PyPI page
Home page
Author:
DocBerry Contributors
License:
MIT
Summary:
Extract structured Markdown, tables, figures, and equations from scientific PDFs with proper reading order.
Latest version:
0.1.2
Required dependencies:
docling
|
docling-core
|
numpy
|
pandas
|
pillow
|
pymupdf
Optional dependencies:
accelerate
|
docberry
|
opencv-python
|
pix2tex
|
torch
|
transformers
Downloads last day:
9
Downloads last week:
21
Downloads last month:
357