update readme

Fix CI: avoid missing .gitmodules entry by removing gitlink and adding to .gitignore.

.github/ISSUE_TEMPLATE/bug_report.yml

@@ -1,50 +0,0 @@
-name: Bug Report
-description: Report a bug in LEANN
-labels: ["bug"]
-
-body:
-  - type: textarea
-    id: description
-    attributes:
-      label: What happened?
-      description: A clear description of the bug
-    validations:
-      required: true
-
-  - type: textarea
-    id: reproduce
-    attributes:
-      label: How to reproduce
-      placeholder: |
-        1. Install with...
-        2. Run command...
-        3. See error
-    validations:
-      required: true
-
-  - type: textarea
-    id: error
-    attributes:
-      label: Error message
-      description: Paste any error messages
-      render: shell
-
-  - type: input
-    id: version
-    attributes:
-      label: LEANN Version
-      placeholder: "0.1.0"
-    validations:
-      required: true
-
-  - type: dropdown
-    id: os
-    attributes:
-      label: Operating System
-      options:
-        - macOS
-        - Linux
-        - Windows
-        - Docker
-    validations:
-      required: true

.github/ISSUE_TEMPLATE/config.yml

@@ -1,8 +0,0 @@
-blank_issues_enabled: true
-contact_links:
-  - name: Documentation
-    url: https://github.com/LEANN-RAG/LEANN-RAG/tree/main/docs
-    about: Read the docs first
-  - name: Discussions
-    url: https://github.com/LEANN-RAG/LEANN-RAG/discussions
-    about: Ask questions and share ideas

.github/ISSUE_TEMPLATE/feature_request.yml

@@ -1,27 +0,0 @@
-name: Feature Request
-description: Suggest a new feature for LEANN
-labels: ["enhancement"]
-
-body:
-  - type: textarea
-    id: problem
-    attributes:
-      label: What problem does this solve?
-      description: Describe the problem or need
-    validations:
-      required: true
-
-  - type: textarea
-    id: solution
-    attributes:
-      label: Proposed solution
-      description: How would you like this to work?
-    validations:
-      required: true
-
-  - type: textarea
-    id: example
-    attributes:
-      label: Example usage
-      description: Show how the API might look
-      render: python

.github/pull_request_template.md

@@ -1,13 +0,0 @@
-## What does this PR do?
-
-<!-- Brief description of your changes -->
-
-## Related Issues
-
-Fixes #
-
-## Checklist
-
-- [ ] Tests pass (`uv run pytest`)
-- [ ] Code formatted (`ruff format` and `ruff check`)
-- [ ] Pre-commit hooks pass (`pre-commit run --all-files`)

.github/workflows/build-reusable.yml

@@ -54,17 +54,6 @@ jobs:
             python: '3.12'
           - os: ubuntu-22.04
             python: '3.13'
-          # ARM64 Linux builds
-          - os: ubuntu-24.04-arm
-            python: '3.9'
-          - os: ubuntu-24.04-arm
-            python: '3.10'
-          - os: ubuntu-24.04-arm
-            python: '3.11'
-          - os: ubuntu-24.04-arm
-            python: '3.12'
-          - os: ubuntu-24.04-arm
-            python: '3.13'
           - os: macos-14
             python: '3.9'
           - os: macos-14
@@ -119,46 +108,13 @@ jobs:
             pkg-config libabsl-dev libaio-dev libprotobuf-dev \
             patchelf
 
-          # Debug: Show system information
-          echo "🔍 System Information:"
-          echo "Architecture: $(uname -m)"
-          echo "OS: $(uname -a)"
-          echo "CPU info: $(lscpu | head -5)"
-
-          # Install math library based on architecture
-          ARCH=$(uname -m)
-          echo "🔍 Setting up math library for architecture: $ARCH"
-
-          if [[ "$ARCH" == "x86_64" ]]; then
-            # Install Intel MKL for DiskANN on x86_64
-            echo "📦 Installing Intel MKL for x86_64..."
-            wget -q https://registrationcenter-download.intel.com/akdlm/IRC_NAS/79153e0f-74d7-45af-b8c2-258941adf58a/intel-onemkl-2025.0.0.940.sh
-            sudo sh intel-onemkl-2025.0.0.940.sh -a --components intel.oneapi.lin.mkl.devel --action install --eula accept -s
-            source /opt/intel/oneapi/setvars.sh
-            echo "MKLROOT=/opt/intel/oneapi/mkl/latest" >> $GITHUB_ENV
-            echo "LD_LIBRARY_PATH=/opt/intel/oneapi/compiler/latest/linux/compiler/lib/intel64_lin" >> $GITHUB_ENV
-            echo "LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/opt/intel/oneapi/mkl/latest/lib/intel64" >> $GITHUB_ENV
-            echo "✅ Intel MKL installed for x86_64"
-
-            # Debug: Check MKL installation
-            echo "🔍 MKL Installation Check:"
-            ls -la /opt/intel/oneapi/mkl/latest/ || echo "MKL directory not found"
-            ls -la /opt/intel/oneapi/mkl/latest/lib/ || echo "MKL lib directory not found"
-
-          elif [[ "$ARCH" == "aarch64" ]]; then
-            # Use OpenBLAS for ARM64 (MKL installer not compatible with ARM64)
-            echo "📦 Installing OpenBLAS for ARM64..."
-            sudo apt-get install -y libopenblas-dev liblapack-dev liblapacke-dev
-            echo "✅ OpenBLAS installed for ARM64"
-
-            # Debug: Check OpenBLAS installation
-            echo "🔍 OpenBLAS Installation Check:"
-            dpkg -l | grep openblas || echo "OpenBLAS package not found"
-            ls -la /usr/lib/aarch64-linux-gnu/openblas/ || echo "OpenBLAS directory not found"
-          fi
-
-          # Debug: Show final library paths
-          echo "🔍 Final LD_LIBRARY_PATH: $LD_LIBRARY_PATH"
+          # Install Intel MKL for DiskANN
+          wget -q https://registrationcenter-download.intel.com/akdlm/IRC_NAS/79153e0f-74d7-45af-b8c2-258941adf58a/intel-onemkl-2025.0.0.940.sh
+          sudo sh intel-onemkl-2025.0.0.940.sh -a --components intel.oneapi.lin.mkl.devel --action install --eula accept -s
+          source /opt/intel/oneapi/setvars.sh
+          echo "MKLROOT=/opt/intel/oneapi/mkl/latest" >> $GITHUB_ENV
+          echo "LD_LIBRARY_PATH=/opt/intel/oneapi/compiler/latest/linux/compiler/lib/intel64_lin" >> $GITHUB_ENV
+          echo "LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/opt/intel/oneapi/mkl/latest/lib/intel64" >> $GITHUB_ENV
 
       - name: Install system dependencies (macOS)
         if: runner.os == 'macOS'

.gitignore

@@ -22,7 +22,6 @@ demo/experiment_results/**/*.json
 *.sh
 *.txt
 !CMakeLists.txt
-!llms.txt
 latency_breakdown*.json
 experiment_results/eval_results/diskann/*.json
 aws/
@@ -96,8 +95,4 @@ tests/__pytest_cache__/
 tests/__pycache__/
 paru-bin/
 
-CLAUDE.md
-CLAUDE.local.md
-.claude/*.local.*
-.claude/local/*
 benchmarks/data/

.gitmodules

@@ -14,7 +14,3 @@
 [submodule "packages/leann-backend-hnsw/third_party/libzmq"]
 	path = packages/leann-backend-hnsw/third_party/libzmq
 	url = https://github.com/zeromq/libzmq.git
-[submodule "packages/astchunk-leann"]
-	path = packages/astchunk-leann
-	url = git@github.com:yichuan-w/astchunk-leann.git
-	branch = main

README.md

@@ -8,8 +8,6 @@
   <img src="https://img.shields.io/badge/Platform-Ubuntu%20%26%20Arch%20%26%20WSL%20%7C%20macOS%20(ARM64%2FIntel)-lightgrey" alt="Platform">
   <img src="https://img.shields.io/badge/License-MIT-green.svg" alt="MIT License">
   <img src="https://img.shields.io/badge/MCP-Native%20Integration-blue" alt="MCP Integration">
-  <a href="https://join.slack.com/t/leann-e2u9779/shared_invite/zt-3ckd2f6w1-OX08~NN4gkWhh10PRVBj1Q"><img src="https://img.shields.io/badge/Slack-Join-4A154B?logo=slack&logoColor=white" alt="Join Slack">
-  <a href="assets/wechat_user_group.JPG" title="Join WeChat group"><img src="https://img.shields.io/badge/WeChat-Join-2DC100?logo=wechat&logoColor=white" alt="Join WeChat group"></a>
 </p>
 
 <h2 align="center" tabindex="-1" class="heading-element" dir="auto">
@@ -222,8 +220,7 @@ 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.
 
@@ -629,46 +626,6 @@ Options:
 
 </details>
 
-## 🚀 Advanced Features
-
-### 🎯 Metadata Filtering
-
-LEANN supports a simple metadata filtering system to enable sophisticated use cases like document filtering by date/type, code search by file extension, and content management based on custom criteria.
-
-```python
-# Add metadata during indexing
-builder.add_text(
-    "def authenticate_user(token): ...",
-    metadata={"file_extension": ".py", "lines_of_code": 25}
-)
-
-# Search with filters
-results = searcher.search(
-    query="authentication function",
-    metadata_filters={
-        "file_extension": {"==": ".py"},
-        "lines_of_code": {"<": 100}
-    }
-)
-```
-
-**Supported operators**: `==`, `!=`, `<`, `<=`, `>`, `>=`, `in`, `not_in`, `contains`, `starts_with`, `ends_with`, `is_true`, `is_false`
-
-📖 **[Complete Metadata filtering guide →](docs/metadata_filtering.md)**
-
-### 🔍 Grep Search
-
-For exact text matching instead of semantic search, use the `use_grep` parameter:
-
-```python
-# Exact text search
-results = searcher.search("banana‑crocodile", use_grep=True, top_k=1)
-```
-
-**Use cases**: Finding specific code patterns, error messages, function names, or exact phrases where semantic similarity isn't needed.
-
-📖 **[Complete grep search guide →](docs/grep_search.md)**
-
 ## 🏗️ Architecture & How It Works
 
 <p align="center">

apps/browser_rag.py

@@ -10,8 +10,7 @@ from pathlib import Path
 # Add parent directory to path for imports
 sys.path.insert(0, str(Path(__file__).parent))
 
-from base_rag_example import BaseRAGExample
-from chunking import create_text_chunks
+from base_rag_example import BaseRAGExample, create_text_chunks
 
 from .history_data.history import ChromeHistoryReader
 

apps/chunking/__init__.py

@@ -1,38 +1,16 @@
-"""Unified chunking utilities facade.
-
-This module re-exports the packaged utilities from `leann.chunking_utils` so
-that both repo apps (importing `chunking`) and installed wheels share one
-single implementation. When running from the repo without installation, it
-adds the `packages/leann-core/src` directory to `sys.path` as a fallback.
+"""
+Chunking utilities for LEANN RAG applications.
+Provides AST-aware and traditional text chunking functionality.
 """
 
