PyPI page
Home page
Author:
Christoph Auer
License:
MIT
Summary:
SDK and CLI for parsing PDF, DOCX, HTML, and more, to a unified document representation for powering downstream workflows such as gen AI applications.
Latest version:
2.32.0
Required dependencies:
beautifulsoup4
|
certifi
|
docling-core
|
docling-ibm-models
|
docling-parse
|
easyocr
|
filetype
|
huggingface-hub
|
lxml
|
marko
|
openpyxl
|
pandas
|
pillow
|
pluggy
|
pydantic
|
pydantic-settings
|
pylatexenc
|
pypdfium2
|
python-docx
|
python-pptx
|
requests
|
rtree
|
scipy
|
tqdm
|
typer
Optional dependencies:
accelerate
|
ocrmac
|
onnxruntime
|
rapidocr-onnxruntime
|
tesserocr
|
transformers
Downloads last day:
0
Downloads last week:
5
Downloads last month:
20
7-day smoothing