Question 1

As a Gen AI Engineer, you have a task to decide if you need a vector database for your Q&A chat bot. In which of the following scenarios you should use a vector database?

Options :

A : When you need to handle large-scale data, perform fast semantic searches, and require persistent storage.

B : When you need to quickly prototype a solution with a smaller dataset that can be handled in-memory.

C : When you need to store and retrieve large amounts of structured data based on exact matches.

D : When you need to perform keyword-based searches on a relational database.

Answer: A

Question 2

As a Gen AI engineer working on improving a search engine’s ranking algorithm, you want to evaluate the effectiveness of your new ranking model. Which metric would you use to assess how well the model ranks the most relevant documents higher, taking into account both the position of the documents and their relevance?

Options :

A : Normalized Discounted Cumulative Gain (NDCG)

B : Mean Reciprocal Rank (MRR)

C : Precision at k

D : F1 Score

Answer: A

Question 3

As a Gen AI engineer working on a project that involves processing large volumes of text using a pre-trained model, which of the following methods is most commonly used for batch inference due to its practicality and ease of integration?

Options :

A : TensorRT

B : Ray on Spark

C : REST API calls for batch or real-time completion

D : vLLM

Answer: C

Question 4

As a Gen AI engineer setting up LLM-as-a-Judge for evaluating your model outputs, which of the following best practices should you follow to ensure effective evaluation?

Options :

A : Employ a wide variety of examples, including only examples of good outputs, to guide the LLM’s evaluation process.

B : Use a broad rubric scale, such as 1-10, to capture nuanced differences in the quality of outputs.

C : Use a high-token LLM to provide more context and detail in the evaluation, improving the quality of feedback from the model.

D : Avoid using an additive scale, as it can complicate the evaluation process and introduce inconsistencies.

Answer: C

Question 5

Which of the following parameters can affect the determinism and creativity of an LLM?

Options :

A : All of these options

B : "Top-k" value

C : "Top-p" value

D : "Temperature" value

Answer: A

Smartly Prepare Exam with Free Online Databricks-Certified-Generative-AI-Engineer-Associate Practice Test

Buying Options: