Use latest APIs for tool use, code execution and cache in topic pages

[ekzhu]

Why are these changes needed?

Use the latest APIs for the followings in topic pages:

1. Tool use
2. Caching
3. Code executors

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 :white_check_mark:

Project coverage is 36.63%. Comparing base (ca506ba) to head (7193343). Report is 3 commits behind head on main.

Additional details and impacted files

@@            Coverage Diff             @@
##             main    #2071      +/-   ##
==========================================
- Coverage   36.79%   36.63%   -0.16%     
==========================================
  Files          66       66              
  Lines        7060     7058       -2     
  Branches     1541     1541              
==========================================
- Hits         2598     2586      -12     
- Misses       4234     4244      +10     
  Partials      228      228              

Flag	Coverage Δ
unittests	36.63% <ø> (-0.16%)	:arrow_down:

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

:umbrella: View full report in Codecov by Sentry.
:loudspeaker: Have feedback on the report? Share it here.

[ekzhu]

@qingyun-wu could you run the notebooks to make sure the outputs are expected? Much appreciated!

[qingyun-wu]

@qingyun-wu could you run the notebooks to make sure the outputs are expected? Much appreciated!

Will do.

[qingyun-wu]

The reflection notebook's output is expected. "Approach 1. Two-agent chat with function call for task decomposition"of task_decomposition is not: The response of the tool call is null.

Haven't run the rest.

[ekzhu]

The reflection notebook's output is expected. "Approach 1. Two-agent chat with function call for task decomposition"of task_decomposition is not: The response of the tool call is null.

Haven't run the rest.

Looks like there is a bug in the notebook. The llm_config for planner and assistant agents should be separate. I have fixed it.

I have also updated all notebooks to use the latest tool use APIs, removing langchain dependency.

[ekzhu]

@qingyun-wu @jackgerrits @sonichi Can you take a look? I have fixed the notebooks to use the latest APIs.