llama-index-vector-stores-chroma

import os import chromadb from llama_index.core import VectorStoreIndex, SimpleDirectoryReader, StorageContext, Settings from llama_index.embeddings.huggingface import HuggingFaceEmbedding from llama_index.vector_stores.chroma import ChromaVectorStore # --- Configuration --- # For a fully local setup, use a local LLM and Embedding model. # If using OpenAI, uncomment and set API key: # from llama_index.llms.openai import OpenAI # os.environ["OPENAI_API_KEY"] = os.environ.get("OPENAI_API_KEY", "") # Settings.llm = OpenAI() # Using a local embedding model for demonstration without external API keys Settings.embed_model = HuggingFaceEmbedding(model_name="BAAI/bge-small-en-v1.5") # 1. Create a Chroma client and collection # Use EphemeralClient for in-memory, or PersistentClient for disk storage chroma_client = chromadb.EphemeralClient() # For persistent storage: chromadb.PersistentClient(path="./chroma_db") chroma_collection = chroma_client.create_collection("my_documents_collection") # 2. Set up the ChromaVectorStore vector_store = ChromaVectorStore(chroma_collection=chroma_collection) # 3. Create a StorageContext and link the vector store storage_context = StorageContext.from_defaults(vector_store=vector_store) # 4. Load documents (e.g., from a 'data' directory) # Create a dummy file for demonstration if 'data' doesn't exist if not os.path.exists("data"): os.makedirs("data") with open("data/example.txt", "w") as f: f.write("The quick brown fox jumps over the lazy dog. LlamaIndex is great.") documents = SimpleDirectoryReader("data").load_data() # 5. Create a VectorStoreIndex from documents # embed_model is implicitly used from Settings.embed_model index = VectorStoreIndex.from_documents(documents, storage_context=storage_context) # 6. Query the index query_engine = index.as_query_engine() response = query_engine.query("What is LlamaIndex?") print(response.response)