LangServe + Rag Mongo

[simonprudhomme]

Hello everyone.

I just deployed the rag-mongo template with LangServe.

I would like to be able to change the collection when I send my request to this endpoint.

from rag_mongo import chain as rag_mongo_chain
add_routes(app, rag_mongo_chain, path="/rag-mongo")

Right now, the retriever is created/configured inside the packages chain.py.

# Set DB
if os.environ.get("MONGO_URI", None) is None:
    raise Exception("Missing `MONGO_URI` environment variable.")
MONGO_URI = os.environ["MONGO_URI"]

DB_NAME = "langchain-test-2"
COLLECTION_NAME = "test"
ATLAS_VECTOR_SEARCH_INDEX_NAME = "default"

client = MongoClient(MONGO_URI)
db = client[DB_NAME]
MONGODB_COLLECTION = db[COLLECTION_NAME]

# Read from MongoDB Atlas Vector Search
vectorstore = MongoDBAtlasVectorSearch.from_connection_string(
    MONGO_URI,
    DB_NAME + "." + COLLECTION_NAME,
    OpenAIEmbeddings(disallowed_special=()),
    index_name=ATLAS_VECTOR_SEARCH_INDEX_NAME,
)
retriever = vectorstore.as_retriever()