Databricks Certified Generative AI Engineer Associate — Question 60

A Generative AI Engineer has a provisioned throughput model serving endpoint as part of a RAG application and would like to monitor the serving endpoint’s incoming requests and outgoing responses.

Which Databricks feature should they use?

Answer options

• A. AutoML
• B. Vector Search
• C. Inference Tables
• D. Feature Serving

Correct answer: C

Explanation

The correct answer is Inference Tables, as they are specifically designed to monitor and log the requests and responses associated with serving endpoints. AutoML, Vector Search, and Feature Serving do not provide the same level of monitoring for incoming and outgoing data in this context.