Databricks-GenAI-Assoc Application Development Practice Question
A GenAI engineer is building a retrieval-augmented generation (RAG) application using Databricks Vector Search. During testing, they observe that for some queries, the retrieval step returns document chunks that are semantically similar but not actually relevant to the user's question, leading to poor answer quality. They want to improve retrieval precision without changing the embedding model. Which of the following approaches is most appropriate?
⚠ Common exam trap
The trap here is assuming that any change to the retrieval pipeline, such as adjusting chunk size or top_k, will improve precision, when in fact only hybrid search directly combines lexical and semantic signals.
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
✓
Enable hybrid search on the Vector Search index to combine keyword-based and vector similarity scores.
Hybrid search enhances retrieval precision by blending vector similarity with keyword matching, ensuring that chunks containing exact query terms are ranked higher. This directly addresses the problem of semantically similar but irrelevant results without altering the embedding model. The other options either do not tackle the precision issue or violate the constraint of not changing the embedding model.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Reduce the number of retrieved chunks (top_k) to only the single highest-scoring chunk.
Why it's wrong here
Reducing top_k to one chunk lowers recall and may exclude the truly relevant chunk if it is ranked second. It does not improve precision; it simply limits the context. The underlying issue of semantic drift remains, and the application may now miss necessary information, leading to incomplete or incorrect answers.
- ✗
Switch the embedding model to a larger, more powerful model to improve semantic representation.
Why it's wrong here
Changing the embedding model is explicitly excluded by the scenario, and it may not resolve the issue if the problem is that semantic similarity alone is insufficient for the query type. A larger model could still retrieve semantically similar but irrelevant chunks. The engineer needs a retrieval strategy improvement, not an embedding change.
- ✓
Enable hybrid search on the Vector Search index to combine keyword-based and vector similarity scores.
Why this is correct
Hybrid search in Databricks Vector Search combines dense vector similarity with keyword-based (lexical) matching, which helps surface chunks that contain exact terms from the query. This improves precision when purely semantic matches drift to unrelated content. It does not require changing the embedding model and is a supported index configuration, making it the most direct and effective fix for the described issue.
- ✗
Increase the chunk size of the documents to include more context per retrieved chunk.
Why it's wrong here
Increasing chunk size adds more text per chunk, but it does not address the core problem of retrieving semantically similar yet irrelevant chunks. Larger chunks may even dilute relevance and introduce noise. This approach does not improve precision and could worsen answer quality by including tangential information, so it is not the appropriate solution here.
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.