PyPI page
Author:
Ambika Sukla
Summary:
Pure-Python, RAG-friendly document parsers (PDF/HTML/text/XML/Markdown). Java- and Tika-free.
Latest version:
2.1.0
Required dependencies:
beautifulsoup4
|
nltk
|
numpy
|
pdfplumber
|
pypdfium2
Optional dependencies:
fastapi
|
onnxruntime
|
opencv-python-headless
|
pyclipper
|
python-multipart
|
pyyaml
|
rapidocr-onnxruntime
|
shapely
|
six
|
uvicorn
Downloads last day:
980
Downloads last week:
3,676
Downloads last month:
14,763
7-day smoothing