try:
             from bs4 import BeautifulSoup  # noqa
         except ImportError:
-            raise ImportError(
-                "`beautifulsoup4` package not found: `pip install beautifulsoup4`"
-            )
+            raise ImportError("`beautifulsoup4` package not found: `pip install beautifulsoup4`")
 
         super().__init__(*args, **kwargs)
         self.max_count = max_count
@@ -56,9 +50,9 @@ class MboxReader(BaseReader):
     def load_data(
         self,
         file: Path,
-        extra_info: Optional[Dict] = None,
-        fs: Optional[AbstractFileSystem] = None,
-    ) -> List[Document]:
+        extra_info: dict | None = None,
+        fs: AbstractFileSystem | None = None,
+    ) -> list[Document]:
         """Parse file into string."""
         # Import required libraries
         import mailbox
@@ -74,7 +68,7 @@ class MboxReader(BaseReader):
             )
 
         i = 0
-        results: List[str] = []
+        results: list[str] = []
         # Load file using mailbox
         bytes_parser = BytesParser(policy=default).parse
         mbox = mailbox.mbox(file, factory=bytes_parser)  # type: ignore
@@ -124,7 +118,7 @@ class MboxReader(BaseReader):
 class EmlxMboxReader(MboxReader):
     """
     EmlxMboxReader - Modified MboxReader that handles directories of .emlx files.
-    
+
     Extends MboxReader to work with Apple Mail's .emlx format by:
     1. Reading .emlx files from a directory
     2. Converting them to mbox format in memory
@@ -134,13 +128,13 @@ class EmlxMboxReader(MboxReader):
     def load_data(
         self,
         directory: Path,
-        extra_info: Optional[Dict] = None,
-        fs: Optional[AbstractFileSystem] = None,
-    ) -> List[Document]:
+        extra_info: dict | None = None,
+        fs: AbstractFileSystem | None = None,
+    ) -> list[Document]:
         """Parse .emlx files from directory into strings using MboxReader logic."""
-        import tempfile
         import os
-        
+        import tempfile
+
         if fs:
             logger.warning(
                 "fs was specified but EmlxMboxReader doesn't support loading "
@@ -150,37 +144,37 @@ class EmlxMboxReader(MboxReader):
         # Find all .emlx files in the directory
         emlx_files = list(directory.glob("*.emlx"))
         logger.info(f"Found {len(emlx_files)} .emlx files in {directory}")
-        
+
         if not emlx_files:
             logger.warning(f"No .emlx files found in {directory}")
             return []
 
         # Create a temporary mbox file
-        with tempfile.NamedTemporaryFile(mode='w', suffix='.mbox', delete=False) as temp_mbox:
+        with tempfile.NamedTemporaryFile(mode="w", suffix=".mbox", delete=False) as temp_mbox:
             temp_mbox_path = temp_mbox.name
-            
+
             # Convert .emlx files to mbox format
             for emlx_file in emlx_files:
                 try:
                     # Read the .emlx file
-                    with open(emlx_file, 'r', encoding='utf-8', errors='ignore') as f:
+                    with open(emlx_file, encoding="utf-8", errors="ignore") as f:
                         content = f.read()
-                    
+
                     # .emlx format: first line is length, rest is email content
-                    lines = content.split('\n', 1)
+                    lines = content.split("\n", 1)
                     if len(lines) >= 2:
                         email_content = lines[1]  # Skip the length line
-                        
+
                         # Write to mbox format (each message starts with "From " and ends with blank line)
                         temp_mbox.write(f"From {emlx_file.name} {email_content}\n\n")
-                    
+
                 except Exception as e:
                     logger.warning(f"Failed to process {emlx_file}: {e}")
                     continue
-            
+
             # Close the temporary file so MboxReader can read it
             temp_mbox.close()
-            
+
             try:
                 # Use the parent MboxReader's logic to parse the mbox file
                 return super().load_data(Path(temp_mbox_path), extra_info, fs)
@@ -188,5 +182,5 @@ class EmlxMboxReader(MboxReader):
                 # Clean up temporary file
                 try:
                     os.unlink(temp_mbox_path)
-                except:
-                    pass
+                except OSError:
+                    pass

examples/faiss_only.py

@@ -1,11 +1,11 @@
 #!/usr/bin/env python3
 """Test only Faiss HNSW"""
 
+import os
 import sys
 import time
+
 import psutil
-import gc
-import os
 
 
 def get_memory_usage():
@@ -37,20 +37,20 @@ def main():
         import faiss
     except ImportError:
         print("Faiss is not installed.")
-        print("Please install it with `uv pip install faiss-cpu` and you can  then run this script again")
+        print(
+            "Please install it with `uv pip install faiss-cpu` and you can  then run this script again"
+        )
         sys.exit(1)
 
     from llama_index.core import (
-        SimpleDirectoryReader,
-        VectorStoreIndex,
-        StorageContext,
         Settings,
-        node_parser,
-        Document,
+        SimpleDirectoryReader,
+        StorageContext,
+        VectorStoreIndex,
     )
     from llama_index.core.node_parser import SentenceSplitter
-    from llama_index.vector_stores.faiss import FaissVectorStore
     from llama_index.embeddings.huggingface import HuggingFaceEmbedding
+    from llama_index.vector_stores.faiss import FaissVectorStore
 
     tracker = MemoryTracker("Faiss HNSW")
     tracker.checkpoint("Initial")
@@ -90,8 +90,9 @@ def main():
                 vector_store=vector_store, persist_dir="./storage_faiss"
             )
             from llama_index.core import load_index_from_storage
+
             index = load_index_from_storage(storage_context=storage_context)
-            print(f"Index loaded from ./storage_faiss")
+            print("Index loaded from ./storage_faiss")
             tracker.checkpoint("After loading existing index")
             index_loaded = True
         except Exception as e:
@@ -99,19 +100,18 @@ def main():
             print("Cleaning up corrupted index and building new one...")
             # Clean up corrupted index
             import shutil
+
             if os.path.exists("./storage_faiss"):
                 shutil.rmtree("./storage_faiss")
-    
+
     if not index_loaded:
         print("Building new Faiss HNSW index...")
-        
+
         # Use the correct Faiss building pattern from the example
         vector_store = FaissVectorStore(faiss_index=faiss_index)
         storage_context = StorageContext.from_defaults(vector_store=vector_store)
         index = VectorStoreIndex.from_documents(
-            documents, 
-            storage_context=storage_context,
-            transformations=[node_parser]
+            documents, storage_context=storage_context, transformations=[node_parser]
         )
         tracker.checkpoint("After index building")
 
@@ -124,10 +124,10 @@ def main():
     runtime_start_mem = get_memory_usage()
     print(f"Before load memory: {runtime_start_mem:.1f} MB")
     tracker.checkpoint("Before load memory")
-    
+
     query_engine = index.as_query_engine(similarity_top_k=20)
     queries = [
-        "什么是盘古大模型以及盘古开发过程中遇到了什么阴暗面，任务令一般在什么城市颁发",
+        "什么是盘古大模型以及盘古开发过程中遇到了什么阴暗面,任务令一般在什么城市颁发",
         "What is LEANN and how does it work?",
         "华为诺亚方舟实验室的主要研究内容",
     ]
@@ -141,7 +141,7 @@ def main():
 
     runtime_end_mem = get_memory_usage()
     runtime_overhead = runtime_end_mem - runtime_start_mem
-    
+
     peak_memory = tracker.summary()
     print(f"Peak Memory: {peak_memory:.1f} MB")
     print(f"Runtime Memory Overhead: {runtime_overhead:.1f} MB")

examples/google_history_reader_leann.py

@@ -1,15 +1,17 @@
-import os
-import asyncio
 import argparse
+import asyncio
+import os
+
 try:
     import dotenv
+
     dotenv.load_dotenv()
 except ModuleNotFoundError:
     # python-dotenv is not installed; skip loading environment variables
     dotenv = None
 from pathlib import Path
-from typing import List, Any
-from leann.api import LeannBuilder, LeannSearcher, LeannChat
+
+from leann.api import LeannBuilder, LeannChat
 from llama_index.core.node_parser import SentenceSplitter
 
 # dotenv.load_dotenv()  # handled above if python-dotenv is available
@@ -17,42 +19,47 @@ from llama_index.core.node_parser import SentenceSplitter
 # Default Chrome profile path
 DEFAULT_CHROME_PROFILE = os.path.expanduser("~/Library/Application Support/Google/Chrome/Default")
 
-def create_leann_index_from_multiple_chrome_profiles(profile_dirs: List[Path], index_path: str = "chrome_history_index.leann", max_count: int = -1):
+
+def create_leann_index_from_multiple_chrome_profiles(
+    profile_dirs: list[Path],
+    index_path: str = "chrome_history_index.leann",
+    max_count: int = -1,
+):
     """
     Create LEANN index from multiple Chrome profile data sources.
-    
+
     Args:
         profile_dirs: List of Path objects pointing to Chrome profile directories
         index_path: Path to save the LEANN index
         max_count: Maximum number of history entries to process per profile
     """
     print("Creating LEANN index from multiple Chrome profile data sources...")
-    
+
     # Load documents using ChromeHistoryReader from history_data
     from history_data.history import ChromeHistoryReader
+
     reader = ChromeHistoryReader()
-    
+
     INDEX_DIR = Path(index_path).parent
-    
+
     if not INDEX_DIR.exists():
-        print(f"--- Index directory not found, building new index ---")
+        print("--- Index directory not found, building new index ---")
         all_documents = []
         total_processed = 0
-        
+
         # Process each Chrome profile directory
         for i, profile_dir in enumerate(profile_dirs):
-            print(f"\nProcessing Chrome profile {i+1}/{len(profile_dirs)}: {profile_dir}")
-            
+            print(f"\nProcessing Chrome profile {i + 1}/{len(profile_dirs)}: {profile_dir}")
+
             try:
                 documents = reader.load_data(
-                    chrome_profile_path=str(profile_dir),
-                    max_count=max_count
+                    chrome_profile_path=str(profile_dir), max_count=max_count
                 )
                 if documents:
                     print(f"Loaded {len(documents)} history documents from {profile_dir}")
                     all_documents.extend(documents)
                     total_processed += len(documents)
-                    
+
                     # Check if we've reached the max count
                     if max_count > 0 and total_processed >= max_count:
                         print(f"Reached max count of {max_count} documents")
@@ -62,18 +69,22 @@ def create_leann_index_from_multiple_chrome_profiles(profile_dirs: List[Path], i
             except Exception as e:
                 print(f"Error processing {profile_dir}: {e}")
                 continue
-        
+
         if not all_documents:
             print("No documents loaded from any source. Exiting.")
             # highlight info that you need to close all chrome browser before running this script and high light the instruction!!
-            print("\033[91mYou need to close or quit all chrome browser before running this script\033[0m")
+            print(
+                "\033[91mYou need to close or quit all chrome browser before running this script\033[0m"
+            )
             return None
-        
-        print(f"\nTotal loaded {len(all_documents)} history documents from {len(profile_dirs)} profiles")
-        
+
+        print(
+            f"\nTotal loaded {len(all_documents)} history documents from {len(profile_dirs)} profiles"
+        )
+
         # Create text splitter with 256 chunk size
         text_splitter = SentenceSplitter(chunk_size=256, chunk_overlap=128)
-        
+
         # Convert Documents to text strings and chunk them
         all_texts = []
         for doc in all_documents:
@@ -83,45 +94,48 @@ def create_leann_index_from_multiple_chrome_profiles(profile_dirs: List[Path], i
                 text = node.get_content()
                 # text = '[Title] ' + doc.metadata["title"] + '\n' + text
                 all_texts.append(text)
-        
+
         print(f"Created {len(all_texts)} text chunks from {len(all_documents)} documents")
-        
+
         # Create LEANN index directory
-        print(f"--- Index directory not found, building new index ---")
+        print("--- Index directory not found, building new index ---")
         INDEX_DIR.mkdir(exist_ok=True)
 
-        print(f"--- Building new LEANN index ---")
-        
-        print(f"\n[PHASE 1] Building Leann index...")
+        print("--- Building new LEANN index ---")
+
+        print("\n[PHASE 1] Building Leann index...")
 
         # Use HNSW backend for better macOS compatibility
         builder = LeannBuilder(
             backend_name="hnsw",
-            embedding_model="text-embedding-3-small",
-            embedding_mode="openai",
-            
-            graph_degree=32, 
+            embedding_model="facebook/contriever",
+            graph_degree=32,
             complexity=64,
-            is_compact=False,
-            is_recompute=False,
-            num_threads=1  # Force single-threaded mode
+            is_compact=True,
+            is_recompute=True,
+            num_threads=1,  # Force single-threaded mode
         )
 
         print(f"Adding {len(all_texts)} history chunks to index...")
         for chunk_text in all_texts:
             builder.add_text(chunk_text)
-            
+
         builder.build_index(index_path)
         print(f"\nLEANN index built at {index_path}!")
     else:
         print(f"--- Using existing index at {INDEX_DIR} ---")
-    
+
     return index_path
 
-def create_leann_index(profile_path: str = None, index_path: str = "chrome_history_index.leann", max_count: int = 1000):
+
+def create_leann_index(
+    profile_path: str | None = None,
+    index_path: str = "chrome_history_index.leann",
+    max_count: int = 1000,
+):
     """
     Create LEANN index from Chrome history data.
-    
+
     Args:
         profile_path: Path to the Chrome profile directory (optional, uses default if None)
         index_path: Path to save the LEANN index
@@ -129,33 +143,31 @@ def create_leann_index(profile_path: str = None, index_path: str = "chrome_histo
     """
     print("Creating LEANN index from Chrome history data...")
     INDEX_DIR = Path(index_path).parent
-    
+
     if not INDEX_DIR.exists():
-        print(f"--- Index directory not found, building new index ---")
+        print("--- Index directory not found, building new index ---")
         INDEX_DIR.mkdir(exist_ok=True)
 
-        print(f"--- Building new LEANN index ---")
-        
-        print(f"\n[PHASE 1] Building Leann index...")
+        print("--- Building new LEANN index ---")
+
+        print("\n[PHASE 1] Building Leann index...")
 
         # Load documents using ChromeHistoryReader from history_data
         from history_data.history import ChromeHistoryReader
+
         reader = ChromeHistoryReader()
-        
-        documents = reader.load_data(
-            chrome_profile_path=profile_path,
-            max_count=max_count
-        )
-        
+
+        documents = reader.load_data(chrome_profile_path=profile_path, max_count=max_count)
+
         if not documents:
             print("No documents loaded. Exiting.")
             return None
-        
+
         print(f"Loaded {len(documents)} history documents")
-        
+
         # Create text splitter with 256 chunk size
         text_splitter = SentenceSplitter(chunk_size=256, chunk_overlap=25)
-        
+
         # Convert Documents to text strings and chunk them
         all_texts = []
         for doc in documents:
@@ -163,54 +175,55 @@ def create_leann_index(profile_path: str = None, index_path: str = "chrome_histo
             nodes = text_splitter.get_nodes_from_documents([doc])
             for node in nodes:
                 all_texts.append(node.get_content())
-        
+
         print(f"Created {len(all_texts)} text chunks from {len(documents)} documents")
-        
+
         # Create LEANN index directory
-        print(f"--- Index directory not found, building new index ---")
+        print("--- Index directory not found, building new index ---")
         INDEX_DIR.mkdir(exist_ok=True)
 
-        print(f"--- Building new LEANN index ---")
-        
-        print(f"\n[PHASE 1] Building Leann index...")
+        print("--- Building new LEANN index ---")
+
+        print("\n[PHASE 1] Building Leann index...")
 
         # Use HNSW backend for better macOS compatibility
         builder = LeannBuilder(
             backend_name="hnsw",
             embedding_model="facebook/contriever",
-            graph_degree=32, 
+            graph_degree=32,
             complexity=64,
             is_compact=True,
             is_recompute=True,
-            num_threads=1  # Force single-threaded mode
+            num_threads=1,  # Force single-threaded mode
         )
 
         print(f"Adding {len(all_texts)} history chunks to index...")
         for chunk_text in all_texts:
             builder.add_text(chunk_text)
-            
+
         builder.build_index(index_path)
         print(f"\nLEANN index built at {index_path}!")
     else:
         print(f"--- Using existing index at {INDEX_DIR} ---")
-    
+
     return index_path
 
+
 async def query_leann_index(index_path: str, query: str):
     """
     Query the LEANN index.
-    
+
     Args:
         index_path: Path to the LEANN index
         query: The query string
     """
-    print(f"\n[PHASE 2] Starting Leann chat session...")
+    print("\n[PHASE 2] Starting Leann chat session...")
     chat = LeannChat(index_path=index_path)
-    
+
     print(f"You: {query}")
     chat_response = chat.ask(
-        query, 
-        top_k=10, 
+        query,
+        top_k=10,
         recompute_beighbor_embeddings=True,
         complexity=32,
         beam_width=1,
@@ -219,40 +232,60 @@ async def query_leann_index(index_path: str, query: str):
             "model": "gpt-4o",
             "api_key": os.getenv("OPENAI_API_KEY"),
         },
-        llm_kwargs={
-            "temperature": 0.0,
-            "max_tokens": 1000
-        }
+        llm_kwargs={"temperature": 0.0, "max_tokens": 1000},
     )
 
     print(f"Leann chat response: \033[36m{chat_response}\033[0m")
 
+
 async def main():
     # Parse command line arguments
-    parser = argparse.ArgumentParser(description='LEANN Chrome History Reader - Create and query browser history index')
-    parser.add_argument('--chrome-profile', type=str, default=DEFAULT_CHROME_PROFILE,
-                       help=f'Path to Chrome profile directory (default: {DEFAULT_CHROME_PROFILE}), usually you dont need to change this')
-    parser.add_argument('--index-dir', type=str, default="./google_history_index",
-                       help='Directory to store the LEANN index (default: ./chrome_history_index_leann_test)')
-    parser.add_argument('--max-entries', type=int, default=1000,
-                       help='Maximum number of history entries to process (default: 1000)')
-    parser.add_argument('--query', type=str, default=None,
-                       help='Single query to run (default: runs example queries)')
-    parser.add_argument('--auto-find-profiles', action='store_true', default=True,
-                       help='Automatically find all Chrome profiles (default: True)')
-    
+    parser = argparse.ArgumentParser(
+        description="LEANN Chrome History Reader - Create and query browser history index"
+    )
+    parser.add_argument(
+        "--chrome-profile",
+        type=str,
+        default=DEFAULT_CHROME_PROFILE,
+        help=f"Path to Chrome profile directory (default: {DEFAULT_CHROME_PROFILE}), usually you dont need to change this",
+    )
+    parser.add_argument(
+        "--index-dir",
+        type=str,
+        default="./google_history_index",
+        help="Directory to store the LEANN index (default: ./chrome_history_index_leann_test)",
+    )
+    parser.add_argument(
+        "--max-entries",
+        type=int,
+        default=1000,
+        help="Maximum number of history entries to process (default: 1000)",
+    )
+    parser.add_argument(
+        "--query",
+        type=str,
+        default=None,
+        help="Single query to run (default: runs example queries)",
+    )
+    parser.add_argument(
+        "--auto-find-profiles",
+        action="store_true",
+        default=True,
+        help="Automatically find all Chrome profiles (default: True)",
+    )
+
     args = parser.parse_args()
-    
+
     INDEX_DIR = Path(args.index_dir)
     INDEX_PATH = str(INDEX_DIR / "chrome_history.leann")
-    
+
     print(f"Using Chrome profile: {args.chrome_profile}")
     print(f"Index directory: {INDEX_DIR}")
     print(f"Max entries: {args.max_entries}")
-    
+
     # Find Chrome profile directories
     from history_data.history import ChromeHistoryReader
-    
+
     if args.auto_find_profiles:
         profile_dirs = ChromeHistoryReader.find_chrome_profiles()
         if not profile_dirs:
@@ -265,10 +298,12 @@ async def main():
             print(f"Chrome profile not found: {profile_path}")
             return
         profile_dirs = [profile_path]
-    
+
     # Create or load the LEANN index from all sources
-    index_path = create_leann_index_from_multiple_chrome_profiles(profile_dirs, INDEX_PATH, args.max_entries)
-    
+    index_path = create_leann_index_from_multiple_chrome_profiles(
+        profile_dirs, INDEX_PATH, args.max_entries
+    )
+
     if index_path:
         if args.query:
             # Run single query
@@ -277,12 +312,13 @@ async def main():
             # Example queries
             queries = [
                 "What websites did I visit about machine learning?",
-                "Find my search history about programming"
+                "Find my search history about programming",
             ]
-            
+
             for query in queries:
-                print("\n" + "="*60)
+                print("\n" + "=" * 60)
                 await query_leann_index(index_path, query)
 
+
 if __name__ == "__main__":
-    asyncio.run(main()) 
+    asyncio.run(main())

examples/history_data/__init__.py

@@ -1,3 +1,3 @@
 from .history import ChromeHistoryReader
 
-__all__ = ['ChromeHistoryReader'] 
+__all__ = ["ChromeHistoryReader"]

examples/history_data/history.py

@@ -1,77 +1,81 @@
-import sqlite3
 import os
+import sqlite3
 from pathlib import Path
-from typing import List, Any
+from typing import Any
+
 from llama_index.core import Document
 from llama_index.core.readers.base import BaseReader
 
+
 class ChromeHistoryReader(BaseReader):
     """
     Chrome browser history reader that extracts browsing data from SQLite database.
-    
+
     Reads Chrome history from the default Chrome profile location and creates documents
     with embedded metadata similar to the email reader structure.
     """
-    
+
     def __init__(self) -> None:
         """Initialize."""
         pass
-    
-    def load_data(self, input_dir: str = None, **load_kwargs: Any) -> List[Document]:
+
+    def load_data(self, input_dir: str | None = None, **load_kwargs: Any) -> list[Document]:
         """
         Load Chrome history data from the default Chrome profile location.
-        
+
         Args:
             input_dir: Not used for Chrome history (kept for compatibility)
             **load_kwargs:
                 max_count (int): Maximum amount of history entries to read.
                 chrome_profile_path (str): Custom path to Chrome profile directory.
         """
-        docs: List[Document] = []
-        max_count = load_kwargs.get('max_count', 1000)
-        chrome_profile_path = load_kwargs.get('chrome_profile_path', None)
-        
+        docs: list[Document] = []
+        max_count = load_kwargs.get("max_count", 1000)
+        chrome_profile_path = load_kwargs.get("chrome_profile_path", None)
+
         # Default Chrome profile path on macOS
         if chrome_profile_path is None:
-            chrome_profile_path = os.path.expanduser("~/Library/Application Support/Google/Chrome/Default")
-        
+            chrome_profile_path = os.path.expanduser(
+                "~/Library/Application Support/Google/Chrome/Default"
+            )
+
         history_db_path = os.path.join(chrome_profile_path, "History")
-        
+
         if not os.path.exists(history_db_path):
             print(f"Chrome history database not found at: {history_db_path}")
             return docs
-        
+
         try:
             # Connect to the Chrome history database
             print(f"Connecting to database: {history_db_path}")
             conn = sqlite3.connect(history_db_path)
             cursor = conn.cursor()
-            
+
             # Query to get browsing history with metadata (removed created_time column)
             query = """
-            SELECT 
+            SELECT
                 datetime(last_visit_time/1000000-11644473600,'unixepoch','localtime') as last_visit,
-                url, 
-                title, 
-                visit_count, 
-                typed_count, 
+                url,
+                title,
+                visit_count,
+                typed_count,
                 hidden
-            FROM urls 
+            FROM urls
             ORDER BY last_visit_time DESC
             """
-            
+
             print(f"Executing query on database: {history_db_path}")
             cursor.execute(query)
             rows = cursor.fetchall()
             print(f"Query returned {len(rows)} rows")
-            
+
             count = 0
             for row in rows:
                 if count >= max_count and max_count > 0:
                     break
-                
+
                 last_visit, url, title, visit_count, typed_count, hidden = row
-                
+
                 # Create document content with metadata embedded in text
                 doc_content = f"""
 [Title]: {title}
@@ -80,38 +84,38 @@ class ChromeHistoryReader(BaseReader):
 [Visit times]: {visit_count}
 [Typed times]: {typed_count}
 """
-                
+
                 # Create document with embedded metadata
-                doc = Document(text=doc_content, metadata={ "title": title[0:150]})
+                doc = Document(text=doc_content, metadata={"title": title[0:150]})
                 # if len(title) > 150:
                 #     print(f"Title is too long: {title}")
                 docs.append(doc)
                 count += 1
-            
+
             conn.close()
             print(f"Loaded {len(docs)} Chrome history documents")
-            
+
         except Exception as e:
             print(f"Error reading Chrome history: {e}")
             return docs
-        
+
         return docs
 
     @staticmethod
-    def find_chrome_profiles() -> List[Path]:
+    def find_chrome_profiles() -> list[Path]:
         """
         Find all Chrome profile directories.
-        
+
         Returns:
             List of Path objects pointing to Chrome profile directories
         """
         chrome_base_path = Path(os.path.expanduser("~/Library/Application Support/Google/Chrome"))
         profile_dirs = []
-        
+
         if not chrome_base_path.exists():
             print(f"Chrome directory not found at: {chrome_base_path}")
             return profile_dirs
-        
+
         # Find all profile directories
         for profile_dir in chrome_base_path.iterdir():
             if profile_dir.is_dir() and profile_dir.name != "System Profile":
@@ -119,53 +123,59 @@ class ChromeHistoryReader(BaseReader):
                 if history_path.exists():
                     profile_dirs.append(profile_dir)
                     print(f"Found Chrome profile: {profile_dir}")
-        
+
         print(f"Found {len(profile_dirs)} Chrome profiles")
         return profile_dirs
 
     @staticmethod
-    def export_history_to_file(output_file: str = "chrome_history_export.txt", max_count: int = 1000):
+    def export_history_to_file(
+        output_file: str = "chrome_history_export.txt", max_count: int = 1000
+    ):
         """
         Export Chrome history to a text file using the same SQL query format.
-        
+
         Args:
             output_file: Path to the output file
             max_count: Maximum number of entries to export
         """
-        chrome_profile_path = os.path.expanduser("~/Library/Application Support/Google/Chrome/Default")
+        chrome_profile_path = os.path.expanduser(
+            "~/Library/Application Support/Google/Chrome/Default"
+        )
         history_db_path = os.path.join(chrome_profile_path, "History")
-        
+
         if not os.path.exists(history_db_path):
             print(f"Chrome history database not found at: {history_db_path}")
             return
-        
+
         try:
             conn = sqlite3.connect(history_db_path)
             cursor = conn.cursor()
-            
+
             query = """
-            SELECT 
+            SELECT
                 datetime(last_visit_time/1000000-11644473600,'unixepoch','localtime') as last_visit,
-                url, 
-                title, 
-                visit_count, 
-                typed_count, 
+                url,
+                title,
+                visit_count,
+                typed_count,
                 hidden
-            FROM urls 
+            FROM urls
             ORDER BY last_visit_time DESC
             LIMIT ?
             """
-            
+
             cursor.execute(query, (max_count,))
             rows = cursor.fetchall()
-            
-            with open(output_file, 'w', encoding='utf-8') as f:
+
+            with open(output_file, "w", encoding="utf-8") as f:
                 for row in rows:
                     last_visit, url, title, visit_count, typed_count, hidden = row
-                    f.write(f"{last_visit}\t{url}\t{title}\t{visit_count}\t{typed_count}\t{hidden}\n")
-            
+                    f.write(
+                        f"{last_visit}\t{url}\t{title}\t{visit_count}\t{typed_count}\t{hidden}\n"
+                    )
+
             conn.close()
             print(f"Exported {len(rows)} history entries to {output_file}")
-            
+
         except Exception as e:
-            print(f"Error exporting Chrome history: {e}") 
+            print(f"Error exporting Chrome history: {e}")

examples/history_data/wechat_history.py

@@ -2,30 +2,31 @@ import json
 import os
 import re
 import subprocess
-import sys
 import time
+from datetime import datetime
 from pathlib import Path
-from typing import List, Any, Dict, Optional
+from typing import Any
+
 from llama_index.core import Document
 from llama_index.core.readers.base import BaseReader
-from datetime import datetime
+
 
 class WeChatHistoryReader(BaseReader):
     """
     WeChat chat history reader that extracts chat data from exported JSON files.
-    
+
     Reads WeChat chat history from exported JSON files (from wechat-exporter tool)
     and creates documents with embedded metadata similar to the Chrome history reader structure.
-    
+
     Also includes utilities for automatic WeChat chat history export.
     """
-    
+
     def __init__(self) -> None:
         """Initialize."""
         self.packages_dir = Path(__file__).parent.parent.parent / "packages"
         self.wechat_exporter_dir = self.packages_dir / "wechat-exporter"
         self.wechat_decipher_dir = self.packages_dir / "wechat-decipher-macos"
-    
+
     def check_wechat_running(self) -> bool:
         """Check if WeChat is currently running."""
         try:
@@ -33,24 +34,30 @@ class WeChatHistoryReader(BaseReader):
             return result.returncode == 0
         except Exception:
             return False
-    
+
     def install_wechattweak(self) -> bool:
         """Install WeChatTweak CLI tool."""
         try:
             # Create wechat-exporter directory if it doesn't exist
             self.wechat_exporter_dir.mkdir(parents=True, exist_ok=True)
-            
+
             wechattweak_path = self.wechat_exporter_dir / "wechattweak-cli"
             if not wechattweak_path.exists():
                 print("Downloading WeChatTweak CLI...")
-                subprocess.run([
-                    "curl", "-L", "-o", str(wechattweak_path),
-                    "https://github.com/JettChenT/WeChatTweak-CLI/releases/latest/download/wechattweak-cli"
-                ], check=True)
-            
+                subprocess.run(
+                    [
+                        "curl",
+                        "-L",
+                        "-o",
+                        str(wechattweak_path),
+                        "https://github.com/JettChenT/WeChatTweak-CLI/releases/latest/download/wechattweak-cli",
+                    ],
+                    check=True,
+                )
+
             # Make executable
             wechattweak_path.chmod(0o755)
-            
+
             # Install WeChatTweak
             print("Installing WeChatTweak...")
             subprocess.run(["sudo", str(wechattweak_path), "install"], check=True)
@@ -58,7 +65,7 @@ class WeChatHistoryReader(BaseReader):
         except Exception as e:
             print(f"Error installing WeChatTweak: {e}")
             return False
-    
+
     def restart_wechat(self):
         """Restart WeChat to apply WeChatTweak."""
         try:
@@ -69,302 +76,325 @@ class WeChatHistoryReader(BaseReader):
             time.sleep(5)  # Wait for WeChat to start
         except Exception as e:
             print(f"Error restarting WeChat: {e}")
-    
+
     def check_api_available(self) -> bool:
         """Check if WeChatTweak API is available."""
         try:
-            result = subprocess.run([
-                "curl", "-s", "http://localhost:48065/wechat/allcontacts"
-            ], capture_output=True, text=True, timeout=5)
+            result = subprocess.run(
+                ["curl", "-s", "http://localhost:48065/wechat/allcontacts"],
+                capture_output=True,
+                text=True,
+                timeout=5,
+            )
             return result.returncode == 0 and result.stdout.strip()
         except Exception:
             return False
-    
 
-
-    
     def _extract_readable_text(self, content: str) -> str:
         """
         Extract readable text from message content, removing XML and system messages.
-        
+
         Args:
             content: The raw message content (can be string or dict)
-            
+
         Returns:
             Cleaned, readable text
         """
         if not content:
             return ""
-        
+
         # Handle dictionary content (like quoted messages)
         if isinstance(content, dict):
             # Extract text from dictionary structure
             text_parts = []
-            if 'title' in content:
-                text_parts.append(str(content['title']))
-            if 'quoted' in content:
-                text_parts.append(str(content['quoted']))
-            if 'content' in content:
-                text_parts.append(str(content['content']))
-            if 'text' in content:
-                text_parts.append(str(content['text']))
-            
+            if "title" in content:
+                text_parts.append(str(content["title"]))
+            if "quoted" in content:
+                text_parts.append(str(content["quoted"]))
+            if "content" in content:
+                text_parts.append(str(content["content"]))
+            if "text" in content:
+                text_parts.append(str(content["text"]))
+
             if text_parts:
                 return " | ".join(text_parts)
             else:
                 # If we can't extract meaningful text from dict, return empty
                 return ""
-        
+
         # Handle string content
         if not isinstance(content, str):
             return ""
-        
+
         # Remove common prefixes like "wxid_xxx:\n"
-        clean_content = re.sub(r'^wxid_[^:]+:\s*', '', content)
-        clean_content = re.sub(r'^[^:]+:\s*', '', clean_content)
-        
+        clean_content = re.sub(r"^wxid_[^:]+:\s*", "", content)
+        clean_content = re.sub(r"^[^:]+:\s*", "", clean_content)
+
         # If it's just XML or system message, return empty
-        if clean_content.strip().startswith('<') or 'recalled a message' in clean_content:
+        if clean_content.strip().startswith("<") or "recalled a message" in clean_content:
             return ""
-        
+
         return clean_content.strip()
-    
+
     def _is_text_message(self, content: str) -> bool:
         """
         Check if a message contains readable text content.
-        
+
         Args:
             content: The message content (can be string or dict)
-            
+
         Returns:
             True if the message contains readable text, False otherwise
         """
         if not content:
             return False
-        
+
         # Handle dictionary content
         if isinstance(content, dict):
             # Check if dict has any readable text fields
-            text_fields = ['title', 'quoted', 'content', 'text']
+            text_fields = ["title", "quoted", "content", "text"]
             for field in text_fields:
-                if field in content and content[field]:
+                if content.get(field):
                     return True
             return False
-        
+
         # Handle string content
         if not isinstance(content, str):
             return False
-        
+
         # Skip image messages (contain XML with img tags)
-        if '<img' in content and 'cdnurl' in content:
+        if "<img" in content and "cdnurl" in content:
             return False
-        
+
         # Skip emoji messages (contain emoji XML tags)
-        if '<emoji' in content and 'productid' in content:
+        if "<emoji" in content and "productid" in content:
             return False
-        
+
         # Skip voice messages
-        if '<voice' in content:
+        if "<voice" in content:
             return False
-        
+
         # Skip video messages
-        if '<video' in content:
+        if "<video" in content:
             return False
-        
+
         # Skip file messages
-        if '<appmsg' in content and 'appid' in content:
+        if "<appmsg" in content and "appid" in content:
             return False
-        
+
         # Skip system messages (like "recalled a message")
-        if 'recalled a message' in content:
+        if "recalled a message" in content:
             return False
-        
+
         # Check if there's actual readable text (not just XML or system messages)
         # Remove common prefixes like "wxid_xxx:\n" and check for actual content
-        clean_content = re.sub(r'^wxid_[^:]+:\s*', '', content)
-        clean_content = re.sub(r'^[^:]+:\s*', '', clean_content)
-        
+        clean_content = re.sub(r"^wxid_[^:]+:\s*", "", content)
+        clean_content = re.sub(r"^[^:]+:\s*", "", clean_content)
+
         # If after cleaning we have meaningful text, consider it readable
-        if len(clean_content.strip()) > 0 and not clean_content.strip().startswith('<'):
+        if len(clean_content.strip()) > 0 and not clean_content.strip().startswith("<"):
             return True
-        
+
         return False
-    
-    def _concatenate_messages(self, messages: List[Dict], max_length: int = 128, 
-                             time_window_minutes: int = 30, overlap_messages: int = 0) -> List[Dict]:
+
+    def _concatenate_messages(
+        self,
+        messages: list[dict],
+        max_length: int = 128,
+        time_window_minutes: int = 30,
+        overlap_messages: int = 0,
+    ) -> list[dict]:
         """
         Concatenate messages based on length and time rules.
-        
+
         Args:
             messages: List of message dictionaries
             max_length: Maximum length for concatenated message groups. Use -1 to disable length constraint.
             time_window_minutes: Time window in minutes to group messages together. Use -1 to disable time constraint.
             overlap_messages: Number of messages to overlap between consecutive groups
-            
+
         Returns:
             List of concatenated message groups
         """
         if not messages:
             return []
-        
+
         concatenated_groups = []
         current_group = []
         current_length = 0
         last_timestamp = None
-        
+
         for message in messages:
             # Extract message info
-            content = message.get('content', '')
-            message_text = message.get('message', '')
-            create_time = message.get('createTime', 0)
-            from_user = message.get('fromUser', '')
-            to_user = message.get('toUser', '')
-            is_sent_from_self = message.get('isSentFromSelf', False)
-            
+            content = message.get("content", "")
+            message_text = message.get("message", "")
+            create_time = message.get("createTime", 0)
+            message.get("fromUser", "")
+            message.get("toUser", "")
+            message.get("isSentFromSelf", False)
+
             # Extract readable text
             readable_text = self._extract_readable_text(content)
             if not readable_text:
                 readable_text = message_text
-            
+
             # Skip empty messages
             if not readable_text.strip():
                 continue
-            
+
             # Check time window constraint (only if time_window_minutes != -1)
             if time_window_minutes != -1 and last_timestamp is not None and create_time > 0:
                 time_diff_minutes = (create_time - last_timestamp) / 60
                 if time_diff_minutes > time_window_minutes:
                     # Time gap too large, start new group
                     if current_group:
-                        concatenated_groups.append({
-                            'messages': current_group,
-                            'total_length': current_length,
-                            'start_time': current_group[0].get('createTime', 0),
-                            'end_time': current_group[-1].get('createTime', 0)
-                        })
+                        concatenated_groups.append(
+                            {
+                                "messages": current_group,
+                                "total_length": current_length,
+                                "start_time": current_group[0].get("createTime", 0),
+                                "end_time": current_group[-1].get("createTime", 0),
+                            }
+                        )
                         # Keep last few messages for overlap
                         if overlap_messages > 0 and len(current_group) > overlap_messages:
                             current_group = current_group[-overlap_messages:]
-                            current_length = sum(len(self._extract_readable_text(msg.get('content', '')) or msg.get('message', '')) for msg in current_group)
+                            current_length = sum(
+                                len(
+                                    self._extract_readable_text(msg.get("content", ""))
+                                    or msg.get("message", "")
+                                )
+                                for msg in current_group
+                            )
                         else:
                             current_group = []
                             current_length = 0
-            
+
             # Check length constraint (only if max_length != -1)
             message_length = len(readable_text)
             if max_length != -1 and current_length + message_length > max_length and current_group:
                 # Current group would exceed max length, save it and start new
-                concatenated_groups.append({
-                    'messages': current_group,
-                    'total_length': current_length,
-                    'start_time': current_group[0].get('createTime', 0),
-                    'end_time': current_group[-1].get('createTime', 0)
-                })
+                concatenated_groups.append(
+                    {
+                        "messages": current_group,
+                        "total_length": current_length,
+                        "start_time": current_group[0].get("createTime", 0),
+                        "end_time": current_group[-1].get("createTime", 0),
+                    }
+                )
                 # Keep last few messages for overlap
                 if overlap_messages > 0 and len(current_group) > overlap_messages:
                     current_group = current_group[-overlap_messages:]
-                    current_length = sum(len(self._extract_readable_text(msg.get('content', '')) or msg.get('message', '')) for msg in current_group)
+                    current_length = sum(
+                        len(
+                            self._extract_readable_text(msg.get("content", ""))
+                            or msg.get("message", "")
+                        )
+                        for msg in current_group
+                    )
                 else:
                     current_group = []
                     current_length = 0
-            
+
             # Add message to current group
             current_group.append(message)
             current_length += message_length
             last_timestamp = create_time
-        
+
         # Add the last group if it exists
         if current_group:
-            concatenated_groups.append({
-                'messages': current_group,
-                'total_length': current_length,
-                'start_time': current_group[0].get('createTime', 0),
-                'end_time': current_group[-1].get('createTime', 0)
-            })
-        
+            concatenated_groups.append(
+                {
+                    "messages": current_group,
+                    "total_length": current_length,
+                    "start_time": current_group[0].get("createTime", 0),
+                    "end_time": current_group[-1].get("createTime", 0),
+                }
+            )
+
         return concatenated_groups
-    
-    def _create_concatenated_content(self, message_group: Dict, contact_name: str) -> str:
+
+    def _create_concatenated_content(self, message_group: dict, contact_name: str) -> str:
         """
         Create concatenated content from a group of messages.
-        
+
         Args:
             message_group: Dictionary containing messages and metadata
             contact_name: Name of the contact
-            
+
         Returns:
             Formatted concatenated content
         """
-        messages = message_group['messages']
-        start_time = message_group['start_time']
-        end_time = message_group['end_time']
-        
+        messages = message_group["messages"]
+        start_time = message_group["start_time"]
+        end_time = message_group["end_time"]
+
         # Format timestamps
         if start_time:
             try:
                 start_timestamp = datetime.fromtimestamp(start_time)
-                start_time_str = start_timestamp.strftime('%Y-%m-%d %H:%M:%S')
-            except:
+                start_time_str = start_timestamp.strftime("%Y-%m-%d %H:%M:%S")
+            except (ValueError, OSError):
                 start_time_str = str(start_time)
         else:
             start_time_str = "Unknown"
-        
+
         if end_time:
             try:
                 end_timestamp = datetime.fromtimestamp(end_time)
-                end_time_str = end_timestamp.strftime('%Y-%m-%d %H:%M:%S')
-            except:
+                end_time_str = end_timestamp.strftime("%Y-%m-%d %H:%M:%S")
+            except (ValueError, OSError):
                 end_time_str = str(end_time)
         else:
             end_time_str = "Unknown"
-        
+
         # Build concatenated message content
         message_parts = []
         for message in messages:
-            content = message.get('content', '')
-            message_text = message.get('message', '')
-            create_time = message.get('createTime', 0)
-            is_sent_from_self = message.get('isSentFromSelf', False)
-            
+            content = message.get("content", "")
+            message_text = message.get("message", "")
+            create_time = message.get("createTime", 0)
+            is_sent_from_self = message.get("isSentFromSelf", False)
+
             # Extract readable text
             readable_text = self._extract_readable_text(content)
             if not readable_text:
                 readable_text = message_text
-            
+
             # Format individual message
             if create_time:
                 try:
                     timestamp = datetime.fromtimestamp(create_time)
                     # change to YYYY-MM-DD HH:MM:SS
-                    time_str = timestamp.strftime('%Y-%m-%d %H:%M:%S')
-                except:
+                    time_str = timestamp.strftime("%Y-%m-%d %H:%M:%S")
+                except (ValueError, OSError):
                     time_str = str(create_time)
             else:
                 time_str = "Unknown"
-            
+
             sender = "[Me]" if is_sent_from_self else "[Contact]"
             message_parts.append(f"({time_str}) {sender}: {readable_text}")
-        
+
         concatenated_text = "\n".join(message_parts)
-        
+
         # Create final document content
         doc_content = f"""
 Contact: {contact_name}
 Time Range: {start_time_str} - {end_time_str}
-Messages ({len(messages)} messages, {message_group['total_length']} chars):
+Messages ({len(messages)} messages, {message_group["total_length"]} chars):
 
