fix: properly handle Python 3.13 support with PyTorch compatibility

- Support Python 3.13 on most platforms (Ubuntu, ARM64 Mac)
- Exclude Intel Mac + Python 3.13 combination due to PyTorch wheel availability
- PyTorch <2.5 supports Intel Mac but not Python 3.13
- PyTorch 2.5+ supports Python 3.13 but not Intel Mac x86_64
- Document limitation in CI configuration comments
- Update README badges with detailed Python version support and CI status

🤖 Generated with [Claude Code](https://claude.ai/code)

Co-Authored-By: Claude <noreply@anthropic.com>

.github/workflows/build-reusable.yml

@@ -54,16 +54,26 @@ jobs:
             python: '3.12'
           - os: ubuntu-22.04
             python: '3.13'
-          - os: macos-latest
+          - os: macos-14
             python: '3.9'
-          - os: macos-latest
+          - os: macos-14
             python: '3.10'
-          - os: macos-latest
+          - os: macos-14
             python: '3.11'
-          - os: macos-latest
+          - os: macos-14
             python: '3.12'
-          - os: macos-latest
+          - os: macos-14
             python: '3.13'
+          - os: macos-13
+            python: '3.9'
+          - os: macos-13
+            python: '3.10'
+          - os: macos-13
+            python: '3.11'
+          - os: macos-13
+            python: '3.12'
+          # Note: macos-13 + Python 3.13 excluded due to PyTorch compatibility
+          # (PyTorch 2.5+ supports Python 3.13 but not Intel Mac x86_64)
     runs-on: ${{ matrix.os }}
 
     steps:
@@ -109,48 +119,59 @@ jobs:
             uv pip install --system delocate
           fi
 
+      - name: Set macOS environment variables
+        if: runner.os == 'macOS'
+        run: |
+          # Use brew --prefix to automatically detect Homebrew installation path
+          HOMEBREW_PREFIX=$(brew --prefix)
+          echo "HOMEBREW_PREFIX=${HOMEBREW_PREFIX}" >> $GITHUB_ENV
+          echo "OpenMP_ROOT=${HOMEBREW_PREFIX}/opt/libomp" >> $GITHUB_ENV
+
+          # Set CMAKE_PREFIX_PATH to let CMake find all packages automatically
+          echo "CMAKE_PREFIX_PATH=${HOMEBREW_PREFIX}" >> $GITHUB_ENV
+
+          # Set compiler flags for OpenMP (required for both backends)
+          echo "LDFLAGS=-L${HOMEBREW_PREFIX}/opt/libomp/lib" >> $GITHUB_ENV
+          echo "CPPFLAGS=-I${HOMEBREW_PREFIX}/opt/libomp/include" >> $GITHUB_ENV
+
       - name: Build packages
         run: |
           # Build core (platform independent)
-          if [[ "${{ matrix.os }}" == ubuntu-* ]]; then
-            cd packages/leann-core
-            uv build
-            cd ../..
-          fi
+          cd packages/leann-core
+          uv build
+          cd ../..
 
           # Build HNSW backend
           cd packages/leann-backend-hnsw
-          if [ "${{ matrix.os }}" == "macos-latest" ]; then
-            # Use system clang instead of homebrew LLVM for better compatibility
+          if [[ "${{ matrix.os }}" == macos-* ]]; then
+            # Use system clang for better compatibility
             export CC=clang
             export CXX=clang++
             export MACOSX_DEPLOYMENT_TARGET=11.0
-            uv build --wheel --python python
+            uv build --wheel --python ${{ matrix.python }} --find-links ${GITHUB_WORKSPACE}/packages/leann-core/dist
           else
-            uv build --wheel --python python
+            uv build --wheel --python ${{ matrix.python }} --find-links ${GITHUB_WORKSPACE}/packages/leann-core/dist
           fi
           cd ../..
 
           # Build DiskANN backend
           cd packages/leann-backend-diskann
-          if [ "${{ matrix.os }}" == "macos-latest" ]; then
-            # Use system clang instead of homebrew LLVM for better compatibility
+          if [[ "${{ matrix.os }}" == macos-* ]]; then
+            # Use system clang for better compatibility
             export CC=clang
             export CXX=clang++
             # DiskANN requires macOS 13.3+ for sgesdd_ LAPACK function
             export MACOSX_DEPLOYMENT_TARGET=13.3
-            uv build --wheel --python python
+            uv build --wheel --python ${{ matrix.python }} --find-links ${GITHUB_WORKSPACE}/packages/leann-core/dist
           else
-            uv build --wheel --python python
+            uv build --wheel --python ${{ matrix.python }} --find-links ${GITHUB_WORKSPACE}/packages/leann-core/dist
           fi
           cd ../..
 
           # Build meta package (platform independent)
-          if [[ "${{ matrix.os }}" == ubuntu-* ]]; then
-            cd packages/leann
-            uv build
-            cd ../..
-          fi
+          cd packages/leann
+          uv build
+          cd ../..
 
       - name: Repair wheels (Linux)
         if: runner.os == 'Linux'
@@ -199,20 +220,18 @@ jobs:
           echo "📦 Built packages:"
           find packages/*/dist -name "*.whl" -o -name "*.tar.gz" | sort
 
+
       - name: Install built packages for testing
         run: |
-          # Create a virtual environment
-          uv venv
+          # Create a virtual environment with the correct Python version
+          uv venv --python ${{ matrix.python }}
           source .venv/bin/activate || source .venv/Scripts/activate
 
-          # Install the built wheels
-          # Use --find-links to let uv choose the correct wheel for the platform
-          if [[ "${{ matrix.os }}" == ubuntu-* ]]; then
-            uv pip install leann-core --find-links packages/leann-core/dist
-            uv pip install leann --find-links packages/leann/dist
-          fi
-          uv pip install leann-backend-hnsw --find-links packages/leann-backend-hnsw/dist
-          uv pip install leann-backend-diskann --find-links packages/leann-backend-diskann/dist
+          # Install packages using --find-links to prioritize local builds
+          uv pip install --find-links packages/leann-core/dist --find-links packages/leann-backend-hnsw/dist --find-links packages/leann-backend-diskann/dist packages/leann-core/dist/*.whl || uv pip install --find-links packages/leann-core/dist packages/leann-core/dist/*.tar.gz
+          uv pip install --find-links packages/leann-core/dist packages/leann-backend-hnsw/dist/*.whl
+          uv pip install --find-links packages/leann-core/dist packages/leann-backend-diskann/dist/*.whl
+          uv pip install packages/leann/dist/*.whl || uv pip install packages/leann/dist/*.tar.gz
 
           # Install test dependencies using extras
           uv pip install -e ".[test]"

README.md

@@ -3,9 +3,11 @@
 </p>
 
 <p align="center">
-  <img src="https://img.shields.io/badge/Python-3.9%2B-blue.svg" alt="Python 3.9+">
+  <img src="https://img.shields.io/badge/Python-3.9%20%7C%203.10%20%7C%203.11%20%7C%203.12%20%7C%203.13-blue.svg" alt="Python Versions">
+  <img src="https://github.com/yichuan-w/LEANN/actions/workflows/build-and-publish.yml/badge.svg" alt="CI Status">
+  <img src="https://img.shields.io/badge/Platform-Ubuntu%20%7C%20macOS%20(ARM64%2FIntel)-lightgrey" alt="Platform">
   <img src="https://img.shields.io/badge/License-MIT-green.svg" alt="MIT License">
-  <img src="https://img.shields.io/badge/Platform-Linux%20%7C%20macOS-lightgrey" alt="Platform">
+  <img src="https://img.shields.io/badge/MCP-Native%20Integration-blue" alt="MCP Integration">
 </p>
 
 <h2 align="center" tabindex="-1" class="heading-element" dir="auto">
@@ -16,7 +18,10 @@ LEANN is an innovative vector database that democratizes personal AI. Transform
 
 LEANN achieves this through *graph-based selective recomputation* with *high-degree preserving pruning*, computing embeddings on-demand instead of storing them all. [Illustration Fig →](#️-architecture--how-it-works) | [Paper →](https://arxiv.org/abs/2506.08276)
 
-**Ready to RAG Everything?** Transform your laptop into a personal AI assistant that can search your **[file system](#-personal-data-manager-process-any-documents-pdf-txt-md)**, **[emails](#-your-personal-email-secretary-rag-on-apple-mail)**, **[browser history](#-time-machine-for-the-web-rag-your-entire-browser-history)**, **[chat history](#-wechat-detective-unlock-your-golden-memories)**, or external knowledge bases (i.e., 60M documents) - all on your laptop, with zero cloud costs and complete privacy.
+**Ready to RAG Everything?** Transform your laptop into a personal AI assistant that can semantic search your **[file system](#-personal-data-manager-process-any-documents-pdf-txt-md)**, **[emails](#-your-personal-email-secretary-rag-on-apple-mail)**, **[browser history](#-time-machine-for-the-web-rag-your-entire-browser-history)**, **[chat history](#-wechat-detective-unlock-your-golden-memories)**, **[codebase](#-claude-code-integration-transform-your-development-workflow)**\* , or external knowledge bases (i.e., 60M documents) - all on your laptop, with zero cloud costs and complete privacy.
+
+
+\* Claude Code only supports basic `grep`-style keyword search. **LEANN** is a drop-in **semantic search MCP service fully compatible with Claude Code**, unlocking intelligent retrieval without changing your workflow. 🔥 Check out [the easy setup →](packages/leann-mcp/README.md)
 
 
 
@@ -26,7 +31,7 @@ LEANN achieves this through *graph-based selective recomputation* with *high-deg
   <img src="assets/effects.png" alt="LEANN vs Traditional Vector DB Storage Comparison" width="70%">
 </p>
 
-> **The numbers speak for themselves:** Index 60 million Wikipedia chunks in just 6GB instead of 201GB. From emails to browser history, everything fits on your laptop. [See detailed benchmarks for different applications below ↓](#storage-comparison)
+> **The numbers speak for themselves:** Index 60 million text chunks in just 6GB instead of 201GB. From emails to browser history, everything fits on your laptop. [See detailed benchmarks for different applications below ↓](#storage-comparison)
 
 
 🔒 **Privacy:** Your data never leaves your laptop. No OpenAI, no cloud, no "terms of service".
@@ -166,7 +171,7 @@ ollama pull llama3.2:1b
 
 </details>
 
-### Flexible Configuration
+### ⭐ Flexible Configuration
 
 LEANN provides flexible parameters for embedding models, search strategies, and data processing to fit your specific needs.
 
