Exam Certified Generative AI Engineer Associate topic 1 question 24 discussion

The correct answer is C. vsc.create_direct_access_index(). This is the appropriate next step when testing the setup of a vector store using Databricks managed embeddings and the default embedding model, especially if you’re not using a Delta table. create_direct_access_index() lets you manually add documents and embeddings, which is ideal for testing and minimal setup. Option B (create_delta_sync_index()) is used when you already have a Delta table and want your index to automatically sync with it — a better fit for production workflows, not initial testing.

After setting up a vector store endpoint, creating an index is necessary to start populating and organizing the data. The create_delta_sync_index() function specifically creates an index that synchronizes with a Delta table, allowing automatic updates as the data changes. This is likely the most appropriate choice if the engineer plans to use dynamic data that is updated over time.

If the question assumes "if you want to use the default embedding model managed by Databricks", then B. vsc.create_delta_sync_index() might be a more appropriate answer.