 {concatenated_text}
 """
-        # TODO @yichuan give better format and rich info here!    
+        # TODO @yichuan give better format and rich info here!
         doc_content = f"""
 {concatenated_text}
 """
         return doc_content, contact_name
-    
-    def load_data(self, input_dir: str = None, **load_kwargs: Any) -> List[Document]:
+
+    def load_data(self, input_dir: str | None = None, **load_kwargs: Any) -> list[Document]:
         """
         Load WeChat chat history data from exported JSON files.
-        
+
         Args:
             input_dir: Directory containing exported WeChat JSON files
             **load_kwargs:
@@ -376,97 +406,104 @@ Messages ({len(messages)} messages, {message_group['total_length']} chars):
                 time_window_minutes (int): Time window in minutes to group messages together (default: 30).
                 overlap_messages (int): Number of messages to overlap between consecutive groups (default: 2).
         """
-        docs: List[Document] = []
-        max_count = load_kwargs.get('max_count', 1000)
-        wechat_export_dir = load_kwargs.get('wechat_export_dir', None)
-        include_non_text = load_kwargs.get('include_non_text', False)
-        concatenate_messages = load_kwargs.get('concatenate_messages', False)
-        max_length = load_kwargs.get('max_length', 1000)
-        time_window_minutes = load_kwargs.get('time_window_minutes', 30)
-        
+        docs: list[Document] = []
+        max_count = load_kwargs.get("max_count", 1000)
+        wechat_export_dir = load_kwargs.get("wechat_export_dir", None)
+        include_non_text = load_kwargs.get("include_non_text", False)
+        concatenate_messages = load_kwargs.get("concatenate_messages", False)
+        load_kwargs.get("max_length", 1000)
+        load_kwargs.get("time_window_minutes", 30)
+
         # Default WeChat export path
         if wechat_export_dir is None:
             wechat_export_dir = "./wechat_export_test"
-        
+
         if not os.path.exists(wechat_export_dir):
             print(f"WeChat export directory not found at: {wechat_export_dir}")
             return docs
-        
+
         try:
             # Find all JSON files in the export directory
             json_files = list(Path(wechat_export_dir).glob("*.json"))
             print(f"Found {len(json_files)} WeChat chat history files")
-            
+
             count = 0
             for json_file in json_files:
                 if count >= max_count and max_count > 0:
                     break
-                
+
                 try:
-                    with open(json_file, 'r', encoding='utf-8') as f:
+                    with open(json_file, encoding="utf-8") as f:
                         chat_data = json.load(f)
-                    
+
                     # Extract contact name from filename
                     contact_name = json_file.stem
-                    
+
                     if concatenate_messages:
                         # Filter messages to only include readable text messages
                         readable_messages = []
                         for message in chat_data:
                             try:
-                                content = message.get('content', '')
+                                content = message.get("content", "")
                                 if not include_non_text and not self._is_text_message(content):
                                     continue
-                                
+
                                 readable_text = self._extract_readable_text(content)
                                 if not readable_text and not include_non_text:
                                     continue
-                                
+
                                 readable_messages.append(message)
                             except Exception as e:
                                 print(f"Error processing message in {json_file}: {e}")
                                 continue
-                        
+
                         # Concatenate messages based on rules
                         message_groups = self._concatenate_messages(
-                            readable_messages, 
-                            max_length=-1, 
+                            readable_messages,
+                            max_length=-1,
                             time_window_minutes=-1,
-                            overlap_messages=0  # Keep 2 messages overlap between groups
+                            overlap_messages=0,  # Keep 2 messages overlap between groups
                         )
-                        
+
                         # Create documents from concatenated groups
                         for message_group in message_groups:
                             if count >= max_count and max_count > 0:
                                 break
-                            
-                            doc_content, contact_name  = self._create_concatenated_content(message_group, contact_name)
-                            doc = Document(text=doc_content, metadata={"contact_name": contact_name})
+
+                            doc_content, contact_name = self._create_concatenated_content(
+                                message_group, contact_name
+                            )
+                            doc = Document(
+                                text=doc_content,
+                                metadata={"contact_name": contact_name},
+                            )
                             docs.append(doc)
                             count += 1
-                        
-                        print(f"Created {len(message_groups)} concatenated message groups for {contact_name}")
-                        
+
+                        print(
+                            f"Created {len(message_groups)} concatenated message groups for {contact_name}"
+                        )
+
                     else:
                         # Original single-message processing
                         for message in chat_data:
                             if count >= max_count and max_count > 0:
                                 break
-                            
+
                             # Extract message information
-                            from_user = message.get('fromUser', '')
-                            to_user = message.get('toUser', '')
-                            content = message.get('content', '')
-                            message_text = message.get('message', '')
-                            create_time = message.get('createTime', 0)
-                            is_sent_from_self = message.get('isSentFromSelf', False)
-                            
+                            message.get("fromUser", "")
+                            message.get("toUser", "")
+                            content = message.get("content", "")
+                            message_text = message.get("message", "")
+                            create_time = message.get("createTime", 0)
+                            is_sent_from_self = message.get("isSentFromSelf", False)
+
                             # Handle content that might be dict or string
                             try:
                                 # Check if this is a readable text message
                                 if not include_non_text and not self._is_text_message(content):
                                     continue
-                                
+
                                 # Extract readable text
                                 readable_text = self._extract_readable_text(content)
                                 if not readable_text and not include_non_text:
@@ -475,17 +512,17 @@ Messages ({len(messages)} messages, {message_group['total_length']} chars):
                                 # Skip messages that cause processing errors
                                 print(f"Error processing message in {json_file}: {e}")
                                 continue
-                            
+
                             # Convert timestamp to readable format
                             if create_time:
                                 try:
                                     timestamp = datetime.fromtimestamp(create_time)
-                                    time_str = timestamp.strftime('%Y-%m-%d %H:%M:%S')
-                                except:
+                                    time_str = timestamp.strftime("%Y-%m-%d %H:%M:%S")
+                                except (ValueError, OSError):
                                     time_str = str(create_time)
                             else:
                                 time_str = "Unknown"
-                            
+
                             # Create document content with metadata header and contact info
                             doc_content = f"""
 Contact: {contact_name}
@@ -493,57 +530,64 @@ Is sent from self: {is_sent_from_self}
 Time: {time_str}
 Message: {readable_text if readable_text else message_text}
 """
-                            
+
                             # Create document with embedded metadata
                             doc = Document(text=doc_content, metadata={})
                             docs.append(doc)
                             count += 1
-                        
+
                 except Exception as e:
                     print(f"Error reading {json_file}: {e}")
                     continue
-            
+
             print(f"Loaded {len(docs)} WeChat chat documents")
-            
+
         except Exception as e:
             print(f"Error reading WeChat history: {e}")
             return docs
-        
+
         return docs
 
     @staticmethod
-    def find_wechat_export_dirs() -> List[Path]:
+    def find_wechat_export_dirs() -> list[Path]:
         """
         Find all WeChat export directories.
-        
+
         Returns:
             List of Path objects pointing to WeChat export directories
         """
         export_dirs = []
-        
+
         # Look for common export directory names
         possible_dirs = [
             Path("./wechat_export_test"),
             Path("./wechat_export"),
             Path("./wechat_chat_history"),
-            Path("./chat_export")
+            Path("./chat_export"),
         ]
-        
+
         for export_dir in possible_dirs:
             if export_dir.exists() and export_dir.is_dir():
                 json_files = list(export_dir.glob("*.json"))
                 if json_files:
                     export_dirs.append(export_dir)
-                    print(f"Found WeChat export directory: {export_dir} with {len(json_files)} files")
-        
+                    print(
+                        f"Found WeChat export directory: {export_dir} with {len(json_files)} files"
+                    )
+
         print(f"Found {len(export_dirs)} WeChat export directories")
         return export_dirs
 
     @staticmethod
-    def export_chat_to_file(output_file: str = "wechat_chat_export.txt", max_count: int = 1000, export_dir: str = None, include_non_text: bool = False):
+    def export_chat_to_file(
+        output_file: str = "wechat_chat_export.txt",
+        max_count: int = 1000,
+        export_dir: str | None = None,
+        include_non_text: bool = False,
+    ):
         """
         Export WeChat chat history to a text file.
-        
+
         Args:
             output_file: Path to the output file
             max_count: Maximum number of entries to export
@@ -552,36 +596,36 @@ Message: {readable_text if readable_text else message_text}
         """
         if export_dir is None:
             export_dir = "./wechat_export_test"
-        
+
         if not os.path.exists(export_dir):
             print(f"WeChat export directory not found at: {export_dir}")
             return
-        
+
         try:
             json_files = list(Path(export_dir).glob("*.json"))
-            
-            with open(output_file, 'w', encoding='utf-8') as f:
+
+            with open(output_file, "w", encoding="utf-8") as f:
                 count = 0
                 for json_file in json_files:
                     if count >= max_count and max_count > 0:
                         break
-                    
+
                     try:
-                        with open(json_file, 'r', encoding='utf-8') as json_f:
+                        with open(json_file, encoding="utf-8") as json_f:
                             chat_data = json.load(json_f)
-                        
+
                         contact_name = json_file.stem
                         f.write(f"\n=== Chat with {contact_name} ===\n")
-                        
+
                         for message in chat_data:
                             if count >= max_count and max_count > 0:
                                 break
-                            
-                            from_user = message.get('fromUser', '')
-                            content = message.get('content', '')
-                            message_text = message.get('message', '')
-                            create_time = message.get('createTime', 0)
-                            
+
+                            from_user = message.get("fromUser", "")
+                            content = message.get("content", "")
+                            message_text = message.get("message", "")
+                            create_time = message.get("createTime", 0)
+
                             # Skip non-text messages unless requested
                             if not include_non_text:
                                 reader = WeChatHistoryReader()
@@ -591,83 +635,90 @@ Message: {readable_text if readable_text else message_text}
                                 if not readable_text:
                                     continue
                                 message_text = readable_text
-                            
+
                             if create_time:
                                 try:
                                     timestamp = datetime.fromtimestamp(create_time)
-                                    time_str = timestamp.strftime('%Y-%m-%d %H:%M:%S')
-                                except:
+                                    time_str = timestamp.strftime("%Y-%m-%d %H:%M:%S")
+                                except (ValueError, OSError):
                                     time_str = str(create_time)
                             else:
                                 time_str = "Unknown"
-                            
+
                             f.write(f"[{time_str}] {from_user}: {message_text}\n")
                             count += 1
-                            
+
                     except Exception as e:
                         print(f"Error processing {json_file}: {e}")
                         continue
-            
+
             print(f"Exported {count} chat entries to {output_file}")
-            
+
         except Exception as e:
             print(f"Error exporting WeChat chat history: {e}")
 
-    def export_wechat_chat_history(self, export_dir: str = "./wechat_export_direct") -> Optional[Path]:
+    def export_wechat_chat_history(self, export_dir: str = "./wechat_export_direct") -> Path | None:
         """
         Export WeChat chat history using wechat-exporter tool.
-        
+
         Args:
             export_dir: Directory to save exported chat history
-            
+
         Returns:
             Path to export directory if successful, None otherwise
         """
         try:
             import subprocess
             import sys
-            
+
             # Create export directory
             export_path = Path(export_dir)
             export_path.mkdir(exist_ok=True)
-            
+
             print(f"Exporting WeChat chat history to {export_path}...")
-            
+
             # Check if wechat-exporter directory exists
             if not self.wechat_exporter_dir.exists():
                 print(f"wechat-exporter directory not found at: {self.wechat_exporter_dir}")
                 return None
-            
+
             # Install requirements if needed
             requirements_file = self.wechat_exporter_dir / "requirements.txt"
             if requirements_file.exists():
                 print("Installing wechat-exporter requirements...")
-                subprocess.run([
-                    "uv", "pip", "install", "-r", str(requirements_file)
-                ], check=True)
-            
+                subprocess.run(["uv", "pip", "install", "-r", str(requirements_file)], check=True)
+
             # Run the export command
             print("Running wechat-exporter...")
-            result = subprocess.run([
-                sys.executable, str(self.wechat_exporter_dir / "main.py"), 
-                "export-all", str(export_path)
-            ], capture_output=True, text=True, check=True)
-            
+            result = subprocess.run(
+                [
+                    sys.executable,
+                    str(self.wechat_exporter_dir / "main.py"),
+                    "export-all",
+                    str(export_path),
+                ],
+                capture_output=True,
+                text=True,
+                check=True,
+            )
+
             print("Export command output:")
             print(result.stdout)
             if result.stderr:
                 print("Export errors:")
                 print(result.stderr)
-            
+
             # Check if export was successful
             if export_path.exists() and any(export_path.glob("*.json")):
                 json_files = list(export_path.glob("*.json"))
-                print(f"Successfully exported {len(json_files)} chat history files to {export_path}")
+                print(
+                    f"Successfully exported {len(json_files)} chat history files to {export_path}"
+                )
                 return export_path
             else:
                 print("Export completed but no JSON files found")
                 return None
-                
+
         except subprocess.CalledProcessError as e:
             print(f"Export command failed: {e}")
             print(f"Command output: {e.stdout}")
@@ -678,18 +729,18 @@ Message: {readable_text if readable_text else message_text}
             print("Please ensure WeChat is running and WeChatTweak is installed.")
             return None
 
-    def find_or_export_wechat_data(self, export_dir: str = "./wechat_export_direct") -> List[Path]:
+    def find_or_export_wechat_data(self, export_dir: str = "./wechat_export_direct") -> list[Path]:
         """
         Find existing WeChat exports or create new ones.
-        
+
         Args:
             export_dir: Directory to save exported chat history if needed
-            
+
         Returns:
             List of Path objects pointing to WeChat export directories
         """
         export_dirs = []
-        
+
         # Look for existing exports in common locations
         possible_export_dirs = [
             Path("./wechat_database_export"),
@@ -697,23 +748,25 @@ Message: {readable_text if readable_text else message_text}
             Path("./wechat_export"),
             Path("./wechat_export_direct"),
             Path("./wechat_chat_history"),
-            Path("./chat_export")
+            Path("./chat_export"),
         ]
-        
+
         for export_dir_path in possible_export_dirs:
             if export_dir_path.exists() and any(export_dir_path.glob("*.json")):
                 export_dirs.append(export_dir_path)
                 print(f"Found existing export: {export_dir_path}")
-        
+
         # If no existing exports, try to export automatically
         if not export_dirs:
             print("No existing WeChat exports found. Starting direct export...")
-            
+
             # Try to export using wechat-exporter
             exported_path = self.export_wechat_chat_history(export_dir)
             if exported_path:
                 export_dirs = [exported_path]
             else:
-                print("Failed to export WeChat data. Please ensure WeChat is running and WeChatTweak is installed.")
-        
-        return export_dirs 
+                print(
+                    "Failed to export WeChat data. Please ensure WeChat is running and WeChatTweak is installed."
+                )
+
+        return export_dirs

examples/mail_reader_leann.py

@@ -1,33 +1,42 @@
+import argparse
+import asyncio
 import os
 import sys
-import asyncio
-import dotenv
-import argparse
 from pathlib import Path
-from typing import List, Any
+
+import dotenv
 
 # Add the project root to Python path so we can import from examples
 project_root = Path(__file__).parent.parent
 sys.path.insert(0, str(project_root))
 
-from leann.api import LeannBuilder, LeannSearcher, LeannChat
+from leann.api import LeannBuilder, LeannChat
 from llama_index.core.node_parser import SentenceSplitter
 
 dotenv.load_dotenv()
 
+
 # Auto-detect user's mail path
 def get_mail_path():
     """Get the mail path for the current user"""
     home_dir = os.path.expanduser("~")
     return os.path.join(home_dir, "Library", "Mail")
 
+
 # Default mail path for macOS
 DEFAULT_MAIL_PATH = "/Users/yichuan/Library/Mail/V10/0FCA0879-FD8C-4B7E-83BF-FDDA930791C5/[Gmail].mbox/All Mail.mbox/78BA5BE1-8819-4F9A-9613-EB63772F1DD0/Data"
 
-def create_leann_index_from_multiple_sources(messages_dirs: List[Path], index_path: str = "mail_index.leann", max_count: int = -1, include_html: bool = False, embedding_model: str = "facebook/contriever"):
+
+def create_leann_index_from_multiple_sources(
+    messages_dirs: list[Path],
+    index_path: str = "mail_index.leann",
+    max_count: int = -1,
+    include_html: bool = False,
+    embedding_model: str = "facebook/contriever",
+):
     """
     Create LEANN index from multiple mail data sources.
-    
+
     Args:
         messages_dirs: List of Path objects pointing to Messages directories
         index_path: Path to save the LEANN index
@@ -35,31 +44,32 @@ def create_leann_index_from_multiple_sources(messages_dirs: List[Path], index_pa
         include_html: Whether to include HTML content in email processing
     """
     print("Creating LEANN index from multiple mail data sources...")
-    
+
     # Load documents using EmlxReader from LEANN_email_reader
     from examples.email_data.LEANN_email_reader import EmlxReader
+
     reader = EmlxReader(include_html=include_html)
     # from email_data.email import EmlxMboxReader
     # from pathlib import Path
     # reader = EmlxMboxReader()
     INDEX_DIR = Path(index_path).parent
-    
+
     if not INDEX_DIR.exists():
-        print(f"--- Index directory not found, building new index ---")
+        print("--- Index directory not found, building new index ---")
         all_documents = []
         total_processed = 0
-        
+
         # Process each Messages directory
         for i, messages_dir in enumerate(messages_dirs):
-            print(f"\nProcessing Messages directory {i+1}/{len(messages_dirs)}: {messages_dir}")
-            
+            print(f"\nProcessing Messages directory {i + 1}/{len(messages_dirs)}: {messages_dir}")
+
             try:
                 documents = reader.load_data(messages_dir)
                 if documents:
                     print(f"Loaded {len(documents)} email documents from {messages_dir}")
                     all_documents.extend(documents)
                     total_processed += len(documents)
-                    
+
                     # Check if we've reached the max count
                     if max_count > 0 and total_processed >= max_count:
                         print(f"Reached max count of {max_count} documents")
@@ -69,16 +79,18 @@ def create_leann_index_from_multiple_sources(messages_dirs: List[Path], index_pa
             except Exception as e:
                 print(f"Error processing {messages_dir}: {e}")
                 continue
-        
+
         if not all_documents:
             print("No documents loaded from any source. Exiting.")
             return None
-        
-        print(f"\nTotal loaded {len(all_documents)} email documents from {len(messages_dirs)} directories and starting to split them into chunks")
-        
+
+        print(
+            f"\nTotal loaded {len(all_documents)} email documents from {len(messages_dirs)} directories and starting to split them into chunks"
+        )
+
         # Create text splitter with 256 chunk size
         text_splitter = SentenceSplitter(chunk_size=256, chunk_overlap=25)
-        
+
         # Convert Documents to text strings and chunk them
         all_texts = []
         for doc in all_documents:
@@ -88,44 +100,53 @@ def create_leann_index_from_multiple_sources(messages_dirs: List[Path], index_pa
                 text = node.get_content()
                 # text = '[subject] ' + doc.metadata["subject"] + '\n' + text
                 all_texts.append(text)
-        
-        print(f"Finished splitting {len(all_documents)} documents into {len(all_texts)} text chunks")
-        
+
+        print(
+            f"Finished splitting {len(all_documents)} documents into {len(all_texts)} text chunks"
+        )
+
         # Create LEANN index directory
 
-        print(f"--- Index directory not found, building new index ---")
+        print("--- Index directory not found, building new index ---")
         INDEX_DIR.mkdir(exist_ok=True)
 
-        print(f"--- Building new LEANN index ---")
-        
-        print(f"\n[PHASE 1] Building Leann index...")
+        print("--- Building new LEANN index ---")
+
+        print("\n[PHASE 1] Building Leann index...")
 
         # Use HNSW backend for better macOS compatibility
         builder = LeannBuilder(
             backend_name="hnsw",
             embedding_model=embedding_model,
-            graph_degree=32, 
+            graph_degree=32,
             complexity=64,
             is_compact=True,
             is_recompute=True,
-            num_threads=1  # Force single-threaded mode
+            num_threads=1,  # Force single-threaded mode
         )
 
         print(f"Adding {len(all_texts)} email chunks to index...")
         for chunk_text in all_texts:
             builder.add_text(chunk_text)
-            
+
         builder.build_index(index_path)
         print(f"\nLEANN index built at {index_path}!")
     else:
         print(f"--- Using existing index at {INDEX_DIR} ---")
-    
+
     return index_path
 
-def create_leann_index(mail_path: str, index_path: str = "mail_index.leann", max_count: int = 1000, include_html: bool = False, embedding_model: str = "facebook/contriever"):
+
+def create_leann_index(
+    mail_path: str,
+    index_path: str = "mail_index.leann",
+    max_count: int = 1000,
+    include_html: bool = False,
+    embedding_model: str = "facebook/contriever",
+):
     """
     Create LEANN index from mail data.
-    
+
     Args:
         mail_path: Path to the mail directory
         index_path: Path to save the LEANN index
@@ -134,32 +155,33 @@ def create_leann_index(mail_path: str, index_path: str = "mail_index.leann", max
     """
     print("Creating LEANN index from mail data...")
     INDEX_DIR = Path(index_path).parent
-    
+
     if not INDEX_DIR.exists():
-        print(f"--- Index directory not found, building new index ---")
+        print("--- Index directory not found, building new index ---")
         INDEX_DIR.mkdir(exist_ok=True)
 
-        print(f"--- Building new LEANN index ---")
-        
-        print(f"\n[PHASE 1] Building Leann index...")
+        print("--- Building new LEANN index ---")
+
+        print("\n[PHASE 1] Building Leann index...")
 
         # Load documents using EmlxReader from LEANN_email_reader
         from examples.email_data.LEANN_email_reader import EmlxReader
+
         reader = EmlxReader(include_html=include_html)
         # from email_data.email import EmlxMboxReader
         # from pathlib import Path
         # reader = EmlxMboxReader()
         documents = reader.load_data(Path(mail_path))
-        
+
         if not documents:
             print("No documents loaded. Exiting.")
             return None
-        
+
         print(f"Loaded {len(documents)} email documents")
-        
+
         # Create text splitter with 256 chunk size
         text_splitter = SentenceSplitter(chunk_size=256, chunk_overlap=128)
-        
+
         # Convert Documents to text strings and chunk them
         all_texts = []
         for doc in documents:
@@ -167,111 +189,139 @@ def create_leann_index(mail_path: str, index_path: str = "mail_index.leann", max
             nodes = text_splitter.get_nodes_from_documents([doc])
             for node in nodes:
                 all_texts.append(node.get_content())
-        
+
         print(f"Created {len(all_texts)} text chunks from {len(documents)} documents")
-        
+
         # Create LEANN index directory
 
-        print(f"--- Index directory not found, building new index ---")
+        print("--- Index directory not found, building new index ---")
         INDEX_DIR.mkdir(exist_ok=True)
 
-        print(f"--- Building new LEANN index ---")
-        
-        print(f"\n[PHASE 1] Building Leann index...")
+        print("--- Building new LEANN index ---")
+
+        print("\n[PHASE 1] Building Leann index...")
 
         # Use HNSW backend for better macOS compatibility
         builder = LeannBuilder(
             backend_name="hnsw",
             embedding_model=embedding_model,
-            graph_degree=32, 
+            graph_degree=32,
             complexity=64,
             is_compact=True,
             is_recompute=True,
-            num_threads=1  # Force single-threaded mode
+            num_threads=1,  # Force single-threaded mode
         )
 
         print(f"Adding {len(all_texts)} email chunks to index...")
         for chunk_text in all_texts:
             builder.add_text(chunk_text)
-            
+
         builder.build_index(index_path)
         print(f"\nLEANN index built at {index_path}!")
     else:
         print(f"--- Using existing index at {INDEX_DIR} ---")
-    
+
     return index_path
 
+
 async def query_leann_index(index_path: str, query: str):
     """
     Query the LEANN index.
-    
+
     Args:
         index_path: Path to the LEANN index
         query: The query string
     """
-    print(f"\n[PHASE 2] Starting Leann chat session...")
-    chat = LeannChat(index_path=index_path,
-                     llm_config={"type": "openai", "model": "gpt-4o"})
-    
+    print("\n[PHASE 2] Starting Leann chat session...")
+    chat = LeannChat(index_path=index_path, llm_config={"type": "openai", "model": "gpt-4o"})
+
     print(f"You: {query}")
     import time
-    start_time = time.time()
+
+    time.time()
     chat_response = chat.ask(
-        query, 
-        top_k=20, 
+        query,
+        top_k=20,
         recompute_beighbor_embeddings=True,
         complexity=32,
         beam_width=1,
     )
-    end_time = time.time()
+    time.time()
     # print(f"Time taken: {end_time - start_time} seconds")
     # highlight the answer
     print(f"Leann chat response: \033[36m{chat_response}\033[0m")
 
+
 async def main():
     # Parse command line arguments
-    parser = argparse.ArgumentParser(description='LEANN Mail Reader - Create and query email index')
+    parser = argparse.ArgumentParser(description="LEANN Mail Reader - Create and query email index")
     # Remove --mail-path argument and auto-detect all Messages directories
     # Remove DEFAULT_MAIL_PATH
-    parser.add_argument('--index-dir', type=str, default="./mail_index",
-                       help='Directory to store the LEANN index (default: ./mail_index_leann_raw_text_all_dicts)')
-    parser.add_argument('--max-emails', type=int, default=1000,
-                       help='Maximum number of emails to process (-1 means all)')
-    parser.add_argument('--query', type=str, default="Give me some funny advertisement about apple or other companies",
-                       help='Single query to run (default: runs example queries)')
-    parser.add_argument('--include-html', action='store_true', default=False,
-                       help='Include HTML content in email processing (default: False)')
-    parser.add_argument('--embedding-model', type=str, default="facebook/contriever",
-                       help='Embedding model to use (default: facebook/contriever)')
-    
+    parser.add_argument(
+        "--index-dir",
+        type=str,
+        default="./mail_index",
+        help="Directory to store the LEANN index (default: ./mail_index_leann_raw_text_all_dicts)",
+    )
+    parser.add_argument(
+        "--max-emails",
+        type=int,
+        default=1000,
+        help="Maximum number of emails to process (-1 means all)",
+    )
+    parser.add_argument(
+        "--query",
+        type=str,
+        default="Give me some funny advertisement about apple or other companies",
+        help="Single query to run (default: runs example queries)",
+    )
+    parser.add_argument(
+        "--include-html",
+        action="store_true",
+        default=False,
+        help="Include HTML content in email processing (default: False)",
+    )
+    parser.add_argument(
+        "--embedding-model",
+        type=str,
+        default="facebook/contriever",
+        help="Embedding model to use (default: facebook/contriever)",
+    )
+
     args = parser.parse_args()
 
     print(f"args: {args}")
-    
+
     # Automatically find all Messages directories under the current user's Mail directory
     from examples.email_data.LEANN_email_reader import find_all_messages_directories
+
     mail_path = get_mail_path()
     print(f"Searching for email data in: {mail_path}")
     messages_dirs = find_all_messages_directories(mail_path)
     # messages_dirs = find_all_messages_directories(DEFAULT_MAIL_PATH)
     # messages_dirs = [DEFAULT_MAIL_PATH]
     # messages_dirs = messages_dirs[:1]
-    
-    print('len(messages_dirs): ', len(messages_dirs))
-    
-    
+
+    print("len(messages_dirs): ", len(messages_dirs))
+
     if not messages_dirs:
         print("No Messages directories found. Exiting.")
         return
-    
+
     INDEX_DIR = Path(args.index_dir)
     INDEX_PATH = str(INDEX_DIR / "mail_documents.leann")
     print(f"Index directory: {INDEX_DIR}")
     print(f"Found {len(messages_dirs)} Messages directories.")
-    
+
     # Create or load the LEANN index from all sources
-    index_path = create_leann_index_from_multiple_sources(messages_dirs, INDEX_PATH, args.max_emails, args.include_html, args.embedding_model)
-    
+    index_path = create_leann_index_from_multiple_sources(
+        messages_dirs,
+        INDEX_PATH,
+        args.max_emails,
+        args.include_html,
+        args.embedding_model,
+    )
+
     if index_path:
         if args.query:
             # Run single query
@@ -281,11 +331,12 @@ async def main():
             queries = [
                 "Hows Berkeley Graduate Student Instructor",
                 "how's the icloud related advertisement saying",
-                "Whats the number of class recommend to take per semester for incoming EECS students"
+                "Whats the number of class recommend to take per semester for incoming EECS students",
             ]
             for query in queries:
-                print("\n" + "="*60)
+                print("\n" + "=" * 60)
                 await query_leann_index(index_path, query)
 
+
 if __name__ == "__main__":
-    asyncio.run(main()) 
+    asyncio.run(main())

examples/mail_reader_llamaindex.py

@@ -1,26 +1,30 @@
+import argparse
 import os
 import sys
-import argparse
 from pathlib import Path
-from typing import List, Any
 
 # Add the project root to Python path so we can import from examples
 project_root = Path(__file__).parent.parent
 sys.path.insert(0, str(project_root))
 
-from llama_index.core import VectorStoreIndex, StorageContext
+import torch
+from llama_index.core import StorageContext, VectorStoreIndex
 from llama_index.core.node_parser import SentenceSplitter
 
 # --- EMBEDDING MODEL ---
 from llama_index.embeddings.huggingface import HuggingFaceEmbedding
-import torch
 
 # --- END EMBEDDING MODEL ---
-
 # Import EmlxReader from the new module
 from examples.email_data.LEANN_email_reader import EmlxReader
 
-def create_and_save_index(mail_path: str, save_dir: str = "mail_index_embedded", max_count: int = 1000, include_html: bool = False):
+
+def create_and_save_index(
+    mail_path: str,
+    save_dir: str = "mail_index_embedded",
+    max_count: int = 1000,
+    include_html: bool = False,
+):
     print("Creating index from mail data with embedded metadata...")
     documents = EmlxReader(include_html=include_html).load_data(mail_path, max_count=max_count)
     if not documents:
@@ -30,7 +34,7 @@ def create_and_save_index(mail_path: str, save_dir: str = "mail_index_embedded",
     # Use facebook/contriever as the embedder
     embed_model = HuggingFaceEmbedding(model_name="facebook/contriever")
     # set on device
-    import torch
+
     if torch.cuda.is_available():
         embed_model._model.to("cuda")
     # set mps
@@ -39,21 +43,19 @@ def create_and_save_index(mail_path: str, save_dir: str = "mail_index_embedded",
     else:
         embed_model._model.to("cpu")
     index = VectorStoreIndex.from_documents(
-        documents,
-        transformations=[text_splitter],
-        embed_model=embed_model
+        documents, transformations=[text_splitter], embed_model=embed_model
     )
     os.makedirs(save_dir, exist_ok=True)
     index.storage_context.persist(persist_dir=save_dir)
     print(f"Index saved to {save_dir}")
     return index
 
+
 def load_index(save_dir: str = "mail_index_embedded"):
     try:
         storage_context = StorageContext.from_defaults(persist_dir=save_dir)
         index = VectorStoreIndex.from_vector_store(
-            storage_context.vector_store,
-            storage_context=storage_context
+            storage_context.vector_store, storage_context=storage_context
         )
         print(f"Index loaded from {save_dir}")
         return index
@@ -61,6 +63,7 @@ def load_index(save_dir: str = "mail_index_embedded"):
         print(f"Error loading index: {e}")
         return None
 
+
 def query_index(index, query: str):
     if index is None:
         print("No index available for querying.")
@@ -70,39 +73,63 @@ def query_index(index, query: str):
     print(f"Query: {query}")
     print(f"Response: {response}")
 
+
 def main():
     # Parse command line arguments
-    parser = argparse.ArgumentParser(description='LlamaIndex Mail Reader - Create and query email index')
-    parser.add_argument('--mail-path', type=str, 
-                       default="/Users/yichuan/Library/Mail/V10/0FCA0879-FD8C-4B7E-83BF-FDDA930791C5/[Gmail].mbox/All Mail.mbox/78BA5BE1-8819-4F9A-9613-EB63772F1DD0/Data/9/Messages",
-                       help='Path to mail data directory')
-    parser.add_argument('--save-dir', type=str, default="mail_index_embedded",
-                       help='Directory to store the index (default: mail_index_embedded)')
-    parser.add_argument('--max-emails', type=int, default=10000,
-                       help='Maximum number of emails to process')
-    parser.add_argument('--include-html', action='store_true', default=False,
-                       help='Include HTML content in email processing (default: False)')
-    
+    parser = argparse.ArgumentParser(
+        description="LlamaIndex Mail Reader - Create and query email index"
+    )
+    parser.add_argument(
+        "--mail-path",
+        type=str,
+        default="/Users/yichuan/Library/Mail/V10/0FCA0879-FD8C-4B7E-83BF-FDDA930791C5/[Gmail].mbox/All Mail.mbox/78BA5BE1-8819-4F9A-9613-EB63772F1DD0/Data/9/Messages",
+        help="Path to mail data directory",
+    )
+    parser.add_argument(
+        "--save-dir",
+        type=str,
+        default="mail_index_embedded",
+        help="Directory to store the index (default: mail_index_embedded)",
+    )
+    parser.add_argument(
+        "--max-emails",
+        type=int,
+        default=10000,
+        help="Maximum number of emails to process",
+    )
+    parser.add_argument(
+        "--include-html",
+        action="store_true",
+        default=False,
+        help="Include HTML content in email processing (default: False)",
+    )
+
     args = parser.parse_args()
-    
+
     mail_path = args.mail_path
     save_dir = args.save_dir
-    
+
     if os.path.exists(save_dir) and os.path.exists(os.path.join(save_dir, "vector_store.json")):
         print("Loading existing index...")
         index = load_index(save_dir)
     else:
         print("Creating new index...")
-        index = create_and_save_index(mail_path, save_dir, max_count=args.max_emails, include_html=args.include_html)
+        index = create_and_save_index(
+            mail_path,
+            save_dir,
+            max_count=args.max_emails,
+            include_html=args.include_html,
+        )
     if index:
         queries = [
             "Hows Berkeley Graduate Student Instructor",
             "how's the icloud related advertisement saying",
-            "Whats the number of class recommend to take per semester for incoming EECS students"
+            "Whats the number of class recommend to take per semester for incoming EECS students",
         ]
         for query in queries:
-            print("\n" + "="*50)
+            print("\n" + "=" * 50)
             query_index(index, query)
 
+
 if __name__ == "__main__":
-    main() 
+    main()

examples/main_cli_example.py

@@ -1,10 +1,11 @@
 import argparse
-from llama_index.core import SimpleDirectoryReader
-from llama_index.core.node_parser import SentenceSplitter
 import asyncio
+from pathlib import Path
+
 import dotenv
 from leann.api import LeannBuilder, LeannChat
-from pathlib import Path
+from llama_index.core import SimpleDirectoryReader
+from llama_index.core.node_parser import SentenceSplitter
 
 dotenv.load_dotenv()
 
@@ -29,17 +30,22 @@ async def main(args):
         all_texts = []
         for doc in documents:
             nodes = node_parser.get_nodes_from_documents([doc])
-            for node in nodes:
-                all_texts.append(node.get_content())
+            if nodes:
+                all_texts.extend(node.get_content() for node in nodes)
 
         print("--- Index directory not found, building new index ---")
 
         print("\n[PHASE 1] Building Leann index...")
 
