Autogenstudio - Add GroupChat Support to UI

[victordibia]

Why are these changes needed?

Add support for GroupChat, and other quality of life improvements to autogenstudio

groupchatnew.mp4

Related issue number

#1285 #1265 #1294 #1296

Checks

• I've included any doc changes needed for https://microsoft.github.io/autogen/. See https://microsoft.github.io/autogen/docs/Contribute#documentation to build and test documentation locally.
• I've added tests (if relevant) corresponding to the changes introduced in this PR.
• I've made sure all auto checks have passed.

[codecov-commenter]

Codecov Report

All modified and coverable lines are covered by tests ✅

Comparison is base (d243db7) 32.48% compared to head (b5273a3) 32.48%.

Additional details and impacted files

@@           Coverage Diff           @@
##             main    #1352   +/-   ##
=======================================
  Coverage   32.48%   32.48%           
=======================================
  Files          41       41           
  Lines        4907     4907           
  Branches     1120     1120           
=======================================
  Hits         1594     1594           
  Misses       3187     3187           
  Partials      126      126           

Flag	Coverage Δ
unittests	32.44% <ø> (ø)

Flags with carried forward coverage won't be shown. Click here to find out more.

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

[gagb]

@victordibia are you able to build this PR in the studio devcontainer and get autogenstudio ui to succeed?

[victordibia]

@gagb , I just tried this and I am able to run the studio devcontainer. and autogenstudio ui runs once the devcontainer loads. Are you seeing any issues?

[reconsumeralization]

Looks good on my end.

[gagb]

@gagb , I just tried this and I am able to run the studio devcontainer. and autogenstudio ui runs once the devcontainer loads. Are you seeing any issues?

I haven't tried today but when I tested yesterday, in the studio container the autogenstudio ui command runs, but once I try to interact with the webpage (which it opens via a port redirect) the webpage encounters many error messages (toasts). I will have time to test again tomorrow morning. Did that correctly work for you?

[victordibia]

@gagb , I just tried this and I am able to run the studio devcontainer. and autogenstudio ui runs once the devcontainer loads. Are you seeing any issues?

I haven't tried today but when I tested yesterday, in the studio container the autogenstudio ui command runs, but once I try to interact with the webpage (which it opens via a port redirect) the webpage encounters many error messages (toasts). I will have time to test again tomorrow morning. Did that correctly work for you?

Thanks. I'll test again, but If you can share the exact toast errors (e.g., if it is an api key thing .. ), it would be helpful

[gagb]

@gagb , I just tried this and I am able to run the studio devcontainer. and autogenstudio ui runs once the devcontainer loads. Are you seeing any issues?

I haven't tried today but when I tested yesterday, in the studio container the autogenstudio ui command runs, but once I try to interact with the webpage (which it opens via a port redirect) the webpage encounters many error messages (toasts). I will have time to test again tomorrow morning. Did that correctly work for you?

Thanks. I'll test again, but If you can share the exact toast errors (e.g., if it is an api key thing .. ), it would be helpful

I am no longer seeing the toast errors! I am not sure what changed.

But I am still seeing interactions that feel buggy for creating a simple chatgpt like experience -- I can meet 1-1 and show. Some of these are related to adding default params models and agents that do not exist. Why is min max consecutive replies set to 2?

Would be worth addressing these in a separate PR.