Get Started Guide for Helm Deployment

• Time to Complete: 5 - 15 minutes

• Programming Language: Python*

Prerequisites

• Kubernetes Installation:

  • A functional Kubernetes cluster (v1.30.2) must be installed on the target environment (single or multi-node).

  • Recommended Installation Method: Utilize kubeadm, kubectl, and kubelet packages for installation.

  • Installation Guides:

    • Refer to resources like https://adamtheautomator.com/install-kubernetes-ubuntu and other online tutorials for guidance.

      • Note: The provided guide focuses on Ubuntu 22.04 as the host OS.

• Helm Installation:

  • Install Helm according to the official documentation: https://helm.sh/docs/intro/install/

Quick try out

Follow the steps in this section to quickly pull the latest pre-built Model Registry helm charts and run the microservice.

Create directories on your host system

1. Create directories to be used for persistent storage by the Postgres* and MinIO* Docker containers

   mkdir -p /opt/intel/mr/data/mr_postgres
   
   mkdir -p /opt/intel/mr/data/mr_minio
   
   useradd -u 2025 mruser
   
   chown -R mruser:mruser /opt/intel/mr/data/mr_postgres /opt/intel/mr/data/mr_minio
   

   • Note: The data in these directories will persist after the containers are removed. If you would like to subsequently start the containers with no pre-existing data, delete the contents in the directories before starting the containers.

Pull the helm chart and start

1. Pull the Helm chart from Docker Hub

   helm pull oci://registry-1.docker.io/intel/model-registry --version 1.0.1-helm
   

2. Unzip the file

   tar xvf model-registry-1.0.1-helm.tgz
   

3. Navigate into the directory

   cd model-registry
   

4. Open the values.yaml file and enter values for the following variables:

   • MINIO_SECRET_KEY

   • POSTGRES_PASSWORD

   For more information about the supported environment variables, refer to the Environment Variables documentation.

5. Install the helm chart

   helm install modelregistry . -n apps --create-namespace
   

6. Check the status of the pods and verify the microservice is running

   kubectl get pods --namespace apps
   

7. Monitor the logs for the pod associated to the model_registry to identify any issues and verify that it is operating successfully

   kubectl logs -f <pod_name> -n apps
   

After the deployment is complete, refer to the Tutorials for a quick introduction to the core functionality of the Model Registry microservice.

Summary

In this get started guide, you learned how to download and run the Model Registry microservice using a Helm chart.

Learn More

• Understand the components, services, high level and architecture in the Overview.

• Review supported environment variables in the Environment Variables documentation.

Legal Information

Intel, the Intel logo, and Xeon are trademarks of Intel Corporation in the U.S. and/or other countries.

*Other names and brands may be claimed as the property of others.