Question

A Generative AI Engineer has logged a RAG chain as an MLflow model in a Databricks notebook. The team requires that all production models be governed centrally, support cross-workspace sharing, and be referenced by a three-level namespace when deployed to a Model Serving endpoint. Which action correctly satisfies these governance and deployment requirements?

Accepted Answer

Register the model to Unity Catalog by setting the MLflow registry URI to 'databricks-uc' and registering under a catalog.schema.model name

Answer

Register the model to the workspace-local MLflow Model Registry and reference it by model name and version at serving time

Answer

Save the model artifacts to a DBFS path and point the serving endpoint directly at that path

Answer

Export the model as a .pkl file and upload it to a Unity Catalog volume, then load it in the serving container