Databricks Certified Generative AI Engineer Associate — Question 29

A Generative AI Engineer is creating an LLM-powered application that will need access to up-to-date news articles and stock prices.
The design requires the use of stock prices which are stored in Delta tables and finding the latest relevant news articles by searching the internet.
How should the Generative AI Engineer architect their LLM system?

Answer options

• A. Use an LLM to summarize the latest news articles and lookup stock tickers from the summaries to find stock prices.
• B. Query the Delta table for volatile stock prices and use an LLM to generate a search query to investigate potential causes of the stock volatility.
• C. Download and store news articles and stock price information in a vector store. Use a RAG architecture to retrieve and generate at runtime.
• D. Create an agent with tools for SQL querying of Delta tables and web searching, provide retrieved values to an LLM for generation of response.

Correct answer: D

Explanation

The correct answer is D because it allows for real-time querying of both Delta tables for stock prices and the web for news articles, enabling the LLM to generate informed responses. Option A relies too much on summaries, which may not capture full details; B focuses only on volatility without retrieving news; and C, while viable, does not provide real-time access to current information.