Enhance the behavior of the method that loads llm_config and add new tests
Why are these changes needed?
The current _validate_llm_config method contains redundancy and lacks comprehensive issue checks (for example, I was passing a string for tags and it didn't complain and required 30 minutes to debugging to figure out what the issue was). This improved version addresses these problems and includes 2 news tests.
Previous PR. Re-opening from upstream per Sonichi's comment.
Related issue number
Checks
- [x] 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.
- [x] I've added tests (if relevant) corresponding to the changes introduced in this PR.
- [x] I've made sure all auto checks have passed.
There's an error on macOS build. A URL on Huggingface is timing out (working fine locally). I can take a look at it later tonight
@sonichi closed the previous PR and reopened this one. Pls let me know if this is good.
@sonichi @jtoy can you pls review this? It's been open for a while
Are you willing to update the PR to ensure all tests pass?
This PR is against AutoGen 0.2. AutoGen 0.2 has been moved to the 0.2 branch. Please rebase your PR on the 0.2 branch or update it to work with the new AutoGen 0.4 that is now in main.
Looks like this is stale, if you want to pick this up again please feel free to reopen. Thanks!