AWS · AIP-C01
FM API integration
AIP-C01 · Lesson 12 of 23 · 1:29:27
YouTube loads only after you press play. This chapter opens at its timestamp in the full course. Watch on YouTube ↗
In this lesson
Prepare for the AIP-C01 exam (AWS Certified Generative AI Developer - Professional). In this lesson: synchronous and asynchronous model calls with the AWS SDKs, SQS, and batch inference, API Gateway request validation, streaming with ConverseStream, WebSockets, server-sent events, and response streaming, SDK retries with backoff and jitter, usage plans, X-Ray, and model routing. Includes three original practice questions.
Preview the topics
- AnyCompany’s chat answers take twelve seconds to appear, all at once, and customers think the assistant froze. What improves the experience most?
- During flash sales, one partner application sends so many requests that the other applications get throttled by the model quota. What should AnyCompany configure?
- A chat request sometimes takes nine seconds, and the team cannot tell whether the time is spent in API Gateway, in Lambda, or in the model call. What should it use?