@@ -185,12 +190,13 @@ All RAG examples share these common parameters. **Interactive mode** is availabl
 --force-rebuild         # Force rebuild index even if it exists
 
 # Embedding Parameters
---embedding-model MODEL  # e.g., facebook/contriever, text-embedding-3-small or mlx-community/multilingual-e5-base-mlx
---embedding-mode MODE    # sentence-transformers, openai, or mlx
+--embedding-model MODEL  # e.g., facebook/contriever, text-embedding-3-small, nomic-embed-text, mlx-community/Qwen3-Embedding-0.6B-8bit or nomic-embed-text
+--embedding-mode MODE    # sentence-transformers, openai, mlx, or ollama
 
 # LLM Parameters (Text generation models)
 --llm TYPE              # LLM backend: openai, ollama, or hf (default: openai)
 --llm-model MODEL       # Model name (default: gpt-4o) e.g., gpt-4o-mini, llama3.2:1b, Qwen/Qwen2.5-1.5B-Instruct
+--thinking-budget LEVEL # Thinking budget for reasoning models: low/medium/high (supported by o3, o3-mini, GPT-Oss:20b, and other reasoning models)
 
 # Search Parameters
 --top-k N               # Number of results to retrieve (default: 20)
@@ -218,7 +224,7 @@ Ask questions directly about your personal PDFs, documents, and any directory co
   <img src="videos/paper_clear.gif" alt="LEANN Document Search Demo" width="600">
 </p>
 
-The example below asks a question about summarizing our paper (uses default data in `data/`, which is a directory with diverse data sources: two papers, Pride and Prejudice, and a README in Chinese) and this is the **easiest example** to run here:
+The example below asks a question about summarizing our paper (uses default data in `data/`, which is a directory with diverse data sources: two papers, Pride and Prejudice, and a Technical report about LLM in Huawei in Chinese), and this is the **easiest example** to run here:
 
 ```bash
 source .venv/bin/activate # Don't forget to activate the virtual environment
@@ -413,7 +419,26 @@ Once the index is built, you can ask questions like:
 
 </details>
 
+### 🚀 Claude Code Integration: Transform Your Development Workflow!
 
+**The future of code assistance is here.** Transform your development workflow with LEANN's native MCP integration for Claude Code. Index your entire codebase and get intelligent code assistance directly in your IDE.
+
+**Key features:**
+- 🔍 **Semantic code search** across your entire project
+- 📚 **Context-aware assistance** for debugging and development
+- 🚀 **Zero-config setup** with automatic language detection
+
+```bash
+# Install LEANN globally for MCP integration
+uv tool install leann-core
+
+# Setup is automatic - just start using Claude Code!
+```
+Try our fully agentic pipeline with auto query rewriting, semantic search planning, and more:
+
+![LEANN MCP Integration](assets/mcp_leann.png)
+
+**Ready to supercharge your coding?** [Complete Setup Guide →](packages/leann-mcp/README.md)
 
 ## 🖥️ Command Line Interface
 
@@ -427,7 +452,7 @@ source .venv/bin/activate
 leann --help
 ```
 
-**To make it globally available (recommended for daily use):**
+**To make it globally available:**
 ```bash
 # Install the LEANN CLI globally using uv tool
 uv tool install leann
@@ -436,13 +461,15 @@ uv tool install leann
 leann --help
 ```
 
+> **Note**: Global installation is required for Claude Code integration. The `leann_mcp` server depends on the globally available `leann` command.
+
 
