# OpenAI Models Viewer

A web-based interface for browsing and interacting with OpenAI-compatible API endpoints. This application allows you to manage multiple server connections, view available models, and chat with AI models directly from your browser.

## Features

- **Multi-Server Management**: Add and manage multiple OpenAI-compatible endpoints
- **Model Discovery**: Browse and view all available models from configured servers
- **Interactive Chat**: Chat directly with AI models through a clean web interface
- **Local Storage**: Securely stores server configurations in browser localStorage
- **Responsive Design**: Works on desktop and mobile devices

## Project Structure

```
├── app.py              # Flask backend server
├── requirements.txt    # Python dependencies
├── static/
│   ├── index.html      # Main HTML interface
│   ├── script.js       # Client-side JavaScript logic
│   └── style.css       # Styling and layout
```

## Getting Started

### Prerequisites

- Python 3.7+
- pip (Python package manager)

### Installation

1. Clone the repository:
```bash
git clone <repository-url>
cd openai-models-viewer
```

2. Install Python dependencies:
```bash
pip install -r requirements.txt
```

3. Run the application:
```bash
python app.py
```

The application will start on `http://localhost:5000` by default.

### Usage

1. **Add a Server**:
   - Click the gear icon next to the server selector
   - Enter a server name (e.g., "OpenAI Production")
   - Enter the API endpoint URL (e.g., `https://api.openai.com`)
   - Enter your API key
   - Click "Add Server"

2. **View Models**:
   - Select a configured server from the dropdown
   - Models will automatically load and display

3. **Chat with Models**:
   - Click on any model to open the chat interface
   - Type your message and press Enter or click Send
   - View the AI's response in real-time

## Development

### Running with Custom Port

```bash
python app.py 8080
```

### Docker Support

Build and run with Docker:

```bash
docker build -t openai-models-viewer .
docker run -p 5000:5000 openai-models-viewer
```

## API Endpoints

The application connects to standard OpenAI-compatible endpoints:
- `/models` - List available models
- `/v1/chat/completions` - Chat completion endpoint

## Security

- API keys are stored locally in browser localStorage
- All communication happens directly between your browser and the API endpoints
- No server-side storage of sensitive information

## Contributing

1. Fork the repository
2. Create your feature branch
3. Commit your changes
4. Push to the branch
5. Open a pull request

## License

This project is licensed under the MIT License - see the LICENSE file for details.

## Acknowledgments

- Built with Flask (Python web framework)
- Uses modern JavaScript for client-side functionality
- Designed with responsive CSS for cross-device compatibility