Exam Certified Generative AI Engineer Associate topic 1 question 27 discussion

Actual exam question from Databricks's Certified Generative AI Engineer Associate

Question #: 27
Topic #: 1

[All Certified Generative AI Engineer Associate Questions]

What is an effective method to preprocess prompts using custom code before sending them to an LLM?

A. Directly modify the LLM’s internal architecture to include preprocessing steps
B. It is better not to introduce custom code to preprocess prompts as the LLM has not been trained with examples of the preprocessed prompts
C. Rather than preprocessing prompts, it’s more effective to postprocess the LLM outputs to align the outputs to desired outcomes
D. Write a MLflow PyFunc model that has a separate function to process the prompts

Show Suggested Answer

Suggested Answer: D 🗳️

by trendy01 at Oct. 26, 2024, 5:41 a.m.

Comments

Submit Cancel

7e28dac

2 weeks, 1 day ago

Selected Answer: D

D is the most appropriate answer. MLFLow Pyfunc can handle custom functions related to input feed from Delta lake, Prompt Template for LLM's, They are also useful to register the model

upvoted 1 times

...

D appears to be the most appropriate choice. By writing MLflow PyFunc models and having a separate function to handle prompts, you can perform preprocessing more systematically and flexibly. This is a way to improve performance by providing optimized prompts for LLM.

upvoted 3 times

...