Deploying the model
You can use an OpenShift AI model server to deploy the model as an API.
-
You have saved the model as described in Preparing the model for deployment.
-
You have installed KServe and enabled the model serving platform.
-
You have enabled a preinstalled or custom model-serving runtime.
-
You have obtained values for the following MinIO storage parameters:
-
Access Key
-
Secret Key
-
Endpoint
-
Region
-
Bucket
To obtain these values, navigate to your project’s Connections tab. For the MyStorage connection, click the action menu (⋮) and then click Edit.
-
-
In the OpenShift AI dashboard, navigate to the project details page and click the Deployments tab.
-
Click Deploy model.
The Deploy a model wizard opens.
-
In the Model details section, provide information about the model:
-
For Model location, select S3 object storage.
-
Enter the following values from your MinIO storage connection:
-
Access Key
-
Secret Key
-
Endpoint
-
Region
-
Bucket
-
-
For Path, enter
models/fraud. -
For Name, enter
MyStorage. -
For Model type, select Predictive model.
-
Click Next.
-
-
In the Model deployment section, configure the deployment:
-
For Model deployment name, enter
fraud. -
For Description, enter a description of your deployment.
-
For the hardware profile, keep the default value.
-
For Model framework (name - version), select
onnx-1. -
For the Serving runtime field, accept the auto-selected runtime,
OpenVINO Model Server. -
Click Next.
-
-
In the Advanced settings section, accept the defaults by clicking Next.
-
In the Review section, click Deploy model.
-
Confirm that the deployed model is shown on the Deployments tab for the project, and on the Deployments page of the dashboard with a Started status.
