TBNilles/LEANN
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge pull request #19 from yichuan-w/feature/claude-code-research

Browse Source 
Feature/claude code research
This commit is contained in:
Andy Lee
2025-08-05 23:02:34 -07:00
committed by GitHub
parent 4cb544ee38
commit 8b22d2b5d3
8 changed files with 586 additions and 28 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
packages/leann-backend-diskann/third_party/DiskANN vendored

Submodule packages/leann-backend-diskann/third_party/DiskANN updated: af2a26481e...67a2611ad1

1
packages/leann-core/pyproject.toml
View File

@@ -44,6 +44,7 @@ colab = [
[project.scripts]
leann = "leann.cli:main"
leann_mcp = "leann.mcp:main"
[tool.setuptools.packages.find]
where = ["src"]

247
packages/leann-core/src/leann/cli.py
View File

@@ -41,13 +41,23 @@ def extract_pdf_text_with_pdfplumber(file_path: str) -> str:
class LeannCLI:
def __init__(self):
self.indexes_dir = Path.home() / ".leann" / "indexes"
# Always use project-local .leann directory (like .git)
self.indexes_dir = Path.cwd() / ".leann" / "indexes"
self.indexes_dir.mkdir(parents=True, exist_ok=True)
# Default parser for documents
self.node_parser = SentenceSplitter(
chunk_size=256, chunk_overlap=128, separator=" ", paragraph_separator="\n\n"
)
# Code-optimized parser
self.code_parser = SentenceSplitter(
chunk_size=512, # Larger chunks for code context
chunk_overlap=50, # Less overlap to preserve function boundaries
separator="\n", # Split by lines for code
paragraph_separator="\n\n", # Preserve logical code blocks
)
def get_index_path(self, index_name: str) -> str:
index_dir = self.indexes_dir / index_name
return str(index_dir / "documents.leann")
@@ -76,7 +86,9 @@ Examples:
# Build command
build_parser = subparsers.add_parser("build", help="Build document index")
build_parser.add_argument("index_name", help="Index name")
build_parser.add_argument("--docs", type=str, required=True, help="Documents directory")
build_parser.add_argument(
"--docs", type=str, default=".", help="Documents directory (default: current directory)"
)
build_parser.add_argument(
"--backend", type=str, default="hnsw", choices=["hnsw", "diskann"]
)
@@ -138,37 +150,109 @@ Examples:
return parser
def register_project_dir(self):
"""Register current project directory in global registry"""
global_registry = Path.home() / ".leann" / "projects.json"
global_registry.parent.mkdir(exist_ok=True)
current_dir = str(Path.cwd())
# Load existing registry
projects = []
if global_registry.exists():
try:
import json
with open(global_registry) as f:
projects = json.load(f)
except Exception:
projects = []
# Add current directory if not already present
if current_dir not in projects:
projects.append(current_dir)
# Save registry
import json
with open(global_registry, "w") as f:
json.dump(projects, f, indent=2)
def list_indexes(self):
print("Stored LEANN indexes:")
if not self.indexes_dir.exists():
# Get all project directories with .leann
global_registry = Path.home() / ".leann" / "projects.json"
all_projects = []
if global_registry.exists():
try:
import json
with open(global_registry) as f:
all_projects = json.load(f)
except Exception:
pass
# Filter to only existing directories with .leann
valid_projects = []
for project_dir in all_projects:
project_path = Path(project_dir)
if project_path.exists() and (project_path / ".leann" / "indexes").exists():
valid_projects.append(project_path)
# Add current project if it has .leann but not in registry
current_path = Path.cwd()
if (current_path / ".leann" / "indexes").exists() and current_path not in valid_projects:
valid_projects.append(current_path)
if not valid_projects:
print("No indexes found. Use 'leann build <name> --docs <dir>' to create one.")
return
index_dirs = [d for d in self.indexes_dir.iterdir() if d.is_dir()]
total_indexes = 0
current_dir = Path.cwd()
if not index_dirs:
print("No indexes found. Use 'leann build <name> --docs <dir>' to create one.")
return
for project_path in valid_projects:
indexes_dir = project_path / ".leann" / "indexes"
if not indexes_dir.exists():
