Question 1

As a Gen AI engineer working on batch inference with MLflow, which of the following methods are correctly used for performing batch inference in single-node and multi-node environments? Choose two correct answers.

Options :

A : Implement mlflow.pyfunc.spark_udf(spark, model_uri=...) and result_df = prod_df.withColumn("result", model_udf("input")) for multi-node batch inference.

B : Apply mlflow.pyfunc.spark_udf(spark, model_uri=...) and .predict() for single-node batch inference.

C : Utilize mlflow.pyfunc.load_model() and result_df = prod_df.withColumn("result", model_udf("input")) for multi-node batch processing.

D : Use mlflow.pyfunc.load_model() and .predict() for single-node batch inference.

Answer: A,D

Question 2

As a Gen AI engineer working on a project that involves analyzing large volumes of customer feedback stored in a Databricks SQL, which of the following approaches is most appropriate for efficiently generating insights using an AI model?

Options :

A : Implement a custom script to manually invoke the Foundation Models API for each customer feedback entry individually, avoiding batch processing to ensure immediate responses.

B : Utilize a real-time streaming API to continuously feed customer feedback data into the AI model, even though the feedback is stored in SQL and does not change frequently.

C : Use ai_query() to perform batch inference directly from the Databricks SQL, which automatically parses and processes completions from the Foundation Models API.

D : Manually export the customer feedback data from SQL into a CSV file, then process the file one entry at a time using a local AI model without batching.

Answer: C

Question 3

As a Gen AI engineer managing the lifecycle of models in MLflow, which of the following URI patterns are used for referencing models in the Unity Catalog (MLflow) Model Registry? Choose two correct answers.

Options :

A : models:/{model_name}/latest

B : models:/{model_name}@{alias}

C : models:/{model_name}@{version}

D : models:/{model_name}/{model_version}

Answer: B,D

Question 4

As a Gen AI Engineer, you have a task to decide if you need a vector database for your Q&A chat bot. In which of the following scenarios you should use a vector database?

Options :

A : When you need to handle large-scale data, perform fast semantic searches, and require persistent storage.

B : When you need to quickly prototype a solution with a smaller dataset that can be handled in-memory.

C : When you need to store and retrieve large amounts of structured data based on exact matches.

D : When you need to perform keyword-based searches on a relational database.

Answer: A

Question 5

As a Gen AI engineer, you need to design a prompt for a model to extract and format customer data from a support ticket into JSON. Which of the following prompts will best ensure that the model outputs the data in the correct JSON format?

Options :

A : Extract the Customer Name, Issue Type, and Ticket ID from the support ticket and provide the results in JSON format.

B : Extract the following fields from the support ticket and format them as JSON: Customer Name, Issue Type, Ticket ID. Example output: {"Customer Name": "Alice Smith", "Issue Type": "Technical Support", "Ticket ID": "12345"}.

C : Provide a summary of the customer’s support ticket in JSON format.

Answer: B