Chapter 1. Architecture of OpenShift Data Science
Red Hat OpenShift Data Science is a fully Red Hat managed cloud service that is available as an Add-on to Red Hat OpenShift Dedicated and to Red Hat OpenShift Service on Amazon Web Services (ROSA).
OpenShift Data Science integrates the following components and services:
At the service layer:
- OpenShift Data Science dashboard
- A customer-facing dashboard that shows available and installed applications for the OpenShift Data Science environment as well as learning resources such as tutorials, quick start examples, and documentation. You can also access administrative functionality from the dashboard, such as user management, cluster settings, and notebook image settings. In addition, data scientists can create their own projects from the dashboard. This enables them to organize their data science work into a single project.
- Model serving
- Data scientists can deploy trained machine-learning models to serve intelligent applications in production. After deployment, applications can send requests to the model using its deployed API endpoint.
- Data science pipelines
- Data scientists can build portable machine learning (ML) workflows with data science pipelines, using Docker containers. This enables your data scientists to automate workflows as they develop their data science models.
- Jupyter (Red Hat managed)
- A Red Hat managed application that allows data scientists to configure their own notebook server environment and develop machine learning models in JupyterLab.
At the management layer:
- The Red Hat OpenShift Data Science operator
- A meta-operator that deploys and maintains all components and sub-operators that are part of OpenShift Data Science.
- Monitoring services
- Alertmanager, OpenShift Telemetry, and Prometheus work together to gather metrics from OpenShift Data Science and organize and display those metrics in useful ways for monitoring and billing purposes. Alerts from Alertmanager are sent to PagerDuty, responsible for notifying Red Hat of any issues with your managed cloud service.
When you install the OpenShift Data Science Add-on in the Cluster Manager, the following new projects are created:
redhat-ods-operatorproject contains the OpenShift Data Science operator.
redhat-ods-applicationsproject installs the dashboard and other required components of OpenShift Data Science.
redhat-ods-monitoringproject contains services for monitoring and billing.
rhods-notebooksproject is where notebook environments are deployed by default.
You or your data scientists must create additional projects for the applications that will use your machine learning models.
Do not install independent software vendor (ISV) applications in namespaces associated with OpenShift Data Science Add-ons unless you are specifically directed to do so on the application’s card on the dashboard.