-
Notifications
You must be signed in to change notification settings - Fork 5k
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
Allow user to pass in a customized speaker selection method #1791
Conversation
Codecov ReportAttention: Patch coverage is
Additional details and impacted files@@ Coverage Diff @@
## main #1791 +/- ##
===========================================
+ Coverage 36.10% 59.67% +23.56%
===========================================
Files 63 63
Lines 6658 6670 +12
Branches 1470 1600 +130
===========================================
+ Hits 2404 3980 +1576
+ Misses 4056 2330 -1726
- Partials 198 360 +162
Flags with carried forward coverage won't be shown. Click here to find out more. ☔ View full report in Codecov by Sentry. |
@kevin666aa is this ready for review? It is currently a draft PR. Please make a PR once it is ready. Thanks! |
Could you add the link to the newly added example in the Example page on website: https://microsoft.github.io/autogen/docs/Examples? Thanks! |
…t#1791) * init PR * update * update code check * update * update * update * update * Test the ability to have agents a,u,t,o,g,e,n speak in turn. * update * update * update * Evidence that groupchat not terminating because of the TERMINATE substring. * Raising NoEligibleSpeakerException allows graceful exit before max turns * update * To confirm with author that custom function is meant to override graph constraints * Confirmed the expected test behaviour with author * Update autogen/agentchat/groupchat.py * update * update --------- Co-authored-by: Joshua Kim <Joshua@spectdata.com> Co-authored-by: Qingyun Wu <qingyun0327@gmail.com>
Allow user to pass in a
customized_speaker_selection_func(last_speaker: Agent, messages: List[Dict])
to determine what should be the next agent.If the function returns None, the default speaker_selection_method is used.
Why are these changes needed?
Related issue number
Potentially closes #778
Checks