Databricks-Generative-AI-Engineer-Associate無料問題集「Databricks Certified Generative AI Engineer Associate」

質問 1

A Generative Al Engineer is building a production-ready LLM system which replies directly to customers.
The solution makes use of the Foundation Model API via provisioned throughput. They are concerned that the LLM could potentially respond in a toxic or otherwise unsafe way. They also wish to perform this with the least amount of effort.
Which approach will do this?

（A）Host Llama Guard on Foundation Model API and use it to detect unsafe responses

（B）Ask users to report unsafe responses

（C）Add a regex expression on inputs and outputs to detect unsafe responses.

（D）Add some LLM calls to their chain to detect unsafe content before returning text

正解：A 解答を投票する

解説: (JPNTest メンバーにのみ表示されます)

質問 2

A Generative AI Engineer is designing a chatbot for a gaming company that aims to engage users on its platform while its users play online video games.
Which metric would help them increase user engagement and retention for their platform?

（A）Randomness

（B）Repetition of responses

（C）Diversity of responses

（D）Lack of relevance

正解：C 解答を投票する

解説: (JPNTest メンバーにのみ表示されます)

質問 3

A Generative Al Engineer has built an LLM-based system that will automatically translate user text between two languages. They now want to benchmark multiple LLM's on this task and pick the best one. They have an evaluation set with known high quality translation examples. They want to evaluate each LLM using the evaluation set with a performant metric.
Which metric should they choose for this evaluation?

（A）BLEU metric

（B）ROUGE metric

（C）NDCG metric

（D）RECALL metric

正解：A 解答を投票する

解説: (JPNTest メンバーにのみ表示されます)

質問 4

A Generative Al Engineer has already trained an LLM on Databricks and it is now ready to be deployed.
Which of the following steps correctly outlines the easiest process for deploying a model on Databricks?

（A）Wrap the LLM's prediction function into a Flask application and serve using Gunicorn

（B）Log the model using MLflow during training, directly register the model to Unity Catalog using the MLflow API, and start a serving endpoint

（C）Save the model along with its dependencies in a local directory, build the Docker image, and run the Docker container

（D）Log the model as a pickle object, upload the object to Unity Catalog Volume, register it to Unity Catalog using MLflow, and start a serving endpoint

正解：B 解答を投票する

解説: (JPNTest メンバーにのみ表示されます)

質問 5

A Generative Al 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 Al 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 2 answers

（A）Split the document by sentence

（B）Increase the document chunk size

（C）Add the section header as a prefix to chunks

（D）Fine tune the response generation model

（E）Use a larger embedding model

正解：B、C 解答を投票する

解説: (JPNTest メンバーにのみ表示されます)

質問 6

A small and cost-conscious startup in the cancer research field wants to build a RAG application using Foundation Model APIs.
Which strategy would allow the startup to build a good-quality RAG application while being cost-conscious and able to cater to customer needs?

（A）Use the largest LLM possible because that gives the best performance for any general queries

（B）Pick a smaller LLM that is domain-specific

（C）Limit the number of queries a customer can send per day

（D）Limit the number of relevant documents available for the RAG application to retrieve from

正解：B 解答を投票する

解説: (JPNTest メンバーにのみ表示されます)

Databricks-Generative-AI-Engineer-Associate 無料問題集「Databricks Certified Generative AI Engineer Associate」

弊社を連絡する

関連リンク

トップ試験