Databricks Certified Generative AI Engineer - Associate
Get started today
Ultimate access to all questions.
Comments
Loading comments...
Ultimate access to all questions.
A Generative AI Engineer is developing a customer support bot that must adapt its responses based on the sentiment of the end user's initial message. For instance, if the user's message is angry, the bot should attempt to de-escalate the negative sentiment while resolving the query. They aim to ensure this approach adheres to best practices.
Which method accomplishes this?
A
Use an encoder-only LLM model to both detect sentiment and generate replies based upon the detected sentiment.
B
Implement a RAG architecture for how to respond to users depending on detected sentiment.
C
Use linear regression model to classify sentiment and feed the result to a system prompt for the LLM to respond.
D
Create a chain which first uses an LLM to classify sentiment, then changes system prompt for the customer interaction LLM based upon the initial customer query sentiment.