PyPI page
Home page
Author:
STACKIT GmbH & Co. KG
License:
Apache-2.0
Summary:
Extracts the content of documents, websites, etc and maps it to a common format.
Latest version:
4.2.0
Required dependencies:
atlassian-python-api
|
boto3
|
botocore
|
camelot-py
|
datasets
|
dependency-injector
|
docling
|
docx2txt
|
fake-useragent
|
fastapi
|
fasttext
|
html5lib
|
langchain-community
|
langchain-core
|
lxml
|
mammoth
|
markdownify
|
markitdown
|
numpy
|
oauthlib
|
opencv-python-headless
|
pandas
|
partial
|
pdf2image
|
pdfplumber
|
pydantic-settings
|
pypandoc
|
pypandoc-binary
|
pypandoc_binary
|
pypdfium2
|
pytesseract
|
python-multipart
|
pyyaml
|
rag-core-lib
|
requests-oauthlib
|
starlette
|
tabulate
|
tesserocr
|
torch
|
torchvision
|
transformers
|
unstructured
|
uvicorn
|
wheel
Downloads last day:
5
Downloads last week:
36
Downloads last month:
65