> ## 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.

# Vision

> Image understanding capabilities

Vision enables agents to understand and analyze images.

```mermaid theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
graph LR
    subgraph "Vision"
        I[🖼️ Image] --> A[🤖 Agent]
        A --> U[💡 Understanding]
    end
    
    classDef image fill:#6366F1,stroke:#7C90A0,color:#fff
    classDef understanding fill:#10B981,stroke:#7C90A0,color:#fff
    
    class I image
    class A,U understanding
```

## Quick Start

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

    let agent = Agent::new()
        .name("Vision Bot")
        .model("gpt-4o")  // Vision-capable model
        .build()?;

    agent.chat_with_image(
        "Describe this image",
        "photo.png"
    ).await?;
    ```
  </Step>
</Steps>

***

## Vision Models

| Model              | Capability   |
| ------------------ | ------------ |
| `gpt-4o`           | Full vision  |
| `claude-3-opus`    | Full vision  |
| `llama-3.2-vision` | Local vision |

***

## Related

<CardGroup cols={2}>
  <Card title="Images" icon="image" href="/docs/rust/image">
    Image generation
  </Card>

  <Card title="OCR" icon="eye" href="/docs/rust/ocr">
    Text extraction
  </Card>
</CardGroup>