+        # LeannBuilder now automatically detects normalized embeddings and sets appropriate distance metric
+        print(f"Using {args.embedding_model} with {args.embedding_mode} mode")
+
         # Use HNSW backend for better macOS compatibility
         builder = LeannBuilder(
             backend_name="hnsw",
-            embedding_model="facebook/contriever",
+            embedding_model=args.embedding_model,
+            embedding_mode=args.embedding_mode,
+            # distance_metric is automatically set based on embedding model
             graph_degree=32,
             complexity=64,
             is_compact=True,
@@ -56,7 +62,7 @@ async def main(args):
     else:
         print(f"--- Using existing index at {INDEX_DIR} ---")
 
-    print(f"\n[PHASE 2] Starting Leann chat session...")
+    print("\n[PHASE 2] Starting Leann chat session...")
 
     llm_config = {"type": "hf", "model": "Qwen/Qwen3-4B"}
     llm_config = {"type": "ollama", "model": "qwen3:8b"}
@@ -64,7 +70,7 @@ async def main(args):
 
     chat = LeannChat(index_path=INDEX_PATH, llm_config=llm_config)
     # query = (
-    #     "什么是盘古大模型以及盘古开发过程中遇到了什么阴暗面，任务令一般在什么城市颁发"
+    #     "什么是盘古大模型以及盘古开发过程中遇到了什么阴暗面,任务令一般在什么城市颁发"
     # )
     query = args.query
 
@@ -74,9 +80,7 @@ async def main(args):
 
 
 if __name__ == "__main__":
-    parser = argparse.ArgumentParser(
-        description="Run Leann Chat with various LLM backends."
-    )
+    parser = argparse.ArgumentParser(description="Run Leann Chat with various LLM backends.")
     parser.add_argument(
         "--llm",
         type=str,
@@ -90,6 +94,19 @@ if __name__ == "__main__":
         default="Qwen/Qwen3-0.6B",
         help="The model name to use (e.g., 'llama3:8b' for ollama, 'deepseek-ai/deepseek-llm-7b-chat' for hf, 'gpt-4o' for openai).",
     )
+    parser.add_argument(
+        "--embedding-model",
+        type=str,
+        default="facebook/contriever",
+        help="The embedding model to use (e.g., 'facebook/contriever', 'text-embedding-3-small').",
+    )
+    parser.add_argument(
+        "--embedding-mode",
+        type=str,
+        default="sentence-transformers",
+        choices=["sentence-transformers", "openai", "mlx"],
+        help="The embedding backend mode.",
+    )
     parser.add_argument(
         "--host",
         type=str,

examples/multi_vector_aggregator.py

@@ -14,48 +14,55 @@ Key features:
 - Document-level result consolidation
 """
 
-import numpy as np
-from typing import List, Dict, Any, Tuple, Optional
-from dataclasses import dataclass
 from collections import defaultdict
-import json
+from dataclasses import dataclass
+from typing import Any
+
+import numpy as np
+
 
 @dataclass
 class PatchResult:
     """Represents a single patch search result."""
+
     patch_id: int
     image_name: str
     image_path: str
-    coordinates: Tuple[int, int, int, int]  # (x1, y1, x2, y2)
+    coordinates: tuple[int, int, int, int]  # (x1, y1, x2, y2)
     score: float
     attention_score: float
     scale: float
-    metadata: Dict[str, Any]
+    metadata: dict[str, Any]
+
 
 @dataclass
 class AggregatedResult:
     """Represents an aggregated document-level result."""
+
     image_name: str
     image_path: str
     doc_score: float
     patch_count: int
     best_patch: PatchResult
-    all_patches: List[PatchResult]
+    all_patches: list[PatchResult]
     aggregation_method: str
-    spatial_clusters: Optional[List[List[PatchResult]]] = None
+    spatial_clusters: list[list[PatchResult]] | None = None
+
 
 class MultiVectorAggregator:
     """
     Aggregates multiple patch-level results into document-level results.
     """
-    
-    def __init__(self, 
-                 aggregation_method: str = "maxsim",
-                 spatial_clustering: bool = True,
-                 cluster_distance_threshold: float = 100.0):
+
+    def __init__(
+        self,
+        aggregation_method: str = "maxsim",
+        spatial_clustering: bool = True,
+        cluster_distance_threshold: float = 100.0,
+    ):
         """
         Initialize the aggregator.
-        
+
         Args:
             aggregation_method: "maxsim", "voting", "weighted", or "mean"
             spatial_clustering: Whether to cluster spatially close patches
@@ -64,23 +71,23 @@ class MultiVectorAggregator:
         self.aggregation_method = aggregation_method
         self.spatial_clustering = spatial_clustering
         self.cluster_distance_threshold = cluster_distance_threshold
-    
-    def aggregate_results(self, 
-                         search_results: List[Dict[str, Any]], 
-                         top_k: int = 10) -> List[AggregatedResult]:
+
+    def aggregate_results(
+        self, search_results: list[dict[str, Any]], top_k: int = 10
+    ) -> list[AggregatedResult]:
         """
         Aggregate patch-level search results into document-level results.
-        
+
         Args:
             search_results: List of search results from LeannSearcher
             top_k: Number of top documents to return
-            
+
         Returns:
             List of aggregated document results
         """
         # Group results by image
         image_groups = defaultdict(list)
-        
+
         for result in search_results:
             metadata = result.metadata
             if "image_name" in metadata and "patch_id" in metadata:
@@ -92,55 +99,57 @@ class MultiVectorAggregator:
                     score=result.score,
                     attention_score=metadata.get("attention_score", 0.0),
                     scale=metadata.get("scale", 1.0),
-                    metadata=metadata
+                    metadata=metadata,
                 )
                 image_groups[metadata["image_name"]].append(patch_result)
-        
+
         # Aggregate each image group
         aggregated_results = []
         for image_name, patches in image_groups.items():
             if len(patches) == 0:
                 continue
-                
+
             agg_result = self._aggregate_image_patches(image_name, patches)
             aggregated_results.append(agg_result)
-        
+
         # Sort by aggregated score and return top-k
         aggregated_results.sort(key=lambda x: x.doc_score, reverse=True)
         return aggregated_results[:top_k]
-    
-    def _aggregate_image_patches(self, image_name: str, patches: List[PatchResult]) -> AggregatedResult:
+
+    def _aggregate_image_patches(
+        self, image_name: str, patches: list[PatchResult]
+    ) -> AggregatedResult:
         """Aggregate patches for a single image."""
-        
+
         if self.aggregation_method == "maxsim":
             doc_score = max(patch.score for patch in patches)
             best_patch = max(patches, key=lambda p: p.score)
-            
+
         elif self.aggregation_method == "voting":
             # Count patches above threshold
             threshold = np.percentile([p.score for p in patches], 75)
             doc_score = sum(1 for patch in patches if patch.score >= threshold)
             best_patch = max(patches, key=lambda p: p.score)
-            
+
         elif self.aggregation_method == "weighted":
             # Weight by attention scores
             total_weighted_score = sum(p.score * p.attention_score for p in patches)
             total_weights = sum(p.attention_score for p in patches)
             doc_score = total_weighted_score / max(total_weights, 1e-8)
             best_patch = max(patches, key=lambda p: p.score * p.attention_score)
-            
+
         elif self.aggregation_method == "mean":
             doc_score = np.mean([patch.score for patch in patches])
             best_patch = max(patches, key=lambda p: p.score)
-            
+
         else:
             raise ValueError(f"Unknown aggregation method: {self.aggregation_method}")
-        
+
         # Spatial clustering if enabled
         spatial_clusters = None
         if self.spatial_clustering:
             spatial_clusters = self._cluster_patches_spatially(patches)
-        
+
         return AggregatedResult(
             image_name=image_name,
             image_path=patches[0].image_path,
@@ -149,23 +158,23 @@ class MultiVectorAggregator:
             best_patch=best_patch,
             all_patches=sorted(patches, key=lambda p: p.score, reverse=True),
             aggregation_method=self.aggregation_method,
-            spatial_clusters=spatial_clusters
+            spatial_clusters=spatial_clusters,
         )
-    
-    def _cluster_patches_spatially(self, patches: List[PatchResult]) -> List[List[PatchResult]]:
+
+    def _cluster_patches_spatially(self, patches: list[PatchResult]) -> list[list[PatchResult]]:
         """Cluster patches that are spatially close to each other."""
         if len(patches) <= 1:
             return [patches]
-        
+
         clusters = []
         remaining_patches = patches.copy()
-        
+
         while remaining_patches:
             # Start new cluster with highest scoring remaining patch
             seed_patch = max(remaining_patches, key=lambda p: p.score)
             current_cluster = [seed_patch]
             remaining_patches.remove(seed_patch)
-            
+
             # Add nearby patches to cluster
             added_to_cluster = True
             while added_to_cluster:
@@ -175,145 +184,177 @@ class MultiVectorAggregator:
                         current_cluster.append(patch)
                         remaining_patches.remove(patch)
                         added_to_cluster = True
-            
+
             clusters.append(current_cluster)
-        
+
         return sorted(clusters, key=lambda cluster: max(p.score for p in cluster), reverse=True)
-    
-    def _is_patch_nearby(self, patch: PatchResult, cluster: List[PatchResult]) -> bool:
+
+    def _is_patch_nearby(self, patch: PatchResult, cluster: list[PatchResult]) -> bool:
         """Check if a patch is spatially close to any patch in the cluster."""
         patch_center = self._get_patch_center(patch.coordinates)
-        
+
         for cluster_patch in cluster:
             cluster_center = self._get_patch_center(cluster_patch.coordinates)
-            distance = np.sqrt((patch_center[0] - cluster_center[0])**2 + 
-                             (patch_center[1] - cluster_center[1])**2)
-            
+            distance = np.sqrt(
+                (patch_center[0] - cluster_center[0]) ** 2
+                + (patch_center[1] - cluster_center[1]) ** 2
+            )
+
             if distance <= self.cluster_distance_threshold:
                 return True
-        
+
         return False
-    
-    def _get_patch_center(self, coordinates: Tuple[int, int, int, int]) -> Tuple[float, float]:
+
+    def _get_patch_center(self, coordinates: tuple[int, int, int, int]) -> tuple[float, float]:
         """Get center point of a patch."""
         x1, y1, x2, y2 = coordinates
         return ((x1 + x2) / 2, (y1 + y2) / 2)
-    
-    def print_aggregated_results(self, results: List[AggregatedResult], max_patches_per_doc: int = 3):
+
+    def print_aggregated_results(
+        self, results: list[AggregatedResult], max_patches_per_doc: int = 3
+    ):
         """Pretty print aggregated results."""
         print(f"\n🔍 Aggregated Results (method: {self.aggregation_method})")
         print("=" * 80)
-        
+
         for i, result in enumerate(results):
-            print(f"\n{i+1}. {result.image_name}")
+            print(f"\n{i + 1}. {result.image_name}")
             print(f"   Doc Score: {result.doc_score:.4f} | Patches: {result.patch_count}")
             print(f"   Path: {result.image_path}")
-            
+
             # Show best patch
             best = result.best_patch
-            print(f"   🌟 Best Patch: #{best.patch_id} at {best.coordinates} (score: {best.score:.4f})")
-            
+            print(
+                f"   🌟 Best Patch: #{best.patch_id} at {best.coordinates} (score: {best.score:.4f})"
+            )
+
             # Show top patches
-            print(f"   📍 Top Patches:")
+            print("   📍 Top Patches:")
             for j, patch in enumerate(result.all_patches[:max_patches_per_doc]):
-                print(f"      {j+1}. Patch #{patch.patch_id}: {patch.score:.4f} at {patch.coordinates}")
-            
+                print(
+                    f"      {j + 1}. Patch #{patch.patch_id}: {patch.score:.4f} at {patch.coordinates}"
+                )
+
             # Show spatial clusters if available
             if result.spatial_clusters and len(result.spatial_clusters) > 1:
                 print(f"   🗂️ Spatial Clusters: {len(result.spatial_clusters)}")
                 for j, cluster in enumerate(result.spatial_clusters[:2]):  # Show top 2 clusters
                     cluster_score = max(p.score for p in cluster)
-                    print(f"      Cluster {j+1}: {len(cluster)} patches (best: {cluster_score:.4f})")
+                    print(
+                        f"      Cluster {j + 1}: {len(cluster)} patches (best: {cluster_score:.4f})"
+                    )
+
 
 def demo_aggregation():
     """Demonstrate the multi-vector aggregation functionality."""
     print("=== Multi-Vector Aggregation Demo ===")
-    
+
     # Simulate some patch-level search results
     # In real usage, these would come from LeannSearcher.search()
-    
+
     class MockResult:
         def __init__(self, score, metadata):
             self.score = score
             self.metadata = metadata
-    
+
     # Simulate results for 2 images with multiple patches each
     mock_results = [
         # Image 1: cats_and_kitchen.jpg - 4 patches
-        MockResult(0.85, {
-            "image_name": "cats_and_kitchen.jpg",
-            "image_path": "/path/to/cats_and_kitchen.jpg",
-            "patch_id": 3,
-            "coordinates": [100, 50, 224, 174],  # Kitchen area
-            "attention_score": 0.92,
-            "scale": 1.0
-        }),
-        MockResult(0.78, {
-            "image_name": "cats_and_kitchen.jpg", 
-            "image_path": "/path/to/cats_and_kitchen.jpg",
-            "patch_id": 7,
-            "coordinates": [200, 300, 324, 424],  # Cat area
-            "attention_score": 0.88,
-            "scale": 1.0
-        }),
-        MockResult(0.72, {
-            "image_name": "cats_and_kitchen.jpg",
-            "image_path": "/path/to/cats_and_kitchen.jpg", 
-            "patch_id": 12,
-            "coordinates": [150, 100, 274, 224],  # Appliances
-            "attention_score": 0.75,
-            "scale": 1.0
-        }),
-        MockResult(0.65, {
-            "image_name": "cats_and_kitchen.jpg",
-            "image_path": "/path/to/cats_and_kitchen.jpg",
-            "patch_id": 15,
-            "coordinates": [50, 250, 174, 374],  # Furniture
-            "attention_score": 0.70,
-            "scale": 1.0
-        }),
-        
-        # Image 2: city_street.jpg - 3 patches  
-        MockResult(0.68, {
-            "image_name": "city_street.jpg",
-            "image_path": "/path/to/city_street.jpg",
-            "patch_id": 2,
-            "coordinates": [300, 100, 424, 224],  # Buildings
-            "attention_score": 0.80,
-            "scale": 1.0
-        }),
-        MockResult(0.62, {
-            "image_name": "city_street.jpg",
-            "image_path": "/path/to/city_street.jpg",
-            "patch_id": 8,
-            "coordinates": [100, 350, 224, 474],  # Street level
-            "attention_score": 0.75,
-            "scale": 1.0
-        }),
-        MockResult(0.55, {
-            "image_name": "city_street.jpg", 
-            "image_path": "/path/to/city_street.jpg",
-            "patch_id": 11,
-            "coordinates": [400, 200, 524, 324],  # Sky area
-            "attention_score": 0.60,
-            "scale": 1.0
-        }),
+        MockResult(
+            0.85,
+            {
+                "image_name": "cats_and_kitchen.jpg",
+                "image_path": "/path/to/cats_and_kitchen.jpg",
+                "patch_id": 3,
+                "coordinates": [100, 50, 224, 174],  # Kitchen area
+                "attention_score": 0.92,
+                "scale": 1.0,
+            },
+        ),
+        MockResult(
+            0.78,
+            {
+                "image_name": "cats_and_kitchen.jpg",
+                "image_path": "/path/to/cats_and_kitchen.jpg",
+                "patch_id": 7,
+                "coordinates": [200, 300, 324, 424],  # Cat area
+                "attention_score": 0.88,
+                "scale": 1.0,
+            },
+        ),
+        MockResult(
+            0.72,
+            {
+                "image_name": "cats_and_kitchen.jpg",
+                "image_path": "/path/to/cats_and_kitchen.jpg",
+                "patch_id": 12,
+                "coordinates": [150, 100, 274, 224],  # Appliances
+                "attention_score": 0.75,
+                "scale": 1.0,
+            },
+        ),
+        MockResult(
+            0.65,
+            {
+                "image_name": "cats_and_kitchen.jpg",
+                "image_path": "/path/to/cats_and_kitchen.jpg",
+                "patch_id": 15,
+                "coordinates": [50, 250, 174, 374],  # Furniture
+                "attention_score": 0.70,
+                "scale": 1.0,
+            },
+        ),
+        # Image 2: city_street.jpg - 3 patches
+        MockResult(
+            0.68,
+            {
+                "image_name": "city_street.jpg",
+                "image_path": "/path/to/city_street.jpg",
+                "patch_id": 2,
+                "coordinates": [300, 100, 424, 224],  # Buildings
+                "attention_score": 0.80,
+                "scale": 1.0,
+            },
+        ),
+        MockResult(
+            0.62,
+            {
+                "image_name": "city_street.jpg",
+                "image_path": "/path/to/city_street.jpg",
+                "patch_id": 8,
+                "coordinates": [100, 350, 224, 474],  # Street level
+                "attention_score": 0.75,
+                "scale": 1.0,
+            },
+        ),
+        MockResult(
+            0.55,
+            {
+                "image_name": "city_street.jpg",
+                "image_path": "/path/to/city_street.jpg",
+                "patch_id": 11,
+                "coordinates": [400, 200, 524, 324],  # Sky area
+                "attention_score": 0.60,
+                "scale": 1.0,
+            },
+        ),
     ]
-    
+
     # Test different aggregation methods
     methods = ["maxsim", "voting", "weighted", "mean"]
-    
+
     for method in methods:
-        print(f"\n{'='*20} {method.upper()} AGGREGATION {'='*20}")
-        
+        print(f"\n{'=' * 20} {method.upper()} AGGREGATION {'=' * 20}")
+
         aggregator = MultiVectorAggregator(
             aggregation_method=method,
             spatial_clustering=True,
-            cluster_distance_threshold=100.0
+            cluster_distance_threshold=100.0,
         )
-        
+
         aggregated = aggregator.aggregate_results(mock_results, top_k=5)
         aggregator.print_aggregated_results(aggregated)
 
+
 if __name__ == "__main__":
-    demo_aggregation()
+    demo_aggregation()

examples/openai_hnsw_example.py

@@ -6,22 +6,24 @@ Complete example showing how to build and search with OpenAI embeddings using HN
 """
 
 import os
-import dotenv
 from pathlib import Path
+
+import dotenv
 from leann.api import LeannBuilder, LeannSearcher
 
 # Load environment variables
 dotenv.load_dotenv()
 
+
 def main():
     # Check if OpenAI API key is available
     api_key = os.getenv("OPENAI_API_KEY")
     if not api_key:
         print("ERROR: OPENAI_API_KEY environment variable not set")
         return False
-    
+
     print(f"✅ OpenAI API key found: {api_key[:10]}...")
-    
+
     # Sample texts
     sample_texts = [
         "Machine learning is a powerful technology that enables computers to learn from data.",
@@ -33,15 +35,15 @@ def main():
         "Artificial intelligence aims to create machines that can perform human-like tasks.",
         "Python is a popular programming language used extensively in data science and AI.",
         "Neural networks are inspired by the structure and function of the human brain.",
-        "Big data refers to extremely large datasets that require special tools to process."
+        "Big data refers to extremely large datasets that require special tools to process.",
     ]
-    
+
     INDEX_DIR = Path("./simple_openai_test_index")
     INDEX_PATH = str(INDEX_DIR / "simple_test.leann")
-    
-    print(f"\n=== Building Index with OpenAI Embeddings ===")
+
+    print("\n=== Building Index with OpenAI Embeddings ===")
     print(f"Index path: {INDEX_PATH}")
-    
+
     try:
         # Use proper configuration for OpenAI embeddings
         builder = LeannBuilder(
@@ -49,60 +51,63 @@ def main():
             embedding_model="text-embedding-3-small",
             embedding_mode="openai",
             # HNSW settings for OpenAI embeddings
-            M=16,                    # Smaller graph degree
-            efConstruction=64,       # Smaller construction complexity  
-            is_compact=True,         # Enable compact storage for recompute
-            is_recompute=True,       # MUST enable for OpenAI embeddings
+            M=16,  # Smaller graph degree
+            efConstruction=64,  # Smaller construction complexity
+            is_compact=True,  # Enable compact storage for recompute
+            is_recompute=True,  # MUST enable for OpenAI embeddings
             num_threads=1,
         )
-        
+
         print(f"Adding {len(sample_texts)} texts to the index...")
         for i, text in enumerate(sample_texts):
             metadata = {"id": f"doc_{i}", "topic": "AI"}
             builder.add_text(text, metadata)
-        
+
         print("Building index...")
         builder.build_index(INDEX_PATH)
-        print(f"✅ Index built successfully!")
-        
+        print("✅ Index built successfully!")
+
     except Exception as e:
         print(f"❌ Error building index: {e}")
         import traceback
+
         traceback.print_exc()
         return False
-    
-    print(f"\n=== Testing Search ===")
-    
+
+    print("\n=== Testing Search ===")
+
     try:
         searcher = LeannSearcher(INDEX_PATH)
-        
+
         test_queries = [
             "What is machine learning?",
             "How do neural networks work?",
-            "Programming languages for data science"
+            "Programming languages for data science",
         ]
-        
+
         for query in test_queries:
             print(f"\n🔍 Query: '{query}'")
             results = searcher.search(query, top_k=3)
-            
+
             print(f"   Found {len(results)} results:")
             for i, result in enumerate(results):
-                print(f"   {i+1}. Score: {result.score:.4f}")
+                print(f"   {i + 1}. Score: {result.score:.4f}")
                 print(f"      Text: {result.text[:80]}...")
-        
-        print(f"\n✅ Search test completed successfully!")
+
+        print("\n✅ Search test completed successfully!")
         return True
-        
+
     except Exception as e:
         print(f"❌ Error during search: {e}")
         import traceback
+
         traceback.print_exc()
         return False
 
+
 if __name__ == "__main__":
     success = main()
     if success:
-        print(f"\n🎉 Simple OpenAI index test completed successfully!")
+        print("\n🎉 Simple OpenAI index test completed successfully!")
     else:
-        print(f"\n💥 Simple OpenAI index test failed!")
+        print("\n💥 Simple OpenAI index test failed!")

examples/resue_index.py

@@ -1,18 +1,23 @@
 import asyncio
-from leann.api import LeannChat
 from pathlib import Path
 
+from leann.api import LeannChat
+
 INDEX_DIR = Path("./test_pdf_index_huawei")
 INDEX_PATH = str(INDEX_DIR / "pdf_documents.leann")
 
+
 async def main():
-    print(f"\n[PHASE 2] Starting Leann chat session...")
+    print("\n[PHASE 2] Starting Leann chat session...")
     chat = LeannChat(index_path=INDEX_PATH)
     query = "What is the main idea of RL and give me 5 exapmle of classic RL algorithms?"
     query = "Based on the paper, what are the main techniques LEANN explores to reduce the storage overhead and DLPM explore to achieve Fairness and Efiiciency trade-off?"
-    # query = "什么是盘古大模型以及盘古开发过程中遇到了什么阴暗面，任务令一般在什么城市颁发"
-    response = chat.ask(query,top_k=20,recompute_beighbor_embeddings=True,complexity=32,beam_width=1)
+    # query = "什么是盘古大模型以及盘古开发过程中遇到了什么阴暗面,任务令一般在什么城市颁发"
+    response = chat.ask(
+        query, top_k=20, recompute_beighbor_embeddings=True, complexity=32, beam_width=1
+    )
     print(f"\n[PHASE 2] Response: {response}")
 
+
 if __name__ == "__main__":
-    asyncio.run(main())
+    asyncio.run(main())

examples/run_evaluation.py

@@ -5,24 +5,21 @@ It correctly compares results by fetching the text content for both the new sear
 results and the golden standard results, making the comparison robust to ID changes.
 """
 
-import json
 import argparse
+import json
+import sys
 import time
 from pathlib import Path
-import sys
-import numpy as np
-from typing import List
 
-from leann.api import LeannSearcher, LeannBuilder
+import numpy as np
+from leann.api import LeannBuilder, LeannSearcher
 
 
 def download_data_if_needed(data_root: Path, download_embeddings: bool = False):
     """Checks if the data directory exists, and if not, downloads it from HF Hub."""
     if not data_root.exists():
         print(f"Data directory '{data_root}' not found.")
-        print(
-            "Downloading evaluation data from Hugging Face Hub... (this may take a moment)"
-        )
+        print("Downloading evaluation data from Hugging Face Hub... (this may take a moment)")
         try:
             from huggingface_hub import snapshot_download
 
@@ -63,7 +60,7 @@ def download_data_if_needed(data_root: Path, download_embeddings: bool = False):
             sys.exit(1)
 
 
-def download_embeddings_if_needed(data_root: Path, dataset_type: str = None):
+def download_embeddings_if_needed(data_root: Path, dataset_type: str | None = None):
     """Download embeddings files specifically."""
     embeddings_dir = data_root / "embeddings"
 
@@ -101,7 +98,7 @@ def download_embeddings_if_needed(data_root: Path, dataset_type: str = None):
 
 
 # --- Helper Function to get Golden Passages ---
-def get_golden_texts(searcher: LeannSearcher, golden_ids: List[int]) -> set:
+def get_golden_texts(searcher: LeannSearcher, golden_ids: list[int]) -> set:
     """
     Retrieves the text for golden passage IDs directly from the LeannSearcher's
     passage manager.
@@ -113,24 +110,20 @@ def get_golden_texts(searcher: LeannSearcher, golden_ids: List[int]) -> set:
             passage_data = searcher.passage_manager.get_passage(str(gid))
             golden_texts.add(passage_data["text"])
         except KeyError:
-            print(
-                f"Warning: Golden passage ID '{gid}' not found in the index's passage data."
-            )
+            print(f"Warning: Golden passage ID '{gid}' not found in the index's passage data.")
     return golden_texts
 
 
-def load_queries(file_path: Path) -> List[str]:
+def load_queries(file_path: Path) -> list[str]:
     queries = []
-    with open(file_path, "r", encoding="utf-8") as f:
+    with open(file_path, encoding="utf-8") as f:
         for line in f:
             data = json.loads(line)
             queries.append(data["query"])
     return queries
 
 
-def build_index_from_embeddings(
-    embeddings_file: str, output_path: str, backend: str = "hnsw"
-):
+def build_index_from_embeddings(embeddings_file: str, output_path: str, backend: str = "hnsw"):
     """
     Build a LEANN index from pre-computed embeddings.
 
@@ -173,9 +166,7 @@ def build_index_from_embeddings(
 
 
 def main():
-    parser = argparse.ArgumentParser(
-        description="Run recall evaluation on a LEANN index."
-    )
+    parser = argparse.ArgumentParser(description="Run recall evaluation on a LEANN index.")
     parser.add_argument(
         "index_path",
         type=str,
@@ -202,9 +193,7 @@ def main():
     parser.add_argument(
         "--num-queries", type=int, default=10, help="Number of queries to evaluate."
     )
-    parser.add_argument(
-        "--top-k", type=int, default=3, help="The 'k' value for recall@k."
-    )
+    parser.add_argument("--top-k", type=int, default=3, help="The 'k' value for recall@k.")
     parser.add_argument(
         "--ef-search", type=int, default=120, help="The 'efSearch' parameter for HNSW."
     )
@@ -219,9 +208,7 @@ def main():
     # Download data based on mode
     if args.mode == "build":
         # For building mode, we need embeddings
-        download_data_if_needed(
-            data_root, download_embeddings=False
-        )  # Basic data first
+        download_data_if_needed(data_root, download_embeddings=False)  # Basic data first
 
         # Auto-detect dataset type and download embeddings
         if args.embeddings_file:
@@ -262,9 +249,7 @@ def main():
         print(f"Index built successfully: {built_index_path}")
 
         # Ask if user wants to run evaluation
-        eval_response = (
-            input("Run evaluation on the built index? (y/n): ").strip().lower()
-        )
+        eval_response = input("Run evaluation on the built index? (y/n): ").strip().lower()
         if eval_response != "y":
             print("Index building complete. Exiting.")
             return
@@ -293,12 +278,8 @@ def main():
                         break
 
             if not args.index_path:
-                print(
-                    "No indices found. The data download should have included pre-built indices."
-                )
-                print(
-                    "Please check the data/indices/ directory or provide --index-path manually."
-                )
+                print("No indices found. The data download should have included pre-built indices.")
+                print("Please check the data/indices/ directory or provide --index-path manually.")
                 sys.exit(1)
 
     # Detect dataset type from index path to select the correct ground truth
@@ -310,14 +291,10 @@ def main():
     else:
         # Fallback: try to infer from the index directory name
         dataset_type = Path(args.index_path).name
-        print(
-            f"WARNING: Could not detect dataset type from path, inferred '{dataset_type}'."
-        )
+        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"
-    )
+    golden_results_file = data_root / "ground_truth" / dataset_type / "flat_results_nq_k3.json"
 
     print(f"INFO: Detected dataset type: {dataset_type}")
     print(f"INFO: Using queries file: {queries_file}")
@@ -327,7 +304,7 @@ def main():
         searcher = LeannSearcher(args.index_path)
         queries = load_queries(queries_file)
 
-        with open(golden_results_file, "r") as f:
+        with open(golden_results_file) as f:
             golden_results_data = json.load(f)
 
         num_eval_queries = min(args.num_queries, len(queries))
@@ -339,9 +316,7 @@ def main():
 
         for i in range(num_eval_queries):
             start_time = time.time()
-            new_results = searcher.search(
-                queries[i], top_k=args.top_k, ef=args.ef_search
-            )
+            new_results = searcher.search(queries[i], top_k=args.top_k, ef=args.ef_search)
             search_times.append(time.time() - start_time)
 
             # Correct Recall Calculation: Based on TEXT content

examples/simple_demo.py

@@ -4,18 +4,25 @@ Run: uv run python examples/simple_demo.py
 """
 
 import argparse
-from leann import LeannBuilder, LeannSearcher, LeannChat
+
+from leann import LeannBuilder, LeannChat, LeannSearcher
 
 
 def main():
-    parser = argparse.ArgumentParser(description="Simple demo of Leann with selectable embedding models.")
-    parser.add_argument("--embedding_model", type=str, default="sentence-transformers/all-mpnet-base-v2",
-                        help="The embedding model to use, e.g., 'sentence-transformers/all-mpnet-base-v2' or 'text-embedding-ada-002'.")
+    parser = argparse.ArgumentParser(
+        description="Simple demo of Leann with selectable embedding models."
+    )
+    parser.add_argument(
+        "--embedding_model",
+        type=str,
+        default="sentence-transformers/all-mpnet-base-v2",
+        help="The embedding model to use, e.g., 'sentence-transformers/all-mpnet-base-v2' or 'text-embedding-ada-002'.",
+    )
     args = parser.parse_args()
 
     print(f"=== Leann Simple Demo with {args.embedding_model} ===")
     print()
-    
+
     # Sample knowledge base
     chunks = [
         "Machine learning is a subset of artificial intelligence that enables computers to learn without being explicitly programmed.",
@@ -27,7 +34,7 @@ def main():
         "Big data refers to extremely large datasets that require special tools and techniques to process.",
         "Cloud computing provides on-demand access to computing resources over the internet.",
     ]
-    
+
     print("1. Building index (no embeddings stored)...")
     builder = LeannBuilder(
         embedding_model=args.embedding_model,
@@ -37,45 +44,45 @@ def main():
         builder.add_text(chunk)
     builder.build_index("demo_knowledge.leann")
     print()
-    
+
     print("2. Searching with real-time embeddings...")
     searcher = LeannSearcher("demo_knowledge.leann")
-    
+
     queries = [
         "What is machine learning?",
-        "How does neural network work?", 
+        "How does neural network work?",
         "Tell me about data processing",
     ]
-    
+
     for query in queries:
         print(f"Query: {query}")
         results = searcher.search(query, top_k=2)
-        
+
         for i, result in enumerate(results, 1):
             print(f"  {i}. Score: {result.score:.3f}")
             print(f"     Text: {result.text[:100]}...")
         print()
-    
+
     print("3. Interactive chat demo:")
     print("   (Note: Requires OpenAI API key for real responses)")
-    
+
     chat = LeannChat("demo_knowledge.leann")
-    
+
     # Demo questions
     demo_questions: list[str] = [
         "What is the difference between machine learning and deep learning?",
         "How is data science related to big data?",
     ]
-    
+
     for question in demo_questions:
         print(f"   Q: {question}")
         response = chat.ask(question)
         print(f"   A: {response}")
         print()
-    
+
     print("Demo completed! Try running:")
     print("   uv run python examples/document_search.py")
 
 
 if __name__ == "__main__":
-    main()
+    main()

examples/wechat_history_reader_leann.py

@@ -1,13 +1,11 @@
-import os
-import asyncio
-import dotenv
 import argparse
+import asyncio
+import os
 from pathlib import Path
-from typing import List, Any, Optional
-from leann.api import LeannBuilder, LeannSearcher, LeannChat
+
+import dotenv
+from leann.api import LeannBuilder, LeannChat
 from llama_index.core.node_parser import SentenceSplitter
-import requests
-import time
 
 dotenv.load_dotenv()
 
@@ -16,7 +14,7 @@ DEFAULT_WECHAT_EXPORT_DIR = "./wechat_export_direct"
 
 
 def create_leann_index_from_multiple_wechat_exports(
-    export_dirs: List[Path],
+    export_dirs: list[Path],
     index_path: str = "wechat_history_index.leann",
     max_count: int = -1,
 ):
@@ -38,15 +36,13 @@ def create_leann_index_from_multiple_wechat_exports(
     INDEX_DIR = Path(index_path).parent
 
     if not INDEX_DIR.exists():
-        print(f"--- Index directory not found, building new index ---")
+        print("--- Index directory not found, building new index ---")
         all_documents = []
         total_processed = 0
 
         # Process each WeChat export directory
         for i, export_dir in enumerate(export_dirs):
-            print(
-                f"\nProcessing WeChat export {i + 1}/{len(export_dirs)}: {export_dir}"
-            )
+            print(f"\nProcessing WeChat export {i + 1}/{len(export_dirs)}: {export_dir}")
 
             try:
                 documents = reader.load_data(
@@ -86,7 +82,12 @@ def create_leann_index_from_multiple_wechat_exports(
             # Split the document into chunks
             nodes = text_splitter.get_nodes_from_documents([doc])
             for node in nodes:
-                text = '[Contact] means the message is from: ' + doc.metadata["contact_name"] + '\n' + node.get_content()
+                text = (
+                    "[Contact] means the message is from: "
+                    + doc.metadata["contact_name"]
+                    + "\n"
+                    + node.get_content()
+                )
                 all_texts.append(text)
 
         print(
@@ -94,12 +95,12 @@ def create_leann_index_from_multiple_wechat_exports(
         )
 
         # Create LEANN index directory
-        print(f"--- Index directory not found, building new index ---")
+        print("--- Index directory not found, building new index ---")
         INDEX_DIR.mkdir(exist_ok=True)
 
-        print(f"--- Building new LEANN index ---")
+        print("--- Building new LEANN index ---")
 
-        print(f"\n[PHASE 1] Building Leann index...")
+        print("\n[PHASE 1] Building Leann index...")
 
         # Use HNSW backend for better macOS compatibility
         builder = LeannBuilder(
@@ -125,7 +126,7 @@ def create_leann_index_from_multiple_wechat_exports(
 
 
 def create_leann_index(
-    export_dir: str = None,
+    export_dir: str | None = None,
     index_path: str = "wechat_history_index.leann",
     max_count: int = 1000,
 ):
@@ -141,12 +142,12 @@ def create_leann_index(
     INDEX_DIR = Path(index_path).parent
 
     if not INDEX_DIR.exists():
-        print(f"--- Index directory not found, building new index ---")
+        print("--- Index directory not found, building new index ---")
         INDEX_DIR.mkdir(exist_ok=True)
 
-        print(f"--- Building new LEANN index ---")
+        print("--- Building new LEANN index ---")
 
-        print(f"\n[PHASE 1] Building Leann index...")
+        print("\n[PHASE 1] Building Leann index...")
 
         # Load documents using WeChatHistoryReader from history_data
         from history_data.wechat_history import WeChatHistoryReader
@@ -179,12 +180,12 @@ def create_leann_index(
         print(f"Created {len(all_texts)} text chunks from {len(documents)} documents")
 
         # Create LEANN index directory
-        print(f"--- Index directory not found, building new index ---")
+        print("--- Index directory not found, building new index ---")
         INDEX_DIR.mkdir(exist_ok=True)
 
-        print(f"--- Building new LEANN index ---")
+        print("--- Building new LEANN index ---")
 
-        print(f"\n[PHASE 1] Building Leann index...")
+        print("\n[PHASE 1] Building Leann index...")
 
         # Use HNSW backend for better macOS compatibility
         builder = LeannBuilder(
@@ -217,7 +218,7 @@ async def query_leann_index(index_path: str, query: str):
         index_path: Path to the LEANN index
         query: The query string
     """
-    print(f"\n[PHASE 2] Starting Leann chat session...")
+    print("\n[PHASE 2] Starting Leann chat session...")
     chat = LeannChat(index_path=index_path)
 
     print(f"You: {query}")
@@ -307,7 +308,7 @@ async def main():
         else:
             # Example queries
             queries = [
-                "我想买魔术师约翰逊的球衣，给我一些对应聊天记录?",
+                "我想买魔术师约翰逊的球衣,给我一些对应聊天记录?",
             ]
 
             for query in queries:

packages/__init__.py

@@ -1 +0,0 @@
-

packages/leann-backend-diskann/__init__.py

@@ -1 +1 @@
-# This file makes the directory a Python package 
+# This file makes the directory a Python package

packages/leann-backend-diskann/leann_backend_diskann/__init__.py

@@ -1 +1 @@
-from . import diskann_backend
+from . import diskann_backend as diskann_backend

packages/leann-backend-diskann/leann_backend_diskann/diskann_backend.py

@@ -1,20 +1,19 @@
-import numpy as np
+import contextlib
+import logging
 import os
 import struct
 import sys
 from pathlib import Path
-from typing import Dict, Any, List, Literal, Optional
-import contextlib
+from typing import Any, Literal
 
-import logging
-
-from leann.searcher_base import BaseSearcher
-from leann.registry import register_backend
+import numpy as np
 from leann.interface import (
-    LeannBackendFactoryInterface,
     LeannBackendBuilderInterface,
+    LeannBackendFactoryInterface,
     LeannBackendSearcherInterface,
 )
+from leann.registry import register_backend
+from leann.searcher_base import BaseSearcher
 
 logger = logging.getLogger(__name__)
 
@@ -100,7 +99,7 @@ class DiskannBuilder(LeannBackendBuilderInterface):
     def __init__(self, **kwargs):
         self.build_params = kwargs
 
-    def build(self, data: np.ndarray, ids: List[str], index_path: str, **kwargs):
+    def build(self, data: np.ndarray, ids: list[str], index_path: str, **kwargs):
         path = Path(index_path)
         index_dir = path.parent
         index_prefix = path.stem
@@ -164,18 +163,44 @@ class DiskannSearcher(BaseSearcher):
 
             self.num_threads = kwargs.get("num_threads", 8)
 
-            fake_zmq_port = 6666
+            # For DiskANN, we need to reinitialize the index when zmq_port changes
+            # Store the initialization parameters for later use
             full_index_prefix = str(self.index_dir / self.index_path.stem)
-            self._index = diskannpy.StaticDiskFloatIndex(
-                metric_enum,
-                full_index_prefix,
-                self.num_threads,
-                kwargs.get("num_nodes_to_cache", 0),
-                1,
-                fake_zmq_port,  # Initial port, can be updated at runtime
-                "",
-                "",
-            )
+            self._init_params = {
+                "metric_enum": metric_enum,
+                "full_index_prefix": full_index_prefix,
+                "num_threads": self.num_threads,
+                "num_nodes_to_cache": kwargs.get("num_nodes_to_cache", 0),
+                "cache_mechanism": 1,
+                "pq_prefix": "",
+                "partition_prefix": "",
+            }
+            self._diskannpy = diskannpy
+            self._current_zmq_port = None
+            self._index = None
+            logger.debug("DiskANN searcher initialized (index will be loaded on first search)")
+
+    def _ensure_index_loaded(self, zmq_port: int):
+        """Ensure the index is loaded with the correct zmq_port."""
+        if self._index is None or self._current_zmq_port != zmq_port:
+            # Need to (re)load the index with the correct zmq_port
+            with suppress_cpp_output_if_needed():
+                if self._index is not None:
+                    logger.debug(f"Reloading DiskANN index with new zmq_port: {zmq_port}")
+                else:
+                    logger.debug(f"Loading DiskANN index with zmq_port: {zmq_port}")
+
+                self._index = self._diskannpy.StaticDiskFloatIndex(
+                    self._init_params["metric_enum"],
+                    self._init_params["full_index_prefix"],
+                    self._init_params["num_threads"],
+                    self._init_params["num_nodes_to_cache"],
+                    self._init_params["cache_mechanism"],
+                    zmq_port,
+                    self._init_params["pq_prefix"],
+                    self._init_params["partition_prefix"],
+                )
+                self._current_zmq_port = zmq_port
 
     def search(
         self,
@@ -186,11 +211,11 @@ class DiskannSearcher(BaseSearcher):
         prune_ratio: float = 0.0,
         recompute_embeddings: bool = False,
         pruning_strategy: Literal["global", "local", "proportional"] = "global",
-        zmq_port: Optional[int] = None,
+        zmq_port: int | None = None,
         batch_recompute: bool = False,
         dedup_node_dis: bool = False,
         **kwargs,
-    ) -> Dict[str, Any]:
+    ) -> dict[str, Any]:
         """
         Search for nearest neighbors using DiskANN index.
 
