Databricks Certified Generative AI Engineer Associate — Question 50

A Generative AI Engineer is developing a RAG system for their company to perform internal document Q&A for structured HR policies, but the answers returned are frequently incomplete and unstructured. It seems that the retriever is not returning all relevant context. The Generative AI Engineer has experimented with different embedding and response generating LLMs but that did not improve results.

Which TWO options could be used to improve the response quality? (Choose two.)

Answer options

• A. Add the section header as a prefix to chunks
• B. Split the document by sentence
• C. Use a larger embedding model
• D. Increase the document chunk size
• E. Fine tune the response generation model

Correct answer: A, D

Explanation

Option A is correct because adding the section header can provide essential context that enhances the relevance of the retrieved information. Option D is also correct as increasing the chunk size may allow for more comprehensive context to be included in each response. Options B and C may lead to fragmentation or insufficient context, while E may not address the root issue of context retrieval.