Databricks-GenAI-Assoc Design Applications Practice Question
A team is deploying a RAG chatbot that answers questions from internal policy documents. The documents change frequently, and the team wants retrieval to reflect updates within minutes without re-running a full embedding job. The source Delta table already has change data feed enabled. Which approach should the team use to keep the Databricks Vector Search index current?
⚠ Common exam trap
Many exam-takers confuse index freshness with endpoint capacity, when freshness depends on how changes flow from the Delta table into the index rather than on how much compute serves queries.
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
✓
Configure the index to sync from the Delta table so changes are propagated incrementally
A Delta-synced vector search index consumes change data feed events to apply inserts, updates, and deletes incrementally, keeping embeddings aligned with the source table. Rebuilding the index or tuning the endpoint addresses cost and throughput rather than freshness, and metadata filters only narrow an already-indexed set.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Increase the cluster size of the vector search endpoint
Why it's wrong here
Endpoint cluster size affects query throughput and latency, not how new or modified rows enter the index. A larger endpoint still serves the same stale vectors until a sync occurs, so it cannot make updated policy documents searchable and only adds cost.
- ✓
Configure the index to sync from the Delta table so changes are propagated incrementally
Why this is correct
A vector search index that syncs from a Delta table with change data feed enabled picks up inserts, updates, and deletes incrementally, so newly modified policy chunks become searchable shortly after they land. This meets the requirement of reflecting updates within minutes without recomputing embeddings for the entire corpus.
- ✗
Drop and recreate the vector search index on a schedule
Why it's wrong here
Dropping and recreating the index forces a full re-embedding and rebuild, which is expensive and leaves a window where the index is unavailable or stale. It also discards any incremental state, so the approach directly contradicts the goal of reflecting frequent document updates within minutes at low cost.
- ✗
Add a metadata filter for the document modification timestamp
Why it's wrong here
A metadata filter restricts which indexed rows a query considers, but it cannot introduce rows that were never indexed. If updated chunks are absent from the index, filtering by timestamp returns nothing new, so this option changes query scoping rather than index freshness.
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.