 
 ### Usage Examples
 
 ```bash
-# Build an index from documents
-leann build my-docs --docs ./documents
+# build from a specific directory, and my_docs is the index name
+leann build my-docs --docs ./your_documents
 
 # Search your documents
 leann search my-docs "machine learning concepts"
@@ -574,8 +601,11 @@ MIT License - see [LICENSE](LICENSE) for details.
 
 ## 🙏 Acknowledgments
 
-This work is done at [**Berkeley Sky Computing Lab**](https://sky.cs.berkeley.edu/).
+Core Contributors: [Yichuan Wang](https://yichuan-w.github.io/) & [Zhifei Li](https://github.com/andylizf).
 
+We welcome more contributors! Feel free to open issues or submit PRs.
+
+This work is done at [**Berkeley Sky Computing Lab**](https://sky.cs.berkeley.edu/).
 
 ---
 

apps/base_rag_example.py

@@ -75,7 +75,7 @@ class BaseRAGExample(ABC):
             "--embedding-mode",
             type=str,
             default="sentence-transformers",
-            choices=["sentence-transformers", "openai", "mlx"],
+            choices=["sentence-transformers", "openai", "mlx", "ollama"],
             help="Embedding backend mode (default: sentence-transformers)",
         )
 
@@ -85,7 +85,7 @@ class BaseRAGExample(ABC):
             "--llm",
             type=str,
             default="openai",
-            choices=["openai", "ollama", "hf"],
+            choices=["openai", "ollama", "hf", "simulated"],
             help="LLM backend to use (default: openai)",
         )
         llm_group.add_argument(
@@ -100,6 +100,13 @@ class BaseRAGExample(ABC):
             default="http://localhost:11434",
             help="Host for Ollama API (default: http://localhost:11434)",
         )
+        llm_group.add_argument(
+            "--thinking-budget",
+            type=str,
+            choices=["low", "medium", "high"],
+            default=None,
+            help="Thinking budget for reasoning models (low/medium/high). Supported by GPT-Oss:20b and other reasoning models.",
+        )
 
         # Search parameters
         search_group = parser.add_argument_group("Search Parameters")
@@ -228,7 +235,17 @@ class BaseRAGExample(ABC):
                 if not query:
                     continue
 
-                response = chat.ask(query, top_k=args.top_k, complexity=args.search_complexity)
+                # Prepare LLM kwargs with thinking budget if specified
+                llm_kwargs = {}
+                if hasattr(args, "thinking_budget") and args.thinking_budget:
+                    llm_kwargs["thinking_budget"] = args.thinking_budget
+
+                response = chat.ask(
+                    query,
+                    top_k=args.top_k,
+                    complexity=args.search_complexity,
+                    llm_kwargs=llm_kwargs,
+                )
                 print(f"\nAssistant: {response}\n")
 
             except KeyboardInterrupt:
@@ -247,7 +264,15 @@ class BaseRAGExample(ABC):
         )
 
         print(f"\n[Query]: \033[36m{query}\033[0m")
-        response = chat.ask(query, top_k=args.top_k, complexity=args.search_complexity)
+
+        # Prepare LLM kwargs with thinking budget if specified
+        llm_kwargs = {}
+        if hasattr(args, "thinking_budget") and args.thinking_budget:
+            llm_kwargs["thinking_budget"] = args.thinking_budget
+
+        response = chat.ask(
+            query, top_k=args.top_k, complexity=args.search_complexity, llm_kwargs=llm_kwargs
+        )
         print(f"\n[Response]: \033[36m{response}\033[0m")
 
     async def run(self):

docs/THINKING_BUDGET_FEATURE.md

@@ -0,0 +1,123 @@
+# Thinking Budget Feature Implementation
+
+## Overview
+
+This document describes the implementation of the **thinking budget** feature for LEANN, which allows users to control the computational effort for reasoning models like GPT-Oss:20b.
+
+## Feature Description
+
+The thinking budget feature provides three levels of computational effort for reasoning models:
+- **`low`**: Fast responses, basic reasoning (default for simple queries)
+- **`medium`**: Balanced speed and reasoning depth
+- **`high`**: Maximum reasoning effort, best for complex analytical questions
+
+## Implementation Details
+
+### 1. Command Line Interface
+
+Added `--thinking-budget` parameter to both CLI and RAG examples:
+
+```bash
+# LEANN CLI
+leann ask my-index --llm ollama --model gpt-oss:20b --thinking-budget high
+
+# RAG Examples
+python apps/email_rag.py --llm ollama --llm-model gpt-oss:20b --thinking-budget high
+python apps/document_rag.py --llm openai --llm-model o3 --thinking-budget medium
+```
+
+### 2. LLM Backend Support
+
+#### Ollama Backend (`packages/leann-core/src/leann/chat.py`)
+
+```python
+def ask(self, prompt: str, **kwargs) -> str:
+    # Handle thinking budget for reasoning models
+    options = kwargs.copy()
+    thinking_budget = kwargs.get("thinking_budget")
+    if thinking_budget:
+        options.pop("thinking_budget", None)
+        if thinking_budget in ["low", "medium", "high"]:
+            options["reasoning"] = {"effort": thinking_budget, "exclude": False}
+```
+
+**API Format**: Uses Ollama's `reasoning` parameter with `effort` and `exclude` fields.
+
+#### OpenAI Backend (`packages/leann-core/src/leann/chat.py`)
+
+```python
+def ask(self, prompt: str, **kwargs) -> str:
+    # Handle thinking budget for reasoning models
+    thinking_budget = kwargs.get("thinking_budget")
+    if thinking_budget and thinking_budget in ["low", "medium", "high"]:
+        # Check if this is an o-series model
+        o_series_models = ["o3", "o3-mini", "o4-mini", "o1", "o3-pro", "o3-deep-research"]
+        if any(model in self.model for model in o_series_models):
+            params["reasoning_effort"] = thinking_budget
+```
+
+**API Format**: Uses OpenAI's `reasoning_effort` parameter for o-series models.
+
+### 3. Parameter Propagation
+
+The thinking budget parameter is properly propagated through the LEANN architecture:
+
+1. **CLI** (`packages/leann-core/src/leann/cli.py`): Captures `--thinking-budget` argument
+2. **Base RAG** (`apps/base_rag_example.py`): Adds parameter to argument parser
+3. **LeannChat** (`packages/leann-core/src/leann/api.py`): Passes `llm_kwargs` to LLM
+4. **LLM Interface**: Handles the parameter in backend-specific implementations
+
+## Files Modified
+
+### Core Implementation
+- `packages/leann-core/src/leann/chat.py`: Added thinking budget support to OllamaChat and OpenAIChat
+- `packages/leann-core/src/leann/cli.py`: Added `--thinking-budget` argument
+- `apps/base_rag_example.py`: Added thinking budget parameter to RAG examples
+
+### Documentation
+- `README.md`: Added thinking budget parameter to usage examples
+- `docs/configuration-guide.md`: Added detailed documentation and usage guidelines
+
+### Examples
+- `examples/thinking_budget_demo.py`: Comprehensive demo script with usage examples
+
+## Usage Examples
+
+### Basic Usage
+```bash
+# High reasoning effort for complex questions
+leann ask my-index --llm ollama --model gpt-oss:20b --thinking-budget high
+
+# Medium reasoning for balanced performance
+leann ask my-index --llm openai --model gpt-4o --thinking-budget medium
+
+# Low reasoning for fast responses
+leann ask my-index --llm ollama --model gpt-oss:20b --thinking-budget low
+```
+
+### RAG Examples
+```bash
+# Email RAG with high reasoning
+python apps/email_rag.py --llm ollama --llm-model gpt-oss:20b --thinking-budget high
+
+# Document RAG with medium reasoning
+python apps/document_rag.py --llm openai --llm-model gpt-4o --thinking-budget medium
+```
+
+## Supported Models
+
+### Ollama Models
+- **GPT-Oss:20b**: Primary target model with reasoning capabilities
+- **Other reasoning models**: Any Ollama model that supports the `reasoning` parameter
+
+### OpenAI Models
+- **o3, o3-mini, o4-mini, o1**: o-series reasoning models with `reasoning_effort` parameter
+- **GPT-OSS models**: Models that support reasoning capabilities
+
+## Testing
+
+The implementation includes comprehensive testing:
+- Parameter handling verification
+- Backend-specific API format validation
+- CLI argument parsing tests
+- Integration with existing LEANN architecture

docs/configuration-guide.md

@@ -49,14 +49,25 @@ Based on our experience developing LEANN, embedding models fall into three categ
 - **Cons**: Slower inference, longer index build times
 - **Use when**: Quality is paramount and you have sufficient compute resources. **Highly recommended** for production use
 
-### Quick Start: OpenAI Embeddings (Fastest Setup)
+### Quick Start: Cloud and Local Embedding Options
 
+**OpenAI Embeddings (Fastest Setup)**
 For immediate testing without local model downloads:
 ```bash
 # Set OpenAI embeddings (requires OPENAI_API_KEY)
 --embedding-mode openai --embedding-model text-embedding-3-small
 ```
 
+**Ollama Embeddings (Privacy-Focused)**
+For local embeddings with complete privacy:
+```bash
+# First, pull an embedding model
+ollama pull nomic-embed-text
+
+# Use Ollama embeddings
+--embedding-mode ollama --embedding-model nomic-embed-text
+```
+
 <details>
 <summary><strong>Cloud vs Local Trade-offs</strong></summary>
 
@@ -103,13 +114,15 @@ For immediate testing without local model downloads:
 **OpenAI** (`--llm openai`)
 - **Pros**: Best quality, consistent performance, no local resources needed
 - **Cons**: Costs money ($0.15-2.5 per million tokens), requires internet, data privacy concerns
-- **Models**: `gpt-4o-mini` (fast, cheap), `gpt-4o` (best quality), `o3-mini` (reasoning, not so expensive)
+- **Models**: `gpt-4o-mini` (fast, cheap), `gpt-4o` (best quality), `o3` (reasoning), `o3-mini` (reasoning, cheaper)
+- **Thinking Budget**: Use `--thinking-budget low/medium/high` for o-series reasoning models (o3, o3-mini, o4-mini)
 - **Note**: Our current default, but we recommend switching to Ollama for most use cases
 
 **Ollama** (`--llm ollama`)
 - **Pros**: Fully local, free, privacy-preserving, good model variety
 - **Cons**: Requires local GPU/CPU resources, slower than cloud APIs, need to install extra [ollama app](https://github.com/ollama/ollama?tab=readme-ov-file#ollama) and pre-download models by `ollama pull`
 - **Models**: `qwen3:0.6b` (ultra-fast), `qwen3:1.7b` (balanced), `qwen3:4b` (good quality), `qwen3:7b` (high quality), `deepseek-r1:1.5b` (reasoning)
+- **Thinking Budget**: Use `--thinking-budget low/medium/high` for reasoning models like GPT-Oss:20b
 
 **HuggingFace** (`--llm hf`)
 - **Pros**: Free tier available, huge model selection, direct model loading (vs Ollama's server-based approach)
@@ -151,6 +164,36 @@ For immediate testing without local model downloads:
 - LLM processing time ∝ top_k × chunk_size
 - Total context = top_k × chunk_size tokens
 
+### Thinking Budget for Reasoning Models
+
+**`--thinking-budget`** (reasoning effort level)
+- Controls the computational effort for reasoning models
+- Options: `low`, `medium`, `high`
+- Guidelines:
+  - `low`: Fast responses, basic reasoning (default for simple queries)
+  - `medium`: Balanced speed and reasoning depth
+  - `high`: Maximum reasoning effort, best for complex analytical questions
+- **Supported Models**:
+  - **Ollama**: `gpt-oss:20b`, `gpt-oss:120b`
+  - **OpenAI**: `o3`, `o3-mini`, `o4-mini`, `o1` (o-series reasoning models)
+- **Note**: Models without reasoning support will show a warning and proceed without reasoning parameters
+- **Example**: `--thinking-budget high` for complex analytical questions
+
+**📖 For detailed usage examples and implementation details, check out [Thinking Budget Documentation](THINKING_BUDGET_FEATURE.md)**
+
+**💡 Quick Examples:**
+```bash
+# OpenAI o-series reasoning model
+python apps/document_rag.py --query "What are the main techniques LEANN explores?" \
+  --index-dir hnswbuild --backend hnsw \
+  --llm openai --llm-model o3 --thinking-budget medium
+
+# Ollama reasoning model
+python apps/document_rag.py --query "What are the main techniques LEANN explores?" \
+  --index-dir hnswbuild --backend hnsw \
+  --llm ollama --llm-model gpt-oss:20b --thinking-budget high
+```
+
 ### Graph Degree (HNSW/DiskANN)
 
 **`--graph-degree`**
@@ -179,9 +222,15 @@ For immediate testing without local model downloads:
 
 3. **Use MLX on Apple Silicon** (optional optimization):
    ```bash
-   --embedding-mode mlx --embedding-model mlx-community/multilingual-e5-base-mlx
+   --embedding-mode mlx --embedding-model mlx-community/Qwen3-Embedding-0.6B-8bit
    ```
+    MLX might not be the best choice, as we tested and found that it only offers 1.3x acceleration compared to HF, so maybe using ollama is a better choice for embedding generation
 
+4. **Use Ollama**
+   ```bash
