Skip to main content
Version: Next

Vertical Pod Autoscaler (VPA)

The following is an example on how to use VPA with the MLOps Python client:

vpa_spec = mlops.DeployVpaResourceSpec(
    cpu=mlops.DeployVpaResourceBounds(
        unit="CORES",
        max=2,
        min=1
    ),
    memory=mlops.DeployVpaResourceBounds(
        unit="GIB",
        max=3,
        min=2
    )
)


deployment = mlops.DeployDeployment(
                display_name="shady-mlops-client-deployment-test-2",
                description="shady-mlops-client-deployment-test-2",
                project_id=projects[0].id ,
                # monitor_disable=True,
                security=mlops.DeploySecurity(
                    passphrase=mlops.DeployAuthenticationPassphrase(
                        hash="this is a new plain-text",
                        passphrase_hash_type=mlops.DeployPassphraseHashType.PLAINTEXT
                    )
                ),
                deployment_environment_id=environments[0].id,
                single_deployment=mlops.DeploySingleDeployment(
                    deployment_composition=deployment_composition,
                    kubernetes_resource_spec=mlops.DeployKubernetesResourceSpec(
                        kubernetes_resource_requirement=mlops.DeployKubernetesResourceRequirement(
                            requests={
                                "cpu": "500m",
                                "memory": "350Mi"
                            },
                        ),
                        replicas=1,
                    ),
                    vpa_spec=vpa_spec
                ),
                custom_cors= mlops.DeployCors(
                    origins= ["http://localhost:8888/notebooks/mlops_client_basic.ipynb"]
                )
            )
Feedback