continue
print(f"Found {len(index_dirs)} indexes:")
for i, index_dir in enumerate(index_dirs, 1):
index_name = index_dir.name
status = "✓" if self.index_exists(index_name) else "✗"
index_dirs = [d for d in indexes_dir.iterdir() if d.is_dir()]
if not index_dirs:
continue
print(f" {i}. {index_name} [{status}]")
if self.index_exists(index_name):
index_dir / "documents.leann.meta.json"
size_mb = sum(f.stat().st_size for f in index_dir.iterdir() if f.is_file()) / (
1024 * 1024
)
print(f" Size: {size_mb:.1f} MB")
# Show project header
if project_path == current_dir:
print(f"\n📁 Current project ({project_path}):")
else:
print(f"\n📂 {project_path}:")
if index_dirs:
example_name = index_dirs[0].name
print("\nUsage:")
print(f' leann search {example_name} "your query"')
print(f" leann ask {example_name} --interactive")
for index_dir in index_dirs:
total_indexes += 1
index_name = index_dir.name
meta_file = index_dir / "documents.leann.meta.json"
status = "✓" if meta_file.exists() else "✗"
print(f" {total_indexes}. {index_name} [{status}]")
if status == "✓":
size_mb = sum(f.stat().st_size for f in index_dir.iterdir() if f.is_file()) / (
1024 * 1024
)
print(f" Size: {size_mb:.1f} MB")
if total_indexes > 0:
print(f"\nTotal: {total_indexes} indexes across {len(valid_projects)} projects")
print("\nUsage (current project only):")
# Show example from current project
current_indexes_dir = current_dir / ".leann" / "indexes"
if current_indexes_dir.exists():
current_index_dirs = [d for d in current_indexes_dir.iterdir() if d.is_dir()]
if current_index_dirs:
example_name = current_index_dirs[0].name
print(f' leann search {example_name} "your query"')
print(f" leann ask {example_name} --interactive")
def load_documents(self, docs_dir: str):
print(f"Loading documents from {docs_dir}...")
@@ -203,17 +287,125 @@ Examples:
documents.extend(default_docs)
# Load other file types with default reader
code_extensions = [
# Original document types
".txt",
".md",
".docx",
# Code files for Claude Code integration
".py",
".js",
".ts",
".jsx",
".tsx",
".java",
".cpp",
".c",
".h",
".hpp",
".cs",
".go",
".rs",
".rb",
".php",
".swift",
".kt",
".scala",
".r",
".sql",
".sh",
".bash",
".zsh",
".fish",
".ps1",
".bat",
# Config and markup files
".json",
".yaml",
".yml",
".xml",
".toml",
".ini",
".cfg",
".conf",
".html",
".css",
".scss",
".less",
".vue",
".svelte",
# Data science
".ipynb",
".R",
".py",
".jl",
]
other_docs = SimpleDirectoryReader(
docs_dir,
recursive=True,
encoding="utf-8",
required_exts=[".txt", ".md", ".docx"],
required_exts=code_extensions,
).load_data(show_progress=True)
documents.extend(other_docs)
all_texts = []
# Define code file extensions for intelligent chunking
code_file_exts = {
".py",
".js",
".ts",
".jsx",
".tsx",
".java",
".cpp",
".c",
".h",
".hpp",
".cs",
".go",
".rs",
".rb",
".php",
".swift",
".kt",
".scala",
".r",
".sql",
".sh",
".bash",
".zsh",
".fish",
".ps1",
".bat",
".json",
".yaml",
".yml",
".xml",
".toml",
".ini",
".cfg",
".conf",
".html",
".css",
".scss",
".less",
".vue",
".svelte",
".ipynb",
".R",
".jl",
}
for doc in documents:
nodes = self.node_parser.get_nodes_from_documents([doc])
# Check if this is a code file based on source path
source_path = doc.metadata.get("source", "")
is_code_file = any(source_path.endswith(ext) for ext in code_file_exts)
# Use appropriate parser based on file type
parser = self.code_parser if is_code_file else self.node_parser
nodes = parser.get_nodes_from_documents([doc])
for node in nodes:
all_texts.append(node.get_content())
@@ -226,6 +418,8 @@ Examples:
index_dir = self.indexes_dir / index_name
index_path = self.get_index_path(index_name)
print(f"📂 Indexing: {Path(docs_dir).resolve()}")
if index_dir.exists() and not args.force:
print(f"Index '{index_name}' already exists. Use --force to rebuild.")
return
@@ -255,6 +449,9 @@ Examples:
builder.build_index(index_path)
print(f"Index built at {index_path}")
# Register this project directory in global registry
self.register_project_dir()
async def search_documents(self, args):
index_name = args.index_name
query = args.query

