Databricks-GenAI-Assoc Application Development Practice Question
A GenAI engineer has built a retrieval-augmented generation (RAG) application using Databricks Vector Search and a Databricks-hosted LLM served via Mosaic AI Model Serving. Users report that responses are sometimes irrelevant or cite incorrect document passages. The engineer wants to systematically improve answer quality by identifying which retrieved chunks are actually being used by the LLM. Which approach should the engineer take to capture the relationship between retrieved context and the generated response for later evaluation?
⚠ Common exam trap
The trap here is assuming that endpoint request logging alone provides enough detail to know which retrieved chunks influenced the answer, when it only captures the final prompt and response.
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 MLflow Tracing on the RAG chain to log each retrieval and generation step with inputs and outputs.
MLflow Tracing instruments each stage of a RAG pipeline, recording retrieved chunks and the LLM's output as linked spans. This gives the engineer the data needed to see which context was passed and potentially used, enabling targeted improvements and evaluation. Other options either change retrieval behavior or log only endpoint-level data, lacking the granular linkage required.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Configure the Model Serving endpoint to log all requests and responses to a Delta table for offline analysis.
Why it's wrong here
Inference table logging captures inputs and outputs but not the intermediate retrieval step or which specific chunks were passed to the LLM. Without tracing the retrieval span, the engineer cannot reliably map retrieved passages to the generated answer, making this insufficient for the stated goal.
- ✗
Increase the Vector Search index's embedding dimension to improve semantic matching.
Why it's wrong here
Changing embedding dimensions requires re-embedding and rebuilding the index, and it does not record which chunks the LLM used. It may alter retrieval results but provides no traceability between context and response, so it fails to meet the requirement of identifying used chunks.
- ✗
Add a reranker model after Vector Search to reorder retrieved chunks by relevance score.
Why it's wrong here
A reranker improves the ordering of retrieved chunks but does not provide visibility into which chunks the LLM actually used. It addresses retrieval quality, not traceability, so it does not satisfy the need to capture the context-response relationship for evaluation.
- ✓
Enable MLflow Tracing on the RAG chain to log each retrieval and generation step with inputs and outputs.
Why this is correct
MLflow Tracing captures spans for retrieval and LLM calls, including retrieved chunks and the final response, enabling correlation analysis. This directly addresses the need to see which context influenced the answer and supports systematic evaluation and debugging of the RAG pipeline.
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.