Large Multimodal Models

[BeibinLi]

Why are these changes needed?

Large Multimodal Models. Right now, LLaVA is supported from agentchat.

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 #515 (a6cdcfa) into main (957ec00) will decrease coverage by 24.97%.
The diff coverage is 18.00%.

@@             Coverage Diff             @@
##             main     #515       +/-   ##
===========================================
- Coverage   41.75%   16.79%   -24.97%     
===========================================
  Files          21       23        +2     
  Lines        2632     2823      +191     
  Branches      592      620       +28     
===========================================
- Hits         1099      474      -625     
- Misses       1442     2347      +905     
+ Partials       91        2       -89     

Flag	Coverage Δ
unittests	16.79% <18.00%> (-24.97%)	⬇️

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/multimodal_conversable_agent.py	30.90% <30.90%> (ø)
autogen/img_utils.py	17.46% <17.46%> (ø)
autogen/agentchat/contrib/llava_agent.py	6.32% <6.32%> (ø)

... and 13 files with indirect coverage changes