Analyze, summarize, and explain information in PDF textbooks and whitepapers using OCR and AI analysis. Upload PDFs to get markdown summaries and analysis with real-time progress tracking.
- PDF text extraction with OCR
- Real-time tracking of analysis progress
- Chunked file upload
- Automatic error recovery
- Memory-efficient processing
- Markdown formatted output
# Build and run with Docker
./scripts/build_local.sh
# Or clean and rebuild
./scripts/clean_and_build.sh- Docker & Docker Compose
- Node.js 20+
- Python 3.12+
- Bun 1.0+
- uv package manager
- Poppler Utils
The application is configured through a central .env file. See Local Setup for details.
Key configuration groups:
- Ports and networking
- Version management
- AI and processing settings
- Timeouts and health checks
- Frontend: Controlled by
package.json - Backend: Controlled by
backend/version - Images: Tagged with respective component versions
# Frontend (default: http://localhost:5173)
cd frontend
bun install
bun run dev
# Backend (default: http://localhost:8000)
cd backend
python -m venv venv
source venv/bin/activate
pip install -r requirements.txt
uvicorn main:app --reload- Fork the repository
- Create a feature branch
- Commit your changes
- Push to the branch
- Create a Pull Request
MIT License