> ## 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

> Retrieval-Augmented Generation

RAG (Retrieval-Augmented Generation) enhances agents with external knowledge.

```mermaid theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
graph LR
    subgraph "RAG Pipeline"
        Q[❓ Question] --> R[🔍 Retrieve]
        R --> D[📄 Documents]
        D --> A[🤖 Agent]
        A --> O[💬 Answer]
    end
    
    classDef input fill:#6366F1,stroke:#7C90A0,color:#fff
    classDef process fill:#F59E0B,stroke:#7C90A0,color:#fff
    classDef output fill:#10B981,stroke:#7C90A0,color:#fff
    
    class Q input
    class R,D,A process
    class O output
```

## Quick Start

<Steps>
  <Step title="Set Up RAG">
    ```rust theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
    use praisonai::{Agent, KnowledgeConfig};

    let config = KnowledgeConfig::new()
        .source("docs/")
        .chunk_size(1000)
        .retrieval_k(5);

    let agent = Agent::new()
        .name("RAG Bot")
        .knowledge(config)
        .build()?;

    agent.chat("Answer based on documents").await?;
    ```
  </Step>
</Steps>

***

## RAG Components

| Component | Description          |
| --------- | -------------------- |
| Loader    | Load documents       |
| Chunker   | Split into chunks    |
| Embedder  | Create vectors       |
| Retriever | Find relevant chunks |
| Reranker  | Improve relevance    |

***

## Related

<CardGroup cols={2}>
  <Card title="Knowledge" icon="book" href="/docs/rust/knowledge">
    Knowledge base
  </Card>

  <Card title="Chunking" icon="scissors" href="/docs/rust/chunking">
    Document chunking
  </Card>
</CardGroup>