@@ -213,18 +238,15 @@ class DiskannSearcher(BaseSearcher):
         Returns:
             Dict with 'labels' (list of lists) and 'distances' (ndarray)
         """
-        # Handle zmq_port compatibility: DiskANN can now update port at runtime
+        # Handle zmq_port compatibility: Ensure index is loaded with correct port
         if recompute_embeddings:
             if zmq_port is None:
-                raise ValueError(
-                    "zmq_port must be provided if recompute_embeddings is True"
-                )
-            current_port = self._index.get_zmq_port()
-            if zmq_port != current_port:
-                logger.debug(
-                    f"Updating DiskANN zmq_port from {current_port} to {zmq_port}"
-                )
-                self._index.set_zmq_port(zmq_port)
+                raise ValueError("zmq_port must be provided if recompute_embeddings is True")
+            self._ensure_index_loaded(zmq_port)
+        else:
+            # If not recomputing, we still need an index, use a default port
+            if self._index is None:
+                self._ensure_index_loaded(6666)  # Default port when not recomputing
 
         # DiskANN doesn't support "proportional" strategy
         if pruning_strategy == "proportional":
@@ -259,8 +281,6 @@ class DiskannSearcher(BaseSearcher):
                 use_global_pruning,
             )
 
-        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}

packages/leann-backend-diskann/leann_backend_diskann/diskann_embedding_server.py

@@ -3,16 +3,16 @@ DiskANN-specific embedding server
 """
 
 import argparse
+import json
+import logging
+import os
+import sys
 import threading
 import time
-import os
-import zmq
-import numpy as np
-import json
 from pathlib import Path
-from typing import Optional
-import sys
-import logging
+
+import numpy as np
+import zmq
 
 # Set up logging based on environment variable
 LOG_LEVEL = os.getenv("LEANN_LOG_LEVEL", "WARNING").upper()
@@ -32,7 +32,7 @@ if not logger.handlers:
 
 
 def create_diskann_embedding_server(
-    passages_file: Optional[str] = None,
+    passages_file: str | None = None,
     zmq_port: int = 5555,
     model_name: str = "sentence-transformers/all-mpnet-base-v2",
     embedding_mode: str = "sentence-transformers",
@@ -50,8 +50,8 @@ def create_diskann_embedding_server(
     sys.path.insert(0, str(leann_core_path))
 
     try:
-        from leann.embedding_compute import compute_embeddings
         from leann.api import PassageManager
+        from leann.embedding_compute import compute_embeddings
 
         logger.info("Successfully imported unified embedding computation module")
     except ImportError as e:
@@ -76,7 +76,7 @@ def create_diskann_embedding_server(
         raise ValueError("Only metadata files (.meta.json) are supported")
 
     # Load metadata to get passage sources
-    with open(passages_file, "r") as f:
+    with open(passages_file) as f:
         meta = json.load(f)
 
     passages = PassageManager(meta["passage_sources"])
@@ -150,9 +150,7 @@ def create_diskann_embedding_server(
                         ):
                             texts = request
                             is_text_request = True
-                            logger.info(
-                                f"✅ MSGPACK: Direct text request for {len(texts)} texts"
-                            )
+                            logger.info(f"✅ MSGPACK: Direct text request for {len(texts)} texts")
                         else:
                             raise ValueError("Not a valid msgpack text request")
                     except Exception as msgpack_error:
@@ -167,9 +165,7 @@ def create_diskann_embedding_server(
                             passage_data = passages.get_passage(str(nid))
                             txt = passage_data["text"]
                             if not txt:
-                                raise RuntimeError(
-                                    f"FATAL: Empty text for passage ID {nid}"
-                                )
+                                raise RuntimeError(f"FATAL: Empty text for passage ID {nid}")
                             texts.append(txt)
                         except KeyError as e:
                             logger.error(f"Passage ID {nid} not found: {e}")
@@ -180,9 +176,7 @@ def create_diskann_embedding_server(
 
                     # Debug logging
                     logger.debug(f"Processing {len(texts)} texts")
-                    logger.debug(
-                        f"Text lengths: {[len(t) for t in texts[:5]]}"
-                    )  # Show first 5
+                    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)
@@ -199,9 +193,7 @@ def create_diskann_embedding_server(
                 else:
                     # For DiskANN C++ compatibility: return protobuf format
                     resp_proto = embedding_pb2.NodeEmbeddingResponse()
-                    hidden_contiguous = np.ascontiguousarray(
-                        embeddings, dtype=np.float32
-                    )
+                    hidden_contiguous = np.ascontiguousarray(embeddings, dtype=np.float32)
 
                     # Serialize embeddings data
                     resp_proto.embeddings_data = hidden_contiguous.tobytes()

packages/leann-backend-diskann/leann_backend_diskann/embedding_pb2.py

@@ -1,27 +1,28 @@
-# -*- coding: utf-8 -*-
 # Generated by the protocol buffer compiler.  DO NOT EDIT!
 # source: embedding.proto
+# ruff: noqa
 """Generated protocol buffer code."""
-from google.protobuf.internal import builder as _builder
+
 from google.protobuf import descriptor as _descriptor
 from google.protobuf import descriptor_pool as _descriptor_pool
 from google.protobuf import symbol_database as _symbol_database
+from google.protobuf.internal import builder as _builder
+
 # @@protoc_insertion_point(imports)
 
 _sym_db = _symbol_database.Default()
 
 
-
-
-DESCRIPTOR = _descriptor_pool.Default().AddSerializedFile(b'\n\x0f\x65mbedding.proto\x12\x0eprotoembedding\"(\n\x14NodeEmbeddingRequest\x12\x10\n\x08node_ids\x18\x01 \x03(\r\"Y\n\x15NodeEmbeddingResponse\x12\x17\n\x0f\x65mbeddings_data\x18\x01 \x01(\x0c\x12\x12\n\ndimensions\x18\x02 \x03(\x05\x12\x13\n\x0bmissing_ids\x18\x03 \x03(\rb\x06proto3')
+DESCRIPTOR = _descriptor_pool.Default().AddSerializedFile(
+    b'\n\x0f\x65mbedding.proto\x12\x0eprotoembedding"(\n\x14NodeEmbeddingRequest\x12\x10\n\x08node_ids\x18\x01 \x03(\r"Y\n\x15NodeEmbeddingResponse\x12\x17\n\x0f\x65mbeddings_data\x18\x01 \x01(\x0c\x12\x12\n\ndimensions\x18\x02 \x03(\x05\x12\x13\n\x0bmissing_ids\x18\x03 \x03(\rb\x06proto3'
+)
 
 _builder.BuildMessageAndEnumDescriptors(DESCRIPTOR, globals())
-_builder.BuildTopDescriptorsAndMessages(DESCRIPTOR, 'embedding_pb2', globals())
-if _descriptor._USE_C_DESCRIPTORS == False:
-
-  DESCRIPTOR._options = None
-  _NODEEMBEDDINGREQUEST._serialized_start=35
-  _NODEEMBEDDINGREQUEST._serialized_end=75
-  _NODEEMBEDDINGRESPONSE._serialized_start=77
-  _NODEEMBEDDINGRESPONSE._serialized_end=166
+_builder.BuildTopDescriptorsAndMessages(DESCRIPTOR, "embedding_pb2", globals())
+if not _descriptor._USE_C_DESCRIPTORS:
+    DESCRIPTOR._options = None
+    _NODEEMBEDDINGREQUEST._serialized_start = 35
+    _NODEEMBEDDINGREQUEST._serialized_end = 75
+    _NODEEMBEDDINGRESPONSE._serialized_start = 77
+    _NODEEMBEDDINGRESPONSE._serialized_end = 166
 # @@protoc_insertion_point(module_scope)

packages/leann-backend-diskann/pyproject.toml

@@ -4,8 +4,8 @@ build-backend = "scikit_build_core.build"
 
 [project]
 name = "leann-backend-diskann"
-version = "0.1.12"
-dependencies = ["leann-core==0.1.12", "numpy", "protobuf>=3.19.0"]
+version = "0.1.15"
+dependencies = ["leann-core==0.1.15", "numpy", "protobuf>=3.19.0"]
 
 [tool.scikit-build]
 # Key: simplified CMake path
@@ -16,4 +16,4 @@ wheel.packages = ["leann_backend_diskann"]
 editable.mode = "redirect"
 cmake.build-type = "Release"
 build.verbose = true
-build.tool-args = ["-j8"]
+build.tool-args = ["-j8"]

packages/leann-backend-diskann/third_party/embedding.proto

@@ -2,12 +2,12 @@ syntax = "proto3";
 
 package protoembedding;
 
-message NodeEmbeddingRequest { 
-  repeated uint32 node_ids = 1; 
+message NodeEmbeddingRequest {
+  repeated uint32 node_ids = 1;
 }
 
 message NodeEmbeddingResponse {
   bytes embeddings_data = 1;        // All embedded binary datas
   repeated int32 dimensions = 2;    // Shape [batch_size, embedding_dim]
   repeated uint32 missing_ids = 3;  // Missing node ids
-}
+}

packages/leann-backend-hnsw/CMakeLists.txt

@@ -52,4 +52,4 @@ set(FAISS_BUILD_AVX512 OFF CACHE BOOL "" FORCE)
 # IMPORTANT: Disable building AVX versions to speed up compilation
 set(FAISS_BUILD_AVX_VERSIONS OFF CACHE BOOL "" FORCE)
 
-add_subdirectory(third_party/faiss)
+add_subdirectory(third_party/faiss)

packages/leann-backend-hnsw/leann_backend_hnsw/__init__.py

@@ -1 +1 @@
-from . import hnsw_backend
+from . import hnsw_backend as hnsw_backend

packages/leann-backend-hnsw/leann_backend_hnsw/convert_to_csr.py

@@ -1,87 +1,115 @@
+import argparse
+import gc  # Import garbage collector interface
+import os
 import struct
 import sys
-import numpy as np
-import os
-import argparse
-import gc # Import garbage collector interface
 import time
+
+import numpy as np
+
 # --- FourCCs (add more if needed) ---
-INDEX_HNSW_FLAT_FOURCC = int.from_bytes(b'IHNf', 'little')
+INDEX_HNSW_FLAT_FOURCC = int.from_bytes(b"IHNf", "little")
 # Add other HNSW fourccs if you expect different storage types inside HNSW
 # INDEX_HNSW_PQ_FOURCC = int.from_bytes(b'IHNp', 'little')
 # INDEX_HNSW_SQ_FOURCC = int.from_bytes(b'IHNs', 'little')
 # INDEX_HNSW_CAGRA_FOURCC = int.from_bytes(b'IHNc', 'little') # Example
 
-EXPECTED_HNSW_FOURCCS = {INDEX_HNSW_FLAT_FOURCC} # Modify if needed
-NULL_INDEX_FOURCC = int.from_bytes(b'null', 'little')
+EXPECTED_HNSW_FOURCCS = {INDEX_HNSW_FLAT_FOURCC}  # Modify if needed
+NULL_INDEX_FOURCC = int.from_bytes(b"null", "little")
 
 # --- Helper functions for reading/writing binary data ---
 
+
 def read_struct(f, fmt):
     """Reads data according to the struct format."""
     size = struct.calcsize(fmt)
     data = f.read(size)
     if len(data) != size:
-        raise EOFError(f"File ended unexpectedly reading struct fmt '{fmt}'. Expected {size} bytes, got {len(data)}.")
+        raise EOFError(
+            f"File ended unexpectedly reading struct fmt '{fmt}'. Expected {size} bytes, got {len(data)}."
+        )
     return struct.unpack(fmt, data)[0]
 
+
 def read_vector_raw(f, element_fmt_char):
     """Reads a vector (size followed by data), returns count and raw bytes."""
-    count = -1 # Initialize count
-    total_bytes = -1 # Initialize total_bytes
+    count = -1  # Initialize count
+    total_bytes = -1  # Initialize total_bytes
     try:
-        count = read_struct(f, '<Q') # size_t usually 64-bit unsigned
+        count = read_struct(f, "<Q")  # size_t usually 64-bit unsigned
         element_size = struct.calcsize(element_fmt_char)
         # --- FIX for MemoryError: Check for unreasonably large count ---
-        max_reasonable_count = 10 * (10**9) # ~10 billion elements limit
+        max_reasonable_count = 10 * (10**9)  # ~10 billion elements limit
         if count > max_reasonable_count or count < 0:
-            raise MemoryError(f"Vector count {count} seems unreasonably large, possibly due to file corruption or incorrect format read.")
+            raise MemoryError(
+                f"Vector count {count} seems unreasonably large, possibly due to file corruption or incorrect format read."
+            )
 
         total_bytes = count * element_size
         # --- FIX for MemoryError: Check for huge byte size before allocation ---
-        max_reasonable_bytes = 50 * (1024**3) # ~50 GB limit
-        if total_bytes > max_reasonable_bytes or total_bytes < 0: # Check for overflow
-             raise MemoryError(f"Attempting to read {total_bytes} bytes ({count} elements * {element_size} bytes/element), which exceeds the safety limit. File might be corrupted or format mismatch.")
+        max_reasonable_bytes = 50 * (1024**3)  # ~50 GB limit
+        if total_bytes > max_reasonable_bytes or total_bytes < 0:  # Check for overflow
+            raise MemoryError(
+                f"Attempting to read {total_bytes} bytes ({count} elements * {element_size} bytes/element), which exceeds the safety limit. File might be corrupted or format mismatch."
+            )
 
         data_bytes = f.read(total_bytes)
 
         if len(data_bytes) != total_bytes:
-             raise EOFError(f"File ended unexpectedly reading vector data. Expected {total_bytes} bytes, got {len(data_bytes)}.")
+            raise EOFError(
+                f"File ended unexpectedly reading vector data. Expected {total_bytes} bytes, got {len(data_bytes)}."
+            )
         return count, data_bytes
     except (MemoryError, OverflowError) as e:
-         # Add context to the error message
-         print(f"\nError during raw vector read (element_fmt='{element_fmt_char}', count={count}, total_bytes={total_bytes}): {e}", file=sys.stderr)
-         raise e # Re-raise the original error type
+        # Add context to the error message
+        print(
+            f"\nError during raw vector read (element_fmt='{element_fmt_char}', count={count}, total_bytes={total_bytes}): {e}",
+            file=sys.stderr,
+        )
+        raise e  # Re-raise the original error type
+
 
 def read_numpy_vector(f, np_dtype, struct_fmt_char):
     """Reads a vector into a NumPy array."""
-    count = -1 # Initialize count for robust error handling
-    print(f"  Reading vector (dtype={np_dtype}, fmt='{struct_fmt_char}')... ", end='', flush=True)
+    count = -1  # Initialize count for robust error handling
+    print(
+        f"  Reading vector (dtype={np_dtype}, fmt='{struct_fmt_char}')... ",
+        end="",
+        flush=True,
+    )
     try:
         count, data_bytes = read_vector_raw(f, struct_fmt_char)
         print(f"Count={count}, Bytes={len(data_bytes)}")
         if count > 0 and len(data_bytes) > 0:
             arr = np.frombuffer(data_bytes, dtype=np_dtype)
             if arr.size != count:
-                raise ValueError(f"Inconsistent array size after reading. Expected {count}, got {arr.size}")
+                raise ValueError(
+                    f"Inconsistent array size after reading. Expected {count}, got {arr.size}"
+                )
             return arr
         elif count == 0:
-             return np.array([], dtype=np_dtype)
+            return np.array([], dtype=np_dtype)
         else:
-             raise ValueError("Read zero bytes but count > 0.")
+            raise ValueError("Read zero bytes but count > 0.")
     except MemoryError as e:
         # Now count should be defined (or -1 if error was in read_struct)
-        print(f"\nMemoryError creating NumPy array (dtype={np_dtype}, count={count}). {e}", file=sys.stderr)
+        print(
+            f"\nMemoryError creating NumPy array (dtype={np_dtype}, count={count}). {e}",
+            file=sys.stderr,
+        )
         raise e
-    except Exception as e: # Catch other potential errors like ValueError
-        print(f"\nError reading numpy vector (dtype={np_dtype}, fmt='{struct_fmt_char}', count={count}): {e}", file=sys.stderr)
+    except Exception as e:  # Catch other potential errors like ValueError
+        print(
+            f"\nError reading numpy vector (dtype={np_dtype}, fmt='{struct_fmt_char}', count={count}): {e}",
+            file=sys.stderr,
+        )
         raise e
 
 
 def write_numpy_vector(f, arr, struct_fmt_char):
     """Writes a NumPy array as a vector (size followed by data)."""
     count = arr.size
-    f.write(struct.pack('<Q', count))
+    f.write(struct.pack("<Q", count))
     try:
         expected_dtype = np.dtype(struct_fmt_char)
         if arr.dtype != expected_dtype:
@@ -89,23 +117,30 @@ def write_numpy_vector(f, arr, struct_fmt_char):
         else:
             data_to_write = arr.tobytes()
         f.write(data_to_write)
-        del data_to_write # Hint GC
+        del data_to_write  # Hint GC
     except MemoryError as e:
-         print(f"\nMemoryError converting NumPy array to bytes for writing (size={count}, dtype={arr.dtype}). {e}", file=sys.stderr)
-         raise e
+        print(
+            f"\nMemoryError converting NumPy array to bytes for writing (size={count}, dtype={arr.dtype}). {e}",
+            file=sys.stderr,
+        )
+        raise e
+
 
 def write_list_vector(f, lst, struct_fmt_char):
     """Writes a Python list as a vector iteratively."""
     count = len(lst)
-    f.write(struct.pack('<Q', count))
-    fmt = '<' + struct_fmt_char
+    f.write(struct.pack("<Q", count))
+    fmt = "<" + struct_fmt_char
     chunk_size = 1024 * 1024
     element_size = struct.calcsize(fmt)
     # Allocate buffer outside the loop if possible, or handle MemoryError during allocation
     try:
         buffer = bytearray(chunk_size * element_size)
     except MemoryError:
-        print(f"MemoryError: Cannot allocate buffer for writing list vector chunk (size {chunk_size * element_size} bytes).", file=sys.stderr)
+        print(
+            f"MemoryError: Cannot allocate buffer for writing list vector chunk (size {chunk_size * element_size} bytes).",
+            file=sys.stderr,
+        )
         raise
     buffer_count = 0
 
@@ -116,66 +151,80 @@ def write_list_vector(f, lst, struct_fmt_char):
             buffer_count += 1
 
             if buffer_count == chunk_size or i == count - 1:
-                f.write(buffer[:buffer_count * element_size])
+                f.write(buffer[: buffer_count * element_size])
                 buffer_count = 0
 
         except struct.error as e:
-            print(f"\nStruct packing error for item {item} at index {i} with format '{fmt}'. {e}", file=sys.stderr)
+            print(
+                f"\nStruct packing error for item {item} at index {i} with format '{fmt}'. {e}",
+                file=sys.stderr,
+            )
             raise e
 
 
 def get_cum_neighbors(cum_nneighbor_per_level_np, level):
     """Helper to get cumulative neighbors count, matching C++ logic."""
-    if level < 0: return 0
+    if level < 0:
+        return 0
     if level < len(cum_nneighbor_per_level_np):
         return cum_nneighbor_per_level_np[level]
     else:
         return cum_nneighbor_per_level_np[-1] if len(cum_nneighbor_per_level_np) > 0 else 0
 
-def 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, storage_fourcc, storage_data):
+
+def 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,
+    storage_fourcc,
+    storage_data,
+):
     """Write HNSW data in compact format following C++ read order exactly."""
     # Write IndexHNSW Header
-    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']))
+    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 HNSW struct parts (standard order)
-    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, assign_probas_np, "d")
+    write_numpy_vector(f_out, cum_nneighbor_per_level_np, "i")
+    write_numpy_vector(f_out, levels_np, "i")
 
     # Write compact format flag
-    f_out.write(struct.pack('<?', True)) # storage_is_compact = True
+    f_out.write(struct.pack("<?", True))  # storage_is_compact = True
 
     # Write compact data in CORRECT C++ read order: level_ptr, node_offsets FIRST
     if isinstance(compact_level_ptr, np.ndarray):
-        write_numpy_vector(f_out, compact_level_ptr, 'Q')
+        write_numpy_vector(f_out, compact_level_ptr, "Q")
     else:
-        write_list_vector(f_out, compact_level_ptr, 'Q')
-    
-    write_numpy_vector(f_out, compact_node_offsets_np, 'Q')
+        write_list_vector(f_out, compact_level_ptr, "Q")
+
+    write_numpy_vector(f_out, compact_node_offsets_np, "Q")
 
     # Write HNSW scalar parameters
-    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", 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"]))
 
     # Write storage fourcc (this determines how to read what follows)
-    f_out.write(struct.pack('<I', storage_fourcc))
-    
+    f_out.write(struct.pack("<I", storage_fourcc))
+
     # Write compact neighbors data AFTER storage fourcc
-    write_list_vector(f_out, compact_neighbors_data, 'i')
-    
+    write_list_vector(f_out, compact_neighbors_data, "i")
+
     # Write storage data if not NULL (only after neighbors)
     if storage_fourcc != NULL_INDEX_FOURCC and storage_data:
         f_out.write(storage_data)
@@ -183,11 +232,12 @@ def write_compact_format(f_out, original_hnsw_data, assign_probas_np, cum_nneigh
 
 # --- Main Conversion Logic ---
 
+
 def convert_hnsw_graph_to_csr(input_filename, output_filename, prune_embeddings=True):
     """
     Converts an HNSW graph file to the CSR format.
     Supports both original and already-compact formats (backward compatibility).
-    
+
     Args:
         input_filename: Input HNSW index file
         output_filename: Output CSR index file
@@ -196,172 +246,228 @@ def convert_hnsw_graph_to_csr(input_filename, output_filename, prune_embeddings=
     print(f"Starting conversion: {input_filename} -> {output_filename}")
     start_time = time.time()
     original_hnsw_data = {}
-    neighbors_np = None # Initialize to allow check in finally block
+    neighbors_np = None  # Initialize to allow check in finally block
     try:
-        with open(input_filename, 'rb') as f_in, open(output_filename, 'wb') as f_out:
-
+        with open(input_filename, "rb") as f_in, open(output_filename, "wb") as f_out:
             # --- Read IndexHNSW FourCC and Header ---
             print(f"[{time.time() - start_time:.2f}s] Reading Index HNSW header...")
             # ... (Keep the header reading logic as before) ...
-            hnsw_index_fourcc = read_struct(f_in, '<I')
+            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')
-            print(f"[{time.time() - start_time:.2f}s]   Header read: d={original_hnsw_data['d']}, ntotal={original_hnsw_data['ntotal']}")
-
+                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")
+            print(
+                f"[{time.time() - start_time:.2f}s]   Header read: d={original_hnsw_data['d']}, ntotal={original_hnsw_data['ntotal']}"
+            )
 
             # --- Read original HNSW struct data ---
             print(f"[{time.time() - start_time:.2f}s] Reading HNSW struct vectors...")
-            assign_probas_np = read_numpy_vector(f_in, np.float64, 'd')
-            print(f"[{time.time() - start_time:.2f}s]   Read assign_probas ({assign_probas_np.size})")
+            assign_probas_np = read_numpy_vector(f_in, np.float64, "d")
+            print(
+                f"[{time.time() - start_time:.2f}s]   Read assign_probas ({assign_probas_np.size})"
+            )
             gc.collect()
 
-            cum_nneighbor_per_level_np = read_numpy_vector(f_in, np.int32, 'i')
-            print(f"[{time.time() - start_time:.2f}s]   Read cum_nneighbor_per_level ({cum_nneighbor_per_level_np.size})")
+            cum_nneighbor_per_level_np = read_numpy_vector(f_in, np.int32, "i")
+            print(
+                f"[{time.time() - start_time:.2f}s]   Read cum_nneighbor_per_level ({cum_nneighbor_per_level_np.size})"
+            )
             gc.collect()
 
-            levels_np = read_numpy_vector(f_in, np.int32, 'i')
+            levels_np = read_numpy_vector(f_in, np.int32, "i")
             print(f"[{time.time() - start_time:.2f}s]   Read levels ({levels_np.size})")
             gc.collect()
 
             ntotal = len(levels_np)
-            if ntotal != original_hnsw_data['ntotal']:
-                 print(f"Warning: ntotal mismatch! Header says {original_hnsw_data['ntotal']}, levels vector size is {ntotal}. Using levels vector size.", file=sys.stderr)
-                 original_hnsw_data['ntotal'] = ntotal
+            if ntotal != original_hnsw_data["ntotal"]:
+                print(
+                    f"Warning: ntotal mismatch! Header says {original_hnsw_data['ntotal']}, levels vector size is {ntotal}. Using levels vector size.",
+                    file=sys.stderr,
+                )
+                original_hnsw_data["ntotal"] = ntotal
 
             # --- Check for compact format flag ---
             print(f"[{time.time() - start_time:.2f}s]   Probing for compact storage flag...")
             pos_before_compact = f_in.tell()
             try:
-                is_compact_flag = read_struct(f_in, '<?')
+                is_compact_flag = read_struct(f_in, "<?")
                 print(f"[{time.time() - start_time:.2f}s]   Found compact flag: {is_compact_flag}")
-                
+
                 if is_compact_flag:
                     # Input is already in compact format - read compact data
-                    print(f"[{time.time() - start_time:.2f}s]   Input is already in compact format, reading compact data...")
-                    
-                    compact_level_ptr = read_numpy_vector(f_in, np.uint64, 'Q')
-                    print(f"[{time.time() - start_time:.2f}s]   Read compact_level_ptr ({compact_level_ptr.size})")
-                    
-                    compact_node_offsets_np = read_numpy_vector(f_in, np.uint64, 'Q')
-                    print(f"[{time.time() - start_time:.2f}s]   Read compact_node_offsets ({compact_node_offsets_np.size})")
-                    
+                    print(
+                        f"[{time.time() - start_time:.2f}s]   Input is already in compact format, reading compact data..."
+                    )
+
+                    compact_level_ptr = read_numpy_vector(f_in, np.uint64, "Q")
+                    print(
+                        f"[{time.time() - start_time:.2f}s]   Read compact_level_ptr ({compact_level_ptr.size})"
+                    )
+
+                    compact_node_offsets_np = read_numpy_vector(f_in, np.uint64, "Q")
+                    print(
+                        f"[{time.time() - start_time:.2f}s]   Read compact_node_offsets ({compact_node_offsets_np.size})"
+                    )
+
                     # Read scalar parameters
-                    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')
-                    print(f"[{time.time() - start_time:.2f}s]   Read scalar params (ep={original_hnsw_data['entry_point']}, max_lvl={original_hnsw_data['max_level']})")
+                    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")
+                    print(
+                        f"[{time.time() - start_time:.2f}s]   Read scalar params (ep={original_hnsw_data['entry_point']}, max_lvl={original_hnsw_data['max_level']})"
+                    )
 
                     # Read storage fourcc
-                    storage_fourcc = read_struct(f_in, '<I')
-                    print(f"[{time.time() - start_time:.2f}s]   Found storage fourcc: {storage_fourcc:08x}")
-                    
+                    storage_fourcc = read_struct(f_in, "<I")
+                    print(
+                        f"[{time.time() - start_time:.2f}s]   Found storage fourcc: {storage_fourcc:08x}"
+                    )
+
                     if prune_embeddings and storage_fourcc != NULL_INDEX_FOURCC:
                         # Read compact neighbors data
-                        compact_neighbors_data_np = read_numpy_vector(f_in, np.int32, 'i')
-                        print(f"[{time.time() - start_time:.2f}s]   Read compact neighbors data ({compact_neighbors_data_np.size})")
+                        compact_neighbors_data_np = read_numpy_vector(f_in, np.int32, "i")
+                        print(
+                            f"[{time.time() - start_time:.2f}s]   Read compact neighbors data ({compact_neighbors_data_np.size})"
+                        )
                         compact_neighbors_data = compact_neighbors_data_np.tolist()
                         del compact_neighbors_data_np
-                        
+
                         # Skip storage data and write with NULL marker
-                        print(f"[{time.time() - start_time:.2f}s]   Pruning embeddings: Writing NULL storage marker.")
+                        print(
+                            f"[{time.time() - start_time:.2f}s]   Pruning embeddings: Writing NULL storage marker."
+                        )
                         storage_fourcc = NULL_INDEX_FOURCC
                     elif not prune_embeddings:
                         # Read and preserve compact neighbors and storage
-                        compact_neighbors_data_np = read_numpy_vector(f_in, np.int32, 'i')
+                        compact_neighbors_data_np = read_numpy_vector(f_in, np.int32, "i")
                         compact_neighbors_data = compact_neighbors_data_np.tolist()
                         del compact_neighbors_data_np
-                        
+
                         # Read remaining storage data
                         storage_data = f_in.read()
                     else:
                         # Already pruned (NULL storage)
-                        compact_neighbors_data_np = read_numpy_vector(f_in, np.int32, 'i')
+                        compact_neighbors_data_np = read_numpy_vector(f_in, np.int32, "i")
                         compact_neighbors_data = compact_neighbors_data_np.tolist()
                         del compact_neighbors_data_np
-                        storage_data = b''
-                    
+                        storage_data = b""
+
                     # Write the updated compact format
                     print(f"[{time.time() - start_time:.2f}s] Writing updated compact format...")
-                    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, storage_fourcc, storage_data if not prune_embeddings else b'')
-                    
+                    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,
+                        storage_fourcc,
+                        storage_data if not prune_embeddings else b"",
+                    )
+
                     print(f"[{time.time() - start_time:.2f}s] Conversion complete.")
                     return True
-                    
+
                 else:
                     # is_compact=False, rewind and read original format
                     f_in.seek(pos_before_compact)
-                    print(f"[{time.time() - start_time:.2f}s]   Compact flag is False, reading original format...")
-                    
+                    print(
+                        f"[{time.time() - start_time:.2f}s]   Compact flag is False, reading original format..."
+                    )
+
             except EOFError:
                 # No compact flag found, assume original format
                 f_in.seek(pos_before_compact)
-                print(f"[{time.time() - start_time:.2f}s]   No compact flag found, assuming original format...")
+                print(
+                    f"[{time.time() - start_time:.2f}s]   No compact flag found, assuming original format..."
+                )
 
             # --- Handle potential extra byte in original format (like C++ code) ---
-            print(f"[{time.time() - start_time:.2f}s]   Probing for potential extra byte before non-compact offsets...")
+            print(
+                f"[{time.time() - start_time:.2f}s]   Probing for potential extra byte before non-compact offsets..."
+            )
             pos_before_probe = f_in.tell()
             try:
-                suspected_flag = read_struct(f_in, '<B')  # Read 1 byte
+                suspected_flag = read_struct(f_in, "<B")  # Read 1 byte
                 if suspected_flag == 0x00:
-                    print(f"[{time.time() - start_time:.2f}s]   Found and consumed an unexpected 0x00 byte.")
+                    print(
+                        f"[{time.time() - start_time:.2f}s]   Found and consumed an unexpected 0x00 byte."
+                    )
                 elif suspected_flag == 0x01:
-                    print(f"[{time.time() - start_time:.2f}s]   ERROR: Found 0x01 but is_compact should be False")
+                    print(
+                        f"[{time.time() - start_time:.2f}s]   ERROR: Found 0x01 but is_compact should be False"
+                    )
                     raise ValueError("Inconsistent compact flag state")
                 else:
                     # Rewind - this byte is part of offsets data
                     f_in.seek(pos_before_probe)
-                    print(f"[{time.time() - start_time:.2f}s]   Rewound to original position (byte was 0x{suspected_flag:02x})")
+                    print(
+                        f"[{time.time() - start_time:.2f}s]   Rewound to original position (byte was 0x{suspected_flag:02x})"
+                    )
             except EOFError:
                 f_in.seek(pos_before_probe)
-                print(f"[{time.time() - start_time:.2f}s]   No extra byte found (EOF), proceeding with offsets read")
+                print(
+                    f"[{time.time() - start_time:.2f}s]   No extra byte found (EOF), proceeding with offsets read"
+                )
 
             # --- Read original format data ---
-            offsets_np = read_numpy_vector(f_in, np.uint64, 'Q')
+            offsets_np = read_numpy_vector(f_in, np.uint64, "Q")
             print(f"[{time.time() - start_time:.2f}s]   Read offsets ({offsets_np.size})")
             if len(offsets_np) != ntotal + 1:
-                 raise ValueError(f"Inconsistent offsets size: len(levels)={ntotal} but len(offsets)={len(offsets_np)}")
+                raise ValueError(
+                    f"Inconsistent offsets size: len(levels)={ntotal} but len(offsets)={len(offsets_np)}"
+                )
             gc.collect()
 
             print(f"[{time.time() - start_time:.2f}s]   Attempting to read neighbors vector...")
-            neighbors_np = read_numpy_vector(f_in, np.int32, 'i')
+            neighbors_np = read_numpy_vector(f_in, np.int32, "i")
             print(f"[{time.time() - start_time:.2f}s]   Read neighbors ({neighbors_np.size})")
             expected_neighbors_size = offsets_np[-1] if ntotal > 0 else 0
             if neighbors_np.size != expected_neighbors_size:
-                 print(f"Warning: neighbors vector size mismatch. Expected {expected_neighbors_size} based on offsets, got {neighbors_np.size}.")
+                print(
+                    f"Warning: neighbors vector size mismatch. Expected {expected_neighbors_size} based on offsets, got {neighbors_np.size}."
+                )
             gc.collect()
 
-            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')
-            print(f"[{time.time() - start_time:.2f}s]   Read scalar params (ep={original_hnsw_data['entry_point']}, max_lvl={original_hnsw_data['max_level']})")
+            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")
+            print(
+                f"[{time.time() - start_time:.2f}s]   Read scalar params (ep={original_hnsw_data['entry_point']}, max_lvl={original_hnsw_data['max_level']})"
+            )
 
             print(f"[{time.time() - start_time:.2f}s] Checking for storage data...")
             storage_fourcc = None
             try:
-                storage_fourcc = read_struct(f_in, '<I')
-                print(f"[{time.time() - start_time:.2f}s]   Found storage fourcc: {storage_fourcc:08x}.")
+                storage_fourcc = read_struct(f_in, "<I")
+                print(
+                    f"[{time.time() - start_time:.2f}s]   Found storage fourcc: {storage_fourcc:08x}."
+                )
             except EOFError:
-                 print(f"[{time.time() - start_time:.2f}s]   No storage data found (EOF).")
+                print(f"[{time.time() - start_time:.2f}s]   No storage data found (EOF).")
             except Exception as e:
-                 print(f"[{time.time() - start_time:.2f}s]   Error reading potential storage data: {e}")
-
+                print(
+                    f"[{time.time() - start_time:.2f}s]   Error reading potential storage data: {e}"
+                )
 
             # --- Perform Conversion ---
             print(f"[{time.time() - start_time:.2f}s] Converting to CSR format...")
@@ -373,17 +479,21 @@ def convert_hnsw_graph_to_csr(input_filename, output_filename, prune_embeddings=
 
             current_level_ptr_idx = 0
             current_data_idx = 0
-            total_valid_neighbors_counted = 0 # For validation
+            total_valid_neighbors_counted = 0  # For validation
 
             # Optimize calculation by getting slices once per node if possible
             for i in range(ntotal):
-                if i > 0 and i % (ntotal // 100 or 1) == 0: # Log progress roughly every 1%
+                if i > 0 and i % (ntotal // 100 or 1) == 0:  # Log progress roughly every 1%
                     progress = (i / ntotal) * 100
                     elapsed = time.time() - start_time
-                    print(f"\r[{elapsed:.2f}s]   Converting node {i}/{ntotal} ({progress:.1f}%)...", end="")
+                    print(
+                        f"\r[{elapsed:.2f}s]   Converting node {i}/{ntotal} ({progress:.1f}%)...",
+                        end="",
+                    )
 
                 node_max_level = levels_np[i] - 1
-                if node_max_level < -1: node_max_level = -1
+                if node_max_level < -1:
+                    node_max_level = -1
 
                 node_ptr_start_index = current_level_ptr_idx
                 compact_node_offsets_np[i] = node_ptr_start_index
@@ -394,13 +504,17 @@ def convert_hnsw_graph_to_csr(input_filename, output_filename, prune_embeddings=
                 for level in range(node_max_level + 1):
                     compact_level_ptr.append(current_data_idx)
 
-                    begin_orig_np = original_offset_start + get_cum_neighbors(cum_nneighbor_per_level_np, level)
-                    end_orig_np = original_offset_start + get_cum_neighbors(cum_nneighbor_per_level_np, level + 1)
+                    begin_orig_np = original_offset_start + get_cum_neighbors(
+                        cum_nneighbor_per_level_np, level
+                    )
+                    end_orig_np = original_offset_start + get_cum_neighbors(
+                        cum_nneighbor_per_level_np, level + 1
+                    )
 
                     begin_orig = int(begin_orig_np)
                     end_orig = int(end_orig_np)
 
-                    neighbors_len = len(neighbors_np) # Cache length
+                    neighbors_len = len(neighbors_np)  # Cache length
                     begin_orig = min(max(0, begin_orig), neighbors_len)
                     end_orig = min(max(begin_orig, end_orig), neighbors_len)
 
@@ -413,83 +527,117 @@ def convert_hnsw_graph_to_csr(input_filename, output_filename, prune_embeddings=
 
                         if num_valid > 0:
                             # Append valid neighbors
-                            compact_neighbors_data.extend(level_neighbors_slice[valid_neighbors_mask])
+                            compact_neighbors_data.extend(
+                                level_neighbors_slice[valid_neighbors_mask]
+                            )
                             current_data_idx += num_valid
                             total_valid_neighbors_counted += num_valid
 
-
                 compact_level_ptr.append(current_data_idx)
                 current_level_ptr_idx += num_pointers_expected
 
             compact_node_offsets_np[ntotal] = current_level_ptr_idx
-            print(f"\r[{time.time() - start_time:.2f}s]   Conversion loop finished.                        ") # Clear progress line
+            print(
+                f"\r[{time.time() - start_time:.2f}s]   Conversion loop finished.                        "
+            )  # Clear progress line
 
             # --- Validation Checks ---
             print(f"[{time.time() - start_time:.2f}s] Running validation checks...")
             valid_check_passed = True
             # Check 1: Total valid neighbors count
-            print(f"    Checking total valid neighbor count...")
+            print("    Checking total valid neighbor count...")
             expected_valid_count = np.sum(neighbors_np >= 0)
             if total_valid_neighbors_counted != len(compact_neighbors_data):
-                 print(f"Error: Mismatch between counted valid neighbors ({total_valid_neighbors_counted}) and final compact_data size ({len(compact_neighbors_data)})!", file=sys.stderr)
-                 valid_check_passed = False
+                print(
+                    f"Error: Mismatch between counted valid neighbors ({total_valid_neighbors_counted}) and final compact_data size ({len(compact_neighbors_data)})!",
+                    file=sys.stderr,
+                )
+                valid_check_passed = False
             if expected_valid_count != len(compact_neighbors_data):
-                 print(f"Error: Mismatch between NumPy count of valid neighbors ({expected_valid_count}) and final compact_data size ({len(compact_neighbors_data)})!", file=sys.stderr)
-                 valid_check_passed = False
+                print(
+                    f"Error: Mismatch between NumPy count of valid neighbors ({expected_valid_count}) and final compact_data size ({len(compact_neighbors_data)})!",
+                    file=sys.stderr,
+                )
+                valid_check_passed = False
             else:
-                 print(f"    OK: Total valid neighbors = {len(compact_neighbors_data)}")
+                print(f"    OK: Total valid neighbors = {len(compact_neighbors_data)}")
 
             # Check 2: Final pointer indices consistency
-            print(f"    Checking final pointer indices...")
+            print("    Checking final pointer indices...")
             if compact_node_offsets_np[ntotal] != len(compact_level_ptr):
-                 print(f"Error: Final node offset ({compact_node_offsets_np[ntotal]}) doesn't match level_ptr size ({len(compact_level_ptr)})!", file=sys.stderr)
-                 valid_check_passed = False
-            if (len(compact_level_ptr) > 0 and compact_level_ptr[-1] != len(compact_neighbors_data)) or \
-               (len(compact_level_ptr) == 0 and len(compact_neighbors_data) != 0):
-                 last_ptr = compact_level_ptr[-1] if len(compact_level_ptr) > 0 else -1
-                 print(f"Error: Last level pointer ({last_ptr}) doesn't match compact_data size ({len(compact_neighbors_data)})!", file=sys.stderr)
-                 valid_check_passed = False
+                print(
+                    f"Error: Final node offset ({compact_node_offsets_np[ntotal]}) doesn't match level_ptr size ({len(compact_level_ptr)})!",
+                    file=sys.stderr,
+                )
+                valid_check_passed = False
+            if (
+                len(compact_level_ptr) > 0 and compact_level_ptr[-1] != len(compact_neighbors_data)
+            ) or (len(compact_level_ptr) == 0 and len(compact_neighbors_data) != 0):
+                last_ptr = compact_level_ptr[-1] if len(compact_level_ptr) > 0 else -1
+                print(
+                    f"Error: Last level pointer ({last_ptr}) doesn't match compact_data size ({len(compact_neighbors_data)})!",
+                    file=sys.stderr,
+                )
+                valid_check_passed = False
             else:
-                 print(f"    OK: Final pointers match data size.")
+                print("    OK: Final pointers match data size.")
 
             if not valid_check_passed:
-                print("Error: Validation checks failed. Output file might be incorrect.", file=sys.stderr)
+                print(
+                    "Error: Validation checks failed. Output file might be incorrect.",
+                    file=sys.stderr,
+                )
                 # Optional: Exit here if validation fails
                 # return False
 
             # --- Explicitly delete large intermediate arrays ---
-            print(f"[{time.time() - start_time:.2f}s] Deleting original neighbors and offsets arrays...")
+            print(
+                f"[{time.time() - start_time:.2f}s] Deleting original neighbors and offsets arrays..."
+            )
             del neighbors_np
             del offsets_np
             gc.collect()
 
-            print(f"    CSR Stats: |data|={len(compact_neighbors_data)}, |level_ptr|={len(compact_level_ptr)}")
+            print(
+                f"    CSR Stats: |data|={len(compact_neighbors_data)}, |level_ptr|={len(compact_level_ptr)}"
+            )
 
