> ## 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.

# Youtube知识库

> 了解如何在知识库中使用 YouTube 视频字幕。

**YouTubeKnowledgeBase** 遍历 YouTube URL 列表，提取视频字幕，将它们转换为向量嵌入，并将它们加载到向量数据库中。

## 用法

<Note>
  我们在此示例中使用本地 PgVector 数据库。[确保它正在运行](http://localhost:3333/vectordb/pgvector)
</Note>

```shell theme={null}
pip install bs4
```

```python knowledge_base.py theme={null}
from agno.knowledge.youtube import YouTubeKnowledgeBase
from agno.vectordb.pgvector import PgVector

knowledge_base = YouTubeKnowledgeBase(
    urls=["https://www.youtube.com/watch?v=CDC3GOuJyZ0"],
    # 表名: ai.website_documents
    vector_db=PgVector(
        table_name="youtube_documents",
        db_url="postgresql+psycopg://ai:ai@localhost:5532/ai",
    ),
)
```

然后将 `knowledge_base` 与 `Agent` 一起使用：

```python agent.py theme={null}
from agno.agent import Agent
from knowledge_base import knowledge_base

agent = Agent(
    knowledge=knowledge_base,
    search_knowledge=True,
)
agent.knowledge.load(recreate=False)

agent.print_response("Ask me about something from the knowledge base")
```

#### YouTubeKnowledgeBase 也支持异步加载。

```shell theme={null}
pip install qdrant-client
```

我们在此示例中使用本地 Qdrant 数据库。[确保它正在运行](https://docs.agno.com/vectordb/qdrant)

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

from agno.agent import Agent
from agno.knowledge.youtube import YouTubeKnowledgeBase, YouTubeReader
from agno.vectordb.qdrant import Qdrant

COLLECTION_NAME = "youtube-reader"

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

knowledge_base = YouTubeKnowledgeBase(
    urls=[
        "https://www.youtube.com/watch?v=CDC3GOuJyZ0",
        "https://www.youtube.com/watch?v=JbF_8g1EXj4",
    ],
    vector_db=vector_db,
    reader=YouTubeReader(chunk=True),
)

agent = Agent(
    knowledge=knowledge_base,
    search_knowledge=True,
)

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

    # 创建并使用代理
    asyncio.run(
        agent.aprint_response(
            "What is the major focus of the knowledge provided in both the videos, explain briefly.",
            markdown=True,
        )
    )
```

## 参数

| 参数       | 类型                        | 默认值    | 描述                                                                |
| -------- | ------------------------- | ------ | ----------------------------------------------------------------- |
| `urls`   | `List[str]`               | `[]`   | 要读取的视频的 URL                                                       |
| `reader` | `Optional[YouTubeReader]` | `None` | 一个 `YouTubeReader`，用于读取 URL 处的视频字幕，并将它们转换为 `Documents` 以便导入向量数据库。 |

`YouTubeKnowledgeBase` 是 [AgentKnowledge](/reference/knowledge/base) 类的一个子类，可以访问相同的参数。

## 开发者资源

* 查看 [同步加载食谱](https://github.com/agno-agi/agno/blob/main/cookbook/agent_concepts/knowledge/youtube_kb.py)
* 查看 [异步加载食谱](https://github.com/agno-agi/agno/blob/main/cookbook/agent_concepts/knowledge/youtube_kb_async.py)