MongoDB + RAG + Galileo Overview
MongoDB Atlas Vector Search lets you keep your knowledge base inside MongoDB while enjoying hybrid search and AI-ready workloads.
In this guide you’ll:
- Embed and store vectors in Atlas
- Setup Galileo
- Stream LangGraph traces to Galileo for end-to-end observability
Set up MongoDB
Sign up to MongoDB Atlas and set up your credentials. You can setup the vector store as follows:
from langchain_mongodb import MongoDBAtlasVectorSearch
from langchain_openai import OpenAIEmbeddings
from pymongo import MongoClient
client = MongoClient(MONGODB_URI)
DB_NAME = "rag_demo"
COLLECTION_NAME = "blog_vectors"
collection = client[DB_NAME][COLLECTION_NAME]
embeddings = OpenAIEmbeddings()
vector_store = MongoDBAtlasVectorSearch(
collection = collection,
embedding = embeddings,
index_name = "rag-index",
relevance_score_fn = "cosine"
)
Use Galileo for logging
import os
from galileo.handlers.langchain import GalileoCallback
# --- Galileo ---
os.environ["GALILEO_API_KEY"] = "<galileo-key>"
os.environ["GALILEO_PROJECT"] = "<galileo-project>"
os.environ["GALILEO_LOG_STREAM"] = "mongo_rag_demo"
galileo_handler = GalileoCallback()
Once the callback is created we can add it to the agent.
query = "What types of agent memory does Lilian Weng describe?"
inputs = {"messages": [HumanMessage(content=query)]}
result = graph.invoke(
inputs,
config={"recursion_limit": 5, "callbacks": [galileo_handler]}
)
Find the full notebook here
