Answer-first summary for fast verification
Answer: Create a Feature Serving Endpoint from a FeatureSpec that references an online store synced from the Delta table. Query the Feature Serving Endpoint as part of the agent logic / tool implementation.
Option A is optimal because it leverages Databricks Feature Serving Endpoint with an online store synced from the Delta table, providing low-latency, real-time access to the continuously updated showtime data. This approach is specifically designed for high-performance feature retrieval in production scenarios, aligning with the requirement for least effort and highest performance. The community discussion supports A, noting its design for low-latency access and real-time sync from Delta tables. Option D (vector search) is inefficient for structured, location-based queries like showtimes, as it relies on embeddings and similarity search, which is overkill and less accurate for exact matches. Option B (direct SQL queries) lacks optimization and may introduce latency, while Option C (external database sync) adds unnecessary complexity and latency due to periodic writes.
Author: LeetQuiz Editorial Team
Ultimate access to all questions.
No comments yet.
A Generative AI Engineer is enhancing a cinema's website chatbot to answer questions about specific movie showtimes at the user's local theater. The user's location is already provided to the agent, and a continuously updated Delta table contains the latest showtime information by location. They want to implement this new capability in their RAG application.
Which approach accomplishes this with the least effort and the highest performance?
A
Create a Feature Serving Endpoint from a FeatureSpec that references an online store synced from the Delta table. Query the Feature Serving Endpoint as part of the agent logic / tool implementation.
B
Query the Delta table directly via a SQL query constructed from the user’s input using a text-to-SQL LLM in the agent logic / tool implementation.
C
Set up a task in Databricks Workflows to write the information in the Delta table periodically to an external database such as MySQL and query the information from there as part of the agent logic / tool implementation.
D
Write the Delta table contents to a text column, then embed those texts using an embedding model and store these in the vector index. Look up the information based on the embedding as part of the agent logic / tool implementation.