A team building a RAG application on Databricks needs to keep a vector index synchronized with an updating Delta table of policy documents. Which Databricks feature is the canonical fit?

• ASpark Streaming with a custom pipeline to write to a third-party vector database
• BDatabricks Vector Search with Delta Sync: define the source Delta table and the embedding model, and Databricks manages the sync
• CDaily batch export of the table to JSON, manual upload to an external vector store
• DManually re-index after every document change