Databricks-GenAI-Assoc Data Preparation Practice Question
A team is building a RAG application using Databricks Vector Search with a Delta table as the source. They need the index to automatically reflect new and updated chunks as the source table changes, without rebuilding the entire index each time. Which configuration should they use?
⚠ Common exam trap
The trap here is thinking that Vector Search automatically tracks changes to any Delta table, when incremental sync requires Delta Sync and Change Data Feed to be configured.
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 Vector Search index with sync mode set to TRIGGERED or CONTINUOUS and specify a Delta table with Change Data Feed enabled as the source.
Delta Sync indexes in Databricks Vector Search rely on Change Data Feed to pick up inserts, updates, and deletes incrementally. Choosing a triggered or continuous sync mode keeps embeddings current without full recomputation. Enabling CDF on the source Delta table is a prerequisite, and this pattern is the documented way to keep a RAG index fresh as documents change.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Enable Delta Lake time travel on the source table and point the Vector Search index at a specific version using VERSION AS OF.
Why it's wrong here
Time travel pins the index to a snapshot, which is the opposite of incremental freshness. Vector Search does not read a version-pinned table and automatically advance; it would remain stale. Time travel is useful for auditing or rollback of the source data, not for keeping a vector index synchronized with ongoing changes.
- ✗
Use an external HNSW index built on a Databricks cluster and register it in Unity Catalog as a model, then query it with the model serving endpoint.
Why it's wrong here
Building an external HNSW index and registering it as a model bypasses Databricks Vector Search's managed synchronization. There is no automatic propagation of Delta changes to a model-registered index; the team would need to rebuild and redeploy. This approach adds operational overhead and does not satisfy the auto-sync requirement.
- ✓
Create a Vector Search index with sync mode set to TRIGGERED or CONTINUOUS and specify a Delta table with Change Data Feed enabled as the source.
Why this is correct
Databricks Vector Search supports Delta Sync indexes that read Change Data Feed from the source Delta table to incrementally update embeddings. Enabling CDF and choosing a triggered or continuous sync keeps the index fresh without full rebuilds. This is the supported pattern for production RAG pipelines where source documents are frequently updated.
- ✗
Create a standard Vector Search index and schedule a nightly job that drops the index and recreates it from the full Delta table.
Why it's wrong here
Dropping and recreating the index discards all embeddings and forces recomputation of every chunk, which is expensive and introduces downtime. It also loses index metadata and endpoint bindings temporarily. While it technically refreshes content, it is not incremental and does not meet the requirement of reflecting changes without rebuilding.
About these practice questions
One of 330 original Databricks-GenAI-Assoc practice questions on Courseiva, each with a full explanation and wrong-answer analysis — not exam dumps or protected exam content. 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.