PyPI page
Author:
Christoph Auer
Summary:
Modular version of the Docling package: 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:
2.142.1
Required dependencies:
certifi
|
docling-core
|
filetype
|
langcodes
|
pluggy
|
pydantic
|
pydantic-settings
|
requests
|
tqdm
Optional dependencies:
accelerate
|
arelle-release
|
beautifulsoup4
|
defusedxml
|
docling-core
|
docling-ibm-models
|
docling-parse
|
easyocr
|
einops
|
httpx
|
huggingface-hub
|
librosa
|
lxml
|
mail-parser
|
marko
|
mlx-vlm
|
mlx-whisper
|
nemotron-ocr
|
numba
|
numpy
|
ocrmac
|
odfdo
|
onnxruntime
|
onnxruntime-gpu
|
open-clip-torch
|
openai-whisper
|
openpyxl
|
pandas
|
peft
|
pillow
|
playwright
|
polyfactory
|
pylatexenc
|
pypdfium2
|
python-docx
|
python-dotenv
|
python-oxmsg
|
python-pptx
|
qwen-vl-utils
|
rapidocr
|
resemblyzer
|
rich
|
rtree
|
scikit-image
|
scikit-learn
|
scipy
|
soundfile
|
tesserocr
|
timm
|
torch
|
torchvision
|
transformers
|
tritonclient
|
typer
|
websockets
|
whisper-s2t-reborn
Downloads last day:
157,601
Downloads last week:
916,554
Downloads last month:
2,765,585
7-day smoothing