-import sys
-from pathlib import Path
-
-try:
-    from leann.chunking_utils import (
-        CODE_EXTENSIONS,
-        create_ast_chunks,
-        create_text_chunks,
-        create_traditional_chunks,
-        detect_code_files,
-        get_language_from_extension,
-    )
-except Exception:  # pragma: no cover - best-effort fallback for dev environment
-    repo_root = Path(__file__).resolve().parents[2]
-    leann_src = repo_root / "packages" / "leann-core" / "src"
-    if leann_src.exists():
-        sys.path.insert(0, str(leann_src))
-        from leann.chunking_utils import (
-            CODE_EXTENSIONS,
-            create_ast_chunks,
-            create_text_chunks,
-            create_traditional_chunks,
-            detect_code_files,
-            get_language_from_extension,
-        )
-    else:
-        raise
+from .utils import (
+    CODE_EXTENSIONS,
+    create_ast_chunks,
+    create_text_chunks,
+    create_traditional_chunks,
+    detect_code_files,
+    get_language_from_extension,
+)
 
 __all__ = [
     "CODE_EXTENSIONS",

apps/chunking/utils.py

@@ -1,6 +1,6 @@
 """
 Enhanced chunking utilities with AST-aware code chunking support.
-Packaged within leann-core so installed wheels can import it reliably.
+Provides unified interface for both traditional and AST-based text chunking.
 """
 
 import logging
@@ -22,9 +22,30 @@ CODE_EXTENSIONS = {
     ".jsx": "typescript",
 }
 
+# Default chunk parameters for different content types
+DEFAULT_CHUNK_PARAMS = {
+    "code": {
+        "max_chunk_size": 512,
+        "chunk_overlap": 64,
+    },
+    "text": {
+        "chunk_size": 256,
+        "chunk_overlap": 128,
+    },
+}
+
 
 def detect_code_files(documents, code_extensions=None) -> tuple[list, list]:
-    """Separate documents into code files and regular text files."""
+    """
+    Separate documents into code files and regular text files.
+
+    Args:
+        documents: List of LlamaIndex Document objects
+        code_extensions: Dict mapping file extensions to languages (defaults to CODE_EXTENSIONS)
+
+    Returns:
+        Tuple of (code_documents, text_documents)
+    """
     if code_extensions is None:
         code_extensions = CODE_EXTENSIONS
 
@@ -32,10 +53,16 @@ def detect_code_files(documents, code_extensions=None) -> tuple[list, list]:
     text_docs = []
 
     for doc in documents:
-        file_path = doc.metadata.get("file_path", "") or doc.metadata.get("file_name", "")
+        # Get file path from metadata
+        file_path = doc.metadata.get("file_path", "")
+        if not file_path:
+            # Fallback to file_name
+            file_path = doc.metadata.get("file_name", "")
+
         if file_path:
             file_ext = Path(file_path).suffix.lower()
             if file_ext in code_extensions:
+                # Add language info to metadata
                 doc.metadata["language"] = code_extensions[file_ext]
                 doc.metadata["is_code"] = True
                 code_docs.append(doc)
@@ -43,6 +70,7 @@ def detect_code_files(documents, code_extensions=None) -> tuple[list, list]:
                 doc.metadata["is_code"] = False
                 text_docs.append(doc)
         else:
+            # If no file path, treat as text
             doc.metadata["is_code"] = False
             text_docs.append(doc)
 
@@ -51,7 +79,7 @@ def detect_code_files(documents, code_extensions=None) -> tuple[list, list]:
 
 
 def get_language_from_extension(file_path: str) -> Optional[str]:
-    """Return language string from a filename/extension using CODE_EXTENSIONS."""
+    """Get the programming language from file extension."""
     ext = Path(file_path).suffix.lower()
     return CODE_EXTENSIONS.get(ext)
 
@@ -62,26 +90,40 @@ def create_ast_chunks(
     chunk_overlap: int = 64,
     metadata_template: str = "default",
 ) -> list[str]:
-    """Create AST-aware chunks from code documents using astchunk.
+    """
+    Create AST-aware chunks from code documents using astchunk.
 
-    Falls back to traditional chunking if astchunk is unavailable.
+    Args:
+        documents: List of code documents
+        max_chunk_size: Maximum characters per chunk
+        chunk_overlap: Number of AST nodes to overlap between chunks
+        metadata_template: Template for chunk metadata
+
+    Returns:
+        List of text chunks with preserved code structure
     """
     try:
-        from astchunk import ASTChunkBuilder  # optional dependency
+        from astchunk import ASTChunkBuilder
     except ImportError as e:
         logger.error(f"astchunk not available: {e}")
         logger.info("Falling back to traditional chunking for code files")
         return create_traditional_chunks(documents, max_chunk_size, chunk_overlap)
 
     all_chunks = []
+
     for doc in documents:
+        # Get language from metadata (set by detect_code_files)
         language = doc.metadata.get("language")
         if not language:
-            logger.warning("No language detected; falling back to traditional chunking")
-            all_chunks.extend(create_traditional_chunks([doc], max_chunk_size, chunk_overlap))
+            logger.warning(
+                "No language detected for document, falling back to traditional chunking"
+            )
+            traditional_chunks = create_traditional_chunks([doc], max_chunk_size, chunk_overlap)
+            all_chunks.extend(traditional_chunks)
             continue
 
         try:
+            # Configure astchunk
             configs = {
                 "max_chunk_size": max_chunk_size,
                 "language": language,
@@ -89,6 +131,7 @@ def create_ast_chunks(
                 "chunk_overlap": chunk_overlap if chunk_overlap > 0 else 0,
             }
 
+            # Add repository-level metadata if available
             repo_metadata = {
                 "file_path": doc.metadata.get("file_path", ""),
                 "file_name": doc.metadata.get("file_name", ""),
@@ -97,13 +140,17 @@ def create_ast_chunks(
             }
             configs["repo_level_metadata"] = repo_metadata
 
+            # Create chunk builder and process
             chunk_builder = ASTChunkBuilder(**configs)
             code_content = doc.get_content()
+
             if not code_content or not code_content.strip():
                 logger.warning("Empty code content, skipping")
                 continue
 
             chunks = chunk_builder.chunkify(code_content)
+
+            # Extract text content from chunks
             for chunk in chunks:
                 if hasattr(chunk, "text"):
                     chunk_text = chunk.text
@@ -112,6 +159,7 @@ def create_ast_chunks(
                 elif isinstance(chunk, str):
                     chunk_text = chunk
                 else:
+                    # Try to convert to string
                     chunk_text = str(chunk)
 
                 if chunk_text and chunk_text.strip():
@@ -120,10 +168,12 @@ def create_ast_chunks(
             logger.info(
                 f"Created {len(chunks)} AST chunks from {language} file: {doc.metadata.get('file_name', 'unknown')}"
             )
+
         except Exception as e:
             logger.warning(f"AST chunking failed for {language} file: {e}")
             logger.info("Falling back to traditional chunking")
-            all_chunks.extend(create_traditional_chunks([doc], max_chunk_size, chunk_overlap))
+            traditional_chunks = create_traditional_chunks([doc], max_chunk_size, chunk_overlap)
+            all_chunks.extend(traditional_chunks)
 
     return all_chunks
 
@@ -131,10 +181,23 @@ def create_ast_chunks(
 def create_traditional_chunks(
     documents, chunk_size: int = 256, chunk_overlap: int = 128
 ) -> list[str]:
-    """Create traditional text chunks using LlamaIndex SentenceSplitter."""
+    """
+    Create traditional text chunks using LlamaIndex SentenceSplitter.
+
+    Args:
+        documents: List of documents to chunk
+        chunk_size: Size of each chunk in characters
+        chunk_overlap: Overlap between chunks
+
+    Returns:
+        List of text chunks
+    """
+    # Handle invalid chunk_size values
     if chunk_size <= 0:
         logger.warning(f"Invalid chunk_size={chunk_size}, using default value of 256")
         chunk_size = 256
+
+    # Ensure chunk_overlap is not negative and not larger than chunk_size
     if chunk_overlap < 0:
         chunk_overlap = 0
     if chunk_overlap >= chunk_size:
@@ -152,9 +215,12 @@ def create_traditional_chunks(
         try:
             nodes = node_parser.get_nodes_from_documents([doc])
             if nodes:
-                all_texts.extend(node.get_content() for node in nodes)
+                chunk_texts = [node.get_content() for node in nodes]
+                all_texts.extend(chunk_texts)
+                logger.debug(f"Created {len(chunk_texts)} traditional chunks from document")
         except Exception as e:
             logger.error(f"Traditional chunking failed for document: {e}")
+            # As last resort, add the raw content
             content = doc.get_content()
             if content and content.strip():
                 all_texts.append(content.strip())
@@ -172,13 +238,32 @@ def create_text_chunks(
     code_file_extensions: Optional[list[str]] = None,
     ast_fallback_traditional: bool = True,
 ) -> list[str]:
-    """Create text chunks from documents with optional AST support for code files."""
+    """
+    Create text chunks from documents with optional AST support for code files.
+
+    Args:
+        documents: List of LlamaIndex Document objects
+        chunk_size: Size for traditional text chunks
+        chunk_overlap: Overlap for traditional text chunks
+        use_ast_chunking: Whether to use AST chunking for code files
+        ast_chunk_size: Size for AST chunks
+        ast_chunk_overlap: Overlap for AST chunks
+        code_file_extensions: Custom list of code file extensions
+        ast_fallback_traditional: Fall back to traditional chunking on AST errors
+
+    Returns:
+        List of text chunks
+    """
     if not documents:
         logger.warning("No documents provided for chunking")
         return []
 
+    # Create a local copy of supported extensions for this function call
     local_code_extensions = CODE_EXTENSIONS.copy()
+
+    # Update supported extensions if provided
     if code_file_extensions:
+        # Map extensions to languages (simplified mapping)
         ext_mapping = {
             ".py": "python",
             ".java": "java",
@@ -188,32 +273,47 @@ def create_text_chunks(
         }
         for ext in code_file_extensions:
             if ext.lower() not in local_code_extensions:
+                # Try to guess language from extension
                 if ext.lower() in ext_mapping:
                     local_code_extensions[ext.lower()] = ext_mapping[ext.lower()]
                 else:
                     logger.warning(f"Unsupported extension {ext}, will use traditional chunking")
 
     all_chunks = []
+
     if use_ast_chunking:
+        # Separate code and text documents using local extensions
         code_docs, text_docs = detect_code_files(documents, local_code_extensions)
+
+        # Process code files with AST chunking
         if code_docs:
+            logger.info(f"Processing {len(code_docs)} code files with AST chunking")
             try:
-                all_chunks.extend(
-                    create_ast_chunks(
-                        code_docs, max_chunk_size=ast_chunk_size, chunk_overlap=ast_chunk_overlap
-                    )
+                ast_chunks = create_ast_chunks(
+                    code_docs, max_chunk_size=ast_chunk_size, chunk_overlap=ast_chunk_overlap
                 )
+                all_chunks.extend(ast_chunks)
+                logger.info(f"Created {len(ast_chunks)} AST chunks from code files")
             except Exception as e:
                 logger.error(f"AST chunking failed: {e}")
                 if ast_fallback_traditional:
-                    all_chunks.extend(
-                        create_traditional_chunks(code_docs, chunk_size, chunk_overlap)
+                    logger.info("Falling back to traditional chunking for code files")
+                    traditional_code_chunks = create_traditional_chunks(
+                        code_docs, chunk_size, chunk_overlap
                     )
+                    all_chunks.extend(traditional_code_chunks)
                 else:
                     raise
+
+        # Process text files with traditional chunking
         if text_docs:
-            all_chunks.extend(create_traditional_chunks(text_docs, chunk_size, chunk_overlap))
+            logger.info(f"Processing {len(text_docs)} text files with traditional chunking")
+            text_chunks = create_traditional_chunks(text_docs, chunk_size, chunk_overlap)
+            all_chunks.extend(text_chunks)
+            logger.info(f"Created {len(text_chunks)} traditional chunks from text files")
     else:
+        # Use traditional chunking for all files
+        logger.info(f"Processing {len(documents)} documents with traditional chunking")
         all_chunks = create_traditional_chunks(documents, chunk_size, chunk_overlap)
 
     logger.info(f"Total chunks created: {len(all_chunks)}")

apps/email_rag.py

@@ -9,8 +9,7 @@ from pathlib import Path
 # Add parent directory to path for imports
 sys.path.insert(0, str(Path(__file__).parent))
 
