Databricks Certified Generative AI Engineer Associate · Free Practice Question Medium
Question 22
A Generative AI Engineer is tasked with writing chunked user feedback data into Delta Lake tables. Which operation sequence ensures optimal data preparation and storage?
- A Write all feedback data as one large chunk into Delta Lake.
- B Skip chunking and directly write the feedback into Delta Lake.
- C Chunk the text first → Write the chunks into Delta Lake → Define the schema later.
- D Define schema for feedback data → Chunk the text → Write chunks into Delta Lake tables.
Reveal correct answer
Correct answer: D
Explanation
Defining the schema first ensures data consistency, and chunking facilitates efficient storage and retrieval in Delta Lake tables.A. Incorrect: Storing data as one large chunk reduces query performance and accessibility.
B. Incorrect: Unstructured data without chunking limits downstream processing efficiency.
C. Incorrect: Schema must be defined before writing to ensure proper organization.
D. Correct: Defining the schema first ensures structured data storage, improving accessibility and consistency.
Discussion
Think the marked answer is wrong, or have a better explanation? Share it below — comments appear after review.
You must be logged in to post a comment.
