[Fix] Enable AST chunking when installed (package chunking utils) (#101)

* fix(core): package chunking utils for AST chunking; re-export in apps; CLI imports packaged utils

* style

* chore: fix ruff warnings (RUF059, F401)

* style

.github/workflows/build-reusable.yml

@@ -54,6 +54,17 @@ 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
@@ -108,13 +119,46 @@ jobs:
             pkg-config libabsl-dev libaio-dev libprotobuf-dev \
             patchelf
 
-          # 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
+          # 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"
 
       - name: Install system dependencies (macOS)
         if: runner.os == 'macOS'

.gitignore

@@ -22,6 +22,7 @@ demo/experiment_results/**/*.json
 *.sh
 *.txt
 !CMakeLists.txt
+!llms.txt
 latency_breakdown*.json
 experiment_results/eval_results/diskann/*.json
 aws/

.gitmodules

@@ -14,3 +14,7 @@
 [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

@@ -656,6 +656,19 @@ results = searcher.search(
 
 📖 **[Complete Metadata filtering guide →](docs/metadata_filtering.md)**
 
+### 🔍 Grep Search
+
+For exact text matching instead of semantic search, use the `use_grep` parameter:
+
+```python
+# Exact text search
+results = searcher.search("banana‑crocodile", use_grep=True, top_k=1)
+```
+
+**Use cases**: Finding specific code patterns, error messages, function names, or exact phrases where semantic similarity isn't needed.
+
+📖 **[Complete grep search guide →](docs/grep_search.md)**
+
 ## 🏗️ Architecture & How It Works
 
 <p align="center">

apps/chunking/__init__.py

@@ -1,16 +1,38 @@
-"""
-Chunking utilities for LEANN RAG applications.
-Provides AST-aware and traditional text chunking functionality.
+"""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.
 """
 
-from .utils import (
-    CODE_EXTENSIONS,
-    create_ast_chunks,
-    create_text_chunks,
-    create_traditional_chunks,
-    detect_code_files,
-    get_language_from_extension,
-)
+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
 
 __all__ = [
     "CODE_EXTENSIONS",

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

@@ -26,6 +26,21 @@ 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

@@ -0,0 +1,149 @@
+# 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()
+```

examples/grep_search_example.py

@@ -0,0 +1,35 @@
+"""
+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")

llms.txt

@@ -0,0 +1,28 @@
+# 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 = "0.3.2"
-dependencies = ["leann-core==0.3.2", "numpy", "protobuf>=3.19.0"]
+version = "0.3.4"
+dependencies = ["leann-core==0.3.4", "numpy", "protobuf>=3.19.0"]
 
 [tool.scikit-build]
 # Key: simplified CMake path

packages/leann-backend-hnsw/CMakeLists.txt

@@ -49,9 +49,28 @@ 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 additional SIMD versions to speed up compilation
+# Disable x86-specific SIMD optimizations (important for ARM64 compatibility)
 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 = "0.3.2"
+version = "0.3.4"
 description = "Custom-built HNSW (Faiss) backend for the Leann toolkit."
 dependencies = [
-    "leann-core==0.3.2",
+    "leann-core==0.3.4",
     "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 = "0.3.2"
+version = "0.3.4"
 description = "Core API and plugin system for LEANN"
 readme = "README.md"
 requires-python = ">=3.9"

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

@@ -6,6 +6,8 @@ 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
@@ -653,6 +655,7 @@ class LeannSearcher:
         expected_zmq_port: int = 5557,
         metadata_filters: Optional[dict[str, dict[str, Union[str, int, float, bool, list]]]] = None,
         batch_size: int = 0,
+        use_grep: bool = False,
         **kwargs,
     ) -> list[SearchResult]:
         """
@@ -679,6 +682,10 @@ class LeannSearcher:
         Returns:
             List of SearchResult objects with text, metadata, and similarity scores
         """
+        # Handle grep search
+        if use_grep:
+            return self._grep_search(query, top_k)
+
         logger.info("🔍 LeannSearcher.search() called:")
         logger.info(f"  Query: '{query}'")
         logger.info(f"  Top_k: {top_k}")
@@ -795,9 +802,96 @@ class LeannSearcher:
         logger.info(f"  {GREEN}✓ Final enriched results: {len(enriched_results)} passages{RESET}")
         return enriched_results
 