+   --embedding-mode ollama --embedding-model nomic-embed-text
+   ```
+   To discover additional embedding models in ollama, check out https://ollama.com/search?c=embedding or read more about embedding models at https://ollama.com/blog/embedding-models, please do check the model size that works best for you
 ### If Search Quality is Poor
 
 1. **Increase retrieval count**:

packages/leann-backend-diskann/CMakeLists.txt

@@ -1,8 +0,0 @@
-# packages/leann-backend-diskann/CMakeLists.txt (simplified version)
-
-cmake_minimum_required(VERSION 3.20)
-project(leann_backend_diskann_wrapper)
-
-# Tell CMake to directly enter the DiskANN submodule and execute its own CMakeLists.txt
-# DiskANN will handle everything itself, including compiling Python bindings
-add_subdirectory(src/third_party/DiskANN)

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

@@ -4,7 +4,7 @@ import os
 import struct
 import sys
 from pathlib import Path
-from typing import Any, Literal
+from typing import Any, Literal, Optional
 
 import numpy as np
 import psutil
@@ -259,7 +259,7 @@ class DiskannSearcher(BaseSearcher):
         prune_ratio: float = 0.0,
         recompute_embeddings: bool = False,
         pruning_strategy: Literal["global", "local", "proportional"] = "global",
-        zmq_port: int | None = None,
+        zmq_port: Optional[int] = None,
         batch_recompute: bool = False,
         dedup_node_dis: bool = False,
         **kwargs,

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

@@ -10,6 +10,7 @@ import sys
 import threading
 import time
 from pathlib import Path
+from typing import Optional
 
 import numpy as np
 import zmq
@@ -32,7 +33,7 @@ if not logger.handlers:
 
 
 def create_diskann_embedding_server(
-    passages_file: str | None = None,
+    passages_file: Optional[str] = None,
     zmq_port: int = 5555,
     model_name: str = "sentence-transformers/all-mpnet-base-v2",
     embedding_mode: str = "sentence-transformers",
@@ -261,7 +262,7 @@ if __name__ == "__main__":
         "--embedding-mode",
         type=str,
         default="sentence-transformers",
-        choices=["sentence-transformers", "openai", "mlx"],
+        choices=["sentence-transformers", "openai", "mlx", "ollama"],
         help="Embedding backend mode",
     )
     parser.add_argument(

packages/leann-backend-diskann/pyproject.toml

@@ -4,8 +4,8 @@ build-backend = "scikit_build_core.build"
 
 [project]
 name = "leann-backend-diskann"
-version = "0.2.1"
-dependencies = ["leann-core==0.2.1", "numpy", "protobuf>=3.19.0"]
+version = "0.2.7"
+dependencies = ["leann-core==0.2.7", "numpy", "protobuf>=3.19.0"]
 
 [tool.scikit-build]
 # Key: simplified CMake path
@@ -17,3 +17,5 @@ editable.mode = "redirect"
 cmake.build-type = "Release"
 build.verbose = true
 build.tool-args = ["-j8"]
+# Let CMake find packages via Homebrew prefix
+cmake.define = {CMAKE_PREFIX_PATH = {env = "CMAKE_PREFIX_PATH"}, OpenMP_ROOT = {env = "OpenMP_ROOT"}}

packages/leann-backend-hnsw/CMakeLists.txt

@@ -5,11 +5,20 @@ set(CMAKE_CXX_COMPILER_WORKS 1)
 
 # Set OpenMP path for macOS
 if(APPLE)
-    set(OpenMP_C_FLAGS "-Xpreprocessor -fopenmp -I/opt/homebrew/opt/libomp/include")
-    set(OpenMP_CXX_FLAGS "-Xpreprocessor -fopenmp -I/opt/homebrew/opt/libomp/include")
+    # Detect Homebrew installation path (Apple Silicon vs Intel)
+    if(EXISTS "/opt/homebrew/opt/libomp")
+        set(HOMEBREW_PREFIX "/opt/homebrew")
+    elseif(EXISTS "/usr/local/opt/libomp")
+        set(HOMEBREW_PREFIX "/usr/local")
+    else()
+        message(FATAL_ERROR "Could not find libomp installation. Please install with: brew install libomp")
+    endif()
+    
+    set(OpenMP_C_FLAGS "-Xpreprocessor -fopenmp -I${HOMEBREW_PREFIX}/opt/libomp/include")
+    set(OpenMP_CXX_FLAGS "-Xpreprocessor -fopenmp -I${HOMEBREW_PREFIX}/opt/libomp/include")
     set(OpenMP_C_LIB_NAMES "omp")
     set(OpenMP_CXX_LIB_NAMES "omp")
-    set(OpenMP_omp_LIBRARY "/opt/homebrew/opt/libomp/lib/libomp.dylib")
+    set(OpenMP_omp_LIBRARY "${HOMEBREW_PREFIX}/opt/libomp/lib/libomp.dylib")
 
     # Force use of system libc++ to avoid version mismatch
     set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -stdlib=libc++")

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

@@ -2,7 +2,7 @@ import logging
 import os
 import shutil
 from pathlib import Path
-from typing import Any, Literal
+from typing import Any, Literal, Optional
 
 import numpy as np
 from leann.interface import (
@@ -152,7 +152,7 @@ class HNSWSearcher(BaseSearcher):
         self,
         query: np.ndarray,
         top_k: int,
-        zmq_port: int | None = None,
+        zmq_port: Optional[int] = None,
         complexity: int = 64,
         beam_width: int = 1,
         prune_ratio: float = 0.0,

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

@@ -10,6 +10,7 @@ import sys
 import threading
 import time
 from pathlib import Path
+from typing import Union
 
 import msgpack
 import numpy as np
@@ -33,7 +34,7 @@ if not logger.handlers:
 
 
 def create_hnsw_embedding_server(
-    passages_file: str | None = None,
+    passages_file: Union[str, None] = None,
     zmq_port: int = 5555,
     model_name: str = "sentence-transformers/all-mpnet-base-v2",
     distance_metric: str = "mips",
@@ -295,7 +296,7 @@ if __name__ == "__main__":
         "--embedding-mode",
         type=str,
         default="sentence-transformers",
-        choices=["sentence-transformers", "openai", "mlx"],
+        choices=["sentence-transformers", "openai", "mlx", "ollama"],
         help="Embedding backend mode",
     )
 

packages/leann-backend-hnsw/pyproject.toml

@@ -6,10 +6,10 @@ build-backend = "scikit_build_core.build"
 
 [project]
 name = "leann-backend-hnsw"
-version = "0.2.1"
+version = "0.2.7"
 description = "Custom-built HNSW (Faiss) backend for the Leann toolkit."
 dependencies = [
-    "leann-core==0.2.1",
+    "leann-core==0.2.7",
     "numpy",
     "pyzmq>=23.0.0",
     "msgpack>=1.0.0",
@@ -22,6 +22,8 @@ cmake.build-type = "Release"
 build.verbose = true
 build.tool-args = ["-j8"]
 
-# CMake definitions to optimize compilation
+# CMake definitions to optimize compilation and find Homebrew packages
 [tool.scikit-build.cmake.define]
 CMAKE_BUILD_PARALLEL_LEVEL = "8"
+CMAKE_PREFIX_PATH = {env = "CMAKE_PREFIX_PATH"}
+OpenMP_ROOT = {env = "OpenMP_ROOT"}

packages/leann-core/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "leann-core"
-version = "0.2.1"
+version = "0.2.7"
 description = "Core API and plugin system for LEANN"
 readme = "README.md"
 requires-python = ">=3.9"
@@ -31,8 +31,10 @@ dependencies = [
     "PyPDF2>=3.0.0",
     "pymupdf>=1.23.0",
     "pdfplumber>=0.10.0",
-    "mlx>=0.26.3; sys_platform == 'darwin'",
-    "mlx-lm>=0.26.0; sys_platform == 'darwin'",
+    "nbconvert>=7.0.0",  # For .ipynb file support
+    "gitignore-parser>=0.1.12",  # For proper .gitignore handling
+    "mlx>=0.26.3; sys_platform == 'darwin' and platform_machine == 'arm64'",
+    "mlx-lm>=0.26.0; sys_platform == 'darwin' and platform_machine == 'arm64'",
 ]
 
 [project.optional-dependencies]
@@ -44,6 +46,7 @@ colab = [
 
 [project.scripts]
 leann = "leann.cli:main"
+leann_mcp = "leann.mcp:main"
 
 [tool.setuptools.packages.find]
 where = ["src"]

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

@@ -10,7 +10,7 @@ import time
 import warnings
 from dataclasses import dataclass, field
 from pathlib import Path
-from typing import Any, Literal
+from typing import Any, Literal, Optional
 
 import numpy as np
 
@@ -33,7 +33,7 @@ def compute_embeddings(
     model_name: str,
     mode: str = "sentence-transformers",
     use_server: bool = True,
-    port: int | None = None,
+    port: Optional[int] = None,
     is_build=False,
 ) -> np.ndarray:
     """
@@ -157,12 +157,12 @@ class LeannBuilder:
         self,
         backend_name: str,
         embedding_model: str = "facebook/contriever",
-        dimensions: int | None = None,
+        dimensions: Optional[int] = None,
         embedding_mode: str = "sentence-transformers",
         **backend_kwargs,
     ):
         self.backend_name = backend_name
-        backend_factory: LeannBackendFactoryInterface | None = BACKEND_REGISTRY.get(backend_name)
+        backend_factory: Optional[LeannBackendFactoryInterface] = 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
@@ -242,7 +242,7 @@ class LeannBuilder:
         self.backend_kwargs = backend_kwargs
         self.chunks: list[dict[str, Any]] = []
 
-    def add_text(self, text: str, metadata: dict[str, Any] | None = None):
+    def add_text(self, text: str, metadata: Optional[dict[str, Any]] = None):
         if metadata is None:
             metadata = {}
         passage_id = metadata.get("id", str(len(self.chunks)))
@@ -554,7 +554,7 @@ class LeannSearcher:
         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], strict=False)
+                zip(results["labels"][0], results["distances"][0])
             ):
                 try:
                     passage_data = self.passage_manager.get_passage(string_id)
@@ -592,7 +592,7 @@ class LeannChat:
     def __init__(
         self,
         index_path: str,
-        llm_config: dict[str, Any] | None = None,
+        llm_config: Optional[dict[str, Any]] = None,
         enable_warmup: bool = False,
         **kwargs,
     ):
@@ -608,7 +608,7 @@ class LeannChat:
         prune_ratio: float = 0.0,
         recompute_embeddings: bool = True,
         pruning_strategy: Literal["global", "local", "proportional"] = "global",
-        llm_kwargs: dict[str, Any] | None = None,
+        llm_kwargs: Optional[dict[str, Any]] = None,
         expected_zmq_port: int = 5557,
         **search_kwargs,
     ):

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

@@ -8,7 +8,7 @@ import difflib
 import logging
 import os
 from abc import ABC, abstractmethod
-from typing import Any
+from typing import Any, Optional
 
 import torch
 
@@ -17,12 +17,12 @@ logging.basicConfig(level=logging.INFO)
 logger = logging.getLogger(__name__)
 
 
-def check_ollama_models() -> list[str]:
+def check_ollama_models(host: str) -> list[str]:
     """Check available Ollama models and return a list"""
     try:
         import requests
 
-        response = requests.get("http://localhost:11434/api/tags", timeout=5)
+        response = requests.get(f"{host}/api/tags", timeout=5)
         if response.status_code == 200:
             data = response.json()
             return [model["name"] for model in data.get("models", [])]
@@ -309,10 +309,12 @@ def search_hf_models(query: str, limit: int = 10) -> list[str]:
     return search_hf_models_fuzzy(query, limit)
 
 
-def validate_model_and_suggest(model_name: str, llm_type: str) -> str | None:
+def validate_model_and_suggest(
+    model_name: str, llm_type: str, host: str = "http://localhost:11434"
+) -> Optional[str]:
     """Validate model name and provide suggestions if invalid"""
     if llm_type == "ollama":
-        available_models = check_ollama_models()
+        available_models = check_ollama_models(host)
         if available_models and model_name not in available_models:
             error_msg = f"Model '{model_name}' not found in your local Ollama installation."
 
@@ -469,7 +471,7 @@ class OllamaChat(LLMInterface):
                 requests.get(host)
 
             # Pre-check model availability with helpful suggestions
-            model_error = validate_model_and_suggest(model, "ollama")
+            model_error = validate_model_and_suggest(model, "ollama", host)
             if model_error:
                 raise ValueError(model_error)
 
@@ -489,11 +491,35 @@ class OllamaChat(LLMInterface):
         import requests
 
         full_url = f"{self.host}/api/generate"
+
+        # Handle thinking budget for reasoning models
+        options = kwargs.copy()
+        thinking_budget = kwargs.get("thinking_budget")
+        if thinking_budget:
+            # Remove thinking_budget from options as it's not a standard Ollama option
+            options.pop("thinking_budget", None)
+            # Only apply reasoning parameters to models that support it
+            reasoning_supported_models = [
+                "gpt-oss:20b",
+                "gpt-oss:120b",
+                "deepseek-r1",
+                "deepseek-coder",
+            ]
+
+            if thinking_budget in ["low", "medium", "high"]:
+                if any(model in self.model.lower() for model in reasoning_supported_models):
+                    options["reasoning"] = {"effort": thinking_budget, "exclude": False}
+                    logger.info(f"Applied reasoning effort={thinking_budget} to model {self.model}")
+                else:
