Docs Home Pulumi IaC Pulumi ESC Pulumi Insights Pulumi Cloud Packages Tutorials
  1. Packages
  2. Google Cloud Native
  3. API Docs
  4. ml
  5. ml/v1
  6. Version

Google Cloud Native is in preview. Google Cloud Classic is fully supported.

Google Cloud Native v0.32.0 published on Wednesday, Nov 29, 2023 by Pulumi
pulumi/pulumi-google-native

google-native.ml/v1.Version

Explore with Pulumi AI

Google Cloud Native is in preview. Google Cloud Classic is fully supported.

Google Cloud Native v0.32.0 published on Wednesday, Nov 29, 2023 by Pulumi
pulumi/pulumi-google-native

Creates a new version of a model from a trained TensorFlow model. If the version created in the cloud by this call is the first deployed version of the specified model, it will be made the default version of the model. When you add a version to a model that already has one or more versions, the default version does not automatically change. If you want a new version to be the default, you must call projects.models.versions.setDefault.

Create Version Resource

Resources are created with functions called constructors. To learn more about declaring and configuring resources, see Resources.

Constructor syntax

new Version(name: string, args: VersionArgs, opts?: CustomResourceOptions);
@overload
def Version(resource_name: str,
            args: VersionArgs,
            opts: Optional[ResourceOptions] = None)

@overload
def Version(resource_name: str,
            opts: Optional[ResourceOptions] = None,
            model_id: Optional[str] = None,
            runtime_version: Optional[str] = None,
            python_version: Optional[str] = None,
            manual_scaling: Optional[GoogleCloudMlV1__ManualScalingArgs] = None,
            name: Optional[str] = None,
            etag: Optional[str] = None,
            explanation_config: Optional[GoogleCloudMlV1__ExplanationConfigArgs] = None,
            framework: Optional[VersionFramework] = None,
            labels: Optional[Mapping[str, str]] = None,
            machine_type: Optional[str] = None,
            accelerator_config: Optional[GoogleCloudMlV1__AcceleratorConfigArgs] = None,
            deployment_uri: Optional[str] = None,
            description: Optional[str] = None,
            package_uris: Optional[Sequence[str]] = None,
            prediction_class: Optional[str] = None,
            project: Optional[str] = None,
            container: Optional[GoogleCloudMlV1__ContainerSpecArgs] = None,
            request_logging_config: Optional[GoogleCloudMlV1__RequestLoggingConfigArgs] = None,
            routes: Optional[GoogleCloudMlV1__RouteMapArgs] = None,
            auto_scaling: Optional[GoogleCloudMlV1__AutoScalingArgs] = None,
            service_account: Optional[str] = None)
func NewVersion(ctx *Context, name string, args VersionArgs, opts ...ResourceOption) (*Version, error)
public Version(string name, VersionArgs args, CustomResourceOptions? opts = null)
public Version(String name, VersionArgs args)
public Version(String name, VersionArgs args, CustomResourceOptions options)

type: google-native:ml/v1:Version
properties: # The arguments to resource properties.
options: # Bag of options to control resource's behavior.

Parameters

name This property is required. string
The unique name of the resource.
args This property is required. VersionArgs
The arguments to resource properties.
opts CustomResourceOptions
Bag of options to control resource's behavior.
resource_name This property is required. str
The unique name of the resource.
args This property is required. VersionArgs
The arguments to resource properties.
opts ResourceOptions
Bag of options to control resource's behavior.
ctx Context
Context object for the current deployment.
name This property is required. string
The unique name of the resource.
args This property is required. VersionArgs
The arguments to resource properties.
opts ResourceOption
Bag of options to control resource's behavior.
name This property is required. string
The unique name of the resource.
args This property is required. VersionArgs
The arguments to resource properties.
opts CustomResourceOptions
Bag of options to control resource's behavior.
name This property is required. String
The unique name of the resource.
args This property is required. VersionArgs
The arguments to resource properties.
options CustomResourceOptions
Bag of options to control resource's behavior.

Constructor example

The following reference example uses placeholder values for all input properties.

var exampleversionResourceResourceFromMlv1 = new GoogleNative.Ml.V1.Version("exampleversionResourceResourceFromMlv1", new()
{
    ModelId = "string",
    RuntimeVersion = "string",
    PythonVersion = "string",
    ManualScaling = new GoogleNative.Ml.V1.Inputs.GoogleCloudMlV1__ManualScalingArgs
    {
        Nodes = 0,
    },
    Name = "string",
    Etag = "string",
    ExplanationConfig = new GoogleNative.Ml.V1.Inputs.GoogleCloudMlV1__ExplanationConfigArgs
    {
        IntegratedGradientsAttribution = new GoogleNative.Ml.V1.Inputs.GoogleCloudMlV1__IntegratedGradientsAttributionArgs
        {
            NumIntegralSteps = 0,
        },
        SampledShapleyAttribution = new GoogleNative.Ml.V1.Inputs.GoogleCloudMlV1__SampledShapleyAttributionArgs
        {
            NumPaths = 0,
        },
        XraiAttribution = new GoogleNative.Ml.V1.Inputs.GoogleCloudMlV1__XraiAttributionArgs
        {
            NumIntegralSteps = 0,
        },
    },
    Framework = GoogleNative.Ml.V1.VersionFramework.FrameworkUnspecified,
    Labels = 
    {
        { "string", "string" },
    },
    MachineType = "string",
    AcceleratorConfig = new GoogleNative.Ml.V1.Inputs.GoogleCloudMlV1__AcceleratorConfigArgs
    {
        Count = "string",
        Type = GoogleNative.Ml.V1.GoogleCloudMlV1__AcceleratorConfigType.AcceleratorTypeUnspecified,
    },
    DeploymentUri = "string",
    Description = "string",
    PackageUris = new[]
    {
        "string",
    },
    PredictionClass = "string",
    Project = "string",
    Container = new GoogleNative.Ml.V1.Inputs.GoogleCloudMlV1__ContainerSpecArgs
    {
        Args = new[]
        {
            "string",
        },
        Command = new[]
        {
            "string",
        },
        Env = new[]
        {
            new GoogleNative.Ml.V1.Inputs.GoogleCloudMlV1__EnvVarArgs
            {
                Name = "string",
                Value = "string",
            },
        },
        Image = "string",
        Ports = new[]
        {
            new GoogleNative.Ml.V1.Inputs.GoogleCloudMlV1__ContainerPortArgs
            {
                ContainerPort = 0,
            },
        },
    },
    RequestLoggingConfig = new GoogleNative.Ml.V1.Inputs.GoogleCloudMlV1__RequestLoggingConfigArgs
    {
        BigqueryTableName = "string",
        SamplingPercentage = 0,
    },
    Routes = new GoogleNative.Ml.V1.Inputs.GoogleCloudMlV1__RouteMapArgs
    {
        Health = "string",
        Predict = "string",
    },
    AutoScaling = new GoogleNative.Ml.V1.Inputs.GoogleCloudMlV1__AutoScalingArgs
    {
        MaxNodes = 0,
        Metrics = new[]
        {
            new GoogleNative.Ml.V1.Inputs.GoogleCloudMlV1__MetricSpecArgs
            {
                Name = GoogleNative.Ml.V1.GoogleCloudMlV1__MetricSpecName.MetricNameUnspecified,
                Target = 0,
            },
        },
        MinNodes = 0,
    },
    ServiceAccount = "string",
});
Copy
example, err := ml.NewVersion(ctx, "exampleversionResourceResourceFromMlv1", &ml.VersionArgs{
	ModelId:        pulumi.String("string"),
	RuntimeVersion: pulumi.String("string"),
	PythonVersion:  pulumi.String("string"),
	ManualScaling: &ml.GoogleCloudMlV1__ManualScalingArgs{
		Nodes: pulumi.Int(0),
	},
	Name: pulumi.String("string"),
	Etag: pulumi.String("string"),
	ExplanationConfig: &ml.GoogleCloudMlV1__ExplanationConfigArgs{
		IntegratedGradientsAttribution: &ml.GoogleCloudMlV1__IntegratedGradientsAttributionArgs{
			NumIntegralSteps: pulumi.Int(0),
		},
		SampledShapleyAttribution: &ml.GoogleCloudMlV1__SampledShapleyAttributionArgs{
			NumPaths: pulumi.Int(0),
		},
		XraiAttribution: &ml.GoogleCloudMlV1__XraiAttributionArgs{
			NumIntegralSteps: pulumi.Int(0),
		},
	},
	Framework: ml.VersionFrameworkFrameworkUnspecified,
	Labels: pulumi.StringMap{
		"string": pulumi.String("string"),
	},
	MachineType: pulumi.String("string"),
	AcceleratorConfig: &ml.GoogleCloudMlV1__AcceleratorConfigArgs{
		Count: pulumi.String("string"),
		Type:  ml.GoogleCloudMlV1__AcceleratorConfigTypeAcceleratorTypeUnspecified,
	},
	DeploymentUri: pulumi.String("string"),
	Description:   pulumi.String("string"),
	PackageUris: pulumi.StringArray{
		pulumi.String("string"),
	},
	PredictionClass: pulumi.String("string"),
	Project:         pulumi.String("string"),
	Container: &ml.GoogleCloudMlV1__ContainerSpecArgs{
		Args: pulumi.StringArray{
			pulumi.String("string"),
		},
		Command: pulumi.StringArray{
			pulumi.String("string"),
		},
		Env: ml.GoogleCloudMlV1__EnvVarArray{
			&ml.GoogleCloudMlV1__EnvVarArgs{
				Name:  pulumi.String("string"),
				Value: pulumi.String("string"),
			},
		},
		Image: pulumi.String("string"),
		Ports: ml.GoogleCloudMlV1__ContainerPortArray{
			&ml.GoogleCloudMlV1__ContainerPortArgs{
				ContainerPort: pulumi.Int(0),
			},
		},
	},
	RequestLoggingConfig: &ml.GoogleCloudMlV1__RequestLoggingConfigArgs{
		BigqueryTableName:  pulumi.String("string"),
		SamplingPercentage: pulumi.Float64(0),
	},
	Routes: &ml.GoogleCloudMlV1__RouteMapArgs{
		Health:  pulumi.String("string"),
		Predict: pulumi.String("string"),
	},
	AutoScaling: &ml.GoogleCloudMlV1__AutoScalingArgs{
		MaxNodes: pulumi.Int(0),
		Metrics: ml.GoogleCloudMlV1__MetricSpecArray{
			&ml.GoogleCloudMlV1__MetricSpecArgs{
				Name:   ml.GoogleCloudMlV1__MetricSpecNameMetricNameUnspecified,
				Target: pulumi.Int(0),
			},
		},
		MinNodes: pulumi.Int(0),
	},
	ServiceAccount: pulumi.String("string"),
})
Copy
var exampleversionResourceResourceFromMlv1 = new com.pulumi.googlenative.ml_v1.Version("exampleversionResourceResourceFromMlv1", com.pulumi.googlenative.ml_v1.VersionArgs.builder()
    .modelId("string")
    .runtimeVersion("string")
    .pythonVersion("string")
    .manualScaling(GoogleCloudMlV1__ManualScalingArgs.builder()
        .nodes(0)
        .build())
    .name("string")
    .etag("string")
    .explanationConfig(GoogleCloudMlV1__ExplanationConfigArgs.builder()
        .integratedGradientsAttribution(GoogleCloudMlV1__IntegratedGradientsAttributionArgs.builder()
            .numIntegralSteps(0)
            .build())
        .sampledShapleyAttribution(GoogleCloudMlV1__SampledShapleyAttributionArgs.builder()
            .numPaths(0)
            .build())
        .xraiAttribution(GoogleCloudMlV1__XraiAttributionArgs.builder()
            .numIntegralSteps(0)
            .build())
        .build())
    .framework("FRAMEWORK_UNSPECIFIED")
    .labels(Map.of("string", "string"))
    .machineType("string")
    .acceleratorConfig(GoogleCloudMlV1__AcceleratorConfigArgs.builder()
        .count("string")
        .type("ACCELERATOR_TYPE_UNSPECIFIED")
        .build())
    .deploymentUri("string")
    .description("string")
    .packageUris("string")
    .predictionClass("string")
    .project("string")
    .container(GoogleCloudMlV1__ContainerSpecArgs.builder()
        .args("string")
        .command("string")
        .env(GoogleCloudMlV1__EnvVarArgs.builder()
            .name("string")
            .value("string")
            .build())
        .image("string")
        .ports(GoogleCloudMlV1__ContainerPortArgs.builder()
            .containerPort(0)
            .build())
        .build())
    .requestLoggingConfig(GoogleCloudMlV1__RequestLoggingConfigArgs.builder()
        .bigqueryTableName("string")
        .samplingPercentage(0)
        .build())
    .routes(GoogleCloudMlV1__RouteMapArgs.builder()
        .health("string")
        .predict("string")
        .build())
    .autoScaling(GoogleCloudMlV1__AutoScalingArgs.builder()
        .maxNodes(0)
        .metrics(GoogleCloudMlV1__MetricSpecArgs.builder()
            .name("METRIC_NAME_UNSPECIFIED")
            .target(0)
            .build())
        .minNodes(0)
        .build())
    .serviceAccount("string")
    .build());
Copy
exampleversion_resource_resource_from_mlv1 = google_native.ml.v1.Version("exampleversionResourceResourceFromMlv1",
    model_id="string",
    runtime_version="string",
    python_version="string",
    manual_scaling={
        "nodes": 0,
    },
    name="string",
    etag="string",
    explanation_config={
        "integrated_gradients_attribution": {
            "num_integral_steps": 0,
        },
        "sampled_shapley_attribution": {
            "num_paths": 0,
        },
        "xrai_attribution": {
            "num_integral_steps": 0,
        },
    },
    framework=google_native.ml.v1.VersionFramework.FRAMEWORK_UNSPECIFIED,
    labels={
        "string": "string",
    },
    machine_type="string",
    accelerator_config={
        "count": "string",
        "type": google_native.ml.v1.GoogleCloudMlV1__AcceleratorConfigType.ACCELERATOR_TYPE_UNSPECIFIED,
    },
    deployment_uri="string",
    description="string",
    package_uris=["string"],
    prediction_class="string",
    project="string",
    container={
        "args": ["string"],
        "command": ["string"],
        "env": [{
            "name": "string",
            "value": "string",
        }],
        "image": "string",
        "ports": [{
            "container_port": 0,
        }],
    },
    request_logging_config={
        "bigquery_table_name": "string",
        "sampling_percentage": 0,
    },
    routes={
        "health": "string",
        "predict": "string",
    },
    auto_scaling={
        "max_nodes": 0,
        "metrics": [{
            "name": google_native.ml.v1.GoogleCloudMlV1__MetricSpecName.METRIC_NAME_UNSPECIFIED,
            "target": 0,
        }],
        "min_nodes": 0,
    },
    service_account="string")
Copy
const exampleversionResourceResourceFromMlv1 = new google_native.ml.v1.Version("exampleversionResourceResourceFromMlv1", {
    modelId: "string",
    runtimeVersion: "string",
    pythonVersion: "string",
    manualScaling: {
        nodes: 0,
    },
    name: "string",
    etag: "string",
    explanationConfig: {
        integratedGradientsAttribution: {
            numIntegralSteps: 0,
        },
        sampledShapleyAttribution: {
            numPaths: 0,
        },
        xraiAttribution: {
            numIntegralSteps: 0,
        },
    },
    framework: google_native.ml.v1.VersionFramework.FrameworkUnspecified,
    labels: {
        string: "string",
    },
    machineType: "string",
    acceleratorConfig: {
        count: "string",
        type: google_native.ml.v1.GoogleCloudMlV1__AcceleratorConfigType.AcceleratorTypeUnspecified,
    },
    deploymentUri: "string",
    description: "string",
    packageUris: ["string"],
    predictionClass: "string",
    project: "string",
    container: {
        args: ["string"],
        command: ["string"],
        env: [{
            name: "string",
            value: "string",
        }],
        image: "string",
        ports: [{
            containerPort: 0,
        }],
    },
    requestLoggingConfig: {
        bigqueryTableName: "string",
        samplingPercentage: 0,
    },
    routes: {
        health: "string",
        predict: "string",
    },
    autoScaling: {
        maxNodes: 0,
        metrics: [{
            name: google_native.ml.v1.GoogleCloudMlV1__MetricSpecName.MetricNameUnspecified,
            target: 0,
        }],
        minNodes: 0,
    },
    serviceAccount: "string",
});
Copy
type: google-native:ml/v1:Version
properties:
    acceleratorConfig:
        count: string
        type: ACCELERATOR_TYPE_UNSPECIFIED
    autoScaling:
        maxNodes: 0
        metrics:
            - name: METRIC_NAME_UNSPECIFIED
              target: 0
        minNodes: 0
    container:
        args:
            - string
        command:
            - string
        env:
            - name: string
              value: string
        image: string
        ports:
            - containerPort: 0
    deploymentUri: string
    description: string
    etag: string
    explanationConfig:
        integratedGradientsAttribution:
            numIntegralSteps: 0
        sampledShapleyAttribution:
            numPaths: 0
        xraiAttribution:
            numIntegralSteps: 0
    framework: FRAMEWORK_UNSPECIFIED
    labels:
        string: string
    machineType: string
    manualScaling:
        nodes: 0
    modelId: string
    name: string
    packageUris:
        - string
    predictionClass: string
    project: string
    pythonVersion: string
    requestLoggingConfig:
        bigqueryTableName: string
        samplingPercentage: 0
    routes:
        health: string
        predict: string
    runtimeVersion: string
    serviceAccount: string
Copy

Version Resource Properties

To learn more about resource properties and how to use them, see Inputs and Outputs in the Architecture and Concepts docs.

