langchain-pinecone

import os from langchain_pinecone import PineconeVectorStore from langchain_openai import OpenAIEmbeddings from langchain_core.documents import Document from pinecone import Pinecone, ServerlessSpec # --- Configuration (replace with your actual keys and environment) --- # It's recommended to set these as environment variables. PINECONE_API_KEY = os.environ.get("PINECONE_API_KEY", "YOUR_PINECONE_API_KEY") PINECONE_ENVIRONMENT = os.environ.get("PINECONE_ENVIRONMENT", "gcp-starter") # e.g., 'us-west-2' OPENAI_API_KEY = os.environ.get("OPENAI_API_KEY", "YOUR_OPENAI_API_KEY") if PINECONE_API_KEY == "YOUR_PINECONE_API_KEY" or OPENAI_API_KEY == "YOUR_OPENAI_API_KEY": print("Warning: Please set PINECONE_API_KEY and OPENAI_API_KEY environment variables.") print("Quickstart will likely fail due to missing credentials.") index_name = "my-langchain-test-index" dimension = 1536 # OpenAI text-embedding-ada-002 model dimension metric = "cosine" # --- Initialize Pinecone Client (pinecone-client v3.x recommended) --- try: pc = Pinecone(api_key=PINECONE_API_KEY, environment=PINECONE_ENVIRONMENT) except Exception as e: print(f"Error initializing Pinecone client: {e}") exit(1) # --- Create/Connect to Pinecone Index --- if index_name not in pc.list_indexes().names(): print(f"Creating Pinecone index '{index_name}'...") pc.create_index( name=index_name, dimension=dimension, metric=metric, spec=ServerlessSpec(cloud="aws", region="us-west-2") # Adjust spec as needed ) print(f"Index '{index_name}' created.") else: print(f"Connecting to existing Pinecone index '{index_name}'.") # --- Initialize Embeddings Model --- embeddings = OpenAIEmbeddings(api_key=OPENAI_API_KEY) # --- Prepare Documents --- documents = [ Document(page_content="The quick brown fox jumps over the lazy dog."), Document(page_content="A computer is an electronic device that processes data."), Document(page_content="LangChain is a framework for developing applications powered by language models."), Document(page_content="Pinecone is a vector database for building AI applications.") ] # --- Create or Connect to the Vector Store from Documents --- # This method handles embedding and upserting the documents. print("Adding documents to Pinecone vector store...") vectorstore = PineconeVectorStore.from_documents( documents, embeddings, index_name=index_name ) print("Documents added.") # --- Perform a Similarity Search --- query = "What is LangChain?" print(f"\nPerforming similarity search for: '{query}'") results = vectorstore.similarity_search(query, k=1) print("\nSearch Results:") for doc in results: print(f"- Content: {doc.page_content}") # --- Optional: Clean up --- # print(f"\nDeleting index '{index_name}' for cleanup...") # pc.delete_index(index_name) # print(f"Index '{index_name}' deleted.")