Skip to main content

Milvus

Distributed vector database for large-scale similarity search.

Setup

# Docker
docker run -d -p 19530:19530 milvusdb/milvus

pip install pymilvus

Quick Start (Agent with Knowledge)

Use Milvus as a knowledge store with an agent:
from praisonaiagents import Agent

agent = Agent(
    name="Assistant",
    instructions="You are a helpful assistant with access to documents.",
    knowledge=["./docs/guide.pdf"]
)

agent.chat("What does the guide say?")

Advanced Usage (Direct Store)

from praisonai.persistence.factory import create_knowledge_store

store = create_knowledge_store("milvus", url="http://localhost:19530")

store.create_collection("documents", dimension=384)
store.insert("documents", [doc])
results = store.search("documents", query_embedding, limit=5)

Configuration

OptionDescription
urlMilvus server URL
collection_nameDefault collection name