Inputs

In Python, inputs that are objects can be passed either as argument classes or as dictionary literals.

The Version resource accepts the following input properties:

ModelId
This property is required.
Changes to this property will trigger replacement.
string
PythonVersion This property is required. string
The version of Python used in prediction. The following Python versions are available: * Python '3.7' is available when runtime_version is set to '1.15' or later. * Python '3.5' is available when runtime_version is set to a version from '1.4' to '1.14'. * Python '2.7' is available when runtime_version is set to '1.15' or earlier. Read more about the Python versions available for each runtime version.
RuntimeVersion This property is required. string
The AI Platform runtime version to use for this deployment. For more information, see the runtime version list and how to manage runtime versions.
AcceleratorConfig Pulumi.GoogleNative.Ml.V1.Inputs.GoogleCloudMlV1__AcceleratorConfig
Optional. Accelerator config for using GPUs for online prediction (beta). Only specify this field if you have specified a Compute Engine (N1) machine type in the machineType field. Learn more about using GPUs for online prediction.
AutoScaling Pulumi.GoogleNative.Ml.V1.Inputs.GoogleCloudMlV1__AutoScaling
Automatically scale the number of nodes used to serve the model in response to increases and decreases in traffic. Care should be taken to ramp up traffic according to the model's ability to scale or you will start seeing increases in latency and 429 response codes.
Container Pulumi.GoogleNative.Ml.V1.Inputs.GoogleCloudMlV1__ContainerSpec
Optional. Specifies a custom container to use for serving predictions. If you specify this field, then machineType is required. If you specify this field, then deploymentUri is optional. If you specify this field, then you must not specify runtimeVersion, packageUris, framework, pythonVersion, or predictionClass.
DeploymentUri string
The Cloud Storage URI of a directory containing trained model artifacts to be used to create the model version. See the guide to deploying models for more information. The total number of files under this directory must not exceed 1000. During projects.models.versions.create, AI Platform Prediction copies all files from the specified directory to a location managed by the service. From then on, AI Platform Prediction uses these copies of the model artifacts to serve predictions, not the original files in Cloud Storage, so this location is useful only as a historical record. If you specify container, then this field is optional. Otherwise, it is required. Learn how to use this field with a custom container.
Description string
Optional. The description specified for the version when it was created.
Etag string
etag is used for optimistic concurrency control as a way to help prevent simultaneous updates of a model from overwriting each other. It is strongly suggested that systems make use of the etag in the read-modify-write cycle to perform model updates in order to avoid race conditions: An etag is returned in the response to GetVersion, and systems are expected to put that etag in the request to UpdateVersion to ensure that their change will be applied to the model as intended.
ExplanationConfig Pulumi.GoogleNative.Ml.V1.Inputs.GoogleCloudMlV1__ExplanationConfig
Optional. Configures explainability features on the model's version. Some explanation features require additional metadata to be loaded as part of the model payload.
Framework Pulumi.GoogleNative.Ml.V1.VersionFramework
Optional. The machine learning framework AI Platform uses to train this version of the model. Valid values are TENSORFLOW, SCIKIT_LEARN, XGBOOST. If you do not specify a framework, AI Platform will analyze files in the deployment_uri to determine a framework. If you choose SCIKIT_LEARN or XGBOOST, you must also set the runtime version of the model to 1.4 or greater. Do not specify a framework if you're deploying a custom prediction routine or if you're using a custom container.
Labels Dictionary<string, string>
Optional. One or more labels that you can add, to organize your model versions. Each label is a key-value pair, where both the key and the value are arbitrary strings that you supply. For more information, see the documentation on using labels. Note that this field is not updatable for mls1* models.
MachineType string
Optional. The type of machine on which to serve the model. Currently only applies to online prediction service. To learn about valid values for this field, read Choosing a machine type for online prediction. If this field is not specified and you are using a regional endpoint, then the machine type defaults to n1-standard-2. If this field is not specified and you are using the global endpoint (ml.googleapis.com), then the machine type defaults to mls1-c1-m2.
ManualScaling Pulumi.GoogleNative.Ml.V1.Inputs.GoogleCloudMlV1__ManualScaling
Manually select the number of nodes to use for serving the model. You should generally use auto_scaling with an appropriate min_nodes instead, but this option is available if you want more predictable billing. Beware that latency and error rates will increase if the traffic exceeds that capability of the system to serve it based on the selected number of nodes.
Name string
The name specified for the version when it was created. The version name must be unique within the model it is created in.
PackageUris List<string>
Optional. Cloud Storage paths (gs://…) of packages for custom prediction routines or scikit-learn pipelines with custom code. For a custom prediction routine, one of these packages must contain your Predictor class (see predictionClass). Additionally, include any dependencies used by your Predictor or scikit-learn pipeline uses that are not already included in your selected runtime version. If you specify this field, you must also set runtimeVersion to 1.4 or greater.
PredictionClass string
Optional. The fully qualified name (module_name.class_name) of a class that implements the Predictor interface described in this reference field. The module containing this class should be included in a package provided to the packageUris field. Specify this field if and only if you are deploying a custom prediction routine (beta). If you specify this field, you must set runtimeVersion to 1.4 or greater and you must set machineType to a legacy (MLS1) machine type. The following code sample provides the Predictor interface: class Predictor(object): """Interface for constructing custom predictors.""" def predict(self, instances, **kwargs): """Performs custom prediction. Instances are the decoded values from the request. They have already been deserialized from JSON. Args: instances: A list of prediction input instances. **kwargs: A dictionary of keyword args provided as additional fields on the predict request body. Returns: A list of outputs containing the prediction results. This list must be JSON serializable. """ raise NotImplementedError() @classmethod def from_path(cls, model_dir): """Creates an instance of Predictor using the given path. Loading of the predictor should be done in this method. Args: model_dir: The local directory that contains the exported model file along with any additional files uploaded when creating the version resource. Returns: An instance implementing this Predictor class. """ raise NotImplementedError() Learn more about the Predictor interface and custom prediction routines.
Project Changes to this property will trigger replacement. string
RequestLoggingConfig Pulumi.GoogleNative.Ml.V1.Inputs.GoogleCloudMlV1__RequestLoggingConfig
Optional. Only specify this field in a projects.models.versions.patch request. Specifying it in a projects.models.versions.create request has no effect. Configures the request-response pair logging on predictions from this Version.
Routes Pulumi.GoogleNative.Ml.V1.Inputs.GoogleCloudMlV1__RouteMap
Optional. Specifies paths on a custom container's HTTP server where AI Platform Prediction sends certain requests. If you specify this field, then you must also specify the container field. If you specify the container field and do not specify this field, it defaults to the following: json { "predict": "/v1/models/MODEL/versions/VERSION:predict", "health": "/v1/models/MODEL/versions/VERSION" } See RouteMap for more details about these default values.
ServiceAccount string
Optional. Specifies the service account for resource access control. If you specify this field, then you must also specify either the containerSpec or the predictionClass field. Learn more about using a custom service account.
ModelId
This property is required.
Changes to this property will trigger replacement.
string
PythonVersion This property is required. string
The version of Python used in prediction. The following Python versions are available: * Python '3.7' is available when runtime_version is set to '1.15' or later. * Python '3.5' is available when runtime_version is set to a version from '1.4' to '1.14'. * Python '2.7' is available when runtime_version is set to '1.15' or earlier. Read more about the Python versions available for each runtime version.
RuntimeVersion This property is required. string
The AI Platform runtime version to use for this deployment. For more information, see the runtime version list and how to manage runtime versions.
AcceleratorConfig GoogleCloudMlV1__AcceleratorConfigArgs
Optional. Accelerator config for using GPUs for online prediction (beta). Only specify this field if you have specified a Compute Engine (N1) machine type in the machineType field. Learn more about using GPUs for online prediction.
AutoScaling GoogleCloudMlV1__AutoScalingArgs
Automatically scale the number of nodes used to serve the model in response to increases and decreases in traffic. Care should be taken to ramp up traffic according to the model's ability to scale or you will start seeing increases in latency and 429 response codes.
Container GoogleCloudMlV1__ContainerSpecArgs
Optional. Specifies a custom container to use for serving predictions. If you specify this field, then machineType is required. If you specify this field, then deploymentUri is optional. If you specify this field, then you must not specify runtimeVersion, packageUris, framework, pythonVersion, or predictionClass.
DeploymentUri string
The Cloud Storage URI of a directory containing trained model artifacts to be used to create the model version. See the guide to deploying models for more information. The total number of files under this directory must not exceed 1000. During projects.models.versions.create, AI Platform Prediction copies all files from the specified directory to a location managed by the service. From then on, AI Platform Prediction uses these copies of the model artifacts to serve predictions, not the original files in Cloud Storage, so this location is useful only as a historical record. If you specify container, then this field is optional. Otherwise, it is required. Learn how to use this field with a custom container.
Description string
Optional. The description specified for the version when it was created.
Etag string
etag is used for optimistic concurrency control as a way to help prevent simultaneous updates of a model from overwriting each other. It is strongly suggested that systems make use of the etag in the read-modify-write cycle to perform model updates in order to avoid race conditions: An etag is returned in the response to GetVersion, and systems are expected to put that etag in the request to UpdateVersion to ensure that their change will be applied to the model as intended.
ExplanationConfig GoogleCloudMlV1__ExplanationConfigArgs
Optional. Configures explainability features on the model's version. Some explanation features require additional metadata to be loaded as part of the model payload.
Framework VersionFramework
Optional. The machine learning framework AI Platform uses to train this version of the model. Valid values are TENSORFLOW, SCIKIT_LEARN, XGBOOST. If you do not specify a framework, AI Platform will analyze files in the deployment_uri to determine a framework. If you choose SCIKIT_LEARN or XGBOOST, you must also set the runtime version of the model to 1.4 or greater. Do not specify a framework if you're deploying a custom prediction routine or if you're using a custom container.
Labels map[string]string
Optional. One or more labels that you can add, to organize your model versions. Each label is a key-value pair, where both the key and the value are arbitrary strings that you supply. For more information, see the documentation on using labels. Note that this field is not updatable for mls1* models.
MachineType string
Optional. The type of machine on which to serve the model. Currently only applies to online prediction service. To learn about valid values for this field, read Choosing a machine type for online prediction. If this field is not specified and you are using a regional endpoint, then the machine type defaults to n1-standard-2. If this field is not specified and you are using the global endpoint (ml.googleapis.com), then the machine type defaults to mls1-c1-m2.
ManualScaling GoogleCloudMlV1__ManualScalingArgs
Manually select the number of nodes to use for serving the model. You should generally use auto_scaling with an appropriate min_nodes instead, but this option is available if you want more predictable billing. Beware that latency and error rates will increase if the traffic exceeds that capability of the system to serve it based on the selected number of nodes.
Name string
The name specified for the version when it was created. The version name must be unique within the model it is created in.
PackageUris []string
Optional. Cloud Storage paths (gs://…) of packages for custom prediction routines or scikit-learn pipelines with custom code. For a custom prediction routine, one of these packages must contain your Predictor class (see predictionClass). Additionally, include any dependencies used by your Predictor or scikit-learn pipeline uses that are not already included in your selected runtime version. If you specify this field, you must also set runtimeVersion to 1.4 or greater.
PredictionClass string
Optional. The fully qualified name (module_name.class_name) of a class that implements the Predictor interface described in this reference field. The module containing this class should be included in a package provided to the packageUris field. Specify this field if and only if you are deploying a custom prediction routine (beta). If you specify this field, you must set runtimeVersion to 1.4 or greater and you must set machineType to a legacy (MLS1) machine type. The following code sample provides the Predictor interface: class Predictor(object): """Interface for constructing custom predictors.""" def predict(self, instances, **kwargs): """Performs custom prediction. Instances are the decoded values from the request. They have already been deserialized from JSON. Args: instances: A list of prediction input instances. **kwargs: A dictionary of keyword args provided as additional fields on the predict request body. Returns: A list of outputs containing the prediction results. This list must be JSON serializable. """ raise NotImplementedError() @classmethod def from_path(cls, model_dir): """Creates an instance of Predictor using the given path. Loading of the predictor should be done in this method. Args: model_dir: The local directory that contains the exported model file along with any additional files uploaded when creating the version resource. Returns: An instance implementing this Predictor class. """ raise NotImplementedError() Learn more about the Predictor interface and custom prediction routines.
Project Changes to this property will trigger replacement. string
RequestLoggingConfig GoogleCloudMlV1__RequestLoggingConfigArgs
Optional. Only specify this field in a projects.models.versions.patch request. Specifying it in a projects.models.versions.create request has no effect. Configures the request-response pair logging on predictions from this Version.
Routes GoogleCloudMlV1__RouteMapArgs
Optional. Specifies paths on a custom container's HTTP server where AI Platform Prediction sends certain requests. If you specify this field, then you must also specify the container field. If you specify the container field and do not specify this field, it defaults to the following: json { "predict": "/v1/models/MODEL/versions/VERSION:predict", "health": "/v1/models/MODEL/versions/VERSION" } See RouteMap for more details about these default values.
ServiceAccount string
Optional. Specifies the service account for resource access control. If you specify this field, then you must also specify either the containerSpec or the predictionClass field. Learn more about using a custom service account.
modelId
This property is required.
Changes to this property will trigger replacement.
String
pythonVersion This property is required. String
The version of Python used in prediction. The following Python versions are available: * Python '3.7' is available when runtime_version is set to '1.15' or later. * Python '3.5' is available when runtime_version is set to a version from '1.4' to '1.14'. * Python '2.7' is available when runtime_version is set to '1.15' or earlier. Read more about the Python versions available for each runtime version.
runtimeVersion This property is required. String
The AI Platform runtime version to use for this deployment. For more information, see the runtime version list and how to manage runtime versions.
acceleratorConfig GoogleCloudMlV1__AcceleratorConfig
Optional. Accelerator config for using GPUs for online prediction (beta). Only specify this field if you have specified a Compute Engine (N1) machine type in the machineType field. Learn more about using GPUs for online prediction.
autoScaling GoogleCloudMlV1__AutoScaling
Automatically scale the number of nodes used to serve the model in response to increases and decreases in traffic. Care should be taken to ramp up traffic according to the model's ability to scale or you will start seeing increases in latency and 429 response codes.
container GoogleCloudMlV1__ContainerSpec
Optional. Specifies a custom container to use for serving predictions. If you specify this field, then machineType is required. If you specify this field, then deploymentUri is optional. If you specify this field, then you must not specify runtimeVersion, packageUris, framework, pythonVersion, or predictionClass.
deploymentUri String
The Cloud Storage URI of a directory containing trained model artifacts to be used to create the model version. See the guide to deploying models for more information. The total number of files under this directory must not exceed 1000. During projects.models.versions.create, AI Platform Prediction copies all files from the specified directory to a location managed by the service. From then on, AI Platform Prediction uses these copies of the model artifacts to serve predictions, not the original files in Cloud Storage, so this location is useful only as a historical record. If you specify container, then this field is optional. Otherwise, it is required. Learn how to use this field with a custom container.
description String
Optional. The description specified for the version when it was created.
etag String
etag is used for optimistic concurrency control as a way to help prevent simultaneous updates of a model from overwriting each other. It is strongly suggested that systems make use of the etag in the read-modify-write cycle to perform model updates in order to avoid race conditions: An etag is returned in the response to GetVersion, and systems are expected to put that etag in the request to UpdateVersion to ensure that their change will be applied to the model as intended.
explanationConfig GoogleCloudMlV1__ExplanationConfig
Optional. Configures explainability features on the model's version. Some explanation features require additional metadata to be loaded as part of the model payload.
framework VersionFramework
Optional. The machine learning framework AI Platform uses to train this version of the model. Valid values are TENSORFLOW, SCIKIT_LEARN, XGBOOST. If you do not specify a framework, AI Platform will analyze files in the deployment_uri to determine a framework. If you choose SCIKIT_LEARN or XGBOOST, you must also set the runtime version of the model to 1.4 or greater. Do not specify a framework if you're deploying a custom prediction routine or if you're using a custom container.
labels Map<String,String>
Optional. One or more labels that you can add, to organize your model versions. Each label is a key-value pair, where both the key and the value are arbitrary strings that you supply. For more information, see the documentation on using labels. Note that this field is not updatable for mls1* models.
machineType String
Optional. The type of machine on which to serve the model. Currently only applies to online prediction service. To learn about valid values for this field, read Choosing a machine type for online prediction. If this field is not specified and you are using a regional endpoint, then the machine type defaults to n1-standard-2. If this field is not specified and you are using the global endpoint (ml.googleapis.com), then the machine type defaults to mls1-c1-m2.
manualScaling GoogleCloudMlV1__ManualScaling
Manually select the number of nodes to use for serving the model. You should generally use auto_scaling with an appropriate min_nodes instead, but this option is available if you want more predictable billing. Beware that latency and error rates will increase if the traffic exceeds that capability of the system to serve it based on the selected number of nodes.
name String
The name specified for the version when it was created. The version name must be unique within the model it is created in.
packageUris List<String>
Optional. Cloud Storage paths (gs://…) of packages for custom prediction routines or scikit-learn pipelines with custom code. For a custom prediction routine, one of these packages must contain your Predictor class (see predictionClass). Additionally, include any dependencies used by your Predictor or scikit-learn pipeline uses that are not already included in your selected runtime version. If you specify this field, you must also set runtimeVersion to 1.4 or greater.
predictionClass String
Optional. The fully qualified name (module_name.class_name) of a class that implements the Predictor interface described in this reference field. The module containing this class should be included in a package provided to the packageUris field. Specify this field if and only if you are deploying a custom prediction routine (beta). If you specify this field, you must set runtimeVersion to 1.4 or greater and you must set machineType to a legacy (MLS1) machine type. The following code sample provides the Predictor interface: class Predictor(object): """Interface for constructing custom predictors.""" def predict(self, instances, **kwargs): """Performs custom prediction. Instances are the decoded values from the request. They have already been deserialized from JSON. Args: instances: A list of prediction input instances. **kwargs: A dictionary of keyword args provided as additional fields on the predict request body. Returns: A list of outputs containing the prediction results. This list must be JSON serializable. """ raise NotImplementedError() @classmethod def from_path(cls, model_dir): """Creates an instance of Predictor using the given path. Loading of the predictor should be done in this method. Args: model_dir: The local directory that contains the exported model file along with any additional files uploaded when creating the version resource. Returns: An instance implementing this Predictor class. """ raise NotImplementedError() Learn more about the Predictor interface and custom prediction routines.
project Changes to this property will trigger replacement. String
requestLoggingConfig GoogleCloudMlV1__RequestLoggingConfig
Optional. Only specify this field in a projects.models.versions.patch request. Specifying it in a projects.models.versions.create request has no effect. Configures the request-response pair logging on predictions from this Version.
routes GoogleCloudMlV1__RouteMap
Optional. Specifies paths on a custom container's HTTP server where AI Platform Prediction sends certain requests. If you specify this field, then you must also specify the container field. If you specify the container field and do not specify this field, it defaults to the following: json { "predict": "/v1/models/MODEL/versions/VERSION:predict", "health": "/v1/models/MODEL/versions/VERSION" } See RouteMap for more details about these default values.
