> ## Documentation Index
> Fetch the complete documentation index at: https://ikun.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# MongoDB Agent 连接知识

## 设置

请按照 [MongoDB 设置指南](https://www.mongodb.com/docs/atlas/getting-started/) 中的说明获取连接字符串。

安装 MongoDB 包

```shell theme={null}
pip install "pymongo[srv]"
```

## 示例

```python agent_with_knowledge.py theme={null}
from agno.agent import Agent
from agno.knowledge.pdf_url import PDFUrlKnowledgeBase
from agno.vectordb.mongodb import MongoDb

# MongoDB Atlas 连接字符串
"""
示例连接字符串：
"mongodb+srv://<username>:<password>@cluster0.mongodb.net/?retryWrites=true&w=majority"
"mongodb://localhost/?directConnection=true"
"""
mdb_connection_string = ""

knowledge_base = PDFUrlKnowledgeBase(
    urls=["https://agno-public.s3.amazonaws.com/recipes/ThaiRecipes.pdf"],
    vector_db=MongoDb(
        collection_name="recipes",
        db_url=mdb_connection_string,
        wait_until_index_ready=60,
        wait_after_insert=300
    ),
)  # 请根据您的需求调整 wait_after_insert 和 wait_until_index_ready

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

agent = Agent(knowledge=knowledge_base, show_tool_calls=True)
agent.print_response("How to make Thai curry?", markdown=True)
```

<Card title="异步支持 ⚡">
  <div className="mt-2">
    <p>
      MongoDB 也支持异步操作，可实现并发处理，从而提高性能。
    </p>

    ```python async_mongodb.py theme={null}
    import asyncio

    from agno.agent import Agent
    from agno.knowledge.pdf_url import PDFUrlKnowledgeBase
    from agno.vectordb.mongodb import MongoDb

    # MongoDB Atlas 连接字符串
    """
    示例连接字符串：
    "mongodb+srv://<username>:<password>@cluster0.mongodb.net/?retryWrites=true&w=majority"
    "mongodb://localhost:27017/agno?authSource=admin"
    """
    mdb_connection_string = "mongodb+srv://<username>:<password>@cluster0.mongodb.net/?retryWrites=true&w=majority"

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

    # 创建并使用 Agent
    agent = Agent(knowledge=knowledge_base, show_tool_calls=True)

    if __name__ == "__main__":
        # 首次运行后注释掉此行
        asyncio.run(knowledge_base.aload(recreate=False))

        asyncio.run(agent.aprint_response("How to make Thai curry?", markdown=True))
    ```

    <Tip className="mt-4">
      在对吞吐量要求较高的应用中，请使用 <code>aload()</code> 和 <code>aprint\_response()</code> 方法配合 <code>asyncio.run()</code> 来实现非阻塞操作。
    </Tip>
  </div>
</Card>

## MongoDB 参数

<Snippet file="vectordb_mongodb_params.mdx" />

## 开发者资源

* 查看 [Cookbook (同步)](https://github.com/agno-agi/agno/blob/main/cookbook/agent_concepts/knowledge/vector_dbs/mongo_db/mongo_db.py)
* 查看 [Cookbook (异步)](https://github.com/agno-agi/agno/blob/main/cookbook/agent_concepts/knowledge/vector_dbs/mongo_db/async_mongo_db.py)