+                    logger.warning(
+                        f"Thinking budget '{thinking_budget}' requested but model '{self.model}' may not support reasoning parameters. Proceeding without reasoning."
+                    )
+
         payload = {
             "model": self.model,
             "prompt": prompt,
             "stream": False,  # Keep it simple for now
-            "options": kwargs,
+            "options": options,
         }
         logger.debug(f"Sending request to Ollama: {payload}")
         try:
@@ -659,7 +685,7 @@ class HFChat(LLMInterface):
 class OpenAIChat(LLMInterface):
     """LLM interface for OpenAI models."""
 
-    def __init__(self, model: str = "gpt-4o", api_key: str | None = None):
+    def __init__(self, model: str = "gpt-4o", api_key: Optional[str] = None):
         self.model = model
         self.api_key = api_key or os.getenv("OPENAI_API_KEY")
 
@@ -684,11 +710,38 @@ class OpenAIChat(LLMInterface):
         params = {
             "model": self.model,
             "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"]},
         }
 
+        # Handle max_tokens vs max_completion_tokens based on model
+        max_tokens = kwargs.get("max_tokens", 1000)
+        if "o3" in self.model or "o4" in self.model or "o1" in self.model:
+            # o-series models use max_completion_tokens
+            params["max_completion_tokens"] = max_tokens
+            params["temperature"] = 1.0
+        else:
+            # Other models use max_tokens
+            params["max_tokens"] = max_tokens
+
+        # Handle thinking budget for reasoning models
+        thinking_budget = kwargs.get("thinking_budget")
+        if thinking_budget and thinking_budget in ["low", "medium", "high"]:
+            # Check if this is an o-series model (partial match for model names)
+            o_series_models = ["o3", "o3-mini", "o4-mini", "o1", "o3-pro", "o3-deep-research"]
+            if any(model in self.model for model in o_series_models):
+                # Use the correct OpenAI reasoning parameter format
+                params["reasoning_effort"] = thinking_budget
+                logger.info(f"Applied reasoning_effort={thinking_budget} to model {self.model}")
+            else:
+                logger.warning(
+                    f"Thinking budget '{thinking_budget}' requested but model '{self.model}' may not support reasoning parameters. Proceeding without reasoning."
+                )
+
+        # Add other kwargs (excluding thinking_budget as it's handled above)
+        for k, v in kwargs.items():
+            if k not in ["max_tokens", "temperature", "thinking_budget"]:
+                params[k] = v
+
         logger.info(f"Sending request to OpenAI with model {self.model}")
 
         try:
@@ -708,7 +761,7 @@ class SimulatedChat(LLMInterface):
         return "This is a simulated answer from the LLM based on the retrieved context."
 
 
-def get_llm(llm_config: dict[str, Any] | None = None) -> LLMInterface:
+def get_llm(llm_config: Optional[dict[str, Any]] = None) -> LLMInterface:
     """
     Factory function to get an LLM interface based on configuration.
 

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

@@ -1,6 +1,7 @@
 import argparse
 import asyncio
 from pathlib import Path
+from typing import Union
 
 from llama_index.core import SimpleDirectoryReader
 from llama_index.core.node_parser import SentenceSplitter
@@ -41,13 +42,23 @@ def extract_pdf_text_with_pdfplumber(file_path: str) -> str:
 
 class LeannCLI:
     def __init__(self):
-        self.indexes_dir = Path.home() / ".leann" / "indexes"
+        # Always use project-local .leann directory (like .git)
+        self.indexes_dir = Path.cwd() / ".leann" / "indexes"
         self.indexes_dir.mkdir(parents=True, exist_ok=True)
 
+        # Default parser for documents
         self.node_parser = SentenceSplitter(
             chunk_size=256, chunk_overlap=128, separator=" ", paragraph_separator="\n\n"
         )
 
+        # Code-optimized parser
+        self.code_parser = SentenceSplitter(
+            chunk_size=512,  # Larger chunks for code context
+            chunk_overlap=50,  # Less overlap to preserve function boundaries
+            separator="\n",  # Split by lines for code
+            paragraph_separator="\n\n",  # Preserve logical code blocks
+        )
+
     def get_index_path(self, index_name: str) -> str:
         index_dir = self.indexes_dir / index_name
         return str(index_dir / "documents.leann")
@@ -64,10 +75,11 @@ class LeannCLI:
             formatter_class=argparse.RawDescriptionHelpFormatter,
             epilog="""
 Examples:
-  leann build my-docs --docs ./documents    # Build index named my-docs
-  leann search my-docs "query"             # Search in my-docs index
-  leann ask my-docs "question"             # Ask my-docs index
-  leann list                              # List all stored indexes
+  leann build my-docs --docs ./documents                    # Build index named my-docs
+  leann build my-ppts --docs ./ --file-types .pptx,.pdf    # Index only PowerPoint and PDF files
+  leann search my-docs "query"                             # Search in my-docs index
+  leann ask my-docs "question"                             # Ask my-docs index
+  leann list                                              # List all stored indexes
             """,
         )
 
@@ -75,18 +87,34 @@ 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(
+            "index_name", nargs="?", help="Index name (default: current directory name)"
+        )
+        build_parser.add_argument(
+            "--docs", type=str, default=".", help="Documents directory (default: current 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(
+            "--embedding-mode",
+            type=str,
+            default="sentence-transformers",
+            choices=["sentence-transformers", "openai", "mlx", "ollama"],
+            help="Embedding backend mode (default: sentence-transformers)",
+        )
         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)
         build_parser.add_argument("--compact", action="store_true", default=True)
         build_parser.add_argument("--recompute", action="store_true", default=True)
+        build_parser.add_argument(
+            "--file-types",
+            type=str,
+            help="Comma-separated list of file extensions to include (e.g., '.txt,.pdf,.pptx'). If not specified, uses default supported types.",
+        )
 
         # Search command
         search_parser = subparsers.add_parser("search", help="Search documents")
@@ -96,7 +124,12 @@ Examples:
         search_parser.add_argument("--complexity", type=int, default=64)
         search_parser.add_argument("--beam-width", type=int, default=1)
         search_parser.add_argument("--prune-ratio", type=float, default=0.0)
-        search_parser.add_argument("--recompute-embeddings", action="store_true")
+        search_parser.add_argument(
+            "--recompute-embeddings",
+            action="store_true",
+            default=True,
+            help="Recompute embeddings (default: True)",
+        )
         search_parser.add_argument(
             "--pruning-strategy",
             choices=["global", "local", "proportional"],
@@ -119,94 +152,370 @@ Examples:
         ask_parser.add_argument("--complexity", type=int, default=32)
         ask_parser.add_argument("--beam-width", type=int, default=1)
         ask_parser.add_argument("--prune-ratio", type=float, default=0.0)
-        ask_parser.add_argument("--recompute-embeddings", action="store_true")
+        ask_parser.add_argument(
+            "--recompute-embeddings",
+            action="store_true",
+            default=True,
+            help="Recompute embeddings (default: True)",
+        )
         ask_parser.add_argument(
             "--pruning-strategy",
             choices=["global", "local", "proportional"],
             default="global",
         )
+        ask_parser.add_argument(
+            "--thinking-budget",
+            type=str,
+            choices=["low", "medium", "high"],
+            default=None,
+            help="Thinking budget for reasoning models (low/medium/high). Supported by GPT-Oss:20b and other reasoning models.",
+        )
 
         # List command
         subparsers.add_parser("list", help="List all indexes")
 
         return parser
 
+    def register_project_dir(self):
+        """Register current project directory in global registry"""
+        global_registry = Path.home() / ".leann" / "projects.json"
+        global_registry.parent.mkdir(exist_ok=True)
+
+        current_dir = str(Path.cwd())
+
+        # Load existing registry
+        projects = []
+        if global_registry.exists():
+            try:
+                import json
+
+                with open(global_registry) as f:
+                    projects = json.load(f)
+            except Exception:
+                projects = []
+
+        # Add current directory if not already present
+        if current_dir not in projects:
+            projects.append(current_dir)
+
+        # Save registry
+        import json
+
+        with open(global_registry, "w") as f:
+            json.dump(projects, f, indent=2)
+
+    def _build_gitignore_parser(self, docs_dir: str):
+        """Build gitignore parser using gitignore-parser library."""
+        from gitignore_parser import parse_gitignore
+
+        # Try to parse the root .gitignore
+        gitignore_path = Path(docs_dir) / ".gitignore"
+
+        if gitignore_path.exists():
+            try:
+                # gitignore-parser automatically handles all subdirectory .gitignore files!
+                matches = parse_gitignore(str(gitignore_path))
+                print(f"📋 Loaded .gitignore from {docs_dir} (includes all subdirectories)")
+                return matches
+            except Exception as e:
+                print(f"Warning: Could not parse .gitignore: {e}")
+        else:
+            print("📋 No .gitignore found")
+
+        # Fallback: basic pattern matching for essential files
+        essential_patterns = {".git", ".DS_Store", "__pycache__", "node_modules", ".venv", "venv"}
+
+        def basic_matches(file_path):
+            path_parts = Path(file_path).parts
+            return any(part in essential_patterns for part in path_parts)
+
+        return basic_matches
+
+    def _should_exclude_file(self, relative_path: Path, gitignore_matches) -> bool:
+        """Check if a file should be excluded using gitignore parser."""
+        return gitignore_matches(str(relative_path))
+
     def list_indexes(self):
         print("Stored LEANN indexes:")
 
-        if not self.indexes_dir.exists():
+        # Get all project directories with .leann
+        global_registry = Path.home() / ".leann" / "projects.json"
+        all_projects = []
+
+        if global_registry.exists():
+            try:
+                import json
+
+                with open(global_registry) as f:
+                    all_projects = json.load(f)
+            except Exception:
+                pass
+
+        # Filter to only existing directories with .leann
+        valid_projects = []
+        for project_dir in all_projects:
+            project_path = Path(project_dir)
+            if project_path.exists() and (project_path / ".leann" / "indexes").exists():
+                valid_projects.append(project_path)
+
+        # Add current project if it has .leann but not in registry
+        current_path = Path.cwd()
+        if (current_path / ".leann" / "indexes").exists() and current_path not in valid_projects:
+            valid_projects.append(current_path)
+
+        if not valid_projects:
             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()]
+        total_indexes = 0
+        current_dir = Path.cwd()
 
-        if not index_dirs:
-            print("No indexes found. Use 'leann build <name> --docs <dir>' to create one.")
-            return
+        for project_path in valid_projects:
+            indexes_dir = project_path / ".leann" / "indexes"
+            if not indexes_dir.exists():
+                continue
 
-        print(f"Found {len(index_dirs)} indexes:")
-        for i, index_dir in enumerate(index_dirs, 1):
-            index_name = index_dir.name
-            status = "✓" if self.index_exists(index_name) else "✗"
+            index_dirs = [d for d in indexes_dir.iterdir() if d.is_dir()]
+            if not index_dirs:
+                continue
 
-            print(f"  {i}. {index_name} [{status}]")
-            if self.index_exists(index_name):
-                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")
