PDF to Semantic Markdown
Convert PDF files to well-structured Markdown. Figures and diagrams are saved as PNG images and referenced in the output Markdown.
Dependencies
Install before first use:
sudo pip3 install PyMuPDF
Pre-installed: pdf2image, pillow, openai.
Usage
Run the conversion script:
python3 /home/ubuntu/skills/pdf-to-semantic-markdown/scripts/pdf_to_markdown.py <input.pdf> [output_dir] [--model MODEL] [--dpi DPI] [--batch BATCH]
| Argume
[Description truncada. Veja o README completo no GitHub.]