PyPI page
Home page
Author:
thomas meschede
License:
MIT
Summary:
This library contains a set of tools in order to extract and synthesize structured information from documents
Latest version:
0.8.0
Required dependencies:
appdirs
|
chardet
|
diskcache
|
lxml
|
packaging
|
pikepdf
|
pint
|
pydantic
|
pydantic-settings
|
python-magic
|
pyyaml
|
shapely
|
tabulate
Optional dependencies:
beautifulsoup4
|
dask
|
extruct
|
fastcoref
|
goose3
|
gpt4all
|
hnswlib
|
langdetect
|
networkx
|
openai
|
pandas
|
pandoc
|
pdf2image
|
pdfminer.six
|
pygraphviz
|
pytesseract
|
python-pptx
|
pytorch-lightning
|
quantities
|
quantulum3
|
readability-lxml
|
scikit-learn
|
spacy
|
stemming
|
timm
|
tldextract
|
torch
|
tqdm
|
transformers
|
urlextract
Downloads last day:
4
Downloads last week:
31
Downloads last month:
120