+            # Show project header
+            if project_path == current_dir:
+                print(f"\n📁 Current project ({project_path}):")
+            else:
+                print(f"\n📂 {project_path}:")
 
-        if index_dirs:
-            example_name = index_dirs[0].name
-            print("\nUsage:")
-            print(f'  leann search {example_name} "your query"')
-            print(f"  leann ask {example_name} --interactive")
+            for index_dir in index_dirs:
+                total_indexes += 1
+                index_name = index_dir.name
+                meta_file = index_dir / "documents.leann.meta.json"
+                status = "✓" if meta_file.exists() else "✗"
 
-    def load_documents(self, docs_dir: str):
+                print(f"  {total_indexes}. {index_name} [{status}]")
+                if status == "✓":
+                    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 total_indexes > 0:
+            print(f"\nTotal: {total_indexes} indexes across {len(valid_projects)} projects")
+            print("\nUsage (current project only):")
+
+            # Show example from current project
+            current_indexes_dir = current_dir / ".leann" / "indexes"
+            if current_indexes_dir.exists():
+                current_index_dirs = [d for d in current_indexes_dir.iterdir() if d.is_dir()]
+                if current_index_dirs:
+                    example_name = current_index_dirs[0].name
+                    print(f'  leann search {example_name} "your query"')
+                    print(f"  leann ask {example_name} --interactive")
+
+    def load_documents(self, docs_dir: str, custom_file_types: Union[str, None] = None):
         print(f"Loading documents from {docs_dir}...")
+        if custom_file_types:
+            print(f"Using custom file types: {custom_file_types}")
 
-        # Try to use better PDF parsers first
+        # Build gitignore parser
+        gitignore_matches = self._build_gitignore_parser(docs_dir)
+
+        # Try to use better PDF parsers first, but only if PDFs are requested
         documents = []
         docs_path = Path(docs_dir)
 
-        for file_path in docs_path.rglob("*.pdf"):
-            print(f"Processing PDF: {file_path}")
+        # Check if we should process PDFs
+        should_process_pdfs = custom_file_types is None or ".pdf" in custom_file_types
 
-            # 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 should_process_pdfs:
+            for file_path in docs_path.rglob("*.pdf"):
+                # Check if file matches any exclude pattern
+                relative_path = file_path.relative_to(docs_path)
+                if self._should_exclude_file(relative_path, gitignore_matches):
+                    continue
 
-            if text:
-                # Create a simple document structure
-                from llama_index.core import Document
+                print(f"Processing PDF: {file_path}")
 
-                doc = Document(text=text, metadata={"source": str(file_path)})
-                documents.append(doc)
-            else:
-                # Fallback to default reader
-                print(f"Using default reader for {file_path}")
-                default_docs = SimpleDirectoryReader(
-                    str(file_path.parent),
-                    filename_as_id=True,
-                    required_exts=[file_path.suffix],
-                ).load_data()
-                documents.extend(default_docs)
+                # 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:
+                    # Fallback to default reader
+                    print(f"Using default reader for {file_path}")
+                    try:
+                        default_docs = SimpleDirectoryReader(
+                            str(file_path.parent),
+                            filename_as_id=True,
+                            required_exts=[file_path.suffix],
+                        ).load_data()
+                        documents.extend(default_docs)
+                    except Exception as e:
+                        print(f"Warning: Could not process {file_path}: {e}")
 
         # Load other file types with default reader
-        other_docs = SimpleDirectoryReader(
-            docs_dir,
-            recursive=True,
-            encoding="utf-8",
-            required_exts=[".txt", ".md", ".docx"],
-        ).load_data(show_progress=True)
-        documents.extend(other_docs)
+        if custom_file_types:
+            # Parse custom file types from comma-separated string
+            code_extensions = [ext.strip() for ext in custom_file_types.split(",") if ext.strip()]
+            # Ensure extensions start with a dot
+            code_extensions = [ext if ext.startswith(".") else f".{ext}" for ext in code_extensions]
+        else:
+            # Use default supported file types
+            code_extensions = [
+                # Original document types
+                ".txt",
+                ".md",
+                ".docx",
+                ".pptx",
+                # Code files for Claude Code integration
+                ".py",
+                ".js",
+                ".ts",
+                ".jsx",
+                ".tsx",
+                ".java",
+                ".cpp",
+                ".c",
+                ".h",
+                ".hpp",
+                ".cs",
+                ".go",
+                ".rs",
+                ".rb",
+                ".php",
+                ".swift",
+                ".kt",
+                ".scala",
+                ".r",
+                ".sql",
+                ".sh",
+                ".bash",
+                ".zsh",
+                ".fish",
+                ".ps1",
+                ".bat",
+                # Config and markup files
+                ".json",
+                ".yaml",
+                ".yml",
+                ".xml",
+                ".toml",
+                ".ini",
+                ".cfg",
+                ".conf",
+                ".html",
+                ".css",
+                ".scss",
+                ".less",
+                ".vue",
+                ".svelte",
+                # Data science
+                ".ipynb",
+                ".R",
+                ".py",
+                ".jl",
+            ]
+        # Try to load other file types, but don't fail if none are found
+        try:
+            # Create a custom file filter function using our PathSpec
+            def file_filter(file_path: str) -> bool:
+                """Return True if file should be included (not excluded)"""
+                try:
+                    docs_path_obj = Path(docs_dir)
+                    file_path_obj = Path(file_path)
+                    relative_path = file_path_obj.relative_to(docs_path_obj)
+                    return not self._should_exclude_file(relative_path, gitignore_matches)
+                except (ValueError, OSError):
+                    return True  # Include files that can't be processed
+
+            other_docs = SimpleDirectoryReader(
+                docs_dir,
+                recursive=True,
+                encoding="utf-8",
+                required_exts=code_extensions,
+                file_extractor={},  # Use default extractors
+                filename_as_id=True,
+            ).load_data(show_progress=True)
+
+            # Filter documents after loading based on gitignore rules
+            filtered_docs = []
+            for doc in other_docs:
+                file_path = doc.metadata.get("file_path", "")
+                if file_filter(file_path):
+                    filtered_docs.append(doc)
+
+            documents.extend(filtered_docs)
+        except ValueError as e:
+            if "No files found" in str(e):
+                print("No additional files found for other supported types.")
+            else:
+                raise e
 
         all_texts = []
+
+        # Define code file extensions for intelligent chunking
+        code_file_exts = {
+            ".py",
+            ".js",
+            ".ts",
+            ".jsx",
+            ".tsx",
+            ".java",
+            ".cpp",
+            ".c",
+            ".h",
+            ".hpp",
+            ".cs",
+            ".go",
+            ".rs",
+            ".rb",
+            ".php",
+            ".swift",
+            ".kt",
+            ".scala",
+            ".r",
+            ".sql",
+            ".sh",
+            ".bash",
+            ".zsh",
+            ".fish",
+            ".ps1",
+            ".bat",
+            ".json",
+            ".yaml",
+            ".yml",
+            ".xml",
+            ".toml",
+            ".ini",
+            ".cfg",
+            ".conf",
+            ".html",
+            ".css",
+            ".scss",
+            ".less",
+            ".vue",
+            ".svelte",
+            ".ipynb",
+            ".R",
+            ".jl",
+        }
+
         for doc in documents:
-            nodes = self.node_parser.get_nodes_from_documents([doc])
+            # Check if this is a code file based on source path
+            source_path = doc.metadata.get("source", "")
+            is_code_file = any(source_path.endswith(ext) for ext in code_file_exts)
+
+            # Use appropriate parser based on file type
+            parser = self.code_parser if is_code_file else self.node_parser
+            nodes = parser.get_nodes_from_documents([doc])
+
             for node in nodes:
                 all_texts.append(node.get_content())
 
@@ -215,15 +524,23 @@ Examples:
 
     async def build_index(self, args):
         docs_dir = args.docs
-        index_name = args.index_name
+        # Use current directory name if index_name not provided
+        if args.index_name:
+            index_name = args.index_name
+        else:
+            index_name = Path.cwd().name
+            print(f"Using current directory name as index: '{index_name}'")
+
         index_dir = self.indexes_dir / index_name
         index_path = self.get_index_path(index_name)
 
+        print(f"📂 Indexing: {Path(docs_dir).resolve()}")
+
         if index_dir.exists() and not args.force:
             print(f"Index '{index_name}' already exists. Use --force to rebuild.")
             return
 
-        all_texts = self.load_documents(docs_dir)
+        all_texts = self.load_documents(docs_dir, args.file_types)
         if not all_texts:
             print("No documents found")
             return
@@ -235,6 +552,7 @@ Examples:
         builder = LeannBuilder(
             backend_name=args.backend,
             embedding_model=args.embedding_model,
+            embedding_mode=args.embedding_mode,
             graph_degree=args.graph_degree,
             complexity=args.complexity,
             is_compact=args.compact,
@@ -248,6 +566,9 @@ Examples:
         builder.build_index(index_path)
         print(f"Index built at {index_path}")
 
+        # Register this project directory in global registry
+        self.register_project_dir()
+
     async def search_documents(self, args):
         index_name = args.index_name
         query = args.query
@@ -308,6 +629,11 @@ Examples:
                 if not user_input:
                     continue
 
+                # Prepare LLM kwargs with thinking budget if specified
+                llm_kwargs = {}
+                if args.thinking_budget:
+                    llm_kwargs["thinking_budget"] = args.thinking_budget
+
                 response = chat.ask(
                     user_input,
                     top_k=args.top_k,
@@ -316,11 +642,17 @@ Examples:
                     prune_ratio=args.prune_ratio,
                     recompute_embeddings=args.recompute_embeddings,
                     pruning_strategy=args.pruning_strategy,
+                    llm_kwargs=llm_kwargs,
                 )
                 print(f"LEANN: {response}")
         else:
             query = input("Enter your question: ").strip()
             if query:
+                # Prepare LLM kwargs with thinking budget if specified
+                llm_kwargs = {}
+                if args.thinking_budget:
+                    llm_kwargs["thinking_budget"] = args.thinking_budget
+
                 response = chat.ask(
                     query,
                     top_k=args.top_k,
@@ -329,6 +661,7 @@ Examples:
                     prune_ratio=args.prune_ratio,
                     recompute_embeddings=args.recompute_embeddings,
                     pruning_strategy=args.pruning_strategy,
+                    llm_kwargs=llm_kwargs,
                 )
                 print(f"LEANN: {response}")
 

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