             # --- Write CSR HNSW graph data using unified function ---
-            print(f"[{time.time() - start_time:.2f}s] Writing CSR HNSW graph data in FAISS-compatible order...")
-            
+            print(
+                f"[{time.time() - start_time:.2f}s] Writing CSR HNSW graph data in FAISS-compatible order..."
+            )
+
             # Determine storage fourcc and data based on prune_embeddings
             if prune_embeddings:
-                print(f"   Pruning embeddings: Writing NULL storage marker.")
+                print("   Pruning embeddings: Writing NULL storage marker.")
                 output_storage_fourcc = NULL_INDEX_FOURCC
-                storage_data = b''
+                storage_data = b""
             else:
                 # Keep embeddings - read and preserve original storage data
                 if storage_fourcc and storage_fourcc != NULL_INDEX_FOURCC:
-                    print(f"   Preserving embeddings: Reading original storage data...")
+                    print("   Preserving embeddings: Reading original storage data...")
                     storage_data = f_in.read()  # Read remaining storage data
                     output_storage_fourcc = storage_fourcc
                     print(f"   Read {len(storage_data)} bytes of storage data")
                 else:
-                    print(f"   No embeddings found in original file (NULL storage)")
+                    print("   No embeddings found in original file (NULL storage)")
                     output_storage_fourcc = NULL_INDEX_FOURCC
-                    storage_data = b''
-            
+                    storage_data = b""
+
             # Use the unified write function
-            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, output_storage_fourcc, storage_data)
-            
+            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,
+                output_storage_fourcc,
+                storage_data,
+            )
+
             # Clean up memory
             del assign_probas_np, cum_nneighbor_per_level_np, levels_np
             del compact_neighbors_data, compact_level_ptr, compact_node_offsets_np
@@ -503,40 +651,66 @@ def convert_hnsw_graph_to_csr(input_filename, output_filename, prune_embeddings=
         print(f"Error: Input file not found: {input_filename}", file=sys.stderr)
         return False
     except MemoryError as e:
-         print(f"\nFatal MemoryError during conversion: {e}. Insufficient RAM.", file=sys.stderr)
-         # Clean up potentially partially written output file?
-         try: os.remove(output_filename)
-         except OSError: pass
-         return False
+        print(
+            f"\nFatal MemoryError during conversion: {e}. Insufficient RAM.",
+            file=sys.stderr,
+        )
+        # Clean up potentially partially written output file?
+        try:
+            os.remove(output_filename)
+        except OSError:
+            pass
+        return False
     except EOFError as e:
-        print(f"Error: Reached end of file unexpectedly reading {input_filename}. {e}", file=sys.stderr)
-        try: os.remove(output_filename)
-        except OSError: pass
+        print(
+            f"Error: Reached end of file unexpectedly reading {input_filename}. {e}",
+            file=sys.stderr,
+        )
+        try:
+            os.remove(output_filename)
+        except OSError:
+            pass
         return False
     except Exception as e:
         print(f"An unexpected error occurred during conversion: {e}", file=sys.stderr)
         import traceback
+
         traceback.print_exc()
         try:
             os.remove(output_filename)
-        except OSError: pass
+        except OSError:
+            pass
         return False
     # Ensure neighbors_np is deleted even if an error occurs after its allocation
     finally:
-        if 'neighbors_np' in locals() and neighbors_np is not None:
-            del neighbors_np
-            gc.collect()
+        try:
+            if "neighbors_np" in locals() and neighbors_np is not None:
+                del neighbors_np
+                gc.collect()
+        except NameError:
+            pass
 
 
 # --- Script Execution ---
 if __name__ == "__main__":
-    parser = argparse.ArgumentParser(description="Convert a Faiss IndexHNSWFlat file to a CSR-based HNSW graph file.")
+    parser = argparse.ArgumentParser(
+        description="Convert a Faiss IndexHNSWFlat file to a CSR-based HNSW graph file."
+    )
     parser.add_argument("input_index_file", help="Path to the input IndexHNSWFlat file")
-    parser.add_argument("output_csr_graph_file", help="Path to write the output CSR HNSW graph file")
-    parser.add_argument("--prune-embeddings", action="store_true", default=True, 
-                       help="Prune embedding storage (write NULL storage marker)")
-    parser.add_argument("--keep-embeddings", action="store_true", 
-                       help="Keep embedding storage (overrides --prune-embeddings)")
+    parser.add_argument(
+        "output_csr_graph_file", help="Path to write the output CSR HNSW graph file"
+    )
+    parser.add_argument(
+        "--prune-embeddings",
+        action="store_true",
+        default=True,
+        help="Prune embedding storage (write NULL storage marker)",
+    )
+    parser.add_argument(
+        "--keep-embeddings",
+        action="store_true",
+        help="Keep embedding storage (overrides --prune-embeddings)",
+    )
 
     args = parser.parse_args()
 
@@ -545,10 +719,12 @@ if __name__ == "__main__":
         sys.exit(1)
 
     if os.path.abspath(args.input_index_file) == os.path.abspath(args.output_csr_graph_file):
-         print(f"Error: Input and output filenames cannot be the same.", file=sys.stderr)
-         sys.exit(1)
+        print("Error: Input and output filenames cannot be the same.", file=sys.stderr)
+        sys.exit(1)
 
     prune_embeddings = args.prune_embeddings and not args.keep_embeddings
-    success = convert_hnsw_graph_to_csr(args.input_index_file, args.output_csr_graph_file, prune_embeddings)
+    success = convert_hnsw_graph_to_csr(
+        args.input_index_file, args.output_csr_graph_file, prune_embeddings
+    )
     if not success:
-        sys.exit(1)
+        sys.exit(1)

packages/leann-backend-hnsw/leann_backend_hnsw/hnsw_backend.py

@@ -1,19 +1,19 @@
-import numpy as np
-import os
-from pathlib import Path
-from typing import Dict, Any, List, Literal, Optional
-import shutil
 import logging
+import os
+import shutil
+from pathlib import Path
+from typing import Any, Literal
 
-from leann.searcher_base import BaseSearcher
-from .convert_to_csr import convert_hnsw_graph_to_csr
-
-from leann.registry import register_backend
+import numpy as np
 from leann.interface import (
-    LeannBackendFactoryInterface,
     LeannBackendBuilderInterface,
+    LeannBackendFactoryInterface,
     LeannBackendSearcherInterface,
 )
+from leann.registry import register_backend
+from leann.searcher_base import BaseSearcher
+
+from .convert_to_csr import convert_hnsw_graph_to_csr
 
 logger = logging.getLogger(__name__)
 
@@ -28,6 +28,12 @@ def get_metric_map():
     }
 
 
+def normalize_l2(data: np.ndarray) -> np.ndarray:
+    norms = np.linalg.norm(data, axis=1, keepdims=True)
+    norms[norms == 0] = 1  # Avoid division by zero
+    return data / norms
+
+
 @register_backend("hnsw")
 class HNSWBackend(LeannBackendFactoryInterface):
     @staticmethod
@@ -51,9 +57,11 @@ class HNSWBuilder(LeannBackendBuilderInterface):
         if not self.is_recompute:
             if self.is_compact:
                 # TODO: support this case @andy
-                raise ValueError("is_recompute is False, but is_compact is True. This is not compatible now. change is compact to False and you can use the original HNSW index.")
+                raise ValueError(
+                    "is_recompute is False, but is_compact is True. This is not compatible now. change is compact to False and you can use the original HNSW index."
+                )
 
-    def build(self, data: np.ndarray, ids: List[str], index_path: str, **kwargs):
+    def build(self, data: np.ndarray, ids: list[str], index_path: str, **kwargs):
         from . import faiss  # type: ignore
 
         path = Path(index_path)
@@ -74,7 +82,7 @@ class HNSWBuilder(LeannBackendBuilderInterface):
         index.hnsw.efConstruction = self.efConstruction
 
         if self.distance_metric.lower() == "cosine":
-            faiss.normalize_L2(data)
+            data = normalize_l2(data)
 
         index.add(data.shape[0], faiss.swig_ptr(data))
         index_file = index_dir / f"{index_prefix}.index"
@@ -99,16 +107,12 @@ class HNSWBuilder(LeannBackendBuilderInterface):
             # index_file_old = index_file.with_suffix(".old")
             # shutil.move(str(index_file), str(index_file_old))
             shutil.move(str(csr_temp_file), str(index_file))
-            logger.info(
-                f"INFO: Replaced original index with {mode_str} version at '{index_file}'"
-            )
+            logger.info(f"INFO: Replaced original index with {mode_str} version at '{index_file}'")
         else:
             # Clean up and fail fast
             if csr_temp_file.exists():
                 os.remove(csr_temp_file)
-            raise RuntimeError(
-                "CSR conversion failed - cannot proceed with compact format"
-            )
+            raise RuntimeError("CSR conversion failed - cannot proceed with compact format")
 
 
 class HNSWSearcher(BaseSearcher):
@@ -146,7 +150,7 @@ class HNSWSearcher(BaseSearcher):
         self,
         query: np.ndarray,
         top_k: int,
-        zmq_port: Optional[int] = None,
+        zmq_port: int | None = None,
         complexity: int = 64,
         beam_width: int = 1,
         prune_ratio: float = 0.0,
@@ -154,7 +158,7 @@ class HNSWSearcher(BaseSearcher):
         pruning_strategy: Literal["global", "local", "proportional"] = "global",
         batch_size: int = 0,
         **kwargs,
-    ) -> Dict[str, Any]:
+    ) -> dict[str, Any]:
         """
         Search for nearest neighbors using HNSW index.
 
@@ -183,20 +187,16 @@ class HNSWSearcher(BaseSearcher):
                 raise RuntimeError("Recompute is required for pruned index.")
         if recompute_embeddings:
             if zmq_port is None:
-                raise ValueError(
-                    "zmq_port must be provided if recompute_embeddings is True"
-                )
+                raise ValueError("zmq_port must be provided if recompute_embeddings is True")
 
         if query.dtype != np.float32:
             query = query.astype(np.float32)
         if self.distance_metric == "cosine":
-            faiss.normalize_L2(query)
+            query = normalize_l2(query)
 
         params = faiss.SearchParametersHNSW()
         if zmq_port is not None:
-            params.zmq_port = (
-                zmq_port  # C++ code won't use this if recompute_embeddings is False
-            )
+            params.zmq_port = zmq_port  # C++ code won't use this if recompute_embeddings is False
         params.efSearch = complexity
         params.beam_size = beam_width
 
@@ -209,9 +209,7 @@ class HNSWSearcher(BaseSearcher):
             params.send_neigh_times_ratio = 0.0
         elif pruning_strategy == "proportional":
             params.local_prune = False
-            params.send_neigh_times_ratio = (
-                1.0  # Any value > 1e-6 triggers proportional mode
-            )
+            params.send_neigh_times_ratio = 1.0  # Any value > 1e-6 triggers proportional mode
         else:  # "global"
             params.local_prune = False
             params.send_neigh_times_ratio = 0.0
@@ -232,8 +230,6 @@ class HNSWSearcher(BaseSearcher):
             params,
         )
 
-        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}

packages/leann-backend-hnsw/leann_backend_hnsw/hnsw_embedding_server.py

@@ -3,17 +3,17 @@ HNSW-specific embedding server
 """
 
 import argparse
+import json
+import logging
+import os
+import sys
 import threading
 import time
-import os
-import zmq
-import numpy as np
-import msgpack
-import json
 from pathlib import Path
-from typing import Optional
-import sys
-import logging
+
+import msgpack
+import numpy as np
+import zmq
 
 # Set up logging based on environment variable
 LOG_LEVEL = os.getenv("LEANN_LOG_LEVEL", "WARNING").upper()
@@ -33,7 +33,7 @@ if not logger.handlers:
 
 
 def create_hnsw_embedding_server(
-    passages_file: Optional[str] = None,
+    passages_file: str | None = None,
     zmq_port: int = 5555,
     model_name: str = "sentence-transformers/all-mpnet-base-v2",
     distance_metric: str = "mips",
@@ -52,8 +52,8 @@ def create_hnsw_embedding_server(
     sys.path.insert(0, str(leann_core_path))
 
     try:
-        from leann.embedding_compute import compute_embeddings
         from leann.api import PassageManager
+        from leann.embedding_compute import compute_embeddings
 
         logger.info("Successfully imported unified embedding computation module")
     except ImportError as e:
@@ -78,13 +78,11 @@ def create_hnsw_embedding_server(
         raise ValueError("Only metadata files (.meta.json) are supported")
 
     # Load metadata to get passage sources
-    with open(passages_file, "r") as f:
+    with open(passages_file) as f:
         meta = json.load(f)
 
     # Convert relative paths to absolute paths based on metadata file location
-    metadata_dir = Path(
-        passages_file
-    ).parent.parent  # Go up one level from the metadata file
+    metadata_dir = Path(passages_file).parent.parent  # Go up one level from the metadata file
     passage_sources = []
     for source in meta["passage_sources"]:
         source_copy = source.copy()
@@ -134,9 +132,7 @@ def create_hnsw_embedding_server(
                         response = embeddings.tolist()
                         socket.send(msgpack.packb(response))
                         e2e_end = time.time()
-                        logger.info(
-                            f"⏱️  Text embedding E2E time: {e2e_end - e2e_start:.6f}s"
-                        )
+                        logger.info(f"⏱️  Text embedding E2E time: {e2e_end - e2e_start:.6f}s")
                         continue
 
                 # Handle distance calculation requests
@@ -162,17 +158,13 @@ def create_hnsw_embedding_server(
                             texts.append(txt)
                         except KeyError:
                             logger.error(f"Passage ID {nid} not found")
-                            raise RuntimeError(
-                                f"FATAL: Passage with ID {nid} not found"
-                            )
+                            raise RuntimeError(f"FATAL: Passage with ID {nid} not found")
                         except Exception as e:
                             logger.error(f"Exception looking up passage ID {nid}: {e}")
                             raise
 
                     # Process embeddings
-                    embeddings = compute_embeddings(
-                        texts, model_name, mode=embedding_mode
-                    )
+                    embeddings = compute_embeddings(texts, model_name, mode=embedding_mode)
                     logger.info(
                         f"Computed embeddings for {len(texts)} texts, shape: {embeddings.shape}"
                     )
@@ -186,18 +178,12 @@ def create_hnsw_embedding_server(
                         distances = -np.dot(embeddings, query_vector)
 
                     response_payload = distances.flatten().tolist()
-                    response_bytes = msgpack.packb(
-                        [response_payload], use_single_float=True
-                    )
-                    logger.debug(
-                        f"Sending distance response with {len(distances)} distances"
-                    )
+                    response_bytes = msgpack.packb([response_payload], use_single_float=True)
+                    logger.debug(f"Sending distance response with {len(distances)} distances")
 
                     socket.send(response_bytes)
                     e2e_end = time.time()
-                    logger.info(
-                        f"⏱️  Distance calculation E2E time: {e2e_end - e2e_start:.6f}s"
-                    )
+                    logger.info(f"⏱️  Distance calculation E2E time: {e2e_end - e2e_start:.6f}s")
                     continue
 
                 # Standard embedding request (passage ID lookup)
@@ -222,9 +208,7 @@ def create_hnsw_embedding_server(
                         passage_data = passages.get_passage(str(nid))
                         txt = passage_data["text"]
                         if not txt:
-                            raise RuntimeError(
-                                f"FATAL: Empty text for passage ID {nid}"
-                            )
+                            raise RuntimeError(f"FATAL: Empty text for passage ID {nid}")
                         texts.append(txt)
                     except KeyError:
                         raise RuntimeError(f"FATAL: Passage with ID {nid} not found")
@@ -243,11 +227,9 @@ def create_hnsw_embedding_server(
                     logger.error(
                         f"NaN or Inf detected in embeddings! Requested IDs: {node_ids[:5]}..."
                     )
-                    assert False
+                    raise AssertionError()
 
-                hidden_contiguous_f32 = np.ascontiguousarray(
-                    embeddings, dtype=np.float32
-                )
+                hidden_contiguous_f32 = np.ascontiguousarray(embeddings, dtype=np.float32)
                 response_payload = [
                     list(hidden_contiguous_f32.shape),
                     hidden_contiguous_f32.flatten().tolist(),

packages/leann-backend-hnsw/pyproject.toml

@@ -6,10 +6,10 @@ build-backend = "scikit_build_core.build"
 
 [project]
 name = "leann-backend-hnsw"
-version = "0.1.12"
+version = "0.1.15"
 description = "Custom-built HNSW (Faiss) backend for the Leann toolkit."
 dependencies = [
-    "leann-core==0.1.12", 
+    "leann-core==0.1.15",
     "numpy",
     "pyzmq>=23.0.0",
     "msgpack>=1.0.0",
@@ -24,4 +24,4 @@ build.tool-args = ["-j8"]
 
 # CMake definitions to optimize compilation
 [tool.scikit-build.cmake.define]
-CMAKE_BUILD_PARALLEL_LEVEL = "8"
+CMAKE_BUILD_PARALLEL_LEVEL = "8"

packages/leann-core/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "leann-core"
-version = "0.1.12"
+version = "0.1.15"
 description = "Core API and plugin system for LEANN"
 readme = "README.md"
 requires-python = ">=3.9"
@@ -20,6 +20,8 @@ dependencies = [
     "torch>=2.0.0",
     "sentence-transformers>=2.2.0",
     "llama-index-core>=0.12.0",
+    "llama-index-readers-file>=0.4.0",  # Essential for document reading
+    "llama-index-embeddings-huggingface>=0.5.5",  # For embeddings
     "python-dotenv>=1.0.0",
     "openai>=1.0.0",
     "huggingface-hub>=0.20.0",
@@ -33,8 +35,15 @@ dependencies = [
     "mlx-lm>=0.26.0; sys_platform == 'darwin'",
 ]
 
+[project.optional-dependencies]
+colab = [
+    "torch>=2.0.0,<3.0.0",  # Limit torch version to avoid conflicts
+    "transformers>=4.30.0,<5.0.0",  # Limit transformers version
+    "accelerate>=0.20.0,<1.0.0",  # Limit accelerate version
+]
+
 [project.scripts]
 leann = "leann.cli:main"
 
 [tool.setuptools.packages.find]
-where = ["src"]
+where = ["src"]

packages/leann-core/src/leann/__init__.py

@@ -14,4 +14,4 @@ from .registry import BACKEND_REGISTRY, autodiscover_backends
 
 autodiscover_backends()
 
-__all__ = ["LeannBuilder", "LeannSearcher", "LeannChat", "BACKEND_REGISTRY"]
+__all__ = ["BACKEND_REGISTRY", "LeannBuilder", "LeannChat", "LeannSearcher"]

packages/leann-core/src/leann/api.py

@@ -4,27 +4,31 @@ with the correct, original embedding logic from the user's reference code.
 """
 
 import json
-import pickle
-from leann.interface import LeannBackendSearcherInterface
-import numpy as np
-import time
-from pathlib import Path
-from typing import List, Dict, Any, Optional, Literal
-from dataclasses import dataclass, field
-from .registry import BACKEND_REGISTRY
-from .interface import LeannBackendFactoryInterface
-from .chat import get_llm
 import logging
+import pickle
+import time
+import warnings
+from dataclasses import dataclass, field
+from pathlib import Path
+from typing import Any, Literal
+
+import numpy as np
+
+from leann.interface import LeannBackendSearcherInterface
+
+from .chat import get_llm
+from .interface import LeannBackendFactoryInterface
+from .registry import BACKEND_REGISTRY
 
 logger = logging.getLogger(__name__)
 
 
 def compute_embeddings(
-    chunks: List[str],
+    chunks: list[str],
     model_name: str,
     mode: str = "sentence-transformers",
     use_server: bool = True,
-    port: Optional[int] = None,
+    port: int | None = None,
     is_build=False,
 ) -> np.ndarray:
     """
@@ -61,9 +65,7 @@ def compute_embeddings(
         )
 
 
-def compute_embeddings_via_server(
-    chunks: List[str], model_name: str, port: int
-) -> np.ndarray:
+def compute_embeddings_via_server(chunks: list[str], model_name: str, port: int) -> np.ndarray:
     """Computes embeddings using sentence-transformers.
 
     Args:
@@ -73,9 +75,9 @@ def compute_embeddings_via_server(
     logger.info(
         f"Computing embeddings for {len(chunks)} chunks using SentenceTransformer model '{model_name}' (via embedding server)..."
     )
-    import zmq
     import msgpack
     import numpy as np
+    import zmq
 
     # Connect to embedding server
     context = zmq.Context()
@@ -104,11 +106,11 @@ class SearchResult:
     id: str
     score: float
     text: str
-    metadata: Dict[str, Any] = field(default_factory=dict)
+    metadata: dict[str, Any] = field(default_factory=dict)
 
 
 class PassageManager:
-    def __init__(self, passage_sources: List[Dict[str, Any]]):
+    def __init__(self, passage_sources: list[dict[str, Any]]):
         self.offset_maps = {}
         self.passage_files = {}
         self.global_offset_map = {}  # Combined map for fast lookup
@@ -117,8 +119,15 @@ class PassageManager:
             assert source["type"] == "jsonl", "only jsonl is supported"
             passage_file = source["path"]
             index_file = source["index_path"]  # .idx file
+
+            # Fix path resolution for Colab and other environments
+            if not Path(index_file).is_absolute():
+                # If relative path, try to resolve it properly
+                index_file = str(Path(index_file).resolve())
+
             if not Path(index_file).exists():
                 raise FileNotFoundError(f"Passage index file not found: {index_file}")
+
             with open(index_file, "rb") as f:
                 offset_map = pickle.load(f)
                 self.offset_maps[passage_file] = offset_map
@@ -128,11 +137,11 @@ class PassageManager:
                 for passage_id, offset in offset_map.items():
                     self.global_offset_map[passage_id] = (passage_file, offset)
 
-    def get_passage(self, passage_id: str) -> Dict[str, Any]:
+    def get_passage(self, passage_id: str) -> dict[str, Any]:
         if passage_id in self.global_offset_map:
             passage_file, offset = self.global_offset_map[passage_id]
             # Lazy file opening - only open when needed
-            with open(passage_file, "r", encoding="utf-8") as f:
+            with open(passage_file, encoding="utf-8") as f:
                 f.seek(offset)
                 return json.loads(f.readline())
         raise KeyError(f"Passage ID not found: {passage_id}")
@@ -143,24 +152,92 @@ class LeannBuilder:
         self,
         backend_name: str,
         embedding_model: str = "facebook/contriever",
-        dimensions: Optional[int] = None,
+        dimensions: int | None = None,
         embedding_mode: str = "sentence-transformers",
         **backend_kwargs,
     ):
         self.backend_name = backend_name
-        backend_factory: LeannBackendFactoryInterface | None = BACKEND_REGISTRY.get(
-            backend_name
-        )
+        backend_factory: LeannBackendFactoryInterface | None = BACKEND_REGISTRY.get(backend_name)
         if backend_factory is None:
             raise ValueError(f"Backend '{backend_name}' not found or not registered.")
         self.backend_factory = backend_factory
         self.embedding_model = embedding_model
         self.dimensions = dimensions
         self.embedding_mode = embedding_mode
-        self.backend_kwargs = backend_kwargs
-        self.chunks: List[Dict[str, Any]] = []
 
-    def add_text(self, text: str, metadata: Optional[Dict[str, Any]] = None):
+        # Check if we need to use cosine distance for normalized embeddings
+        normalized_embeddings_models = {
+            # OpenAI models
+            ("openai", "text-embedding-ada-002"),
+            ("openai", "text-embedding-3-small"),
+            ("openai", "text-embedding-3-large"),
+            # Voyage AI models
+            ("voyage", "voyage-2"),
+            ("voyage", "voyage-3"),
+            ("voyage", "voyage-large-2"),
+            ("voyage", "voyage-multilingual-2"),
+            ("voyage", "voyage-code-2"),
+            # Cohere models
+            ("cohere", "embed-english-v3.0"),
+            ("cohere", "embed-multilingual-v3.0"),
+            ("cohere", "embed-english-light-v3.0"),
+            ("cohere", "embed-multilingual-light-v3.0"),
+        }
+
+        # Also check for patterns in model names
+        is_normalized = False
+        current_model_lower = embedding_model.lower()
+        current_mode_lower = embedding_mode.lower()
+
+        # Check exact matches
+        for mode, model in normalized_embeddings_models:
+            if (current_mode_lower == mode and current_model_lower == model) or (
+                mode in current_mode_lower and model in current_model_lower
+            ):
+                is_normalized = True
+                break
+
+        # Check patterns
+        if not is_normalized:
+            # OpenAI patterns
+            if "openai" in current_mode_lower or "openai" in current_model_lower:
+                if any(
+                    pattern in current_model_lower
+                    for pattern in ["text-embedding", "ada", "3-small", "3-large"]
+                ):
+                    is_normalized = True
+            # Voyage patterns
+            elif "voyage" in current_mode_lower or "voyage" in current_model_lower:
+                is_normalized = True
+            # Cohere patterns
+            elif "cohere" in current_mode_lower or "cohere" in current_model_lower:
+                if "embed" in current_model_lower:
+                    is_normalized = True
+
+        # Handle distance metric
+        if is_normalized and "distance_metric" not in backend_kwargs:
+            backend_kwargs["distance_metric"] = "cosine"
+            warnings.warn(
+                f"Detected normalized embeddings model '{embedding_model}' with mode '{embedding_mode}'. "
+                f"Automatically setting distance_metric='cosine' for optimal performance. "
+                f"Normalized embeddings (L2 norm = 1) should use cosine similarity instead of MIPS.",
+                UserWarning,
+                stacklevel=2,
+            )
+        elif is_normalized and backend_kwargs.get("distance_metric", "").lower() != "cosine":
+            current_metric = backend_kwargs.get("distance_metric", "mips")
+            warnings.warn(
+                f"Warning: Using '{current_metric}' distance metric with normalized embeddings model "
+                f"'{embedding_model}' may lead to suboptimal search results. "
+                f"Consider using 'cosine' distance metric for better performance.",
+                UserWarning,
+                stacklevel=2,
+            )
+
+        self.backend_kwargs = backend_kwargs
+        self.chunks: list[dict[str, Any]] = []
+
+    def add_text(self, text: str, metadata: dict[str, Any] | None = None):
         if metadata is None:
             metadata = {}
         passage_id = metadata.get("id", str(len(self.chunks)))
@@ -190,9 +267,7 @@ class LeannBuilder:
             try:
                 from tqdm import tqdm
 
-                chunk_iterator = tqdm(
-                    self.chunks, desc="Writing passages", unit="chunk"
-                )
+                chunk_iterator = tqdm(self.chunks, desc="Writing passages", unit="chunk")
             except ImportError:
                 chunk_iterator = self.chunks
 
@@ -222,9 +297,7 @@ class LeannBuilder:
         string_ids = [chunk["id"] for chunk in self.chunks]
         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
-        )
+        builder_instance.build(embeddings, string_ids, index_path, **current_backend_kwargs)
         leann_meta_path = index_dir / f"{index_name}.meta.json"
         meta_data = {
             "version": "1.0",
@@ -273,9 +346,7 @@ class LeannBuilder:
         ids, embeddings = data
 
         if not isinstance(embeddings, np.ndarray):
-            raise ValueError(
-                f"Expected embeddings to be numpy array, got {type(embeddings)}"
-            )
+            raise ValueError(f"Expected embeddings to be numpy array, got {type(embeddings)}")
 
         if len(ids) != embeddings.shape[0]:
             raise ValueError(
@@ -287,9 +358,7 @@ class LeannBuilder:
         if self.dimensions is None:
             self.dimensions = embedding_dim
         elif self.dimensions != embedding_dim:
-            raise ValueError(
-                f"Dimension mismatch: expected {self.dimensions}, got {embedding_dim}"
-            )
+            raise ValueError(f"Dimension mismatch: expected {self.dimensions}, got {embedding_dim}")
 
         logger.info(
             f"Building index from precomputed embeddings: {len(ids)} items, {embedding_dim} dimensions"
@@ -374,26 +443,24 @@ class LeannBuilder:
         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}"
-        )
+        logger.info(f"Index built successfully from precomputed embeddings: {index_path}")
 
 
 class LeannSearcher:
     def __init__(self, index_path: str, enable_warmup: bool = False, **backend_kwargs):
+        # Fix path resolution for Colab and other environments
+        if not Path(index_path).is_absolute():
+            index_path = str(Path(index_path).resolve())
+
         self.meta_path_str = f"{index_path}.meta.json"
         if not Path(self.meta_path_str).exists():
-            raise FileNotFoundError(
-                f"Leann metadata file not found at {self.meta_path_str}"
-            )
-        with open(self.meta_path_str, "r", encoding="utf-8") as f:
+            raise FileNotFoundError(f"Leann metadata file not found at {self.meta_path_str}")
+        with open(self.meta_path_str, encoding="utf-8") as f:
             self.meta_data = json.load(f)
         backend_name = self.meta_data["backend_name"]
         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_mode = self.meta_data.get("embedding_mode", "sentence-transformers")
         self.passage_manager = PassageManager(self.meta_data.get("passage_sources", []))
         backend_factory = BACKEND_REGISTRY.get(backend_name)
         if backend_factory is None:
@@ -415,7 +482,7 @@ class LeannSearcher:
         pruning_strategy: Literal["global", "local", "proportional"] = "global",
         expected_zmq_port: int = 5557,
         **kwargs,
-    ) -> List[SearchResult]:
+    ) -> list[SearchResult]:
         logger.info("🔍 LeannSearcher.search() called:")
         logger.info(f"  Query: '{query}'")
         logger.info(f"  Top_k: {top_k}")
@@ -442,7 +509,7 @@ class LeannSearcher:
             zmq_port=zmq_port,
         )
         # logger.info(f"  Generated embedding shape: {query_embedding.shape}")
-        embedding_time = time.time() - start_time
+        time.time() - start_time
         # logger.info(f"  Embedding time: {embedding_time} seconds")
 
         start_time = time.time()
@@ -457,17 +524,15 @@ class LeannSearcher:
             zmq_port=zmq_port,
             **kwargs,
         )
-        search_time = time.time() - start_time
+        time.time() - start_time
         # logger.info(f"  Search time: {search_time} seconds")
-        logger.info(
-            f"  Backend returned: labels={len(results.get('labels', [[]])[0])} results"
-        )
+        logger.info(f"  Backend returned: labels={len(results.get('labels', [[]])[0])} results")
 
         enriched_results = []
         if "labels" in results and "distances" in results:
             logger.info(f"  Processing {len(results['labels'][0])} passage IDs:")
             for i, (string_id, dist) in enumerate(
-                zip(results["labels"][0], results["distances"][0])
+                zip(results["labels"][0], results["distances"][0], strict=False)
             ):
                 try:
                     passage_data = self.passage_manager.get_passage(string_id)
@@ -479,15 +544,15 @@ class LeannSearcher:
                             metadata=passage_data.get("metadata", {}),
                         )
                     )
-                    
+
                     # Color codes for better logging
                     GREEN = "\033[92m"
                     BLUE = "\033[94m"
                     YELLOW = "\033[93m"
                     RESET = "\033[0m"
-                    
+
                     # Truncate text for display (first 100 chars)
-                    display_text = passage_data['text']
+                    display_text = passage_data["text"]
                     logger.info(
                         f"   {GREEN}✓{RESET} {BLUE}[{i + 1:2d}]{RESET} {YELLOW}ID:{RESET} '{string_id}' {YELLOW}Score:{RESET} {dist:.4f} {YELLOW}Text:{RESET} {display_text}"
                     )
@@ -505,7 +570,7 @@ class LeannChat:
     def __init__(
         self,
         index_path: str,
-        llm_config: Optional[Dict[str, Any]] = None,
+        llm_config: dict[str, Any] | None = None,
         enable_warmup: bool = False,
         **kwargs,
     ):
@@ -521,7 +586,7 @@ class LeannChat:
         prune_ratio: float = 0.0,
         recompute_embeddings: bool = True,
         pruning_strategy: Literal["global", "local", "proportional"] = "global",
-        llm_kwargs: Optional[Dict[str, Any]] = None,
+        llm_kwargs: dict[str, Any] | None = None,
         expected_zmq_port: int = 5557,
         **search_kwargs,
     ):

packages/leann-core/src/leann/chat.py

@@ -4,11 +4,12 @@ This file contains the chat generation logic for the LEANN project,
 supporting different backends like Ollama, Hugging Face Transformers, and a simulation mode.
 """
 
-from abc import ABC, abstractmethod
-from typing import Dict, Any, Optional, List
+import difflib
 import logging
 import os
-import difflib
+from abc import ABC, abstractmethod
+from typing import Any
+
 import torch
 
 # Configure logging
@@ -16,10 +17,11 @@ logging.basicConfig(level=logging.INFO)
 logger = logging.getLogger(__name__)
 
 
-def check_ollama_models() -> List[str]:
+def check_ollama_models() -> list[str]:
     """Check available Ollama models and return a list"""
     try:
         import requests
+
         response = requests.get("http://localhost:11434/api/tags", timeout=5)
         if response.status_code == 200:
             data = response.json()
@@ -31,51 +33,52 @@ def check_ollama_models() -> List[str]:
 
 def check_ollama_model_exists_remotely(model_name: str) -> tuple[bool, list[str]]:
     """Check if a model exists in Ollama's remote library and return available tags
-    
+
     Returns:
         (model_exists, available_tags): bool and list of matching tags
     """
     try:
-        import requests
         import re
-        
+
+        import requests
+
         # Split model name and tag
-        if ':' in model_name:
-            base_model, requested_tag = model_name.split(':', 1)
+        if ":" in model_name:
+            base_model, requested_tag = model_name.split(":", 1)
         else:
             base_model, requested_tag = model_name, None
-        
+
         # First check if base model exists in library
         library_response = requests.get("https://ollama.com/library", timeout=8)
         if library_response.status_code != 200:
             return True, []  # Assume exists if can't check
-            
+
         # Extract model names from library page
         models_in_library = re.findall(r'href="/library/([^"]+)"', library_response.text)
-        
+
         if base_model not in models_in_library:
             return False, []  # Base model doesn't exist
-        
+
         # If base model exists, get available tags
         tags_response = requests.get(f"https://ollama.com/library/{base_model}/tags", timeout=8)
         if tags_response.status_code != 200:
             return True, []  # Base model exists but can't get tags
-            
+
         # Extract tags for this model - be more specific to avoid HTML artifacts
-        tag_pattern = rf'{re.escape(base_model)}:[a-zA-Z0-9\.\-_]+'
+        tag_pattern = rf"{re.escape(base_model)}:[a-zA-Z0-9\.\-_]+"
         raw_tags = re.findall(tag_pattern, tags_response.text)
-        
+
         # Clean up tags - remove HTML artifacts and duplicates
         available_tags = []
         seen = set()
         for tag in raw_tags:
             # Skip if it looks like HTML (contains < or >)
-            if '<' in tag or '>' in tag:
+            if "<" in tag or ">" in tag:
                 continue
             if tag not in seen:
                 seen.add(tag)
                 available_tags.append(tag)
-        
+
         # Check if exact model exists
         if requested_tag is None:
             # User just requested base model, suggest tags
@@ -83,76 +86,80 @@ def check_ollama_model_exists_remotely(model_name: str) -> tuple[bool, list[str]
         else:
             exact_match = model_name in available_tags
             return exact_match, available_tags[:10]
-            
+
     except Exception:
         pass
-    
+
     # If scraping fails, assume model might exist (don't block user)
     return True, []
 
 
-def search_ollama_models_fuzzy(query: str, available_models: List[str]) -> List[str]:
+def search_ollama_models_fuzzy(query: str, available_models: list[str]) -> list[str]:
     """Use intelligent fuzzy search for Ollama models"""
     if not available_models:
         return []
-    
+
     query_lower = query.lower()
     suggestions = []
-    
+
     # 1. Exact matches first
     exact_matches = [m for m in available_models if query_lower == m.lower()]
     suggestions.extend(exact_matches)
-    
+
     # 2. Starts with query
-    starts_with = [m for m in available_models if m.lower().startswith(query_lower) and m not in suggestions]
+    starts_with = [
+        m for m in available_models if m.lower().startswith(query_lower) and m not in suggestions
+    ]
     suggestions.extend(starts_with)
-    
+
     # 3. Contains query
     contains = [m for m in available_models if query_lower in m.lower() and m not in suggestions]
     suggestions.extend(contains)
-    
+
     # 4. Base model name matching (remove version numbers)
     def get_base_name(model_name: str) -> str:
         """Extract base name without version (e.g., 'llama3:8b' -> 'llama3')"""
-        return model_name.split(':')[0].split('-')[0]
-    
+        return model_name.split(":")[0].split("-")[0]
+
     query_base = get_base_name(query_lower)
     base_matches = [
-        m for m in available_models 
+        m
+        for m in available_models
         if get_base_name(m.lower()) == query_base and m not in suggestions
     ]
     suggestions.extend(base_matches)
-    
+
     # 5. Family/variant matching
     model_families = {
-        'llama': ['llama2', 'llama3', 'alpaca', 'vicuna', 'codellama'],
-        'qwen': ['qwen', 'qwen2', 'qwen3'],
-        'gemma': ['gemma', 'gemma2'],
-        'phi': ['phi', 'phi2', 'phi3'],
-        'mistral': ['mistral', 'mixtral', 'openhermes'],
-        'dolphin': ['dolphin', 'openchat'],
-        'deepseek': ['deepseek', 'deepseek-coder']
+        "llama": ["llama2", "llama3", "alpaca", "vicuna", "codellama"],
+        "qwen": ["qwen", "qwen2", "qwen3"],
+        "gemma": ["gemma", "gemma2"],
+        "phi": ["phi", "phi2", "phi3"],
+        "mistral": ["mistral", "mixtral", "openhermes"],
+        "dolphin": ["dolphin", "openchat"],
+        "deepseek": ["deepseek", "deepseek-coder"],
     }
-    
+
     query_family = None
     for family, variants in model_families.items():
         if any(variant in query_lower for variant in variants):
             query_family = family
             break
-    
+
     if query_family:
         family_variants = model_families[query_family]
         family_matches = [
-            m for m in available_models
+            m
+            for m in available_models
             if any(variant in m.lower() for variant in family_variants) and m not in suggestions
         ]
         suggestions.extend(family_matches)
-    
+
     # 6. Use difflib for remaining fuzzy matches
     remaining_models = [m for m in available_models if m not in suggestions]
     difflib_matches = difflib.get_close_matches(query_lower, remaining_models, n=3, cutoff=0.4)
     suggestions.extend(difflib_matches)
-    
+
     return suggestions[:8]  # Return top 8 suggestions
 
 
@@ -162,15 +169,13 @@ def search_ollama_models_fuzzy(query: str, available_models: List[str]) -> List[
 # Remove this too - no need for fallback
 
 
-def suggest_similar_models(invalid_model: str, available_models: List[str]) -> List[str]:
+def suggest_similar_models(invalid_model: str, available_models: list[str]) -> list[str]:
     """Use difflib to find similar model names"""
     if not available_models:
         return []
-    
+
     # Get close matches using fuzzy matching
-    suggestions = difflib.get_close_matches(
-        invalid_model, available_models, n=3, cutoff=0.3
-    )
+    suggestions = difflib.get_close_matches(invalid_model, available_models, n=3, cutoff=0.3)
     return suggestions
 
 
@@ -178,49 +183,50 @@ def check_hf_model_exists(model_name: str) -> bool:
     """Quick check if HuggingFace model exists without downloading"""
     try:
         from huggingface_hub import model_info
+
         model_info(model_name)
         return True
     except Exception:
         return False
 
 
-def get_popular_hf_models() -> List[str]:
+def get_popular_hf_models() -> list[str]:
     """Return a list of popular HuggingFace models for suggestions"""
     try:
         from huggingface_hub import list_models
-        
+
         # Get popular text-generation models, sorted by downloads
         models = list_models(
             filter="text-generation",
             sort="downloads",
             direction=-1,
-            limit=20  # Get top 20 most downloaded
+            limit=20,  # Get top 20 most downloaded
         )
-        
+
         # Extract model names and filter for chat/conversation models
         model_names = []
-        chat_keywords = ['chat', 'instruct', 'dialog', 'conversation', 'assistant']
-        
+        chat_keywords = ["chat", "instruct", "dialog", "conversation", "assistant"]
+
         for model in models:
-            model_name = model.id if hasattr(model, 'id') else str(model)
+            model_name = model.id if hasattr(model, "id") else str(model)
             # Prioritize models with chat-related keywords
             if any(keyword in model_name.lower() for keyword in chat_keywords):
                 model_names.append(model_name)
             elif len(model_names) < 10:  # Fill up with other popular models
                 model_names.append(model_name)
-                
+
         return model_names[:10] if model_names else _get_fallback_hf_models()
-        
+
     except Exception:
         # Fallback to static list if API call fails
         return _get_fallback_hf_models()
 
