Change contrib-tests.yml tests to use --skip-openai

[maxim-saplin]

Why are these changes needed?

contrib-tests.yml workflow used pip uninstall -y openai trick to skip the tests depending on OpenAI. Changed it to use pytest argument --skip-openai instead

Related issue number

Closes #1112

Notes

As of now the tests in contrib-tests.yml are mostly skipped cause they depend on OpenAI (~70-80% of individual tests are skipped). It makes sense to tidy up the file and remove all those OpenAI dependent tests as they don't do anything. Here're the breakdown for individual files:

RetrieveChatTest

	• test/test_retrieve_utils.py
	• [x][Always Skipped] test/agentchat/contrib/test_retrievechat.py
	• test/agentchat/contrib/test_qdrant_retrievechat.py


[x]CompressionTest
	
	• [x][Always Skipped]test/agentchat/contrib/test_compressible_agent.py


[x]GPTAssistantAgent
	
	• [x][Always Skipped]test/agentchat/contrib/test_gpt_assistant.py


[x]TeachableAgent

	• [x][Always Skipped]test/agentchat/contrib/test_teachable_agent.py


[x]LMMTest
	• test/agentchat/contrib/test_img_utils.py
	• test/agentchat/contrib/test_lmm.py
[x]test/agentchat/contrib/test_llava.py - depends on LLAVA imports

Checks

• [ N/A] 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.
• [N/A ] 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 ✅

Comparison is base (78a2d84) 31.80% compared to head (29d110f) 35.87%.

Additional details and impacted files

@@            Coverage Diff             @@
##             main    #1132      +/-   ##
==========================================
+ Coverage   31.80%   35.87%   +4.06%     
==========================================
  Files          29       31       +2     
  Lines        4112     4298     +186     
  Branches      961     1042      +81     
==========================================
+ Hits         1308     1542     +234     
+ Misses       2710     2650      -60     
- Partials       94      106      +12     

Flag	Coverage Δ
unittests	35.85% <ø> (+4.09%)	⬆️

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.

[afourney]

LGTM, but may conflict with #1072 since several tests needed to be corrected in that PR as well.

[sonichi]

There's a small issue.

[maxim-saplin]

@sonichi, I've modified both files, please check