PyPI page
Home page
Author:
None
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:
2.64.0
Required dependencies:
accelerate
|
beautifulsoup4
|
certifi
|
docling-core
|
docling-ibm-models
|
docling-parse
|
filetype
|
huggingface_hub
|
lxml
|
marko
|
mlx-vlm
|
mlx-whisper
|
ocrmac
|
onnxruntime
|
openai-whisper
|
openpyxl
|
pandas
|
pillow
|
pluggy
|
polyfactory
|
pydantic
|
pydantic-settings
|
pylatexenc
|
pypdfium2
|
python-docx
|
python-pptx
|
rapidocr
|
requests
|
rtree
|
scipy
|
tqdm
|
typer
|
vllm
Optional dependencies:
accelerate
|
easyocr
|
qwen-vl-utils
|
rapidocr
|
tesserocr
|
transformers
Downloads last day:
75,939
Downloads last week:
396,575
Downloads last month:
2,053,097