Milvus 集成

代码

cookbook/agent_concepts/vector_dbs/milvus.py

from agno.agent import Agent
from agno.knowledge.pdf_url import PDFUrlKnowledgeBase
from agno.vectordb.milvus import Milvus

COLLECTION_NAME = "thai-recipes"

vector_db = Milvus(collection=COLLECTION_NAME, url="http://localhost:6333")

knowledge_base = PDFUrlKnowledgeBase(
    urls=["https://agno-public.s3.amazonaws.com/recipes/ThaiRecipes.pdf"],
    vector_db=vector_db,
)

knowledge_base.load(recreate=False)  # 首次运行后注释此行

agent = Agent(knowledge=knowledge_base, show_tool_calls=True)
agent.print_response("List down the ingredients to make Massaman Gai", markdown=True)

用法

1. 创建虚拟环境

   打开 Terminal 并创建一个 python 虚拟环境。

   Mac

   python3 -m venv .venv
   source .venv/bin/activate
   

2. 安装库

   pip install -U pymilvus pypdf openai agno
   

3. 运行 Agent

   Mac

   python cookbook/agent_concepts/vector_dbs/milvus.py
   

Assistant

Responses are generated using AI and may contain mistakes.