Mike Lissner
Mike Lissner
Alberto, I think this means we've got our architecture in good shape? What else is on your mind?
> probably the simplest solution to start with is to set 1 uvicorn worker per microservice instance with one GPU allocated and let the microservice scale horizontally while using a...
This sounds great to me. @legaltextai, do you think you can split this off into smaller issues and start tackling each of these with Alberto's help?
Well, the API for doing query vectorizing will be almost identical to the one doing text vectorization, and we'll need that, so it seems like making it is the right...
I just worked through the page. Lots of really good improvements. We should try to do the easy ones in one push and the harder ones in a second go,...
I think it'll be best if a real dev take this on and help land it. I'll assign to Elisa for the next sprint.
I agree with all points here, thank you both! > tbh, I thought it would look much worse I agree with this too! I think it's worth a bit of...
Great! Intro sent!
Yep!
We were! I just switched the assignee back to Elisa to get it over the line. Thank you both!