Question

You are building a RAG application on Databricks. Your source data lives in a Delta table with a text column containing pre-chunked passages, but you have NOT computed embeddings yourself and prefer not to manage the embedding pipeline. You want Databricks Vector Search to automatically compute and keep embeddings in sync as the Delta table changes. Which configuration should you choose when creating the Vector Search index?

Accepted Answer

Create a Delta Sync Index with 'Compute embeddings' enabled, specifying an embedding model endpoint and the text column to embed.

Answer

Create a Direct Vector Access Index and push precomputed embedding vectors via the REST API.

Answer

Create a Delta Sync Index using self-managed embeddings, pointing to an existing column that already contains vector values.

Answer

Create a Direct Vector Access Index with 'Compute embeddings' enabled so it re-embeds on every query.