Databricks-GenAI-Assoc Design Applications Practice Question
A team is designing a Databricks GenAI application that must return grounded answers with citations to source documents. The application uses Databricks Vector Search for retrieval and a Foundation Model API for generation. Which TWO design choices are required to return accurate citations alongside each answer? (Choose two.)
⚠ Common exam trap
The trap here is assuming that better retrieval quality automatically yields citations, when provenance metadata and explicit attribution instructions are what actually enable them.
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
✓
Instruct the model in the prompt to reference the provided chunks by their identifiers and include those identifiers in the response.
Citations require two things working together: source metadata attached to each retrieved chunk so the application knows where content came from, and prompt instructions that tell the model to attribute statements to specific chunk identifiers. Precision tuning, billing mode, and temperature settings do not supply the provenance information or the attribution behavior needed to render citations.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✓
Instruct the model in the prompt to reference the provided chunks by their identifiers and include those identifiers in the response.
Why this is correct
Even with metadata available, the model must be told to attribute its statements to specific chunks. Prompting the model to cite chunk identifiers, and structuring the prompt so each chunk carries a visible ID, gives the model the information it needs to ground its answer and lets the application resolve those IDs into human-readable citations.
- ✗
Set the model's temperature to zero to guarantee that citations are factually correct.
Why it's wrong here
Zero temperature makes sampling deterministic and reduces variability, but it does not guarantee that citations are correct or that any citations appear at all. A deterministic model can still produce an ungrounded answer or omit attributions if the prompt and metadata do not support citation behavior, so this setting alone is insufficient.
- ✗
Increase the embedding model's dimensionality to the maximum supported value so retrieval is more precise.
Why it's wrong here
Higher dimensionality can improve semantic precision, but precision alone does not produce citations. Without source metadata attached to retrieved chunks, the application cannot tell which document a passage came from, so increasing dimensions does not enable citation rendering and may raise latency and storage cost.
- ✗
Enable Foundation Model API pay-per-token billing so the model has access to citation formatting.
Why it's wrong here
Billing mode does not change model capabilities or output formatting. Citation behavior comes from prompt instructions and the presence of source metadata in the retrieved context, not from how the endpoint is billed. Switching billing modes would not make the application emit citations and may not even be available for the chosen model.
- ✓
Store source metadata such as document ID, title, and chunk position alongside each embedding in the Vector Search index.
Why this is correct
Citations require knowing which source document and location each retrieved chunk came from. Storing document ID, title, and chunk position as metadata in the Vector Search index makes that information available with each retrieved result, so the application can map generated claims back to specific sources and render accurate citations.
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.