serviceAccount String
Optional. Specifies the service account for resource access control. If you specify this field, then you must also specify either the containerSpec or the predictionClass field. Learn more about using a custom service account.
modelId
This property is required.
Changes to this property will trigger replacement.
string
pythonVersion This property is required. string
The version of Python used in prediction. The following Python versions are available: * Python '3.7' is available when runtime_version is set to '1.15' or later. * Python '3.5' is available when runtime_version is set to a version from '1.4' to '1.14'. * Python '2.7' is available when runtime_version is set to '1.15' or earlier. Read more about the Python versions available for each runtime version.
runtimeVersion This property is required. string
The AI Platform runtime version to use for this deployment. For more information, see the runtime version list and how to manage runtime versions.
acceleratorConfig GoogleCloudMlV1__AcceleratorConfig
Optional. Accelerator config for using GPUs for online prediction (beta). Only specify this field if you have specified a Compute Engine (N1) machine type in the machineType field. Learn more about using GPUs for online prediction.
autoScaling GoogleCloudMlV1__AutoScaling
Automatically scale the number of nodes used to serve the model in response to increases and decreases in traffic. Care should be taken to ramp up traffic according to the model's ability to scale or you will start seeing increases in latency and 429 response codes.
container GoogleCloudMlV1__ContainerSpec
Optional. Specifies a custom container to use for serving predictions. If you specify this field, then machineType is required. If you specify this field, then deploymentUri is optional. If you specify this field, then you must not specify runtimeVersion, packageUris, framework, pythonVersion, or predictionClass.
deploymentUri string
The Cloud Storage URI of a directory containing trained model artifacts to be used to create the model version. See the guide to deploying models for more information. The total number of files under this directory must not exceed 1000. During projects.models.versions.create, AI Platform Prediction copies all files from the specified directory to a location managed by the service. From then on, AI Platform Prediction uses these copies of the model artifacts to serve predictions, not the original files in Cloud Storage, so this location is useful only as a historical record. If you specify container, then this field is optional. Otherwise, it is required. Learn how to use this field with a custom container.
description string
Optional. The description specified for the version when it was created.
etag string
etag is used for optimistic concurrency control as a way to help prevent simultaneous updates of a model from overwriting each other. It is strongly suggested that systems make use of the etag in the read-modify-write cycle to perform model updates in order to avoid race conditions: An etag is returned in the response to GetVersion, and systems are expected to put that etag in the request to UpdateVersion to ensure that their change will be applied to the model as intended.
explanationConfig GoogleCloudMlV1__ExplanationConfig
Optional. Configures explainability features on the model's version. Some explanation features require additional metadata to be loaded as part of the model payload.
framework VersionFramework
Optional. The machine learning framework AI Platform uses to train this version of the model. Valid values are TENSORFLOW, SCIKIT_LEARN, XGBOOST. If you do not specify a framework, AI Platform will analyze files in the deployment_uri to determine a framework. If you choose SCIKIT_LEARN or XGBOOST, you must also set the runtime version of the model to 1.4 or greater. Do not specify a framework if you're deploying a custom prediction routine or if you're using a custom container.
labels {[key: string]: string}
Optional. One or more labels that you can add, to organize your model versions. Each label is a key-value pair, where both the key and the value are arbitrary strings that you supply. For more information, see the documentation on using labels. Note that this field is not updatable for mls1* models.
machineType string
Optional. The type of machine on which to serve the model. Currently only applies to online prediction service. To learn about valid values for this field, read Choosing a machine type for online prediction. If this field is not specified and you are using a regional endpoint, then the machine type defaults to n1-standard-2. If this field is not specified and you are using the global endpoint (ml.googleapis.com), then the machine type defaults to mls1-c1-m2.
manualScaling GoogleCloudMlV1__ManualScaling
Manually select the number of nodes to use for serving the model. You should generally use auto_scaling with an appropriate min_nodes instead, but this option is available if you want more predictable billing. Beware that latency and error rates will increase if the traffic exceeds that capability of the system to serve it based on the selected number of nodes.
name string
The name specified for the version when it was created. The version name must be unique within the model it is created in.
packageUris string[]
Optional. Cloud Storage paths (gs://…) of packages for custom prediction routines or scikit-learn pipelines with custom code. For a custom prediction routine, one of these packages must contain your Predictor class (see predictionClass). Additionally, include any dependencies used by your Predictor or scikit-learn pipeline uses that are not already included in your selected runtime version. If you specify this field, you must also set runtimeVersion to 1.4 or greater.
predictionClass string
Optional. The fully qualified name (module_name.class_name) of a class that implements the Predictor interface described in this reference field. The module containing this class should be included in a package provided to the packageUris field. Specify this field if and only if you are deploying a custom prediction routine (beta). If you specify this field, you must set runtimeVersion to 1.4 or greater and you must set machineType to a legacy (MLS1) machine type. The following code sample provides the Predictor interface: class Predictor(object): """Interface for constructing custom predictors.""" def predict(self, instances, **kwargs): """Performs custom prediction. Instances are the decoded values from the request. They have already been deserialized from JSON. Args: instances: A list of prediction input instances. **kwargs: A dictionary of keyword args provided as additional fields on the predict request body. Returns: A list of outputs containing the prediction results. This list must be JSON serializable. """ raise NotImplementedError() @classmethod def from_path(cls, model_dir): """Creates an instance of Predictor using the given path. Loading of the predictor should be done in this method. Args: model_dir: The local directory that contains the exported model file along with any additional files uploaded when creating the version resource. Returns: An instance implementing this Predictor class. """ raise NotImplementedError() Learn more about the Predictor interface and custom prediction routines.
project Changes to this property will trigger replacement. string
requestLoggingConfig GoogleCloudMlV1__RequestLoggingConfig
Optional. Only specify this field in a projects.models.versions.patch request. Specifying it in a projects.models.versions.create request has no effect. Configures the request-response pair logging on predictions from this Version.
routes GoogleCloudMlV1__RouteMap
Optional. Specifies paths on a custom container's HTTP server where AI Platform Prediction sends certain requests. If you specify this field, then you must also specify the container field. If you specify the container field and do not specify this field, it defaults to the following: json { "predict": "/v1/models/MODEL/versions/VERSION:predict", "health": "/v1/models/MODEL/versions/VERSION" } See RouteMap for more details about these default values.
serviceAccount string
Optional. Specifies the service account for resource access control. If you specify this field, then you must also specify either the containerSpec or the predictionClass field. Learn more about using a custom service account.
model_id
This property is required.
Changes to this property will trigger replacement.
str
python_version This property is required. str
The version of Python used in prediction. The following Python versions are available: * Python '3.7' is available when runtime_version is set to '1.15' or later. * Python '3.5' is available when runtime_version is set to a version from '1.4' to '1.14'. * Python '2.7' is available when runtime_version is set to '1.15' or earlier. Read more about the Python versions available for each runtime version.
runtime_version This property is required. str
The AI Platform runtime version to use for this deployment. For more information, see the runtime version list and how to manage runtime versions.
accelerator_config GoogleCloudMlV1AcceleratorConfigArgs
Optional. Accelerator config for using GPUs for online prediction (beta). Only specify this field if you have specified a Compute Engine (N1) machine type in the machineType field. Learn more about using GPUs for online prediction.
auto_scaling GoogleCloudMlV1AutoScalingArgs
Automatically scale the number of nodes used to serve the model in response to increases and decreases in traffic. Care should be taken to ramp up traffic according to the model's ability to scale or you will start seeing increases in latency and 429 response codes.
container GoogleCloudMlV1ContainerSpecArgs
Optional. Specifies a custom container to use for serving predictions. If you specify this field, then machineType is required. If you specify this field, then deploymentUri is optional. If you specify this field, then you must not specify runtimeVersion, packageUris, framework, pythonVersion, or predictionClass.
deployment_uri str
The Cloud Storage URI of a directory containing trained model artifacts to be used to create the model version. See the guide to deploying models for more information. The total number of files under this directory must not exceed 1000. During projects.models.versions.create, AI Platform Prediction copies all files from the specified directory to a location managed by the service. From then on, AI Platform Prediction uses these copies of the model artifacts to serve predictions, not the original files in Cloud Storage, so this location is useful only as a historical record. If you specify container, then this field is optional. Otherwise, it is required. Learn how to use this field with a custom container.
description str
Optional. The description specified for the version when it was created.
etag str
etag is used for optimistic concurrency control as a way to help prevent simultaneous updates of a model from overwriting each other. It is strongly suggested that systems make use of the etag in the read-modify-write cycle to perform model updates in order to avoid race conditions: An etag is returned in the response to GetVersion, and systems are expected to put that etag in the request to UpdateVersion to ensure that their change will be applied to the model as intended.
explanation_config GoogleCloudMlV1ExplanationConfigArgs
Optional. Configures explainability features on the model's version. Some explanation features require additional metadata to be loaded as part of the model payload.
framework VersionFramework
Optional. The machine learning framework AI Platform uses to train this version of the model. Valid values are TENSORFLOW, SCIKIT_LEARN, XGBOOST. If you do not specify a framework, AI Platform will analyze files in the deployment_uri to determine a framework. If you choose SCIKIT_LEARN or XGBOOST, you must also set the runtime version of the model to 1.4 or greater. Do not specify a framework if you're deploying a custom prediction routine or if you're using a custom container.
labels Mapping[str, str]
Optional. One or more labels that you can add, to organize your model versions. Each label is a key-value pair, where both the key and the value are arbitrary strings that you supply. For more information, see the documentation on using labels. Note that this field is not updatable for mls1* models.
machine_type str
Optional. The type of machine on which to serve the model. Currently only applies to online prediction service. To learn about valid values for this field, read Choosing a machine type for online prediction. If this field is not specified and you are using a regional endpoint, then the machine type defaults to n1-standard-2. If this field is not specified and you are using the global endpoint (ml.googleapis.com), then the machine type defaults to mls1-c1-m2.
manual_scaling GoogleCloudMlV1ManualScalingArgs
Manually select the number of nodes to use for serving the model. You should generally use auto_scaling with an appropriate min_nodes instead, but this option is available if you want more predictable billing. Beware that latency and error rates will increase if the traffic exceeds that capability of the system to serve it based on the selected number of nodes.
name str
The name specified for the version when it was created. The version name must be unique within the model it is created in.
package_uris Sequence[str]
Optional. Cloud Storage paths (gs://…) of packages for custom prediction routines or scikit-learn pipelines with custom code. For a custom prediction routine, one of these packages must contain your Predictor class (see predictionClass). Additionally, include any dependencies used by your Predictor or scikit-learn pipeline uses that are not already included in your selected runtime version. If you specify this field, you must also set runtimeVersion to 1.4 or greater.
prediction_class str
Optional. The fully qualified name (module_name.class_name) of a class that implements the Predictor interface described in this reference field. The module containing this class should be included in a package provided to the packageUris field. Specify this field if and only if you are deploying a custom prediction routine (beta). If you specify this field, you must set runtimeVersion to 1.4 or greater and you must set machineType to a legacy (MLS1) machine type. The following code sample provides the Predictor interface: class Predictor(object): """Interface for constructing custom predictors.""" def predict(self, instances, **kwargs): """Performs custom prediction. Instances are the decoded values from the request. They have already been deserialized from JSON. Args: instances: A list of prediction input instances. **kwargs: A dictionary of keyword args provided as additional fields on the predict request body. Returns: A list of outputs containing the prediction results. This list must be JSON serializable. """ raise NotImplementedError() @classmethod def from_path(cls, model_dir): """Creates an instance of Predictor using the given path. Loading of the predictor should be done in this method. Args: model_dir: The local directory that contains the exported model file along with any additional files uploaded when creating the version resource. Returns: An instance implementing this Predictor class. """ raise NotImplementedError() Learn more about the Predictor interface and custom prediction routines.
project Changes to this property will trigger replacement. str
request_logging_config GoogleCloudMlV1RequestLoggingConfigArgs
Optional. Only specify this field in a projects.models.versions.patch request. Specifying it in a projects.models.versions.create request has no effect. Configures the request-response pair logging on predictions from this Version.
routes GoogleCloudMlV1RouteMapArgs
Optional. Specifies paths on a custom container's HTTP server where AI Platform Prediction sends certain requests. If you specify this field, then you must also specify the container field. If you specify the container field and do not specify this field, it defaults to the following: json { "predict": "/v1/models/MODEL/versions/VERSION:predict", "health": "/v1/models/MODEL/versions/VERSION" } See RouteMap for more details about these default values.
service_account str
Optional. Specifies the service account for resource access control. If you specify this field, then you must also specify either the containerSpec or the predictionClass field. Learn more about using a custom service account.
modelId
This property is required.
Changes to this property will trigger replacement.
String
pythonVersion This property is required. String
The version of Python used in prediction. The following Python versions are available: * Python '3.7' is available when runtime_version is set to '1.15' or later. * Python '3.5' is available when runtime_version is set to a version from '1.4' to '1.14'. * Python '2.7' is available when runtime_version is set to '1.15' or earlier. Read more about the Python versions available for each runtime version.
runtimeVersion This property is required. String
The AI Platform runtime version to use for this deployment. For more information, see the runtime version list and how to manage runtime versions.
acceleratorConfig Property Map
Optional. Accelerator config for using GPUs for online prediction (beta). Only specify this field if you have specified a Compute Engine (N1) machine type in the machineType field. Learn more about using GPUs for online prediction.
autoScaling Property Map
Automatically scale the number of nodes used to serve the model in response to increases and decreases in traffic. Care should be taken to ramp up traffic according to the model's ability to scale or you will start seeing increases in latency and 429 response codes.
container Property Map
Optional. Specifies a custom container to use for serving predictions. If you specify this field, then machineType is required. If you specify this field, then deploymentUri is optional. If you specify this field, then you must not specify runtimeVersion, packageUris, framework, pythonVersion, or predictionClass.
deploymentUri String
The Cloud Storage URI of a directory containing trained model artifacts to be used to create the model version. See the guide to deploying models for more information. The total number of files under this directory must not exceed 1000. During projects.models.versions.create, AI Platform Prediction copies all files from the specified directory to a location managed by the service. From then on, AI Platform Prediction uses these copies of the model artifacts to serve predictions, not the original files in Cloud Storage, so this location is useful only as a historical record. If you specify container, then this field is optional. Otherwise, it is required. Learn how to use this field with a custom container.
description String
Optional. The description specified for the version when it was created.
etag String
etag is used for optimistic concurrency control as a way to help prevent simultaneous updates of a model from overwriting each other. It is strongly suggested that systems make use of the etag in the read-modify-write cycle to perform model updates in order to avoid race conditions: An etag is returned in the response to GetVersion, and systems are expected to put that etag in the request to UpdateVersion to ensure that their change will be applied to the model as intended.
explanationConfig Property Map
Optional. Configures explainability features on the model's version. Some explanation features require additional metadata to be loaded as part of the model payload.
framework "FRAMEWORK_UNSPECIFIED" | "TENSORFLOW" | "SCIKIT_LEARN" | "XGBOOST"
Optional. The machine learning framework AI Platform uses to train this version of the model. Valid values are TENSORFLOW, SCIKIT_LEARN, XGBOOST. If you do not specify a framework, AI Platform will analyze files in the deployment_uri to determine a framework. If you choose SCIKIT_LEARN or XGBOOST, you must also set the runtime version of the model to 1.4 or greater. Do not specify a framework if you're deploying a custom prediction routine or if you're using a custom container.
labels Map<String>
Optional. One or more labels that you can add, to organize your model versions. Each label is a key-value pair, where both the key and the value are arbitrary strings that you supply. For more information, see the documentation on using labels. Note that this field is not updatable for mls1* models.
machineType String
Optional. The type of machine on which to serve the model. Currently only applies to online prediction service. To learn about valid values for this field, read Choosing a machine type for online prediction. If this field is not specified and you are using a regional endpoint, then the machine type defaults to n1-standard-2. If this field is not specified and you are using the global endpoint (ml.googleapis.com), then the machine type defaults to mls1-c1-m2.
manualScaling Property Map
Manually select the number of nodes to use for serving the model. You should generally use auto_scaling with an appropriate min_nodes instead, but this option is available if you want more predictable billing. Beware that latency and error rates will increase if the traffic exceeds that capability of the system to serve it based on the selected number of nodes.
name String
The name specified for the version when it was created. The version name must be unique within the model it is created in.
packageUris List<String>
Optional. Cloud Storage paths (gs://…) of packages for custom prediction routines or scikit-learn pipelines with custom code. For a custom prediction routine, one of these packages must contain your Predictor class (see predictionClass). Additionally, include any dependencies used by your Predictor or scikit-learn pipeline uses that are not already included in your selected runtime version. If you specify this field, you must also set runtimeVersion to 1.4 or greater.
predictionClass String
Optional. The fully qualified name (module_name.class_name) of a class that implements the Predictor interface described in this reference field. The module containing this class should be included in a package provided to the packageUris field. Specify this field if and only if you are deploying a custom prediction routine (beta). If you specify this field, you must set runtimeVersion to 1.4 or greater and you must set machineType to a legacy (MLS1) machine type. The following code sample provides the Predictor interface: class Predictor(object): """Interface for constructing custom predictors.""" def predict(self, instances, **kwargs): """Performs custom prediction. Instances are the decoded values from the request. They have already been deserialized from JSON. Args: instances: A list of prediction input instances. **kwargs: A dictionary of keyword args provided as additional fields on the predict request body. Returns: A list of outputs containing the prediction results. This list must be JSON serializable. """ raise NotImplementedError() @classmethod def from_path(cls, model_dir): """Creates an instance of Predictor using the given path. Loading of the predictor should be done in this method. Args: model_dir: The local directory that contains the exported model file along with any additional files uploaded when creating the version resource. Returns: An instance implementing this Predictor class. """ raise NotImplementedError() Learn more about the Predictor interface and custom prediction routines.
project Changes to this property will trigger replacement. String
requestLoggingConfig Property Map
Optional. Only specify this field in a projects.models.versions.patch request. Specifying it in a projects.models.versions.create request has no effect. Configures the request-response pair logging on predictions from this Version.
routes Property Map
Optional. Specifies paths on a custom container's HTTP server where AI Platform Prediction sends certain requests. If you specify this field, then you must also specify the container field. If you specify the container field and do not specify this field, it defaults to the following: json { "predict": "/v1/models/MODEL/versions/VERSION:predict", "health": "/v1/models/MODEL/versions/VERSION" } See RouteMap for more details about these default values.
serviceAccount String
Optional. Specifies the service account for resource access control. If you specify this field, then you must also specify either the containerSpec or the predictionClass field. Learn more about using a custom service account.