+    def _find_jsonl_file(self) -> Optional[str]:
+        """Find the .jsonl file containing raw passages for grep search"""
+        index_path = Path(self.meta_path_str).parent
+        potential_files = [
+            index_path / "documents.leann.passages.jsonl",
+            index_path.parent / "documents.leann.passages.jsonl",
+        ]
+
+        for file_path in potential_files:
+            if file_path.exists():
+                return str(file_path)
+        return None
+
+    def _grep_search(self, query: str, top_k: int = 5) -> list[SearchResult]:
+        """Perform grep-based search on raw passages"""
+        jsonl_file = self._find_jsonl_file()
+        if not jsonl_file:
+            raise FileNotFoundError("No .jsonl passages file found for grep search")
+
+        try:
+            cmd = ["grep", "-i", "-n", query, jsonl_file]
+            result = subprocess.run(cmd, capture_output=True, text=True, check=False)
+
+            if result.returncode == 1:
+                return []
+            elif result.returncode != 0:
+                raise RuntimeError(f"Grep failed: {result.stderr}")
+
+            matches = []
+            for line in result.stdout.strip().split("\n"):
+                if not line:
+                    continue
+                parts = line.split(":", 1)
+                if len(parts) != 2:
+                    continue
+
+                try:
+                    data = json.loads(parts[1])
+                    text = data.get("text", "")
+                    score = text.lower().count(query.lower())
+
+                    matches.append(
+                        SearchResult(
+                            id=data.get("id", parts[0]),
+                            text=text,
+                            metadata=data.get("metadata", {}),
+                            score=float(score),
+                        )
+                    )
+                except json.JSONDecodeError:
+                    continue
+
+            matches.sort(key=lambda x: x.score, reverse=True)
+            return matches[:top_k]
+
+        except FileNotFoundError:
+            raise RuntimeError(
+                "grep command not found. Please install grep or use semantic search."
+            )
+
+    def _python_regex_search(self, query: str, top_k: int = 5) -> list[SearchResult]:
+        """Fallback regex search"""
+        jsonl_file = self._find_jsonl_file()
+        if not jsonl_file:
+            raise FileNotFoundError("No .jsonl file found")
+
+        pattern = re.compile(re.escape(query), re.IGNORECASE)
+        matches = []
+
+        with open(jsonl_file, encoding="utf-8") as f:
+            for line_num, line in enumerate(f, 1):
+                if pattern.search(line):
+                    try:
+                        data = json.loads(line.strip())
+                        matches.append(
+                            SearchResult(
+                                id=data.get("id", str(line_num)),
+                                text=data.get("text", ""),
+                                metadata=data.get("metadata", {}),
+                                score=float(len(pattern.findall(data.get("text", "")))),
+                            )
+                        )
+                    except json.JSONDecodeError:
+                        continue
+
+        matches.sort(key=lambda x: x.score, reverse=True)
+        return matches[:top_k]
+
     def cleanup(self):
         """Explicitly cleanup embedding server resources.
-
         This method should be called after you're done using the searcher,
         especially in test environments or batch processing scenarios.
         """
@@ -853,6 +947,7 @@ class LeannChat:
         expected_zmq_port: int = 5557,
         metadata_filters: Optional[dict[str, dict[str, Union[str, int, float, bool, list]]]] = None,
         batch_size: int = 0,
+        use_grep: bool = False,
         **search_kwargs,
     ):
         if llm_kwargs is None:

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

@@ -1,6 +1,6 @@
 """
 Enhanced chunking utilities with AST-aware code chunking support.
-Provides unified interface for both traditional and AST-based text chunking.
+Packaged within leann-core so installed wheels can import it reliably.
 """
 
 import logging
@@ -22,30 +22,9 @@ 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.
-
-    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)
-    """
+    """Separate documents into code files and regular text files."""
     if code_extensions is None:
         code_extensions = CODE_EXTENSIONS
 
@@ -53,16 +32,10 @@ def detect_code_files(documents, code_extensions=None) -> tuple[list, list]:
     text_docs = []
 
     for doc in documents:
-        # 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", "")
-
+        file_path = doc.metadata.get("file_path", "") or 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)
@@ -70,7 +43,6 @@ 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)
 
@@ -79,7 +51,7 @@ def detect_code_files(documents, code_extensions=None) -> tuple[list, list]:
 
 
 def get_language_from_extension(file_path: str) -> Optional[str]:
-    """Get the programming language from file extension."""
+    """Return language string from a filename/extension using CODE_EXTENSIONS."""
     ext = Path(file_path).suffix.lower()
     return CODE_EXTENSIONS.get(ext)
 
@@ -90,40 +62,26 @@ 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.
 
