> ## 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.

# PgVector 代理知识

## 设置

```shell theme={null}
docker run -d \
  -e POSTGRES_DB=ai \
  -e POSTGRES_USER=ai \
  -e POSTGRES_PASSWORD=ai \
  -e PGDATA=/var/lib/postgresql/data/pgdata \
  -v pgvolume:/var/lib/postgresql/data \
  -p 5532:5432 \
  --name pgvector \
  agnohq/pgvector:16
```

## 示例

```python agent_with_knowledge.py theme={null}
from agno.agent import Agent
from agno.models.openai import OpenAIChat
from agno.knowledge.pdf_url import PDFUrlKnowledgeBase
from agno.vectordb.pgvector import PgVector, SearchType

db_url = "postgresql+psycopg://ai:ai@localhost:5532/ai"
knowledge_base = PDFUrlKnowledgeBase(
    urls=["https://agno-public.s3.amazonaws.com/recipes/ThaiRecipes.pdf"],
    vector_db=PgVector(table_name="recipes", db_url=db_url, search_type=SearchType.hybrid),
)
# 加载知识库：首次运行后注释掉此行
knowledge_base.load(recreate=True, upsert=True)

agent = Agent(
    model=OpenAIChat(id="gpt-4o"),
    knowledge=knowledge_base,
    # 添加一个读取聊天记录的工具。
    read_chat_history=True,
    show_tool_calls=True,
    markdown=True,
    # debug_mode=True,
)
agent.print_response("How do I make chicken and galangal in coconut milk soup", stream=True)
agent.print_response("What was my last question?", stream=True)
```

<Card title="异步支持 ⚡">
  <div className="mt-2">
    <p>
      PgVector 还支持异步操作，能够实现并发，从而带来更好的性能。
    </p>

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

    from agno.agent import Agent
    from agno.knowledge.pdf_url import PDFUrlKnowledgeBase
    from agno.vectordb.pgvector import PgVector

    db_url = "postgresql+psycopg://ai:ai@localhost:5532/ai"

    vector_db = PgVector(table_name="recipes", db_url=db_url)

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

    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))

        # 创建并使用代理
        asyncio.run(agent.aprint_response("How to make Tom Kha Gai", markdown=True))
    ```

    <Tip className="mt-4">
      在处理高吞吐量应用程序时，请使用 <code>aload()</code> 和 <code>aprint\_response()</code> 方法与 <code>asyncio.run()</code> 一起使用，以实现非阻塞操作。
    </Tip>
  </div>
</Card>

## PgVector 参数

<Snippet file="vectordb_pgvector_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/pgvector_db/pg_vector.py)
* 查看 [Cookbook (异步)](https://github.com/agno-agi/agno/blob/main/cookbook/agent_concepts/knowledge/vector_dbs/pgvector_db/async_pg_vector.py)