Hain-Lee H.

i do see this warning, but it still seems to work (i can upload a dataset): UserWarning: :warning::warning: The Phoenix server (6.0.0) and client (7.1.1) versions are severely mismatched. Upgrade either the client or server to ensure API compatibility

yup, i did

got it, thanks!

ah ok, so i should specify the headers arg instead of api_key?

awesome, thanks so much for taking the time to answer my questions

haha, yeah otherwise it's llm-judges all the way down 😆

or at this stage is it more like "you can, and we're still figuring out the easiest ways for creating an llm judge"? i know there's the documented conceptual steps of creating a judge, but it doesn't show what do actually do for step 5 so i've just been writing my own code to run llm_classify in a loop

would you recommend using experiments and datasets to develop the llm judge itself?

got it, so sounds like for the task itself it's best to have groundtruth dataset and run experiments over that to start with, rather than to work backwards by trying to create a custom eval first. would the custom eval for the task be more for monitoring then? and to craft an llm as a judge eval itself we would leverage the experiment/dataset workflow like i described?