A voice-enabled application that helps users fill out PDF forms using natural language conversation with an AI assistant. No typing or reading required!

• 🎤 Voice Input: Speak your answers instead of typing
• 🔊 Voice Output: AI responses are read aloud
• 🤖 AI-Powered: Uses Google Gemini AI for natural conversation
• 📄 PDF Form Filling: Automatically extracts and fills PDF form fields
• ♿ Accessible: Designed for users who prefer voice interaction

• FastAPI (Python) - High-performance web framework
• Google Gemini API - AI conversation engine
• PyPDF2 - PDF processing and form field extraction

• React with TypeScript - Modern UI framework
• Web Speech API - Browser-native speech recognition and synthesis
• Vite - Fast build tool

Before you begin, make sure you have:

• Python 3.8+ installed (Download)
• Node.js 16+ and npm installed (Download)
• Git installed (Download)
• A Google Gemini API key (Get one here)

git clone https://github.com/yourusername/HackHive2026.git
cd HackHive2026

1. Navigate to the backend directory:

   cd backend

2. Create a virtual environment (recommended):

   # On Windows
   python -m venv venv
   .\.venv\Scripts\Activate.ps1
   
   # On macOS/Linux
   python3 -m venv venv
   source venv/bin/activate.ps1

3. Install Python dependencies:

   pip install -r requirements.txt

4. Create a .env file in the backend directory:

   # Windows
   copy .env.example .env
   
   # macOS/Linux
   cp .env.example .env

5. Add your Gemini API key to .env:

   GEMINI_API_KEY=your_actual_api_key_here
   

6. Start the backend server: With uvicorn:

   uvicorn app.main:app --reload --host 0.0.0.0 --port 8000

   ✅ Backend will run at http://localhost:8000

1. Open a new terminal and navigate to the frontend directory:

   cd frontend

2. Install Node dependencies:

   npm install

3. Start the development server:

   npm run dev

   ✅ Frontend will run at http://localhost:5173

Open your browser and go to:

http://localhost:5173

🎉 You're ready to use the app!

Backend won't start:

• Make sure Python 3.8+ is installed: python --version
• Check that all dependencies are installed: pip install -r requirements.txt
• Make sure port 8000 is not in use, or change it: uvicorn app.main:app --port 8001

Frontend won't start:

• Make sure Node.js 16+ is installed: node --version
• Delete node_modules and try again:

  rm -r node_modules
  npm install
  npm run dev

API Key errors:

• Verify your .env file is in the backend folder
• Make sure the API key is valid: GEMINI_API_KEY=your_key_here
• The app works without a key but with limited AI responses

Speech recognition not working:

• Use a modern browser (Chrome or Edge recommended)
• Ensure your microphone is connected and permitted
• Check browser console for errors (F12 → Console)

1. Upload a PDF: Click "Choose PDF File" and select a PDF form
2. Start Voice Input: Click the microphone button to start speaking
3. Answer Questions: The AI will ask you questions about each form field
4. Review Progress: See which fields have been filled
5. Download: Once complete, download your filled PDF

• POST /api/upload-pdf - Upload and process a PDF
• POST /api/chat - Send a message to the AI assistant
• POST /api/update-field - Manually update a form field
• POST /api/fill-pdf - Generate and download filled PDF
• GET /api/session/{sessionId} - Get session status

• Speech Recognition: Works best in Chrome/Edge (uses WebKit Speech API)
• Speech Synthesis: Supported in all modern browsers
• PDF Upload: Supported in all modern browsers

• PDF form field extraction works best with PDFs that have proper form fields (AcroForm)

• Raihan Carder
• Tony Park
• Suhi Kasim
• Aarnav Shrivastava