Databricks-GenAI-Assoc Data Preparation Practice Question
A Generative AI engineer is preparing a Delta table of support tickets for embedding generation. The pipeline computes embeddings with ai_query and stores them in a separate embeddings table keyed by ticket_id. Tickets are frequently updated by agents, and the engineer wants the embeddings table to reflect the latest ticket text without recomputing embeddings for tickets whose text has not changed. Which design best achieves this?
⚠ Common exam trap
The trap here is assuming a hash or file-optimization feature can skip unchanged rows across runs, when only a change data capture flow persists that decision.
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
✓
Use change data capture with APPLY CHANGES to merge ticket updates into the embeddings table, recomputing embeddings only for changed rows.
To update embeddings only for changed tickets, the pipeline must consume a change feed and apply changes to the embeddings table. APPLY CHANGES merges inserts, updates, and deletes while allowing embedding derivation to run only on changed rows. Full refreshes recompute everything, and file-level or query-level filters cannot persist decisions across updates.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Add a hash column of the ticket text and use a QUALIFY clause to filter unchanged rows within the same query.
Why it's wrong here
A hash column can identify changed text, but QUALIFY only filters within a single query execution and has no persistence across pipeline runs. It cannot decide which rows to skip in a future update based on what was already embedded. The result would still recompute embeddings for all rows in scope.
- ✓
Use change data capture with APPLY CHANGES to merge ticket updates into the embeddings table, recomputing embeddings only for changed rows.
Why this is correct
APPLY CHANGES processes the change feed and applies inserts, updates, and deletes to the embeddings table. By deriving embeddings from the changed rows only, unchanged tickets keep their existing vectors and are not re-embedded. This matches the requirement to reflect updates while avoiding redundant embedding computation.
- ✗
Enable Auto Optimize on the embeddings table so only modified files are rewritten during updates.
Why it's wrong here
Auto Optimize compacts small files and can optimize write layout, but it does not determine which rows need new embeddings. It operates at the file level for storage efficiency, not at the semantic level of detecting changed ticket text. Embedding recomputation would still occur for all rows in the write path.
- ✗
Run a full refresh of the embeddings table on every pipeline update so all ticket embeddings stay current.
Why it's wrong here
A full refresh recomputes every embedding on each update, which is exactly the expensive behavior the engineer wants to avoid. It ignores the fact that most ticket text is unchanged between updates. This approach wastes compute and increases cost without improving freshness for unchanged tickets.
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.