Databricks-GenAI-Assoc Design Applications Practice Question
A GenAI engineer is building a RAG chatbot backed by a Databricks Vector Search index that is synced from a Delta table with Change Data Feed enabled. Source documents are frequently updated, and some are deleted. The engineer wants the index to reflect deletions and updates automatically with minimal operational overhead. Which configuration should be used?
⚠ Common exam trap
The trap here is assuming that a scheduled full refresh or a Direct Vector Access index provides the same incremental delete handling as a continuous Delta Sync index.
Answer choices
Why each option matters
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
✓
Create a Delta Sync index with a pipeline_type of CONTINUOUS, pointing at the source Delta table, and let Databricks manage synchronization.
Automatic reflection of inserts, updates, and deletes from a Delta source into a Vector Search index is achieved with a Delta Sync index running in CONTINUOUS pipeline mode, which consumes the source table's Change Data Feed. Triggered refreshes, Direct Vector Access, and index-side Change Data Feed all either add manual work, introduce staleness, or rely on unsupported behavior.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Create a Direct Vector Access index and write a Structured Streaming job that upserts embeddings into it whenever the source table changes.
Why it's wrong here
A Direct Vector Access index requires the engineer to compute and write embeddings and to handle deletes manually, which increases operational overhead rather than reducing it. It is intended for cases where you manage vectors outside Delta Sync, so it does not automatically propagate source-table deletions and updates the way the requirement demands.
- ✗
Create a Delta Sync index and enable Change Data Feed on the index itself so that deletions flow back into the source Delta table.
Why it's wrong here
Change Data Feed is a property of Delta tables, not of Vector Search indexes, and data flows from the source table into the index, not the reverse. Enabling CDF on the index is not a supported configuration, and it would not cause deletions in the source to be reflected in the index, so this option misstates how synchronization works.
- ✗
Create a Delta Sync index with a pipeline_type of TRIGGERED and schedule a Databricks Job to run a full refresh every 15 minutes.
Why it's wrong here
A TRIGGERED Delta Sync index only recomputes when the sync pipeline is explicitly run, and a full refresh rebuilds embeddings for every row. That approach discards incremental sync benefits, burns compute on unchanged documents, and adds up to 15 minutes of staleness, so it does not meet the goal of automatic, low-overhead updates and deletions.
- ✓
Create a Delta Sync index with a pipeline_type of CONTINUOUS, pointing at the source Delta table, and let Databricks manage synchronization.
Why this is correct
A CONTINUOUS Delta Sync index uses the source table's Change Data Feed to incrementally propagate inserts, updates, and deletes to the vector index without manual refreshes. This satisfies the requirement for automatic reflection of deletions and updates while minimizing operational overhead, because Databricks manages the sync pipeline and embedding computation end to end.
About these practice questions
This Databricks-GenAI-Assoc question is part of Courseiva's 330-question bank — original exam-style content with full explanations and wrong-answer analysis, never real exam questions or exam dumps. Learn why practice questions differ from exam dumps →
JA
Written and reviewed by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
Last reviewed September 2026 · checked against the official Databricks exam blueprint
This Databricks-GenAI-Assoc practice question is part of Courseiva's free Databricks certification practice question bank. Courseiva provides original exam-style practice questions with explanations, topic-based practice, mock exams, readiness tracking, and study analytics to help learners prepare for the Databricks-GenAI-Assoc exam.