Databricks Certified Generative AI Engineer Associate — Question 13

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. The current approach is to include a micro-service in between the endpoint and the user interface to write logs to a remote server.
Which Databricks feature should they use instead which will perform the same task?

Answer options

• A. Vector Search
• B. Lakeview
• C. DBSQL
• D. Inference Tables

Correct answer: D

Explanation

Inference Tables are designed to log incoming requests and outgoing responses for serving endpoints, making them suitable for this task. The other options, such as Vector Search, Lakeview, and DBSQL, do not provide the same logging capabilities and are focused on different functionalities.