PyPI page
Home page
Author:
Magure
License:
Apache-2.0
Summary:
PDF extraction that OCRs only the pages that need it - a gated LiteParse wrapper
Latest version:
0.4.1
Required dependencies:
liteparse
Optional dependencies:
docling-ibm-models
|
fastapi
|
httpx
|
huggingface-hub
|
mag-pdf
|
numpy
|
onnxruntime
|
pillow
|
pypdfium2
|
pytest
|
python-multipart
|
reportlab
|
uvicorn
Downloads last day:
2
Downloads last week:
47
Downloads last month:
224
7-day smoothing