[Feature request] Marker document parsing #2111
HenkieTenkie62
started this conversation in
Ideas
Replies: 0 comments
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
-
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?
Beta Was this translation helpful? Give feedback.
All reactions