-    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
+    Falls back to traditional chunking if astchunk is unavailable.
     """
     try:
-        from astchunk import ASTChunkBuilder
+        from astchunk import ASTChunkBuilder  # optional dependency
     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 for document, falling back to traditional chunking"
-            )
-            traditional_chunks = create_traditional_chunks([doc], max_chunk_size, chunk_overlap)
-            all_chunks.extend(traditional_chunks)
+            logger.warning("No language detected; falling back to traditional chunking")
+            all_chunks.extend(create_traditional_chunks([doc], max_chunk_size, chunk_overlap))
             continue
 
         try:
-            # Configure astchunk
             configs = {
                 "max_chunk_size": max_chunk_size,
                 "language": language,
@@ -131,7 +89,6 @@ 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", ""),
@@ -140,17 +97,13 @@ 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
@@ -159,7 +112,6 @@ 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():
@@ -168,12 +120,10 @@ 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")
-            traditional_chunks = create_traditional_chunks([doc], max_chunk_size, chunk_overlap)
-            all_chunks.extend(traditional_chunks)
+            all_chunks.extend(create_traditional_chunks([doc], max_chunk_size, chunk_overlap))
 
     return all_chunks
 
@@ -181,23 +131,10 @@ 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.
-
-    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
+    """Create traditional text chunks using LlamaIndex SentenceSplitter."""
     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:
@@ -215,12 +152,9 @@ def create_traditional_chunks(
         try:
             nodes = node_parser.get_nodes_from_documents([doc])
             if 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")
+                all_texts.extend(node.get_content() for node in nodes)
         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())
@@ -238,32 +172,13 @@ 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.
-
-    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
-    """
+    """Create text chunks from documents with optional AST support for code files."""
     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",
@@ -273,47 +188,32 @@ 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:
-                ast_chunks = create_ast_chunks(
-                    code_docs, max_chunk_size=ast_chunk_size, chunk_overlap=ast_chunk_overlap
+                all_chunks.extend(
+                    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:
-                    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(
+                        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:
-            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")
+            all_chunks.extend(create_traditional_chunks(text_docs, chunk_size, chunk_overlap))
     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)}")

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

@@ -1,6 +1,5 @@
 import argparse
 import asyncio
-import sys
 from pathlib import Path
 from typing import Any, Optional, Union
 
@@ -322,9 +321,17 @@ Examples:
 
         return basic_matches
 
-    def _should_exclude_file(self, relative_path: Path, gitignore_matches) -> bool:
-        """Check if a file should be excluded using gitignore parser."""
-        return gitignore_matches(str(relative_path))
+    def _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 _is_git_submodule(self, path: Path) -> bool:
         """Check if a path is a git submodule."""
@@ -396,7 +403,9 @@ Examples:
         print(f"   {current_path}")
         print("   " + "─" * 45)
 
-        current_indexes = self._discover_indexes_in_project(current_path)
+        current_indexes = self._discover_indexes_in_project(
+            current_path, exclude_dirs=other_projects
+        )
         if current_indexes:
             for idx in current_indexes:
                 total_indexes += 1
@@ -435,9 +444,14 @@ Examples:
             print("   leann build my-docs --docs ./documents")
         else:
             # Count only projects that have at least one discoverable index
-            projects_count = sum(
-                1 for p in valid_projects if len(self._discover_indexes_in_project(p)) > 0
-            )
+            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
             print(f"📊 Total: {total_indexes} indexes across {projects_count} projects")
 
             if current_indexes_count > 0:
@@ -454,9 +468,22 @@ Examples:
                 print("\n💡 Create your first index:")
                 print("   leann build my-docs --docs ./documents")
 
-    def _discover_indexes_in_project(self, project_path: Path):
-        """Discover all indexes in a project directory (both CLI and apps formats)"""
+    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.
+        """
         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"
@@ -495,6 +522,17 @@ 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
@@ -1022,7 +1060,8 @@ Examples:
 
