Olicorne
Olicorne
I'm not sure I understand. *How* can it be safer to rely on litellm for openrouter models instead of relying on openrouter *itself* for its own costs?
Thanks I didn't know. But still, that means that one of the github branch is at most 24h late. Then you have to wait litellm to release. Then you have...
Btw I've been testing it and it works great. I did notice an issue : say I have two windows, split vertically, I toggle maximized (using gnome, NOT cortile) on...
I just found out that in gnome tweaks on ubuntu 22 in section Windows there's the option `Focus on hover`. This might avoid those issues.
I haven't taken a look at the other backends either so my request is at least about `whisper_api_model` indeed but my point can be valid for other backends as well....
Hello. I had somehow mistaken "srt" and "text" output format. Sorry about that! But I'm still surprised that "srt" output shows that much text per block. I would have thought...
Up: I would still love that
> Here's my cal if that's easier: https://calendly.com/d/4mp-gd3-k5k/litellm-1-1-onboarding-chat Done
I ended up doing my own litellm embeddings class and it seems to be working fine: https://github.com/thiswillbeyourgithub/wdoc/blob/main/wdoc/utils/customs/litellm_embeddings.py
Adressed in #5800