-from base_rag_example import BaseRAGExample
-from chunking import create_text_chunks
+from base_rag_example import BaseRAGExample, create_text_chunks
 
 from .email_data.LEANN_email_reader import EmlxReader
 

apps/history_data/history.py

@@ -74,7 +74,7 @@ class ChromeHistoryReader(BaseReader):
                 if count >= max_count and max_count > 0:
                     break
 
-                last_visit, url, title, visit_count, typed_count, _hidden = row
+                last_visit, url, title, visit_count, typed_count, hidden = row
 
                 # Create document content with metadata embedded in text
                 doc_content = f"""

docs/ast_chunking_guide.md

@@ -26,21 +26,6 @@ leann build my-code-index --docs ./src --use-ast-chunking
 uv pip install -e "."
 ```
 
-#### For normal users (PyPI install)
-- Use `pip install leann` or `uv pip install leann`.
-- `astchunk` is pulled automatically from PyPI as a dependency; no extra steps.
-
-#### For developers (from source, editable)
-```bash
-git clone https://github.com/yichuan-w/LEANN.git leann
-cd leann
-git submodule update --init --recursive
-uv sync
-```
-- This repo vendors `astchunk` as a git submodule at `packages/astchunk-leann` (our fork).
-- `[tool.uv.sources]` maps the `astchunk` package to that path in editable mode.
-- You can edit code under `packages/astchunk-leann` and Python will use your changes immediately (no separate `pip install astchunk` needed).
-
 ## Best Practices
 
 ### When to Use AST Chunking

docs/grep_search.md

@@ -1,149 +0,0 @@
-# LEANN Grep Search Usage Guide
-
-## Overview
-
-LEANN's grep search functionality provides exact text matching for finding specific code patterns, error messages, function names, or exact phrases in your indexed documents.
-
-## Basic Usage
-
-### Simple Grep Search
-
-```python
-from leann.api import LeannSearcher
-
-searcher = LeannSearcher("your_index_path")
-
-# Exact text search
-results = searcher.search("def authenticate_user", use_grep=True, top_k=5)
-
-for result in results:
-    print(f"Score: {result.score}")
-    print(f"Text: {result.text[:100]}...")
-    print("-" * 40)
-```
-
-### Comparison: Semantic vs Grep Search
-
-```python
-# Semantic search - finds conceptually similar content
-semantic_results = searcher.search("machine learning algorithms", top_k=3)
-
-# Grep search - finds exact text matches
-grep_results = searcher.search("def train_model", use_grep=True, top_k=3)
-```
-
-## When to Use Grep Search
-
-### Use Cases
-
-- **Code Search**: Finding specific function definitions, class names, or variable references
-- **Error Debugging**: Locating exact error messages or stack traces
-- **Documentation**: Finding specific API endpoints or exact terminology
-
-### Examples
-
-```python
-# Find function definitions
-functions = searcher.search("def __init__", use_grep=True)
-
-# Find import statements
-imports = searcher.search("from sklearn import", use_grep=True)
-
-# Find specific error types
-errors = searcher.search("FileNotFoundError", use_grep=True)
-
-# Find TODO comments
-todos = searcher.search("TODO:", use_grep=True)
-
-# Find configuration entries
-configs = searcher.search("server_port=", use_grep=True)
-```
-
-## Technical Details
-
-### How It Works
-
-1. **File Location**: Grep search operates on the raw text stored in `.jsonl` files
-2. **Command Execution**: Uses the system `grep` command with case-insensitive search
-3. **Result Processing**: Parses JSON lines and extracts text and metadata
-4. **Scoring**: Simple frequency-based scoring based on query term occurrences
-
-### Search Process
-
-```
-Query: "def train_model"
-  ↓
-grep -i -n "def train_model" documents.leann.passages.jsonl
-  ↓
-Parse matching JSON lines
-  ↓
-Calculate scores based on term frequency
-  ↓
-Return top_k results
-```
-
-### Scoring Algorithm
-
-```python
-# Term frequency in document
-score = text.lower().count(query.lower())
-```
-
-Results are ranked by score (highest first), with higher scores indicating more occurrences of the search term.
-
-## Error Handling
-
-### Common Issues
-
-#### Grep Command Not Found
-```
-RuntimeError: grep command not found. Please install grep or use semantic search.
-```
-
-**Solution**: Install grep on your system:
-- **Ubuntu/Debian**: `sudo apt-get install grep`
-- **macOS**: grep is pre-installed
-- **Windows**: Use WSL or install grep via Git Bash/MSYS2
-
-#### No Results Found
-```python
-# Check if your query exists in the raw data
-results = searcher.search("your_query", use_grep=True)
-if not results:
-    print("No exact matches found. Try:")
-    print("1. Check spelling and case")
-    print("2. Use partial terms")
-    print("3. Switch to semantic search")
-```
-
-## Complete Example
-
-```python
-#!/usr/bin/env python3
-"""
-Grep Search Example
-Demonstrates grep search for exact text matching.
-"""
-
-from leann.api import LeannSearcher
-
-def demonstrate_grep_search():
-    # Initialize searcher
-    searcher = LeannSearcher("my_index")
-
-    print("=== Function Search ===")
-    functions = searcher.search("def __init__", use_grep=True, top_k=5)
-    for i, result in enumerate(functions, 1):
-        print(f"{i}. Score: {result.score}")
-        print(f"   Preview: {result.text[:60]}...")
-        print()
-
-    print("=== Error Search ===")
-    errors = searcher.search("FileNotFoundError", use_grep=True, top_k=3)
-    for result in errors:
-        print(f"Content: {result.text.strip()}")
-        print("-" * 40)
-
-if __name__ == "__main__":
-    demonstrate_grep_search()
-```

docs/metadata_filtering.md

@@ -1,300 +0,0 @@
-# LEANN Metadata Filtering Usage Guide
-
-## Overview
-
-Leann possesses metadata filtering capabilities that allow you to filter search results based on arbitrary metadata fields set during chunking. This feature enables use cases like spoiler-free book search, document filtering by date/type, code search by file type, and potentially much more.
-
-## Basic Usage
-
-### Adding Metadata to Your Documents
-
-When building your index, add metadata to each text chunk:
-
-```python
-from leann.api import LeannBuilder
-
-builder = LeannBuilder("hnsw")
-
-# Add text with metadata
-builder.add_text(
-    text="Chapter 1: Alice falls down the rabbit hole",
-    metadata={
-        "chapter": 1,
-        "character": "Alice",
-        "themes": ["adventure", "curiosity"],
-        "word_count": 150
-    }
-)
-
-builder.build_index("alice_in_wonderland_index")
-```
-
-### Searching with Metadata Filters
-
-Use the `metadata_filters` parameter in search calls:
-
-```python
-from leann.api import LeannSearcher
-
-searcher = LeannSearcher("alice_in_wonderland_index")
-
-# Search with filters
-results = searcher.search(
-    query="What happens to Alice?",
-    top_k=10,
-    metadata_filters={
-        "chapter": {"<=": 5},           # Only chapters 1-5
-        "spoiler_level": {"!=": "high"} # No high spoilers
-    }
-)
-```
-
-## Filter Syntax
-
-### Basic Structure
-
-```python
-metadata_filters = {
-    "field_name": {"operator": value},
-    "another_field": {"operator": value}
-}
-```
-
-### Supported Operators
-
-#### Comparison Operators
-- `"=="`: Equal to
-- `"!="`: Not equal to
-- `"<"`: Less than
-- `"<="`: Less than or equal
-- `">"`: Greater than
-- `">="`: Greater than or equal
-
-```python
-# Examples
-{"chapter": {"==": 1}}           # Exactly chapter 1
-{"page": {">": 100}}            # Pages after 100
-{"rating": {">=": 4.0}}         # Rating 4.0 or higher
-{"word_count": {"<": 500}}      # Short passages
-```
-
-#### Membership Operators
-- `"in"`: Value is in list
-- `"not_in"`: Value is not in list
-
-```python
-# Examples
-{"character": {"in": ["Alice", "Bob"]}}      # Alice OR Bob
-{"genre": {"not_in": ["horror", "thriller"]}} # Exclude genres
-{"tags": {"in": ["fiction", "adventure"]}}   # Any of these tags
-```
-
-#### String Operators
-- `"contains"`: String contains substring
-- `"starts_with"`: String starts with prefix
-- `"ends_with"`: String ends with suffix
-
-```python
-# Examples
-{"title": {"contains": "alice"}}        # Title contains "alice"
-{"filename": {"ends_with": ".py"}}      # Python files
-{"author": {"starts_with": "Dr."}}      # Authors with "Dr." prefix
-```
-
-#### Boolean Operators
-- `"is_true"`: Field is truthy
-- `"is_false"`: Field is falsy
-
-```python
-# Examples
-{"is_published": {"is_true": True}}     # Published content
-{"is_draft": {"is_false": False}}       # Not drafts
-```
-
-### Multiple Operators on Same Field
-
-You can apply multiple operators to the same field (AND logic):
-
-```python
-metadata_filters = {
-    "word_count": {
-        ">=": 100,    # At least 100 words
-        "<=": 500     # At most 500 words
-    }
-}
-```
-
-### Compound Filters
-
-Multiple fields are combined with AND logic:
-
-```python
-metadata_filters = {
-    "chapter": {"<=": 10},              # Up to chapter 10
-    "character": {"==": "Alice"},       # About Alice
-    "spoiler_level": {"!=": "high"}     # No major spoilers
-}
-```
-
-## Use Case Examples
-
-### 1. Spoiler-Free Book Search
-
-```python
-# Reader has only read up to chapter 5
-def search_spoiler_free(query, max_chapter):
-    return searcher.search(
-        query=query,
-        metadata_filters={
-            "chapter": {"<=": max_chapter},
-            "spoiler_level": {"in": ["none", "low"]}
-        }
-    )
-
-results = search_spoiler_free("What happens to Alice?", max_chapter=5)
-```
-
-### 2. Document Management by Date
-
-```python
-# Find recent documents
-recent_docs = searcher.search(
-    query="project updates",
-    metadata_filters={
-        "date": {">=": "2024-01-01"},
-        "document_type": {"==": "report"}
-    }
-)
-```
-
-### 3. Code Search by File Type
-
-```python
-# Search only Python files
-python_code = searcher.search(
-    query="authentication function",
-    metadata_filters={
-        "file_extension": {"==": ".py"},
-        "lines_of_code": {"<": 100}
-    }
-)
-```
-
-### 4. Content Filtering by Audience
-
-```python
-# Age-appropriate content
-family_content = searcher.search(
-    query="adventure stories",
-    metadata_filters={
-        "age_rating": {"in": ["G", "PG"]},
-        "content_warnings": {"not_in": ["violence", "adult_themes"]}
-    }
-)
-```
-
-### 5. Multi-Book Series Management
-
-```python
-# Search across first 3 books only
-early_series = searcher.search(
-    query="character development",
-    metadata_filters={
-        "series": {"==": "Harry Potter"},
-        "book_number": {"<=": 3}
-    }
-)
-```
-
-## Running the Example
-
-You can see metadata filtering in action with our spoiler-free book RAG example:
-
-```bash
-# Don't forget to set up the environment
-uv venv
-source .venv/bin/activate
-
-# Set your OpenAI API key (required for embeddings, but you can update the example locally and use ollama instead)
-export OPENAI_API_KEY="your-api-key-here"
-
-# Run the spoiler-free book RAG example
-uv run examples/spoiler_free_book_rag.py
-```
-
-This example demonstrates:
-- Building an index with metadata (chapter numbers, characters, themes, locations)
-- Searching with filters to avoid spoilers (e.g., only show results up to chapter 5)
-- Different scenarios for readers at various points in the book
-
-The example uses Alice's Adventures in Wonderland as sample data and shows how you can search for information without revealing plot points from later chapters.
-
-## Advanced Patterns
-
-### Custom Chunking with metadata
-
-```python
-def chunk_book_with_metadata(book_text, book_info):
-    chunks = []
-
-    for chapter_num, chapter_text in parse_chapters(book_text):
-        # Extract entities, themes, etc.
-        characters = extract_characters(chapter_text)
-        themes = classify_themes(chapter_text)
-        spoiler_level = assess_spoiler_level(chapter_text, chapter_num)
-
