PrompTab

Intelligent Chrome extension for prompt optimization using AI techniques including RAG, Chain-of-Thought, Role-playing, Few-shot learning and other.

Features

Core Functionality

• Intelligent Prompt Optimization: Automatic prompt improvement using AI techniques
• RAG System: Retrieval-Augmented Generation with vector knowledge base
• Interactive Variables: Create and manage variables in prompts for reusability
• Template Library: Save and organize frequently used prompts
• Direct Integration: Send optimized prompts to ChatGPT and Perplexity
• Multilingual Support: Russian and English languages

Advanced AI Techniques

• Chain-of-Thought: Step-by-step reasoning for complex prompts
• Role-playing: Context-aware persona-based optimization
• Few-shot Learning: Example-based prompt enhancement
• Vector Search: Semantic similarity for relevant examples
• Context Awareness: Intelligent context preservation

Architecture

Backend Stack

• Framework: FastAPI (Python 3.11+)
• Database: PostgreSQL 14+ with pgvector extension
• Vector Store: Sentence Transformers + pgvector
• LLM Integration: OpenAI, Perplexity, Ollama
• Caching: Redis for performance optimization
• Authentication: JWT-based security
• Monitoring: Prometheus + Grafana
• Container: Docker + Docker Compose

Frontend Stack

• Framework: React 18 + TypeScript
• Build System: Webpack 5 with optimization
• UI Library: Material-UI (MUI) v5
• State Management: React Query for server state
• Internationalization: i18next
• Extension: Chrome Extension Manifest V3
• Testing: Jest + React Testing Library

Infrastructure

• Database: PostgreSQL with pgvector for embeddings
• Cache: Redis for session and data caching
• LLM Services: Multiple AI provider integrations
• Monitoring: Prometheus metrics + Grafana dashboards
• Reverse Proxy: Nginx for production deployment
• Local LLM: Ollama for open-source model support

Installation

Prerequisites

• Docker and Docker Compose
• Node.js 18+ (for frontend development)
• Python 3.11+ (for backend development)
• PostgreSQL 14+ with pgvector extension
• Redis 7+

Quick Start with Docker

1. Clone the repository

git clone https://github.com/LISA-ITMO/promptab.git
cd promptab

2. Configure environment variables

cp .env.example .env
# Edit .env with your API keys and configuration

3. Start all services

docker-compose up -d

4. Install Chrome extension

• Open Chrome and go to chrome://extensions/
• Enable "Developer mode"
• Click "Load unpacked extension"
• Select the frontend/dist folder

Manual Setup

Backend Setup

cd backend
python -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate
pip install -r requirements.txt
pip install -r requirements-docs.txt

# Run database migrations
alembic upgrade head

# Start development server
uvicorn app.main:app --reload --host 0.0.0.0 --port 8000

Frontend Setup

cd frontend
npm install

# Development mode
npm start

# Build for production
npm run build

# Package extension
npm run package

Configuration

Environment Variables

Create .env file in the root directory:

# Database
POSTGRES_DB=promptab
POSTGRES_USER=promptab_user
POSTGRES_PASSWORD=your_password
DATABASE_URL=postgresql://promptab_user:your_password@localhost:5432/promptab

# Redis
REDIS_URL=redis://localhost:6379

# LLM API Keys
OPENAI_API_KEY=your_openai_key
ANTHROPIC_API_KEY=your_anthropic_key
PERPLEXITY_API_KEY=your_perplexity_key

# Security
SECRET_KEY=your_secret_key
JWT_ALGORITHM=HS256
ACCESS_TOKEN_EXPIRE_MINUTES=30

# Monitoring
SENTRY_DSN=your_sentry_dsn
PROMETHEUS_PORT=9090

# Ollama (Local LLM)
OLLAMA_BASE_URL=http://localhost:11434

API Configuration

The backend provides RESTful API endpoints:

• Authentication: /api/auth/
• Prompts: /api/prompts/
• Templates: /api/templates/
• Variables: /api/variables/
• Optimization: /api/optimize/
• Health Check: /health

Testing

Backend Tests

cd backend

# Run all tests
pytest

# Run with coverage
pytest --cov=app --cov-report=html

# Run specific test categories
pytest tests/test_api_prompts.py
pytest tests/test_services.py
pytest tests/test_models.py

Documentation

Backend Documentation

• Live Documentation: GitHub Pages
• API Reference: Complete API documentation with examples
• Architecture Guide: Detailed system architecture and design decisions
• Development Guide: Setup and development workflow

Building Documentation Locally

# Backend documentation
cd backend
./scripts/build_docs.sh

# View locally
cd docs/_build/html
python -m http.server 8000

CI/CD Pipeline

GitHub Actions Workflows

1. Documentation Pipeline (.github/workflows/docs.yml)
   • Automatic Sphinx documentation build
   • Quality checks and validation
   • Deployment to GitHub Pages

Quality Assurance

• Code Quality: ESLint, Prettier, Black, Ruff
• Type Checking: TypeScript, MyPy
• Security: Bandit, Safety
• Performance: Bundle analysis, load testing

Development

Project Structure

promptab/
├── backend/                 # FastAPI backend
│   ├── app/
│   │   ├── api/            # API endpoints
│   │   ├── core/           # Core configuration
│   │   ├── db/             # Database models
│   │   ├── models/         # Pydantic models
│   │   ├── schemas/        # API schemas
│   │   └── services/       # Business logic
│   ├── docs/               # Sphinx documentation
│   ├── tests/              # Backend tests
│   └── scripts/            # Build and utility scripts
├── frontend/               # React Chrome extension
│   ├── src/
│   │   ├── components/     # React components
│   │   ├── hooks/          # Custom React hooks
│   │   ├── services/       # API services
│   │   ├── utils/          # Utility functions
│   │   ├── popup/          # Extension popup
│   │   ├── options/        # Extension options
│   │   ├── background/     # Background scripts
│   │   └── contentScript/  # Content scripts
│   ├── scripts/            # Build scripts
│   └── dist/               # Built extension
├── docker/                 # Docker configurations
├── docs/                   # Project documentation
└── .github/                # GitHub Actions workflows

Contributing

Development Workflow

1. Fork the repository
2. Create a feature branch

git checkout -b feature/your-feature-name

3. Make your changes
4. Run tests and linting

# Backend
cd backend && pytest && black app/ && ruff check app/

# Frontend
cd frontend && npm test && npm run lint

5. Commit your changes

git commit -m "feat: add your feature description"

6. Push and create a pull request

Code Standards

• Backend: Follow PEP 8, use type hints, add docstrings
• Frontend: Follow ESLint rules, use TypeScript, add JSDoc
• Testing: Maintain >80% code coverage
• Documentation: Update docs for new features

Security

Security Features

• Authentication: JWT-based secure authentication
• Authorization: Role-based access control
• Input Validation: Comprehensive input sanitization
• Rate Limiting: API rate limiting and abuse prevention
• HTTPS: Secure communication protocols
• Secrets Management: Environment-based configuration

Security Best Practices

• Regular dependency updates
• Security scanning in CI/CD
• Input validation and sanitization
• Proper error handling
• Secure session management

📄 License

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

Support

• Issues: GitHub Issues
• Documentation: GitHub Pages
• Discussions: GitHub Discussions
• Email: natig.aminov@gmail.com

---