getomni-ai / zerox

PDF to Markdown with vision models
https://getomni.ai/ocr-demo
MIT License
6.68k stars 363 forks source link

Adding HTML support for Zerox #18

Closed xdotli closed 2 months ago

xdotli commented 2 months ago

libreoffice-convert encounters edges cases where it cannot locate the input and output files when converting HTML so writing our own soffice cli wrapper.