Hi ApprehensiveSeaturtle9 , using the clearml-serving model remove ... CLI command you can remove the model endpoint and all associated monitoring. This should also remove the model registered in the system.

Hi thank you for your answer, this command call the method func_model_remove which remove the endpoint , model_monitoring and canary_endpoint but it does not remove the OutputModel and the py_code_mymodel.py (preprocessing) from the serving service

ApprehensiveSeaturtle9 when removing the endpoint, the function also internally removes the registered input model

Yes, I think you're correct - care to add a PR? 🙂

It does but not the OutputModel and the preprocess artifact. I managed to do it by adding:

if _task.artifacts.get(model_endpoint.preprocess_artifact):
    _task.delete_artifacts([model_endpoint.preprocess_artifact])
Model.remove(model_endpoint.model_id)

Maybe this should be add to the func_model_remove method?