Databricks Databricks-Generative-AI-Engineer-Associate 問題集

質問 1：
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. Limit the number of relevant documents available for the RAG application to retrieve from
C. Limit the number of queries a customer can send per day
D. Pick a smaller LLM that is domain-specific
正解：D
解説: (Topexam メンバーにのみ表示されます)

質問 2：
A Generative AI Engineer just deployed an LLM application at a digital marketing company that assists with answering customer service inquiries.
Which metric should they monitor for their customer service LLM application in production?
A. HuggingFace Leaderboard values for the base LLM
B. Number of customer inquiries processed per unit of time
C. Energy usage per query
D. Final perplexity scores for the training of the model
正解：B
解説: (Topexam メンバーにのみ表示されます)

質問 3：
A Generative Al Engineer has developed an LLM application to answer questions about internal company policies. The Generative AI Engineer must ensure that the application doesn't hallucinate or leak confidential data.
Which approach should NOT be used to mitigate hallucination or confidential data leakage?
A. Limit the data available based on the user's access level
B. Add guardrails to filter outputs from the LLM before it is shown to the user
C. Fine-tune the model on your data, hoping it will learn what is appropriate and not
D. Use a strong system prompt to ensure the model aligns with your needs.
正解：C
解説: (Topexam メンバーにのみ表示されます)

質問 4：
A Generative Al Engineer is creating an LLM-based application. The documents for its retriever have been chunked to a maximum of 512 tokens each. The Generative Al Engineer knows that cost and latency are more important than quality for this application. They have several context length levels to choose from.
Which will fulfill their need?
A. context length 32768: smallest model is 14GB and embedding dimension 4096
B. context length 514; smallest model is 0.44GB and embedding dimension 768
C. context length 2048: smallest model is 11GB and embedding dimension 2560
D. context length 512: smallest model is 0.13GB and embedding dimension 384
正解：D
解説: (Topexam メンバーにのみ表示されます)

質問 5：
A Generative AI Engineer is designing an LLM-powered live sports commentary platform. The platform provides real-time updates and LLM-generated analyses for any users who would like to have live summaries, rather than reading a series of potentially outdated news articles.
Which tool below will give the platform access to real-time data for generating game analyses based on the latest game scores?
A. Feature Serving
B. DatabrickslQ
C. AutoML
D. Foundation Model APIs
正解：A
解説: (Topexam メンバーにのみ表示されます)