-
Notifications
You must be signed in to change notification settings - Fork 5.3k
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
Progress bar for learn_from_user_feedback #776
Conversation
Codecov ReportAttention: Patch coverage is
Additional details and impacted files@@ Coverage Diff @@
## main #776 +/- ##
==========================================
+ Coverage 27.76% 37.21% +9.44%
==========================================
Files 27 27
Lines 3493 3493
Branches 791 791
==========================================
+ Hits 970 1300 +330
+ Misses 2452 2073 -379
- Partials 71 120 +49
Flags with carried forward coverage won't be shown. Click here to find out more. ☔ View full report in Codecov by Sentry. |
@gagb @qingyun-wu Do one of you have time to review this small change? |
* Use tqdm to report progress in learn_from_user_feedback() * Update contrib-openai.yml Append `pytest-asyncio` to `pip install coverage` for TeachableAgent. * Replace pytest-asyncio with pytest * Temporary usage of pull_request action. * Restore pull_request_target action.
Why are these changes needed?
TeachableAgent.learn_from_user_feedback
can take awhile to complete. This PR adds a progress bar.Returning immediately for asynchronous behavior is one option, but that would cause problems for all of the current teachability tests, which immediately start a new chat assuming that the vector DB has been fully updated. If an application needs asynchronous behavior, it can easily call
learn_from_user_feedback
from a separate process. But our focus for now is research, and the teachability mechanisms are still evolving.Related issue number
Closes #329
Checks