In this hands-on workshop, you will learn how to deploy a sample generative AI (GenAI) application on AWS EKS using OPEA and AWS CloudFormation. You’ll explore common infrastructure patterns for GenAI apps on AWS and leverage OPEA components to streamline the deployment process. This allows you to focus on building and optimizing the application without having to recreate complex infrastructure from scratch. Additionally, you will apply guardrails to control the behavior of your application and optimize its performance by integrating AWS services like OpenSearch.
If you complete the tasks ahead of schedule, there are optional exercises available, offering alternative ways to run LLM models (serverless) within your RAG deployment.
The workshop takes about two hours to complete in an AWS-sponsored setting with preconfigured accounts and about three hours to complete in your own account, given the extra deployment wait times.
This workshop is rated as Level 300 - Advanced and is designed for developers who want to gain hands-on experience with deploying generative AI applications on AWS services. This workshop is designed for developers with an advanced understanding of cloud infrastructure and AI/ML concepts. Participants should have a solid understanding of cloud computing, particularly with AWS services like Elastic Kubernetes Service (EKS) and CloudFormation, as these will be used to configure and manage the environment. Experience with containerization, Docker, and Kubernetes, especially within AWS EKS, will help you navigate the setup and deployment process.
While you don’t need to be a specialist in Retrieval-Augmented Generation (RAG), a basic understanding of generative AI models will be helpful. The workshop will explain the key RAG concepts, so you don’t need to have prior expertise in this area. Additionally, an understanding of how to integrate AWS services like OpenSearch to optimize AI performance will enhance your learning experience.
This workshop assumes that participants are comfortable working with the AWS Cloud Shell and in a hands-on lab environment. Participants should also be eager to deepen their expertise in deploying AI applications at scale using AWS and OPEA.