A Generative Al Engineer wants their (inetuned LLMs in their prod Databncks workspace available for testing in their dev workspace as well. All of their workspaces are Unity Catalog enabled and they are currently logging their models into the Model Registry in MLflow.
What is the most cost-effective and secure option for the Generative Al Engineer to accomplish their gAi?

1. A. Use an external model registry which can be accessed from all workspaces
2. B. Setup a script to export the model from prod and import it to dev.
3. C. Setup a duplicate training pipeline in dev, so that an identical model is available in dev.
4. D. Use MLflow to log the model directly into Unity Catalog, and enable READ access in the dev workspace to the model.

Correct Answer: D

A Generative AI Engineer has a provisioned throughput model serving endpoint as part of a RAG application and would like to monitor the serving endpoint??s incoming requests and outgoing responses. The current approach is to include a micro-service in between the endpoint and the user interface to write logs to a remote server.
Which Databricks feature should they use instead which will perform the same task?

1. A. Vector Search
2. B. Lakeview
3. C. DBSQL
4. D. Inference Tables

Correct Answer: D

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

1. A. DistilBERT
2. B. MPT-30B
3. C. Llama2-70B
4. D. DBRX

Correct Answer: C

A Generative AI Engineer is tasked with deploying an application that takes advantage of a custom MLflow Pyfunc model to return some interim results.
How should they configure the endpoint to pass the secrets and credentials?

1. A. Use spark.conf.set ()
2. B. Pass variables using the Databricks Feature Store API
3. C. Add credentials using environment variables
4. D. Pass the secrets in plain text

Correct Answer: C

A Generative Al Engineer has built an LLM-based system that will automatically translate user text between two languages. They now want to benchmark multiple LLM's on this task and pick the best one. They have an evaluation set with known high quality translation examples. They want to evaluate each LLM using the evaluation set with a performant metric.
Which metric should they choose for this evaluation?

1. A. ROUGE metric
2. B. BLEU metric
3. C. NDCG metric
4. D. RECALL metric

Correct Answer: B