[Discussion]: Docling integration

[loorisr]

Hello,

What about a coupling with Docling ? https://github.com/DS4SD/docling
It is a tool to convert pdf, docx, html, ... in Markdown format.

If a requested url is a pdf, docx, pttx, we could send the document to Docling for Markdown conversion?

I think the easiest would be to use an external container as an API like:
https://github.com/drmingler/docling-api or https://github.com/aidotse/docling-inference