llama-index-vector-stores-milvus

import os from llama_index.core import VectorStoreIndex, SimpleDirectoryReader from llama_index.vector_stores.milvus import MilvusVectorStore from llama_index.core.settings import Settings from llama_index.llms.openai import OpenAI from llama_index.embeddings.openai import OpenAIEmbedding # Set up OpenAI API key (replace with your actual key or use environment variable) os.environ["OPENAI_API_KEY"] = os.environ.get("OPENAI_API_KEY", "sk-YOUR_OPENAI_API_KEY") # Configure LlamaIndex settings Settings.llm = OpenAI(model="gpt-3.5-turbo") Settings.embed_model = OpenAIEmbedding(model="text-embedding-ada-002") # 1. Prepare some dummy data # Create a dummy data directory and file if they don't exist if not os.path.exists("data"): os.makedirs("data") with open("data/milvus_doc.txt", "w") as f: f.write("The Milvus vector database is designed for AI applications and similarity search. It supports efficient storage and querying of billions of vectors. LlamaIndex provides a robust framework to integrate with various vector stores, including Milvus, to build powerful RAG systems. This integration allows users to leverage Milvus's capabilities for high-performance vector search within their LlamaIndex applications.") # 2. Load documents documents = SimpleDirectoryReader("data").load_data() # 3. Initialize MilvusVectorStore (using Milvus Lite for local setup) # For Milvus Lite, uri='./milvus.db' is convenient. For a Milvus server, use 'http://localhost:19530' or your server address. # dim must match the dimension of your embedding model (e.g., 1536 for text-embedding-ada-002) vector_store = MilvusVectorStore( uri="./milvus_test.db", dim=Settings.embed_model.embed_dimension, collection_name="llama_index_milvus_collection", overwrite=True # Set to True for a fresh start, False to append ) # 4. Create an index index = VectorStoreIndex.from_documents(documents, vector_store=vector_store) # 5. Query the index query_engine = index.as_query_engine() response = query_engine.query("What is Milvus used for?") print(response) # To demonstrate loading an existing index (if overwrite was False or after a run) # vector_store_load = MilvusVectorStore( # uri="./milvus_test.db", # dim=Settings.embed_model.embed_dimension, # collection_name="llama_index_milvus_collection", # overwrite=False # ) # index_loaded = VectorStoreIndex.from_vector_store(vector_store_load) # response_loaded = index_loaded.as_query_engine().query("What is LlamaIndex?") # print(response_loaded)