langchain-chroma

import os from langchain_chroma import Chroma from langchain_openai import OpenAIEmbeddings from langchain_core.documents import Document from langchain_text_splitters import RecursiveCharacterTextSplitter # Set your OpenAI API key from environment variables os.environ["OPENAI_API_KEY"] = os.environ.get("OPENAI_API_KEY", "YOUR_OPENAI_API_KEY") # Sample documents raw_documents = [ "The quick brown fox jumps over the lazy dog.", "The cat sat on the mat.", "Chroma is an open-source vector database.", "LangChain provides tools for building LLM applications.", "RAG combines retrieval and generation for better answers." ] # 1. Split documents (optional but good practice for RAG) text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200) documents = [Document(page_content=d) for d in raw_documents] split_documents = text_splitter.split_documents(documents) # 2. Initialize embeddings embeddings = OpenAIEmbeddings() # 3. Create a Chroma vector store (in-memory for this example) # For persistence, pass a 'persist_directory' argument: persist_directory="./chroma_db" vector_store = Chroma( collection_name="my_documents_collection", embedding_function=embeddings, ) # Add documents to the vector store vector_store.add_documents(split_documents) # 4. Perform a similarity search query = "What is Chroma?" results = vector_store.similarity_search(query, k=1) print(f"Query: {query}") for doc in results: print(f"- Found document: {doc.page_content}")