88 lines
2.8 KiB
Python
88 lines
2.8 KiB
Python
import os
|
|
import httpx
|
|
from mcp.server.fastmcp import FastMCP
|
|
from qdrant_client import QdrantClient
|
|
from qdrant_client.models import Distance, VectorParams, PointStruct
|
|
import uuid
|
|
import logging
|
|
|
|
# Configuration
|
|
QDRANT_URL = os.getenv("QDRANT_URL", "http://qdrant.openshift-gitops.svc:6333")
|
|
TEI_URL = os.getenv("TEI_URL", "http://text-embeddings.tei.svc.cluster.local:8080")
|
|
EMBEDDING_DIM = 768 # BAAI/bge-base-en-v1.5
|
|
|
|
# Initialize
|
|
mcp = FastMCP("knowledge-mcp")
|
|
qdrant = QdrantClient(url=QDRANT_URL)
|
|
|
|
def get_embedding(text: str) -> list[float]:
|
|
"""Get embedding from TEI."""
|
|
url = f"{TEI_URL}/embed" # Adjust based on TEI version, often /v1/embeddings or /embed
|
|
# Trying standard TEI /embed endpoint for raw lists
|
|
try:
|
|
response = httpx.post(url, json={"inputs": text}, timeout=10.0)
|
|
response.raise_for_status()
|
|
return response.json()[0]
|
|
except Exception as e:
|
|
# Fallback to OpenAI compatible endpoint if needed
|
|
logging.error(f"Embedding failed: {e}")
|
|
raise
|
|
|
|
@mcp.tool()
|
|
def create_notebook(name: str) -> str:
|
|
"""Create a new RAG notebook (Qdrant collection)."""
|
|
clean_name = name.lower().replace(" ", "-")
|
|
|
|
# Check if exists
|
|
if qdrant.collection_exists(clean_name):
|
|
return f"Notebook '{clean_name}' already exists."
|
|
|
|
qdrant.create_collection(
|
|
collection_name=clean_name,
|
|
vectors_config=VectorParams(size=EMBEDDING_DIM, distance=Distance.COSINE),
|
|
)
|
|
return f"Notebook '{clean_name}' created successfully."
|
|
|
|
@mcp.tool()
|
|
def add_source(notebook: str, text: str, source_name: str = "manual") -> str:
|
|
"""Add text content to a notebook. Ingests, chunks, and indexes."""
|
|
if not qdrant.collection_exists(notebook):
|
|
return f"Error: Notebook '{notebook}' does not exist."
|
|
|
|
# Very basic chunking for now
|
|
chunks = [text[i:i+500] for i in range(0, len(text), 500)]
|
|
points = []
|
|
|
|
for chunk in chunks:
|
|
vector = get_embedding(chunk)
|
|
points.append(PointStruct(
|
|
id=str(uuid.uuid4()),
|
|
vector=vector,
|
|
payload={"source": source_name, "text": chunk}
|
|
))
|
|
|
|
qdrant.upsert(collection_name=notebook, points=points)
|
|
return f"Added {len(points)} chunks from '{source_name}' to '{notebook}'."
|
|
|
|
@mcp.tool()
|
|
def query_notebook(notebook: str, query: str, limit: int = 5) -> str:
|
|
"""Query the notebook for relevant context."""
|
|
if not qdrant.collection_exists(notebook):
|
|
return f"Error: Notebook '{notebook}' does not exist."
|
|
|
|
vector = get_embedding(query)
|
|
hits = qdrant.search(
|
|
collection_name=notebook,
|
|
query_vector=vector,
|
|
limit=limit
|
|
)
|
|
|
|
results = []
|
|
for hit in hits:
|
|
results.append(f"--- (Score: {hit.score:.2f}) ---\n{hit.payload.get('text', '')}\n")
|
|
|
|
return "\n".join(results)
|
|
|
|
if __name__ == "__main__":
|
|
mcp.run()
|