Outputs

All input properties are implicitly available as output properties. Additionally, the Version resource produces the following output properties:

CreateTime string
The time the version was created.
ErrorMessage string
The details of a failure or a cancellation.
Id string
The provider-assigned unique ID for this managed resource.
IsDefault bool
If true, this version will be used to handle prediction requests that do not specify a version. You can change the default version by calling projects.methods.versions.setDefault.
LastMigrationModelId string
The AI Platform (Unified) Model ID for the last model migration.
LastMigrationTime string
The last time this version was successfully migrated to AI Platform (Unified).
LastUseTime string
The time the version was last used for prediction.
State string
The state of a version.
CreateTime string
The time the version was created.
ErrorMessage string
The details of a failure or a cancellation.
Id string
The provider-assigned unique ID for this managed resource.
IsDefault bool
If true, this version will be used to handle prediction requests that do not specify a version. You can change the default version by calling projects.methods.versions.setDefault.
LastMigrationModelId string
The AI Platform (Unified) Model ID for the last model migration.
LastMigrationTime string
The last time this version was successfully migrated to AI Platform (Unified).
LastUseTime string
The time the version was last used for prediction.
State string
The state of a version.
createTime String
The time the version was created.
errorMessage String
The details of a failure or a cancellation.
id String
The provider-assigned unique ID for this managed resource.
isDefault Boolean
If true, this version will be used to handle prediction requests that do not specify a version. You can change the default version by calling projects.methods.versions.setDefault.
lastMigrationModelId String
The AI Platform (Unified) Model ID for the last model migration.
lastMigrationTime String
The last time this version was successfully migrated to AI Platform (Unified).
lastUseTime String
The time the version was last used for prediction.
state String
The state of a version.
createTime string
The time the version was created.
errorMessage string
The details of a failure or a cancellation.
id string
The provider-assigned unique ID for this managed resource.
isDefault boolean
If true, this version will be used to handle prediction requests that do not specify a version. You can change the default version by calling projects.methods.versions.setDefault.
lastMigrationModelId string
The AI Platform (Unified) Model ID for the last model migration.
lastMigrationTime string
The last time this version was successfully migrated to AI Platform (Unified).
lastUseTime string
The time the version was last used for prediction.
state string
The state of a version.
create_time str
The time the version was created.
error_message str
The details of a failure or a cancellation.
id str
The provider-assigned unique ID for this managed resource.
is_default bool
If true, this version will be used to handle prediction requests that do not specify a version. You can change the default version by calling projects.methods.versions.setDefault.
last_migration_model_id str
The AI Platform (Unified) Model ID for the last model migration.
last_migration_time str
The last time this version was successfully migrated to AI Platform (Unified).
last_use_time str
The time the version was last used for prediction.
state str
The state of a version.
createTime String
The time the version was created.
errorMessage String
The details of a failure or a cancellation.
id String
The provider-assigned unique ID for this managed resource.
isDefault Boolean
If true, this version will be used to handle prediction requests that do not specify a version. You can change the default version by calling projects.methods.versions.setDefault.
lastMigrationModelId String
The AI Platform (Unified) Model ID for the last model migration.
lastMigrationTime String
The last time this version was successfully migrated to AI Platform (Unified).
lastUseTime String
The time the version was last used for prediction.
state String
The state of a version.

Supporting Types

GoogleCloudMlV1__AcceleratorConfig
, GoogleCloudMlV1__AcceleratorConfigArgs

Count string
The number of accelerators to attach to each machine running the job.
Type Pulumi.GoogleNative.Ml.V1.GoogleCloudMlV1__AcceleratorConfigType
The type of accelerator to use.
Count string
The number of accelerators to attach to each machine running the job.
Type GoogleCloudMlV1__AcceleratorConfigType
The type of accelerator to use.
count String
The number of accelerators to attach to each machine running the job.
type GoogleCloudMlV1__AcceleratorConfigType
The type of accelerator to use.
count string
The number of accelerators to attach to each machine running the job.
type GoogleCloudMlV1__AcceleratorConfigType
The type of accelerator to use.
count str
The number of accelerators to attach to each machine running the job.
type GoogleCloudMlV1AcceleratorConfigType
The type of accelerator to use.

GoogleCloudMlV1__AcceleratorConfigResponse
, GoogleCloudMlV1__AcceleratorConfigResponseArgs

Count This property is required. string
The number of accelerators to attach to each machine running the job.
Type This property is required. string
The type of accelerator to use.
Count This property is required. string
The number of accelerators to attach to each machine running the job.
Type This property is required. string
The type of accelerator to use.
count This property is required. String
The number of accelerators to attach to each machine running the job.
type This property is required. String
The type of accelerator to use.
count This property is required. string
The number of accelerators to attach to each machine running the job.
type This property is required. string
The type of accelerator to use.
count This property is required. str
The number of accelerators to attach to each machine running the job.
type This property is required. str
The type of accelerator to use.
count This property is required. String
The number of accelerators to attach to each machine running the job.
type This property is required. String
The type of accelerator to use.

GoogleCloudMlV1__AcceleratorConfigType
, GoogleCloudMlV1__AcceleratorConfigTypeArgs

AcceleratorTypeUnspecified
ACCELERATOR_TYPE_UNSPECIFIEDUnspecified accelerator type. Default to no GPU.
NvidiaTeslaK80
NVIDIA_TESLA_K80Nvidia Tesla K80 GPU.
NvidiaTeslaP100
NVIDIA_TESLA_P100Nvidia Tesla P100 GPU.
NvidiaTeslaV100
NVIDIA_TESLA_V100Nvidia V100 GPU.
NvidiaTeslaP4
NVIDIA_TESLA_P4Nvidia Tesla P4 GPU.
NvidiaTeslaT4
NVIDIA_TESLA_T4Nvidia T4 GPU.
NvidiaTeslaA100
NVIDIA_TESLA_A100Nvidia A100 GPU.
TpuV2
TPU_V2TPU v2.
TpuV3
TPU_V3TPU v3.
TpuV2Pod
TPU_V2_PODTPU v2 POD.
TpuV3Pod
TPU_V3_PODTPU v3 POD.
TpuV4Pod
TPU_V4_PODTPU v4 POD.
GoogleCloudMlV1__AcceleratorConfigTypeAcceleratorTypeUnspecified
ACCELERATOR_TYPE_UNSPECIFIEDUnspecified accelerator type. Default to no GPU.
GoogleCloudMlV1__AcceleratorConfigTypeNvidiaTeslaK80
NVIDIA_TESLA_K80Nvidia Tesla K80 GPU.
GoogleCloudMlV1__AcceleratorConfigTypeNvidiaTeslaP100
NVIDIA_TESLA_P100Nvidia Tesla P100 GPU.
GoogleCloudMlV1__AcceleratorConfigTypeNvidiaTeslaV100
NVIDIA_TESLA_V100Nvidia V100 GPU.
GoogleCloudMlV1__AcceleratorConfigTypeNvidiaTeslaP4
NVIDIA_TESLA_P4Nvidia Tesla P4 GPU.
GoogleCloudMlV1__AcceleratorConfigTypeNvidiaTeslaT4
NVIDIA_TESLA_T4Nvidia T4 GPU.
GoogleCloudMlV1__AcceleratorConfigTypeNvidiaTeslaA100
NVIDIA_TESLA_A100Nvidia A100 GPU.
GoogleCloudMlV1__AcceleratorConfigTypeTpuV2
TPU_V2TPU v2.
GoogleCloudMlV1__AcceleratorConfigTypeTpuV3
TPU_V3TPU v3.
GoogleCloudMlV1__AcceleratorConfigTypeTpuV2Pod
TPU_V2_PODTPU v2 POD.
GoogleCloudMlV1__AcceleratorConfigTypeTpuV3Pod
TPU_V3_PODTPU v3 POD.
GoogleCloudMlV1__AcceleratorConfigTypeTpuV4Pod
TPU_V4_PODTPU v4 POD.
AcceleratorTypeUnspecified
ACCELERATOR_TYPE_UNSPECIFIEDUnspecified accelerator type. Default to no GPU.
NvidiaTeslaK80
NVIDIA_TESLA_K80Nvidia Tesla K80 GPU.
NvidiaTeslaP100
NVIDIA_TESLA_P100Nvidia Tesla P100 GPU.
NvidiaTeslaV100
NVIDIA_TESLA_V100Nvidia V100 GPU.
NvidiaTeslaP4
NVIDIA_TESLA_P4Nvidia Tesla P4 GPU.
NvidiaTeslaT4
NVIDIA_TESLA_T4Nvidia T4 GPU.
NvidiaTeslaA100
NVIDIA_TESLA_A100Nvidia A100 GPU.
TpuV2
TPU_V2TPU v2.
TpuV3
TPU_V3TPU v3.
TpuV2Pod
TPU_V2_PODTPU v2 POD.
TpuV3Pod
TPU_V3_PODTPU v3 POD.
TpuV4Pod
TPU_V4_PODTPU v4 POD.
AcceleratorTypeUnspecified
ACCELERATOR_TYPE_UNSPECIFIEDUnspecified accelerator type. Default to no GPU.
NvidiaTeslaK80
NVIDIA_TESLA_K80Nvidia Tesla K80 GPU.
NvidiaTeslaP100
NVIDIA_TESLA_P100Nvidia Tesla P100 GPU.
NvidiaTeslaV100
NVIDIA_TESLA_V100Nvidia V100 GPU.
NvidiaTeslaP4
NVIDIA_TESLA_P4Nvidia Tesla P4 GPU.
NvidiaTeslaT4
NVIDIA_TESLA_T4Nvidia T4 GPU.
NvidiaTeslaA100
NVIDIA_TESLA_A100Nvidia A100 GPU.
TpuV2
TPU_V2TPU v2.
TpuV3
TPU_V3TPU v3.
TpuV2Pod
TPU_V2_PODTPU v2 POD.
TpuV3Pod
TPU_V3_PODTPU v3 POD.
TpuV4Pod
TPU_V4_PODTPU v4 POD.
ACCELERATOR_TYPE_UNSPECIFIED
ACCELERATOR_TYPE_UNSPECIFIEDUnspecified accelerator type. Default to no GPU.
NVIDIA_TESLA_K80
NVIDIA_TESLA_K80Nvidia Tesla K80 GPU.
NVIDIA_TESLA_P100
NVIDIA_TESLA_P100Nvidia Tesla P100 GPU.
NVIDIA_TESLA_V100
NVIDIA_TESLA_V100Nvidia V100 GPU.
NVIDIA_TESLA_P4
NVIDIA_TESLA_P4Nvidia Tesla P4 GPU.
NVIDIA_TESLA_T4
NVIDIA_TESLA_T4Nvidia T4 GPU.
NVIDIA_TESLA_A100
NVIDIA_TESLA_A100Nvidia A100 GPU.
TPU_V2
TPU_V2TPU v2.
TPU_V3
TPU_V3TPU v3.
TPU_V2_POD
TPU_V2_PODTPU v2 POD.
TPU_V3_POD
TPU_V3_PODTPU v3 POD.
TPU_V4_POD
TPU_V4_PODTPU v4 POD.
"ACCELERATOR_TYPE_UNSPECIFIED"
ACCELERATOR_TYPE_UNSPECIFIEDUnspecified accelerator type. Default to no GPU.
"NVIDIA_TESLA_K80"
NVIDIA_TESLA_K80Nvidia Tesla K80 GPU.
"NVIDIA_TESLA_P100"
NVIDIA_TESLA_P100Nvidia Tesla P100 GPU.
"NVIDIA_TESLA_V100"
NVIDIA_TESLA_V100Nvidia V100 GPU.
"NVIDIA_TESLA_P4"
NVIDIA_TESLA_P4Nvidia Tesla P4 GPU.
"NVIDIA_TESLA_T4"
NVIDIA_TESLA_T4Nvidia T4 GPU.
"NVIDIA_TESLA_A100"
NVIDIA_TESLA_A100Nvidia A100 GPU.
"TPU_V2"
TPU_V2TPU v2.
"TPU_V3"
TPU_V3TPU v3.
"TPU_V2_POD"
TPU_V2_PODTPU v2 POD.
"TPU_V3_POD"
TPU_V3_PODTPU v3 POD.
"TPU_V4_POD"
TPU_V4_PODTPU v4 POD.

