Deploy a ML model, trained and registered in Databricks to AKS

[yopbibo]

Hi,

I can train, registered a ML Model in my Datbricks Workspace.

Then, to deploy it on AKS, I need to register the model in Azure ML, and then, deploy to AKS.

Is it possible to skip the Azure ML step?

I would like to deploy directly into my AKS instance, without registering in AML.

Thanks!

[Debayan]

Hi, Thanks for reaching out to Databricks.

Registering a model can be done, and it is not mentioned if it is optional or not in Microsoft documents.

Reference : https://docs.microsoft.com/en-gb/azure/databricks/applications/mlflow/models#register-models-in-the-...y.

As you will be deploying it in AKS, it will be better to reach out to Microsoft support on the same.

[yopbibo]

ok, thanks!

I will ask them.

I wish I could serve my models directly in Databricks, but still missing some features

[sidharthpradhan]

Is it still the case, can't we serve the model in Databricks. I am new to this, so I am just wondering the capabilities.