AWS EKS Deployment Guide
This guide describes how to setup the Private AI container on AWS EKS.
Note:
If you are using the AWS Marketplace, please follow the AWS Marketplace Guide instead.
1. Prerequisites
Before you begin, ensure that you have installed the following tools:
Please also see our installation documentation for more information on how to load the Private AI docker image.
2. Create EKS cluster and node roles
Follow the AWS documentation to create an IAM role for your EKS cluster (if you don't have one already)
and this is to create an IAM role for your EKS node group.
Once you have both of these roles created, proceed to the next step to create your EKS cluster.
3. Create EKS Cluster
Follow the AWS documentation to create your EKS cluster which gives you the option to perform this task via eksctl, the AWS CLI tool or simply through the management console in the AWS portal.
Reminder:
Once you've created your cluster, don't forget to update your kubectl config to commincate with it by running:
aws eks update-kubeconfig --region region-code --name my-cluster4. Create EKS Node Group
Follow the AWS documentation to create an EKS node group either through eksctl or the management console in the AWS portal.
attention
For the AMI type, be sure to select an AMI with memory >16GB. In addition to this, if you plan to use the GPU container, be sure to select the GPU enabled Linux AMI and a disk size of >30GB.
For image and PDF processing we recommend choosing a larger instance type such as the m5zn.3xlarge for optimal performance.
5. Deploy
From here, you can follow our Kubernetes setup guide to go the rest of the way.