Throttle API Calls

[WaelKarkoub]

Why are these changes needed?

This PR introduces a naive time-based rate limiter to throttle API calls more effectively. While the existing FAQ suggests using max_retries for rate limit errors, this approach can be unreliable and requires fine-tuning. The new rate limiter provides a direct solution to control the flow of API requests, improving the overall reliability.

The user can now specify the api_rate_limit in the config list.

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

Attention: Patch coverage is 33.33333% with 20 lines in your changes missing coverage. Please review.

Project coverage is 12.60%. Comparing base (f9d3fda) to head (896f6ea).
Report is 11 commits behind head on main.

Files	Patch %	Lines
autogen/oai/client.py	18.75%	13 Missing ⚠️
autogen/oai/rate_limiters.py	50.00%	6 Missing and 1 partial ⚠️

Additional details and impacted files

@@             Coverage Diff             @@
##             main    #2283       +/-   ##
===========================================
- Coverage   33.88%   12.60%   -21.29%     
===========================================
  Files          87       89        +2     
  Lines        9422     9547      +125     
  Branches     2011     2194      +183     
===========================================
- Hits         3193     1203     -1990     
- Misses       5961     8327     +2366     
+ Partials      268       17      -251     

Flag	Coverage Δ
unittest	12.60% <33.33%> (?)
unittests	?

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.

Requested changes were made