next-ai-draw-io/README.md

# Next AI Draw.io

A next.js web application that integrates AI capabilities with draw.io diagrams. This app allows you to create, modify, and enhance diagrams through natural language commands and AI-assisted visualization.

https://github.com/user-attachments/assets/b2eef5f3-b335-4e71-a755-dc2e80931979

Demo site: [https://next-ai-draw-io.vercel.app](https://next-ai-draw-io.vercel.app)

## Features

-   **LLM-Powered Diagram Creation**: Leverage Large Language Models to create and manipulate draw.io diagrams directly through natural language commands
-   **Image-Based Diagram Replication**: Upload existing diagrams or images and have the AI replicate and enhance them automatically
-   **Diagram History**: Comprehensive version control that tracks all changes, allowing you to view and restore previous versions of your diagrams before the AI editing.
-   **Interactive Chat Interface**: Communicate with AI to refine your diagrams in real-time
-   **AWS Architecture Diagram Support**: Specialized support for generating AWS architecture diagrams
-   **Animated Connectors**: Create dynamic and animated connectors between diagram elements for better visualization

## **Examples**

Here are some example prompts and their generated diagrams:

<div align="center">
<table width="100%">
  <tr>
    <td width="50%" valign="top">
      <strong>GCP architecture diagram</strong><br />
      <p><strong>Prompt:</strong> Generate a GCP architecture diagram with **GCP icons**. In this diagram, users connect to a frontend hosted on an instance.</p>
      <img src="./public/gcp_demo.svg" alt="GCP Architecture Diagram" width="480" />
    </td>
    <td width="50%" valign="top">
      <strong>AWS architecture diagram</strong><br />
      <p><strong>Prompt:</strong> Generate a AWS architecture diagram with **AWS icons**. In this diagram, users connect to a frontend hosted on an instance.</p>
      <img src="./public/aws_demo.svg" alt="AWS Architecture Diagram" width="480" />
    </td>
  </tr>
  <tr>
    <td width="50%" valign="top">
      <strong>Azure architecture diagram</strong><br />
      <p><strong>Prompt:</strong> Generate a Azure architecture diagram with **Azure icons**. In this diagram, users connect to a frontend hosted on an instance.</p>
      <img src="./public/azure_demo.svg" alt="Azure Architecture Diagram" width="480" />
    </td>
    <td width="50%" valign="top">
      <strong>Animated transformer connectors</strong><br />
      <p><strong>Prompt:</strong> Give me a **animated connector** diagram of transformer's architecture.</p>
      <img src="./public/animated_connectors.svg" alt="Transformer Architecture with Animated Connectors" width="480" />
    </td>
  </tr>
  <tr>
    <td colspan="2" valign="top" align="center">
      <strong>Cat sketch prompt</strong><br />
      <p><strong>Prompt:</strong> Draw a cute cat for me.</p>
      <img src="./public/cat_demo.svg" alt="Cat Drawing" width="260" />
    </td>
  </tr>
</table>
</div>

## How It Works

The application uses the following technologies:

-   **Next.js**: For the frontend framework and routing
-   **@ai-sdk/react**: For the chat interface and AI interactions
-   **react-drawio**: For diagram representation and manipulation

Diagrams are represented as XML that can be rendered in draw.io. The AI processes your commands and generates or modifies this XML accordingly.

## Multi-Provider Support

-   AWS Bedrock (default)
-   OpenAI / OpenAI-compatible APIs (via `OPENAI_BASE_URL`)
-   Anthropic
-   Google AI
-   Azure OpenAI
-   Ollama

Note that `claude-sonnet-4-5` has trained on draw.io diagrams with AWS logos, so if you want to create AWS architecture diagrams, this is the best choice.

## Getting Started

### Installation

1. Clone the repository:

```bash
git clone https://github.com/DayuanJiang/next-ai-draw-io
cd next-ai-draw-io
```

2. Install dependencies:

```bash
npm install
# or
yarn install
```

3. Configure your AI provider:

Create a `.env.local` file in the root directory:

```bash
cp env.example .env.local
```

Edit `.env.local` and configure your chosen provider:

-   Set `AI_PROVIDER` to your chosen provider (bedrock, openai, anthropic, google, azure, ollama)
-   Set `AI_MODEL` to the specific model you want to use
-   Add the required API keys for your provider

See the [Multi-Provider Support](#multi-provider-support) section above for provider-specific configuration examples.

4. Run the development server:

```bash
npm run dev
```

5. Open [http://localhost:3000](http://localhost:3000) in your browser to see the application.

## Deployment

The easiest way to deploy your Next.js app is to use the [Vercel Platform](https://vercel.com/new) from the creators of Next.js.

Check out the [Next.js deployment documentation](https://nextjs.org/docs/app/building-your-application/deploying) for more details.

Or you can deploy by this button.
[![Deploy with Vercel](https://vercel.com/button)](https://vercel.com/new/clone?repository-url=https%3A%2F%2Fgithub.com%2FDayuanJiang%2Fnext-ai-draw-io)

Be sure to **set the environment variables** in the Vercel dashboard as you did in your local `.env.local` file.

## Project Structure

```
app/                  # Next.js application routes and pages
  extract_xml.ts      # Utilities for XML processing
components/           # React components
  chat-input.tsx      # User input component for AI interaction
  chatPanel.tsx       # Chat interface with diagram control
  ui/                 # UI components (buttons, cards, etc.)
lib/                  # Utility functions and helpers
  utils.ts            # General utilities including XML conversion
public/               # Static assets including example images
```

## TODOs

-   [x] Allow the LLM to modify the XML instead of generating it from scratch everytime.
-   [x] Improve the smoothness of shape streaming updates.
-   [x] Add multiple AI provider support (OpenAI, Anthropic, Google, Azure, Ollama)
-   [ ] Solve the bug that generation will fail for session that longer than 60s.

## License

This project is licensed under the MIT License.

## Support & Contact

For support or inquiries, please open an issue on the GitHub repository or contact the maintainer at:

-   Email: me[at]jiang.jp

---