feat: add lightrag-mcp MCP server + agent tooling

- Add AGENTS.md with repo guidelines - Add lightrag-mcp: FastMCP server exposing insert_documents() + query_documents() to LLM agents via stdio transport, talks to LightRAG REST API - Add scripts/patch-vllm-cpu.py for CPU inference patching - Add .env.vllm for vLLM configuration - Update flake.nix with expanded dev shell - Update .env.lightrag - Remove CLAUDE.md (replaced by AGENTS.md)
2026-04-19 21:46:47 +08:00
parent c5dc2cf637
commit 4495a3cc62
14 changed files with 3510 additions and 100 deletions
@@ -0,0 +1,83 @@
+import asyncio
+import os
+from mcp import ClientSession, StdioServerParameters
+from mcp.client.stdio import stdio_client
+
+
+async def main():
+    server = StdioServerParameters(
+        command="uv",
+        args=[
+            "run",
+            "--directory",
+            "/home/df/projects/rags/lightrag-mcp",
+            "python",
+            "main.py",
+        ],
+    )
+
+    async with stdio_client(server) as (read, write):
+        async with ClientSession(read, write) as session:
+            await session.initialize()
+
+            print("--- INSERT ---")
+            result = await session.call_tool(
+                "insert_documents",
+                arguments={
+                    "documents": [
+                        "Python is a high-level programming language known for its simplicity and readability.",
+                        "JavaScript was created in 1995 by Brendan Eich at Netscape.",
+                        "Machine learning is a subset of artificial intelligence that enables systems to learn from data.",
+                    ]
+                },
+            )
+            print(f"Insert result: {result.content[0].text[:200]}")
+
+            print("\n--- QUERY (mix) ---")
+            result = await session.call_tool(
+                "query_documents",
+                arguments={
+                    "query": "Tell me about programming languages",
+                    "mode": "mix",
+                    "top_k": 60,
+                },
+            )
+            import json
+
+            data = json.loads(result.content[0].text)
+            d = data.get("data", {})
+            print(f"Entities: {len(d.get('entities', []))}")
+            print(f"Relationships: {len(d.get('relationships', []))}")
+            print(f"Chunks: {len(d.get('chunks', []))}")
+            for c in d.get("chunks", [])[:2]:
+                print(f"  - {c.get('content', '')[:100]}")
+
+            print("\n--- QUERY (local) ---")
+            result = await session.call_tool(
+                "query_documents",
+                arguments={"query": "What is Python?", "mode": "local", "top_k": 60},
+            )
+            data = json.loads(result.content[0].text)
+            d = data.get("data", {})
+            print(f"Entities: {len(d.get('entities', []))}")
+            print(f"Chunks: {len(d.get('chunks', []))}")
+
+            print("\n--- QUERY (global) ---")
+            result = await session.call_tool(
+                "query_documents",
+                arguments={
+                    "query": "What topics are covered?",
+                    "mode": "global",
+                    "top_k": 60,
+                },
+            )
+            data = json.loads(result.content[0].text)
+            d = data.get("data", {})
+            print(f"Entities: {len(d.get('entities', []))}")
+            print(f"Relationships: {len(d.get('relationships', []))}")
+
+    print("\nDone!")
+
+
+if __name__ == "__main__":
+    asyncio.run(main())