-        # Create chunks with rich metadata
-        for paragraph in split_paragraphs(chapter_text):
-            chunks.append({
-                "text": paragraph,
-                "metadata": {
-                    "book_title": book_info["title"],
-                    "chapter": chapter_num,
-                    "characters": characters,
-                    "themes": themes,
-                    "spoiler_level": spoiler_level,
-                    "word_count": len(paragraph.split()),
-                    "reading_level": calculate_reading_level(paragraph)
-                }
-            })
-
-    return chunks
-```
-
-## Performance Considerations
-
-### Efficient Filtering Strategies
-
-1. **Post-search filtering**: Applies filters after vector search, which should be efficient for typical result sets (10-100 results).
-
-2. **Metadata design**: Keep metadata fields simple and avoid deeply nested structures.
-
-### Best Practices
-
-1. **Consistent metadata schema**: Use consistent field names and value types across your documents.
-
-2. **Reasonable metadata size**: Keep metadata reasonably sized to avoid storage overhead.
-
-3. **Type consistency**: Use consistent data types for the same fields (e.g., always integers for chapter numbers).
-
-4. **Index multiple granularities**: Consider chunking at different levels (paragraph, section, chapter) with appropriate metadata.
-
-### Adding Metadata to Existing Indices
-
-To add metadata filtering to existing indices, you'll need to rebuild them with metadata:
-
-```python
-# Read existing passages and add metadata
-def add_metadata_to_existing_chunks(chunks):
-    for chunk in chunks:
-        # Extract or assign metadata based on content
-        chunk["metadata"] = extract_metadata(chunk["text"])
-    return chunks
-
-# Rebuild index with metadata
-enhanced_chunks = add_metadata_to_existing_chunks(existing_chunks)
-builder = LeannBuilder("hnsw")
-for chunk in enhanced_chunks:
-    builder.add_text(chunk["text"], chunk["metadata"])
-builder.build_index("enhanced_index")
-```

examples/grep_search_example.py

@@ -1,35 +0,0 @@
-"""
-Grep Search Example
-
-Shows how to use grep-based text search instead of semantic search.
-Useful when you need exact text matches rather than meaning-based results.
-"""
-
-from leann import LeannSearcher
-
-# Load your index
-searcher = LeannSearcher("my-documents.leann")
-
-# Regular semantic search
-print("=== Semantic Search ===")
-results = searcher.search("machine learning algorithms", top_k=3)
-for result in results:
-    print(f"Score: {result.score:.3f}")
-    print(f"Text: {result.text[:80]}...")
-    print()
-
-# Grep-based search for exact text matches
-print("=== Grep Search ===")
-results = searcher.search("def train_model", top_k=3, use_grep=True)
-for result in results:
-    print(f"Score: {result.score}")
-    print(f"Text: {result.text[:80]}...")
-    print()
-
-# Find specific error messages
-error_results = searcher.search("FileNotFoundError", use_grep=True)
-print(f"Found {len(error_results)} files mentioning FileNotFoundError")
-
-# Search for function definitions
-func_results = searcher.search("class SearchResult", use_grep=True, top_k=5)
-print(f"Found {len(func_results)} class definitions")

examples/spoiler_free_book_rag.py

@@ -1,250 +0,0 @@
-#!/usr/bin/env python3
-"""
-Spoiler-Free Book RAG Example using LEANN Metadata Filtering
-
-This example demonstrates how to use LEANN's metadata filtering to create
-a spoiler-free book RAG system where users can search for information
-up to a specific chapter they've read.
-
-Usage:
-    python spoiler_free_book_rag.py
-"""
-
-import os
-import sys
-from typing import Any, Optional
-
-# Add LEANN to path (adjust path as needed)
-sys.path.insert(0, os.path.join(os.path.dirname(__file__), "../packages/leann-core/src"))
-
-from leann.api import LeannBuilder, LeannSearcher
-
-
-def chunk_book_with_metadata(book_title: str = "Sample Book") -> list[dict[str, Any]]:
-    """
-    Create sample book chunks with metadata for demonstration.
-
-    In a real implementation, this would parse actual book files (epub, txt, etc.)
-    and extract chapter boundaries, character mentions, etc.
-
-    Args:
-        book_title: Title of the book
-
-    Returns:
-        List of chunk dictionaries with text and metadata
-    """
-    # Sample book chunks with metadata
-    # In practice, you'd use proper text processing libraries
-
-    sample_chunks = [
-        {
-            "text": "Alice was beginning to get very tired of sitting by her sister on the bank, and of having nothing to do.",
-            "metadata": {
-                "book": book_title,
-                "chapter": 1,
-                "page": 1,
-                "characters": ["Alice", "Sister"],
-                "themes": ["boredom", "curiosity"],
-                "location": "riverbank",
-            },
-        },
-        {
-            "text": "So she was considering in her own mind (as well as she could, for the hot day made her feel very sleepy and stupid), whether the pleasure of making a daisy-chain would be worth the trouble of getting up and picking the daisies, when suddenly a White Rabbit with pink eyes ran close by her.",
-            "metadata": {
-                "book": book_title,
-                "chapter": 1,
-                "page": 2,
-                "characters": ["Alice", "White Rabbit"],
-                "themes": ["decision", "surprise", "magic"],
-                "location": "riverbank",
-            },
-        },
-        {
-            "text": "Alice found herself falling down a very deep well. Either the well was very deep, or she fell very slowly, for she had plenty of time as she fell to look about her and to wonder what was going to happen next.",
-            "metadata": {
-                "book": book_title,
-                "chapter": 2,
-                "page": 15,
-                "characters": ["Alice"],
-                "themes": ["falling", "wonder", "transformation"],
-                "location": "rabbit hole",
-            },
-        },
-        {
-            "text": "Alice meets the Cheshire Cat, who tells her that everyone in Wonderland is mad, including Alice herself.",
-            "metadata": {
-                "book": book_title,
-                "chapter": 6,
-                "page": 85,
-                "characters": ["Alice", "Cheshire Cat"],
-                "themes": ["madness", "philosophy", "identity"],
-                "location": "Duchess's house",
-            },
-        },
-        {
-            "text": "At the Queen's croquet ground, Alice witnesses the absurd trial that reveals the arbitrary nature of Wonderland's justice system.",
-            "metadata": {
-                "book": book_title,
-                "chapter": 8,
-                "page": 120,
-                "characters": ["Alice", "Queen of Hearts", "King of Hearts"],
-                "themes": ["justice", "absurdity", "authority"],
-                "location": "Queen's court",
-            },
-        },
-        {
-            "text": "Alice realizes that Wonderland was all a dream, even the Rabbit, as she wakes up on the riverbank next to her sister.",
-            "metadata": {
-                "book": book_title,
-                "chapter": 12,
-                "page": 180,
-                "characters": ["Alice", "Sister", "Rabbit"],
-                "themes": ["revelation", "reality", "growth"],
-                "location": "riverbank",
-            },
-        },
-    ]
-
-    return sample_chunks
-
-
-def build_spoiler_free_index(book_chunks: list[dict[str, Any]], index_name: str) -> str:
-    """
-    Build a LEANN index with book chunks that include spoiler metadata.
-
-    Args:
-        book_chunks: List of book chunks with metadata
-        index_name: Name for the index
-
-    Returns:
-        Path to the built index
-    """
-    print(f"📚 Building spoiler-free book index: {index_name}")
-
-    # Initialize LEANN builder
-    builder = LeannBuilder(
-        backend_name="hnsw", embedding_model="text-embedding-3-small", embedding_mode="openai"
-    )
-
-    # Add each chunk with its metadata
-    for chunk in book_chunks:
-        builder.add_text(text=chunk["text"], metadata=chunk["metadata"])
-
-    # Build the index
-    index_path = f"{index_name}_book_index"
-    builder.build_index(index_path)
-
-    print(f"✅ Index built successfully: {index_path}")
-    return index_path
-
-
-def spoiler_free_search(
-    index_path: str,
-    query: str,
-    max_chapter: int,
-    character_filter: Optional[list[str]] = None,
-) -> list[dict[str, Any]]:
-    """
-    Perform a spoiler-free search on the book index.
-
-    Args:
-        index_path: Path to the LEANN index
-        query: Search query
-        max_chapter: Maximum chapter number to include
-        character_filter: Optional list of characters to focus on
-
-    Returns:
-        List of search results safe for the reader
-    """
-    print(f"🔍 Searching: '{query}' (up to chapter {max_chapter})")
-
-    searcher = LeannSearcher(index_path)
-
-    metadata_filters = {"chapter": {"<=": max_chapter}}
-
-    if character_filter:
-        metadata_filters["characters"] = {"contains": character_filter[0]}
-
-    results = searcher.search(query=query, top_k=10, metadata_filters=metadata_filters)
-
-    return results
-
-
-def demo_spoiler_free_rag():
-    """
-    Demonstrate the spoiler-free book RAG system.
-    """
-    print("🎭 Spoiler-Free Book RAG Demo")
-    print("=" * 40)
-
-    # Step 1: Prepare book data
-    book_title = "Alice's Adventures in Wonderland"
-    book_chunks = chunk_book_with_metadata(book_title)
-
-    print(f"📖 Loaded {len(book_chunks)} chunks from '{book_title}'")
-
-    # Step 2: Build the index (in practice, this would be done once)
-    try:
-        index_path = build_spoiler_free_index(book_chunks, "alice_wonderland")
-    except Exception as e:
-        print(f"❌ Failed to build index (likely missing dependencies): {e}")
-        print(
-            "💡 This demo shows the filtering logic - actual indexing requires LEANN dependencies"
-        )
-        return
-
-    # Step 3: Demonstrate various spoiler-free searches
-    search_scenarios = [
-        {
-            "description": "Reader who has only read Chapter 1",
-            "query": "What can you tell me about the rabbit?",
-            "max_chapter": 1,
-        },
-        {
-            "description": "Reader who has read up to Chapter 5",
-            "query": "Tell me about Alice's adventures",
-            "max_chapter": 5,
-        },
-        {
-            "description": "Reader who has read most of the book",
-            "query": "What does the Cheshire Cat represent?",
-            "max_chapter": 10,
-        },
-        {
-            "description": "Reader who has read the whole book",
-            "query": "What can you tell me about the rabbit?",
-            "max_chapter": 12,
-        },
-    ]
-
-    for scenario in search_scenarios:
-        print(f"\n📚 Scenario: {scenario['description']}")
-        print(f"   Query: {scenario['query']}")
-
-        try:
-            results = spoiler_free_search(
-                index_path=index_path,
-                query=scenario["query"],
-                max_chapter=scenario["max_chapter"],
-            )
-
-            print(f"   📄 Found {len(results)} results:")
-            for i, result in enumerate(results[:3], 1):  # Show top 3
-                chapter = result.metadata.get("chapter", "?")
-                location = result.metadata.get("location", "?")
-                print(f"      {i}. Chapter {chapter} ({location}): {result.text[:80]}...")
-
-        except Exception as e:
-            print(f"   ❌ Search failed: {e}")
-
-
-if __name__ == "__main__":
-    print("📚 LEANN Spoiler-Free Book RAG Example")