GoogleCloudMlV1__AutoScaling
, GoogleCloudMlV1__AutoScalingArgs

MaxNodes int
The maximum number of nodes to scale this model under load. The actual value will depend on resource quota and availability.
Metrics List<Pulumi.GoogleNative.Ml.V1.Inputs.GoogleCloudMlV1__MetricSpec>
MetricSpec contains the specifications to use to calculate the desired nodes count.
MinNodes int
Optional. The minimum number of nodes to allocate for this model. These nodes are always up, starting from the time the model is deployed. Therefore, the cost of operating this model will be at least rate * min_nodes * number of hours since last billing cycle, where rate is the cost per node-hour as documented in the pricing guide, even if no predictions are performed. There is additional cost for each prediction performed. Unlike manual scaling, if the load gets too heavy for the nodes that are up, the service will automatically add nodes to handle the increased load as well as scale back as traffic drops, always maintaining at least min_nodes. You will be charged for the time in which additional nodes are used. If min_nodes is not specified and AutoScaling is used with a legacy (MLS1) machine type, min_nodes defaults to 0, in which case, when traffic to a model stops (and after a cool-down period), nodes will be shut down and no charges will be incurred until traffic to the model resumes. If min_nodes is not specified and AutoScaling is used with a Compute Engine (N1) machine type, min_nodes defaults to 1. min_nodes must be at least 1 for use with a Compute Engine machine type. You can set min_nodes when creating the model version, and you can also update min_nodes for an existing version: update_body.json: { 'autoScaling': { 'minNodes': 5 } } HTTP request: PATCH https://ml.googleapis.com/v1/{name=projects//models//versions/*}?update_mask=autoScaling.minNodes -d @./update_body.json
MaxNodes int
The maximum number of nodes to scale this model under load. The actual value will depend on resource quota and availability.
Metrics []GoogleCloudMlV1__MetricSpec
MetricSpec contains the specifications to use to calculate the desired nodes count.
MinNodes int
Optional. The minimum number of nodes to allocate for this model. These nodes are always up, starting from the time the model is deployed. Therefore, the cost of operating this model will be at least rate * min_nodes * number of hours since last billing cycle, where rate is the cost per node-hour as documented in the pricing guide, even if no predictions are performed. There is additional cost for each prediction performed. Unlike manual scaling, if the load gets too heavy for the nodes that are up, the service will automatically add nodes to handle the increased load as well as scale back as traffic drops, always maintaining at least min_nodes. You will be charged for the time in which additional nodes are used. If min_nodes is not specified and AutoScaling is used with a legacy (MLS1) machine type, min_nodes defaults to 0, in which case, when traffic to a model stops (and after a cool-down period), nodes will be shut down and no charges will be incurred until traffic to the model resumes. If min_nodes is not specified and AutoScaling is used with a Compute Engine (N1) machine type, min_nodes defaults to 1. min_nodes must be at least 1 for use with a Compute Engine machine type. You can set min_nodes when creating the model version, and you can also update min_nodes for an existing version: update_body.json: { 'autoScaling': { 'minNodes': 5 } } HTTP request: PATCH https://ml.googleapis.com/v1/{name=projects//models//versions/*}?update_mask=autoScaling.minNodes -d @./update_body.json
maxNodes Integer
The maximum number of nodes to scale this model under load. The actual value will depend on resource quota and availability.
metrics List<GoogleCloudMlV1__MetricSpec>
MetricSpec contains the specifications to use to calculate the desired nodes count.
minNodes Integer
Optional. The minimum number of nodes to allocate for this model. These nodes are always up, starting from the time the model is deployed. Therefore, the cost of operating this model will be at least rate * min_nodes * number of hours since last billing cycle, where rate is the cost per node-hour as documented in the pricing guide, even if no predictions are performed. There is additional cost for each prediction performed. Unlike manual scaling, if the load gets too heavy for the nodes that are up, the service will automatically add nodes to handle the increased load as well as scale back as traffic drops, always maintaining at least min_nodes. You will be charged for the time in which additional nodes are used. If min_nodes is not specified and AutoScaling is used with a legacy (MLS1) machine type, min_nodes defaults to 0, in which case, when traffic to a model stops (and after a cool-down period), nodes will be shut down and no charges will be incurred until traffic to the model resumes. If min_nodes is not specified and AutoScaling is used with a Compute Engine (N1) machine type, min_nodes defaults to 1. min_nodes must be at least 1 for use with a Compute Engine machine type. You can set min_nodes when creating the model version, and you can also update min_nodes for an existing version: update_body.json: { 'autoScaling': { 'minNodes': 5 } } HTTP request: PATCH https://ml.googleapis.com/v1/{name=projects//models//versions/*}?update_mask=autoScaling.minNodes -d @./update_body.json
maxNodes number
The maximum number of nodes to scale this model under load. The actual value will depend on resource quota and availability.
metrics GoogleCloudMlV1__MetricSpec[]
MetricSpec contains the specifications to use to calculate the desired nodes count.
minNodes number
Optional. The minimum number of nodes to allocate for this model. These nodes are always up, starting from the time the model is deployed. Therefore, the cost of operating this model will be at least rate * min_nodes * number of hours since last billing cycle, where rate is the cost per node-hour as documented in the pricing guide, even if no predictions are performed. There is additional cost for each prediction performed. Unlike manual scaling, if the load gets too heavy for the nodes that are up, the service will automatically add nodes to handle the increased load as well as scale back as traffic drops, always maintaining at least min_nodes. You will be charged for the time in which additional nodes are used. If min_nodes is not specified and AutoScaling is used with a legacy (MLS1) machine type, min_nodes defaults to 0, in which case, when traffic to a model stops (and after a cool-down period), nodes will be shut down and no charges will be incurred until traffic to the model resumes. If min_nodes is not specified and AutoScaling is used with a Compute Engine (N1) machine type, min_nodes defaults to 1. min_nodes must be at least 1 for use with a Compute Engine machine type. You can set min_nodes when creating the model version, and you can also update min_nodes for an existing version: update_body.json: { 'autoScaling': { 'minNodes': 5 } } HTTP request: PATCH https://ml.googleapis.com/v1/{name=projects//models//versions/*}?update_mask=autoScaling.minNodes -d @./update_body.json
max_nodes int
The maximum number of nodes to scale this model under load. The actual value will depend on resource quota and availability.
metrics Sequence[GoogleCloudMlV1MetricSpec]
MetricSpec contains the specifications to use to calculate the desired nodes count.
min_nodes int
Optional. The minimum number of nodes to allocate for this model. These nodes are always up, starting from the time the model is deployed. Therefore, the cost of operating this model will be at least rate * min_nodes * number of hours since last billing cycle, where rate is the cost per node-hour as documented in the pricing guide, even if no predictions are performed. There is additional cost for each prediction performed. Unlike manual scaling, if the load gets too heavy for the nodes that are up, the service will automatically add nodes to handle the increased load as well as scale back as traffic drops, always maintaining at least min_nodes. You will be charged for the time in which additional nodes are used. If min_nodes is not specified and AutoScaling is used with a legacy (MLS1) machine type, min_nodes defaults to 0, in which case, when traffic to a model stops (and after a cool-down period), nodes will be shut down and no charges will be incurred until traffic to the model resumes. If min_nodes is not specified and AutoScaling is used with a Compute Engine (N1) machine type, min_nodes defaults to 1. min_nodes must be at least 1 for use with a Compute Engine machine type. You can set min_nodes when creating the model version, and you can also update min_nodes for an existing version: update_body.json: { 'autoScaling': { 'minNodes': 5 } } HTTP request: PATCH https://ml.googleapis.com/v1/{name=projects//models//versions/*}?update_mask=autoScaling.minNodes -d @./update_body.json
maxNodes Number
The maximum number of nodes to scale this model under load. The actual value will depend on resource quota and availability.
metrics List<Property Map>
MetricSpec contains the specifications to use to calculate the desired nodes count.
minNodes Number
Optional. The minimum number of nodes to allocate for this model. These nodes are always up, starting from the time the model is deployed. Therefore, the cost of operating this model will be at least rate * min_nodes * number of hours since last billing cycle, where rate is the cost per node-hour as documented in the pricing guide, even if no predictions are performed. There is additional cost for each prediction performed. Unlike manual scaling, if the load gets too heavy for the nodes that are up, the service will automatically add nodes to handle the increased load as well as scale back as traffic drops, always maintaining at least min_nodes. You will be charged for the time in which additional nodes are used. If min_nodes is not specified and AutoScaling is used with a legacy (MLS1) machine type, min_nodes defaults to 0, in which case, when traffic to a model stops (and after a cool-down period), nodes will be shut down and no charges will be incurred until traffic to the model resumes. If min_nodes is not specified and AutoScaling is used with a Compute Engine (N1) machine type, min_nodes defaults to 1. min_nodes must be at least 1 for use with a Compute Engine machine type. You can set min_nodes when creating the model version, and you can also update min_nodes for an existing version: update_body.json: { 'autoScaling': { 'minNodes': 5 } } HTTP request: PATCH https://ml.googleapis.com/v1/{name=projects//models//versions/*}?update_mask=autoScaling.minNodes -d @./update_body.json

GoogleCloudMlV1__AutoScalingResponse
, GoogleCloudMlV1__AutoScalingResponseArgs

MaxNodes This property is required. int
The maximum number of nodes to scale this model under load. The actual value will depend on resource quota and availability.
Metrics This property is required. List<Pulumi.GoogleNative.Ml.V1.Inputs.GoogleCloudMlV1__MetricSpecResponse>
MetricSpec contains the specifications to use to calculate the desired nodes count.
MinNodes This property is required. int
Optional. The minimum number of nodes to allocate for this model. These nodes are always up, starting from the time the model is deployed. Therefore, the cost of operating this model will be at least rate * min_nodes * number of hours since last billing cycle, where rate is the cost per node-hour as documented in the pricing guide, even if no predictions are performed. There is additional cost for each prediction performed. Unlike manual scaling, if the load gets too heavy for the nodes that are up, the service will automatically add nodes to handle the increased load as well as scale back as traffic drops, always maintaining at least min_nodes. You will be charged for the time in which additional nodes are used. If min_nodes is not specified and AutoScaling is used with a legacy (MLS1) machine type, min_nodes defaults to 0, in which case, when traffic to a model stops (and after a cool-down period), nodes will be shut down and no charges will be incurred until traffic to the model resumes. If min_nodes is not specified and AutoScaling is used with a Compute Engine (N1) machine type, min_nodes defaults to 1. min_nodes must be at least 1 for use with a Compute Engine machine type. You can set min_nodes when creating the model version, and you can also update min_nodes for an existing version: update_body.json: { 'autoScaling': { 'minNodes': 5 } } HTTP request: PATCH https://ml.googleapis.com/v1/{name=projects//models//versions/*}?update_mask=autoScaling.minNodes -d @./update_body.json
MaxNodes This property is required. int
The maximum number of nodes to scale this model under load. The actual value will depend on resource quota and availability.
Metrics This property is required. []GoogleCloudMlV1__MetricSpecResponse
MetricSpec contains the specifications to use to calculate the desired nodes count.
MinNodes This property is required. int
Optional. The minimum number of nodes to allocate for this model. These nodes are always up, starting from the time the model is deployed. Therefore, the cost of operating this model will be at least rate * min_nodes * number of hours since last billing cycle, where rate is the cost per node-hour as documented in the pricing guide, even if no predictions are performed. There is additional cost for each prediction performed. Unlike manual scaling, if the load gets too heavy for the nodes that are up, the service will automatically add nodes to handle the increased load as well as scale back as traffic drops, always maintaining at least min_nodes. You will be charged for the time in which additional nodes are used. If min_nodes is not specified and AutoScaling is used with a legacy (MLS1) machine type, min_nodes defaults to 0, in which case, when traffic to a model stops (and after a cool-down period), nodes will be shut down and no charges will be incurred until traffic to the model resumes. If min_nodes is not specified and AutoScaling is used with a Compute Engine (N1) machine type, min_nodes defaults to 1. min_nodes must be at least 1 for use with a Compute Engine machine type. You can set min_nodes when creating the model version, and you can also update min_nodes for an existing version: update_body.json: { 'autoScaling': { 'minNodes': 5 } } HTTP request: PATCH https://ml.googleapis.com/v1/{name=projects//models//versions/*}?update_mask=autoScaling.minNodes -d @./update_body.json
maxNodes This property is required. Integer
The maximum number of nodes to scale this model under load. The actual value will depend on resource quota and availability.
metrics This property is required. List<GoogleCloudMlV1__MetricSpecResponse>
MetricSpec contains the specifications to use to calculate the desired nodes count.
minNodes This property is required. Integer
Optional. The minimum number of nodes to allocate for this model. These nodes are always up, starting from the time the model is deployed. Therefore, the cost of operating this model will be at least rate * min_nodes * number of hours since last billing cycle, where rate is the cost per node-hour as documented in the pricing guide, even if no predictions are performed. There is additional cost for each prediction performed. Unlike manual scaling, if the load gets too heavy for the nodes that are up, the service will automatically add nodes to handle the increased load as well as scale back as traffic drops, always maintaining at least min_nodes. You will be charged for the time in which additional nodes are used. If min_nodes is not specified and AutoScaling is used with a legacy (MLS1) machine type, min_nodes defaults to 0, in which case, when traffic to a model stops (and after a cool-down period), nodes will be shut down and no charges will be incurred until traffic to the model resumes. If min_nodes is not specified and AutoScaling is used with a Compute Engine (N1) machine type, min_nodes defaults to 1. min_nodes must be at least 1 for use with a Compute Engine machine type. You can set min_nodes when creating the model version, and you can also update min_nodes for an existing version: update_body.json: { 'autoScaling': { 'minNodes': 5 } } HTTP request: PATCH https://ml.googleapis.com/v1/{name=projects//models//versions/*}?update_mask=autoScaling.minNodes -d @./update_body.json
maxNodes This property is required. number
The maximum number of nodes to scale this model under load. The actual value will depend on resource quota and availability.
metrics This property is required. GoogleCloudMlV1__MetricSpecResponse[]
MetricSpec contains the specifications to use to calculate the desired nodes count.
minNodes This property is required. number
Optional. The minimum number of nodes to allocate for this model. These nodes are always up, starting from the time the model is deployed. Therefore, the cost of operating this model will be at least rate * min_nodes * number of hours since last billing cycle, where rate is the cost per node-hour as documented in the pricing guide, even if no predictions are performed. There is additional cost for each prediction performed. Unlike manual scaling, if the load gets too heavy for the nodes that are up, the service will automatically add nodes to handle the increased load as well as scale back as traffic drops, always maintaining at least min_nodes. You will be charged for the time in which additional nodes are used. If min_nodes is not specified and AutoScaling is used with a legacy (MLS1) machine type, min_nodes defaults to 0, in which case, when traffic to a model stops (and after a cool-down period), nodes will be shut down and no charges will be incurred until traffic to the model resumes. If min_nodes is not specified and AutoScaling is used with a Compute Engine (N1) machine type, min_nodes defaults to 1. min_nodes must be at least 1 for use with a Compute Engine machine type. You can set min_nodes when creating the model version, and you can also update min_nodes for an existing version: update_body.json: { 'autoScaling': { 'minNodes': 5 } } HTTP request: PATCH https://ml.googleapis.com/v1/{name=projects//models//versions/*}?update_mask=autoScaling.minNodes -d @./update_body.json
max_nodes This property is required. int
The maximum number of nodes to scale this model under load. The actual value will depend on resource quota and availability.
metrics This property is required. Sequence[GoogleCloudMlV1MetricSpecResponse]
MetricSpec contains the specifications to use to calculate the desired nodes count.
min_nodes This property is required. int
Optional. The minimum number of nodes to allocate for this model. These nodes are always up, starting from the time the model is deployed. Therefore, the cost of operating this model will be at least rate * min_nodes * number of hours since last billing cycle, where rate is the cost per node-hour as documented in the pricing guide, even if no predictions are performed. There is additional cost for each prediction performed. Unlike manual scaling, if the load gets too heavy for the nodes that are up, the service will automatically add nodes to handle the increased load as well as scale back as traffic drops, always maintaining at least min_nodes. You will be charged for the time in which additional nodes are used. If min_nodes is not specified and AutoScaling is used with a legacy (MLS1) machine type, min_nodes defaults to 0, in which case, when traffic to a model stops (and after a cool-down period), nodes will be shut down and no charges will be incurred until traffic to the model resumes. If min_nodes is not specified and AutoScaling is used with a Compute Engine (N1) machine type, min_nodes defaults to 1. min_nodes must be at least 1 for use with a Compute Engine machine type. You can set min_nodes when creating the model version, and you can also update min_nodes for an existing version: update_body.json: { 'autoScaling': { 'minNodes': 5 } } HTTP request: PATCH https://ml.googleapis.com/v1/{name=projects//models//versions/*}?update_mask=autoScaling.minNodes -d @./update_body.json
maxNodes This property is required. Number
The maximum number of nodes to scale this model under load. The actual value will depend on resource quota and availability.
metrics This property is required. List<Property Map>
MetricSpec contains the specifications to use to calculate the desired nodes count.
minNodes This property is required. Number
Optional. The minimum number of nodes to allocate for this model. These nodes are always up, starting from the time the model is deployed. Therefore, the cost of operating this model will be at least rate * min_nodes * number of hours since last billing cycle, where rate is the cost per node-hour as documented in the pricing guide, even if no predictions are performed. There is additional cost for each prediction performed. Unlike manual scaling, if the load gets too heavy for the nodes that are up, the service will automatically add nodes to handle the increased load as well as scale back as traffic drops, always maintaining at least min_nodes. You will be charged for the time in which additional nodes are used. If min_nodes is not specified and AutoScaling is used with a legacy (MLS1) machine type, min_nodes defaults to 0, in which case, when traffic to a model stops (and after a cool-down period), nodes will be shut down and no charges will be incurred until traffic to the model resumes. If min_nodes is not specified and AutoScaling is used with a Compute Engine (N1) machine type, min_nodes defaults to 1. min_nodes must be at least 1 for use with a Compute Engine machine type. You can set min_nodes when creating the model version, and you can also update min_nodes for an existing version: update_body.json: { 'autoScaling': { 'minNodes': 5 } } HTTP request: PATCH https://ml.googleapis.com/v1/{name=projects//models//versions/*}?update_mask=autoScaling.minNodes -d @./update_body.json

GoogleCloudMlV1__ContainerPort
, GoogleCloudMlV1__ContainerPortArgs

ContainerPort int
Number of the port to expose on the container. This must be a valid port number: 0 < PORT_NUMBER < 65536.
ContainerPort int
Number of the port to expose on the container. This must be a valid port number: 0 < PORT_NUMBER < 65536.
containerPort Integer
Number of the port to expose on the container. This must be a valid port number: 0 < PORT_NUMBER < 65536.
containerPort number
Number of the port to expose on the container. This must be a valid port number: 0 < PORT_NUMBER < 65536.
container_port int
Number of the port to expose on the container. This must be a valid port number: 0 < PORT_NUMBER < 65536.
containerPort Number
Number of the port to expose on the container. This must be a valid port number: 0 < PORT_NUMBER < 65536.

GoogleCloudMlV1__ContainerPortResponse
, GoogleCloudMlV1__ContainerPortResponseArgs

ContainerPort This property is required. int
Number of the port to expose on the container. This must be a valid port number: 0 < PORT_NUMBER < 65536.
ContainerPort This property is required. int
Number of the port to expose on the container. This must be a valid port number: 0 < PORT_NUMBER < 65536.
containerPort This property is required. Integer
Number of the port to expose on the container. This must be a valid port number: 0 < PORT_NUMBER < 65536.
containerPort This property is required. number
Number of the port to expose on the container. This must be a valid port number: 0 < PORT_NUMBER < 65536.
container_port This property is required. int
Number of the port to expose on the container. This must be a valid port number: 0 < PORT_NUMBER < 65536.
containerPort This property is required. Number
Number of the port to expose on the container. This must be a valid port number: 0 < PORT_NUMBER < 65536.

