A developer is building a chain that takes a user's question, retrieves relevant documents, and generates an answer. The chain should be logged as an MLflow model and served. Which code snippet correctly logs the chain?

mlflow.transformers.log_model(chain, artifact_path='model')

mlflow.langchain.log_model(chain, artifact_path='model')

mlflow.pyfunc.log_model(chain, artifact_path='model')

mlflow.sklearn.log_model(chain, artifact_path='model')

A developer is building a simple chain that takes a user's question, retrieves relevant documents from a vector store, and passes them along with the question to a chat model. The chain should be logged as an MLflow model for later serving. Which code snippet correctly implements this chain?

chain = {'context': retriever, 'question': lambda x: x['question']} | prompt | model

chain = prompt | model | retriever

chain = prompt | retriever | model

chain = retriever | prompt | model

A company wants to serve a generative AI application that uses a Foundation Model API for text generation. They need to expose the application as a REST endpoint for internal applications. Which approach should they use?

Deploy the application as a Databricks Model Serving endpoint with the pyfunc model that calls the Foundation Model API.

Use the Foundation Model API directly from client applications without any wrapper.

Create a Databricks job that runs the application on a schedule and stores results in a table.

Use a Databricks SQL warehouse to query the Foundation Model API via SQL.

Which scenario is best suited for using ai_query() in Databricks?

Streaming live sensor data to a dashboard

Running a real-time inference endpoint for a web application

Processing a batch of customer reviews to classify sentiment

Training a new LLM model on a large corpus

DatabricksCertified Generative AI Engineer Associate

Domain 4Objective 2

Develop and Deploy LLM Applications GENERATIVE-AI-ENGINEER-ASSOCIATE Practice Questions (Page 3)

Part of the Section 4: Assembling and Deploying Applications domain, which makes up ~11% of our current practice bank. Databricks does not publish an official question count, but from its 90-minute exam (~35–60 total, ~4–7 in this domain), expect 1–2 from this objective — we provide 14 practice questions to prepare you well beyond it. (estimate)

14questions here

3free pages

4concepts

Questions 11–14

11application · medium
A developer is building a chain that takes a user's question, retrieves relevant documents, and generates an answer. The chain should be logged as an MLflow model and served. Which code snippet correctly logs the chain?
Select an answer first
12application · medium
A developer is building a simple chain that takes a user's question, retrieves relevant documents from a vector store, and passes them along with the question to a chat model. The chain should be logged as an MLflow model for later serving. Which code snippet correctly implements this chain?
Select an answer first
13application · medium
A company wants to serve a generative AI application that uses a Foundation Model API for text generation. They need to expose the application as a REST endpoint for internal applications. Which approach should they use?
Select an answer first
14foundation · easy
Which scenario is best suited for using ai_query() in Databricks?
Select an answer first

Finished these 4 questions?

Review the revealed explanations, or continue through the curriculum.

No more pagesBack to GENERATIVE-AI-ENGINEER-ASSOCIATE

Free Basic Practice is a study aid with revealable answers — not a scored exam. Examers.io is independent and not affiliated with or endorsed by Databricks. “GENERATIVE-AI-ENGINEER-ASSOCIATE” is a trademark of its owner, used for identification only.