[Core] Compatibility with function call style API (Azure OpenAI and Gemini)

[ekzhu]

Why are these changes needed?

Add an optional argument to register_for_llm to support functional call style APIs (Azure OpenAI up to 2023-10-01-preview)

e.g.

@agent2.register_for_llm(api_style="function")
def my_function(a: Annotated[str, "description of a parameter"] = "a", b: int, c=3.14) -> str:
  return a + str(b * c)

Related issue number

#1206
#1150
#1198

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

Attention: Patch coverage is 66.66667% with 2 lines in your changes missing coverage. Please review.

Project coverage is 41.31%. Comparing base (4426093) to head (9132abb).
Report is 709 commits behind head on main.

Files	Patch %	Lines
autogen/agentchat/conversable_agent.py	66.66%	1 Missing and 1 partial ⚠️

Additional details and impacted files

@@            Coverage Diff             @@
##             main    #1227      +/-   ##
==========================================
+ Coverage   31.43%   41.31%   +9.88%     
==========================================
  Files          32       32              
  Lines        4381     4393      +12     
  Branches     1022     1081      +59     
==========================================
+ Hits         1377     1815     +438     
+ Misses       2896     2437     -459     
- Partials      108      141      +33     

Flag	Coverage Δ
unittests	41.24% <66.66%> (+9.86%)	⬆️

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]

Can anyone test this with Azure OpenAI would be great! I patched this based only on their JSON schema.

[sonichi]

Could you make one "openai" test that uses azure openai endpoints (use filter_dict on api_type)?

[sonichi]

Update this part

[ekzhu]

I think 2023-10-01-preview exists as listed in the API spec repo. https://github.com/Azure/azure-rest-api-specs/tree/main/specification/cognitiveservices/data-plane/AzureOpenAI/inference/preview