DatraAI (SynthGen)

A SaaS platform for generating privacy-safe synthetic data using SDV (Synthetic Data Vault) with an AI-powered chat interface.

🚀 Features

• AI-Powered Chat Interface - Conversational interface for generating synthetic data
• SDV Integration - Uses CTGAN and GaussianCopula models for high-quality synthetic data
• Privacy-Safe - Generate realistic data without exposing sensitive information
• Multiple File Formats - Support for CSV and Excel uploads
• Real-time Job Tracking - Monitor generation progress with live updates

🏗️ Architecture

├── backend/          # FastAPI server
│   ├── core/         # Core utilities (Supabase, Mistral AI)
│   ├── routes/       # API endpoints
│   └── services/     # Business logic (SDV, file handling)
│
├── frontend/         # Next.js 15 (App Router)
│   ├── app/          # Pages and API routes
│   ├── components/   # React components
│   ├── hooks/        # Custom React hooks
│   └── lib/          # Utilities and API client

🛠️ Tech Stack

Backend

• FastAPI - Modern Python web framework
• SDV - Synthetic Data Vault for data generation
• Supabase - Authentication, database, and storage
• Mistral AI - LLM for chat interface

Frontend

• Next.js 15 - React framework with App Router
• TypeScript - Type-safe JavaScript
• TailwindCSS - Utility-first CSS
• shadcn/ui - UI component library

📦 Installation

Prerequisites

• Python 3.9+
• Node.js 18+
• Supabase account
• Mistral AI API key

Backend Setup

cd backend

# Create virtual environment
python -m venv venv
.\venv\Scripts\activate  # Windows
# source venv/bin/activate  # macOS/Linux

# Install dependencies
pip install -r requirements.txt

# Configure environment
cp .env.example .env
# Edit .env with your credentials

# Run server
uvicorn main:app --reload --host 0.0.0.0 --port 8000

Frontend Setup

cd frontend

# Install dependencies
npm install

# Configure environment
# Create .env.local with:
# NEXT_PUBLIC_SUPABASE_URL=your_supabase_url
# NEXT_PUBLIC_SUPABASE_ANON_KEY=your_anon_key
# NEXT_PUBLIC_API_URL=http://localhost:8000

# Run development server
npm run dev

🔧 Environment Variables

Backend (.env)

SUPABASE_URL=your_supabase_url
SUPABASE_SERVICE_ROLE_KEY=your_service_role_key
MISTRAL_API_KEY=your_mistral_api_key

Frontend (.env.local)

NEXT_PUBLIC_SUPABASE_URL=your_supabase_url
NEXT_PUBLIC_SUPABASE_ANON_KEY=your_anon_key
NEXT_PUBLIC_API_URL=http://localhost:8000

📖 API Documentation

Once the backend is running, visit:

• Swagger UI: http://localhost:8000/docs
• ReDoc: http://localhost:8000/redoc

🔐 Security

• Backend uses SERVICE_ROLE_KEY (bypasses RLS) - server-side only
• Frontend uses ANON_KEY - respects Row Level Security
• Signed URLs expire after 1 hour
• Maximum upload size: 50MB

📄 License

MIT License - see LICENSE for details.

🤝 Contributing

1. Fork the repository
2. Create your feature branch (git checkout -b feature/amazing-feature)
3. Commit your changes (git commit -m 'Add amazing feature')
4. Push to the branch (git push origin feature/amazing-feature)
5. Open a Pull Request