Snap Study is an innovative web application that transforms images of text into digestible summaries using OCR (Optical Character Recognition) and AI summarization technology. Perfect for students and professionals who want to quickly extract and understand information from textual images.
- Image Upload: Easy-to-use interface for uploading images containing text.
- OCR Processing: Converts image text to machine-readable format using Tesseract.js.
- AI Summarization: Generates concise summaries using the Llama2 model.
- Responsive Design: Beautiful, mobile-friendly interface with gradient animations.
- Real-time Processing: Live feedback during text extraction and summarization.
- React.js
- Tailwind CSS
- Tesseract.js (OCR)
- Axios (API calls)
- GSAP (Animations)
- Node.js
- Express.js
- Python
- Ollama (Llama2 model)
- CORS
Before running the application, ensure you have the following installed:
- Node.js (v18 or higher)
- Python (v3.8 or higher)
- Ollama with the Llama2 model
- Clone the repository:
git clone https://github.com/Shreyanshdiwakar/Snap-study.git
- Install frontend dependencies:
cd client
npm install
- Install backend dependencies:
cd backend
npm install
pip install ollama
- Ensure Ollama is running with the Llama2 model:
ollama run llama2-uncensored
- Start the backend server:
cd backend
npm run dev
- Start the frontend development server:
cd client
npm run dev
- Access the application at
http://localhost:5173
- Open the application in your browser.
- Click the file upload button to select an image containing text.
- Wait for the OCR process to extract the text.
- Review the extracted text.
- Get an AI-generated summary of the content.
snap-study/
├── client/ # Frontend React application
│ ├── src/
│ │ ├── App.jsx # Main application component
│ │ ├── main.jsx # Entry point
│ │ └── index.css # Global styles
│ └── public/
├── backend/ # Backend server
│ ├── app.mjs # Express server setup
│ └── run_ollama.py # Python script for Llama2 integration
Contributions are welcome! Please feel free to submit a Pull Request.
This project is licensed under the MIT License - see the LICENSE file for details.
- Tesseract.js for OCR capabilities.
- Ollama for providing the Llama2 model integration.
- The React and Node.js communities for excellent documentation and tools.
For any queries or suggestions, please open an issue in the repository.