← back

Sematic

A voice-to-diagram whiteboard that won at Hack the North

TypeScript · AWScode ↗site ↗

AI-Powered Diagram Builder

A collaborative whiteboard application with AI-powered diagram generation using voice and text commands.

Features

Architecture

Quick Start

Prerequisites

Local Development

  1. Clone the repository

    git clone <your-repo-url>
    cd sematic
    
  2. Install dependencies

    npm install
    cd frontend && npm install
    
  3. Set up environment variables

    # Create .env file in project root
    GEMINI_API_KEY=your_gemini_api_key_here
    
  4. Run locally

    # Start frontend
    cd frontend && npm start
    
    # The app will run in local mode with simulation
    

Production Deployment

  1. Configure AWS credentials

    aws configure
    # Or use AWS environment variables
    
  2. Set Gemini API key

    export GEMINI_API_KEY="your_gemini_api_key_here"
    
  3. Deploy to AWS

    npx ampx sandbox --once
    # For permanent deployment:
    # npx ampx generate --out deployment
    
  4. Access your app

    • The deployment will provide a CloudFront URL
    • Amplify will automatically configure authentication and API endpoints

Environment Configuration

The app automatically switches between local and production modes:

No code changes needed - the same codebase works in both environments!

Project Structure

├── amplify/                 # AWS Amplify configuration
│   ├── auth/               # Cognito authentication
│   ├── data/               # DynamoDB schema  
│   ├── functions/          # Lambda functions
│   └── storage/            # S3 configuration
├── frontend/               # React application
│   ├── src/
│   │   ├── components/     # React components
│   │   ├── services/       # API services
│   │   └── ...
│   └── package.json
├── .env                    # Environment variables (local)
└── README.md

API Reference

Whiteboard Operations

AI Processing

Real-time Collaboration

Contributing

  1. Fork the repository
  2. Create a feature branch
  3. Make your changes
  4. Test locally and with production build
  5. Submit a pull request

License

MIT License - see LICENSE file for details

Support

For issues and questions: