AWS Certified Generative AI – Professional (AIP-C01) — Question 3

A company is developing a customer support application that uses Amazon Bedrock foundation models (FMs) to provide real-time AI assistance to the company's employees. The application must display AI-generated responses character by character as the responses are generated. The application needs to support thousands of concurrent users with minimal latency. The responses typically take 15 to 45 seconds to finish.
Which solution will meet these requirements?

Answer options

Correct answer: A

Explanation

Option A is correct because using a WebSocket API allows for real-time streaming of responses character by character, which is essential for the application's requirements. Option B relies on polling, which introduces unnecessary latency and does not stream responses in real-time. Option C lacks a gateway, which is crucial for managing multiple connections and ensuring scalability. Option D does not support real-time streaming and instead focuses on retrieving complete responses, which does not meet the application's need for character-by-character display.