134
packages/leann-core/src/leann/mcp.py Executable file
View File

@@ -0,0 +1,134 @@
#!/usr/bin/env python3
import json
import os
import subprocess
import sys
def handle_request(request):
if request.get("method") == "initialize":
return {
"jsonrpc": "2.0",
"id": request.get("id"),
"result": {
"capabilities": {"tools": {}},
"protocolVersion": "2024-11-05",
"serverInfo": {"name": "leann-mcp", "version": "1.0.0"},
},
}
elif request.get("method") == "tools/list":
return {
"jsonrpc": "2.0",
"id": request.get("id"),
"result": {
"tools": [
{
"name": "leann_search",
"description": "Search LEANN index",
"inputSchema": {
"type": "object",
"properties": {
"index_name": {"type": "string"},
"query": {"type": "string"},
"top_k": {"type": "integer", "default": 5},
},
"required": ["index_name", "query"],
},
},
{
"name": "leann_ask",
"description": "Ask question using LEANN RAG",
"inputSchema": {
"type": "object",
"properties": {
"index_name": {"type": "string"},
"question": {"type": "string"},
},
"required": ["index_name", "question"],
},
},
{
"name": "leann_list",
"description": "List all LEANN indexes",
"inputSchema": {"type": "object", "properties": {}},
},
]
},
}
elif request.get("method") == "tools/call":
tool_name = request["params"]["name"]
args = request["params"].get("arguments", {})
# Set working directory and environment
env = os.environ.copy()
cwd = "/Users/andyl/Projects/LEANN-RAG"
try:
if tool_name == "leann_search":
cmd = [
"leann",
"search",
args["index_name"],
args["query"],
"--recompute-embeddings",
f"--top-k={args.get('top_k', 5)}",
]
result = subprocess.run(cmd, capture_output=True, text=True, cwd=cwd, env=env)
elif tool_name == "leann_ask":
cmd = f'echo "{args["question"]}" | leann ask {args["index_name"]} --recompute-embeddings --llm ollama --model qwen3:8b'
result = subprocess.run(
cmd, shell=True, capture_output=True, text=True, cwd=cwd, env=env
)
elif tool_name == "leann_list":
result = subprocess.run(
["leann", "list"], capture_output=True, text=True, cwd=cwd, env=env
)
return {
"jsonrpc": "2.0",
"id": request.get("id"),
"result": {
"content": [
{
"type": "text",
"text": result.stdout
if result.returncode == 0
else f"Error: {result.stderr}",
}
]
},
}
except Exception as e:
return {
"jsonrpc": "2.0",
"id": request.get("id"),
"error": {"code": -1, "message": str(e)},
}
def main():
for line in sys.stdin:
try:
request = json.loads(line.strip())
response = handle_request(request)
if response:
print(json.dumps(response))
sys.stdout.flush()
except Exception as e:
error_response = {
"jsonrpc": "2.0",
"id": None,
"error": {"code": -1, "message": str(e)},
}
print(json.dumps(error_response))
sys.stdout.flush()
if __name__ == "__main__":
main()

69
packages/leann-mcp/README.md Normal file
View File

@@ -0,0 +1,69 @@
# LEANN Claude Code Integration
Intelligent code assistance using LEANN's vector search directly in Claude Code.
## Prerequisites
First, install LEANN CLI globally:
```bash
uv tool install leann
```
This makes the `leann` command available system-wide, which `leann_mcp` requires.
## Quick Setup
Add the LEANN MCP server to Claude Code:
```bash
claude mcp add leann-server -- leann_mcp
```
## Available Tools
- **`leann_list`** - List available indexes across all projects
- **`leann_search`** - Search code and documents with semantic queries
- **`leann_ask`** - Ask questions and get AI-powered answers from your codebase
## Quick Start
```bash
# Build an index for your project
leann build my-project
# Start Claude Code
claude
```
Then in Claude Code:
```
Help me understand this codebase. List available indexes and search for authentication patterns.
```
<p align="center">
<img src="../../assets/claude_code_leann.png" alt="LEANN in Claude Code" width="80%">
</p>
## How It Works
- **`leann`** - Core CLI tool for indexing and searching (installed globally)
- **`leann_mcp`** - MCP server that wraps `leann` commands for Claude Code integration
- Claude Code calls `leann_mcp`, which executes `leann` commands and returns results
## File Support
Python, JavaScript, TypeScript, Java, Go, Rust, SQL, YAML, JSON, and 30+ more file types.
## Storage
- Project indexes in `.leann/` directory (like `.git`)
- Global project registry at `~/.leann/projects.json`
- Multi-project support built-in
## Removing
```bash
claude mcp remove leann-server
```