PyPI page
Home page
Author:
Bhargava Chary Peddapudi
Summary:
HTML to RAG-ready Markdown: a learned boilerplate filter that removes site chrome (navigation, footers, cookie banners, related links, comments) and keeps article, documentation and pricing content. Pure NumPy inference, no model download.
Latest version:
0.1.4
Required dependencies:
beautifulsoup4
|
lxml
|
numpy
|
pyyaml
Optional dependencies:
fastapi
|
html2text
|
httpx
|
langchain-core
|
llama-index-core
|
markdownify
|
markitdown
|
pydantic
|
pytest
|
readability-lxml
|
ruff
|
scikit-learn
|
trafilatura
|
uvicorn
Downloads last day:
1
Downloads last week:
15
Downloads last month:
1,098
7-day smoothing