Yuki Watanabe

@kaungmyat-htet Thank you for stepping forward for the contribution! > Is the below code correct? To remove in examples/transformers/conversational.py: Yes, the provided code change is correct. Just passing the string...

@kaungmyat-htet The updated version is correct! When an input example is passed, MLflow automatically runs prediction and infer signature based on its output, so we don't need to pass output...

@isuyyy The feature totally makes sense, looking forward to the PR!

Thanks for the heads-up. Taking a look at the PR and it looks great overall. Will take care of minor issues and merge it soon.

@bobojobo The proposal makes sense to me! Would you mind opening a PR for this?

Commented in the discussion, but wondering enabling OpenAI autologging together gives the visibility for the partial response. https://github.com/mlflow/mlflow/discussions/16211

Hi @Flametaa, the proposal makes sense to me! Would you be interested in opening a PR for this feature? Here are some pointers to get started: * Contribution guide: https://github.com/mlflow/mlflow/blob/master/CONTRIBUTING.md...

@deepupv We use SQLAlchemy to generate SQL and it seems there is [a similar issue](https://github.com/sqlalchemy/sqlalchemy/discussions/10524) opened in their repository, which I suspect is relevant. Will investigate how to prevent this...

@harupy Got it. For more context, we will highly likely to remove the `custom_metrics` parameter in the API simplification effort I'm working on (and going to close it in Q3)....

Hi @ekzhu, I'm Yuki from MLflow team. This issue is a dependency for us to integrate AutoGen 0.4>= with MLflow Tracing. Could you provide an update or a timeline for...