ChromaDB 代理知识

设置

pip install chromadb

示例

agent_with_knowledge.py

import typer
from rich.prompt import Prompt
from typing import Optional

from agno.agent import Agent
from agno.knowledge.pdf_url import PDFUrlKnowledgeBase
from agno.vectordb.chroma import ChromaDb

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

def pdf_agent(user: str = "user"):
    run_id: Optional[str] = None

    agent = Agent(
        run_id=run_id,
        user_id=user,
        knowledge_base=knowledge_base,
        use_tools=True,
        show_tool_calls=True,
        debug_mode=True,
    )
    if run_id is None:
        run_id = agent.run_id
        print(f"Started Run: {run_id}\n")
    else:
        print(f"Continuing Run: {run_id}\n")

    while True:
        message = Prompt.ask(f"[bold] :sunglasses: {user} [/bold]")
        if message in ("exit", "bye"):
            break
        agent.print_response(message)

if __name__ == "__main__":
    # Comment out after first run
    knowledge_base.load(recreate=False)

    typer.run(pdf_agent)

异步支持 ⚡

ChromaDB 也支持异步操作，可以实现并发并带来更好的性能。

async_chroma_db.py

# install chromadb - `pip install chromadb`

import asyncio

from agno.agent import Agent
from agno.knowledge.pdf_url import PDFUrlKnowledgeBase
from agno.vectordb.chroma import ChromaDb

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

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

# Create and use the agent
agent = Agent(knowledge=knowledge_base, show_tool_calls=True)

if __name__ == "__main__":
    # Comment out after first run
    asyncio.run(knowledge_base.aload(recreate=False))

    # Create and use the agent
    asyncio.run(agent.aprint_response("How to make Tom Kha Gai", markdown=True))

在吞吐量高的应用程序中使用 aload() 和 aprint_response() 方法配合 asyncio.run() 进行非阻塞操作。

ChromaDb 参数

参数	类型	默认值	描述
collection	str	-	要使用的 collection 的名称。
embedder	Embedder	OpenAIEmbedder()	用于嵌入文档内容的 embedder。
distance	Distance	cosine	要使用的距离度量。
path	str	"tmp/chromadb"	ChromaDB 数据将存储的路径。
persistent_client	bool	False	是否使用持久化的 ChromaDB 客户端。

开发者资源

• 查看 Cookbook (同步)
• 查看 Cookbook (异步)

Assistant

Responses are generated using AI and may contain mistakes.