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

# Image & PDF Support

> Vision and document understanding with automatic base64 encoding

## Overview

The Read tool supports images and PDFs for Claude's vision and document understanding capabilities. File type is detected automatically based on extension, and content is base64-encoded for the LLM.

## Supported Formats

| Type   | Extensions                               | Max Size                         |
| ------ | ---------------------------------------- | -------------------------------- |
| Images | `.png`, `.jpg`, `.jpeg`, `.gif`, `.webp` | 5MB                              |
| PDFs   | `.pdf`                                   | 32MB                             |
| Text   | All others                               | No limit (supports offset/limit) |

## Usage

File type is detected by extension -- no special handling needed:

```rust theme={null}
// Images - automatically base64-encoded
handle.send_input("What's in screenshot.png?").await?;

// PDFs - automatically base64-encoded
handle.send_input("Summarize quarterly-report.pdf").await?;

// Multiple files
handle.send_input("Compare design-v1.png and design-v2.png").await?;
```

## Tool Result Types

The framework uses different content types internally:

```rust theme={null}
pub enum ToolResultData {
    Text(String),                    // Regular text files

    Image {                          // PNG, JPEG, GIF, WebP
        data: Vec<u8>,
        media_type: String,          // "image/png", etc.
    },

    Document {                       // PDF files
        data: Vec<u8>,
        media_type: String,          // "application/pdf"
        description: String,
    },
}
```

## Prompt Caching

Images and PDFs support prompt caching automatically:

```rust theme={null}
// First request: Image cached
handle.send_input("Analyze screenshot.png").await?;

// Second request within 5 min: Cache hit (90% savings)
handle.send_input("What colors are used in screenshot.png?").await?;
```

<Info>
  The last content block gets cache control applied automatically. This reduces costs when analyzing the same files multiple times.
</Info>

## File Attachments

Images and PDFs can also be sent via attachment tags:

```rust theme={null}
let input = r#"Analyze this error:
<vibe-work-attachment>./error.png</vibe-work-attachment>"#;

handle.send_input(input).await?;
```

See [File Attachments](/features/attachments) for details.

## Limitations

* **Extension-based detection**: File type is determined by extension, not file contents.
* **No streaming**: Files are read completely before processing.
* **No image generation**: The SDK only supports reading/analyzing images.
* **Provider support**: Image/PDF analysis requires Claude (AnthropicProvider). Other providers may not support these features.

## Next Steps

<CardGroup cols={2}>
  <Card title="File Attachments" href="/features/attachments">
    Attachment tags for files
  </Card>

  <Card title="Prompt Caching" href="/features/prompt-caching">
    Cache images/PDFs for cost savings
  </Card>
</CardGroup>