             # Try to use better PDF parsers first, but only if PDFs are requested
             documents = []
-            docs_path = Path(docs_dir)
+            # Use resolved absolute paths to avoid mismatches (symlinks, relative vs absolute)
+            docs_path = Path(docs_dir).resolve()
 
             # Check if we should process PDFs
             should_process_pdfs = custom_file_types is None or ".pdf" in custom_file_types
@@ -1031,10 +1070,15 @@ 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
-                        if self._should_exclude_file(relative_path, gitignore_matches):
+                        # Use absolute path for gitignore matching
+                        if self._should_exclude_file(file_path_resolved, gitignore_matches):
                             continue
                     except ValueError:
                         # Skip files that can't be made relative to docs_path
@@ -1077,10 +1121,11 @@ Examples:
                 ) -> bool:
                     """Return True if file should be included (not excluded)"""
                     try:
-                        docs_path_obj = Path(docs_dir)
-                        file_path_obj = Path(file_path)
-                        relative_path = file_path_obj.relative_to(docs_path_obj)
-                        return not self._should_exclude_file(relative_path, gitignore_matches)
+                        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)
                     except (ValueError, OSError):
                         return True  # Include files that can't be processed
 
@@ -1170,13 +1215,8 @@ Examples:
         if use_ast:
             print("🧠 Using AST-aware chunking for code files")
             try:
-                # 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
+                # Import enhanced chunking utilities from packaged module
+                from .chunking_utils import create_text_chunks
 
                 # Use enhanced chunking with AST support
                 all_texts = create_text_chunks(
@@ -1191,7 +1231,9 @@ Examples:
                 )
 
             except ImportError as e:
-                print(f"⚠️  AST chunking not available ({e}), falling back to traditional chunking")
+                print(
+                    f"⚠️  AST chunking utilities not available in package ({e}), falling back to traditional chunking"
+                )
                 use_ast = False
 
         if not use_ast:

packages/leann-mcp/README.md

@@ -2,6 +2,8 @@
 
 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 = "0.3.2"
+version = "0.3.4"
 description = "LEANN - The smallest vector index in the world. RAG Everything with LEANN!"
 readme = "README.md"
 requires-python = ">=3.9"

pyproject.toml

@@ -99,6 +99,7 @@ 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"

uv.lock

@@ -1,5 +1,5 @@
 version = 1
-revision = 3
+revision = 2
 requires-python = ">=3.9"
 resolution-markers = [
     "python_full_version >= '3.12'",
@@ -201,7 +201,7 @@ wheels = [
 [[package]]
 name = "astchunk"
 version = "0.1.0"
-source = { registry = "https://pypi.org/simple" }
+source = { editable = "packages/astchunk-leann" }
 dependencies = [
     { name = "numpy", version = "2.0.2", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version < '3.10'" },
     { name = "numpy", version = "2.2.6", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version == '3.10.*'" },
@@ -214,10 +214,31 @@ dependencies = [
     { name = "tree-sitter-python" },
     { name = "tree-sitter-typescript" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/db/2a/7a35e2fac7d550265ae2ee40651425083b37555f921d1a1b77c3f525e0df/astchunk-0.1.0.tar.gz", hash = "sha256:f4dff0ef8b3b3bcfeac363384db1e153f74d4c825dc2e35864abfab027713be4", size = 18093, upload-time = "2025-06-19T04:37:25.34Z" }
-wheels = [
-    { url = "https://files.pythonhosted.org/packages/be/84/5433ab0e933b572750cb16fd7edf3d6c7902b069461a22ec670042752a4d/astchunk-0.1.0-py3-none-any.whl", hash = "sha256:33ada9fc3620807fdda5846fa1948af463f281a60e0d43d4f3782b6dbb416d24", size = 15396, upload-time = "2025-06-19T04:37:23.87Z" },
+
+[package.metadata]
+requires-dist = [
+    { name = "black", marker = "extra == 'dev'", specifier = ">=22.0.0" },
+    { name = "flake8", marker = "extra == 'dev'", specifier = ">=5.0.0" },
+    { name = "isort", marker = "extra == 'dev'", specifier = ">=5.10.0" },
+    { name = "mypy", marker = "extra == 'dev'", specifier = ">=1.0.0" },
+    { name = "myst-parser", marker = "extra == 'docs'", specifier = ">=0.18.0" },
+    { name = "numpy", specifier = ">=1.20.0" },
+    { name = "pre-commit", marker = "extra == 'dev'", specifier = ">=2.20.0" },
+    { name = "pyrsistent", specifier = ">=0.18.0" },
+    { name = "pytest", marker = "extra == 'dev'", specifier = ">=7.0.0" },
+    { name = "pytest", marker = "extra == 'test'", specifier = ">=7.0.0" },
+    { name = "pytest-cov", marker = "extra == 'dev'", specifier = ">=4.0.0" },
+    { name = "pytest-cov", marker = "extra == 'test'", specifier = ">=4.0.0" },
+    { name = "pytest-xdist", marker = "extra == 'test'", specifier = ">=2.5.0" },
+    { name = "sphinx", marker = "extra == 'docs'", specifier = ">=5.0.0" },
+    { name = "sphinx-rtd-theme", marker = "extra == 'docs'", specifier = ">=1.0.0" },
+    { name = "tree-sitter", specifier = ">=0.20.0" },
+    { name = "tree-sitter-c-sharp", specifier = ">=0.20.0" },
+    { name = "tree-sitter-java", specifier = ">=0.20.0" },
+    { name = "tree-sitter-python", specifier = ">=0.20.0" },
+    { name = "tree-sitter-typescript", specifier = ">=0.20.0" },
 ]
+provides-extras = ["dev", "docs", "test"]
 
