Creating a GenAI Powered Live Stream Virtual Assistant - Project Backend Architecture | S4E02 | Streaming on Streaming
We're looking at the API backend that will power Ivy.
Todd Sharp
Amazon Employee
Published Apr 17, 2024
In this episode, we talk about the architecture behind Project Ivy. We'll break down the CDK script that is used to deploy an Amazon IVS stage, chat room, and create some AWS Lambda functions that the app will use to invoke the LLM and synthesize Ivy's speech.
To view this Twitch stream, please accept cookies.
Any opinions in this post are those of the individual author and may not reflect the opinions of AWS.