Databricks Databricks-Generative-AI-Engineer-Associate Practice Exam Questions

Databricks Databricks-Generative-AI-Engineer-Associate Sample Question Answers

Question # 1

A Generative Al Engineer is tasked with developing an application that is based on an open sourcelarge language model (LLM). They need a foundation LLM with a large context window.Which model fits this need

A. DistilBERT
B. MPT-30B
C. Llama2-70B
D. DBRX

Show Answer

Question # 2

A Generative AI Engineer received the following business requirements for an external chatbot.The chatbot needs to know what types of questions the user asks and routes to appropriate modelsto answer the questions. For example, the user might ask about upcoming event details. Anotheruser might ask about purchasing tickets for a particular event.What is an ideal workflow for such a chatbot?

A. The chatbot should only look at previous event information
B. There should be two different chatbots handling different types of user queries.
C. The chatbot should be implemented as a multi-step LLM workflow. First, identify the type ofquestion asked, then route the question to the appropriate model. If its an upcoming eventquestion, send the query to a text-to-SQL model. If its about ticket purchasing, the customer shouldbe redirected to a payment platform.
D. The chatbot should only process payments

Show Answer

Question # 3

A Generative AI Engineer is building a RAG application that will rely on context retrieved from sourcedocuments that are currently in PDF format. These PDFs can contain both text and images. They wantto develop a solution using the least amount of lines of code.Which Python package should be used to extract the text from the source documents?

A. flask
B. beautifulsoup
C. unstructured
D. numpy

Show Answer

Question # 4

A team wants to serve a code generation model as an assistant for their software developers. Itshould support multiple programming languages. Quality is the primary objective.Which of the Databricks Foundation Model APIs, or models available in the Marketplace, would b the best fit?

A. Llama2-70b
B. BGE-large
C. MPT-7b
D. CodeLlama-34B

Show Answer

Question # 5

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

A. Randomness
B. Diversity of responses
C. Lack of relevance
D. Repetition of responses

Show Answer

Question # 6

A Generative AI Engineer is creating an LLM-powered application that will need access to up-to-datenews articles and stock prices.The design requires the use of stock prices which are stored in Delta tables and finding the latestrelevant news articles by searching the internet.How should the Generative AI Engineer architect their LLM system?

A. Use an LLM to summarize the latest news articles and lookup stock tickers from the summaries to find stock prices.
B. Query the Delta table for volatile stock prices and use an LLM to generate a search query toinvestigate potential causes of the stock volatility.
C. Download and store news articles and stock price information in a vector store. Use a RAGarchitecture to retrieve and generate at runtime.
D. Create an agent with tools for SQL querying of Delta tables and web searching, provide retrievedvalues to an LLM for generation of response.

Show Answer

Question # 7

A Generative AI Engineer is building an LLM to generate article summaries in the form of a type ofpoem, such as a haiku, given the article content. However, the initial output from the LLM does notmatch the desired tone or style.Which approach will NOT improve the LLMs response to achieve the desired response?

A. Provide the LLM with a prompt that explicitly instructs it to generate text in the desired tone and style
B. Use a neutralizer to normalize the tone and style of the underlying documents
C. Include few-shot examples in the prompt to the LLM
D. Fine-tune the LLM on a dataset of desired tone and style

Show Answer

Question # 8

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

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

Show Answer

Question # 9

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

A. Log the model as a pickle object, upload the object to Unity Catalog Volume, register it to UnityCatalog using MLflow, and start a serving endpoint
B. Log the model using MLflow during training, directly register the model to Unity Catalog using theMLflow API, and start a serving endpoint
C. Save the model along with its dependencies in a local directory, build the Docker image, and runthe Docker container
D. Wrap the LLMs prediction function into a Flask application and serve using Gunicorn

Show Answer

Question # 10

A Generative AI Engineer has created a RAG application which can help employees retrieve answersfrom an internal knowledge base, such as Confluence pages or Google Drive. The prototypeapplication is now working with some positive feedback from internal company testers. Now theGenerative Al Engineer wants to formally evaluate the systems performance and understand whereto focus their efforts to further improve the system.How should the Generative AI Engineer evaluate the system

A. Use cosine similarity score to comprehensively evaluate the quality of the final generatedanswers.
B. Curate a dataset that can test the retrieval and generation components of the system separately.Use MLflows built in evaluation metrics to perform the evaluation on the retrieval and generationcomponents.
C. Benchmark multiple LLMs with the same data and pick the best LLM for the job.
D. Use an LLM-as-a-judge to evaluate the quality of the final answers generated.

Show Answer