Large Multimodal Models in AgentChat

[BeibinLi]

Why are these changes needed?

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

Merging #516 (f9d1068) into dev/v0.2 (957ec00) will decrease coverage by 25.67%.
Report is 39 commits behind head on dev/v0.2.
The diff coverage is 50.40%.

@@              Coverage Diff              @@
##           dev/v0.2     #516       +/-   ##
=============================================
- Coverage     41.75%   16.09%   -25.67%     
=============================================
  Files            21       25        +4     
  Lines          2632     2970      +338     
  Branches        592      658       +66     
=============================================
- Hits           1099      478      -621     
- Misses         1442     2476     +1034     
+ Partials         91       16       -75     

Flag	Coverage Δ
unittests	16.09% <50.40%> (-25.67%)	⬇️

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

Files	Coverage Δ
autogen/agentchat/__init__.py	100.00% <100.00%> (ø)
autogen/agentchat/assistant_agent.py	83.33% <ø> (ø)
autogen/agentchat/groupchat.py	22.41% <ø> (-38.80%)	⬇️
autogen/agentchat/user_proxy_agent.py	80.00% <ø> (-20.00%)	⬇️
autogen/code_utils.py	19.91% <ø> (-25.55%)	⬇️
autogen/math_utils.py	0.00% <ø> (-9.29%)	⬇️
autogen/oai/__init__.py	100.00% <100.00%> (ø)
autogen/agentchat/contrib/teachable_agent.py	0.00% <0.00%> (-15.66%)	⬇️
autogen/agentchat/contrib/text_analyzer_agent.py	0.00% <0.00%> (-37.50%)	⬇️
autogen/token_count_utils.py	0.00% <0.00%> (-56.57%)	⬇️
... and 7 more

... and 6 files with indirect coverage changes