-    print("=====================================")
-
-    try:
-        demo_spoiler_free_rag()
-    except ImportError as e:
-        print(f"❌ Cannot run demo due to missing dependencies: {e}")
-    except Exception as e:
-        print(f"❌ Error running demo: {e}")

llms.txt

@@ -1,28 +0,0 @@
-# llms.txt — LEANN MCP and Agent Integration
-product: LEANN
-homepage: https://github.com/yichuan-w/LEANN
-contact: https://github.com/yichuan-w/LEANN/issues
-
-# Installation
-install: uv tool install leann-core --with leann
-
-# MCP Server Entry Point
-mcp.server: leann_mcp
-mcp.protocol_version: 2024-11-05
-
-# Tools
-mcp.tools: leann_list, leann_search
-
-mcp.tool.leann_list.description: List available LEANN indexes
-mcp.tool.leann_list.input: {}
-
-mcp.tool.leann_search.description: Semantic search across a named LEANN index
-mcp.tool.leann_search.input.index_name: string, required
-mcp.tool.leann_search.input.query: string, required
-mcp.tool.leann_search.input.top_k: integer, optional, default=5, min=1, max=20
-mcp.tool.leann_search.input.complexity: integer, optional, default=32, min=16, max=128
-
-# Notes
-note: Build indexes with `leann build <name> --docs <files...>` before searching.
-example.add: claude mcp add --scope user leann-server -- leann_mcp
-example.verify: claude mcp list | cat

packages/leann-backend-diskann/pyproject.toml

@@ -4,8 +4,8 @@ build-backend = "scikit_build_core.build"
 
 [project]
 name = "leann-backend-diskann"
-version = "0.3.4"
-dependencies = ["leann-core==0.3.4", "numpy", "protobuf>=3.19.0"]
+version = "0.3.2"
+dependencies = ["leann-core==0.3.2", "numpy", "protobuf>=3.19.0"]
 
 [tool.scikit-build]
 # Key: simplified CMake path

packages/leann-backend-hnsw/CMakeLists.txt

@@ -49,28 +49,9 @@ set(BUILD_TESTING OFF CACHE BOOL "" FORCE)
 set(FAISS_ENABLE_C_API OFF CACHE BOOL "" FORCE)
 set(FAISS_OPT_LEVEL "generic" CACHE STRING "" FORCE)
 
-# Disable x86-specific SIMD optimizations (important for ARM64 compatibility)
+# Disable additional SIMD versions to speed up compilation
 set(FAISS_ENABLE_AVX2 OFF CACHE BOOL "" FORCE)
 set(FAISS_ENABLE_AVX512 OFF CACHE BOOL "" FORCE)
-set(FAISS_ENABLE_SSE4_1 OFF CACHE BOOL "" FORCE)
-
-# ARM64-specific configuration
-if(CMAKE_SYSTEM_PROCESSOR MATCHES "aarch64|arm64")
-    message(STATUS "Configuring Faiss for ARM64 architecture")
-
-    if(CMAKE_SYSTEM_NAME STREQUAL "Linux")
-        # Use SVE optimization level for ARM64 Linux (as seen in Faiss conda build)
-        set(FAISS_OPT_LEVEL "sve" CACHE STRING "" FORCE)
-        message(STATUS "Setting FAISS_OPT_LEVEL to 'sve' for ARM64 Linux")
-    else()
-        # Use generic optimization for other ARM64 platforms (like macOS)
-        set(FAISS_OPT_LEVEL "generic" CACHE STRING "" FORCE)
-        message(STATUS "Setting FAISS_OPT_LEVEL to 'generic' for ARM64 ${CMAKE_SYSTEM_NAME}")
-    endif()
-
-    # ARM64 compatibility: Faiss submodule has been modified to fix x86 header inclusion
-    message(STATUS "Using ARM64-compatible Faiss submodule")
-endif()
 
 # Additional optimization options from INSTALL.md
 set(CMAKE_BUILD_TYPE "Release" CACHE STRING "" FORCE)

packages/leann-backend-hnsw/pyproject.toml

@@ -6,10 +6,10 @@ build-backend = "scikit_build_core.build"
 
 [project]
 name = "leann-backend-hnsw"
-version = "0.3.4"
+version = "0.3.2"
 description = "Custom-built HNSW (Faiss) backend for the Leann toolkit."
 dependencies = [
-    "leann-core==0.3.4",
+    "leann-core==0.3.2",
     "numpy",
     "pyzmq>=23.0.0",
     "msgpack>=1.0.0",

packages/leann-core/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "leann-core"
-version = "0.3.4"
+version = "0.3.2"
 description = "Core API and plugin system for LEANN"
 readme = "README.md"
 requires-python = ">=3.9"

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

@@ -6,13 +6,11 @@ with the correct, original embedding logic from the user's reference code.
 import json
 import logging
 import pickle
-import re
-import subprocess
 import time
 import warnings
 from dataclasses import dataclass, field
 from pathlib import Path
-from typing import Any, Literal, Optional, Union
+from typing import Any, Literal, Optional
 
 import numpy as np
 
@@ -20,7 +18,6 @@ from leann.interface import LeannBackendSearcherInterface
 
 from .chat import get_llm
 from .interface import LeannBackendFactoryInterface
-from .metadata_filter import MetadataFilterEngine
 from .registry import BACKEND_REGISTRY
 
 logger = logging.getLogger(__name__)
@@ -128,7 +125,6 @@ class PassageManager:
         # footprint on very large corpora (e.g., 60M+ passages). Instead, keep
         # per-shard maps and do a lightweight per-shard lookup on demand.
         self._total_count: int = 0
-        self.filter_engine = MetadataFilterEngine()  # Initialize filter engine
 
         # Derive index base name for standard sibling fallbacks, e.g., <index_name>.passages.*
         index_name_base = None
@@ -216,56 +212,6 @@ class PassageManager:
                 continue
         raise KeyError(f"Passage ID not found: {passage_id}")
 
-    def filter_search_results(
-        self,
-        search_results: list[SearchResult],
-        metadata_filters: Optional[dict[str, dict[str, Union[str, int, float, bool, list]]]],
-    ) -> list[SearchResult]:
-        """
-        Apply metadata filters to search results.
-
-        Args:
-            search_results: List of SearchResult objects
-            metadata_filters: Filter specifications to apply
-
-        Returns:
-            Filtered list of SearchResult objects
-        """
-        if not metadata_filters:
-            return search_results
-
-        logger.debug(f"Applying metadata filters to {len(search_results)} results")
-
-        # Convert SearchResult objects to dictionaries for the filter engine
-        result_dicts = []
-        for result in search_results:
-            result_dicts.append(
-                {
-                    "id": result.id,
-                    "score": result.score,
-                    "text": result.text,
-                    "metadata": result.metadata,
-                }
-            )
-
-        # Apply filters using the filter engine
-        filtered_dicts = self.filter_engine.apply_filters(result_dicts, metadata_filters)
-
-        # Convert back to SearchResult objects
-        filtered_results = []
-        for result_dict in filtered_dicts:
-            filtered_results.append(
-                SearchResult(
-                    id=result_dict["id"],
-                    score=result_dict["score"],
-                    text=result_dict["text"],
-                    metadata=result_dict["metadata"],
-                )
-            )
-
-        logger.debug(f"Filtered results: {len(filtered_results)} remaining")
-        return filtered_results
-
     def __len__(self) -> int:
         return self._total_count
 
@@ -653,43 +599,12 @@ class LeannSearcher:
         recompute_embeddings: bool = True,
         pruning_strategy: Literal["global", "local", "proportional"] = "global",
         expected_zmq_port: int = 5557,
-        metadata_filters: Optional[dict[str, dict[str, Union[str, int, float, bool, list]]]] = None,
         batch_size: int = 0,
-        use_grep: bool = False,
         **kwargs,
     ) -> list[SearchResult]:
-        """
-        Search for nearest neighbors with optional metadata filtering.
-
-        Args:
-            query: Text query to search for
-            top_k: Number of nearest neighbors to return
-            complexity: Search complexity/candidate list size, higher = more accurate but slower
-            beam_width: Number of parallel search paths/IO requests per iteration
-            prune_ratio: Ratio of neighbors to prune via approximate distance (0.0-1.0)
-            recompute_embeddings: Whether to fetch fresh embeddings from server vs use stored codes
-            pruning_strategy: Candidate selection strategy - "global" (default), "local", or "proportional"
-            expected_zmq_port: ZMQ port for embedding server communication
-            metadata_filters: Optional filters to apply to search results based on metadata.
-                Format: {"field_name": {"operator": value}}
-                Supported operators:
-                - Comparison: "==", "!=", "<", "<=", ">", ">="
-                - Membership: "in", "not_in"
-                - String: "contains", "starts_with", "ends_with"
-                Example: {"chapter": {"<=": 5}, "tags": {"in": ["fiction", "drama"]}}
-            **kwargs: Backend-specific parameters
-
-        Returns:
-            List of SearchResult objects with text, metadata, and similarity scores
-        """
-        # Handle grep search
-        if use_grep:
-            return self._grep_search(query, top_k)
-
         logger.info("🔍 LeannSearcher.search() called:")
         logger.info(f"  Query: '{query}'")
         logger.info(f"  Top_k: {top_k}")
-        logger.info(f"  Metadata filters: {metadata_filters}")
         logger.info(f"  Additional kwargs: {kwargs}")
 
         # Smart top_k detection and adjustment
@@ -789,109 +704,15 @@ class LeannSearcher:
                         f"   {RED}✗{RESET} [{i + 1:2d}] ID: '{string_id}' -> {RED}ERROR: Passage not found!{RESET}"
                     )
 
-        # Apply metadata filters if specified
-        if metadata_filters:
-            logger.info(f"  🔍 Applying metadata filters: {metadata_filters}")
-            enriched_results = self.passage_manager.filter_search_results(
-                enriched_results, metadata_filters
-            )
-
         # Define color codes outside the loop for final message
         GREEN = "\033[92m"
         RESET = "\033[0m"
         logger.info(f"  {GREEN}✓ Final enriched results: {len(enriched_results)} passages{RESET}")
         return enriched_results
 
-    def _find_jsonl_file(self) -> Optional[str]:
-        """Find the .jsonl file containing raw passages for grep search"""
-        index_path = Path(self.meta_path_str).parent
-        potential_files = [
-            index_path / "documents.leann.passages.jsonl",
-            index_path.parent / "documents.leann.passages.jsonl",
-        ]
-
-        for file_path in potential_files:
-            if file_path.exists():
-                return str(file_path)
-        return None
-
-    def _grep_search(self, query: str, top_k: int = 5) -> list[SearchResult]:
-        """Perform grep-based search on raw passages"""
-        jsonl_file = self._find_jsonl_file()
-        if not jsonl_file:
-            raise FileNotFoundError("No .jsonl passages file found for grep search")
-
-        try:
-            cmd = ["grep", "-i", "-n", query, jsonl_file]
-            result = subprocess.run(cmd, capture_output=True, text=True, check=False)
-
-            if result.returncode == 1:
-                return []
-            elif result.returncode != 0:
-                raise RuntimeError(f"Grep failed: {result.stderr}")
-
-            matches = []
-            for line in result.stdout.strip().split("\n"):
-                if not line:
-                    continue
-                parts = line.split(":", 1)
-                if len(parts) != 2:
-                    continue
-
-                try:
-                    data = json.loads(parts[1])
-                    text = data.get("text", "")
-                    score = text.lower().count(query.lower())
-
-                    matches.append(
-                        SearchResult(
-                            id=data.get("id", parts[0]),
-                            text=text,
-                            metadata=data.get("metadata", {}),
-                            score=float(score),
-                        )
-                    )
-                except json.JSONDecodeError:
-                    continue
-
-            matches.sort(key=lambda x: x.score, reverse=True)
-            return matches[:top_k]