GoogleCloudMlV1__ContainerSpec
, GoogleCloudMlV1__ContainerSpecArgs

Args List<string>
Immutable. Specifies arguments for the command that runs when the container starts. This overrides the container's CMD. Specify this field as an array of executable and arguments, similar to a Docker CMD's "default parameters" form. If you don't specify this field but do specify the command field, then the command from the command field runs without any additional arguments. See the Kubernetes documentation about how the command and args fields interact with a container's ENTRYPOINT and CMD. If you don't specify this field and don't specify the commmand field, then the container's ENTRYPOINT and CMD determine what runs based on their default behavior. See the Docker documentation about how CMD and ENTRYPOINT interact. In this field, you can reference environment variables set by AI Platform Prediction and environment variables set in the env field. You cannot reference environment variables set in the Docker image. In order for environment variables to be expanded, reference them by using the following syntax: $( VARIABLE_NAME) Note that this differs from Bash variable expansion, which does not use parentheses. If a variable cannot be resolved, the reference in the input string is used unchanged. To avoid variable expansion, you can escape this syntax with $$; for example: $$(VARIABLE_NAME) This field corresponds to the args field of the Kubernetes Containers v1 core API.
Command List<string>
Immutable. Specifies the command that runs when the container starts. This overrides the container's ENTRYPOINT. Specify this field as an array of executable and arguments, similar to a Docker ENTRYPOINT's "exec" form, not its "shell" form. If you do not specify this field, then the container's ENTRYPOINT runs, in conjunction with the args field or the container's CMD, if either exists. If this field is not specified and the container does not have an ENTRYPOINT, then refer to the Docker documentation about how CMD and ENTRYPOINT interact. If you specify this field, then you can also specify the args field to provide additional arguments for this command. However, if you specify this field, then the container's CMD is ignored. See the Kubernetes documentation about how the command and args fields interact with a container's ENTRYPOINT and CMD. In this field, you can reference environment variables set by AI Platform Prediction and environment variables set in the env field. You cannot reference environment variables set in the Docker image. In order for environment variables to be expanded, reference them by using the following syntax: $( VARIABLE_NAME) Note that this differs from Bash variable expansion, which does not use parentheses. If a variable cannot be resolved, the reference in the input string is used unchanged. To avoid variable expansion, you can escape this syntax with $$; for example: $$(VARIABLE_NAME) This field corresponds to the command field of the Kubernetes Containers v1 core API.
Env List<Pulumi.GoogleNative.Ml.V1.Inputs.GoogleCloudMlV1__EnvVar>
Immutable. List of environment variables to set in the container. After the container starts running, code running in the container can read these environment variables. Additionally, the command and args fields can reference these variables. Later entries in this list can also reference earlier entries. For example, the following example sets the variable VAR_2 to have the value foo bar: json [ { "name": "VAR_1", "value": "foo" }, { "name": "VAR_2", "value": "$(VAR_1) bar" } ] If you switch the order of the variables in the example, then the expansion does not occur. This field corresponds to the env field of the Kubernetes Containers v1 core API.
Image string
URI of the Docker image to be used as the custom container for serving predictions. This URI must identify an image in Artifact Registry and begin with the hostname {REGION}-docker.pkg.dev, where {REGION} is replaced by the region that matches AI Platform Prediction regional endpoint that you are using. For example, if you are using the us-central1-ml.googleapis.com endpoint, then this URI must begin with us-central1-docker.pkg.dev. To use a custom container, the AI Platform Google-managed service account must have permission to pull (read) the Docker image at this URI. The AI Platform Google-managed service account has the following format: service-{PROJECT_NUMBER}@cloud-ml.google.com.iam.gserviceaccount.com {PROJECT_NUMBER} is replaced by your Google Cloud project number. By default, this service account has necessary permissions to pull an Artifact Registry image in the same Google Cloud project where you are using AI Platform Prediction. In this case, no configuration is necessary. If you want to use an image from a different Google Cloud project, learn how to grant the Artifact Registry Reader (roles/artifactregistry.reader) role for a repository to your projet's AI Platform Google-managed service account. To learn about the requirements for the Docker image itself, read Custom container requirements.
Ports List<Pulumi.GoogleNative.Ml.V1.Inputs.GoogleCloudMlV1__ContainerPort>
Immutable. List of ports to expose from the container. AI Platform Prediction sends any prediction requests that it receives to the first port on this list. AI Platform Prediction also sends liveness and health checks to this port. If you do not specify this field, it defaults to following value: json [ { "containerPort": 8080 } ] AI Platform Prediction does not use ports other than the first one listed. This field corresponds to the ports field of the Kubernetes Containers v1 core API.
Args []string
Immutable. Specifies arguments for the command that runs when the container starts. This overrides the container's CMD. Specify this field as an array of executable and arguments, similar to a Docker CMD's "default parameters" form. If you don't specify this field but do specify the command field, then the command from the command field runs without any additional arguments. See the Kubernetes documentation about how the command and args fields interact with a container's ENTRYPOINT and CMD. If you don't specify this field and don't specify the commmand field, then the container's ENTRYPOINT and CMD determine what runs based on their default behavior. See the Docker documentation about how CMD and ENTRYPOINT interact. In this field, you can reference environment variables set by AI Platform Prediction and environment variables set in the env field. You cannot reference environment variables set in the Docker image. In order for environment variables to be expanded, reference them by using the following syntax: $( VARIABLE_NAME) Note that this differs from Bash variable expansion, which does not use parentheses. If a variable cannot be resolved, the reference in the input string is used unchanged. To avoid variable expansion, you can escape this syntax with $$; for example: $$(VARIABLE_NAME) This field corresponds to the args field of the Kubernetes Containers v1 core API.
Command []string
Immutable. Specifies the command that runs when the container starts. This overrides the container's ENTRYPOINT. Specify this field as an array of executable and arguments, similar to a Docker ENTRYPOINT's "exec" form, not its "shell" form. If you do not specify this field, then the container's ENTRYPOINT runs, in conjunction with the args field or the container's CMD, if either exists. If this field is not specified and the container does not have an ENTRYPOINT, then refer to the Docker documentation about how CMD and ENTRYPOINT interact. If you specify this field, then you can also specify the args field to provide additional arguments for this command. However, if you specify this field, then the container's CMD is ignored. See the Kubernetes documentation about how the command and args fields interact with a container's ENTRYPOINT and CMD. In this field, you can reference environment variables set by AI Platform Prediction and environment variables set in the env field. You cannot reference environment variables set in the Docker image. In order for environment variables to be expanded, reference them by using the following syntax: $( VARIABLE_NAME) Note that this differs from Bash variable expansion, which does not use parentheses. If a variable cannot be resolved, the reference in the input string is used unchanged. To avoid variable expansion, you can escape this syntax with $$; for example: $$(VARIABLE_NAME) This field corresponds to the command field of the Kubernetes Containers v1 core API.
Env []GoogleCloudMlV1__EnvVar
Immutable. List of environment variables to set in the container. After the container starts running, code running in the container can read these environment variables. Additionally, the command and args fields can reference these variables. Later entries in this list can also reference earlier entries. For example, the following example sets the variable VAR_2 to have the value foo bar: json [ { "name": "VAR_1", "value": "foo" }, { "name": "VAR_2", "value": "$(VAR_1) bar" } ] If you switch the order of the variables in the example, then the expansion does not occur. This field corresponds to the env field of the Kubernetes Containers v1 core API.
Image string
URI of the Docker image to be used as the custom container for serving predictions. This URI must identify an image in Artifact Registry and begin with the hostname {REGION}-docker.pkg.dev, where {REGION} is replaced by the region that matches AI Platform Prediction regional endpoint that you are using. For example, if you are using the us-central1-ml.googleapis.com endpoint, then this URI must begin with us-central1-docker.pkg.dev. To use a custom container, the AI Platform Google-managed service account must have permission to pull (read) the Docker image at this URI. The AI Platform Google-managed service account has the following format: service-{PROJECT_NUMBER}@cloud-ml.google.com.iam.gserviceaccount.com {PROJECT_NUMBER} is replaced by your Google Cloud project number. By default, this service account has necessary permissions to pull an Artifact Registry image in the same Google Cloud project where you are using AI Platform Prediction. In this case, no configuration is necessary. If you want to use an image from a different Google Cloud project, learn how to grant the Artifact Registry Reader (roles/artifactregistry.reader) role for a repository to your projet's AI Platform Google-managed service account. To learn about the requirements for the Docker image itself, read Custom container requirements.
Ports []GoogleCloudMlV1__ContainerPort
Immutable. List of ports to expose from the container. AI Platform Prediction sends any prediction requests that it receives to the first port on this list. AI Platform Prediction also sends liveness and health checks to this port. If you do not specify this field, it defaults to following value: json [ { "containerPort": 8080 } ] AI Platform Prediction does not use ports other than the first one listed. This field corresponds to the ports field of the Kubernetes Containers v1 core API.
args List<String>
Immutable. Specifies arguments for the command that runs when the container starts. This overrides the container's CMD. Specify this field as an array of executable and arguments, similar to a Docker CMD's "default parameters" form. If you don't specify this field but do specify the command field, then the command from the command field runs without any additional arguments. See the Kubernetes documentation about how the command and args fields interact with a container's ENTRYPOINT and CMD. If you don't specify this field and don't specify the commmand field, then the container's ENTRYPOINT and CMD determine what runs based on their default behavior. See the Docker documentation about how CMD and ENTRYPOINT interact. In this field, you can reference environment variables set by AI Platform Prediction and environment variables set in the env field. You cannot reference environment variables set in the Docker image. In order for environment variables to be expanded, reference them by using the following syntax: $( VARIABLE_NAME) Note that this differs from Bash variable expansion, which does not use parentheses. If a variable cannot be resolved, the reference in the input string is used unchanged. To avoid variable expansion, you can escape this syntax with $$; for example: $$(VARIABLE_NAME) This field corresponds to the args field of the Kubernetes Containers v1 core API.
command List<String>
Immutable. Specifies the command that runs when the container starts. This overrides the container's ENTRYPOINT. Specify this field as an array of executable and arguments, similar to a Docker ENTRYPOINT's "exec" form, not its "shell" form. If you do not specify this field, then the container's ENTRYPOINT runs, in conjunction with the args field or the container's CMD, if either exists. If this field is not specified and the container does not have an ENTRYPOINT, then refer to the Docker documentation about how CMD and ENTRYPOINT interact. If you specify this field, then you can also specify the args field to provide additional arguments for this command. However, if you specify this field, then the container's CMD is ignored. See the Kubernetes documentation about how the command and args fields interact with a container's ENTRYPOINT and CMD. In this field, you can reference environment variables set by AI Platform Prediction and environment variables set in the env field. You cannot reference environment variables set in the Docker image. In order for environment variables to be expanded, reference them by using the following syntax: $( VARIABLE_NAME) Note that this differs from Bash variable expansion, which does not use parentheses. If a variable cannot be resolved, the reference in the input string is used unchanged. To avoid variable expansion, you can escape this syntax with $$; for example: $$(VARIABLE_NAME) This field corresponds to the command field of the Kubernetes Containers v1 core API.
env List<GoogleCloudMlV1__EnvVar>
Immutable. List of environment variables to set in the container. After the container starts running, code running in the container can read these environment variables. Additionally, the command and args fields can reference these variables. Later entries in this list can also reference earlier entries. For example, the following example sets the variable VAR_2 to have the value foo bar: json [ { "name": "VAR_1", "value": "foo" }, { "name": "VAR_2", "value": "$(VAR_1) bar" } ] If you switch the order of the variables in the example, then the expansion does not occur. This field corresponds to the env field of the Kubernetes Containers v1 core API.
image String
URI of the Docker image to be used as the custom container for serving predictions. This URI must identify an image in Artifact Registry and begin with the hostname {REGION}-docker.pkg.dev, where {REGION} is replaced by the region that matches AI Platform Prediction regional endpoint that you are using. For example, if you are using the us-central1-ml.googleapis.com endpoint, then this URI must begin with us-central1-docker.pkg.dev. To use a custom container, the AI Platform Google-managed service account must have permission to pull (read) the Docker image at this URI. The AI Platform Google-managed service account has the following format: service-{PROJECT_NUMBER}@cloud-ml.google.com.iam.gserviceaccount.com {PROJECT_NUMBER} is replaced by your Google Cloud project number. By default, this service account has necessary permissions to pull an Artifact Registry image in the same Google Cloud project where you are using AI Platform Prediction. In this case, no configuration is necessary. If you want to use an image from a different Google Cloud project, learn how to grant the Artifact Registry Reader (roles/artifactregistry.reader) role for a repository to your projet's AI Platform Google-managed service account. To learn about the requirements for the Docker image itself, read Custom container requirements.
ports List<GoogleCloudMlV1__ContainerPort>
Immutable. List of ports to expose from the container. AI Platform Prediction sends any prediction requests that it receives to the first port on this list. AI Platform Prediction also sends liveness and health checks to this port. If you do not specify this field, it defaults to following value: json [ { "containerPort": 8080 } ] AI Platform Prediction does not use ports other than the first one listed. This field corresponds to the ports field of the Kubernetes Containers v1 core API.
args string[]
Immutable. Specifies arguments for the command that runs when the container starts. This overrides the container's CMD. Specify this field as an array of executable and arguments, similar to a Docker CMD's "default parameters" form. If you don't specify this field but do specify the command field, then the command from the command field runs without any additional arguments. See the Kubernetes documentation about how the command and args fields interact with a container's ENTRYPOINT and CMD. If you don't specify this field and don't specify the commmand field, then the container's ENTRYPOINT and CMD determine what runs based on their default behavior. See the Docker documentation about how CMD and ENTRYPOINT interact. In this field, you can reference environment variables set by AI Platform Prediction and environment variables set in the env field. You cannot reference environment variables set in the Docker image. In order for environment variables to be expanded, reference them by using the following syntax: $( VARIABLE_NAME) Note that this differs from Bash variable expansion, which does not use parentheses. If a variable cannot be resolved, the reference in the input string is used unchanged. To avoid variable expansion, you can escape this syntax with $$; for example: $$(VARIABLE_NAME) This field corresponds to the args field of the Kubernetes Containers v1 core API.
command string[]
Immutable. Specifies the command that runs when the container starts. This overrides the container's ENTRYPOINT. Specify this field as an array of executable and arguments, similar to a Docker ENTRYPOINT's "exec" form, not its "shell" form. If you do not specify this field, then the container's ENTRYPOINT runs, in conjunction with the args field or the container's CMD, if either exists. If this field is not specified and the container does not have an ENTRYPOINT, then refer to the Docker documentation about how CMD and ENTRYPOINT interact. If you specify this field, then you can also specify the args field to provide additional arguments for this command. However, if you specify this field, then the container's CMD is ignored. See the Kubernetes documentation about how the command and args fields interact with a container's ENTRYPOINT and CMD. In this field, you can reference environment variables set by AI Platform Prediction and environment variables set in the env field. You cannot reference environment variables set in the Docker image. In order for environment variables to be expanded, reference them by using the following syntax: $( VARIABLE_NAME) Note that this differs from Bash variable expansion, which does not use parentheses. If a variable cannot be resolved, the reference in the input string is used unchanged. To avoid variable expansion, you can escape this syntax with $$; for example: $$(VARIABLE_NAME) This field corresponds to the command field of the Kubernetes Containers v1 core API.
env GoogleCloudMlV1__EnvVar[]
Immutable. List of environment variables to set in the container. After the container starts running, code running in the container can read these environment variables. Additionally, the command and args fields can reference these variables. Later entries in this list can also reference earlier entries. For example, the following example sets the variable VAR_2 to have the value foo bar: json [ { "name": "VAR_1", "value": "foo" }, { "name": "VAR_2", "value": "$(VAR_1) bar" } ] If you switch the order of the variables in the example, then the expansion does not occur. This field corresponds to the env field of the Kubernetes Containers v1 core API.
image string
URI of the Docker image to be used as the custom container for serving predictions. This URI must identify an image in Artifact Registry and begin with the hostname {REGION}-docker.pkg.dev, where {REGION} is replaced by the region that matches AI Platform Prediction regional endpoint that you are using. For example, if you are using the us-central1-ml.googleapis.com endpoint, then this URI must begin with us-central1-docker.pkg.dev. To use a custom container, the AI Platform Google-managed service account must have permission to pull (read) the Docker image at this URI. The AI Platform Google-managed service account has the following format: service-{PROJECT_NUMBER}@cloud-ml.google.com.iam.gserviceaccount.com {PROJECT_NUMBER} is replaced by your Google Cloud project number. By default, this service account has necessary permissions to pull an Artifact Registry image in the same Google Cloud project where you are using AI Platform Prediction. In this case, no configuration is necessary. If you want to use an image from a different Google Cloud project, learn how to grant the Artifact Registry Reader (roles/artifactregistry.reader) role for a repository to your projet's AI Platform Google-managed service account. To learn about the requirements for the Docker image itself, read Custom container requirements.
ports GoogleCloudMlV1__ContainerPort[]
Immutable. List of ports to expose from the container. AI Platform Prediction sends any prediction requests that it receives to the first port on this list. AI Platform Prediction also sends liveness and health checks to this port. If you do not specify this field, it defaults to following value: json [ { "containerPort": 8080 } ] AI Platform Prediction does not use ports other than the first one listed. This field corresponds to the ports field of the Kubernetes Containers v1 core API.
args Sequence[str]
Immutable. Specifies arguments for the command that runs when the container starts. This overrides the container's CMD. Specify this field as an array of executable and arguments, similar to a Docker CMD's "default parameters" form. If you don't specify this field but do specify the command field, then the command from the command field runs without any additional arguments. See the Kubernetes documentation about how the command and args fields interact with a container's ENTRYPOINT and CMD. If you don't specify this field and don't specify the commmand field, then the container's ENTRYPOINT and CMD determine what runs based on their default behavior. See the Docker documentation about how CMD and ENTRYPOINT interact. In this field, you can reference environment variables set by AI Platform Prediction and environment variables set in the env field. You cannot reference environment variables set in the Docker image. In order for environment variables to be expanded, reference them by using the following syntax: $( VARIABLE_NAME) Note that this differs from Bash variable expansion, which does not use parentheses. If a variable cannot be resolved, the reference in the input string is used unchanged. To avoid variable expansion, you can escape this syntax with $$; for example: $$(VARIABLE_NAME) This field corresponds to the args field of the Kubernetes Containers v1 core API.
command Sequence[str]
Immutable. Specifies the command that runs when the container starts. This overrides the container's ENTRYPOINT. Specify this field as an array of executable and arguments, similar to a Docker ENTRYPOINT's "exec" form, not its "shell" form. If you do not specify this field, then the container's ENTRYPOINT runs, in conjunction with the args field or the container's CMD, if either exists. If this field is not specified and the container does not have an ENTRYPOINT, then refer to the Docker documentation about how CMD and ENTRYPOINT interact. If you specify this field, then you can also specify the args field to provide additional arguments for this command. However, if you specify this field, then the container's CMD is ignored. See the Kubernetes documentation about how the command and args fields interact with a container's ENTRYPOINT and CMD. In this field, you can reference environment variables set by AI Platform Prediction and environment variables set in the env field. You cannot reference environment variables set in the Docker image. In order for environment variables to be expanded, reference them by using the following syntax: $( VARIABLE_NAME) Note that this differs from Bash variable expansion, which does not use parentheses. If a variable cannot be resolved, the reference in the input string is used unchanged. To avoid variable expansion, you can escape this syntax with $$; for example: $$(VARIABLE_NAME) This field corresponds to the command field of the Kubernetes Containers v1 core API.
env Sequence[GoogleCloudMlV1EnvVar]
Immutable. List of environment variables to set in the container. After the container starts running, code running in the container can read these environment variables. Additionally, the command and args fields can reference these variables. Later entries in this list can also reference earlier entries. For example, the following example sets the variable VAR_2 to have the value foo bar: json [ { "name": "VAR_1", "value": "foo" }, { "name": "VAR_2", "value": "$(VAR_1) bar" } ] If you switch the order of the variables in the example, then the expansion does not occur. This field corresponds to the env field of the Kubernetes Containers v1 core API.
image str
URI of the Docker image to be used as the custom container for serving predictions. This URI must identify an image in Artifact Registry and begin with the hostname {REGION}-docker.pkg.dev, where {REGION} is replaced by the region that matches AI Platform Prediction regional endpoint that you are using. For example, if you are using the us-central1-ml.googleapis.com endpoint, then this URI must begin with us-central1-docker.pkg.dev. To use a custom container, the AI Platform Google-managed service account must have permission to pull (read) the Docker image at this URI. The AI Platform Google-managed service account has the following format: service-{PROJECT_NUMBER}@cloud-ml.google.com.iam.gserviceaccount.com {PROJECT_NUMBER} is replaced by your Google Cloud project number. By default, this service account has necessary permissions to pull an Artifact Registry image in the same Google Cloud project where you are using AI Platform Prediction. In this case, no configuration is necessary. If you want to use an image from a different Google Cloud project, learn how to grant the Artifact Registry Reader (roles/artifactregistry.reader) role for a repository to your projet's AI Platform Google-managed service account. To learn about the requirements for the Docker image itself, read Custom container requirements.
ports Sequence[GoogleCloudMlV1ContainerPort]
Immutable. List of ports to expose from the container. AI Platform Prediction sends any prediction requests that it receives to the first port on this list. AI Platform Prediction also sends liveness and health checks to this port. If you do not specify this field, it defaults to following value: json [ { "containerPort": 8080 } ] AI Platform Prediction does not use ports other than the first one listed. This field corresponds to the ports field of the Kubernetes Containers v1 core API.
args List<String>
Immutable. Specifies arguments for the command that runs when the container starts. This overrides the container's CMD. Specify this field as an array of executable and arguments, similar to a Docker CMD's "default parameters" form. If you don't specify this field but do specify the command field, then the command from the command field runs without any additional arguments. See the Kubernetes documentation about how the command and args fields interact with a container's ENTRYPOINT and CMD. If you don't specify this field and don't specify the commmand field, then the container's ENTRYPOINT and CMD determine what runs based on their default behavior. See the Docker documentation about how CMD and ENTRYPOINT interact. In this field, you can reference environment variables set by AI Platform Prediction and environment variables set in the env field. You cannot reference environment variables set in the Docker image. In order for environment variables to be expanded, reference them by using the following syntax: $( VARIABLE_NAME) Note that this differs from Bash variable expansion, which does not use parentheses. If a variable cannot be resolved, the reference in the input string is used unchanged. To avoid variable expansion, you can escape this syntax with $$; for example: $$(VARIABLE_NAME) This field corresponds to the args field of the Kubernetes Containers v1 core API.
command List<String>
Immutable. Specifies the command that runs when the container starts. This overrides the container's ENTRYPOINT. Specify this field as an array of executable and arguments, similar to a Docker ENTRYPOINT's "exec" form, not its "shell" form. If you do not specify this field, then the container's ENTRYPOINT runs, in conjunction with the args field or the container's CMD, if either exists. If this field is not specified and the container does not have an ENTRYPOINT, then refer to the Docker documentation about how CMD and ENTRYPOINT interact. If you specify this field, then you can also specify the args field to provide additional arguments for this command. However, if you specify this field, then the container's CMD is ignored. See the Kubernetes documentation about how the command and args fields interact with a container's ENTRYPOINT and CMD. In this field, you can reference environment variables set by AI Platform Prediction and environment variables set in the env field. You cannot reference environment variables set in the Docker image. In order for environment variables to be expanded, reference them by using the following syntax: $( VARIABLE_NAME) Note that this differs from Bash variable expansion, which does not use parentheses. If a variable cannot be resolved, the reference in the input string is used unchanged. To avoid variable expansion, you can escape this syntax with $$; for example: $$(VARIABLE_NAME) This field corresponds to the command field of the Kubernetes Containers v1 core API.
env List<Property Map>
Immutable. List of environment variables to set in the container. After the container starts running, code running in the container can read these environment variables. Additionally, the command and args fields can reference these variables. Later entries in this list can also reference earlier entries. For example, the following example sets the variable VAR_2 to have the value foo bar: json [ { "name": "VAR_1", "value": "foo" }, { "name": "VAR_2", "value": "$(VAR_1) bar" } ] If you switch the order of the variables in the example, then the expansion does not occur. This field corresponds to the env field of the Kubernetes Containers v1 core API.
image String
URI of the Docker image to be used as the custom container for serving predictions. This URI must identify an image in Artifact Registry and begin with the hostname {REGION}-docker.pkg.dev, where {REGION} is replaced by the region that matches AI Platform Prediction regional endpoint that you are using. For example, if you are using the us-central1-ml.googleapis.com endpoint, then this URI must begin with us-central1-docker.pkg.dev. To use a custom container, the AI Platform Google-managed service account must have permission to pull (read) the Docker image at this URI. The AI Platform Google-managed service account has the following format: service-{PROJECT_NUMBER}@cloud-ml.google.com.iam.gserviceaccount.com {PROJECT_NUMBER} is replaced by your Google Cloud project number. By default, this service account has necessary permissions to pull an Artifact Registry image in the same Google Cloud project where you are using AI Platform Prediction. In this case, no configuration is necessary. If you want to use an image from a different Google Cloud project, learn how to grant the Artifact Registry Reader (roles/artifactregistry.reader) role for a repository to your projet's AI Platform Google-managed service account. To learn about the requirements for the Docker image itself, read Custom container requirements.
ports List<Property Map>
Immutable. List of ports to expose from the container. AI Platform Prediction sends any prediction requests that it receives to the first port on this list. AI Platform Prediction also sends liveness and health checks to this port. If you do not specify this field, it defaults to following value: json [ { "containerPort": 8080 } ] AI Platform Prediction does not use ports other than the first one listed. This field corresponds to the ports field of the Kubernetes Containers v1 core API.

