PyPI page
Home page
Author:
None
License:
Proprietary
Summary:
Structured text extraction framework for digital and scanned PDFs with inline formatting preservation
Latest version:
0.4.0
Required dependencies:
doclayout-yolo
|
huggingface_hub
|
numpy
|
opencv-contrib-python
|
paddlepaddle
|
paddlex
|
pillow
|
pymupdf
|
pypdfium2
|
rapidocr-onnxruntime
|
scikit-learn
|
scipy
|
timm
|
torch
|
torchvision
|
transformers
Optional dependencies:
anthropic
|
paddleocr
|
paddlex
Downloads last day:
2
Downloads last week:
120
Downloads last month:
1,007