Files
LEANN/packages/leann-core/src/leann/mcp.py
ww26 a85d0ad4a7 Feature/optimize ollama batching (#152)
* feat: add metadata output to search results

- Add --show-metadata flag to display file paths in search results
- Preserve document metadata (file_path, file_name, timestamps) during chunking
- Update MCP tool schema to support show_metadata parameter
- Enhance CLI search output to display metadata when requested
- Fix pre-existing bug: args.backend -> args.backend_name

Resolves yichuan-w/LEANN#144

* fix: resolve ZMQ linking issues in Python extension

- Use pkg_check_modules IMPORTED_TARGET to create PkgConfig::ZMQ
- Set PKG_CONFIG_PATH to prioritize ARM64 Homebrew on Apple Silicon
- Override macOS -undefined dynamic_lookup to force proper symbol resolution
- Use PUBLIC linkage for ZMQ in faiss library for transitive linking
- Mark cppzmq includes as SYSTEM to suppress warnings

Fixes editable install ZMQ symbol errors while maintaining compatibility
across Linux, macOS Intel, and macOS ARM64 platforms.

* style: apply ruff formatting

* chore: update faiss submodule to use ww2283 fork

Use ww2283/faiss fork with fix/zmq-linking branch to resolve CI checkout
failures. The ZMQ linking fixes are not yet merged upstream.

* feat: implement true batch processing for Ollama embeddings

Migrate from deprecated /api/embeddings to modern /api/embed endpoint
which supports batch inputs. This reduces HTTP overhead by sending
32 texts per request instead of making individual API calls.

Changes:
- Update endpoint from /api/embeddings to /api/embed
- Change parameter from 'prompt' (single) to 'input' (array)
- Update response parsing for batch embeddings array
- Increase timeout to 60s for batch processing
- Improve error handling for batch requests

Performance:
- Reduces API calls by 32x (batch size)
- Eliminates HTTP connection overhead per text
- Note: Ollama still processes batch items sequentially internally

Related: #151

* fall back to original faiss as i merge the PR

---------

Co-authored-by: yichuan520030910320 <yichuan_wang@berkeley.edu>
2025-10-30 16:39:14 -07:00

162 lines
6.4 KiB
Python
Executable File

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