-
-        except FileNotFoundError:
-            raise RuntimeError(
-                "grep command not found. Please install grep or use semantic search."
-            )
-
-    def _python_regex_search(self, query: str, top_k: int = 5) -> list[SearchResult]:
-        """Fallback regex search"""
-        jsonl_file = self._find_jsonl_file()
-        if not jsonl_file:
-            raise FileNotFoundError("No .jsonl file found")
-
-        pattern = re.compile(re.escape(query), re.IGNORECASE)
-        matches = []
-
-        with open(jsonl_file, encoding="utf-8") as f:
-            for line_num, line in enumerate(f, 1):
-                if pattern.search(line):
-                    try:
-                        data = json.loads(line.strip())
-                        matches.append(
-                            SearchResult(
-                                id=data.get("id", str(line_num)),
-                                text=data.get("text", ""),
-                                metadata=data.get("metadata", {}),
-                                score=float(len(pattern.findall(data.get("text", "")))),
-                            )
-                        )
-                    except json.JSONDecodeError:
-                        continue
-
-        matches.sort(key=lambda x: x.score, reverse=True)
-        return matches[:top_k]
-
     def cleanup(self):
         """Explicitly cleanup embedding server resources.
+
         This method should be called after you're done using the searcher,
         especially in test environments or batch processing scenarios.
         """
@@ -945,9 +766,7 @@ class LeannChat:
         pruning_strategy: Literal["global", "local", "proportional"] = "global",
         llm_kwargs: Optional[dict[str, Any]] = None,
         expected_zmq_port: int = 5557,
-        metadata_filters: Optional[dict[str, dict[str, Union[str, int, float, bool, list]]]] = None,
         batch_size: int = 0,
-        use_grep: bool = False,
         **search_kwargs,
     ):
         if llm_kwargs is None:
@@ -962,7 +781,6 @@ class LeannChat:
             recompute_embeddings=recompute_embeddings,
             pruning_strategy=pruning_strategy,
             expected_zmq_port=expected_zmq_port,
-            metadata_filters=metadata_filters,
             batch_size=batch_size,
             **search_kwargs,
         )

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

@@ -1,5 +1,6 @@
 import argparse
 import asyncio
+import sys
 from pathlib import Path
 from typing import Any, Optional, Union
 
@@ -321,17 +322,9 @@ Examples:
 
         return basic_matches
 
-    def _should_exclude_file(self, file_path: Path, gitignore_matches) -> bool:
-        """Check if a file should be excluded using gitignore parser.
-
-        Always match against absolute, posix-style paths for consistency with
-        gitignore_parser expectations.
-        """
-        try:
-            absolute_path = file_path.resolve()
-        except Exception:
-            absolute_path = Path(str(file_path))
-        return gitignore_matches(absolute_path.as_posix())
+    def _should_exclude_file(self, relative_path: Path, gitignore_matches) -> bool:
+        """Check if a file should be excluded using gitignore parser."""
+        return gitignore_matches(str(relative_path))
 
     def _is_git_submodule(self, path: Path) -> bool:
         """Check if a path is a git submodule."""
@@ -403,9 +396,7 @@ Examples:
         print(f"   {current_path}")
         print("   " + "─" * 45)
 
-        current_indexes = self._discover_indexes_in_project(
-            current_path, exclude_dirs=other_projects
-        )
+        current_indexes = self._discover_indexes_in_project(current_path)
         if current_indexes:
             for idx in current_indexes:
                 total_indexes += 1
@@ -444,14 +435,9 @@ Examples:
             print("   leann build my-docs --docs ./documents")
         else:
             # Count only projects that have at least one discoverable index
-            projects_count = 0
-            for p in valid_projects:
-                if p == current_path:
-                    discovered = self._discover_indexes_in_project(p, exclude_dirs=other_projects)
-                else:
-                    discovered = self._discover_indexes_in_project(p)
-                if len(discovered) > 0:
-                    projects_count += 1
+            projects_count = sum(
+                1 for p in valid_projects if len(self._discover_indexes_in_project(p)) > 0
+            )
             print(f"📊 Total: {total_indexes} indexes across {projects_count} projects")
 
             if current_indexes_count > 0:
@@ -468,22 +454,9 @@ Examples:
                 print("\n💡 Create your first index:")
                 print("   leann build my-docs --docs ./documents")
 
-    def _discover_indexes_in_project(
-        self, project_path: Path, exclude_dirs: Optional[list[Path]] = None
-    ):
-        """Discover all indexes in a project directory (both CLI and apps formats)
-
-        exclude_dirs: when provided, skip any APP-format index files that are
-        located under these directories. This prevents duplicates when the
-        current project is a parent directory of other registered projects.
-        """
+    def _discover_indexes_in_project(self, project_path: Path):
+        """Discover all indexes in a project directory (both CLI and apps formats)"""
         indexes = []
-        exclude_dirs = exclude_dirs or []
-        # normalize to resolved paths once for comparison
-        try:
-            exclude_dirs_resolved = [p.resolve() for p in exclude_dirs]
-        except Exception:
-            exclude_dirs_resolved = exclude_dirs
 
         # 1. CLI format: .leann/indexes/index_name/
         cli_indexes_dir = project_path / ".leann" / "indexes"
@@ -522,17 +495,6 @@ Examples:
                         continue
                 except Exception:
                     pass
-                # Skip meta files that live under excluded directories
-                try:
-                    meta_parent_resolved = meta_file.parent.resolve()
-                    if any(
-                        meta_parent_resolved.is_relative_to(ex_dir)
-                        for ex_dir in exclude_dirs_resolved
-                    ):
-                        continue
-                except Exception:
-                    # best effort; if resolve or comparison fails, do not exclude
-                    pass
                 # Use the parent directory name as the app index display name
                 display_name = meta_file.parent.name
                 # Extract file base used to store files
@@ -1060,8 +1022,7 @@ Examples:
 
             # Try to use better PDF parsers first, but only if PDFs are requested
             documents = []
-            # Use resolved absolute paths to avoid mismatches (symlinks, relative vs absolute)
-            docs_path = Path(docs_dir).resolve()
+            docs_path = Path(docs_dir)
 
             # Check if we should process PDFs
             should_process_pdfs = custom_file_types is None or ".pdf" in custom_file_types
@@ -1070,15 +1031,10 @@ Examples:
                 for file_path in docs_path.rglob("*.pdf"):
                     # Check if file matches any exclude pattern
                     try:
-                        # Ensure both paths are resolved before computing relativity
-                        file_path_resolved = file_path.resolve()
-                        # Determine directory scope using the non-resolved path to avoid
-                        # misclassifying symlinked entries as outside the docs directory
                         relative_path = file_path.relative_to(docs_path)
                         if not include_hidden and _path_has_hidden_segment(relative_path):
                             continue
-                        # Use absolute path for gitignore matching
-                        if self._should_exclude_file(file_path_resolved, gitignore_matches):
+                        if self._should_exclude_file(relative_path, gitignore_matches):
                             continue
                     except ValueError:
                         # Skip files that can't be made relative to docs_path
@@ -1121,11 +1077,10 @@ Examples:
                 ) -> bool:
                     """Return True if file should be included (not excluded)"""
                     try:
-                        docs_path_obj = Path(docs_dir).resolve()
-                        file_path_obj = Path(file_path).resolve()
-                        # Use absolute path for gitignore matching
-                        _ = file_path_obj.relative_to(docs_path_obj)  # validate scope
-                        return not self._should_exclude_file(file_path_obj, gitignore_matches)
+                        docs_path_obj = Path(docs_dir)
+                        file_path_obj = Path(file_path)
+                        relative_path = file_path_obj.relative_to(docs_path_obj)
+                        return not self._should_exclude_file(relative_path, gitignore_matches)
                     except (ValueError, OSError):
                         return True  # Include files that can't be processed
 
@@ -1215,8 +1170,13 @@ Examples:
         if use_ast:
             print("🧠 Using AST-aware chunking for code files")
             try:
-                # Import enhanced chunking utilities from packaged module
-                from .chunking_utils import create_text_chunks
+                # Import enhanced chunking utilities
+                # Add apps directory to path to import chunking utilities
+                apps_dir = Path(__file__).parent.parent.parent.parent.parent / "apps"
+                if apps_dir.exists():
+                    sys.path.insert(0, str(apps_dir))
+
+                from chunking import create_text_chunks
 
                 # Use enhanced chunking with AST support
                 all_texts = create_text_chunks(
@@ -1231,9 +1191,7 @@ Examples:
                 )
 
             except ImportError as e:
-                print(
-                    f"⚠️  AST chunking utilities not available in package ({e}), falling back to traditional chunking"
-                )
+                print(f"⚠️  AST chunking not available ({e}), falling back to traditional chunking")
                 use_ast = False
 
         if not use_ast:

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

@@ -1,240 +0,0 @@
-"""
-Metadata filtering engine for LEANN search results.
-
-This module provides generic metadata filtering capabilities that can be applied
-to search results from any LEANN backend. The filtering supports various
-operators for different data types including numbers, strings, booleans, and lists.
-"""
-
-import logging
-from typing import Any, Union
-
-logger = logging.getLogger(__name__)
-
-# Type alias for filter specifications
-FilterValue = Union[str, int, float, bool, list]
-FilterSpec = dict[str, FilterValue]
-MetadataFilters = dict[str, FilterSpec]
-
-
-class MetadataFilterEngine:
-    """
-    Engine for evaluating metadata filters against search results.
-
-    Supports various operators for filtering based on metadata fields:
-    - Comparison: ==, !=, <, <=, >, >=
-    - Membership: in, not_in
-    - String operations: contains, starts_with, ends_with
-    - Boolean operations: is_true, is_false
-    """
-
-    def __init__(self):
-        """Initialize the filter engine with supported operators."""
-        self.operators = {
-            "==": self._equals,
-            "!=": self._not_equals,
-            "<": self._less_than,
-            "<=": self._less_than_or_equal,
-            ">": self._greater_than,
-            ">=": self._greater_than_or_equal,
-            "in": self._in,
-            "not_in": self._not_in,
