Re:Don't bother parsing: Just use images for RAG
by Adityav369 on Monday July 21, 2025 @03:51PM
(#44639688)
Yeah the fine tuning is definitely the best part.
Often, the blocker becomes high quality eval sets (which I guess always is the blocker).
Re:Don't bother parsing: Just use images for RAG
by ted_dunning on Monday July 21, 2025 @04:32PM
(#44640078)
You don't have a license in your repository top-level. That means that nobody who takes licensing at all seriously can use your stuff, even just for reference.
Re:Don't bother parsing: Just use images for RAG
by pilooch on Monday July 21, 2025 @06:10PM
(#44640978)
Good catch, will add it tomorrow. License is Apache2.
Re:Don't bother parsing: Just use images for RAG
by wryun on Monday July 21, 2025 @06:09PM
(#44640963)
They do have: https://github.com/jolibrain/colette/blob/main/pyproject.tom...
I agree it's better to have the full licence at top level, but is there a legal reason why this would be inadequate?
It's open source and available here: https://github.com/jolibrain/colette
It's not our primary business so it's just lying there and we don't advertise much, but it works, somehow and with some tweaks to get it really efficient.
The true genius though is that the whole thing can be made fully differentiable, unlocking the ability to finetune the viz rag on targeted datasets.
The layout model can also be customized for fine grained document understanding.