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 +1,77 @@
+import httpx
+import asyncio
+
+
+async def main():
+    base_url = "http://localhost:9621"
+
+    async with httpx.AsyncClient(timeout=120.0) as client:
+        print("--- INSERT ---")
+        docs = [
+            "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.",
+            "LightRAG combines knowledge graph and vector retrieval for enhanced RAG applications.",
+            "FastMCP is a framework for building MCP servers in Python.",
+        ]
+        r = await client.post(f"{base_url}/documents/texts", json={"texts": docs})
+        r.raise_for_status()
+        print(f"Inserted: {r.json()}")
+
+        print("\n--- QUERY (mix mode) ---")
+        r = await client.post(
+            f"{base_url}/query/data",
+            json={
+                "query": "Tell me about programming languages",
+                "mode": "mix",
+                "only_need_context": True,
+                "top_k": 60,
+            },
+        )
+        r.raise_for_status()
+        result = r.json()
+        print(f"mode=mix keys: {list(result.keys())}")
+        if "chunks" in result:
+            print(f"  chunks: {len(result['chunks'])} returned")
+            for c in result["chunks"][:2]:
+                print(f"    - {c.get('content', '')[:100]}...")
+
+        print("\n--- QUERY (local mode) ---")
+        r = await client.post(
+            f"{base_url}/query/data",
+            json={
+                "query": "What is Python?",
+                "mode": "local",
+                "only_need_context": True,
+                "top_k": 60,
+            },
+        )
+        r.raise_for_status()
+        result = r.json()
+        print(f"mode=local keys: {list(result.keys())}")
+        if "chunks" in result:
+            print(f"  chunks: {len(result['chunks'])} returned")
+
+        print("\n--- QUERY (global mode) ---")
+        r = await client.post(
+            f"{base_url}/query/data",
+            json={
+                "query": "What topics are covered?",
+                "mode": "global",
+                "only_need_context": True,
+                "top_k": 60,
+            },
+        )
+        r.raise_for_status()
+        result = r.json()
+        print(f"mode=global keys: {list(result.keys())}")
+        if "entities" in result:
+            print(f"  entities: {len(result['entities'])} returned")
+        if "relationships" in result:
+            print(f"  relationships: {len(result['relationships'])} returned")
+
+    print("\nDone!")
+
+
+if __name__ == "__main__":
+    asyncio.run(main())