langchain-astradb

import os from langchain_astradb import AstraDBVectorStore from langchain_openai import OpenAIEmbeddings from langchain_core.documents import Document # Ensure you have your Astra DB credentials and OpenAI API key set as environment variables ASTRA_DB_API_ENDPOINT = os.environ.get('ASTRA_DB_API_ENDPOINT', 'https://your.api.endpoint') ASTRA_DB_APPLICATION_TOKEN = os.environ.get('ASTRA_DB_APPLICATION_TOKEN', 'AstraCS:...') OPENAI_API_KEY = os.environ.get('OPENAI_API_KEY', 'sk-...') if not all([ASTRA_DB_API_ENDPOINT, ASTRA_DB_APPLICATION_TOKEN, OPENAI_API_KEY]): print("Please set ASTRA_DB_API_ENDPOINT, ASTRA_DB_APPLICATION_TOKEN, and OPENAI_API_KEY environment variables.") else: print("Connecting to Astra DB Vector Store...") embeddings = OpenAIEmbeddings(api_key=OPENAI_API_KEY) # Initialize the vector store vector_store = AstraDBVectorStore( embedding=embeddings, collection_name="my_documents_collection", api_endpoint=ASTRA_DB_API_ENDPOINT, token=ASTRA_DB_APPLICATION_TOKEN, ) # Add documents docs = [ Document(page_content="LangChain provides tools for building LLM applications.", metadata={"source": "langchain"}), Document(page_content="Astra DB is a serverless vector-capable database.", metadata={"source": "astradb"}) ] vector_store.add_documents(docs) print(f"Added {len(docs)} documents to the collection.") # Perform a similarity search query = "What is Astra DB?" results = vector_store.similarity_search(query, k=1) print(f"\nSimilarity search results for '{query}':") for doc in results: print(f"- Content: {doc.page_content}, Source: {doc.metadata.get('source')}")