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

# Chat with Orion

> Bridging computer-vision tools to AI agents through language.

<Card title="Try Orion" icon="comments" href="https://chat.vlm.run/?utm_source=docs&utm_medium=link&utm_campaign=chat" cta="Try now">
  Navigate over to [Chat](https://chat.vlm.run/?utm_source=docs\&utm_medium=link\&utm_campaign=chat) to interact with our visual AI models in real-time and explore their capabilities.
</Card>

Our [chat playground](https://chat.vlm.run/?utm_source=docs\&utm_medium=link\&utm_campaign=chat) provides an interactive interface for exploring visual AI capabilities of **VLM Run's Orion** family of visual agents through natural conversation. Upload images, documents, or videos and engage in dynamic conversations that leverage our advanced vision-language models for comprehensive analysis and structured data extraction.

<Frame caption="Orion teaser video showing off its capabilities.">
  <video width="100%" controls autoplay>
    <source src="https://storage.googleapis.com/vlm-data-public-prod/web/videos/orion-promo-video.mp4" type="video/mp4" />

    Your browser does not support the video tag.
  </video>
</Frame>

Our [chat](https://chat.vlm.run/?utm_source=docs\&utm_medium=link\&utm_campaign=chat) is built on the same powerful foundation as our [Structured Responses API](/capabilities/structured-responses), but provides an intuitive conversational interface that makes visual AI accessible to everyone - from developers to business users.

We are working on adding more capabilities to the chat, and you can expect to see more features and capabilities added in the coming months.

## Capability Showcase

Explore the full range of visual AI capabilities through interactive examples:

<AccordionGroup>
  <Accordion title="Image Understanding" icon="image">
    Analyze images with detailed captions, object detection, segmentation, and visual question answering. Perfect for content moderation, accessibility, and automated image analysis.

    <Frame caption="Image Understanding Capabilities">
      <img src="https://mintcdn.com/autonomiai/7LCH2ZD074tEU8dT/agents/assets/person-detection.jpg?fit=max&auto=format&n=7LCH2ZD074tEU8dT&q=85&s=d4c5b7fae815e5b344440a9788a36c8d" style={{ display: "block", margin: "0 auto" }} width="80%" data-path="agents/assets/person-detection.jpg" />
    </Frame>
  </Accordion>

  <Accordion title="Document Analysis" icon="file-invoice">
    Upload invoices, receipts, contracts, or any document and extract structured data automatically. The playground supports all our [pre-built document domains](/hub) including invoices, receipts, forms, and more.

    <Frame caption="Document Analysis in Chat Playground">
      <img src="https://mintcdn.com/autonomiai/n0UzFHKSRrWx1Yji/agents/assets/layout-detection-1.png?fit=max&auto=format&n=n0UzFHKSRrWx1Yji&q=85&s=a672a3e03fa028a0277f21170afebd0c" style={{ display: "block", margin: "0 auto" }} width="80%" data-path="agents/assets/layout-detection-1.png" />
    </Frame>
  </Accordion>

  <Accordion title="Video Generation" icon="video">
    Edit and generate images, and videos from text prompts or images. Get creative with your videos and images.

    <Frame caption="Image-to-Video Generation Features">
      <video src="https://storage.googleapis.com/vlm-data-public-prod/web/videos/videogen-image-to-image.mp4" width="100%" controls autoplay playsinline />
    </Frame>
  </Accordion>

  <Accordion title="Multi-Modal Conversations" icon="comments">
    Engage in rich conversations that combine text, images, and structured data. Ask follow-up questions, request modifications, and explore different analysis approaches.

    <Frame caption="Multi-Modal Chat Interface">
      <video src="https://storage.googleapis.com/vlm-data-public-prod/web/videos/steve-jobs-video-ai-v2.mp4" width="100%" controls autoplay playsinline />
    </Frame>
  </Accordion>
</AccordionGroup>

## Supported Content Types

The Chat Playground supports a wide range of visual content:

* **Images**: JPG, PNG, WebP (up to 10MB)
* **Documents**: PDF (up to 25MB, 30 pages max)
* **Videos**: MP4 (up to 100MB)
* **Audio**: MP3 (up to 25MB)

## Try our Chat Playground today

Head over to our [Chat Playground](https://chat.vlm.run) to start building your own visual AI workflows with [VLM Run](https://vlm.run). Sign-up for access on our [platform](https://app.vlm.run).