PyPI page
Home page
Author:
None
License:
MIT
Summary:
Document intelligence framework for Python - Extract text, metadata, and structured data from diverse file formats
Latest version:
3.13.5
Required dependencies:
anyio
|
chardetng-py
|
exceptiongroup
|
html-to-markdown
|
mcp
|
msgspec
|
numpy
|
playa-pdf
|
polars
|
psutil
|
pypdfium2
|
python-calamine
|
python-pptx
|
tomli
|
typing-extensions
Optional dependencies:
click
|
deep-translator
|
easyocr
|
fast-langdetect
|
gmft
|
keybert
|
kreuzberg
|
litestar
|
mailparse
|
paddleocr
|
paddlepaddle
|
playa-pdf
|
rich
|
semantic-text-splitter
|
setuptools
|
spacy
Downloads last day:
4
Downloads last week:
7
Downloads last month:
16