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

# References Format

> Control how knowledge base references are formatted for the agent.

```python references_format.py theme={null}
"""
References Format
=============================

Control how knowledge base references are formatted for the agent.

By default, references are returned as JSON. Set references_format="yaml"
to return them as YAML instead.
"""

from agno.agent import Agent
from agno.knowledge.embedder.openai import OpenAIEmbedder
from agno.knowledge.knowledge import Knowledge
from agno.models.openai import OpenAIResponses
from agno.vectordb.pgvector import PgVector, SearchType

db_url = "postgresql+psycopg://ai:ai@localhost:5532/ai"
knowledge = Knowledge(
    vector_db=PgVector(
        table_name="recipes_yaml_demo",
        db_url=db_url,
        search_type=SearchType.hybrid,
        embedder=OpenAIEmbedder(id="text-embedding-3-small"),
    ),
)

# ---------------------------------------------------------------------------
# Create Agent
# ---------------------------------------------------------------------------
agent = Agent(
    model=OpenAIResponses(id="gpt-5.2"),
    knowledge=knowledge,
    search_knowledge=True,
    # Format knowledge references as YAML instead of the default JSON
    references_format="yaml",
    markdown=True,
)

# ---------------------------------------------------------------------------
# Run Agent
# ---------------------------------------------------------------------------
if __name__ == "__main__":
    knowledge.insert(url="https://agno-public.s3.amazonaws.com/recipes/ThaiRecipes.pdf")
    agent.print_response(
        "How do I make chicken and galangal in coconut milk soup?",
        stream=True,
    )
```

## Run the Example

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

  <Step title="Install dependencies">
    ```bash theme={null}
    uv pip install -U agno openai pgvector psycopg-binary pypdf sqlalchemy
    ```
  </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 `references_format.py`, then run:

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

Full source: [cookbook/02\_agents/07\_knowledge/references\_format.py](https://github.com/agno-agi/agno/blob/main/cookbook/02_agents/07_knowledge/references_format.py)