> ## 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.

# OCR

> Extract text from images

OCR (Optical Character Recognition) extracts text from images.

```mermaid theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
graph LR
    subgraph "OCR"
        I[🖼️ Image] --> O[👁️ OCR]
        O --> T[📝 Text]
        T --> A[🤖 Agent]
    end
    
    classDef image fill:#6366F1,stroke:#7C90A0,color:#fff
    classDef text fill:#10B981,stroke:#7C90A0,color:#fff
    
    class I image
    class O,T,A text
```

## Quick Start

<Steps>
  <Step title="Process Image">
    ```rust theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
    use praisonai::{Agent, tool};

    #[tool]
    async fn extract_text(image_path: String) -> String {
        // OCR processing
        ocr::extract(&image_path).await
    }

    let agent = Agent::new()
        .name("Reader")
        .tool(extract_text)
        .build()?;

    agent.chat("Read the text from screenshot.png").await?;
    ```
  </Step>
</Steps>

***

## Supported Formats

| Format        | Extension       |
| ------------- | --------------- |
| PNG           | `.png`          |
| JPEG          | `.jpg`, `.jpeg` |
| PDF (scanned) | `.pdf`          |
| TIFF          | `.tiff`         |

***

## Related

<CardGroup cols={2}>
  <Card title="Documents" icon="file-lines" href="/docs/rust/documents">
    Document processing
  </Card>

  <Card title="Images" icon="image" href="/docs/rust/image">
    Image generation
  </Card>
</CardGroup>