AWS Certified AI Practitioner (AIF-C01) — Question 168

What is the purpose of chunking in Retrieval Augmented Generation (RAG)?

Answer options

• A. To avoid database storage limitations for large text documents by storing parts or chunks of the text
• B. To improve efficiency by avoiding the need to convert large text into vector embeddings
• C. To improve the contextual relevancy of results retrieved from the vector index
• D. To decrease the cost of storage by storing parts or chunks of the text

Correct answer: C

Explanation

The correct answer, C, highlights that chunking helps to maintain better contextual relevance in the results fetched from the vector index. Options A and D focus on storage limitations and costs, which are not the primary goals of chunking. Option B incorrectly suggests that chunking eliminates the need for vector embeddings, which is not accurate in the context of RAG.