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

# RAG • AI Agent SDK

> rag: Lazy-loaded RAG instance for advanced retrieval with citations.

# rag

<div className="flex items-center gap-2">
  <Badge color="purple">Method</Badge>
</div>

> This is a method of the [**Agent**](../classes/Agent) class in the [**agent**](../modules/agent) module.

Lazy-loaded RAG instance for advanced retrieval with citations.

Returns RAG instance configured with agent's knowledge and retrieval\_config.
Returns None if no knowledge is configured.

## Signature

```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
def rag() -> Any
```

### Returns

<ResponseField name="Returns" type="Any">
  The result of the operation.
</ResponseField>

## Usage

```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
agent = Agent(knowledge=["doc.pdf"], retrieval_config={"citations": True})
    result = agent.rag.query("What is the main finding?")
    print(result.answer)
    for citation in result.citations:
        print(f"[{citation.id}] {citation.source}")
```

## Uses

* `RAGConfig`
* `to_rag_config`
* `RAG`
* `logging.warning`

## Source

<Card title="View on GitHub" icon="github" href="https://github.com/MervinPraison/PraisonAI/blob/main/src/praisonai-agents/praisonaiagents/agent/agent.py#L2933">
  `praisonaiagents/agent/agent.py` at line 2933
</Card>

***

## Related Documentation

<CardGroup cols={2}>
  <Card title="RAG Concept" icon="magnifying-glass" href="/docs/concepts/rag" />

  <Card title="RAG Overview" icon="database" href="/docs/rag/overview" />

  <Card title="Chunking Strategies" icon="scissors" href="/docs/rag/strategies/overview" />
</CardGroup>