langchain-mongodb

import os from pymongo import MongoClient from langchain_mongodb.vectorstores import MongoDBAtlasVectorSearch # NOTE: Replace DummyEmbeddings with a real embedding model (e.g., OpenAIEmbeddings) # For a runnable example without extra API keys, we use a placeholder. class DummyEmbeddings: def embed_documents(self, texts): # Return a list of fixed-size vectors for each text return [[0.1] * 1536 for _ in texts] def embed_query(self, text): # Return a fixed-size vector for a single query return [0.1] * 1536 # Environment variables for MongoDB connection MONGODB_ATLAS_CLUSTER_URI = os.environ.get( "MONGODB_ATLAS_CLUSTER_URI", "mongodb://localhost:27017/" ) MONGODB_DATABASE = os.environ.get("MONGODB_DATABASE", "langchain_db") MONGODB_COLLECTION = os.environ.get("MONGODB_COLLECTION", "vector_collection") # Initialize MongoDB client and collection client = MongoClient(MONGODB_ATLAS_CLUSTER_URI) collection = client[MONGODB_DATABASE][MONGODB_COLLECTION] # Initialize embedding model (replace DummyEmbeddings with e.g., OpenAIEmbeddings) # embeddings = OpenAIEmbeddings(openai_api_key=os.environ.get("OPENAI_API_KEY")) embeddings = DummyEmbeddings() # Initialize MongoDB Atlas Vector Search # Ensure 'default' index exists in MongoDB Atlas on the specified collection vector_search = MongoDBAtlasVectorSearch( collection=collection, embedding=embeddings, index_name="default", # The name of your Atlas Search Vector Index ) # Add documents to the vector store docs = [ "The quick brown fox jumps over the lazy dog.", "A group of cats is called a clowder.", "Python is a high-level, interpreted programming language." ] vector_search.add_texts(docs) print(f"Added {len(docs)} documents to MongoDB Atlas Vector Search.") # Perform a similarity search query = "animals running" results = vector_search.similarity_search(query, k=1) print(f"Similarity search results for '{query}':") for res in results: print(f"- {res.page_content}") # Clean up (optional) - remove added documents # collection.delete_many({"text": {"$in": docs}}) # print("Cleaned up documents.")