​
代码

cookbook/agent_concepts/vector_dbs/chroma_db.py
from agno.agent import Agent
from agno.knowledge.pdf_url import PDFUrlKnowledgeBase
from agno.vectordb.chroma import ChromaDb

# 初始化 ChromaDB
vector_db = ChromaDb(collection="recipes", path="tmp/chromadb", persistent_client=True)

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

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

# 创建并使用 Agent
agent = Agent(knowledge=knowledge_base, show_tool_calls=True)
agent.print_response("Show me how to make Tom Kha 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。

python3 -m venv .venv
source .venv/bin/activate
2

安装库

pip install -U chromadb pypdf openai agno
3

运行 Agent

python cookbook/agent_concepts/vector_dbs/chroma_db.py