Databricks Certified Generative AI Engineer Associate — Question 84
A Generative AI Engineer at an automotive company would like to build a question-answering chatbot to help customers answer specific questions about their vehicles. They have:
• A catalog with hundreds of thousands of cars manufactured since the 1960s
• Historical searches, with user queries and successful matches
• Descriptions of their own cars in multiple languages
They have already selected an open source LLM and created a test set of user queries. They need to discard techniques that will not help them build the chatbot.
Which do they discard?
Answer options
- A. Setting chunk size to match the model's context window to maximize coverage
- B. Implementing metadata filtering based on car models and years
- C. Fine-tuning an embedding model on automotive terminology
- D. Adding few-shot examples for response generation
Correct answer: A
Explanation
The correct answer is A because adjusting the chunk size to fit the model's context window does not directly enhance the chatbot's ability to answer specific queries effectively. Option B is useful for narrowing down relevant information, C helps in understanding automotive terms better, and D improves the chatbot's response quality through examples, all of which are beneficial for building a question-answering system.