Databricks Certified Generative AI Engineer Associate — Question 58

A Generative AI Engineer is developing a RAG application and would like to experiment with different embedding models to improve the application performance.

Which strategy for picking an embedding model should they choose?

Answer options

• A. Pick an embedding model with multilingual support to support potential multilingual user questions
• B. Pick the most recent and most performant open LLM released at the time
• C. Pick an embedding model trained on related domain knowledge
• D. Pick the embedding model ranked highest on the Massive Text Embedding Benchmark (MTEB) leaderboard hosted by HuggingFace

Correct answer: C

Explanation

The correct answer is C because selecting an embedding model trained on domain-specific knowledge ensures that the model is better equipped to understand and process relevant queries, thereby improving performance. Options A and D focus on multilingual support and leaderboard rankings, which may not necessarily align with the specifics of the application’s requirements. Option B prioritizes recency and general performance over domain relevance, which is crucial for a RAG application.