GoogleCloudMlV1__ContainerSpecResponse
, GoogleCloudMlV1__ContainerSpecResponseArgs

Args This property is required. List<string>
Immutable. Specifies arguments for the command that runs when the container starts. This overrides the container's CMD. Specify this field as an array of executable and arguments, similar to a Docker CMD's "default parameters" form. If you don't specify this field but do specify the command field, then the command from the command field runs without any additional arguments. See the Kubernetes documentation about how the command and args fields interact with a container's ENTRYPOINT and CMD. If you don't specify this field and don't specify the commmand field, then the container's ENTRYPOINT and CMD determine what runs based on their default behavior. See the Docker documentation about how CMD and ENTRYPOINT interact. In this field, you can reference environment variables set by AI Platform Prediction and environment variables set in the env field. You cannot reference environment variables set in the Docker image. In order for environment variables to be expanded, reference them by using the following syntax: $( VARIABLE_NAME) Note that this differs from Bash variable expansion, which does not use parentheses. If a variable cannot be resolved, the reference in the input string is used unchanged. To avoid variable expansion, you can escape this syntax with $$; for example: $$(VARIABLE_NAME) This field corresponds to the args field of the Kubernetes Containers v1 core API.
Command This property is required. List<string>
Immutable. Specifies the command that runs when the container starts. This overrides the container's ENTRYPOINT. Specify this field as an array of executable and arguments, similar to a Docker ENTRYPOINT's "exec" form, not its "shell" form. If you do not specify this field, then the container's ENTRYPOINT runs, in conjunction with the args field or the container's CMD, if either exists. If this field is not specified and the container does not have an ENTRYPOINT, then refer to the Docker documentation about how CMD and ENTRYPOINT interact. If you specify this field, then you can also specify the args field to provide additional arguments for this command. However, if you specify this field, then the container's CMD is ignored. See the Kubernetes documentation about how the command and args fields interact with a container's ENTRYPOINT and CMD. In this field, you can reference environment variables set by AI Platform Prediction and environment variables set in the env field. You cannot reference environment variables set in the Docker image. In order for environment variables to be expanded, reference them by using the following syntax: $( VARIABLE_NAME) Note that this differs from Bash variable expansion, which does not use parentheses. If a variable cannot be resolved, the reference in the input string is used unchanged. To avoid variable expansion, you can escape this syntax with $$; for example: $$(VARIABLE_NAME) This field corresponds to the command field of the Kubernetes Containers v1 core API.
Env This property is required. List<Pulumi.GoogleNative.Ml.V1.Inputs.GoogleCloudMlV1__EnvVarResponse>
Immutable. List of environment variables to set in the container. After the container starts running, code running in the container can read these environment variables. Additionally, the command and args fields can reference these variables. Later entries in this list can also reference earlier entries. For example, the following example sets the variable VAR_2 to have the value foo bar: json [ { "name": "VAR_1", "value": "foo" }, { "name": "VAR_2", "value": "$(VAR_1) bar" } ] If you switch the order of the variables in the example, then the expansion does not occur. This field corresponds to the env field of the Kubernetes Containers v1 core API.
Image This property is required. string
URI of the Docker image to be used as the custom container for serving predictions. This URI must identify an image in Artifact Registry and begin with the hostname {REGION}-docker.pkg.dev, where {REGION} is replaced by the region that matches AI Platform Prediction regional endpoint that you are using. For example, if you are using the us-central1-ml.googleapis.com endpoint, then this URI must begin with us-central1-docker.pkg.dev. To use a custom container, the AI Platform Google-managed service account must have permission to pull (read) the Docker image at this URI. The AI Platform Google-managed service account has the following format: service-{PROJECT_NUMBER}@cloud-ml.google.com.iam.gserviceaccount.com {PROJECT_NUMBER} is replaced by your Google Cloud project number. By default, this service account has necessary permissions to pull an Artifact Registry image in the same Google Cloud project where you are using AI Platform Prediction. In this case, no configuration is necessary. If you want to use an image from a different Google Cloud project, learn how to grant the Artifact Registry Reader (roles/artifactregistry.reader) role for a repository to your projet's AI Platform Google-managed service account. To learn about the requirements for the Docker image itself, read Custom container requirements.
Ports This property is required. List<Pulumi.GoogleNative.Ml.V1.Inputs.GoogleCloudMlV1__ContainerPortResponse>
Immutable. List of ports to expose from the container. AI Platform Prediction sends any prediction requests that it receives to the first port on this list. AI Platform Prediction also sends liveness and health checks to this port. If you do not specify this field, it defaults to following value: json [ { "containerPort": 8080 } ] AI Platform Prediction does not use ports other than the first one listed. This field corresponds to the ports field of the Kubernetes Containers v1 core API.
Args This property is required. []string
Immutable. Specifies arguments for the command that runs when the container starts. This overrides the container's CMD. Specify this field as an array of executable and arguments, similar to a Docker CMD's "default parameters" form. If you don't specify this field but do specify the command field, then the command from the command field runs without any additional arguments. See the Kubernetes documentation about how the command and args fields interact with a container's ENTRYPOINT and CMD. If you don't specify this field and don't specify the commmand field, then the container's ENTRYPOINT and CMD determine what runs based on their default behavior. See the Docker documentation about how CMD and ENTRYPOINT interact. In this field, you can reference environment variables set by AI Platform Prediction and environment variables set in the env field. You cannot reference environment variables set in the Docker image. In order for environment variables to be expanded, reference them by using the following syntax: $( VARIABLE_NAME) Note that this differs from Bash variable expansion, which does not use parentheses. If a variable cannot be resolved, the reference in the input string is used unchanged. To avoid variable expansion, you can escape this syntax with $$; for example: $$(VARIABLE_NAME) This field corresponds to the args field of the Kubernetes Containers v1 core API.
Command This property is required. []string
Immutable. Specifies the command that runs when the container starts. This overrides the container's ENTRYPOINT. Specify this field as an array of executable and arguments, similar to a Docker ENTRYPOINT's "exec" form, not its "shell" form. If you do not specify this field, then the container's ENTRYPOINT runs, in conjunction with the args field or the container's CMD, if either exists. If this field is not specified and the container does not have an ENTRYPOINT, then refer to the Docker documentation about how CMD and ENTRYPOINT interact. If you specify this field, then you can also specify the args field to provide additional arguments for this command. However, if you specify this field, then the container's CMD is ignored. See the Kubernetes documentation about how the command and args fields interact with a container's ENTRYPOINT and CMD. In this field, you can reference environment variables set by AI Platform Prediction and environment variables set in the env field. You cannot reference environment variables set in the Docker image. In order for environment variables to be expanded, reference them by using the following syntax: $( VARIABLE_NAME) Note that this differs from Bash variable expansion, which does not use parentheses. If a variable cannot be resolved, the reference in the input string is used unchanged. To avoid variable expansion, you can escape this syntax with $$; for example: $$(VARIABLE_NAME) This field corresponds to the command field of the Kubernetes Containers v1 core API.
Env This property is required. []GoogleCloudMlV1__EnvVarResponse
Immutable. List of environment variables to set in the container. After the container starts running, code running in the container can read these environment variables. Additionally, the command and args fields can reference these variables. Later entries in this list can also reference earlier entries. For example, the following example sets the variable VAR_2 to have the value foo bar: json [ { "name": "VAR_1", "value": "foo" }, { "name": "VAR_2", "value": "$(VAR_1) bar" } ] If you switch the order of the variables in the example, then the expansion does not occur. This field corresponds to the env field of the Kubernetes Containers v1 core API.
Image This property is required. string
URI of the Docker image to be used as the custom container for serving predictions. This URI must identify an image in Artifact Registry and begin with the hostname {REGION}-docker.pkg.dev, where {REGION} is replaced by the region that matches AI Platform Prediction regional endpoint that you are using. For example, if you are using the us-central1-ml.googleapis.com endpoint, then this URI must begin with us-central1-docker.pkg.dev. To use a custom container, the AI Platform Google-managed service account must have permission to pull (read) the Docker image at this URI. The AI Platform Google-managed service account has the following format: service-{PROJECT_NUMBER}@cloud-ml.google.com.iam.gserviceaccount.com {PROJECT_NUMBER} is replaced by your Google Cloud project number. By default, this service account has necessary permissions to pull an Artifact Registry image in the same Google Cloud project where you are using AI Platform Prediction. In this case, no configuration is necessary. If you want to use an image from a different Google Cloud project, learn how to grant the Artifact Registry Reader (roles/artifactregistry.reader) role for a repository to your projet's AI Platform Google-managed service account. To learn about the requirements for the Docker image itself, read Custom container requirements.
Ports This property is required. []GoogleCloudMlV1__ContainerPortResponse
Immutable. List of ports to expose from the container. AI Platform Prediction sends any prediction requests that it receives to the first port on this list. AI Platform Prediction also sends liveness and health checks to this port. If you do not specify this field, it defaults to following value: json [ { "containerPort": 8080 } ] AI Platform Prediction does not use ports other than the first one listed. This field corresponds to the ports field of the Kubernetes Containers v1 core API.
args This property is required. List<String>
Immutable. Specifies arguments for the command that runs when the container starts. This overrides the container's CMD. Specify this field as an array of executable and arguments, similar to a Docker CMD's "default parameters" form. If you don't specify this field but do specify the command field, then the command from the command field runs without any additional arguments. See the Kubernetes documentation about how the command and args fields interact with a container's ENTRYPOINT and CMD. If you don't specify this field and don't specify the commmand field, then the container's ENTRYPOINT and CMD determine what runs based on their default behavior. See the Docker documentation about how CMD and ENTRYPOINT interact. In this field, you can reference environment variables set by AI Platform Prediction and environment variables set in the env field. You cannot reference environment variables set in the Docker image. In order for environment variables to be expanded, reference them by using the following syntax: $( VARIABLE_NAME) Note that this differs from Bash variable expansion, which does not use parentheses. If a variable cannot be resolved, the reference in the input string is used unchanged. To avoid variable expansion, you can escape this syntax with $$; for example: $$(VARIABLE_NAME) This field corresponds to the args field of the Kubernetes Containers v1 core API.
command This property is required. List<String>
Immutable. Specifies the command that runs when the container starts. This overrides the container's ENTRYPOINT. Specify this field as an array of executable and arguments, similar to a Docker ENTRYPOINT's "exec" form, not its "shell" form. If you do not specify this field, then the container's ENTRYPOINT runs, in conjunction with the args field or the container's CMD, if either exists. If this field is not specified and the container does not have an ENTRYPOINT, then refer to the Docker documentation about how CMD and ENTRYPOINT interact. If you specify this field, then you can also specify the args field to provide additional arguments for this command. However, if you specify this field, then the container's CMD is ignored. See the Kubernetes documentation about how the command and args fields interact with a container's ENTRYPOINT and CMD. In this field, you can reference environment variables set by AI Platform Prediction and environment variables set in the env field. You cannot reference environment variables set in the Docker image. In order for environment variables to be expanded, reference them by using the following syntax: $( VARIABLE_NAME) Note that this differs from Bash variable expansion, which does not use parentheses. If a variable cannot be resolved, the reference in the input string is used unchanged. To avoid variable expansion, you can escape this syntax with $$; for example: $$(VARIABLE_NAME) This field corresponds to the command field of the Kubernetes Containers v1 core API.
env This property is required. List<GoogleCloudMlV1__EnvVarResponse>
Immutable. List of environment variables to set in the container. After the container starts running, code running in the container can read these environment variables. Additionally, the command and args fields can reference these variables. Later entries in this list can also reference earlier entries. For example, the following example sets the variable VAR_2 to have the value foo bar: json [ { "name": "VAR_1", "value": "foo" }, { "name": "VAR_2", "value": "$(VAR_1) bar" } ] If you switch the order of the variables in the example, then the expansion does not occur. This field corresponds to the env field of the Kubernetes Containers v1 core API.
image This property is required. String
URI of the Docker image to be used as the custom container for serving predictions. This URI must identify an image in Artifact Registry and begin with the hostname {REGION}-docker.pkg.dev, where {REGION} is replaced by the region that matches AI Platform Prediction regional endpoint that you are using. For example, if you are using the us-central1-ml.googleapis.com endpoint, then this URI must begin with us-central1-docker.pkg.dev. To use a custom container, the AI Platform Google-managed service account must have permission to pull (read) the Docker image at this URI. The AI Platform Google-managed service account has the following format: service-{PROJECT_NUMBER}@cloud-ml.google.com.iam.gserviceaccount.com {PROJECT_NUMBER} is replaced by your Google Cloud project number. By default, this service account has necessary permissions to pull an Artifact Registry image in the same Google Cloud project where you are using AI Platform Prediction. In this case, no configuration is necessary. If you want to use an image from a different Google Cloud project, learn how to grant the Artifact Registry Reader (roles/artifactregistry.reader) role for a repository to your projet's AI Platform Google-managed service account. To learn about the requirements for the Docker image itself, read Custom container requirements.
ports This property is required. List<GoogleCloudMlV1__ContainerPortResponse>
Immutable. List of ports to expose from the container. AI Platform Prediction sends any prediction requests that it receives to the first port on this list. AI Platform Prediction also sends liveness and health checks to this port. If you do not specify this field, it defaults to following value: json [ { "containerPort": 8080 } ] AI Platform Prediction does not use ports other than the first one listed. This field corresponds to the ports field of the Kubernetes Containers v1 core API.
