Certified Machine Learning ProfessionalDemo

By Databricks · Question Mode

QuestionQ111

Custom Model Serving

A machine learning engineer has deployed a recommender model with MLflow Model Serving. They now need to query the version of that model in the Production stage of the MLflow Model Registry.

Which of the following model URIs can be used to query the specified model version?

  • A https://<databricks-instance>/model-serving/recommender/Production/invocations
  • B The version number of the model version in Production is necessary to complete this task.
  • C https://<databricks-instance>/model/recommender/stage-production/invocations
  • D https://<databricks-instance>/model-serving/recommender/stage-production/invocations
  • E https://<databricks-instance>/model/recommender/Production/invocations
Explanation

Legacy MLflow Model Serving identifies a deployed registered-model version by model name and registry stage using the path pattern /model/<model-name>/<stage>/invocations. Production is the stage selector, so the URI does not require an explicit model-version number. Databricks distinguishes this legacy model URL format from the newer serving-endpoints format.

Learn more

Community Discussion

No comments yet. Be the first to start the discussion!