An AI-powered municipal grievance redressal and anti-corruption platform that bridges the gap between citizens and government authorities.
- AI Voice Complaints: Speak your complaint naturally. Our AI automatically transcribes your voice (via Sarvam AI) and categorizes the department, severity, and location (via Groq LLM).
- Live Location Mapping: Drop a pin exactly where the issue is using Mapbox integration.
- Anonymous Whistleblowing: Securely report corruption with cryptographic tracking IDs to follow up without revealing your identity.
- Citizen Dashboard: Track the live status of all your submitted complaints.
- City Heatmaps: Visualize complaint hotspots across the city to allocate resources effectively.
- AI Implementation Plans: Generate step-by-step action plans, required materials, and budget estimates for resolving complex civic issues instantly.
- Automated Routing: Tickets are automatically assigned to the correct municipal department (Water, PWD, Health, etc.) based on AI classification.
- Frontend: React 19, Vite, Tailwind CSS, Mapbox GL JS
- Backend: Node.js, Express, MongoDB Atlas (Mongoose)
- AI Integration: Sarvam AI (Speech-to-Text), Groq (Llama 3 for text classification)
- Authentication: JWT-based stateless authentication
git clone https://github.com/devGPP23/indiainno.git
cd indiainnoCreate a .env file in the root directory and the backend/ directory.
Root .env:
VITE_API_BASE_URL=http://localhost:5000/api
VITE_MAPBOX_TOKEN=your_mapbox_tokenBackend backend/.env:
PORT=5000
MONGO_URI=your_mongodb_atlas_uri
JWT_SECRET=your_jwt_secret
SARVAM_API_KEY=your_sarvam_api_key
GROQ_API_KEY=your_groq_api_keyYou will need to run the backend and frontend simultaneously.
Backend:
cd backend
npm install
npm startFrontend:
# In the root directory
npm install
npm run dev- Create a new Web Service on Render.
- Set the Root Directory to
backend. - Build Command:
npm install - Start Command:
node server.js - Add all environment variables from
backend/.env.
- Import the repository into Vercel.
- The framework preset should auto-detect as Vite.
- Add your
VITE_MAPBOX_TOKEN. - Update
VITE_API_BASE_URLto point to your live Render backend URL (e.g.,https://your-backend.onrender.com/api).