Databricks-GenAI-Assoc Design Applications Practice Question
A generative AI team is building a customer-support assistant on Databricks. The assistant must answer questions using the company's private knowledge base, and the team wants to minimize latency while ensuring that the LLM only uses retrieved documents. They plan to use Databricks Vector Search with a Delta table as the source. Which design choice best balances low latency and grounded responses?
⚠ Common exam trap
The trap here is assuming that retrieving more chunks always improves grounding, when actually larger top-k without a relevance threshold increases latency and introduces noise that can cause the model to ignore the provided context.
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 a Vector Search index with a relevance score threshold and retrieve the top 5 chunks, then include those chunks in the prompt with instructions to answer only from the provided context.
Grounding requires retrieving only relevant context and instructing the model to use it. A Vector Search index with a relevance threshold and a small top-k (e.g., 5) reduces prompt size and latency while filtering weak matches. Including those chunks with an explicit instruction to answer from context limits hallucination. This combination balances performance and accuracy better than unfiltered or keyword-only retrieval.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Use a keyword-based search over the Delta table and pass the top 10 matching rows to the LLM, bypassing Vector Search entirely.
Why it's wrong here
Keyword search may miss semantically similar content and often returns irrelevant rows when exact terms differ. Passing top 10 rows increases prompt size and latency without ensuring relevance. Bypassing Vector Search forfeits semantic retrieval, which is critical for natural-language questions. This design does not reliably ground responses and can degrade answer quality.
- ✓
Use a Vector Search index with a relevance score threshold and retrieve the top 5 chunks, then include those chunks in the prompt with instructions to answer only from the provided context.
Why this is correct
This approach grounds the LLM by supplying only the most relevant retrieved chunks and explicitly instructing it to rely on that context. Limiting to top 5 with a relevance threshold reduces prompt size and latency while filtering out weak matches. Databricks Vector Search supports similarity search with scores, enabling this pattern, and the instruction reduces hallucination risk.
- ✗
Store the entire knowledge base in a single prompt and use a long-context LLM to answer questions without retrieval.
Why it's wrong here
Embedding the entire knowledge base into every prompt is impractical for large corpora, exceeds context limits, and increases latency and cost. It also does not guarantee that the model attends to the correct passage, so answers may be inaccurate. Retrieval is specifically designed to select relevant context, and omitting it undermines grounding and scalability.
- ✗
Configure a Vector Search index with a small embedding dimension and retrieve the top 20 chunks, then pass all chunks directly to the LLM without filtering.
Why it's wrong here
Retrieving top 20 chunks increases prompt size and latency, and passing all chunks without filtering can introduce irrelevant context that leads to ungrounded or contradictory answers. A smaller embedding dimension may reduce retrieval quality, and the lack of a relevance threshold means the LLM may still hallucinate when no good match exists. This design does not reliably ground responses.
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.