@@ -6,6 +6,7 @@ Preserves all optimization parameters to ensure performance
 
 import logging
 import os
+from concurrent.futures import ThreadPoolExecutor, as_completed
 from typing import Any
 
 import numpy as np
@@ -35,7 +36,7 @@ def compute_embeddings(
     Args:
         texts: List of texts to compute embeddings for
         model_name: Model name
-        mode: Computation mode ('sentence-transformers', 'openai', 'mlx')
+        mode: Computation mode ('sentence-transformers', 'openai', 'mlx', 'ollama')
         is_build: Whether this is a build operation (shows progress bar)
         batch_size: Batch size for processing
         adaptive_optimization: Whether to use adaptive optimization based on batch size
@@ -55,6 +56,8 @@ def compute_embeddings(
         return compute_embeddings_openai(texts, model_name)
     elif mode == "mlx":
         return compute_embeddings_mlx(texts, model_name)
+    elif mode == "ollama":
+        return compute_embeddings_ollama(texts, model_name, is_build=is_build)
     else:
         raise ValueError(f"Unsupported embedding mode: {mode}")
 
@@ -365,3 +368,262 @@ def compute_embeddings_mlx(chunks: list[str], model_name: str, batch_size: int =
 
     # Stack numpy arrays
     return np.stack(all_embeddings)
+
+
+def compute_embeddings_ollama(
+    texts: list[str], model_name: str, is_build: bool = False, host: str = "http://localhost:11434"
+) -> np.ndarray:
+    """
+    Compute embeddings using Ollama API.
+
+    Args:
+        texts: List of texts to compute embeddings for
+        model_name: Ollama model name (e.g., "nomic-embed-text", "mxbai-embed-large")
+        is_build: Whether this is a build operation (shows progress bar)
+        host: Ollama host URL (default: http://localhost:11434)
+
+    Returns:
+        Normalized embeddings array, shape: (len(texts), embedding_dim)
+    """
+    try:
+        import requests
+    except ImportError:
+        raise ImportError(
+            "The 'requests' library is required for Ollama embeddings. Install with: uv pip install requests"
+        )
+
+    if not texts:
+        raise ValueError("Cannot compute embeddings for empty text list")
+
+    logger.info(
+        f"Computing embeddings for {len(texts)} texts using Ollama API, model: '{model_name}'"
+    )
+
+    # Check if Ollama is running
+    try:
+        response = requests.get(f"{host}/api/version", timeout=5)
+        response.raise_for_status()
+    except requests.exceptions.ConnectionError:
+        error_msg = (
+            f"❌ Could not connect to Ollama at {host}.\n\n"
+            "Please ensure Ollama is running:\n"
+            "  • macOS/Linux: ollama serve\n"
+            "  • Windows: Make sure Ollama is running in the system tray\n\n"
+            "Installation: https://ollama.com/download"
+        )
+        raise RuntimeError(error_msg)
+    except Exception as e:
+        raise RuntimeError(f"Unexpected error connecting to Ollama: {e}")
+
+    # Check if model exists and provide helpful suggestions
+    try:
+        response = requests.get(f"{host}/api/tags", timeout=5)
+        response.raise_for_status()
+        models = response.json()
+        model_names = [model["name"] for model in models.get("models", [])]
+
+        # Filter for embedding models (models that support embeddings)
+        embedding_models = []
+        suggested_embedding_models = [
+            "nomic-embed-text",
+            "mxbai-embed-large",
+            "bge-m3",
+            "all-minilm",
+            "snowflake-arctic-embed",
+        ]
+
+        for model in model_names:
+            # Check if it's an embedding model (by name patterns or known models)
+            base_name = model.split(":")[0]
+            if any(emb in base_name for emb in ["embed", "bge", "minilm", "e5"]):
+                embedding_models.append(model)
+
+        # Check if model exists (handle versioned names)
+        model_found = any(
+            model_name == name.split(":")[0] or model_name == name for name in model_names
+        )
+
+        if not model_found:
+            error_msg = f"❌ Model '{model_name}' not found in local Ollama.\n\n"
+
+            # Suggest pulling the model
+            error_msg += "📦 To install this embedding model:\n"
+            error_msg += f"   ollama pull {model_name}\n\n"
+
+            # Show available embedding models
+            if embedding_models:
+                error_msg += "✅ Available embedding models:\n"
+                for model in embedding_models[:5]:
+                    error_msg += f"   • {model}\n"
+                if len(embedding_models) > 5:
+                    error_msg += f"   ... and {len(embedding_models) - 5} more\n"
+            else:
+                error_msg += "💡 Popular embedding models to install:\n"
+                for model in suggested_embedding_models[:3]:
+                    error_msg += f"   • ollama pull {model}\n"
+
+            error_msg += "\n📚 Browse more: https://ollama.com/library"
+            raise ValueError(error_msg)
+
+        # Verify the model supports embeddings by testing it
+        try:
+            test_response = requests.post(
+                f"{host}/api/embeddings", json={"model": model_name, "prompt": "test"}, timeout=10
+            )
+            if test_response.status_code != 200:
+                error_msg = (
+                    f"⚠️ Model '{model_name}' exists but may not support embeddings.\n\n"
+                    f"Please use an embedding model like:\n"
+                )
+                for model in suggested_embedding_models[:3]:
+                    error_msg += f"   • {model}\n"
+                raise ValueError(error_msg)
+        except requests.exceptions.RequestException:
+            # If test fails, continue anyway - model might still work
+            pass
+
+    except requests.exceptions.RequestException as e:
+        logger.warning(f"Could not verify model existence: {e}")
+
+    # Process embeddings with optimized concurrent processing
+    import requests
+
+    def get_single_embedding(text_idx_tuple):
+        """Helper function to get embedding for a single text."""
+        text, idx = text_idx_tuple
+        max_retries = 3
+        retry_count = 0
+
+        # Truncate very long texts to avoid API issues
+        truncated_text = text[:8000] if len(text) > 8000 else text
+
+        while retry_count < max_retries:
+            try:
+                response = requests.post(
+                    f"{host}/api/embeddings",
+                    json={"model": model_name, "prompt": truncated_text},
+                    timeout=30,
+                )
+                response.raise_for_status()
+
+                result = response.json()
+                embedding = result.get("embedding")
+
+                if embedding is None:
+                    raise ValueError(f"No embedding returned for text {idx}")
+
+                return idx, embedding
+
+            except requests.exceptions.Timeout:
+                retry_count += 1
+                if retry_count >= max_retries:
+                    logger.warning(f"Timeout for text {idx} after {max_retries} retries")
+                    return idx, None
+
+            except Exception as e:
+                if retry_count >= max_retries - 1:
+                    logger.error(f"Failed to get embedding for text {idx}: {e}")
+                    return idx, None
+                retry_count += 1
+
+        return idx, None
+
+    # Determine if we should use concurrent processing
+    use_concurrent = (
+        len(texts) > 5 and not is_build
+    )  # Don't use concurrent in build mode to avoid overwhelming
+    max_workers = min(4, len(texts))  # Limit concurrent requests to avoid overwhelming Ollama
+
+    all_embeddings = [None] * len(texts)  # Pre-allocate list to maintain order
+    failed_indices = []
+
+    if use_concurrent:
+        logger.info(
+            f"Using concurrent processing with {max_workers} workers for {len(texts)} texts"
+        )
+
+        with ThreadPoolExecutor(max_workers=max_workers) as executor:
+            # Submit all tasks
+            future_to_idx = {
+                executor.submit(get_single_embedding, (text, idx)): idx
+                for idx, text in enumerate(texts)
+            }
+
+            # Add progress bar for concurrent processing
+            try:
+                if is_build or len(texts) > 10:
+                    from tqdm import tqdm
+
+                    futures_iterator = tqdm(
+                        as_completed(future_to_idx),
+                        total=len(texts),
+                        desc="Computing Ollama embeddings",
+                    )
+                else:
+                    futures_iterator = as_completed(future_to_idx)
+            except ImportError:
+                futures_iterator = as_completed(future_to_idx)
+
+            # Collect results as they complete
+            for future in futures_iterator:
+                try:
+                    idx, embedding = future.result()
+                    if embedding is not None:
+                        all_embeddings[idx] = embedding
+                    else:
+                        failed_indices.append(idx)
+                except Exception as e:
+                    idx = future_to_idx[future]
+                    logger.error(f"Exception for text {idx}: {e}")
+                    failed_indices.append(idx)
+
+    else:
+        # Sequential processing with progress bar
+        show_progress = is_build or len(texts) > 10
+
+        try:
+            if show_progress:
+                from tqdm import tqdm
+
+                iterator = tqdm(
+                    enumerate(texts), total=len(texts), desc="Computing Ollama embeddings"
+                )
+            else:
+                iterator = enumerate(texts)
+        except ImportError:
+            iterator = enumerate(texts)
+
+        for idx, text in iterator:
+            result_idx, embedding = get_single_embedding((text, idx))
+            if embedding is not None:
+                all_embeddings[idx] = embedding
+            else:
+                failed_indices.append(idx)
+
+    # Handle failed embeddings
+    if failed_indices:
+        if len(failed_indices) == len(texts):
+            raise RuntimeError("Failed to compute any embeddings")
+
+        logger.warning(f"Failed to compute embeddings for {len(failed_indices)}/{len(texts)} texts")
+
+        # Use zero embeddings as fallback for failed ones
+        valid_embedding = next((e for e in all_embeddings if e is not None), None)
+        if valid_embedding:
+            embedding_dim = len(valid_embedding)
+            for idx in failed_indices:
+                all_embeddings[idx] = [0.0] * embedding_dim
+
+    # Remove None values and convert to numpy array
+    all_embeddings = [e for e in all_embeddings if e is not None]
+
+    # Convert to numpy array and normalize
+    embeddings = np.array(all_embeddings, dtype=np.float32)
+
+    # Normalize embeddings (L2 normalization)
+    norms = np.linalg.norm(embeddings, axis=1, keepdims=True)
+    embeddings = embeddings / (norms + 1e-8)  # Add small epsilon to avoid division by zero
+
+    logger.info(f"Generated {len(embeddings)} embeddings, dimension: {embeddings.shape[1]}")
+
+    return embeddings

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

@@ -6,6 +6,7 @@ import subprocess
 import sys
 import time
 from pathlib import Path
+from typing import Optional
 
 import psutil
 
@@ -182,8 +183,8 @@ class EmbeddingServerManager:
                                        e.g., "leann_backend_diskann.embedding_server"
         """
         self.backend_module_name = backend_module_name
-        self.server_process: subprocess.Popen | None = None
-        self.server_port: int | None = None
+        self.server_process: Optional[subprocess.Popen] = None
+        self.server_port: Optional[int] = None
         self._atexit_registered = False
 
     def start_server(

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

@@ -1,5 +1,5 @@
 from abc import ABC, abstractmethod
-from typing import Any, Literal
+from typing import Any, Literal, Union
 
 import numpy as np
 
@@ -34,7 +34,9 @@ class LeannBackendSearcherInterface(ABC):
         pass
 
     @abstractmethod
-    def _ensure_server_running(self, passages_source_file: str, port: int | None, **kwargs) -> int:
+    def _ensure_server_running(
+        self, passages_source_file: str, port: Union[int, None], **kwargs
+    ) -> int:
         """Ensure server is running"""
         pass
 
@@ -48,7 +50,7 @@ class LeannBackendSearcherInterface(ABC):
