Answer-first summary for fast verification
Answer: Create an agent with tools for SQL querying of Delta tables and web searching, provide retrieved values to an LLM for generation of response.
Option D is the optimal choice because it creates an agent with tools for SQL querying of Delta tables and web searching, which directly addresses the requirement for real-time access to stock prices from Delta tables and the latest news articles via internet search. This approach allows the LLM to dynamically retrieve the most current information at runtime, ensuring the application has access to up-to-date data. In contrast, option A relies on pre-summarized news articles and may not capture real-time stock prices effectively. Option B focuses on querying for volatile stocks but does not comprehensively address the need for latest news articles. Option C involves storing data in a vector store, which may not be as effective for real-time data like stock prices and latest news, as it relies on pre-stored information that can become outdated quickly. The community discussion supports D, emphasizing that agents perform real-time queries and searches to gather up-to-date information, improving LLM response relevance.
Author: LeetQuiz Editorial Team
Ultimate access to all questions.
A Generative AI Engineer is building an LLM-powered application that requires access to real-time stock prices from Delta tables and the ability to find the latest relevant news articles via internet search. How should they architect the LLM system?
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.
No comments yet.