-
Notifications
You must be signed in to change notification settings - Fork 5
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Evidence - FeedbackEvaluator Storage & Basic UI #12758
Conversation
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
This looks good to me -- nice work cleanly following the existing paradigm on the frontend. It looks like you might be having the same issue with snapshot datetimes that @brendanshean did last week, maybe he can speak to how he resolved that.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Nice work on this and well done on integrating with the new UI.
services/QuillLMS/engines/evidence/app/models/evidence/research/gen_ai/trial.rb
Outdated
Show resolved
Hide resolved
...S/engines/evidence/spec/workers/evidence/research/gen_ai/run_trial_evaluation_worker_spec.rb
Outdated
Show resolved
Hide resolved
services/QuillLMS/engines/evidence/app/models/evidence/research/gen_ai/trial.rb
Show resolved
Hide resolved
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
This looks great. I think this will provide some good insight into LLM feedback.
services/QuillLMS/engines/evidence/app/models/evidence/research/gen_ai/trial.rb
Show resolved
Hide resolved
Evidence - FeedbackEvaluator Storage & Basic UI (#12758)
WHAT
Run the FeedbackEvaluator after trials complete, store in a DB table and roll-up, show in UI.
WHY
We want to show this info in the UI of the research tool to make prompt engineering on the feedback prompt more efficient.
HOW
Create a new table
evidence_research_gen_ai_feedback_evaluations
and run evaluations when GEvalScores are calculated. Show in UI.Screenshots
https://www.notion.so/quill/Feedback-Evaluation-Metrics-Storage-185d42e6f941807191e3ddc2da872cd7
What have you done to QA this feature?
I've run some tests locally in the console while connected to the staging DB. I also ran the metrics on staging and seemed to work properly. Viewed the UI locally to ensure the metrics show properly.