-            "contains": self._contains,
-            "starts_with": self._starts_with,
-            "ends_with": self._ends_with,
-            "is_true": self._is_true,
-            "is_false": self._is_false,
-        }
-
-    def apply_filters(
-        self, search_results: list[dict[str, Any]], metadata_filters: MetadataFilters
-    ) -> list[dict[str, Any]]:
-        """
-        Apply metadata filters to a list of search results.
-
-        Args:
-            search_results: List of result dictionaries, each containing 'metadata' field
-            metadata_filters: Dictionary of filter specifications
-                Format: {"field_name": {"operator": value}}
-
-        Returns:
-            Filtered list of search results
-        """
-        if not metadata_filters:
-            return search_results
-
-        logger.debug(f"Applying filters: {metadata_filters}")
-        logger.debug(f"Input results count: {len(search_results)}")
-
-        filtered_results = []
-        for result in search_results:
-            if self._evaluate_filters(result, metadata_filters):
-                filtered_results.append(result)
-
-        logger.debug(f"Filtered results count: {len(filtered_results)}")
-        return filtered_results
-
-    def _evaluate_filters(self, result: dict[str, Any], filters: MetadataFilters) -> bool:
-        """
-        Evaluate all filters against a single search result.
-
-        All filters must pass (AND logic) for the result to be included.
-
-        Args:
-            result: Full search result dictionary (including metadata, text, etc.)
-            filters: Filter specifications to evaluate
-
-        Returns:
-            True if all filters pass, False otherwise
-        """
-        for field_name, filter_spec in filters.items():
-            if not self._evaluate_field_filter(result, field_name, filter_spec):
-                return False
-        return True
-
-    def _evaluate_field_filter(
-        self, result: dict[str, Any], field_name: str, filter_spec: FilterSpec
-    ) -> bool:
-        """
-        Evaluate a single field filter against a search result.
-
-        Args:
-            result: Full search result dictionary
-            field_name: Name of the field to filter on
-            filter_spec: Filter specification for this field
-
-        Returns:
-            True if the filter passes, False otherwise
-        """
-        # First check top-level fields, then check metadata
-        field_value = result.get(field_name)
-        if field_value is None:
-            # Try to get from metadata if not found at top level
-            metadata = result.get("metadata", {})
-            field_value = metadata.get(field_name)
-
-        # Handle missing fields - they fail all filters except existence checks
-        if field_value is None:
-            logger.debug(f"Field '{field_name}' not found in result or metadata")
-            return False
-
-        # Evaluate each operator in the filter spec
-        for operator, expected_value in filter_spec.items():
-            if operator not in self.operators:
-                logger.warning(f"Unsupported operator: {operator}")
-                return False
-
-            try:
-                if not self.operators[operator](field_value, expected_value):
-                    logger.debug(
-                        f"Filter failed: {field_name} {operator} {expected_value} "
-                        f"(actual: {field_value})"
-                    )
-                    return False
-            except Exception as e:
-                logger.warning(
-                    f"Error evaluating filter {field_name} {operator} {expected_value}: {e}"
-                )
-                return False
-
-        return True
-
-    # Comparison operators
-    def _equals(self, field_value: Any, expected_value: Any) -> bool:
-        """Check if field value equals expected value."""
-        return field_value == expected_value
-
-    def _not_equals(self, field_value: Any, expected_value: Any) -> bool:
-        """Check if field value does not equal expected value."""
-        return field_value != expected_value
-
-    def _less_than(self, field_value: Any, expected_value: Any) -> bool:
-        """Check if field value is less than expected value."""
-        return self._numeric_compare(field_value, expected_value, lambda a, b: a < b)
-
-    def _less_than_or_equal(self, field_value: Any, expected_value: Any) -> bool:
-        """Check if field value is less than or equal to expected value."""
-        return self._numeric_compare(field_value, expected_value, lambda a, b: a <= b)
-
-    def _greater_than(self, field_value: Any, expected_value: Any) -> bool:
-        """Check if field value is greater than expected value."""
-        return self._numeric_compare(field_value, expected_value, lambda a, b: a > b)
-
-    def _greater_than_or_equal(self, field_value: Any, expected_value: Any) -> bool:
-        """Check if field value is greater than or equal to expected value."""
-        return self._numeric_compare(field_value, expected_value, lambda a, b: a >= b)
-
-    # Membership operators
-    def _in(self, field_value: Any, expected_value: Any) -> bool:
-        """Check if field value is in the expected list/collection."""
-        if not isinstance(expected_value, (list, tuple, set)):
-            raise ValueError("'in' operator requires a list, tuple, or set")
-        return field_value in expected_value
-
-    def _not_in(self, field_value: Any, expected_value: Any) -> bool:
-        """Check if field value is not in the expected list/collection."""
-        if not isinstance(expected_value, (list, tuple, set)):
-            raise ValueError("'not_in' operator requires a list, tuple, or set")
-        return field_value not in expected_value
-
-    # String operators
-    def _contains(self, field_value: Any, expected_value: Any) -> bool:
-        """Check if field value contains the expected substring."""
-        field_str = str(field_value)
-        expected_str = str(expected_value)
-        return expected_str in field_str
-
-    def _starts_with(self, field_value: Any, expected_value: Any) -> bool:
-        """Check if field value starts with the expected prefix."""
-        field_str = str(field_value)
-        expected_str = str(expected_value)
-        return field_str.startswith(expected_str)
-
-    def _ends_with(self, field_value: Any, expected_value: Any) -> bool:
-        """Check if field value ends with the expected suffix."""
-        field_str = str(field_value)
-        expected_str = str(expected_value)
-        return field_str.endswith(expected_str)
-
-    # Boolean operators
-    def _is_true(self, field_value: Any, expected_value: Any) -> bool:
-        """Check if field value is truthy."""
-        return bool(field_value)
-
-    def _is_false(self, field_value: Any, expected_value: Any) -> bool:
-        """Check if field value is falsy."""
-        return not bool(field_value)
-
-    # Helper methods
-    def _numeric_compare(self, field_value: Any, expected_value: Any, compare_func) -> bool:
-        """
-        Helper for numeric comparisons with type coercion.
-
-        Args:
-            field_value: Value from metadata
-            expected_value: Value to compare against
-            compare_func: Comparison function to apply
-
-        Returns:
-            Result of comparison
-        """
-        try:
-            # Try to convert both values to numbers for comparison
-            if isinstance(field_value, str) and isinstance(expected_value, str):
-                # String comparison if both are strings
-                return compare_func(field_value, expected_value)
-
-            # Numeric comparison - attempt to convert to float
-            field_num = (
-                float(field_value) if not isinstance(field_value, (int, float)) else field_value
-            )
-            expected_num = (
-                float(expected_value)
-                if not isinstance(expected_value, (int, float))
-                else expected_value
-            )
-
-            return compare_func(field_num, expected_num)
-        except (ValueError, TypeError):
-            # Fall back to string comparison if numeric conversion fails
-            return compare_func(str(field_value), str(expected_value))

packages/leann-mcp/README.md

@@ -2,8 +2,6 @@
 
 Transform your development workflow with intelligent code assistance using LEANN's semantic search directly in Claude Code.
 
-For agent-facing discovery details, see `llms.txt` in the repository root.
-
 ## Prerequisites
 
 Install LEANN globally for MCP integration (with default backend):

packages/leann/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "leann"
-version = "0.3.4"
+version = "0.3.2"
 description = "LEANN - The smallest vector index in the world. RAG Everything with LEANN!"
 readme = "README.md"
 requires-python = ">=3.9"

pyproject.toml

@@ -99,7 +99,6 @@ wechat-exporter = "wechat_exporter.main:main"
 leann-core = { path = "packages/leann-core", editable = true }
 leann-backend-diskann = { path = "packages/leann-backend-diskann", editable = true }
 leann-backend-hnsw = { path = "packages/leann-backend-hnsw", editable = true }
-astchunk = { path = "packages/astchunk-leann", editable = true }
 
 [tool.ruff]
 target-version = "py39"

tests/test_metadata_filtering.py

@@ -1,365 +0,0 @@
-"""
-Comprehensive tests for metadata filtering functionality.
-
-This module tests the MetadataFilterEngine class and its integration
-with the LEANN search system.
-"""
-
-import os
-
-# Import the modules we're testing
-import sys
-from unittest.mock import Mock, patch
-
-sys.path.insert(0, os.path.join(os.path.dirname(__file__), "../packages/leann-core/src"))
-
-from leann.api import PassageManager, SearchResult
-from leann.metadata_filter import MetadataFilterEngine
-
-
-class TestMetadataFilterEngine:
-    """Test suite for the MetadataFilterEngine class."""
-
-    def setup_method(self):
-        """Setup test fixtures."""
-        self.engine = MetadataFilterEngine()
-
-        # Sample search results for testing
-        self.sample_results = [
-            {
-                "id": "doc1",
-                "score": 0.95,
-                "text": "This is chapter 1 content",
-                "metadata": {
-                    "chapter": 1,
-                    "character": "Alice",
-                    "tags": ["adventure", "fantasy"],
-                    "word_count": 150,
-                    "is_published": True,
-                    "genre": "fiction",
-                },
-            },
-            {
-                "id": "doc2",
-                "score": 0.87,
-                "text": "This is chapter 3 content",
-                "metadata": {
-                    "chapter": 3,
-                    "character": "Bob",
-                    "tags": ["mystery", "thriller"],
-                    "word_count": 250,
-                    "is_published": True,
-                    "genre": "fiction",
-                },
-            },
-            {
-                "id": "doc3",
-                "score": 0.82,
-                "text": "This is chapter 5 content",
-                "metadata": {
-                    "chapter": 5,
-                    "character": "Alice",
-                    "tags": ["romance", "drama"],
-                    "word_count": 300,
-                    "is_published": False,
-                    "genre": "non-fiction",
-                },
-            },
-            {
-                "id": "doc4",
-                "score": 0.78,
-                "text": "This is chapter 10 content",
-                "metadata": {
-                    "chapter": 10,
-                    "character": "Charlie",
-                    "tags": ["action", "adventure"],
-                    "word_count": 400,