 
-def _get_fallback_hf_models() -> List[str]:
+def _get_fallback_hf_models() -> list[str]:
     """Fallback list of popular HuggingFace models"""
     return [
         "microsoft/DialoGPT-medium",
-        "microsoft/DialoGPT-large", 
+        "microsoft/DialoGPT-large",
         "facebook/blenderbot-400M-distill",
         "microsoft/phi-2",
         "deepseek-ai/deepseek-llm-7b-chat",
@@ -228,44 +234,44 @@ def _get_fallback_hf_models() -> List[str]:
         "facebook/blenderbot_small-90M",
         "microsoft/phi-1_5",
         "facebook/opt-350m",
-        "EleutherAI/gpt-neo-1.3B"
+        "EleutherAI/gpt-neo-1.3B",
     ]
 
 
-def search_hf_models_fuzzy(query: str, limit: int = 10) -> List[str]:
+def search_hf_models_fuzzy(query: str, limit: int = 10) -> list[str]:
     """Use HuggingFace Hub's native fuzzy search for model suggestions"""
     try:
         from huggingface_hub import list_models
-        
+
         # HF Hub's search is already fuzzy! It handles typos and partial matches
         models = list_models(
             search=query,
             filter="text-generation",
-            sort="downloads", 
+            sort="downloads",
             direction=-1,
-            limit=limit
+            limit=limit,
         )
-        
-        model_names = [model.id if hasattr(model, 'id') else str(model) for model in models]
-        
+
+        model_names = [model.id if hasattr(model, "id") else str(model) for model in models]
+
         # If direct search doesn't return enough results, try some variations
         if len(model_names) < 3:
             # Try searching for partial matches or common variations
             variations = []
-            
+
             # Extract base name (e.g., "gpt3" from "gpt-3.5")
-            base_query = query.lower().replace('-', '').replace('.', '').replace('_', '')
+            base_query = query.lower().replace("-", "").replace(".", "").replace("_", "")
             if base_query != query.lower():
                 variations.append(base_query)
-            
+
             # Try common model name patterns
-            if 'gpt' in query.lower():
-                variations.extend(['gpt2', 'gpt-neo', 'gpt-j', 'dialoGPT'])
-            elif 'llama' in query.lower():
-                variations.extend(['llama2', 'alpaca', 'vicuna'])
-            elif 'bert' in query.lower():
-                variations.extend(['roberta', 'distilbert', 'albert'])
-            
+            if "gpt" in query.lower():
+                variations.extend(["gpt2", "gpt-neo", "gpt-j", "dialoGPT"])
+            elif "llama" in query.lower():
+                variations.extend(["llama2", "alpaca", "vicuna"])
+            elif "bert" in query.lower():
+                variations.extend(["roberta", "distilbert", "albert"])
+
             # Search with variations
             for var in variations[:2]:  # Limit to 2 variations to avoid too many API calls
                 try:
@@ -274,13 +280,15 @@ def search_hf_models_fuzzy(query: str, limit: int = 10) -> List[str]:
                         filter="text-generation",
                         sort="downloads",
                         direction=-1,
-                        limit=3
+                        limit=3,
                     )
-                    var_names = [model.id if hasattr(model, 'id') else str(model) for model in var_models]
+                    var_names = [
+                        model.id if hasattr(model, "id") else str(model) for model in var_models
+                    ]
                     model_names.extend(var_names)
-                except:
+                except Exception:
                     continue
-        
+
         # Remove duplicates while preserving order
         seen = set()
         unique_models = []
@@ -288,65 +296,67 @@ def search_hf_models_fuzzy(query: str, limit: int = 10) -> List[str]:
             if model not in seen:
                 seen.add(model)
                 unique_models.append(model)
-        
+
         return unique_models[:limit]
-        
+
     except Exception:
         # If search fails, return empty list
         return []
 
 
-def search_hf_models(query: str, limit: int = 10) -> List[str]:
+def search_hf_models(query: str, limit: int = 10) -> list[str]:
     """Simple search for HuggingFace models based on query (kept for backward compatibility)"""
     return search_hf_models_fuzzy(query, limit)
 
 
-def validate_model_and_suggest(model_name: str, llm_type: str) -> Optional[str]:
+def validate_model_and_suggest(model_name: str, llm_type: str) -> str | None:
     """Validate model name and provide suggestions if invalid"""
     if llm_type == "ollama":
         available_models = check_ollama_models()
         if available_models and model_name not in available_models:
             error_msg = f"Model '{model_name}' not found in your local Ollama installation."
-            
+
             # Check if the model exists remotely and get available tags
             model_exists_remotely, available_tags = check_ollama_model_exists_remotely(model_name)
-            
+
             if model_exists_remotely and model_name in available_tags:
                 # Exact model exists remotely - suggest pulling it
-                error_msg += f"\n\nTo install the requested model:\n"
+                error_msg += "\n\nTo install the requested model:\n"
                 error_msg += f"  ollama pull {model_name}\n"
-                
+
                 # Show local alternatives
                 suggestions = search_ollama_models_fuzzy(model_name, available_models)
                 if suggestions:
                     error_msg += "\nOr use one of these similar installed models:\n"
                     for i, suggestion in enumerate(suggestions, 1):
                         error_msg += f"  {i}. {suggestion}\n"
-                        
+
             elif model_exists_remotely and available_tags:
                 # Base model exists but requested tag doesn't - suggest correct tags
-                base_model = model_name.split(':')[0]
-                requested_tag = model_name.split(':', 1)[1] if ':' in model_name else None
-                
-                error_msg += f"\n\nModel '{base_model}' exists, but tag '{requested_tag}' is not available."
+                base_model = model_name.split(":")[0]
+                requested_tag = model_name.split(":", 1)[1] if ":" in model_name else None
+
+                error_msg += (
+                    f"\n\nModel '{base_model}' exists, but tag '{requested_tag}' is not available."
+                )
                 error_msg += f"\n\nAvailable {base_model} models you can install:\n"
                 for i, tag in enumerate(available_tags[:8], 1):
                     error_msg += f"  {i}. ollama pull {tag}\n"
                 if len(available_tags) > 8:
                     error_msg += f"  ... and {len(available_tags) - 8} more variants\n"
-                    
+
                 # Also show local alternatives
                 suggestions = search_ollama_models_fuzzy(model_name, available_models)
                 if suggestions:
                     error_msg += "\nOr use one of these similar installed models:\n"
                     for i, suggestion in enumerate(suggestions, 1):
                         error_msg += f"  {i}. {suggestion}\n"
-                        
+
             else:
                 # Model doesn't exist remotely - show fuzzy suggestions
                 suggestions = search_ollama_models_fuzzy(model_name, available_models)
                 error_msg += f"\n\nModel '{model_name}' was not found in Ollama's library."
-                
+
                 if suggestions:
                     error_msg += "\n\nDid you mean one of these installed models?\n"
                     for i, suggestion in enumerate(suggestions, 1):
@@ -357,23 +367,25 @@ def validate_model_and_suggest(model_name: str, llm_type: str) -> Optional[str]:
                         error_msg += f"  {i}. {model}\n"
                     if len(available_models) > 8:
                         error_msg += f"  ... and {len(available_models) - 8} more\n"
-            
+
             error_msg += "\n\nCommands:"
             error_msg += "\n  ollama list                    # List installed models"
             if model_exists_remotely and available_tags:
                 if model_name in available_tags:
                     error_msg += f"\n  ollama pull {model_name}          # Install requested model"
                 else:
-                    error_msg += f"\n  ollama pull {available_tags[0]}    # Install recommended variant"
+                    error_msg += (
+                        f"\n  ollama pull {available_tags[0]}    # Install recommended variant"
+                    )
             error_msg += "\n  https://ollama.com/library     # Browse available models"
             return error_msg
-            
+
     elif llm_type == "hf":
         # For HF models, we can do a quick existence check
         if not check_hf_model_exists(model_name):
             # Use HF Hub's native fuzzy search directly
             search_suggestions = search_hf_models_fuzzy(model_name, limit=8)
-            
+
             error_msg = f"Model '{model_name}' not found on HuggingFace Hub."
             if search_suggestions:
                 error_msg += "\n\nDid you mean one of these?\n"
@@ -385,10 +397,10 @@ def validate_model_and_suggest(model_name: str, llm_type: str) -> Optional[str]:
                 error_msg += "\n\nPopular chat models:\n"
                 for i, model in enumerate(popular_models[:5], 1):
                     error_msg += f"  {i}. {model}\n"
-            
+
             error_msg += f"\nSearch more: https://huggingface.co/models?search={model_name}&pipeline_tag=text-generation"
             return error_msg
-    
+
     return None  # Model is valid or we can't check
 
 
@@ -451,28 +463,27 @@ class OllamaChat(LLMInterface):
             # Check if the Ollama server is responsive
             if host:
                 requests.get(host)
-                
+
             # Pre-check model availability with helpful suggestions
             model_error = validate_model_and_suggest(model, "ollama")
             if model_error:
                 raise ValueError(model_error)
-                
+
         except ImportError:
             raise ImportError(
                 "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 {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 {host}. Please ensure Ollama is running."
             )
 
     def ask(self, prompt: str, **kwargs) -> str:
-        import requests
         import json
 
+        import requests
+
         full_url = f"{self.host}/api/generate"
         payload = {
             "model": self.model,
@@ -482,7 +493,7 @@ class OllamaChat(LLMInterface):
         }
         logger.debug(f"Sending request to Ollama: {payload}")
         try:
-            logger.info(f"Sending request to Ollama and waiting for response...")
+            logger.info("Sending request to Ollama and waiting for response...")
             response = requests.post(full_url, data=json.dumps(payload))
             response.raise_for_status()
 
@@ -506,15 +517,15 @@ class HFChat(LLMInterface):
 
     def __init__(self, model_name: str = "deepseek-ai/deepseek-llm-7b-chat"):
         logger.info(f"Initializing HFChat with model='{model_name}'")
-        
+
         # Pre-check model availability with helpful suggestions
         model_error = validate_model_and_suggest(model_name, "hf")
         if model_error:
             raise ValueError(model_error)
-            
+
         try:
-            from transformers import AutoTokenizer, AutoModelForCausalLM
             import torch
+            from transformers import AutoModelForCausalLM, AutoTokenizer
         except ImportError:
             raise ImportError(
                 "The 'transformers' and 'torch' libraries are required for Hugging Face models. Please install them with 'pip install transformers torch'."
@@ -537,36 +548,34 @@ class HFChat(LLMInterface):
             model_name,
             torch_dtype=torch.float16 if self.device != "cpu" else torch.float32,
             device_map="auto" if self.device != "cpu" else None,
-            trust_remote_code=True
+            trust_remote_code=True,
         )
-        
+
         # Move model to device if not using device_map
         if self.device != "cpu" and "device_map" not in str(self.model):
             self.model = self.model.to(self.device)
-        
+
         # Set pad token if not present
         if self.tokenizer.pad_token is None:
             self.tokenizer.pad_token = self.tokenizer.eos_token
 
     def ask(self, prompt: str, **kwargs) -> str:
-        print('kwargs in HF: ', kwargs)
+        print("kwargs in HF: ", kwargs)
         # Check if this is a Qwen model and add /no_think by default
         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"
-        
+
         # Prepare chat template
         messages = [{"role": "user", "content": prompt}]
-        
+
         # Apply chat template if available
         if hasattr(self.tokenizer, "apply_chat_template"):
             try:
                 formatted_prompt = self.tokenizer.apply_chat_template(
-                    messages, 
-                    tokenize=False, 
-                    add_generation_prompt=True
+                    messages, tokenize=False, add_generation_prompt=True
                 )
             except Exception as e:
                 logger.warning(f"Chat template failed, using raw prompt: {e}")
@@ -577,13 +586,13 @@ class HFChat(LLMInterface):
 
         # Tokenize input
         inputs = self.tokenizer(
-            formatted_prompt, 
-            return_tensors="pt", 
+            formatted_prompt,
+            return_tensors="pt",
             padding=True,
             truncation=True,
-            max_length=2048
+            max_length=2048,
         )
-        
+
         # Move inputs to device
         if self.device != "cpu":
             inputs = {k: v.to(self.device) for k, v in inputs.items()}
@@ -597,32 +606,29 @@ class HFChat(LLMInterface):
             "pad_token_id": self.tokenizer.eos_token_id,
             "eos_token_id": self.tokenizer.eos_token_id,
         }
-        
+
         # Handle temperature=0 for greedy decoding
         if generation_config["temperature"] == 0.0:
             generation_config["do_sample"] = False
             generation_config.pop("temperature")
 
         logger.info(f"Generating with HuggingFace model, config: {generation_config}")
-        
+
         # Generate
         with torch.no_grad():
-            outputs = self.model.generate(
-                **inputs,
-                **generation_config
-            )
+            outputs = self.model.generate(**inputs, **generation_config)
 
         # Decode response
-        generated_tokens = outputs[0][inputs["input_ids"].shape[1]:]
+        generated_tokens = outputs[0][inputs["input_ids"].shape[1] :]
         response = self.tokenizer.decode(generated_tokens, skip_special_tokens=True)
-        
+
         return response.strip()
 
 
 class OpenAIChat(LLMInterface):
     """LLM interface for OpenAI models."""
 
-    def __init__(self, model: str = "gpt-4o", api_key: Optional[str] = None):
+    def __init__(self, model: str = "gpt-4o", api_key: str | None = None):
         self.model = model
         self.api_key = api_key or os.getenv("OPENAI_API_KEY")
 
@@ -649,11 +655,7 @@ class OpenAIChat(LLMInterface):
             "messages": [{"role": "user", "content": prompt}],
             "max_tokens": kwargs.get("max_tokens", 1000),
             "temperature": kwargs.get("temperature", 0.7),
-            **{
-                k: v
-                for k, v in kwargs.items()
-                if k not in ["max_tokens", "temperature"]
-            },
+            **{k: v for k, v in kwargs.items() if k not in ["max_tokens", "temperature"]},
         }
 
         logger.info(f"Sending request to OpenAI with model {self.model}")
@@ -675,7 +677,7 @@ class SimulatedChat(LLMInterface):
         return "This is a simulated answer from the LLM based on the retrieved context."
 
 
-def get_llm(llm_config: Optional[Dict[str, Any]] = None) -> LLMInterface:
+def get_llm(llm_config: dict[str, Any] | None = None) -> LLMInterface:
     """
     Factory function to get an LLM interface based on configuration.
 

packages/leann-core/src/leann/cli.py

@@ -5,12 +5,14 @@ from pathlib import Path
 from llama_index.core import SimpleDirectoryReader
 from llama_index.core.node_parser import SentenceSplitter
 
-from .api import LeannBuilder, LeannSearcher, LeannChat
+from .api import LeannBuilder, LeannChat, LeannSearcher
+
 
 def extract_pdf_text_with_pymupdf(file_path: str) -> str:
     """Extract text from PDF using PyMuPDF for better quality."""
     try:
         import fitz  # PyMuPDF
+
         doc = fitz.open(file_path)
         text = ""
         for page in doc:
@@ -21,10 +23,12 @@ def extract_pdf_text_with_pymupdf(file_path: str) -> str:
         # Fallback to default reader
         return None
 
+
 def extract_pdf_text_with_pdfplumber(file_path: str) -> str:
     """Extract text from PDF using pdfplumber for better quality."""
     try:
         import pdfplumber
+
         text = ""
         with pdfplumber.open(file_path) as pdf:
             for page in pdf.pages:
@@ -72,18 +76,12 @@ Examples:
         # Build command
         build_parser = subparsers.add_parser("build", help="Build document index")
         build_parser.add_argument("index_name", help="Index name")
-        build_parser.add_argument(
-            "--docs", type=str, required=True, help="Documents directory"
-        )
+        build_parser.add_argument("--docs", type=str, required=True, help="Documents directory")
         build_parser.add_argument(
             "--backend", type=str, default="hnsw", choices=["hnsw", "diskann"]
         )
-        build_parser.add_argument(
-            "--embedding-model", type=str, default="facebook/contriever"
-        )
-        build_parser.add_argument(
-            "--force", "-f", action="store_true", help="Force rebuild"
-        )
+        build_parser.add_argument("--embedding-model", type=str, default="facebook/contriever")
+        build_parser.add_argument("--force", "-f", action="store_true", help="Force rebuild")
         build_parser.add_argument("--graph-degree", type=int, default=32)
         build_parser.add_argument("--complexity", type=int, default=64)
         build_parser.add_argument("--num-threads", type=int, default=1)
@@ -129,7 +127,7 @@ Examples:
         )
 
         # List command
-        list_parser = subparsers.add_parser("list", help="List all indexes")
+        subparsers.add_parser("list", help="List all indexes")
 
         return parser
 
@@ -137,17 +135,13 @@ Examples:
         print("Stored LEANN indexes:")
 
         if not self.indexes_dir.exists():
-            print(
-                "No indexes found. Use 'leann build <name> --docs <dir>' to create one."
-            )
+            print("No indexes found. Use 'leann build <name> --docs <dir>' to create one.")
             return
 
         index_dirs = [d for d in self.indexes_dir.iterdir() if d.is_dir()]
 
         if not index_dirs:
-            print(
-                "No indexes found. Use 'leann build <name> --docs <dir>' to create one."
-            )
+            print("No indexes found. Use 'leann build <name> --docs <dir>' to create one.")
             return
 
         print(f"Found {len(index_dirs)} indexes:")
@@ -157,15 +151,15 @@ Examples:
 
             print(f"  {i}. {index_name} [{status}]")
             if self.index_exists(index_name):
-                meta_file = index_dir / "documents.leann.meta.json"
-                size_mb = sum(
-                    f.stat().st_size for f in index_dir.iterdir() if f.is_file()
-                ) / (1024 * 1024)
+                index_dir / "documents.leann.meta.json"
+                size_mb = sum(f.stat().st_size for f in index_dir.iterdir() if f.is_file()) / (
+                    1024 * 1024
+                )
                 print(f"     Size: {size_mb:.1f} MB")
 
         if index_dirs:
             example_name = index_dirs[0].name
-            print(f"\nUsage:")
+            print("\nUsage:")
             print(f'  leann search {example_name} "your query"')
             print(f"  leann ask {example_name} --interactive")
 
@@ -175,19 +169,20 @@ Examples:
         # Try to use better PDF parsers first
         documents = []
         docs_path = Path(docs_dir)
-        
+
         for file_path in docs_path.rglob("*.pdf"):
             print(f"Processing PDF: {file_path}")
-            
+
             # Try PyMuPDF first (best quality)
             text = extract_pdf_text_with_pymupdf(str(file_path))
             if text is None:
                 # Try pdfplumber
                 text = extract_pdf_text_with_pdfplumber(str(file_path))
-            
+
             if text:
                 # Create a simple document structure
                 from llama_index.core import Document
+
                 doc = Document(text=text, metadata={"source": str(file_path)})
                 documents.append(doc)
             else:

packages/leann-core/src/leann/embedding_compute.py

@@ -4,11 +4,12 @@ Consolidates all embedding computation logic using SentenceTransformer
 Preserves all optimization parameters to ensure performance
 """
 
-import numpy as np
-import torch
-from typing import List, Dict, Any
 import logging
 import os
+from typing import Any
+
+import numpy as np
+import torch
 
 # Set up logger with proper level
 logger = logging.getLogger(__name__)
@@ -17,11 +18,11 @@ log_level = getattr(logging, LOG_LEVEL, logging.WARNING)
 logger.setLevel(log_level)
 
 # Global model cache to avoid repeated loading
-_model_cache: Dict[str, Any] = {}
+_model_cache: dict[str, Any] = {}
 
 
 def compute_embeddings(
-    texts: List[str],
+    texts: list[str],
     model_name: str,
     mode: str = "sentence-transformers",
     is_build: bool = False,
@@ -59,7 +60,7 @@ def compute_embeddings(
 
 
 def compute_embeddings_sentence_transformers(
-    texts: List[str],
+    texts: list[str],
     model_name: str,
     use_fp16: bool = True,
     device: str = "auto",
@@ -114,9 +115,7 @@ def compute_embeddings_sentence_transformers(
         logger.info(f"Using cached optimized model: {model_name}")
         model = _model_cache[cache_key]
     else:
-        logger.info(
-            f"Loading and caching optimized SentenceTransformer model: {model_name}"
-        )
+        logger.info(f"Loading and caching optimized SentenceTransformer model: {model_name}")
         from sentence_transformers import SentenceTransformer
 
         logger.info(f"Using device: {device}")
@@ -134,9 +133,7 @@ def compute_embeddings_sentence_transformers(
                 if hasattr(torch.mps, "set_per_process_memory_fraction"):
                     torch.mps.set_per_process_memory_fraction(0.9)
             except AttributeError:
-                logger.warning(
-                    "Some MPS optimizations not available in this PyTorch version"
-                )
+                logger.warning("Some MPS optimizations not available in this PyTorch version")
         elif device == "cpu":
             # TODO: Haven't tested this yet
             torch.set_num_threads(min(8, os.cpu_count() or 4))
@@ -226,25 +223,22 @@ def compute_embeddings_sentence_transformers(
             device=device,
         )
 
-    logger.info(
-        f"Generated {len(embeddings)} embeddings, dimension: {embeddings.shape[1]}"
-    )
+    logger.info(f"Generated {len(embeddings)} embeddings, dimension: {embeddings.shape[1]}")
 
     # Validate results
     if np.isnan(embeddings).any() or np.isinf(embeddings).any():
-        raise RuntimeError(
-            f"Detected NaN or Inf values in embeddings, model: {model_name}"
-        )
+        raise RuntimeError(f"Detected NaN or Inf values in embeddings, model: {model_name}")
 
     return embeddings
 
 
-def compute_embeddings_openai(texts: List[str], model_name: str) -> 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 openai
         import os
+
+        import openai
     except ImportError as e:
         raise ImportError(f"OpenAI package not installed: {e}")
 
@@ -294,16 +288,12 @@ def compute_embeddings_openai(texts: List[str], model_name: str) -> np.ndarray:
             raise
 
     embeddings = np.array(all_embeddings, dtype=np.float32)
-    logger.info(
-        f"Generated {len(embeddings)} embeddings, dimension: {embeddings.shape[1]}"
-    )
+    logger.info(f"Generated {len(embeddings)} embeddings, dimension: {embeddings.shape[1]}")
     print(f"len of embeddings: {len(embeddings)}")
     return embeddings
 
 
-def compute_embeddings_mlx(
-    chunks: List[str], model_name: str, batch_size: int = 16
-) -> np.ndarray:
+def compute_embeddings_mlx(chunks: list[str], model_name: str, batch_size: int = 16) -> np.ndarray:
     # TODO: @yichuan-w add progress bar only in build mode
     """Computes embeddings using an MLX model."""
     try:

packages/leann-core/src/leann/embedding_server_manager.py

@@ -1,12 +1,12 @@
-import time
 import atexit
+import logging
+import os
 import socket
 import subprocess
 import sys
-import os
-import logging
+import time
 from pathlib import Path
-from typing import Optional
+
 import psutil
 
 # Set up logging based on environment variable
@@ -33,7 +33,7 @@ def _get_available_port(start_port: int = 5557) -> int:
                 return port
         except OSError:
             port += 1
-    raise RuntimeError(f"No available ports found in range {start_port}-{start_port+100}")
+    raise RuntimeError(f"No available ports found in range {start_port}-{start_port + 100}")
 
 
 def _check_port(port: int) -> bool:
@@ -182,8 +182,8 @@ class EmbeddingServerManager:
                                        e.g., "leann_backend_diskann.embedding_server"
         """
         self.backend_module_name = backend_module_name
-        self.server_process: Optional[subprocess.Popen] = None
-        self.server_port: Optional[int] = None
+        self.server_process: subprocess.Popen | None = None
+        self.server_port: int | None = None
         self._atexit_registered = False
 
     def start_server(
@@ -234,10 +234,10 @@ class EmbeddingServerManager:
             return False, port
 
         logger.info(f"Starting server on port {actual_port} for Colab environment")
-        
+
         # Use a simpler startup strategy for Colab
         command = self._build_server_command(actual_port, model_name, embedding_mode, **kwargs)
-        
+
         try:
             # In Colab, we'll use a more direct approach
             self._launch_server_process_colab(command, actual_port)
@@ -246,26 +246,16 @@ class EmbeddingServerManager:
             logger.error(f"Failed to start embedding server in Colab: {e}")
             return False, actual_port
 
-    def _has_compatible_running_server(
-        self, model_name: str, passages_file: str
-    ) -> bool:
+    def _has_compatible_running_server(self, model_name: str, passages_file: str) -> bool:
         """Check if we have a compatible running server."""
-        if not (
-            self.server_process
-            and self.server_process.poll() is None
-            and self.server_port
-        ):
+        if not (self.server_process and self.server_process.poll() is None and self.server_port):
             return False
 
         if _check_process_matches_config(self.server_port, model_name, passages_file):
-            logger.info(
-                f"Existing server process (PID {self.server_process.pid}) is compatible"
-            )
+            logger.info(f"Existing server process (PID {self.server_process.pid}) is compatible")
             return True
 
-        logger.info(
-            "Existing server process is incompatible. Should start a new server."
-        )
+        logger.info("Existing server process is incompatible. Should start a new server.")
         return False
 
     def _start_new_server(
@@ -400,7 +390,7 @@ class EmbeddingServerManager:
     def _wait_for_server_ready_colab(self, port: int) -> tuple[bool, int]:
         """Wait for the server to be ready with Colab-specific timeout."""
         max_wait, wait_interval = 30, 0.5  # Shorter timeout for Colab
-        
+
         for _ in range(int(max_wait / wait_interval)):
             if _check_port(port):
                 logger.info("Colab embedding server is ready!")
@@ -409,7 +399,7 @@ class EmbeddingServerManager:
             if self.server_process and self.server_process.poll() is not None:
                 # Check for error output
                 stdout, stderr = self.server_process.communicate()
-                logger.error(f"Colab server terminated during startup.")
+                logger.error("Colab server terminated during startup.")
                 logger.error(f"stdout: {stdout}")
                 logger.error(f"stderr: {stderr}")
                 return False, port

packages/leann-core/src/leann/interface.py

@@ -1,15 +1,14 @@
 from abc import ABC, abstractmethod
+from typing import Any, Literal
+
 import numpy as np
-from typing import Dict, Any, List, Literal, Optional
 
 
 class LeannBackendBuilderInterface(ABC):
     """Backend interface for building indexes"""
 
     @abstractmethod
-    def build(
-        self, data: np.ndarray, ids: List[str], index_path: str, **kwargs
-    ) -> None:
+    def build(self, data: np.ndarray, ids: list[str], index_path: str, **kwargs) -> None:
         """Build index
 
         Args:
@@ -35,9 +34,7 @@ class LeannBackendSearcherInterface(ABC):
         pass
 
     @abstractmethod
-    def _ensure_server_running(
-        self, passages_source_file: str, port: Optional[int], **kwargs
-    ) -> int:
+    def _ensure_server_running(self, passages_source_file: str, port: int | None, **kwargs) -> int:
         """Ensure server is running"""
         pass
 
@@ -51,9 +48,9 @@ class LeannBackendSearcherInterface(ABC):
         prune_ratio: float = 0.0,
         recompute_embeddings: bool = False,
         pruning_strategy: Literal["global", "local", "proportional"] = "global",
-        zmq_port: Optional[int] = None,
+        zmq_port: int | None = None,
         **kwargs,
-    ) -> Dict[str, Any]:
+    ) -> dict[str, Any]:
         """Search for nearest neighbors
 
         Args:
@@ -77,7 +74,7 @@ class LeannBackendSearcherInterface(ABC):
         self,
         query: str,
         use_server_if_available: bool = True,
-        zmq_port: Optional[int] = None,
+        zmq_port: int | None = None,
     ) -> np.ndarray:
         """Compute embedding for a query string
 

packages/leann-core/src/leann/registry.py

@@ -1,13 +1,13 @@
 # packages/leann-core/src/leann/registry.py
 
-from typing import Dict, TYPE_CHECKING
 import importlib
 import importlib.metadata
+from typing import TYPE_CHECKING
 
 if TYPE_CHECKING:
     from leann.interface import LeannBackendFactoryInterface
 
-BACKEND_REGISTRY: Dict[str, "LeannBackendFactoryInterface"] = {}
+BACKEND_REGISTRY: dict[str, "LeannBackendFactoryInterface"] = {}
 
 
 def register_backend(name: str):
@@ -31,13 +31,11 @@ def autodiscover_backends():
             backend_module_name = dist_name.replace("-", "_")
             discovered_backends.append(backend_module_name)
 
-    for backend_module_name in sorted(
-        discovered_backends
-    ):  # sort for deterministic loading
+    for backend_module_name in sorted(discovered_backends):  # sort for deterministic loading
         try:
             importlib.import_module(backend_module_name)
             # Registration message is printed by the decorator
-        except ImportError as e:
+        except ImportError:
             # print(f"WARN: Could not import backend module '{backend_module_name}': {e}")
             pass
     # print("INFO: Backend auto-discovery finished.")

packages/leann-core/src/leann/searcher_base.py

@@ -1,7 +1,7 @@
 import json
 from abc import ABC, abstractmethod
 from pathlib import Path
-from typing import Dict, Any, Literal, Optional
+from typing import Any, Literal
 
 import numpy as np
 
@@ -38,9 +38,7 @@ class BaseSearcher(LeannBackendSearcherInterface, ABC):
 
         self.embedding_model = self.meta.get("embedding_model")
         if not self.embedding_model:
-            print(
-                "WARNING: embedding_model not found in meta.json. Recompute will fail."
-            )
+            print("WARNING: embedding_model not found in meta.json. Recompute will fail.")
 
         self.embedding_mode = self.meta.get("embedding_mode", "sentence-transformers")
 
@@ -48,26 +46,22 @@ class BaseSearcher(LeannBackendSearcherInterface, ABC):
             backend_module_name=backend_module_name,
         )
 
-    def _load_meta(self) -> Dict[str, Any]:
+    def _load_meta(self) -> dict[str, Any]:
         """Loads the metadata file associated with the index."""
         # This is the corrected logic for finding the meta file.
         meta_path = self.index_dir / f"{self.index_path.name}.meta.json"
         if not meta_path.exists():
             raise FileNotFoundError(f"Leann metadata file not found at {meta_path}")
-        with open(meta_path, "r", encoding="utf-8") as f:
+        with open(meta_path, encoding="utf-8") as f:
             return json.load(f)
 
-    def _ensure_server_running(
-        self, passages_source_file: str, port: int, **kwargs
-    ) -> int:
+    def _ensure_server_running(self, passages_source_file: str, port: int, **kwargs) -> int:
         """
         Ensures the embedding server is running if recompute is needed.
         This is a helper for subclasses.
         """
         if not self.embedding_model:
-            raise ValueError(
-                "Cannot use recompute mode without 'embedding_model' in meta.json."
-            )
+            raise ValueError("Cannot use recompute mode without 'embedding_model' in meta.json.")
 
         server_started, actual_port = self.embedding_server_manager.start_server(
             port=port,
@@ -78,9 +72,7 @@ class BaseSearcher(LeannBackendSearcherInterface, ABC):
             enable_warmup=kwargs.get("enable_warmup", False),
         )
         if not server_started:
-            raise RuntimeError(
-                f"Failed to start embedding server on port {actual_port}"
-            )
+            raise RuntimeError(f"Failed to start embedding server on port {actual_port}")
 
         return actual_port
 
@@ -109,9 +101,7 @@ class BaseSearcher(LeannBackendSearcherInterface, ABC):
                 # on that port?
 
                 # Ensure we have a server with passages_file for compatibility
-                passages_source_file = (
-                    self.index_dir / f"{self.index_path.name}.meta.json"
-                )
+                passages_source_file = self.index_dir / f"{self.index_path.name}.meta.json"
                 # Convert to absolute path to ensure server can find it
                 zmq_port = self._ensure_server_running(
                     str(passages_source_file.resolve()), zmq_port
@@ -132,8 +122,8 @@ class BaseSearcher(LeannBackendSearcherInterface, ABC):
 
     def _compute_embedding_via_server(self, chunks: list, zmq_port: int) -> np.ndarray:
         """Compute embeddings using the ZMQ embedding server."""
-        import zmq
         import msgpack
+        import zmq
 
         try:
             context = zmq.Context()
@@ -172,9 +162,9 @@ class BaseSearcher(LeannBackendSearcherInterface, ABC):
         prune_ratio: float = 0.0,
         recompute_embeddings: bool = False,
         pruning_strategy: Literal["global", "local", "proportional"] = "global",
-        zmq_port: Optional[int] = None,
+        zmq_port: int | None = None,
         **kwargs,
-    ) -> Dict[str, Any]:
+    ) -> dict[str, Any]:
         """
         Search for the top_k nearest neighbors of the query vector.
 

packages/leann/README.md

@@ -16,25 +16,24 @@ uv pip install leann[diskann]
 
 ```python
 from leann import LeannBuilder, LeannSearcher, LeannChat
+from pathlib import Path
+INDEX_PATH = str(Path("./").resolve() / "demo.leann")
 
 # Build an index
 builder = LeannBuilder(backend_name="hnsw")
 builder.add_text("LEANN saves 97% storage compared to traditional vector databases.")
-builder.build_index("my_index.leann")
+builder.add_text("Tung Tung Tung Sahur called—they need their banana‑crocodile hybrid back")
+builder.build_index(INDEX_PATH)
 
 # Search
-searcher = LeannSearcher("my_index.leann")
-results = searcher.search("storage savings", top_k=3)
+searcher = LeannSearcher(INDEX_PATH)
+results = searcher.search("fantastical AI-generated creatures", top_k=1)
 
 # Chat with your data
-chat = LeannChat("my_index.leann", llm_config={"type": "ollama", "model": "llama3.2:1b"})
-response = chat.ask("How much storage does LEANN save?")
+chat = LeannChat(INDEX_PATH, llm_config={"type": "hf", "model": "Qwen/Qwen3-0.6B"})
+response = chat.ask("How much storage does LEANN save?", top_k=1)
 ```
 
-## Documentation
-
-For full documentation, visit [https://leann.readthedocs.io](https://leann.readthedocs.io)
-
 ## License
 
-MIT License 
+MIT License

packages/leann/__init__.py

@@ -7,6 +7,6 @@ A revolutionary vector database that democratizes personal AI.
 __version__ = "0.1.0"
 
 # Re-export main API from leann-core
-from leann_core import LeannBuilder, LeannSearcher, LeannChat
+from leann_core import LeannBuilder, LeannChat, LeannSearcher
 
-__all__ = ["LeannBuilder", "LeannSearcher", "LeannChat"]
+__all__ = ["LeannBuilder", "LeannChat", "LeannSearcher"]

packages/leann/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "leann"
-version = "0.1.12"
+version = "0.1.15"
 description = "LEANN - The smallest vector index in the world. RAG Everything with LEANN!"
 readme = "README.md"
 requires-python = ">=3.9"
@@ -36,7 +36,5 @@ diskann = [
 ]
 
 [project.urls]
-Homepage = "https://github.com/yourusername/leann"
-Documentation = "https://leann.readthedocs.io"
-Repository = "https://github.com/yourusername/leann"
-Issues = "https://github.com/yourusername/leann/issues" 
+Repository = "https://github.com/yichuan-w/LEANN"
+Issues = "https://github.com/yichuan-w/LEANN/issues"

packages/wechat-exporter/main.py

@@ -1,22 +1,23 @@
 import json
-import typer
-from pathlib import Path
-import requests
-from tqdm import tqdm
-import xml.etree.ElementTree as ET
-from typing_extensions import Annotated
 import sqlite3
+import xml.etree.ElementTree as ElementTree
+from pathlib import Path
+from typing import Annotated
+
+import requests
+import typer
+from tqdm import tqdm
 
 app = typer.Typer()
 
+
 def get_safe_path(s: str) -> str:
     """
     Remove invalid characters to sanitize a path.
     :param s: str to sanitize
     :returns: sanitized str
     """
-    ban_chars = "\\  /  :  *  ?  \"  '  <  >  |  $  \r  \n".replace(
-        ' ', '')
+    ban_chars = "\\  /  :  *  ?  \"  '  <  >  |  $  \r  \n".replace(" ", "")
     for i in ban_chars:
         s = s.replace(i, "")
     return s
@@ -25,36 +26,40 @@ def get_safe_path(s: str) -> str:
 def process_history(history: str):
     if history.startswith("<?xml") or history.startswith("<msg>"):
         try:
-            root = ET.fromstring(history)
-            title = root.find('.//title').text if root.find('.//title') is not None else None
-            quoted = root.find('.//refermsg/content').text if root.find('.//refermsg/content') is not None else None
+            root = ElementTree.fromstring(history)
+            title = root.find(".//title").text if root.find(".//title") is not None else None
+            quoted = (
+                root.find(".//refermsg/content").text
+                if root.find(".//refermsg/content") is not None
+                else None
+            )
             if title and quoted:
-                return {
-                    "title": title,
-                    "quoted": process_history(quoted)
-                }
+                return {"title": title, "quoted": process_history(quoted)}
             if title:
                 return title
         except Exception:
             return history
     return history
 
+
 def get_message(history: dict | str):
     if isinstance(history, dict):
-        if 'title' in history:
-            return history['title']
+        if "title" in history:
+            return history["title"]
     else:
         return history
 
+
 def export_chathistory(user_id: str):
-    res = requests.get("http://localhost:48065/wechat/chatlog", params={
-        "userId": user_id,
-        "count": 100000
-    }).json()
-    for i in range(len(res['chatLogs'])):
-        res['chatLogs'][i]['content'] = process_history(res['chatLogs'][i]['content'])
-        res['chatLogs'][i]['message'] = get_message(res['chatLogs'][i]['content'])
-    return res['chatLogs']
+    res = requests.get(
+        "http://localhost:48065/wechat/chatlog",
+        params={"userId": user_id, "count": 100000},
+    ).json()
+    for i in range(len(res["chatLogs"])):
+        res["chatLogs"][i]["content"] = process_history(res["chatLogs"][i]["content"])
+        res["chatLogs"][i]["message"] = get_message(res["chatLogs"][i]["content"])
+    return res["chatLogs"]
+
 
 @app.command()
 def export_all(dest: Annotated[Path, typer.Argument(help="Destination path to export to.")]):
@@ -64,7 +69,7 @@ def export_all(dest: Annotated[Path, typer.Argument(help="Destination path to ex
     if not dest.is_dir():
         if not dest.exists():
             inp = typer.prompt("Destination path does not exist, create it? (y/n)")
-            if inp.lower() == 'y':
+            if inp.lower() == "y":
                 dest.mkdir(parents=True)
             else:
                 typer.echo("Aborted.", err=True)
@@ -77,12 +82,12 @@ def export_all(dest: Annotated[Path, typer.Argument(help="Destination path to ex
     exported_count = 0
     for user in tqdm(all_users):
         try:
-            usr_chatlog = export_chathistory(user['arg'])
-            
+            usr_chatlog = export_chathistory(user["arg"])
+
             # Only write file if there are messages
             if len(usr_chatlog) > 0:
-                out_path = dest/get_safe_path((user['title'] or "")+"-"+user['arg']+'.json')
-                with open(out_path, 'w', encoding='utf-8') as f:
+                out_path = dest / get_safe_path((user["title"] or "") + "-" + user["arg"] + ".json")
+                with open(out_path, "w", encoding="utf-8") as f:
                     json.dump(usr_chatlog, f, ensure_ascii=False, indent=2)
                 exported_count += 1
         except Exception as e:
@@ -91,23 +96,43 @@ def export_all(dest: Annotated[Path, typer.Argument(help="Destination path to ex
 
     print(f"Exported {exported_count} users' chat history to {dest} in json.")
 
