Question

You are building a RAG application over a Delta table of internal knowledge base articles. The articles are edited frequently throughout the day by the support team, and the business requires that the vector index reflect edits within a few minutes without manual intervention. Your team has already enabled Change Data Feed on the source Delta table and set up a Databricks Vector Search endpoint. Which index configuration best meets these requirements?

Accepted Answer

Create a Delta Sync Index configured for continuous sync mode so the index automatically updates as the source table changes

Answer

Create a Delta Sync Index in triggered sync mode and manually run the sync pipeline whenever an editor reports a change

Answer

Create a Direct Vector Access Index and write a scheduled job that re-embeds and upserts every article each night

Answer

Create a Direct Vector Access Index and rely on the Vector Search endpoint to detect Delta table edits automatically