A Python GUI application for document conversion using CustomTkinter.
- Convert between PDF, DOCX, PPTX, HTML, Markdown, and JSON
- Batch processing support
- OCR with multi-language support
- Table extraction with fast/accurate modes
- Real-time progress tracking
- Install Python 3.8+
- Install Docling:
pip install docling
- Install GUI dependencies:
pip install -r requirements.txt
- Run the application:
python docling-gui.py
Works on macOS, Linux, and Windows, with support for both x86_64 and arm64 architectures.
Docling depends on PyTorch. For different architectures or CPU-only installations:
# Example for Linux CPU-only version
pip install docling --extra-index-url https://download.pytorch.org/whl/cpuDocling supports multiple OCR engines:
| Engine | Installation | Usage |
|---|---|---|
| EasyOCR | Default in Docling | EasyOcrOptions |
| Tesseract | System dependency (see below) | TesseractOcrOptions |
| Tesseract CLI | System dependency | TesseractCliOcrOptions |
| OcrMac | macOS only: pip install ocrmac |
OcrMacOptions |
| RapidOCR | pip install rapidocr_onnxruntime |
RapidOcrOptions |
For Tesseract OCR engine:
brew install tesseract leptonica pkg-config
export TESSDATA_PREFIX=/opt/homebrew/share/tessdata/sudo apt-get install tesseract-ocr
export TESSDATA_PREFIX=/usr/share/tesseract-ocr/4.00/tessdata/For optimal performance:
pip uninstall tesserocr
pip install --no-binary :all: tesserocrTo contribute to Docling development:
poetry install --all-extrasFor more information and advanced usage, refer to the official Docling repository: https://github.com/DS4SD/docling
MIT License