🚀 Namma AI - Smart City Intelligence System

A multi-agent AI architecture built with Agent Development Kit (ADK), Python, Firestore MCP, and Google AI Technologies for smart city intelligence and citizen experience enhancement.

🏗️ Architecture Overview

Namma AI/
├── agents/                 # AI Agents
│   ├── base_agent.py      # Base agent class
│   ├── orchestrator_agent.py  # Main orchestrator
│   ├── report_analysis_agent.py  # Report processing agent
│   └── alerts_query_agent.py    # Query handling agent
├── tools/                  # MCP Tools
│   ├── firestore_tool.py  # Firestore database operations
│   ├── maps_tool.py       # Google Maps APIs
│   └── search_tool.py     # Google Search API
├── templates/             # Web UI
│   └── index.html        # Main interface
├── app.py                # Flask application
├── requirements.txt      # Dependencies
├── config.env           # Environment variables
└── README.md           # This file

🎯 Features

Report Analysis Agent

• Multimodal Analysis: Uses Gemini AI to analyze text, images, videos, and audio
• Smart Categorization: Automatically categorizes events into 15 predefined categories
• Sentiment Analysis: Analyzes sentiment (sad, happy, neutral, angry, fear)
• Event Clustering: Groups similar reports and generates unified summaries
• Duration Forecasting: Predicts event duration based on category and context
• Actionable Advice: Provides specific recommendations for citizens

Alerts Query Agent

• Real-time Traffic: Google Maps traffic API integration
• Route Optimization: Best routes with public transport options
• Contextual Search: Google Search integration for additional context
• Intelligent Responses: Gemini-powered comprehensive answers
• Location-based Queries: Geospatial event retrieval

Categories Supported

1. Cultural Events & Celebrations
2. Traffic + Events Impact
3. Power Outages
4. Monsoon-Related Issues (Flooding, Potholes, Tree Falls, Drainage)
5. Lane Closures & Road Works
6. Traffic Congestion & Incidents
7. Sports Events
8. Safety & Network Issues
9. News & Emergencies

🚀 Quick Start

1. Install Dependencies

pip install -r requirements.txt

2. Environment Setup

Copy your API keys to config.env:

GOOGLE_API_KEY=your_gemini_api_key
GOOGLE_SEARCH_API_KEY=your_search_api_key
GOOGLE_CSE_ID=your_custom_search_engine_id
GOOGLE_MAPS_API_KEY=your_maps_api_key
# Firebase credentials...

3. Run the Application

python app.py

4. Access the Web Interface

Open your browser and go to: http://localhost:5000

📝 Usage Examples

Submitting a Report

{
  "Description": "Heavy traffic congestion at Silk Board Junction",
  "Location Name": "Silk Board Junction, Bangalore",
  "Exact Latitude": 12.9279,
  "Exact Longitude": 77.6271,
  "Media (Image)": "present"
}

Asking a Query

{
  "query": "What's the traffic situation around Marathalli?",
  "user_location": {
    "lat": 12.9279,
    "lng": 77.6271
  },
  "origin": "Marathalli",
  "destination": "Electronic City"
}

🔧 API Endpoints

• GET / - Web interface
• POST /submit_report - Submit incident report
• POST /submit_query - Ask questions
• GET /health - Health check

🛠️ Technologies Used

• Python 3.8+
• Flask - Web framework
• Google Generative AI (Gemini) - AI analysis
• Google Cloud Firestore - Database
• Google Maps APIs - Traffic & routing
• Google Custom Search - Web search
• Agent Development Kit (ADK) - Multi-agent architecture

🏛️ Agent Architecture

Orchestrator Agent

• Routes requests to appropriate sub-agents
• Manages agent coordination
• Handles request validation

Report Analysis Agent

• Processes user reports
• Analyzes media content
• Categorizes events
• Generates forecasts
• Provides actionable advice

Alerts Query Agent

• Handles user queries
• Retrieves relevant events
• Provides real-time information
• Generates intelligent responses

🔒 Security & Privacy

• API keys stored in environment variables
• Firebase service account authentication
• Input validation and sanitization
• Secure HTTPS endpoints (in production)

🚀 Deployment

Local Development

python app.py

Production Deployment

# Using Gunicorn
pip install gunicorn
gunicorn -w 4 -b 0.0.0.0:5000 app:app

# Using Docker
docker build -t namma-ai .
docker run -p 5000:5000 namma-ai

📊 Monitoring & Logging

• Agent activity logging
• API response monitoring
• Error tracking
• Performance metrics

🤝 Contributing

1. Fork the repository
2. Create a feature branch
3. Make your changes
4. Add tests
5. Submit a pull request

📄 License

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

🆘 Support

For support and questions:

• Create an issue in the repository
• Contact the development team
• Check the documentation

🔮 Future Enhancements

• Real-time notifications
• Mobile app integration
• Advanced analytics dashboard
• Machine learning model improvements
• Integration with more city services
• Voice interface support