> ## 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.

# Citations

> Track sources in agent responses

Agents can cite their sources - show where information comes from.

```mermaid theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
graph LR
    subgraph "Citation Flow"
        A[📚 Sources] --> B[🤖 Agent]
        B --> C[💬 Answer]
        C --> D[📖 Citations]
    end
    
    classDef source fill:#6366F1,stroke:#7C90A0,color:#fff
    classDef agent fill:#8B0000,stroke:#7C90A0,color:#fff
    classDef tool fill:#189AB4,stroke:#7C90A0,color:#fff
    classDef output fill:#10B981,stroke:#7C90A0,color:#fff
    
    class A source
    class B agent
    class C,D output
    classDef agent fill:#8B0000,color:#fff
    classDef tool fill:#189AB4,color:#fff

```

## Quick Start

<Steps>
  <Step title="Simple Usage">
    ```typescript theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
    import { Agent } from 'praisonai';

    const agent = new Agent({
      instructions: 'Answer using the provided documents',
      knowledge: './docs/',
      citations: true
    });

    const result = await agent.chat('What is the return policy?');
    console.log(result.content);
    // "You can return items within 30 days [1]"
    console.log(result.citations);
    // [{ id: 1, source: 'returns.md', text: '...' }]
    ```
  </Step>

  <Step title="With Configuration">
    ```typescript theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
    const agent = new Agent({
      citations: {
        format: 'inline',  // or 'footnote', 'endnotes'
        includePageNumbers: true
      }
    });
    ```
  </Step>
</Steps>

***

## User Interaction Flow

```mermaid theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
sequenceDiagram
    participant User
    participant Agent
    participant Knowledge
    
    User->>Agent: "What's the return policy?"
    Agent->>Knowledge: Search documents
    Knowledge-->>Agent: Relevant passages
    Agent->>Agent: Generate answer
    Agent-->>User: Answer + citations
```

***

## Configuration Levels

```typescript theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
// Level 1: Bool - Enable citations
const agent = new Agent({
  citations: true
});

// Level 2: String - Citation style
const agent = new Agent({
  citations: 'inline'  // 'inline', 'footnote', 'endnotes'
});

// Level 3: Dict - Full options
const agent = new Agent({
  citations: {
    format: 'footnote',
    includePageNumbers: true,
    maxCitations: 5,
    minRelevanceScore: 0.7
  }
});
```

***

## Citation Formats

| Format     | Example                       |
| ---------- | ----------------------------- |
| `inline`   | "Returns within 30 days \[1]" |
| `footnote` | "Returns within 30 days¹"     |
| `endnotes` | Citations listed at end       |

***

## API Reference

<Card title="Knowledge Module" icon="code" href="/docs/sdk/reference/typescript/modules/knowledge">
  Knowledge and citation support
</Card>

***

## Best Practices

<AccordionGroup>
  <Accordion title="Use with knowledge base">
    Citations work best when agent has documents to reference.
  </Accordion>

  <Accordion title="Set relevance threshold">
    Use `minRelevanceScore` to ensure quality citations.
  </Accordion>

  <Accordion title="Limit citation count">
    Too many citations can clutter responses.
  </Accordion>
</AccordionGroup>

***

## Related

<CardGroup cols={2}>
  <Card title="Knowledge" icon="brain" href="/docs/js/knowledge-base">
    Knowledge base
  </Card>

  <Card title="RAG" icon="book" href="/docs/js/rag-agent">
    Retrieval augmented generation
  </Card>
</CardGroup>