+
 @app.command()
-def export_sqlite(dest: Annotated[Path, typer.Argument(help="Destination path to export to.")] = Path("chatlog.db")):
+def export_sqlite(
+    dest: Annotated[Path, typer.Argument(help="Destination path to export to.")] = Path(
+        "chatlog.db"
+    ),
+):
     """
     Export all users' chat history to a sqlite database.
     """
     connection = sqlite3.connect(dest)
     cursor = connection.cursor()
-    cursor.execute("CREATE TABLE IF NOT EXISTS chatlog (id INTEGER PRIMARY KEY AUTOINCREMENT, with_id TEXT, from_user TEXT, to_user TEXT, message TEXT, timest DATETIME, auxiliary TEXT)")
+    cursor.execute(
+        "CREATE TABLE IF NOT EXISTS chatlog (id INTEGER PRIMARY KEY AUTOINCREMENT, with_id TEXT, from_user TEXT, to_user TEXT, message TEXT, timest DATETIME, auxiliary TEXT)"
+    )
     cursor.execute("CREATE INDEX IF NOT EXISTS chatlog_with_id_index ON chatlog (with_id)")
     cursor.execute("CREATE TABLE iF NOT EXISTS users (id TEXT PRIMARY KEY, name TEXT)")
 
     all_users = requests.get("http://localhost:48065/wechat/allcontacts").json()
     for user in tqdm(all_users):
-        cursor.execute("INSERT OR IGNORE INTO users (id, name) VALUES (?, ?)", (user['arg'], user['title']))
-        usr_chatlog = export_chathistory(user['arg'])
+        cursor.execute(
+            "INSERT OR IGNORE INTO users (id, name) VALUES (?, ?)",
+            (user["arg"], user["title"]),
+        )
+        usr_chatlog = export_chathistory(user["arg"])
         for msg in usr_chatlog:
-            cursor.execute("INSERT INTO chatlog (with_id, from_user, to_user, message, timest, auxiliary) VALUES (?, ?, ?, ?, ?, ?)", (user['arg'], msg['fromUser'], msg['toUser'], msg['message'], msg['createTime'], str(msg['content'])))
+            cursor.execute(
+                "INSERT INTO chatlog (with_id, from_user, to_user, message, timest, auxiliary) VALUES (?, ?, ?, ?, ?, ?)",
+                (
+                    user["arg"],
+                    msg["fromUser"],
+                    msg["toUser"],
+                    msg["message"],
+                    msg["createTime"],
+                    str(msg["content"]),
+                ),
+            )
     connection.commit()
 
 

pyproject.toml

@@ -25,14 +25,21 @@ dependencies = [
     "requests>=2.25.0",
     "sentence-transformers>=2.2.0",
     "openai>=1.0.0",
+    # PDF parsing dependencies - essential for document processing
     "PyPDF2>=3.0.0",
+    "pdfplumber>=0.11.0",
+    "pymupdf>=1.26.0",
+    "pypdfium2>=4.30.0",
+    # LlamaIndex core and readers - updated versions
     "llama-index>=0.12.44",
+    "llama-index-readers-file>=0.4.0",  # Essential for PDF parsing
     "llama-index-readers-docling",
     "llama-index-node-parser-docling",
-    "ipykernel==6.29.5",
-    "msgpack>=1.1.1",
     "llama-index-vector-stores-faiss>=0.4.0",
     "llama-index-embeddings-huggingface>=0.5.5",
+    # Other dependencies
+    "ipykernel==6.29.5",
+    "msgpack>=1.1.1",
     "mlx>=0.26.3; sys_platform == 'darwin'",
     "mlx-lm>=0.26.0; sys_platform == 'darwin'",
     "psutil>=5.8.0",
@@ -46,12 +53,21 @@ dev = [
     "ruff>=0.1.0",
     "matplotlib",
     "huggingface-hub>=0.20.0",
+    "pre-commit>=3.5.0",
 ]
 
 diskann = [
     "leann-backend-diskann",
 ]
 
+# Add a new optional dependency group for document processing
+documents = [
+    "beautifulsoup4>=4.13.0",  # For HTML parsing
+    "python-docx>=0.8.11",     # For Word documents
+    "openpyxl>=3.1.0",         # For Excel files
+    "pandas>=2.2.0",           # For data processing
+]
+
 [tool.setuptools]
 py-modules = []
 
@@ -60,3 +76,50 @@ py-modules = []
 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 }
+
+[tool.ruff]
+target-version = "py310"
+line-length = 100
+extend-exclude = [
+    "third_party",
+    "*.egg-info",
+    "__pycache__",
+    ".git",
+    ".venv",
+]
+
+[tool.ruff.lint]
+select = [
+    "E",      # pycodestyle errors
+    "W",      # pycodestyle warnings
+    "F",      # pyflakes
+    "I",      # isort
+    "B",      # flake8-bugbear
+    "C4",     # flake8-comprehensions
+    "UP",     # pyupgrade
+    "N",      # pep8-naming
+    "RUF",    # ruff-specific rules
+]
+ignore = [
+    "E501",   # line too long (handled by formatter)
+    "B008",   # do not perform function calls in argument defaults
+    "B904",   # raise without from
+    "N812",   # lowercase imported as non-lowercase
+    "N806",   # variable in function should be lowercase
+    "RUF012", # mutable class attributes should be annotated with typing.ClassVar
+]
+
+[tool.ruff.lint.per-file-ignores]
+"test/**/*.py" = ["E402"]      # module level import not at top of file (common in tests)
+"examples/**/*.py" = ["E402"]  # module level import not at top of file (common in examples)
+
+[tool.ruff.format]
+quote-style = "double"
+indent-style = "space"
+skip-magic-trailing-comma = false
+line-ending = "auto"
+
+[dependency-groups]
+dev = [
+    "ruff>=0.12.4",
+]

scripts/build_and_test.sh

@@ -19,16 +19,16 @@ uv pip install build twine delocate auditwheel scikit-build-core cmake pybind11
 build_package() {
     local package_dir=$1
     local package_name=$(basename $package_dir)
-    
+
     echo "Building $package_name..."
     cd $package_dir
-    
+
     # Clean previous builds
     rm -rf dist/ build/ _skbuild/
-    
+
     # Build directly with pip wheel (avoids sdist issues)
     pip wheel . --no-deps -w dist
-    
+
     # Repair wheel for binary packages
     if [[ "$package_name" != "leann-core" ]] && [[ "$package_name" != "leann" ]]; then
         if [[ "$OSTYPE" == "darwin"* ]]; then
@@ -57,7 +57,7 @@ build_package() {
             fi
         fi
     fi
-    
+
     echo "Built wheels in $package_dir/dist/"
     ls -la dist/
     cd - > /dev/null
@@ -84,4 +84,4 @@ else
 fi
 
 echo -e "\nBuild complete! Test with:"
-echo "uv pip install packages/*/dist/*.whl" 
+echo "uv pip install packages/*/dist/*.whl"

scripts/bump_version.sh

@@ -28,4 +28,4 @@ else
 fi
 
 echo "✅ Version updated to $NEW_VERSION"
-echo "✅ Dependencies updated to use leann-core==$NEW_VERSION" 
+echo "✅ Dependencies updated to use leann-core==$NEW_VERSION"

scripts/release.sh

@@ -15,4 +15,4 @@ VERSION=$1
 git add . && git commit -m "chore: bump version to $VERSION" && git push
 
 # Create release (triggers CI)
-gh release create v$VERSION --generate-notes 
+gh release create v$VERSION --generate-notes

scripts/upload_to_pypi.sh

@@ -27,4 +27,4 @@ else
     else
         echo "Cancelled"
     fi
-fi 
+fi

test/build_mlx_index.py

@@ -1,5 +1,6 @@
 import os
-from leann.api import LeannBuilder, LeannSearcher, LeannChat
+
+from leann.api import LeannBuilder, LeannChat
 
 # Define the path for our new MLX-based index
 INDEX_PATH = "./mlx_diskann_index/leann"
@@ -38,7 +39,5 @@ chat = LeannChat(index_path=INDEX_PATH)
 # add query
 query = "MLX is an array framework for machine learning on Apple silicon."
 print(f"Query: {query}")
-response = chat.ask(
-    query, top_k=3, recompute_beighbor_embeddings=True, complexity=3, beam_width=1
-)
+response = chat.ask(query, top_k=3, recompute_beighbor_embeddings=True, complexity=3, beam_width=1)
 print(f"Response: {response}")

test/mail_reader_llamaindex.py

@@ -1,76 +1,84 @@
-import os
 import email
-from pathlib import Path
-from typing import List, Any
-from llama_index.core import VectorStoreIndex, Document
+import os
+from typing import Any
+
+from llama_index.core import Document, VectorStoreIndex
 from llama_index.core.readers.base import BaseReader
 
+
 class EmlxReader(BaseReader):
     """
     Apple Mail .emlx file reader.
-    
+
     Reads individual .emlx files from Apple Mail's storage format.
     """
-    
+
     def __init__(self) -> None:
         """Initialize."""
         pass
-    
-    def load_data(self, input_dir: str, **load_kwargs: Any) -> List[Document]:
+
+    def load_data(self, input_dir: str, **load_kwargs: Any) -> list[Document]:
         """
         Load data from the input directory containing .emlx files.
-        
+
         Args:
             input_dir: Directory containing .emlx files
             **load_kwargs:
                 max_count (int): Maximum amount of messages to read.
         """
-        docs: List[Document] = []
-        max_count = load_kwargs.get('max_count', 1000)
+        docs: list[Document] = []
+        max_count = load_kwargs.get("max_count", 1000)
         count = 0
-        
+
         # Walk through the directory recursively
         for dirpath, dirnames, filenames in os.walk(input_dir):
             # Skip hidden directories
             dirnames[:] = [d for d in dirnames if not d.startswith(".")]
-            
+
             for filename in filenames:
                 if count >= max_count:
                     break
-                    
+
                 if filename.endswith(".emlx"):
                     filepath = os.path.join(dirpath, filename)
                     try:
                         # Read the .emlx file
-                        with open(filepath, 'r', encoding='utf-8', errors='ignore') as f:
+                        with open(filepath, encoding="utf-8", errors="ignore") as f:
                             content = f.read()
-                        
+
                         # .emlx files have a length prefix followed by the email content
                         # The first line contains the length, followed by the email
-                        lines = content.split('\n', 1)
+                        lines = content.split("\n", 1)
                         if len(lines) >= 2:
                             email_content = lines[1]
-                            
+
                             # Parse the email using Python's email module
                             try:
                                 msg = email.message_from_string(email_content)
-                                
+
                                 # Extract email metadata
-                                subject = msg.get('Subject', 'No Subject')
-                                from_addr = msg.get('From', 'Unknown')
-                                to_addr = msg.get('To', 'Unknown')
-                                date = msg.get('Date', 'Unknown')
-                                
+                                subject = msg.get("Subject", "No Subject")
+                                from_addr = msg.get("From", "Unknown")
+                                to_addr = msg.get("To", "Unknown")
+                                date = msg.get("Date", "Unknown")
+
                                 # Extract email body
                                 body = ""
                                 if msg.is_multipart():
                                     for part in msg.walk():
-                                        if part.get_content_type() == "text/plain" or part.get_content_type() == "text/html":
-                                            body += part.get_payload(decode=True).decode('utf-8', errors='ignore')
+                                        if (
+                                            part.get_content_type() == "text/plain"
+                                            or part.get_content_type() == "text/html"
+                                        ):
+                                            body += part.get_payload(decode=True).decode(
+                                                "utf-8", errors="ignore"
+                                            )
                                             # break
                                 else:
-                                    body = msg.get_payload(decode=True).decode('utf-8', errors='ignore')
-                                
+                                    body = msg.get_payload(decode=True).decode(
+                                        "utf-8", errors="ignore"
+                                    )
+
                                 # Create document content
                                 doc_content = f"""
 From: {from_addr}
@@ -80,32 +88,38 @@ Date: {date}
 
 {body}
 """
-                                
+
                                 # Create metadata
                                 metadata = {
-                                    'file_path': filepath,
-                                    'subject': subject,
-                                    'from': from_addr,
-                                    'to': to_addr,
-                                    'date': date,
-                                    'filename': filename
+                                    "file_path": filepath,
+                                    "subject": subject,
+                                    "from": from_addr,
+                                    "to": to_addr,
+                                    "date": date,
+                                    "filename": filename,
                                 }
                                 if count == 0:
                                     print("--------------------------------")
-                                    print('dir path', dirpath)
+                                    print("dir path", dirpath)
                                     print(metadata)
                                     print(doc_content)
                                     print("--------------------------------")
-                                    body=[]
+                                    body = []
                                     if msg.is_multipart():
                                         for part in msg.walk():
-                                            print("--------------------------------  get content type -------------------------------")
+                                            print(
+                                                "--------------------------------  get content type -------------------------------"
+                                            )
                                             print(part.get_content_type())
                                             print(part)
                                             # body.append(part.get_payload(decode=True).decode('utf-8', errors='ignore'))
-                                            print("--------------------------------  get content type -------------------------------")
+                                            print(
+                                                "--------------------------------  get content type -------------------------------"
+                                            )
                                     else:
-                                        body = msg.get_payload(decode=True).decode('utf-8', errors='ignore')
+                                        body = msg.get_payload(decode=True).decode(
+                                            "utf-8", errors="ignore"
+                                        )
                                         print(body)
 
                                     print(body)
@@ -113,22 +127,23 @@ Date: {date}
                                 doc = Document(text=doc_content, metadata=metadata)
                                 docs.append(doc)
                                 count += 1
-                                
+
                             except Exception as e:
                                 print(f"!!!!!!! Error parsing email from {filepath}: {e} !!!!!!!!")
                                 continue
-                                
+
                     except Exception as e:
                         print(f"!!!!!!! Error reading file !!!!!!!! {filepath}: {e}")
                         continue
-        
+
         print(f"Loaded {len(docs)} email documents")
         return docs
 
+
 # Use the custom EmlxReader instead of MboxReader
 documents = EmlxReader().load_data(
-    "/Users/yichuan/Library/Mail/V10/0FCA0879-FD8C-4B7E-83BF-FDDA930791C5/[Gmail].mbox/All Mail.mbox/78BA5BE1-8819-4F9A-9613-EB63772F1DD0/Data/9/Messages", 
-    max_count=1000
+    "/Users/yichuan/Library/Mail/V10/0FCA0879-FD8C-4B7E-83BF-FDDA930791C5/[Gmail].mbox/All Mail.mbox/78BA5BE1-8819-4F9A-9613-EB63772F1DD0/Data/9/Messages",
+    max_count=1000,
 )  # Returns list of documents
 
 # Configure the index with larger chunk size to handle long metadata
@@ -138,10 +153,9 @@ from llama_index.core.node_parser import SentenceSplitter
 text_splitter = SentenceSplitter(chunk_size=2048, chunk_overlap=200)
 
 index = VectorStoreIndex.from_documents(
-    documents,
-    transformations=[text_splitter]
+    documents, transformations=[text_splitter]
 )  # Initialize index with documents
 
 query_engine = index.as_query_engine()
 res = query_engine.query("Hows Berkeley Graduate Student Instructor")
-print(res)
+print(res)

test/mail_reader_save_load.py

@@ -1,77 +1,82 @@
-import os
 import email
-from pathlib import Path
-from typing import List, Any
-from llama_index.core import VectorStoreIndex, Document, StorageContext
-from llama_index.core.readers.base import BaseReader
+import os
+from typing import Any
+
+from llama_index.core import Document, StorageContext, VectorStoreIndex
 from llama_index.core.node_parser import SentenceSplitter
+from llama_index.core.readers.base import BaseReader
+
 
 class EmlxReader(BaseReader):
     """
     Apple Mail .emlx file reader.
-    
+
     Reads individual .emlx files from Apple Mail's storage format.
     """
-    
+
     def __init__(self) -> None:
         """Initialize."""
         pass
-    
-    def load_data(self, input_dir: str, **load_kwargs: Any) -> List[Document]:
+
+    def load_data(self, input_dir: str, **load_kwargs: Any) -> list[Document]:
         """
         Load data from the input directory containing .emlx files.
-        
+
         Args:
             input_dir: Directory containing .emlx files
             **load_kwargs:
                 max_count (int): Maximum amount of messages to read.
         """
-        docs: List[Document] = []
-        max_count = load_kwargs.get('max_count', 1000)
+        docs: list[Document] = []
+        max_count = load_kwargs.get("max_count", 1000)
         count = 0
-        
+
         # Walk through the directory recursively
         for dirpath, dirnames, filenames in os.walk(input_dir):
             # Skip hidden directories
             dirnames[:] = [d for d in dirnames if not d.startswith(".")]
-            
+
             for filename in filenames:
                 if count >= max_count:
                     break
-                    
+
                 if filename.endswith(".emlx"):
                     filepath = os.path.join(dirpath, filename)
                     try:
                         # Read the .emlx file
-                        with open(filepath, 'r', encoding='utf-8', errors='ignore') as f:
+                        with open(filepath, encoding="utf-8", errors="ignore") as f:
                             content = f.read()
-                        
+
                         # .emlx files have a length prefix followed by the email content
                         # The first line contains the length, followed by the email
-                        lines = content.split('\n', 1)
+                        lines = content.split("\n", 1)
                         if len(lines) >= 2:
                             email_content = lines[1]
-                            
+
                             # Parse the email using Python's email module
                             try:
                                 msg = email.message_from_string(email_content)
-                                
+
                                 # Extract email metadata
-                                subject = msg.get('Subject', 'No Subject')
-                                from_addr = msg.get('From', 'Unknown')
-                                to_addr = msg.get('To', 'Unknown')
-                                date = msg.get('Date', 'Unknown')
-                                
+                                subject = msg.get("Subject", "No Subject")
+                                from_addr = msg.get("From", "Unknown")
+                                to_addr = msg.get("To", "Unknown")
+                                date = msg.get("Date", "Unknown")
+
                                 # Extract email body
                                 body = ""
                                 if msg.is_multipart():
                                     for part in msg.walk():
                                         if part.get_content_type() == "text/plain":
-                                            body = part.get_payload(decode=True).decode('utf-8', errors='ignore')
+                                            body = part.get_payload(decode=True).decode(
+                                                "utf-8", errors="ignore"
+                                            )
                                             break
                                 else:
-                                    body = msg.get_payload(decode=True).decode('utf-8', errors='ignore')
-                                
+                                    body = msg.get_payload(decode=True).decode(
+                                        "utf-8", errors="ignore"
+                                    )
+
                                 # Create document content
                                 doc_content = f"""
 From: {from_addr}
@@ -81,97 +86,96 @@ Date: {date}
 
 {body}
 """
-                                
+
                                 # Create metadata
                                 metadata = {
-                                    'file_path': filepath,
-                                    'subject': subject,
-                                    'from': from_addr,
-                                    'to': to_addr,
-                                    'date': date,
-                                    'filename': filename
+                                    "file_path": filepath,
+                                    "subject": subject,
+                                    "from": from_addr,
+                                    "to": to_addr,
+                                    "date": date,
+                                    "filename": filename,
                                 }
-                                
+
                                 doc = Document(text=doc_content, metadata=metadata)
                                 docs.append(doc)
                                 count += 1
-                                
+
                             except Exception as e:
                                 print(f"Error parsing email from {filepath}: {e}")
                                 continue
-                                
+
                     except Exception as e:
                         print(f"Error reading file {filepath}: {e}")
                         continue
-        
+
         print(f"Loaded {len(docs)} email documents")
         return docs
 
+
 def create_and_save_index(mail_path: str, save_dir: str = "mail_index", max_count: int = 1000):
     """
     Create the index from mail data and save it to disk.
-    
+
     Args:
         mail_path: Path to the mail directory
         save_dir: Directory to save the index
         max_count: Maximum number of emails to process
     """
     print("Creating index from mail data...")
-    
+
     # Load documents
     documents = EmlxReader().load_data(mail_path, max_count=max_count)
-    
+
     if not documents:
         print("No documents loaded. Exiting.")
         return None
-    
+
     # Create text splitter
     text_splitter = SentenceSplitter(chunk_size=256, chunk_overlap=0)
-    
+
     # Create index
-    index = VectorStoreIndex.from_documents(
-        documents,
-        transformations=[text_splitter]
-    )
-    
+    index = VectorStoreIndex.from_documents(documents, transformations=[text_splitter])
+
     # Save the index
     os.makedirs(save_dir, exist_ok=True)
     index.storage_context.persist(persist_dir=save_dir)
     print(f"Index saved to {save_dir}")
-    
+
     return index
 
+
 def load_index(save_dir: str = "mail_index"):
     """
     Load the saved index from disk.
-    
+
     Args:
         save_dir: Directory where the index is saved
-    
+
     Returns:
         Loaded index or None if loading fails
     """
     try:
         # Load storage context
         storage_context = StorageContext.from_defaults(persist_dir=save_dir)
-        
+
         # Load index
         index = VectorStoreIndex.from_vector_store(
-            storage_context.vector_store,
-            storage_context=storage_context
+            storage_context.vector_store, storage_context=storage_context
         )
-        
+
         print(f"Index loaded from {save_dir}")
         return index
-    
+
     except Exception as e:
         print(f"Error loading index: {e}")
         return None
 
+
 def query_index(index, query: str):
     """
     Query the loaded index.
-    
+
     Args:
         index: The loaded index
         query: The query string
@@ -179,16 +183,17 @@ def query_index(index, query: str):
     if index is None:
         print("No index available for querying.")
         return
-    
+
     query_engine = index.as_query_engine()
     response = query_engine.query(query)
     print(f"Query: {query}")
     print(f"Response: {response}")
 
+
 def main():
     mail_path = "/Users/yichuan/Library/Mail/V10/0FCA0879-FD8C-4B7E-83BF-FDDA930791C5/[Gmail].mbox/All Mail.mbox/78BA5BE1-8819-4F9A-9613-EB63772F1DD0/Data/9/Messages"
     save_dir = "mail_index"
-    
+
     # Check if index already exists
     if os.path.exists(save_dir) and os.path.exists(os.path.join(save_dir, "vector_store.json")):
         print("Loading existing index...")
@@ -196,18 +201,19 @@ def main():
     else:
         print("Creating new index...")
         index = create_and_save_index(mail_path, save_dir, max_count=1000)
-    
+
     if index:
         # Example queries
         queries = [
             "Hows Berkeley Graduate Student Instructor",
             "What emails mention GSR appointments?",
-            "Find emails about deadlines"
+            "Find emails about deadlines",
         ]
-        
+
         for query in queries:
-            print("\n" + "="*50)
+            print("\n" + "=" * 50)
             query_index(index, query)
 
+
 if __name__ == "__main__":
-    main() 
+    main()

test/mail_reader_small_chunks.py

@@ -1,77 +1,82 @@
-import os
 import email
-from pathlib import Path
-from typing import List, Any
-from llama_index.core import VectorStoreIndex, Document, StorageContext
-from llama_index.core.readers.base import BaseReader
+import os
+from typing import Any
+
+from llama_index.core import Document, StorageContext, VectorStoreIndex
 from llama_index.core.node_parser import SentenceSplitter
+from llama_index.core.readers.base import BaseReader
+
 
 class EmlxReader(BaseReader):
     """
     Apple Mail .emlx file reader with reduced metadata.
-    
+
     Reads individual .emlx files from Apple Mail's storage format.
     """
-    
+
     def __init__(self) -> None:
         """Initialize."""
         pass
-    
-    def load_data(self, input_dir: str, **load_kwargs: Any) -> List[Document]:
+
+    def load_data(self, input_dir: str, **load_kwargs: Any) -> list[Document]:
         """
         Load data from the input directory containing .emlx files.
-        
+
         Args:
             input_dir: Directory containing .emlx files
             **load_kwargs:
                 max_count (int): Maximum amount of messages to read.
         """
-        docs: List[Document] = []
-        max_count = load_kwargs.get('max_count', 1000)
+        docs: list[Document] = []
+        max_count = load_kwargs.get("max_count", 1000)
         count = 0
-        
+
         # Walk through the directory recursively
         for dirpath, dirnames, filenames in os.walk(input_dir):
             # Skip hidden directories
             dirnames[:] = [d for d in dirnames if not d.startswith(".")]
-            
+
             for filename in filenames:
                 if count >= max_count:
                     break
-                    
+
                 if filename.endswith(".emlx"):
                     filepath = os.path.join(dirpath, filename)
                     try:
                         # Read the .emlx file
-                        with open(filepath, 'r', encoding='utf-8', errors='ignore') as f:
+                        with open(filepath, encoding="utf-8", errors="ignore") as f:
                             content = f.read()
-                        
+
                         # .emlx files have a length prefix followed by the email content
                         # The first line contains the length, followed by the email
-                        lines = content.split('\n', 1)
+                        lines = content.split("\n", 1)
                         if len(lines) >= 2:
                             email_content = lines[1]
-                            
+
                             # Parse the email using Python's email module
                             try:
                                 msg = email.message_from_string(email_content)
-                                
+
                                 # Extract email metadata
-                                subject = msg.get('Subject', 'No Subject')
-                                from_addr = msg.get('From', 'Unknown')
-                                to_addr = msg.get('To', 'Unknown')
-                                date = msg.get('Date', 'Unknown')
-                                
+                                subject = msg.get("Subject", "No Subject")
+                                from_addr = msg.get("From", "Unknown")
+                                to_addr = msg.get("To", "Unknown")
+                                date = msg.get("Date", "Unknown")
+
                                 # Extract email body
                                 body = ""
                                 if msg.is_multipart():
                                     for part in msg.walk():
                                         if part.get_content_type() == "text/plain":
-                                            body = part.get_payload(decode=True).decode('utf-8', errors='ignore')
+                                            body = part.get_payload(decode=True).decode(
+                                                "utf-8", errors="ignore"
+                                            )
                                             break
                                 else:
-                                    body = msg.get_payload(decode=True).decode('utf-8', errors='ignore')
-                                
+                                    body = msg.get_payload(decode=True).decode(
+                                        "utf-8", errors="ignore"
+                                    )
+
                                 # Create document content with metadata embedded in text
                                 doc_content = f"""
 From: {from_addr}
@@ -81,95 +86,96 @@ Date: {date}
 
 {body}
 """
-                                
+
                                 # Create minimal metadata (only essential info)
                                 metadata = {
-                                    'subject': subject[:50],  # Truncate subject
-                                    'from': from_addr[:30],   # Truncate from
-                                    'date': date[:20],        # Truncate date
-                                    'filename': filename      # Keep filename
+                                    "subject": subject[:50],  # Truncate subject
+                                    "from": from_addr[:30],  # Truncate from
+                                    "date": date[:20],  # Truncate date
+                                    "filename": filename,  # Keep filename
                                 }
-                                
+
                                 doc = Document(text=doc_content, metadata=metadata)
                                 docs.append(doc)
                                 count += 1
-                                
+
                             except Exception as e:
                                 print(f"Error parsing email from {filepath}: {e}")
                                 continue
-                                
+
                     except Exception as e:
                         print(f"Error reading file {filepath}: {e}")
                         continue
-        
+
         print(f"Loaded {len(docs)} email documents")
         return docs
 
-def create_and_save_index(mail_path: str, save_dir: str = "mail_index_small", max_count: int = 1000):
+
+def create_and_save_index(
+    mail_path: str, save_dir: str = "mail_index_small", max_count: int = 1000
+):
     """
     Create the index from mail data and save it to disk.
-    
+
     Args:
         mail_path: Path to the mail directory
         save_dir: Directory to save the index
         max_count: Maximum number of emails to process
     """
     print("Creating index from mail data with small chunks...")
-    
+
     # Load documents
     documents = EmlxReader().load_data(mail_path, max_count=max_count)
-    
+
     if not documents:
         print("No documents loaded. Exiting.")
         return None
-    
+
     # Create text splitter with small chunk size
     text_splitter = SentenceSplitter(chunk_size=512, chunk_overlap=50)
-    
+
     # Create index
-    index = VectorStoreIndex.from_documents(
-        documents,
-        transformations=[text_splitter]
-    )
-    
+    index = VectorStoreIndex.from_documents(documents, transformations=[text_splitter])
+
     # Save the index
     os.makedirs(save_dir, exist_ok=True)
     index.storage_context.persist(persist_dir=save_dir)
     print(f"Index saved to {save_dir}")
-    
+
     return index
 
+
 def load_index(save_dir: str = "mail_index_small"):
     """
     Load the saved index from disk.
-    
+
     Args:
         save_dir: Directory where the index is saved
-    
+
     Returns:
         Loaded index or None if loading fails
     """
     try:
         # Load storage context
         storage_context = StorageContext.from_defaults(persist_dir=save_dir)
-        
+
         # Load index
         index = VectorStoreIndex.from_vector_store(
-            storage_context.vector_store,
-            storage_context=storage_context
+            storage_context.vector_store, storage_context=storage_context
         )
-        
+
         print(f"Index loaded from {save_dir}")
         return index
-    
+
     except Exception as e:
         print(f"Error loading index: {e}")
         return None
 
+
 def query_index(index, query: str):
     """
     Query the loaded index.
-    
+
     Args:
         index: The loaded index
         query: The query string
@@ -177,16 +183,17 @@ def query_index(index, query: str):
     if index is None:
         print("No index available for querying.")
         return
-    
+
     query_engine = index.as_query_engine()
     response = query_engine.query(query)
     print(f"Query: {query}")
     print(f"Response: {response}")
 
+
 def main():
     mail_path = "/Users/yichuan/Library/Mail/V10/0FCA0879-FD8C-4B7E-83BF-FDDA930791C5/[Gmail].mbox/All Mail.mbox/78BA5BE1-8819-4F9A-9613-EB63772F1DD0/Data/9/Messages"
     save_dir = "mail_index_small"
-    
+
     # Check if index already exists
     if os.path.exists(save_dir) and os.path.exists(os.path.join(save_dir, "vector_store.json")):
         print("Loading existing index...")
@@ -194,18 +201,19 @@ def main():
     else:
         print("Creating new index...")
         index = create_and_save_index(mail_path, save_dir, max_count=1000)
-    
+
     if index:
         # Example queries
         queries = [
             "Hows Berkeley Graduate Student Instructor",
             "What emails mention GSR appointments?",
-            "Find emails about deadlines"
+            "Find emails about deadlines",
         ]
-        
+
         for query in queries:
-            print("\n" + "="*50)
+            print("\n" + "=" * 50)
             query_index(index, query)
 
+
 if __name__ == "__main__":
-    main() 
+    main()

test/mail_reader_test.py

@@ -1,89 +1,94 @@
-import os
 import email
-from pathlib import Path
-from typing import List, Any
-from llama_index.core import VectorStoreIndex, Document
+import os
+from typing import Any
+
+from llama_index.core import Document, VectorStoreIndex
 from llama_index.core.readers.base import BaseReader
 
+
 class EmlxReader(BaseReader):
     """
     Apple Mail .emlx file reader.
-    
+
     Reads individual .emlx files from Apple Mail's storage format.
     """
-    
+
     def __init__(self) -> None:
         """Initialize."""
         pass
-    
-    def load_data(self, input_dir: str, **load_kwargs: Any) -> List[Document]:
+
+    def load_data(self, input_dir: str, **load_kwargs: Any) -> list[Document]:
         """
         Load data from the input directory containing .emlx files.
-        
+
         Args:
             input_dir: Directory containing .emlx files
             **load_kwargs:
                 max_count (int): Maximum amount of messages to read.
         """
-        docs: List[Document] = []
-        max_count = load_kwargs.get('max_count', 1000)
+        docs: list[Document] = []
+        max_count = load_kwargs.get("max_count", 1000)
         count = 0
-        
+
         # Check if directory exists and is accessible
         if not os.path.exists(input_dir):
             print(f"Error: Directory '{input_dir}' does not exist")
             return docs
-        
+
         if not os.access(input_dir, os.R_OK):
             print(f"Error: Directory '{input_dir}' is not accessible (permission denied)")
             print("This is likely due to macOS security restrictions on Mail app data")
             return docs
-        
+
         print(f"Scanning directory: {input_dir}")
-        
+
         # Walk through the directory recursively
         for dirpath, dirnames, filenames in os.walk(input_dir):
             # Skip hidden directories
             dirnames[:] = [d for d in dirnames if not d.startswith(".")]
-            
+
             for filename in filenames:
                 if count >= max_count:
                     break
-                    
+
                 if filename.endswith(".emlx"):
                     filepath = os.path.join(dirpath, filename)
                     print(f"Found .emlx file: {filepath}")
                     try:
                         # Read the .emlx file
-                        with open(filepath, 'r', encoding='utf-8', errors='ignore') as f:
+                        with open(filepath, encoding="utf-8", errors="ignore") as f:
                             content = f.read()
-                        
+
                         # .emlx files have a length prefix followed by the email content
                         # The first line contains the length, followed by the email
-                        lines = content.split('\n', 1)
+                        lines = content.split("\n", 1)
                         if len(lines) >= 2:
                             email_content = lines[1]
-                            
+
                             # Parse the email using Python's email module
                             try:
                                 msg = email.message_from_string(email_content)
-                                
+
                                 # Extract email metadata
-                                subject = msg.get('Subject', 'No Subject')
-                                from_addr = msg.get('From', 'Unknown')
-                                to_addr = msg.get('To', 'Unknown')
-                                date = msg.get('Date', 'Unknown')
-                                
+                                subject = msg.get("Subject", "No Subject")
+                                from_addr = msg.get("From", "Unknown")
+                                to_addr = msg.get("To", "Unknown")
+                                date = msg.get("Date", "Unknown")
+
                                 # Extract email body
                                 body = ""
                                 if msg.is_multipart():
                                     for part in msg.walk():
                                         if part.get_content_type() == "text/plain":
-                                            body = part.get_payload(decode=True).decode('utf-8', errors='ignore')
+                                            body = part.get_payload(decode=True).decode(
+                                                "utf-8", errors="ignore"
+                                            )
                                             break
                                 else:
-                                    body = msg.get_payload(decode=True).decode('utf-8', errors='ignore')
-                                
+                                    body = msg.get_payload(decode=True).decode(
+                                        "utf-8", errors="ignore"
+                                    )
+
                                 # Create document content
                                 doc_content = f"""
 From: {from_addr}
@@ -93,55 +98,57 @@ Date: {date}
 
 {body}
 """
-                                
+
                                 # Create metadata
                                 metadata = {
-                                    'file_path': filepath,
-                                    'subject': subject,
-                                    'from': from_addr,
-                                    'to': to_addr,
-                                    'date': date,
-                                    'filename': filename
+                                    "file_path": filepath,
+                                    "subject": subject,
+                                    "from": from_addr,
+                                    "to": to_addr,
+                                    "date": date,
+                                    "filename": filename,
                                 }
-                                
+
                                 doc = Document(text=doc_content, metadata=metadata)
                                 docs.append(doc)
                                 count += 1
-                                
+
                             except Exception as e:
                                 print(f"Error parsing email from {filepath}: {e}")
                                 continue
-                                
+
                     except Exception as e:
                         print(f"Error reading file {filepath}: {e}")
                         continue
-        
+
         print(f"Loaded {len(docs)} email documents")
         return docs
 
+
 def main():
     # Use the current directory where the sample.emlx file is located
     current_dir = os.path.dirname(os.path.abspath(__file__))
-    
+
     print("Testing EmlxReader with sample .emlx file...")
     print(f"Scanning directory: {current_dir}")
-    
+
     # Use the custom EmlxReader
     documents = EmlxReader().load_data(current_dir, max_count=1000)
-    
+
     if not documents:
         print("No documents loaded. Make sure sample.emlx exists in the examples directory.")
         return
-    
+
     print(f"\nSuccessfully loaded {len(documents)} document(s)")
-    
+
     # Initialize index with documents
     index = VectorStoreIndex.from_documents(documents)
     query_engine = index.as_query_engine()
-    
+
     print("\nTesting query: 'Hows Berkeley Graduate Student Instructor'")
     res = query_engine.query("Hows Berkeley Graduate Student Instructor")
     print(f"Response: {res}")
 
+
 if __name__ == "__main__":
-    main() 
+    main()

test/micro_tpt.py

@@ -2,20 +2,20 @@
 
 import argparse
 import time
+from contextlib import contextmanager
 from dataclasses import dataclass
-from typing import Dict, List, Optional, Tuple
 
 import numpy as np
 import torch
 from torch import nn
-from transformers import AutoModel, BitsAndBytesConfig
 from tqdm import tqdm
-from contextlib import contextmanager
+from transformers import AutoModel, BitsAndBytesConfig
+
 
