> ## Documentation Index
> Fetch the complete documentation index at: https://agno-v2-docs-scavio-google-v2.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Multiple Knowledge Bases

> Serve a PgVector-backed knowledge agent and manage documents through AgentOS knowledge endpoints.

```python multiple_knowledge_bases.py theme={null}
"""
Multiple Knowledge Bases
========================

Demonstrates multiple knowledge bases.
"""

from agno.agent import Agent
from agno.db.json import JsonDb
from agno.knowledge.knowledge import Knowledge
from agno.models.openai import OpenAIChat
from agno.os import AgentOS
from agno.vectordb.pgvector import PgVector

# ---------------------------------------------------------------------------
# Create Example
# ---------------------------------------------------------------------------

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


vector_db = PgVector(table_name="vectors", db_url=db_url)
secondary_vector_db = PgVector(table_name="more_vectors", db_url=db_url)
contents_db = JsonDb(db_path="./agno_json_data", knowledge_table="main_knowledge")
secondary_contents_db = JsonDb(
    db_path="./agno_json_data_2", knowledge_table="secondary_knowledge"
)

# Create knowledge bases
knowledge_base = Knowledge(
    name="Main Knowledge Base",
    description="A simple knowledge base",
    contents_db=contents_db,
    vector_db=vector_db,
)

main_agent = Agent(
    name="Main Agent",
    model=OpenAIChat(id="gpt-4o"),
    knowledge=knowledge_base,
    add_datetime_to_context=True,
    markdown=True,
    db=contents_db,
)

agent_os = AgentOS(
    description="Example app for basic agent with knowledge capabilities",
    id="knowledge-demo",
    agents=[main_agent],
)
app = agent_os.get_app()

# ---------------------------------------------------------------------------
# Run Example
# ---------------------------------------------------------------------------

if __name__ == "__main__":
    """ Run your AgentOS:
    Now you can interact with your knowledge base using the API. Examples:
    - http://localhost:8001/knowledge/{id}/documents
    - http://localhost:8001/knowledge/{id}/documents/123
    - http://localhost:8001/knowledge/{id}/documents?agent_id=123
    - http://localhost:8001/knowledge/{id}/documents?limit=10&page=0&sort_by=created_at&sort_order=desc
    """
    agent_os.serve(app="multiple_knowledge_bases:app", reload=True)
```

## Run the Example

<Steps>
  <Snippet file="create-venv-step.mdx" />

  <Step title="Install dependencies">
    ```bash theme={null}
    uv pip install -U "agno[os]" "psycopg[binary]" openai pgvector
    ```
  </Step>

  <Step title="Export your OpenAI API key">
    <CodeGroup>
      ```bash Mac/Linux theme={null}
      export OPENAI_API_KEY="your_openai_api_key_here"
      ```

      ```bash Windows theme={null}
      $Env:OPENAI_API_KEY="your_openai_api_key_here"
      ```
    </CodeGroup>
  </Step>

  <Snippet file="run-pgvector-step.mdx" />

  <Step title="Run the example">
    Save the code above as `multiple_knowledge_bases.py`, then run:

    ```bash theme={null}
    python multiple_knowledge_bases.py
    ```
  </Step>
</Steps>

Full source: [cookbook/05\_agent\_os/advanced\_demo/multiple\_knowledge\_bases.py](https://github.com/agno-agi/agno/blob/main/cookbook/05_agent_os/advanced_demo/multiple_knowledge_bases.py)