 [[package]]
 name = "asttokens"
@@ -1564,7 +1585,7 @@ name = "importlib-metadata"
 version = "8.7.0"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
-    { name = "zipp" },
+    { name = "zipp", marker = "python_full_version < '3.10'" },
 ]
 sdist = { url = "https://files.pythonhosted.org/packages/76/66/650a33bd90f786193e4de4b3ad86ea60b53c89b669a5c7be931fac31cdb0/importlib_metadata-8.7.0.tar.gz", hash = "sha256:d13b81ad223b890aa16c5471f2ac3056cf76c5f10f82d6f9292f0b415f389000", size = 56641, upload-time = "2025-04-27T15:29:01.736Z" }
 wheels = [
@@ -2117,7 +2138,7 @@ wheels = [
 
 [[package]]
 name = "leann-backend-diskann"
-version = "0.3.2"
+version = "0.3.3"
 source = { editable = "packages/leann-backend-diskann" }
 dependencies = [
     { name = "leann-core" },
@@ -2129,14 +2150,14 @@ dependencies = [
 
 [package.metadata]
 requires-dist = [
-    { name = "leann-core", specifier = "==0.3.2" },
+    { name = "leann-core", specifier = "==0.3.3" },
     { name = "numpy" },
     { name = "protobuf", specifier = ">=3.19.0" },
 ]
 
 [[package]]
 name = "leann-backend-hnsw"
-version = "0.3.2"
+version = "0.3.3"
 source = { editable = "packages/leann-backend-hnsw" }
 dependencies = [
     { name = "leann-core" },
@@ -2149,7 +2170,7 @@ dependencies = [
 
 [package.metadata]
 requires-dist = [
-    { name = "leann-core", specifier = "==0.3.2" },
+    { name = "leann-core", specifier = "==0.3.3" },
     { name = "msgpack", specifier = ">=1.0.0" },
     { name = "numpy" },
     { name = "pyzmq", specifier = ">=23.0.0" },
@@ -2157,7 +2178,7 @@ requires-dist = [
 
 [[package]]
 name = "leann-core"
-version = "0.3.2"
+version = "0.3.3"
 source = { editable = "packages/leann-core" }
 dependencies = [
     { name = "accelerate" },
@@ -2297,7 +2318,7 @@ test = [
 
 [package.metadata]
 requires-dist = [
-    { name = "astchunk", specifier = ">=0.1.0" },
+    { name = "astchunk", editable = "packages/astchunk-leann" },
     { name = "beautifulsoup4", marker = "extra == 'documents'", specifier = ">=4.13.0" },
     { name = "black", marker = "extra == 'dev'", specifier = ">=23.0" },
     { name = "boto3" },