[Feature request] Marker document parsing

[HenkieTenkie62]

Hey i've tried docling and a few others (PyMuPDF, Tesseract) but had settled on using Marker.
It's performance, especially for equations, is superb.

This is the Marker project:
https://github.com/datalab-to/marker

this is an API for the provided server:
https://github.com/adithya-s-k/marker-api?tab=readme-ov-file

And this is a Docker image for the api server:
https://hub.docker.com/r/georgelpreput/marker

With the option force OCR, I never get any misread equations (essential for engineering documents!).
Would you consider integrating it in LightRAG?