Skip to content

Containerization and cloud native suite for OPEA

License

Notifications You must be signed in to change notification settings

ChengyuZhu6/GenAIInfra

 
 

Repository files navigation

GenAIInfra

GenAIInfra is the containerization and cloud native suite for OPEA, including artifacts to deploy GenAIExamples in a cloud native way, which can be used by enterprise users to deploy to their own cloud.

Overview

The GenAIInfra repository is organized under four main directories, which include artifacts for OPEA deploying:

Directory Purpose
helm-charts Helm charts for deploying GenAIExamples on Kubernetes.
kubernetes-addons Deploy Kubernetes add-ons for OPEA.
manifests Manifests for deploying GenAIExamples on Kubernetes and on Docker Compose.
scripts Scripts for testing, tools for facilitate OPEA deployment, and etc.

Usages

Prerequisites

GenAIInfra uses Kubernetes as the cloud native infrastructure. You will need the access to either managed kubernetes services (e.g., EKS,ASK,GKE and etc) or self managed kubernetes.

Use helm charts to deploy

To deploy GenAIExamples to Kubernetes using helm charts, you need Helm installed on your machine.

Clone the GenAIInfra repository and change into the helm-charts directory:

git clone https://github.com/opea-project/GenAIInfra.git
cd GenAIInfra/helm-charts

Select the example workflow you want to deploy, set the customized values in values.yaml and deploy the example (e.g. codegen) using helm:

helm install codegen ./codegen

Use manifests to deploy

GenAIInfra also supports deploy GenAIExamples using manifests, you need kubectl installed on your machine.

Clone the GenAIInfra repository and change into the manifests directory:

git clone https://github.com/opea-project/GenAIInfra.git
cd GenAIInfra/manifests

Select the example workflow you want to deploy, deploy the example (e.g. DocSum) using kubectl:

kubectl apply -f ./DocSum/manifests/

About

Containerization and cloud native suite for OPEA

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Languages

  • Smarty 93.9%
  • Makefile 6.1%