milvus-lite

from pymilvus import MilvusClient, DataType import os # Ensure a clean slate for demonstration if os.path.exists("milvus_demo.db"): os.remove("milvus_demo.db") # 1. Set up a Milvus client with a local file for persistence client = MilvusClient(uri="./milvus_demo.db") # 2. Create schema schema = MilvusClient.create_schema( auto_id=False, enable_dynamic_field=True, ) schema.add_field(field_name="id", datatype=DataType.INT64, is_primary=True) schema.add_field(field_name="vector", datatype=DataType.FLOAT_VECTOR, dim=5) schema.add_field(field_name="text", datatype=DataType.VARCHAR, max_length=256) # 3. Create a collection collection_name = "demo_collection" client.create_collection( collection_name=collection_name, schema=schema, # You can specify an index here, Milvus Lite will optimize internally # index_params=MilvusClient.prepare_index_params(metric_type="L2") ) # 4. Insert data data = [ {"id": 1, "vector": [0.1, 0.2, 0.3, 0.4, 0.5], "text": "The quick brown fox"}, {"id": 2, "vector": [0.5, 0.4, 0.3, 0.2, 0.1], "text": "Jumps over the lazy dog"}, {"id": 3, "vector": [0.8, 0.7, 0.6, 0.5, 0.4], "text": "A fast animal"}, ] client.insert(collection_name=collection_name, data=data) client.flush(collection_name=collection_name) # 5. Search for similar vectors search_vectors = [[0.15, 0.25, 0.35, 0.45, 0.55]] res = client.search( collection_name=collection_name, data=search_vectors, limit=2, output_fields=["text"], ) print("Search Results:", res) # 6. Query data by ID query_res = client.query(collection_name=collection_name, filter="id in", output_fields=["text"]) print("Query Results:", query_res) # Clean up (optional for next run) client.drop_collection(collection_name=collection_name) client.close() # Important to close client to ensure data is written to disk print("Milvus Lite demo finished successfully!")