exam questions

Exam Certified Generative AI Engineer Associate All Questions

View all questions & answers for the Certified Generative AI Engineer Associate exam

Exam Certified Generative AI Engineer Associate topic 1 question 72 discussion

Actual exam question from Databricks's Certified Generative AI Engineer Associate
Question #: 72
Topic #: 1
[All Certified Generative AI Engineer Associate Questions]

A Generative AI Engineer is building a RAG application for answering employee questions on company policies.

What are the steps needed to build this RAG application and deploy it?

  • A. Ingest documents from a source -> Index the documents and saves to Vector Search -> User submits queries against an LLM -> LLM retrieves relevant documents -> Evaluate model -> LLM generates a response -> Deploy it using Model Serving
  • B. User submits queries against an LLM -> Ingest documents from a source -> Index the documents and save to Vector Search -> LLM retrieves relevant documents -> LLM generates a response -> Evaluate model -> Deploy it using Model Serving
  • C. Ingest documents from a source -> Index the documents and save to Vector Search -> Evaluate model -> Deploy it using Model Serving -> User submits queries against an LLM -> LLM retrieves relevant documents -> LLM generates a response
  • D. Ingest documents from a source -> Index the documents and save to Vector Search -> User submits queries against an LLM -> LLM retrieves relevant documents -> LLM generates a response -> Evaluate model -> Deploy it using Model Serving
Show Suggested Answer Hide Answer
Suggested Answer: D 🗳️

Comments

Chosen Answer:
This is a voting comment (?). It is better to Upvote an existing comment if you don't have anything to add.
Switch to a voting comment New
Lg22
4 weeks ago
Selected Answer: D
Evaluation should be after response. It should be D.
upvoted 2 times
...
csrazdan
1 month ago
Selected Answer: D
Evaluate has to be done after the response is generated so I think it is D. Refer to Q2 with similar explanation
upvoted 2 times
...
DavidMiller
1 month, 1 week ago
Selected Answer: B
Evaluation must happen after generation to assess output quality (e.g., hallucination rate, grounding accuracy, etc.). This sequencing is critical in production pipelines where model safety and performance matter. The answer marked as should not be considered valid - You can’t evaluate what hasn’t yet been generated.
upvoted 1 times
...
Community vote distribution
A (35%)
C (25%)
B (20%)
Other
Most Voted
A voting comment increases the vote count for the chosen answer by one.

Upvoting a comment with a selected answer will also increase the vote count towards that answer by one. So if you see a comment that you already agree with, you can upvote it instead of posting a new comment.

SaveCancel
Loading ...