         prune_ratio: float = 0.0,
         recompute_embeddings: bool = False,
         pruning_strategy: Literal["global", "local", "proportional"] = "global",
-        zmq_port: int | None = None,
+        zmq_port: Union[int, None] = None,
         **kwargs,
     ) -> dict[str, Any]:
         """Search for nearest neighbors
@@ -74,7 +76,7 @@ class LeannBackendSearcherInterface(ABC):
         self,
         query: str,
         use_server_if_available: bool = True,
-        zmq_port: int | None = None,
+        zmq_port: Union[int, None] = None,
     ) -> np.ndarray:
         """Compute embedding for a query string
 

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

@@ -0,0 +1,176 @@
+#!/usr/bin/env python3
+
+import json
+import subprocess
+import sys
+
+
+def handle_request(request):
+    if request.get("method") == "initialize":
+        return {
+            "jsonrpc": "2.0",
+            "id": request.get("id"),
+            "result": {
+                "capabilities": {"tools": {}},
+                "protocolVersion": "2024-11-05",
+                "serverInfo": {"name": "leann-mcp", "version": "1.0.0"},
+            },
+        }
+
+    elif request.get("method") == "tools/list":
+        return {
+            "jsonrpc": "2.0",
+            "id": request.get("id"),
+            "result": {
+                "tools": [
+                    {
+                        "name": "leann_search",
+                        "description": """🔍 Search code using natural language - like having a coding assistant who knows your entire codebase!
+
+🎯 **Perfect for**:
+- "How does authentication work?" → finds auth-related code
+- "Error handling patterns" → locates try-catch blocks and error logic
+- "Database connection setup" → finds DB initialization code
+- "API endpoint definitions" → locates route handlers
+- "Configuration management" → finds config files and usage
+
+💡 **Pro tip**: Use this before making any changes to understand existing patterns and conventions.""",
+                        "inputSchema": {
+                            "type": "object",
+                            "properties": {
+                                "index_name": {
+                                    "type": "string",
+                                    "description": "Name of the LEANN index to search. Use 'leann_list' first to see available indexes.",
+                                },
+                                "query": {
+                                    "type": "string",
+                                    "description": "Search query - can be natural language (e.g., 'how to handle errors') or technical terms (e.g., 'async function definition')",
+                                },
+                                "top_k": {
+                                    "type": "integer",
+                                    "default": 5,
+                                    "minimum": 1,
+                                    "maximum": 20,
+                                    "description": "Number of search results to return. Use 5-10 for focused results, 15-20 for comprehensive exploration.",
+                                },
+                                "complexity": {
+                                    "type": "integer",
+                                    "default": 32,
+                                    "minimum": 16,
+                                    "maximum": 128,
+                                    "description": "Search complexity level. Use 16-32 for fast searches (recommended), 64+ for higher precision when needed.",
+                                },
+                            },
+                            "required": ["index_name", "query"],
+                        },
+                    },
+                    {
+                        "name": "leann_status",
+                        "description": "📊 Check the health and stats of your code indexes - like a medical checkup for your codebase knowledge!",
+                        "inputSchema": {
+                            "type": "object",
+                            "properties": {
+                                "index_name": {
+                                    "type": "string",
+                                    "description": "Optional: Name of specific index to check. If not provided, shows status of all indexes.",
+                                }
+                            },
+                        },
+                    },
+                    {
+                        "name": "leann_list",
+                        "description": "📋 Show all your indexed codebases - your personal code library! Use this to see what's available for search.",
+                        "inputSchema": {"type": "object", "properties": {}},
+                    },
+                ]
+            },
+        }
+
+    elif request.get("method") == "tools/call":
+        tool_name = request["params"]["name"]
+        args = request["params"].get("arguments", {})
+
+        try:
+            if tool_name == "leann_search":
+                # Validate required parameters
+                if not args.get("index_name") or not args.get("query"):
+                    return {
+                        "jsonrpc": "2.0",
+                        "id": request.get("id"),
+                        "result": {
+                            "content": [
+                                {
+                                    "type": "text",
+                                    "text": "Error: Both index_name and query are required",
+                                }
+                            ]
+                        },
+                    }
+
+                # Build simplified command
+                cmd = [
+                    "leann",
+                    "search",
+                    args["index_name"],
+                    args["query"],
+                    f"--top-k={args.get('top_k', 5)}",
+                    f"--complexity={args.get('complexity', 32)}",
+                ]
+
+                result = subprocess.run(cmd, capture_output=True, text=True)
+
+            elif tool_name == "leann_status":
+                if args.get("index_name"):
+                    # Check specific index status - for now, we'll use leann list and filter
+                    result = subprocess.run(["leann", "list"], capture_output=True, text=True)
+                    # We could enhance this to show more detailed status per index
+                else:
+                    # Show all indexes status
+                    result = subprocess.run(["leann", "list"], capture_output=True, text=True)
+
+            elif tool_name == "leann_list":
+                result = subprocess.run(["leann", "list"], capture_output=True, text=True)
+
+            return {
+                "jsonrpc": "2.0",
+                "id": request.get("id"),
+                "result": {
+                    "content": [
+                        {
+                            "type": "text",
+                            "text": result.stdout
+                            if result.returncode == 0
+                            else f"Error: {result.stderr}",
+                        }
+                    ]
+                },
+            }
+
+        except Exception as e:
+            return {
+                "jsonrpc": "2.0",
+                "id": request.get("id"),
+                "error": {"code": -1, "message": str(e)},
+            }
+
+
+def main():
+    for line in sys.stdin:
+        try:
+            request = json.loads(line.strip())
+            response = handle_request(request)
+            if response:
+                print(json.dumps(response))
+                sys.stdout.flush()
+        except Exception as e:
+            error_response = {
+                "jsonrpc": "2.0",
+                "id": None,
+                "error": {"code": -1, "message": str(e)},
+            }
+            print(json.dumps(error_response))
+            sys.stdout.flush()
+
+
+if __name__ == "__main__":
+    main()

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 Any, Literal
+from typing import Any, Literal, Optional
 
 import numpy as np
 
@@ -169,7 +169,7 @@ class BaseSearcher(LeannBackendSearcherInterface, ABC):
         prune_ratio: float = 0.0,
         recompute_embeddings: bool = False,
         pruning_strategy: Literal["global", "local", "proportional"] = "global",
-        zmq_port: int | None = None,
+        zmq_port: Optional[int] = None,
         **kwargs,
     ) -> dict[str, Any]:
         """

packages/leann-mcp/README.md

@@ -0,0 +1,91 @@
+# 🔥 LEANN Claude Code Integration
+
+Transform your development workflow with intelligent code assistance using LEANN's semantic search directly in Claude Code.
+
+## Prerequisites
+
+**Step 1:** First, complete the basic LEANN installation following the [📦 Installation guide](../../README.md#installation) in the root README:
+
+```bash
+uv venv
+source .venv/bin/activate
+uv pip install leann
+```
+
+**Step 2:** Install LEANN globally for MCP integration:
+```bash
+uv tool install leann-core
+```
+
+This makes the `leann` command available system-wide, which `leann_mcp` requires.
+
+## 🚀 Quick Setup
+
+Add the LEANN MCP server to Claude Code:
+
+```bash
+claude mcp add leann-server -- leann_mcp
+```
+
+## 🛠️ Available Tools
+
+Once connected, you'll have access to these powerful semantic search tools in Claude Code:
+
+- **`leann_list`** - List all available indexes across your projects
+- **`leann_search`** - Perform semantic searches across code and documents
+- **`leann_ask`** - Ask natural language questions and get AI-powered answers from your codebase
+
+## 🎯 Quick Start Example
+
+```bash
+# Build an index for your project (change to your actual path)
+leann build my-project --docs ./
+
+# Start Claude Code
+claude
+```
+
+**Try this in Claude Code:**
+```
+Help me understand this codebase. List available indexes and search for authentication patterns.
+```
+
+<p align="center">
+  <img src="../../assets/claude_code_leann.png" alt="LEANN in Claude Code" width="80%">
+</p>
+
+
+## 🧠 How It Works
+
+The integration consists of three key components working seamlessly together:
+
+- **`leann`** - Core CLI tool for indexing and searching (installed globally via `uv tool install`)
+- **`leann_mcp`** - MCP server that wraps `leann` commands for Claude Code integration
+- **Claude Code** - Calls `leann_mcp`, which executes `leann` commands and returns intelligent results
+
+## 📁 File Support
+
+LEANN understands **30+ file types** including:
+- **Programming**: Python, JavaScript, TypeScript, Java, Go, Rust, C++, C#
+- **Data**: SQL, YAML, JSON, CSV, XML
+- **Documentation**: Markdown, TXT, PDF
+- **And many more!**
+
+## 💾 Storage & Organization
+
+- **Project indexes**: Stored in `.leann/` directory (just like `.git`)
+- **Global registry**: Project tracking at `~/.leann/projects.json`
+- **Multi-project support**: Switch between different codebases seamlessly
+- **Portable**: Transfer indexes between machines with minimal overhead
+
+## 🗑️ Uninstalling
+
+To remove the LEANN MCP server from Claude Code:
+
+```bash
+claude mcp remove leann-server
+```
+To remove LEANN
+```
+uv pip uninstall leann leann-backend-hnsw leann-core
+```

packages/leann/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "leann"
-version = "0.2.1"
+version = "0.2.7"
 description = "LEANN - The smallest vector index in the world. RAG Everything with LEANN!"
 readme = "README.md"
 requires-python = ">=3.9"

pyproject.toml

@@ -32,7 +32,7 @@ dependencies = [
     "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-file>=0.4.0", # Essential for PDF parsing
     # "llama-index-readers-docling",  # Requires Python >= 3.10
     # "llama-index-node-parser-docling",  # Requires Python >= 3.10
     "llama-index-vector-stores-faiss>=0.4.0",
@@ -40,9 +40,12 @@ dependencies = [
     # 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'",
+    "mlx>=0.26.3; sys_platform == 'darwin' and platform_machine == 'arm64'",
+    "mlx-lm>=0.26.0; sys_platform == 'darwin' and platform_machine == 'arm64'",
     "psutil>=5.8.0",
+    "pathspec>=0.12.1",
+    "nbconvert>=7.16.6",
+    "gitignore-parser>=0.1.12",
 ]
 
 [project.optional-dependencies]
@@ -88,7 +91,7 @@ leann-backend-diskann = { path = "packages/leann-backend-diskann", editable = tr
 leann-backend-hnsw = { path = "packages/leann-backend-hnsw", editable = true }
 
 [tool.ruff]
-target-version = "py310"
+target-version = "py39"
 line-length = 100
 extend-exclude = [
     "third_party",