Change default model in LMM

[BeibinLi]

Why are these changes needed?

Address issue #965

Related issue number

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 (a0288e0) 26.54% compared to head (35c06d8) 37.87%.

Additional details and impacted files

@@             Coverage Diff             @@
##             main    #1032       +/-   ##
===========================================
+ Coverage   26.54%   37.87%   +11.33%     
===========================================
  Files          28       28               
  Lines        3805     3807        +2     
  Branches      865      907       +42     
===========================================
+ Hits         1010     1442      +432     
+ Misses       2724     2239      -485     
- Partials       71      126       +55     

Flag	Coverage Δ
unittests	37.82% <100.00%> (+11.33%)	⬆️

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.

[ekzhu]

My understanding is that this is to make sure the model used support multi-modal input correct?

[BeibinLi]

My understanding is that this is to make sure the model used support multi-modal input correct?

Yes, correct. The ConversableAgent defaults to “gpt-4", and we should default to a multimodal model. When the config_list is not set, the default model will be used.