 @dataclass
 class BenchmarkConfig:
     model_path: str
-    batch_sizes: List[int]
+    batch_sizes: list[int]
     seq_length: int
     num_runs: int
     use_fp16: bool = True
@@ -28,47 +28,45 @@ class BenchmarkConfig:
 
 class GraphContainer:
     """Container for managing graphs for different batch sizes (CUDA graphs on NVIDIA, regular on others)."""
-    
+
     def __init__(self, model: nn.Module, seq_length: int):
         self.model = model
         self.seq_length = seq_length
-        self.graphs: Dict[int, 'GraphWrapper'] = {}
-    
-    def get_or_create(self, batch_size: int) -> 'GraphWrapper':
+        self.graphs: dict[int, GraphWrapper] = {}
+
+    def get_or_create(self, batch_size: int) -> "GraphWrapper":
         if batch_size not in self.graphs:
-            self.graphs[batch_size] = GraphWrapper(
-                self.model, batch_size, self.seq_length
-            )
+            self.graphs[batch_size] = GraphWrapper(self.model, batch_size, self.seq_length)
         return self.graphs[batch_size]
 
 
 class GraphWrapper:
     """Wrapper for graph capture and replay (CUDA graphs on NVIDIA, regular on others)."""
-    
+
     def __init__(self, model: nn.Module, batch_size: int, seq_length: int):
         self.model = model
         self.device = self._get_device()
         self.static_input = self._create_random_batch(batch_size, seq_length)
         self.static_attention_mask = torch.ones_like(self.static_input)
-        
+
         # Warm up
         self._warmup()
-        
+
         # Only use CUDA graphs on NVIDIA GPUs
-        if torch.cuda.is_available() and hasattr(torch.cuda, 'CUDAGraph'):
+        if torch.cuda.is_available() and hasattr(torch.cuda, "CUDAGraph"):
             # Capture graph
             self.graph = torch.cuda.CUDAGraph()
             with torch.cuda.graph(self.graph):
                 self.static_output = self.model(
                     input_ids=self.static_input,
-                    attention_mask=self.static_attention_mask
+                    attention_mask=self.static_attention_mask,
                 )
             self.use_cuda_graph = True
         else:
             # For MPS or CPU, just store the model
             self.use_cuda_graph = False
             self.static_output = None
-    
+
     def _get_device(self) -> str:
         if torch.cuda.is_available():
             return "cuda"
@@ -76,22 +74,20 @@ class GraphWrapper:
             return "mps"
         else:
             return "cpu"
-    
+
     def _create_random_batch(self, batch_size: int, seq_length: int) -> torch.Tensor:
         return torch.randint(
-            0, 1000, (batch_size, seq_length), 
-            device=self.device, 
-            dtype=torch.long
+            0, 1000, (batch_size, seq_length), device=self.device, dtype=torch.long
         )
-    
+
     def _warmup(self, num_warmup: int = 3):
         with torch.no_grad():
             for _ in range(num_warmup):
                 self.model(
                     input_ids=self.static_input,
-                    attention_mask=self.static_attention_mask
+                    attention_mask=self.static_attention_mask,
                 )
-    
+
     def __call__(self, input_ids: torch.Tensor, attention_mask: torch.Tensor) -> torch.Tensor:
         if self.use_cuda_graph:
             self.static_input.copy_(input_ids)
@@ -105,14 +101,14 @@ class GraphWrapper:
 
 class ModelOptimizer:
     """Applies various optimizations to the model."""
-    
+
     @staticmethod
     def optimize(model: nn.Module, config: BenchmarkConfig) -> nn.Module:
         print("\nApplying model optimizations:")
-        
+
         if model is None:
             raise ValueError("Cannot optimize None model")
-        
+
         # Move to GPU
         if torch.cuda.is_available():
             model = model.cuda()
@@ -124,53 +120,59 @@ class ModelOptimizer:
             model = model.cpu()
             device = "cpu"
         print(f"- Model moved to {device}")
-        
+
         # FP16
         if config.use_fp16 and not config.use_int4:
             model = model.half()
             # use torch compile
             model = torch.compile(model)
             print("- Using FP16 precision")
-        
+
         # Check if using SDPA (only on CUDA)
-        if torch.cuda.is_available() and torch.version.cuda and float(torch.version.cuda[:3]) >= 11.6:
-            if hasattr(torch.nn.functional, 'scaled_dot_product_attention'):
+        if (
+            torch.cuda.is_available()
+            and torch.version.cuda
+            and float(torch.version.cuda[:3]) >= 11.6
+        ):
+            if hasattr(torch.nn.functional, "scaled_dot_product_attention"):
                 print("- Using PyTorch SDPA (scaled_dot_product_attention)")
             else:
                 print("- PyTorch SDPA not available")
-        
+
         # Flash Attention (only on CUDA)
         if config.use_flash_attention and torch.cuda.is_available():
             try:
-                from flash_attn.flash_attention import FlashAttention
+                from flash_attn.flash_attention import FlashAttention  # noqa: F401
+
                 print("- Flash Attention 2 available")
                 if hasattr(model.config, "attention_mode"):
                     model.config.attention_mode = "flash_attention_2"
                     print("  - Enabled Flash Attention 2 mode")
             except ImportError:
                 print("- Flash Attention not available")
-        
+
         # Memory efficient attention (only on CUDA)
         if torch.cuda.is_available():
             try:
-                from xformers.ops import memory_efficient_attention
-                if hasattr(model, 'enable_xformers_memory_efficient_attention'):
+                from xformers.ops import memory_efficient_attention  # noqa: F401
+
+                if hasattr(model, "enable_xformers_memory_efficient_attention"):
                     model.enable_xformers_memory_efficient_attention()
                     print("- Enabled xformers memory efficient attention")
                 else:
                     print("- Model doesn't support xformers")
             except (ImportError, AttributeError):
                 print("- Xformers not available")
-        
+
         model.eval()
         print("- Model set to eval mode")
-        
+
         return model
 
 
 class Timer:
     """Handles accurate GPU timing using GPU events or CPU timing."""
-    
+
     def __init__(self):
         if torch.cuda.is_available():
             self.start_event = torch.cuda.Event(enable_timing=True)
@@ -182,7 +184,7 @@ class Timer:
         else:
             # CPU timing
             self.use_gpu_timing = False
-    
+
     @contextmanager
     def timing(self):
         if self.use_gpu_timing:
@@ -195,7 +197,7 @@ class Timer:
             start_time = time.time()
             yield
             self.cpu_elapsed = time.time() - start_time
-    
+
     def elapsed_time(self) -> float:
         if self.use_gpu_timing:
             return self.start_event.elapsed_time(self.end_event) / 1000  # ms to seconds
@@ -205,14 +207,14 @@ class Timer:
 
 class Benchmark:
     """Main benchmark runner."""
-    
+
     def __init__(self, config: BenchmarkConfig):
         self.config = config
         try:
             self.model = self._load_model()
             if self.model is None:
                 raise ValueError("Model initialization failed - model is None")
-            
+
             # Only use CUDA graphs on NVIDIA GPUs
             if config.use_cuda_graphs and torch.cuda.is_available():
                 self.graphs = GraphContainer(self.model, config.seq_length)
@@ -220,25 +222,27 @@ class Benchmark:
                 self.graphs = None
             self.timer = Timer()
         except Exception as e:
-            print(f"ERROR in benchmark initialization: {str(e)}")
+            print(f"ERROR in benchmark initialization: {e!s}")
             raise
-    
+
     def _load_model(self) -> nn.Module:
         print(f"Loading model from {self.config.model_path}...")
-        
+
         try:
             # Int4 quantization using HuggingFace integration
             if self.config.use_int4:
                 import bitsandbytes as bnb
+
                 print(f"- bitsandbytes version: {bnb.__version__}")
-                
-                # 检查是否使用自定义的8bit量化
-                if hasattr(self.config, 'use_linear8bitlt') and self.config.use_linear8bitlt:
+
+                # Check if using custom 8bit quantization
+                if hasattr(self.config, "use_linear8bitlt") and self.config.use_linear8bitlt:
                     print("- Using custom Linear8bitLt replacement for all linear layers")
-                    
-                    # 加载原始模型（不使用量化配置）
+
+                    # Load original model (without quantization config)
                     import bitsandbytes as bnb
                     import torch
+
                     # set default to half
                     torch.set_default_dtype(torch.float16)
                     compute_dtype = torch.float16 if self.config.use_fp16 else torch.float32
@@ -246,112 +250,121 @@ class Benchmark:
                         self.config.model_path,
                         torch_dtype=compute_dtype,
                     )
-                    
-                    # 定义替换函数
+
+                    # Define replacement function
                     def replace_linear_with_linear8bitlt(model):
-                        """递归地将模型中的所有nn.Linear层替换为Linear8bitLt"""
+                        """Recursively replace all nn.Linear layers with Linear8bitLt"""
                         for name, module in list(model.named_children()):
                             if isinstance(module, nn.Linear):
-                                # 获取原始线性层的参数
+                                # Get original linear layer parameters
                                 in_features = module.in_features
                                 out_features = module.out_features
                                 bias = module.bias is not None
-                                
-                                # 创建8bit线性层
+
+                                # Create 8bit linear layer
                                 # print size
                                 print(f"in_features: {in_features}, out_features: {out_features}")
                                 new_module = bnb.nn.Linear8bitLt(
-                                    in_features, 
-                                    out_features, 
-                                    bias=bias, 
-                                    has_fp16_weights=False
+                                    in_features,
+                                    out_features,
+                                    bias=bias,
+                                    has_fp16_weights=False,
                                 )
-                                
-                                # 复制权重和偏置
+
+                                # Copy weights and bias
                                 new_module.weight.data = module.weight.data
                                 if bias:
                                     new_module.bias.data = module.bias.data
-                                    
-                                # 替换模块
+
+                                # Replace module
                                 setattr(model, name, new_module)
                             else:
-                                # 递归处理子模块
+                                # Process child modules recursively
                                 replace_linear_with_linear8bitlt(module)
-                        
+
                         return model
-                    
-                    # 替换所有线性层
+
+                    # Replace all linear layers
                     model = replace_linear_with_linear8bitlt(model)
                     # add torch compile
                     model = torch.compile(model)
-                    
-                    # 将模型移到GPU（量化发生在这里）
-                    device = "cuda" if torch.cuda.is_available() else "mps" if torch.backends.mps.is_available() else "cpu"
+
+                    # Move model to GPU (quantization happens here)
+                    device = (
+                        "cuda"
+                        if torch.cuda.is_available()
+                        else "mps"
+                        if torch.backends.mps.is_available()
+                        else "cpu"
+                    )
                     model = model.to(device)
-                    
+
                     print("- All linear layers replaced with Linear8bitLt")
-                    
+
                 else:
-                    # 使用原来的Int4量化方法
+                    # Use original Int4 quantization method
                     print("- Using bitsandbytes for Int4 quantization")
-                    
+
                     # Create quantization config
-                    
+
                     compute_dtype = torch.float16 if self.config.use_fp16 else torch.float32
                     quantization_config = BitsAndBytesConfig(
                         load_in_4bit=True,
                         bnb_4bit_compute_dtype=compute_dtype,
                         bnb_4bit_use_double_quant=True,
-                        bnb_4bit_quant_type="nf4"
+                        bnb_4bit_quant_type="nf4",
                     )
-                    
+
                     print("- Quantization config:", quantization_config)
-                    
+
                     # Load model directly with quantization config
                     model = AutoModel.from_pretrained(
                         self.config.model_path,
                         quantization_config=quantization_config,
                         torch_dtype=compute_dtype,
-                        device_map="auto"  # Let HF decide on device mapping
+                        device_map="auto",  # Let HF decide on device mapping
                     )
-                
+
                 # Check if model loaded successfully
                 if model is None:
                     raise ValueError("Model loading returned None")
-                    
+
                 print(f"- Model type: {type(model)}")
-                
+
                 # Apply optimizations directly here
                 print("\nApplying model optimizations:")
-                
-                if hasattr(self.config, 'use_linear8bitlt') and self.config.use_linear8bitlt:
+
+                if hasattr(self.config, "use_linear8bitlt") and self.config.use_linear8bitlt:
                     print("- Model moved to GPU with Linear8bitLt quantization")
                 else:
                     # Skip moving to GPU since device_map="auto" already did that
                     print("- Model already on GPU due to device_map='auto'")
-                
+
                 # Skip FP16 conversion since we specified compute_dtype
                 print(f"- Using {compute_dtype} for compute dtype")
-                
+
                 # Check CUDA and SDPA
-                if torch.cuda.is_available() and torch.version.cuda and float(torch.version.cuda[:3]) >= 11.6:
-                    if hasattr(torch.nn.functional, 'scaled_dot_product_attention'):
+                if (
+                    torch.cuda.is_available()
+                    and torch.version.cuda
+                    and float(torch.version.cuda[:3]) >= 11.6
+                ):
+                    if hasattr(torch.nn.functional, "scaled_dot_product_attention"):
                         print("- Using PyTorch SDPA (scaled_dot_product_attention)")
                     else:
                         print("- PyTorch SDPA not available")
-                
+
                 # Try xformers if available (only on CUDA)
                 if torch.cuda.is_available():
                     try:
-                        from xformers.ops import memory_efficient_attention
-                        if hasattr(model, 'enable_xformers_memory_efficient_attention'):
+                        if hasattr(model, "enable_xformers_memory_efficient_attention"):
                             model.enable_xformers_memory_efficient_attention()
                             print("- Enabled xformers memory efficient attention")
                         else:
                             print("- Model doesn't support xformers")
                     except (ImportError, AttributeError):
                         print("- Xformers not available")
-                
+
                 # Set to eval mode
                 model.eval()
                 print("- Model set to eval mode")
@@ -365,76 +378,83 @@ class Benchmark:
                     llm_int8_threshold=6.0,
                     llm_int8_has_fp16_weight=False,
                 )
-                
+
                 model = AutoModel.from_pretrained(
                     self.config.model_path,
                     quantization_config=quantization_config,
                     torch_dtype=compute_dtype,
-                    device_map="auto"
+                    device_map="auto",
                 )
-                
+
                 if model is None:
                     raise ValueError("Model loading returned None")
-                    
+
                 print(f"- Model type: {type(model)}")
                 model.eval()
                 print("- Model set to eval mode")
-                
+
             else:
                 # Standard loading for FP16/FP32
                 model = AutoModel.from_pretrained(self.config.model_path)
                 print("- Model loaded in standard precision")
                 print(f"- Model type: {type(model)}")
-                
+
                 # Apply standard optimizations
                 # set default to half
                 import torch
+
                 torch.set_default_dtype(torch.bfloat16)
                 model = ModelOptimizer.optimize(model, self.config)
                 model = model.half()
                 # add torch compile
                 model = torch.compile(model)
-            
+
             # Final check to ensure model is not None
             if model is None:
                 raise ValueError("Model is None after optimization")
-                
+
             print(f"- Final model type: {type(model)}")
             return model
-        
+
         except Exception as e:
-            print(f"ERROR loading model: {str(e)}")
+            print(f"ERROR loading model: {e!s}")
             import traceback
+
             traceback.print_exc()
             raise
-    
+
     def _create_random_batch(self, batch_size: int) -> torch.Tensor:
-        device = "cuda" if torch.cuda.is_available() else "mps" if torch.backends.mps.is_available() else "cpu"
+        device = (
+            "cuda"
+            if torch.cuda.is_available()
+            else "mps"
+            if torch.backends.mps.is_available()
+            else "cpu"
+        )
         return torch.randint(
-            0, 1000,
+            0,
+            1000,
             (batch_size, self.config.seq_length),
             device=device,
-            dtype=torch.long
+            dtype=torch.long,
         )
-    
+
     def _run_inference(
-        self,
-        input_ids: torch.Tensor,
-        graph_wrapper: Optional[GraphWrapper] = None
-    ) -> Tuple[float, torch.Tensor]:
+        self, input_ids: torch.Tensor, graph_wrapper: GraphWrapper | None = None
+    ) -> tuple[float, torch.Tensor]:
         attention_mask = torch.ones_like(input_ids)
-        
+
         with torch.no_grad(), self.timer.timing():
             if graph_wrapper is not None:
                 output = graph_wrapper(input_ids, attention_mask)
             else:
                 output = self.model(input_ids=input_ids, attention_mask=attention_mask)
-        
+
         return self.timer.elapsed_time(), output
-    
-    def run(self) -> Dict[int, Dict[str, float]]:
+
+    def run(self) -> dict[int, dict[str, float]]:
         results = {}
-        
+
         # Reset peak memory stats
         if torch.cuda.is_available():
             torch.cuda.reset_peak_memory_stats()
@@ -443,22 +463,20 @@ class Benchmark:
             pass
         else:
             print("- No GPU memory stats available")
-        
+
         for batch_size in self.config.batch_sizes:
             print(f"\nTesting batch size: {batch_size}")
             times = []
-            
+
             # Get or create graph for this batch size
             graph_wrapper = (
-                self.graphs.get_or_create(batch_size)
-                if self.graphs is not None
-                else None
+                self.graphs.get_or_create(batch_size) if self.graphs is not None else None
             )
-            
+
             # Pre-allocate input tensor
             input_ids = self._create_random_batch(batch_size)
             print(f"Input shape: {input_ids.shape}")
-            
+
             # Run benchmark
             for i in tqdm(range(self.config.num_runs), desc=f"Batch size {batch_size}"):
                 try:
@@ -469,44 +487,44 @@ class Benchmark:
                 except Exception as e:
                     print(f"Error during inference: {e}")
                     break
-            
+
             if not times:
                 print(f"No successful runs for batch size {batch_size}, skipping")
                 continue
-                
+
             # Calculate statistics
             avg_time = np.mean(times)
             std_time = np.std(times)
             throughput = batch_size / avg_time
-            
+
             results[batch_size] = {
                 "avg_time": avg_time,
                 "std_time": std_time,
                 "throughput": throughput,
             }
-            
+
             print(f"Avg Time: {avg_time:.4f}s ± {std_time:.4f}s")
             print(f"Throughput: {throughput:.2f} sequences/second")
-        
+
         # Log memory usage
         if torch.cuda.is_available():
-            peak_memory_gb = torch.cuda.max_memory_allocated() / (1024 ** 3)
+            peak_memory_gb = torch.cuda.max_memory_allocated() / (1024**3)
         elif torch.backends.mps.is_available():
             # MPS doesn't have max_memory_allocated, use 0
             peak_memory_gb = 0.0
         else:
             peak_memory_gb = 0.0
             print("- No GPU memory usage available")
-        
+
         if peak_memory_gb > 0:
             print(f"\nPeak GPU memory usage: {peak_memory_gb:.2f} GB")
         else:
             print("\n- GPU memory usage not available")
-        
+
         # Add memory info to results
         for batch_size in results:
             results[batch_size]["peak_memory_gb"] = peak_memory_gb
-        
+
         return results
 
 
@@ -566,14 +584,14 @@ def main():
         action="store_true",
         help="Enable Linear8bitLt quantization for all linear layers",
     )
-    
+
     args = parser.parse_args()
-    
+
     # Print arguments for debugging
     print("\nCommand line arguments:")
     for arg, value in vars(args).items():
         print(f"- {arg}: {value}")
-    
+
     config = BenchmarkConfig(
         model_path=args.model_path,
         batch_sizes=[int(bs) for bs in args.batch_sizes.split(",")],
@@ -586,45 +604,56 @@ def main():
         use_flash_attention=args.use_flash_attention,
         use_linear8bitlt=args.use_linear8bitlt,
     )
-        
+
     # Print configuration for debugging
     print("\nBenchmark configuration:")
     for field, value in vars(config).items():
         print(f"- {field}: {value}")
-    
+
     try:
         benchmark = Benchmark(config)
         results = benchmark.run()
-        
+
         # Save results to file
         import json
         import os
-        
+
         # Create results directory if it doesn't exist
         os.makedirs("results", exist_ok=True)
-        
+
         # Generate filename based on configuration
-        precision_type = "int4" if config.use_int4 else "int8" if config.use_int8 else "fp16" if config.use_fp16 else "fp32"
+        precision_type = (
+            "int4"
+            if config.use_int4
+            else "int8"
+            if config.use_int8
+            else "fp16"
+            if config.use_fp16
+            else "fp32"
+        )
         model_name = os.path.basename(config.model_path)
         output_file = f"results/benchmark_{model_name}_{precision_type}.json"
-        
+
         # Save results
         with open(output_file, "w") as f:
             json.dump(
                 {
-                    "config": {k: str(v) if isinstance(v, list) else v for k, v in vars(config).items()},
-                    "results": {str(k): v for k, v in results.items()}
-                }, 
-                f, 
-                indent=2
+                    "config": {
+                        k: str(v) if isinstance(v, list) else v for k, v in vars(config).items()
+                    },
+                    "results": {str(k): v for k, v in results.items()},
+                },
+                f,
+                indent=2,
             )
         print(f"Results saved to {output_file}")
-        
+
     except Exception as e:
         print(f"Benchmark failed: {e}")
         import traceback
+
         traceback.print_exc()
 
 
 if __name__ == "__main__":
-    main()
+    main()

test/query_saved_index.py

@@ -1,37 +1,39 @@
 import os
-from llama_index.core import VectorStoreIndex, StorageContext
+
+from llama_index.core import StorageContext, VectorStoreIndex
+
 
 def load_index(save_dir: str = "mail_index"):
     """
     Load the saved index from disk.
-    
+
     Args:
         save_dir: Directory where the index is saved
-    
+
     Returns:
         Loaded index or None if loading fails
     """
     try:
         # Load storage context
         storage_context = StorageContext.from_defaults(persist_dir=save_dir)
-        
+
         # Load index
         index = VectorStoreIndex.from_vector_store(
-            storage_context.vector_store,
-            storage_context=storage_context
+            storage_context.vector_store, storage_context=storage_context
         )
-        
+
         print(f"Index loaded from {save_dir}")
         return index
-    
+
     except Exception as e:
         print(f"Error loading index: {e}")
         return None
 
+
 def query_index(index, query: str):
     """
     Query the loaded index.
-    
+
     Args:
         index: The loaded index
         query: The query string
@@ -39,44 +41,47 @@ def query_index(index, query: str):
     if index is None:
         print("No index available for querying.")
         return
-    
+
     query_engine = index.as_query_engine()
     response = query_engine.query(query)
     print(f"\nQuery: {query}")
     print(f"Response: {response}")
 
+
 def main():
     save_dir = "mail_index"
-    
+
     # Check if index exists
-    if not os.path.exists(save_dir) or not os.path.exists(os.path.join(save_dir, "vector_store.json")):
+    if not os.path.exists(save_dir) or not os.path.exists(
+        os.path.join(save_dir, "vector_store.json")
+    ):
         print(f"Index not found in {save_dir}")
         print("Please run mail_reader_save_load.py first to create the index.")
         return
-    
+
     # Load the index
     index = load_index(save_dir)
-    
+
     if not index:
         print("Failed to load index.")
         return
-    
-    print("\n" + "="*60)
+
+    print("\n" + "=" * 60)
     print("Email Query Interface")
-    print("="*60)
+    print("=" * 60)
     print("Type 'quit' to exit")
     print("Type 'help' for example queries")
-    print("="*60)
-    
+    print("=" * 60)
+
     # Interactive query loop
     while True:
         try:
             query = input("\nEnter your query: ").strip()
-            
-            if query.lower() == 'quit':
+
+            if query.lower() == "quit":
                 print("Goodbye!")
                 break
-            elif query.lower() == 'help':
+            elif query.lower() == "help":
                 print("\nExample queries:")
                 print("- Hows Berkeley Graduate Student Instructor")
                 print("- What emails mention GSR appointments?")
@@ -86,14 +91,15 @@ def main():
                 continue
             elif not query:
                 continue
-            
+
             query_index(index, query)
-            
+
         except KeyboardInterrupt:
             print("\nGoodbye!")
             break
         except Exception as e:
             print(f"Error processing query: {e}")
 
+
 if __name__ == "__main__":
-    main() 
+    main()

test/sanity_checks/README.md

@@ -7,7 +7,7 @@ This directory contains comprehensive sanity checks for the Leann system, ensuri
 ### `test_distance_functions.py`
 Tests all supported distance functions across DiskANN backend:
 - ✅ **MIPS** (Maximum Inner Product Search)
-- ✅ **L2** (Euclidean Distance) 
+- ✅ **L2** (Euclidean Distance)
 - ✅ **Cosine** (Cosine Similarity)
 
 ```bash
@@ -27,7 +27,7 @@ uv run python tests/sanity_checks/test_l2_verification.py
 ### `test_sanity_check.py`
 Comprehensive end-to-end verification including:
 - Distance function testing
-- Embedding model compatibility  
+- Embedding model compatibility
 - Search result correctness validation
 - Backend integration testing
 
@@ -64,7 +64,7 @@ When all tests pass, you should see:
 ```
 📊 测试结果总结:
   mips      : ✅ 通过
-  l2        : ✅ 通过  
+  l2        : ✅ 通过
   cosine    : ✅ 通过
 
 🎉 测试完成!
@@ -98,7 +98,7 @@ pkill -f "embedding_server"
 
 ### Typical Timing (3 documents, consumer hardware):
 - **Index Building**: 2-5 seconds per distance function
-- **Search Query**: 50-200ms 
+- **Search Query**: 50-200ms
 - **Recompute Mode**: 5-15 seconds (higher accuracy)
 
 ### Memory Usage:
@@ -117,4 +117,4 @@ These tests are designed to be run in automated environments:
     uv run python tests/sanity_checks/test_l2_verification.py
 ```
 
-The tests are deterministic and should produce consistent results across different platforms.
+The tests are deterministic and should produce consistent results across different platforms.

test/sanity_checks/benchmark_embeddings.py

@@ -1,43 +1,46 @@
 import time
-import numpy as np
+
 import matplotlib.pyplot as plt
-import torch
-from sentence_transformers import SentenceTransformer
 import mlx.core as mx
+import numpy as np
+import torch
 from mlx_lm import load
+from sentence_transformers import SentenceTransformer
 
 # --- Configuration ---
 MODEL_NAME_TORCH = "Qwen/Qwen3-Embedding-0.6B"
 MODEL_NAME_MLX = "mlx-community/Qwen3-Embedding-0.6B-4bit-DWQ"
 BATCH_SIZES = [1, 8, 16, 32, 64, 128]
 NUM_RUNS = 10  # Number of runs to average for each batch size
-WARMUP_RUNS = 2 # Number of warm-up runs
+WARMUP_RUNS = 2  # Number of warm-up runs
 
 # --- Generate Dummy Data ---
 DUMMY_SENTENCES = ["This is a test sentence for benchmarking." * 5] * max(BATCH_SIZES)
 
 # --- Benchmark Functions ---b
 
+
 def benchmark_torch(model, sentences):
     start_time = time.time()
     model.encode(sentences, convert_to_numpy=True)
     end_time = time.time()
     return (end_time - start_time) * 1000  # Return time in ms
 
+
 def benchmark_mlx(model, tokenizer, sentences):
     start_time = time.time()
-    
+
     # Tokenize sentences using MLX tokenizer
     tokens = []
     for sentence in sentences:
         token_ids = tokenizer.encode(sentence)
         tokens.append(token_ids)
-    
+
     # Pad sequences to the same length
     max_len = max(len(t) for t in tokens)
     input_ids = []
     attention_mask = []
-    
+
     for token_seq in tokens:
         # Pad sequence
         padded = token_seq + [tokenizer.eos_token_id] * (max_len - len(token_seq))
@@ -45,24 +48,25 @@ def benchmark_mlx(model, tokenizer, sentences):
         # Create attention mask (1 for real tokens, 0 for padding)
         mask = [1] * len(token_seq) + [0] * (max_len - len(token_seq))
         attention_mask.append(mask)
-    
+
     # Convert to MLX arrays
     input_ids = mx.array(input_ids)
     attention_mask = mx.array(attention_mask)
-    
+
     # Get embeddings
     embeddings = model(input_ids)
-    
+
     # Mean pooling
     mask = mx.expand_dims(attention_mask, -1)
     sum_embeddings = (embeddings * mask).sum(axis=1)
     sum_mask = mask.sum(axis=1)
     _ = sum_embeddings / sum_mask
-    
+
     mx.eval()  # Ensure computation is finished
     end_time = time.time()
     return (end_time - start_time) * 1000  # Return time in ms
 
+
 # --- Main Execution ---
 def main():
     print("--- Initializing Models ---")
@@ -92,13 +96,15 @@ def main():
     for batch_size in BATCH_SIZES:
         print(f"Benchmarking batch size: {batch_size}")
         sentences_batch = DUMMY_SENTENCES[:batch_size]
-        
+
         # Benchmark PyTorch
         torch_times = [benchmark_torch(model_torch, sentences_batch) for _ in range(NUM_RUNS)]
         results_torch.append(np.mean(torch_times))
-        
+
         # Benchmark MLX
-        mlx_times = [benchmark_mlx(model_mlx, tokenizer_mlx, sentences_batch) for _ in range(NUM_RUNS)]
+        mlx_times = [
+            benchmark_mlx(model_mlx, tokenizer_mlx, sentences_batch) for _ in range(NUM_RUNS)
+        ]
         results_mlx.append(np.mean(mlx_times))
 
     print("\n--- Benchmark Results (Average time per batch in ms) ---")
@@ -109,20 +115,27 @@ def main():
     # --- Plotting ---
     print("\n--- Generating Plot ---")
     plt.figure(figsize=(10, 6))
-    plt.plot(BATCH_SIZES, results_torch, marker='o', linestyle='-', label=f'PyTorch ({device})')
-    plt.plot(BATCH_SIZES, results_mlx, marker='s', linestyle='-', label='MLX')
+    plt.plot(
+        BATCH_SIZES,
+        results_torch,
+        marker="o",
+        linestyle="-",
+        label=f"PyTorch ({device})",
+    )
+    plt.plot(BATCH_SIZES, results_mlx, marker="s", linestyle="-", label="MLX")
 
-    plt.title(f'Embedding Performance: MLX vs PyTorch\nModel: {MODEL_NAME_TORCH}')
+    plt.title(f"Embedding Performance: MLX vs PyTorch\nModel: {MODEL_NAME_TORCH}")
     plt.xlabel("Batch Size")
     plt.ylabel("Average Time per Batch (ms)")
     plt.xticks(BATCH_SIZES)
     plt.grid(True)
     plt.legend()
-    
+
     # Save the plot
     output_filename = "embedding_benchmark.png"
     plt.savefig(output_filename)
     print(f"Plot saved to {output_filename}")
 
+
 if __name__ == "__main__":
     main()

test/sanity_checks/debug_zmq_issue.py

@@ -3,49 +3,52 @@
 Debug script to test ZMQ communication with the exact same setup as main_cli_example.py
 """
 
-import zmq
-import time
-import threading
 import sys
-sys.path.append('packages/leann-backend-diskann')
+import time
+
+import zmq
+
+sys.path.append("packages/leann-backend-diskann")
 from leann_backend_diskann import embedding_pb2
 
+
 def test_zmq_with_same_model():
     print("=== Testing ZMQ with same model as main_cli_example.py ===")
-    
+
     # Test the exact same model that main_cli_example.py uses
     model_name = "sentence-transformers/all-mpnet-base-v2"
-    
+
     # Start server with the same model
     import subprocess
+
     server_cmd = [
-        sys.executable, "-m", 
+        sys.executable,
+        "-m",
         "packages.leann-backend-diskann.leann_backend_diskann.embedding_server",
-        "--zmq-port", "5556",  # Use different port to avoid conflicts
-        "--model-name", model_name
+        "--zmq-port",
+        "5556",  # Use different port to avoid conflicts
+        "--model-name",
+        model_name,
     ]
-    
+
     print(f"Starting server with command: {' '.join(server_cmd)}")
     server_process = subprocess.Popen(
-        server_cmd,
-        stdout=subprocess.PIPE,
-        stderr=subprocess.PIPE,
-        text=True
+        server_cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE, text=True
     )
-    
+
     # Wait for server to start
     print("Waiting for server to start...")
     time.sleep(10)
-    
+
     # Check if server is running
     if server_process.poll() is not None:
         stdout, stderr = server_process.communicate()
         print(f"Server failed to start. stdout: {stdout}")
         print(f"Server failed to start. stderr: {stderr}")
         return False
-    
+
     print(f"Server started with PID: {server_process.pid}")
-    
+
     try:
         # Test client
         context = zmq.Context()
@@ -53,39 +56,39 @@ def test_zmq_with_same_model():
         socket.connect("tcp://127.0.0.1:5556")
         socket.setsockopt(zmq.RCVTIMEO, 30000)  # 30 second timeout like C++
         socket.setsockopt(zmq.SNDTIMEO, 30000)
-        
+
         # Create request with same format as C++
         request = embedding_pb2.NodeEmbeddingRequest()
         request.node_ids.extend([0, 1, 2, 3, 4])  # Test with some node IDs
-        
+
         print(f"Sending request with {len(request.node_ids)} node IDs...")
         start_time = time.time()
-        
+
         # Send request
         socket.send(request.SerializeToString())
-        
+
         # Receive response
         response_data = socket.recv()
         end_time = time.time()
-        
+
         print(f"Received response in {end_time - start_time:.3f} seconds")
         print(f"Response size: {len(response_data)} bytes")
-        
+
         # Parse response
         response = embedding_pb2.NodeEmbeddingResponse()
         response.ParseFromString(response_data)
-        
+
         print(f"Response dimensions: {list(response.dimensions)}")
         print(f"Embeddings data size: {len(response.embeddings_data)} bytes")
         print(f"Missing IDs: {list(response.missing_ids)}")
-        
+
         # Calculate expected size
         if len(response.dimensions) == 2:
             batch_size = response.dimensions[0]
             embedding_dim = response.dimensions[1]
             expected_bytes = batch_size * embedding_dim * 4  # 4 bytes per float
             print(f"Expected bytes: {expected_bytes}, Actual: {len(response.embeddings_data)}")
-            
+
             if len(response.embeddings_data) == expected_bytes:
                 print("✅ Response format is correct!")
                 return True
@@ -95,7 +98,7 @@ def test_zmq_with_same_model():
         else:
             print("❌ Invalid response dimensions!")
             return False
-            
+
     except Exception as e:
         print(f"❌ Error during ZMQ test: {e}")
         return False
@@ -105,9 +108,10 @@ def test_zmq_with_same_model():
         server_process.wait()
         print("Server terminated")
 
+
 if __name__ == "__main__":
     success = test_zmq_with_same_model()
     if success:
         print("\n✅ ZMQ communication test passed!")
     else:
-        print("\n❌ ZMQ communication test failed!") 
+        print("\n❌ ZMQ communication test failed!")

test/simple_mac_tpt_test.py

@@ -1,26 +1,27 @@
 import time
 from dataclasses import dataclass
-from typing import Dict, List
 
 import numpy as np
 import torch
 from torch import nn
-from transformers import AutoModel, BitsAndBytesConfig
 from tqdm import tqdm
+from transformers import AutoModel
 
 # Add MLX imports
 try:
     import mlx.core as mx
     from mlx_lm.utils import load
+
     MLX_AVAILABLE = True
-except ImportError as e:
+except ImportError:
     print("MLX not available. Install with: uv pip install mlx mlx-lm")
     MLX_AVAILABLE = False
 
+
 @dataclass
 class BenchmarkConfig:
     model_path: str = "facebook/contriever"
-    batch_sizes: List[int] = None
+    batch_sizes: list[int] = None
     seq_length: int = 256
     num_runs: int = 5
     use_fp16: bool = True
@@ -30,18 +31,19 @@ class BenchmarkConfig:
     use_flash_attention: bool = False
     use_linear8bitlt: bool = False
     use_mlx: bool = False  # New flag for MLX testing
-    
+
     def __post_init__(self):
         if self.batch_sizes is None:
             self.batch_sizes = [1, 2, 4, 8, 16, 32, 64]
 
+
 class MLXBenchmark:
     """MLX-specific benchmark for embedding models"""
-    
+
     def __init__(self, config: BenchmarkConfig):
         self.config = config
         self.model, self.tokenizer = self._load_model()
-    
+
     def _load_model(self):
         """Load MLX model and tokenizer following the API pattern"""
         print(f"Loading MLX model from {self.config.model_path}...")
@@ -52,55 +54,51 @@ class MLXBenchmark:
         except Exception as e:
             print(f"Error loading MLX model: {e}")
             raise
-    
+
     def _create_random_batch(self, batch_size: int):
         """Create random input batches for MLX testing - same as PyTorch"""
-        return torch.randint(
-            0, 1000,
-            (batch_size, self.config.seq_length),
-            dtype=torch.long
-        )
-    
+        return torch.randint(0, 1000, (batch_size, self.config.seq_length), dtype=torch.long)
+
     def _run_inference(self, input_ids: torch.Tensor) -> float:
         """Run MLX inference with same input as PyTorch"""
         start_time = time.time()
         try:
             # Convert PyTorch tensor to MLX array
             input_ids_mlx = mx.array(input_ids.numpy())
-            
+
             # Get embeddings
             embeddings = self.model(input_ids_mlx)
-            
+
             # Mean pooling (following the API pattern)
             pooled = embeddings.mean(axis=1)
-            
+
             # Convert to numpy (following the API pattern)
             pooled_numpy = np.array(pooled.tolist(), dtype=np.float32)
-            
+
             # Force computation
             _ = pooled_numpy.shape
-            
+
         except Exception as e:
             print(f"MLX inference error: {e}")
-            return float('inf')
+            return float("inf")
         end_time = time.time()
-        
+
         return end_time - start_time
-    
-    def run(self) -> Dict[int, Dict[str, float]]:
+
+    def run(self) -> dict[int, dict[str, float]]:
         """Run the MLX benchmark across all batch sizes"""
         results = {}
-        
+
         print(f"Starting MLX benchmark with model: {self.config.model_path}")
         print(f"Testing batch sizes: {self.config.batch_sizes}")
-        
+
         for batch_size in self.config.batch_sizes:
             print(f"\n=== Testing MLX batch size: {batch_size} ===")
             times = []
-            
+
             # Create input batch (same as PyTorch)
             input_ids = self._create_random_batch(batch_size)
-            
+
             # Warm up
             print("Warming up...")
             for _ in range(3):
@@ -109,26 +107,26 @@ class MLXBenchmark:
                 except Exception as e:
                     print(f"Warmup error: {e}")
                     break
-            
+
             # Run benchmark
-            for i in tqdm(range(self.config.num_runs), desc=f"MLX Batch size {batch_size}"):
+            for _i in tqdm(range(self.config.num_runs), desc=f"MLX Batch size {batch_size}"):
                 try:
                     elapsed_time = self._run_inference(input_ids)
-                    if elapsed_time != float('inf'):
+                    if elapsed_time != float("inf"):
                         times.append(elapsed_time)
                 except Exception as e:
                     print(f"Error during MLX inference: {e}")
                     break
-            
+
             if not times:
                 print(f"Skipping batch size {batch_size} due to errors")
                 continue
-                
+
             # Calculate statistics
             avg_time = np.mean(times)
             std_time = np.std(times)
             throughput = batch_size / avg_time
-            
+
             results[batch_size] = {
                 "avg_time": avg_time,
                 "std_time": std_time,
@@ -136,122 +134,127 @@ class MLXBenchmark:
                 "min_time": np.min(times),
                 "max_time": np.max(times),
             }
-            
+
             print(f"MLX Results for batch size {batch_size}:")
             print(f"  Avg Time: {avg_time:.4f}s ± {std_time:.4f}s")
             print(f"  Min Time: {np.min(times):.4f}s")
             print(f"  Max Time: {np.max(times):.4f}s")
             print(f"  Throughput: {throughput:.2f} sequences/second")
-        
+
         return results
 
+
 class Benchmark:
     def __init__(self, config: BenchmarkConfig):
         self.config = config
-        self.device = "cuda" if torch.cuda.is_available() else "mps" if torch.backends.mps.is_available() else "cpu"
+        self.device = (
+            "cuda"
+            if torch.cuda.is_available()
+            else "mps"
+            if torch.backends.mps.is_available()
+            else "cpu"
+        )
         self.model = self._load_model()
-    
+
     def _load_model(self) -> nn.Module:
         print(f"Loading model from {self.config.model_path}...")
-        
-        
+
         model = AutoModel.from_pretrained(self.config.model_path)
         if self.config.use_fp16:
             model = model.half()
         model = torch.compile(model)
         model = model.to(self.device)
-        
+
         model.eval()
         return model
-    
+
     def _create_random_batch(self, batch_size: int) -> torch.Tensor:
         return torch.randint(
-            0, 1000,
+            0,
+            1000,
             (batch_size, self.config.seq_length),
             device=self.device,
-            dtype=torch.long
+            dtype=torch.long,
         )
-    
+
     def _run_inference(self, input_ids: torch.Tensor) -> float:
         attention_mask = torch.ones_like(input_ids)
-        
+
         start_time = time.time()
         with torch.no_grad():
-            output = self.model(input_ids=input_ids, attention_mask=attention_mask)
+            self.model(input_ids=input_ids, attention_mask=attention_mask)
         end_time = time.time()
-        
+
         return end_time - start_time
-    
-    def run(self) -> Dict[int, Dict[str, float]]:
+
+    def run(self) -> dict[int, dict[str, float]]:
         results = {}
-        
+
         if torch.cuda.is_available():
             torch.cuda.reset_peak_memory_stats()
-        
+
         for batch_size in self.config.batch_sizes:
             print(f"\nTesting batch size: {batch_size}")
             times = []
-            
+
             input_ids = self._create_random_batch(batch_size)
-            
-            for i in tqdm(range(self.config.num_runs), desc=f"Batch size {batch_size}"):
+
+            for _i in tqdm(range(self.config.num_runs), desc=f"Batch size {batch_size}"):
                 try:
                     elapsed_time = self._run_inference(input_ids)
                     times.append(elapsed_time)
                 except Exception as e:
                     print(f"Error during inference: {e}")
                     break
-            
+
             if not times:
                 continue
-                
+
             avg_time = np.mean(times)
             std_time = np.std(times)
             throughput = batch_size / avg_time
-            
+
             results[batch_size] = {
                 "avg_time": avg_time,
                 "std_time": std_time,
                 "throughput": throughput,
             }
-            
+
             print(f"Avg Time: {avg_time:.4f}s ± {std_time:.4f}s")
             print(f"Throughput: {throughput:.2f} sequences/second")
-        
+
         if torch.cuda.is_available():
-            peak_memory_gb = torch.cuda.max_memory_allocated() / (1024 ** 3)
+            peak_memory_gb = torch.cuda.max_memory_allocated() / (1024**3)
         else:
             peak_memory_gb = 0.0
-        
+
         for batch_size in results:
             results[batch_size]["peak_memory_gb"] = peak_memory_gb
-        
+
         return results
 
+
 def run_benchmark():
     """Main function to run the benchmark with optimized parameters."""
     config = BenchmarkConfig()
-    
+
     try:
         benchmark = Benchmark(config)
         results = benchmark.run()
-        
+
         max_throughput = max(results[batch_size]["throughput"] for batch_size in results)
         avg_throughput = np.mean([results[batch_size]["throughput"] for batch_size in results])
-        
+
         return {
             "max_throughput": max_throughput,
             "avg_throughput": avg_throughput,
-            "results": results
+            "results": results,
         }
-        
+
     except Exception as e:
         print(f"Benchmark failed: {e}")
-        return {
-            "max_throughput": 0.0,
-            "avg_throughput": 0.0,
-            "error": str(e)
-        }
+        return {"max_throughput": 0.0, "avg_throughput": 0.0, "error": str(e)}
+
 
 def run_mlx_benchmark():
     """Run MLX-specific benchmark"""
@@ -260,55 +263,49 @@ def run_mlx_benchmark():
         return {
             "max_throughput": 0.0,
             "avg_throughput": 0.0,
-            "error": "MLX not available"
+            "error": "MLX not available",
         }
-    
-    config = BenchmarkConfig(
-        model_path="mlx-community/all-MiniLM-L6-v2-4bit",
-        use_mlx=True
-    )
-    
+
+    config = BenchmarkConfig(model_path="mlx-community/all-MiniLM-L6-v2-4bit", use_mlx=True)
+
     try:
         benchmark = MLXBenchmark(config)
         results = benchmark.run()
-        
+
         if not results:
             return {
                 "max_throughput": 0.0,
                 "avg_throughput": 0.0,
-                "error": "No valid results"
+                "error": "No valid results",
             }
-        
+
         max_throughput = max(results[batch_size]["throughput"] for batch_size in results)
         avg_throughput = np.mean([results[batch_size]["throughput"] for batch_size in results])
-        
+
         return {
             "max_throughput": max_throughput,
             "avg_throughput": avg_throughput,
-            "results": results
+            "results": results,
         }
-        
+
     except Exception as e:
         print(f"MLX benchmark failed: {e}")
-        return {
-            "max_throughput": 0.0,
-            "avg_throughput": 0.0,
-            "error": str(e)
-        }
+        return {"max_throughput": 0.0, "avg_throughput": 0.0, "error": str(e)}
+
 
 if __name__ == "__main__":
     print("=== PyTorch Benchmark ===")
     pytorch_result = run_benchmark()
     print(f"PyTorch Max throughput: {pytorch_result['max_throughput']:.2f} sequences/second")
     print(f"PyTorch Average throughput: {pytorch_result['avg_throughput']:.2f} sequences/second")
-    
+
     print("\n=== MLX Benchmark ===")
     mlx_result = run_mlx_benchmark()
     print(f"MLX Max throughput: {mlx_result['max_throughput']:.2f} sequences/second")
     print(f"MLX Average throughput: {mlx_result['avg_throughput']:.2f} sequences/second")
-    
+
     # Compare results
-    if pytorch_result['max_throughput'] > 0 and mlx_result['max_throughput'] > 0:
-        speedup = mlx_result['max_throughput'] / pytorch_result['max_throughput']
-        print(f"\n=== Comparison ===")
-        print(f"MLX is {speedup:.2f}x {'faster' if speedup > 1 else 'slower'} than PyTorch") 
+    if pytorch_result["max_throughput"] > 0 and mlx_result["max_throughput"] > 0:
+        speedup = mlx_result["max_throughput"] / pytorch_result["max_throughput"]
+        print("\n=== Comparison ===")
+        print(f"MLX is {speedup:.2f}x {'faster' if speedup > 1 else 'slower'} than PyTorch")