-                    "is_published": True,
-                    "genre": "fiction",
-                },
-            },
-        ]
-
-    def test_engine_initialization(self):
-        """Test that the filter engine initializes correctly."""
-        assert self.engine is not None
-        assert len(self.engine.operators) > 0
-        assert "==" in self.engine.operators
-        assert "contains" in self.engine.operators
-        assert "in" in self.engine.operators
-
-    def test_direct_instantiation(self):
-        """Test direct instantiation of the engine."""
-        engine = MetadataFilterEngine()
-        assert isinstance(engine, MetadataFilterEngine)
-
-    def test_no_filters_returns_all_results(self):
-        """Test that passing None or empty filters returns all results."""
-        # Test with None
-        result = self.engine.apply_filters(self.sample_results, None)
-        assert len(result) == len(self.sample_results)
-
-        # Test with empty dict
-        result = self.engine.apply_filters(self.sample_results, {})
-        assert len(result) == len(self.sample_results)
-
-    # Test comparison operators
-    def test_equals_filter(self):
-        """Test equals (==) filter."""
-        filters = {"chapter": {"==": 1}}
-        result = self.engine.apply_filters(self.sample_results, filters)
-        assert len(result) == 1
-        assert result[0]["id"] == "doc1"
-
-    def test_not_equals_filter(self):
-        """Test not equals (!=) filter."""
-        filters = {"genre": {"!=": "fiction"}}
-        result = self.engine.apply_filters(self.sample_results, filters)
-        assert len(result) == 1
-        assert result[0]["metadata"]["genre"] == "non-fiction"
-
-    def test_less_than_filter(self):
-        """Test less than (<) filter."""
-        filters = {"chapter": {"<": 5}}
-        result = self.engine.apply_filters(self.sample_results, filters)
-        assert len(result) == 2
-        chapters = [r["metadata"]["chapter"] for r in result]
-        assert all(ch < 5 for ch in chapters)
-
-    def test_less_than_or_equal_filter(self):
-        """Test less than or equal (<=) filter."""
-        filters = {"chapter": {"<=": 5}}
-        result = self.engine.apply_filters(self.sample_results, filters)
-        assert len(result) == 3
-        chapters = [r["metadata"]["chapter"] for r in result]
-        assert all(ch <= 5 for ch in chapters)
-
-    def test_greater_than_filter(self):
-        """Test greater than (>) filter."""
-        filters = {"word_count": {">": 200}}
-        result = self.engine.apply_filters(self.sample_results, filters)
-        assert len(result) == 3  # Documents with word_count 250, 300, 400
-        word_counts = [r["metadata"]["word_count"] for r in result]
-        assert all(wc > 200 for wc in word_counts)
-
-    def test_greater_than_or_equal_filter(self):
-        """Test greater than or equal (>=) filter."""
-        filters = {"word_count": {">=": 250}}
-        result = self.engine.apply_filters(self.sample_results, filters)
-        assert len(result) == 3
-        word_counts = [r["metadata"]["word_count"] for r in result]
-        assert all(wc >= 250 for wc in word_counts)
-
-    # Test membership operators
-    def test_in_filter(self):
-        """Test in filter."""
-        filters = {"character": {"in": ["Alice", "Bob"]}}
-        result = self.engine.apply_filters(self.sample_results, filters)
-        assert len(result) == 3
-        characters = [r["metadata"]["character"] for r in result]
-        assert all(ch in ["Alice", "Bob"] for ch in characters)
-
-    def test_not_in_filter(self):
-        """Test not_in filter."""
-        filters = {"character": {"not_in": ["Alice", "Bob"]}}
-        result = self.engine.apply_filters(self.sample_results, filters)
-        assert len(result) == 1
-        assert result[0]["metadata"]["character"] == "Charlie"
-
-    # Test string operators
-    def test_contains_filter(self):
-        """Test contains filter."""
-        filters = {"genre": {"contains": "fiction"}}
-        result = self.engine.apply_filters(self.sample_results, filters)
-        assert len(result) == 4  # Both "fiction" and "non-fiction"
-
-    def test_starts_with_filter(self):
-        """Test starts_with filter."""
-        filters = {"genre": {"starts_with": "non"}}
-        result = self.engine.apply_filters(self.sample_results, filters)
-        assert len(result) == 1
-        assert result[0]["metadata"]["genre"] == "non-fiction"
-
-    def test_ends_with_filter(self):
-        """Test ends_with filter."""
-        filters = {"text": {"ends_with": "content"}}
-        result = self.engine.apply_filters(self.sample_results, filters)
-        assert len(result) == 4  # All sample texts end with "content"
-
-    # Test boolean operators
-    def test_is_true_filter(self):
-        """Test is_true filter."""
-        filters = {"is_published": {"is_true": True}}
-        result = self.engine.apply_filters(self.sample_results, filters)
-        assert len(result) == 3
-        assert all(r["metadata"]["is_published"] for r in result)
-
-    def test_is_false_filter(self):
-        """Test is_false filter."""
-        filters = {"is_published": {"is_false": False}}
-        result = self.engine.apply_filters(self.sample_results, filters)
-        assert len(result) == 1
-        assert not result[0]["metadata"]["is_published"]
-
-    # Test compound filters (AND logic)
-    def test_compound_filters(self):
-        """Test multiple filters applied together (AND logic)."""
-        filters = {"genre": {"==": "fiction"}, "chapter": {"<=": 5}}
-        result = self.engine.apply_filters(self.sample_results, filters)
-        assert len(result) == 2
-        for r in result:
-            assert r["metadata"]["genre"] == "fiction"
-            assert r["metadata"]["chapter"] <= 5
-
-    def test_multiple_operators_same_field(self):
-        """Test multiple operators on the same field."""
-        filters = {"word_count": {">=": 200, "<=": 350}}
-        result = self.engine.apply_filters(self.sample_results, filters)
-        assert len(result) == 2
-        for r in result:
-            wc = r["metadata"]["word_count"]
-            assert 200 <= wc <= 350
-
-    # Test edge cases
-    def test_missing_field_fails_filter(self):
-        """Test that missing metadata fields fail filters."""
-        filters = {"nonexistent_field": {"==": "value"}}
-        result = self.engine.apply_filters(self.sample_results, filters)
-        assert len(result) == 0
-
-    def test_invalid_operator(self):
-        """Test that invalid operators are handled gracefully."""
-        filters = {"chapter": {"invalid_op": 1}}
-        result = self.engine.apply_filters(self.sample_results, filters)
-        assert len(result) == 0  # Should filter out all results
-
-    def test_type_coercion_numeric(self):
-        """Test numeric type coercion in comparisons."""
-        # Add a result with string chapter number
-        test_results = [
-            *self.sample_results,
-            {
-                "id": "doc5",
-                "score": 0.75,
-                "text": "String chapter test",
-                "metadata": {"chapter": "2", "genre": "test"},
-            },
-        ]
-
-        filters = {"chapter": {"<": 3}}
-        result = self.engine.apply_filters(test_results, filters)
-        # Should include doc1 (chapter=1) and doc5 (chapter="2")
-        assert len(result) == 2
-        ids = [r["id"] for r in result]
-        assert "doc1" in ids
-        assert "doc5" in ids
-
-    def test_list_membership_with_nested_tags(self):
-        """Test membership operations with list metadata."""
-        # Note: This tests the metadata structure, not list field filtering
-        # For list field filtering, we'd need to modify the test data
-        filters = {"character": {"in": ["Alice"]}}
-        result = self.engine.apply_filters(self.sample_results, filters)
-        assert len(result) == 2
-        assert all(r["metadata"]["character"] == "Alice" for r in result)
-
-    def test_empty_results_list(self):
-        """Test filtering on empty results list."""
-        filters = {"chapter": {"==": 1}}
-        result = self.engine.apply_filters([], filters)
-        assert len(result) == 0
-
-
-class TestPassageManagerFiltering:
-    """Test suite for PassageManager filtering integration."""
-
-    def setup_method(self):
-        """Setup test fixtures."""
-        # Mock the passage manager without actual file I/O
-        self.passage_manager = Mock(spec=PassageManager)
-        self.passage_manager.filter_engine = MetadataFilterEngine()
-
-        # Sample SearchResult objects
-        self.search_results = [
-            SearchResult(
-                id="doc1",
-                score=0.95,
-                text="Chapter 1 content",
-                metadata={"chapter": 1, "character": "Alice"},
-            ),
-            SearchResult(
-                id="doc2",
-                score=0.87,
-                text="Chapter 5 content",
-                metadata={"chapter": 5, "character": "Bob"},
-            ),
-            SearchResult(
-                id="doc3",
-                score=0.82,
-                text="Chapter 10 content",
-                metadata={"chapter": 10, "character": "Alice"},
-            ),
-        ]
-
-    def test_search_result_filtering(self):
-        """Test filtering SearchResult objects."""
-        # Create a real PassageManager instance just for the filtering method
-        # We'll mock the file operations
-        with patch("builtins.open"), patch("json.loads"), patch("pickle.load"):
-            pm = PassageManager([{"type": "jsonl", "path": "test.jsonl"}])
-
-            filters = {"chapter": {"<=": 5}}
-            result = pm.filter_search_results(self.search_results, filters)
-
-            assert len(result) == 2
-            chapters = [r.metadata["chapter"] for r in result]
-            assert all(ch <= 5 for ch in chapters)
-
-    def test_filter_search_results_no_filters(self):
-        """Test that None filters return all results."""
-        with patch("builtins.open"), patch("json.loads"), patch("pickle.load"):
-            pm = PassageManager([{"type": "jsonl", "path": "test.jsonl"}])
-
-            result = pm.filter_search_results(self.search_results, None)
-            assert len(result) == len(self.search_results)
-
-    def test_filter_maintains_search_result_type(self):
-        """Test that filtering returns SearchResult objects."""
-        with patch("builtins.open"), patch("json.loads"), patch("pickle.load"):
-            pm = PassageManager([{"type": "jsonl", "path": "test.jsonl"}])
-
-            filters = {"character": {"==": "Alice"}}
-            result = pm.filter_search_results(self.search_results, filters)
-
-            assert len(result) == 2
-            for r in result:
-                assert isinstance(r, SearchResult)
-                assert r.metadata["character"] == "Alice"
-
-
-# Integration tests would go here, but they require actual LEANN backend setup
-# These would test the full pipeline from LeannSearcher.search() with metadata_filters
-
-if __name__ == "__main__":
-    # Run basic smoke tests
-    engine = MetadataFilterEngine()
-
-    sample_data = [
-        {
-            "id": "test1",
-            "score": 0.9,
-            "text": "Test content",
-            "metadata": {"chapter": 1, "published": True},
-        }
-    ]
-
-    # Test basic filtering
-    result = engine.apply_filters(sample_data, {"chapter": {"==": 1}})
-    assert len(result) == 1
-    print("✅ Basic filtering test passed")
-
-    result = engine.apply_filters(sample_data, {"chapter": {"==": 2}})
-    assert len(result) == 0
-    print("✅ No match filtering test passed")
-
-    print("🎉 All smoke tests passed!")