Evaluation support

[sriharshaboda]

Hi, love the platform and the features. Wondering if there's a plan to support llm evaluation of different task types like classification/extraction. 1) Ability to upload datasets
2) Annotate ground truth
3) Evaluate and produce metrics
Thanks!

[enoch3712]

Hello @sriharshaboda!

Sorry for the delay, im here now!

Yes 100%, is in the pipeline already. Most of the code is already done, is just how i put everything together.

In 2 weeks or so i think i will push it