Databricks Databricks-Generative-AI-Engineer-Associate 시험 개요:

Databricks Databricks-Generative-AI-Engineer-Associate 시험요강:

참조: https://www.databricks.com/learn/certification/genai-engineer-associate

최신 Generative AI Engineer Databricks-Generative-AI-Engineer-Associate 무료샘플문제

문제 #1
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. Save the model along with its dependencies in a local directory, build the Docker image, and run the Docker container
B. Wrap the LLM's prediction function into a Flask application and serve using Gunicorn
C. Log the model using MLflow during training, directly register the model to Unity Catalog using the MLflow API, and start a serving endpoint
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

문제 #2
A Generative AI Engineer has been asked to design an LLM-based application that accomplishes the following business objective: answer employee HR questions using HR PDF documentation.
Which set of high level tasks should the Generative AI Engineer ' s system perform?

A. Split HR documentation into chunks and embed into a vector store. Use the employee question to retrieve best matched chunks of documentation, and use the LLM to generate a response to the employee based upon the documentation retrieved.
B. Use an LLM to summarize HR documentation. Provide summaries of documentation and user query into an LLM with a large context window to generate a response to the user.
C. Calculate averaged embeddings for each HR document, compare embeddings to user query to find the best document. Pass the best document with the user query into an LLM with a large context window to generate a response to the employee.
D. Create an interaction matrix of historical employee questions and HR documentation. Use ALS to factorize the matrix and create embeddings. Calculate the embeddings of new queries and use them to find the best HR documentation. Use an LLM to generate a response to the employee question based upon the documentation retrieved.

문제 #3
A Generative AI Engineer has deployed a customer-support agent in production that retrieves product documentation and generates responses. SMEs have been reviewing agent responses and providing feedback through a web interface that captures ratings of 1-5 stars and written comments. The engineer needs to systematically collect this feedback and use it to create an evaluation dataset that can be used to compare future agent versions against the current baseline performance.
Which approach should the engineer use to accomplish this task?

A. Use the customer review app to collect SME feedback, then directly deploy the highest-rated responses as the new agent baseline without storing them as a formal evaluation dataset.
B. Use Unity Catalog to create a view that filters only 5-star-rated interactions, then register this view as the evaluation dataset to benchmark all future agent versions.
C. Log the SME ratings and comments directly to a Delta table with the corresponding user queries and agent responses, then use MLflow to create an evaluation dataset from this table and register it for future agent evaluations.
D. Export only the written SME comments to a text file and manually score them using a custom script, then use the script's output as the evaluation dataset for future agent comparisons.

문제 #4
Generative AI Engineer at an electronics company just deployed a RAG application for customers to ask questions about products that the company carries. However, they received feedback that the RAG response often returns information about an irrelevant product.
What can the engineer do to improve the relevance of the RAG's response?

A. Use a different LLM to improve the generated response
B. Assess the quality of the retrieved context
C. Implement caching for frequently asked questions
D. Use a different semantic similarity search algorithm

문제 #5
A Generative AI Engineer developed an LLM application using the provisioned throughput Foundation Model API. Now that the application is ready to be deployed, they realize their volume of requests are not sufficiently high enough to create their own provisioned throughput endpoint. They want to choose a strategy that ensures the best cost-effectiveness for their application.
What strategy should the Generative AI Engineer use?

A. Throttle the incoming batch of requests manually to avoid rate limiting issues
B. Change to a model with a fewer number of parameters in order to reduce hardware constraint issues
C. Switch to using External Models instead
D. Deploy the model using pay-per-token throughput as it comes with cost guarantees

질문과 대답: