GradeWise

A modern web app for evaluating scanned answer sheets with text extraction, rubric-based scoring, and clear feedback.

Created and maintained by Divyansh Joshi.

---

✨ Features

• 📄 Document Upload - Support for question papers and answer sheets (images/PDF)
• 🔍 Text Extraction - OCR for scanned documents
• 📝 Question Analysis - Automatic extraction with rubrics and keywords
• 📊 Similarity Scoring - Compare student answers to model answers
• ✏️ Teacher Review - Manual override and feedback capabilities
• 🎨 Modern UI - Clean, responsive interface (Next.js + Tailwind CSS)
• 🎯 Three Usage Modes:
  • Static Demo - Instant results with pre-loaded samples (no API needed)
  • Free Demo - Live grading with our API (10 requests/hour, rate-limited)
  • Custom API Key - Unlimited grading with your own Google AI key
• 📋 All-in-One View - Grade all questions on a single page
• 🖼️ Answer Sheet Preview - Side-by-side view of student work
• ⚡ Rate Limiting - Built-in protection for free demo mode

Tech Stack

• Next.js 15, React 18, TypeScript
• Tailwind CSS, Radix UI, Lucide Icons
• Utility libs: Zod, date-fns, etc.

🚀 Quick Start

Option 1: Try Demo Mode (No Setup Required)

1. Visit the live demo at gradewise.vercel.app
2. Click "Try Demo" to explore with pre-loaded samples
3. No API key or configuration needed!

Option 2: Run Locally

1. Clone the repository

   git clone https://github.com/oldregime/VitGrader.git
   cd VitGrader

2. Install dependencies

   npm install

3. Set up environment variables (optional for live grading)

   cp env.example .env.local

   Add your Google AI API key to .env.local:

   GOOGLE_GENAI_API_KEY=your_api_key_here
   

   Get a free API key from Google AI Studio

4. Run the development server

   npm run dev

5. Open in browser Navigate to http://localhost:9002

Project Structure

src/
  app/           # Next.js App Router pages and layout
  components/    # Reusable UI components
  hooks/         # App hooks
  lib/           # Utilities
  ai/            # Analysis flows (text extraction, scoring, feedback)

Entry point for the UI: src/app/page.tsx.

Scripts

• npm run dev – start dev server
• npm run build – create production build
• npm run start – run production server
• npm run lint – lint codebase
• npm run typecheck – TypeScript checks

📦 Deployment

Deploy to Vercel (Recommended)

1. Click the "Deploy" button above
2. Connect your GitHub account
3. Add your GOOGLE_GENAI_API_KEY as an environment variable
4. Deploy!

Your app will be live at https://your-project.vercel.app

Manual Deployment

1. Build the project

   npm run build

2. Test production build locally

   npm start

3. Deploy to your platform of choice

   • Vercel: vercel deploy
   • Netlify: Connect your repo
   • Self-hosted: Use the .next build output

🎯 Usage

Static Demo Mode (Instant, No API)

1. Visit the homepage
2. Click "Try Static Demo"
3. View all 3 pre-loaded questions on one page
4. Click "Grade All Questions" for instant results
5. See answer sheet preview side-by-side

Free Demo Mode (Live, Rate-Limited)

1. Click "Try Free Demo" on homepage
2. Get 10 free grading requests per hour
3. Uses our API key (no setup needed)
4. Perfect for testing live features

Custom API Key Mode (Unlimited)

1. Go to Settings page
2. Enter your Google AI API key
3. Upload custom question papers
4. Upload student answer sheets
5. Unlimited grading requests

🤝 Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

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

📧 Contact

Divyansh Joshi

• Email: divyansh8065@gmail.com
• GitHub: @oldregime

If you find this project useful, please consider ⭐ starring the repo!

📄 License

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

---

Made with ❤️ by Divyansh Joshi