🚀 ProcureAI - Tender Management System

AI-powered tender scraping, analysis, and bid management system for government procurement.

Features

• 🤖 Automated Tender Scraping - Scrapes Telangana eProcurement portal
• 💬 AI Chat Assistant - RAG-based Q&A about tenders using Gemini
• 📊 Bid Evaluation - Automated compliance and risk scoring
• 🔍 Smart Search - Vector-based tender search
• 📈 Analytics Dashboard - Tender statistics and insights

Tech Stack

Backend:

• FastAPI (Python)
• PostgreSQL
• Qdrant (Vector DB)
• LangGraph + Gemini AI
• Selenium (Web Scraping)

Frontend:

• React + Vite
• TailwindCSS
• Recharts

🚀 Quick Deploy (Recommended)

Option 1: Automated Railway Deploy (Fastest!)

# Run the automated deployment script
.\deploy-railway.ps1

That's it! The script will:

• Install Railway CLI
• Setup project and database
• Configure environment
• Deploy your app
• Initialize database

Option 2: Manual Railway Deploy

# Install Railway CLI
npm install -g @railway/cli

# Login and deploy
railway login
railway init
railway add --plugin postgresql
railway up

# Set environment variables
railway variables set GEMINI_API_KEY="your_key"
railway variables set SECRET_KEY="$(python -c 'import secrets; print(secrets.token_hex(32))')"

# Initialize database
railway run python backend/create_database.py

Option 3: Deploy to Render.com (Most Free)

See DEPLOY_RENDER.md for step-by-step instructions.

📚 Documentation

• DEPLOY_NOW.md - Quick deployment decision guide
• DEPLOY_RAILWAY.md - Railway deployment (10 min)
• DEPLOY_RENDER.md - Render deployment (15 min)
• DEPLOYMENT_GUIDE.md - Complete deployment guide
• QUICK_START.md - Local development setup

🛠️ Local Development

Prerequisites

• Python 3.9+
• Node.js 16+
• PostgreSQL 14+
• Docker (for Qdrant)

Quick Start

1. Backend:

cd backend
python -m venv venv
.\venv\Scripts\Activate.ps1
pip install -r requirements.txt

# Copy and configure .env
copy .env.example .env
notepad .env  # Add your GEMINI_API_KEY

# Start Qdrant
docker run -d -p 6333:6333 qdrant/qdrant

# Initialize database
python create_database.py
python seed_db.py

# Start server
.\start.ps1

2. Frontend:

cd frontend
npm install
.\start.ps1

Access:

• Frontend: http://localhost:5173
• Backend: http://localhost:8000
• API Docs: http://localhost:8000/api/docs

🔑 API Keys

Gemini API Key (Required)

1. Go to https://makersuite.google.com/app/apikey
2. Sign in with Google
3. Create API key
4. Add to .env file or deployment environment

🐳 Docker Deployment

# Create .env file with your keys
echo "GEMINI_API_KEY=your_key" > .env

# Start all services
docker-compose up -d

# Initialize database
docker-compose exec backend python create_database.py

Access at http://localhost:5173

📦 Project Structure

agentathon/
├── backend/
│   ├── app/
│   │   ├── agents/          # AI agents (LangGraph)
│   │   ├── routes/          # API endpoints
│   │   ├── services/        # Business logic
│   │   ├── models.py        # Database models
│   │   └── main.py          # FastAPI app
│   ├── requirements.txt
│   └── Dockerfile
├── frontend/
│   ├── src/
│   │   ├── pages/           # React pages
│   │   ├── components/      # React components
│   │   └── services/        # API client
│   ├── package.json
│   └── vite.config.js
├── docker-compose.yml
└── deployment guides...

🧪 Testing

# Backend tests
cd backend
python test_system.py
python test_api.py

# Frontend
cd frontend
npm test

🚀 Deployment Scripts

Pre-deployment Check

.\check-deployment.ps1

Verifies your project is ready to deploy.

Automated Deploy

# Railway (recommended)
.\deploy-railway.ps1

# Or Linux/Mac
chmod +x deploy-railway.sh
./deploy-railway.sh

📊 Features Overview

1. Tender Scraping

• Automated scraping from Telangana portal
• Scheduled updates every 6 hours
• Manual trigger available

2. AI Chat

• Ask questions about tenders
• RAG-based responses using Gemini
• Context-aware answers

3. Bid Management

• Submit and track bids
• Automated compliance checking
• Risk assessment scoring

4. Dashboard

• Real-time statistics
• Tender analytics
• Activity logs

🔒 Security

• Environment variables for secrets
• CORS protection
• Input validation
• SQL injection prevention
• Rate limiting (recommended for production)

📈 Scaling

For production use:

• Enable database connection pooling
• Add Redis for caching
• Use CDN for static assets
• Setup monitoring (Sentry, Datadog)
• Configure auto-scaling

See DEPLOYMENT_GUIDE.md for details.

🐛 Troubleshooting

Backend won't start:

• Check .env file exists with GEMINI_API_KEY
• Verify PostgreSQL is running
• Check port 8000 is available

Frontend can't reach backend:

• Verify backend is running
• Check CORS settings
• Update API_URL in frontend

Database errors:

• Run python create_database.py
• Check DATABASE_URL format
• Verify PostgreSQL credentials

See troubleshooting guides in deployment docs.

📝 Environment Variables

Backend (.env):

DATABASE_URL=postgresql://user:password@localhost:5432/procureai
GEMINI_API_KEY=your_gemini_api_key
SECRET_KEY=your-secret-key
DEBUG=True
CORS_ORIGINS=http://localhost:5173
QDRANT_HOST=localhost
QDRANT_PORT=6333

Frontend (.env):

VITE_API_URL=http://localhost:8000

🤝 Contributing

1. Fork the repository
2. Create feature branch
3. Commit changes
4. Push to branch
5. Create Pull Request

📄 License

This project is for educational/demo purposes.

🆘 Support

• Check documentation in /docs
• Review deployment guides
• Check API docs at /api/docs
• Create an issue for bugs

🎯 Quick Links

• Deploy Now - Choose deployment option
• Railway Guide - Fastest deployment
• Render Guide - Free deployment
• Local Setup - Development setup
• Full Guide - All options

---

Made with ❤️ for Agentathon 2024

Ready to deploy? Start with DEPLOY_NOW.md