args This property is required. string[]
Immutable. Specifies arguments for the command that runs when the container starts. This overrides the container's CMD. Specify this field as an array of executable and arguments, similar to a Docker CMD's "default parameters" form. If you don't specify this field but do specify the command field, then the command from the command field runs without any additional arguments. See the Kubernetes documentation about how the command and args fields interact with a container's ENTRYPOINT and CMD. If you don't specify this field and don't specify the commmand field, then the container's ENTRYPOINT and CMD determine what runs based on their default behavior. See the Docker documentation about how CMD and ENTRYPOINT interact. In this field, you can reference environment variables set by AI Platform Prediction and environment variables set in the env field. You cannot reference environment variables set in the Docker image. In order for environment variables to be expanded, reference them by using the following syntax: $( VARIABLE_NAME) Note that this differs from Bash variable expansion, which does not use parentheses. If a variable cannot be resolved, the reference in the input string is used unchanged. To avoid variable expansion, you can escape this syntax with $$; for example: $$(VARIABLE_NAME) This field corresponds to the args field of the Kubernetes Containers v1 core API.
command This property is required. string[]
Immutable. Specifies the command that runs when the container starts. This overrides the container's ENTRYPOINT. Specify this field as an array of executable and arguments, similar to a Docker ENTRYPOINT's "exec" form, not its "shell" form. If you do not specify this field, then the container's ENTRYPOINT runs, in conjunction with the args field or the container's CMD, if either exists. If this field is not specified and the container does not have an ENTRYPOINT, then refer to the Docker documentation about how CMD and ENTRYPOINT interact. If you specify this field, then you can also specify the args field to provide additional arguments for this command. However, if you specify this field, then the container's CMD is ignored. See the Kubernetes documentation about how the command and args fields interact with a container's ENTRYPOINT and CMD. In this field, you can reference environment variables set by AI Platform Prediction and environment variables set in the env field. You cannot reference environment variables set in the Docker image. In order for environment variables to be expanded, reference them by using the following syntax: $( VARIABLE_NAME) Note that this differs from Bash variable expansion, which does not use parentheses. If a variable cannot be resolved, the reference in the input string is used unchanged. To avoid variable expansion, you can escape this syntax with $$; for example: $$(VARIABLE_NAME) This field corresponds to the command field of the Kubernetes Containers v1 core API.
env This property is required. GoogleCloudMlV1__EnvVarResponse[]
Immutable. List of environment variables to set in the container. After the container starts running, code running in the container can read these environment variables. Additionally, the command and args fields can reference these variables. Later entries in this list can also reference earlier entries. For example, the following example sets the variable VAR_2 to have the value foo bar: json [ { "name": "VAR_1", "value": "foo" }, { "name": "VAR_2", "value": "$(VAR_1) bar" } ] If you switch the order of the variables in the example, then the expansion does not occur. This field corresponds to the env field of the Kubernetes Containers v1 core API.
image This property is required. string
URI of the Docker image to be used as the custom container for serving predictions. This URI must identify an image in Artifact Registry and begin with the hostname {REGION}-docker.pkg.dev, where {REGION} is replaced by the region that matches AI Platform Prediction regional endpoint that you are using. For example, if you are using the us-central1-ml.googleapis.com endpoint, then this URI must begin with us-central1-docker.pkg.dev. To use a custom container, the AI Platform Google-managed service account must have permission to pull (read) the Docker image at this URI. The AI Platform Google-managed service account has the following format: service-{PROJECT_NUMBER}@cloud-ml.google.com.iam.gserviceaccount.com {PROJECT_NUMBER} is replaced by your Google Cloud project number. By default, this service account has necessary permissions to pull an Artifact Registry image in the same Google Cloud project where you are using AI Platform Prediction. In this case, no configuration is necessary. If you want to use an image from a different Google Cloud project, learn how to grant the Artifact Registry Reader (roles/artifactregistry.reader) role for a repository to your projet's AI Platform Google-managed service account. To learn about the requirements for the Docker image itself, read Custom container requirements.
ports This property is required. GoogleCloudMlV1__ContainerPortResponse[]
Immutable. List of ports to expose from the container. AI Platform Prediction sends any prediction requests that it receives to the first port on this list. AI Platform Prediction also sends liveness and health checks to this port. If you do not specify this field, it defaults to following value: json [ { "containerPort": 8080 } ] AI Platform Prediction does not use ports other than the first one listed. This field corresponds to the ports field of the Kubernetes Containers v1 core API.
args This property is required. Sequence[str]
Immutable. Specifies arguments for the command that runs when the container starts. This overrides the container's CMD. Specify this field as an array of executable and arguments, similar to a Docker CMD's "default parameters" form. If you don't specify this field but do specify the command field, then the command from the command field runs without any additional arguments. See the Kubernetes documentation about how the command and args fields interact with a container's ENTRYPOINT and CMD. If you don't specify this field and don't specify the commmand field, then the container's ENTRYPOINT and CMD determine what runs based on their default behavior. See the Docker documentation about how CMD and ENTRYPOINT interact. In this field, you can reference environment variables set by AI Platform Prediction and environment variables set in the env field. You cannot reference environment variables set in the Docker image. In order for environment variables to be expanded, reference them by using the following syntax: $( VARIABLE_NAME) Note that this differs from Bash variable expansion, which does not use parentheses. If a variable cannot be resolved, the reference in the input string is used unchanged. To avoid variable expansion, you can escape this syntax with $$; for example: $$(VARIABLE_NAME) This field corresponds to the args field of the Kubernetes Containers v1 core API.
command This property is required. Sequence[str]
Immutable. Specifies the command that runs when the container starts. This overrides the container's ENTRYPOINT. Specify this field as an array of executable and arguments, similar to a Docker ENTRYPOINT's "exec" form, not its "shell" form. If you do not specify this field, then the container's ENTRYPOINT runs, in conjunction with the args field or the container's CMD, if either exists. If this field is not specified and the container does not have an ENTRYPOINT, then refer to the Docker documentation about how CMD and ENTRYPOINT interact. If you specify this field, then you can also specify the args field to provide additional arguments for this command. However, if you specify this field, then the container's CMD is ignored. See the Kubernetes documentation about how the command and args fields interact with a container's ENTRYPOINT and CMD. In this field, you can reference environment variables set by AI Platform Prediction and environment variables set in the env field. You cannot reference environment variables set in the Docker image. In order for environment variables to be expanded, reference them by using the following syntax: $( VARIABLE_NAME) Note that this differs from Bash variable expansion, which does not use parentheses. If a variable cannot be resolved, the reference in the input string is used unchanged. To avoid variable expansion, you can escape this syntax with $$; for example: $$(VARIABLE_NAME) This field corresponds to the command field of the Kubernetes Containers v1 core API.
env This property is required. Sequence[GoogleCloudMlV1EnvVarResponse]
Immutable. List of environment variables to set in the container. After the container starts running, code running in the container can read these environment variables. Additionally, the command and args fields can reference these variables. Later entries in this list can also reference earlier entries. For example, the following example sets the variable VAR_2 to have the value foo bar: json [ { "name": "VAR_1", "value": "foo" }, { "name": "VAR_2", "value": "$(VAR_1) bar" } ] If you switch the order of the variables in the example, then the expansion does not occur. This field corresponds to the env field of the Kubernetes Containers v1 core API.
image This property is required. str
URI of the Docker image to be used as the custom container for serving predictions. This URI must identify an image in Artifact Registry and begin with the hostname {REGION}-docker.pkg.dev, where {REGION} is replaced by the region that matches AI Platform Prediction regional endpoint that you are using. For example, if you are using the us-central1-ml.googleapis.com endpoint, then this URI must begin with us-central1-docker.pkg.dev. To use a custom container, the AI Platform Google-managed service account must have permission to pull (read) the Docker image at this URI. The AI Platform Google-managed service account has the following format: service-{PROJECT_NUMBER}@cloud-ml.google.com.iam.gserviceaccount.com {PROJECT_NUMBER} is replaced by your Google Cloud project number. By default, this service account has necessary permissions to pull an Artifact Registry image in the same Google Cloud project where you are using AI Platform Prediction. In this case, no configuration is necessary. If you want to use an image from a different Google Cloud project, learn how to grant the Artifact Registry Reader (roles/artifactregistry.reader) role for a repository to your projet's AI Platform Google-managed service account. To learn about the requirements for the Docker image itself, read Custom container requirements.
ports This property is required. Sequence[GoogleCloudMlV1ContainerPortResponse]
Immutable. List of ports to expose from the container. AI Platform Prediction sends any prediction requests that it receives to the first port on this list. AI Platform Prediction also sends liveness and health checks to this port. If you do not specify this field, it defaults to following value: json [ { "containerPort": 8080 } ] AI Platform Prediction does not use ports other than the first one listed. This field corresponds to the ports field of the Kubernetes Containers v1 core API.
args This property is required. List<String>
Immutable. Specifies arguments for the command that runs when the container starts. This overrides the container's CMD. Specify this field as an array of executable and arguments, similar to a Docker CMD's "default parameters" form. If you don't specify this field but do specify the command field, then the command from the command field runs without any additional arguments. See the Kubernetes documentation about how the command and args fields interact with a container's ENTRYPOINT and CMD. If you don't specify this field and don't specify the commmand field, then the container's ENTRYPOINT and CMD determine what runs based on their default behavior. See the Docker documentation about how CMD and ENTRYPOINT interact. In this field, you can reference environment variables set by AI Platform Prediction and environment variables set in the env field. You cannot reference environment variables set in the Docker image. In order for environment variables to be expanded, reference them by using the following syntax: $( VARIABLE_NAME) Note that this differs from Bash variable expansion, which does not use parentheses. If a variable cannot be resolved, the reference in the input string is used unchanged. To avoid variable expansion, you can escape this syntax with $$; for example: $$(VARIABLE_NAME) This field corresponds to the args field of the Kubernetes Containers v1 core API.
command This property is required. List<String>
Immutable. Specifies the command that runs when the container starts. This overrides the container's ENTRYPOINT. Specify this field as an array of executable and arguments, similar to a Docker ENTRYPOINT's "exec" form, not its "shell" form. If you do not specify this field, then the container's ENTRYPOINT runs, in conjunction with the args field or the container's CMD, if either exists. If this field is not specified and the container does not have an ENTRYPOINT, then refer to the Docker documentation about how CMD and ENTRYPOINT interact. If you specify this field, then you can also specify the args field to provide additional arguments for this command. However, if you specify this field, then the container's CMD is ignored. See the Kubernetes documentation about how the command and args fields interact with a container's ENTRYPOINT and CMD. In this field, you can reference environment variables set by AI Platform Prediction and environment variables set in the env field. You cannot reference environment variables set in the Docker image. In order for environment variables to be expanded, reference them by using the following syntax: $( VARIABLE_NAME) Note that this differs from Bash variable expansion, which does not use parentheses. If a variable cannot be resolved, the reference in the input string is used unchanged. To avoid variable expansion, you can escape this syntax with $$; for example: $$(VARIABLE_NAME) This field corresponds to the command field of the Kubernetes Containers v1 core API.
env This property is required. List<Property Map>
Immutable. List of environment variables to set in the container. After the container starts running, code running in the container can read these environment variables. Additionally, the command and args fields can reference these variables. Later entries in this list can also reference earlier entries. For example, the following example sets the variable VAR_2 to have the value foo bar: json [ { "name": "VAR_1", "value": "foo" }, { "name": "VAR_2", "value": "$(VAR_1) bar" } ] If you switch the order of the variables in the example, then the expansion does not occur. This field corresponds to the env field of the Kubernetes Containers v1 core API.
image This property is required. String
URI of the Docker image to be used as the custom container for serving predictions. This URI must identify an image in Artifact Registry and begin with the hostname {REGION}-docker.pkg.dev, where {REGION} is replaced by the region that matches AI Platform Prediction regional endpoint that you are using. For example, if you are using the us-central1-ml.googleapis.com endpoint, then this URI must begin with us-central1-docker.pkg.dev. To use a custom container, the AI Platform Google-managed service account must have permission to pull (read) the Docker image at this URI. The AI Platform Google-managed service account has the following format: service-{PROJECT_NUMBER}@cloud-ml.google.com.iam.gserviceaccount.com {PROJECT_NUMBER} is replaced by your Google Cloud project number. By default, this service account has necessary permissions to pull an Artifact Registry image in the same Google Cloud project where you are using AI Platform Prediction. In this case, no configuration is necessary. If you want to use an image from a different Google Cloud project, learn how to grant the Artifact Registry Reader (roles/artifactregistry.reader) role for a repository to your projet's AI Platform Google-managed service account. To learn about the requirements for the Docker image itself, read Custom container requirements.
ports This property is required. List<Property Map>
Immutable. List of ports to expose from the container. AI Platform Prediction sends any prediction requests that it receives to the first port on this list. AI Platform Prediction also sends liveness and health checks to this port. If you do not specify this field, it defaults to following value: json [ { "containerPort": 8080 } ] AI Platform Prediction does not use ports other than the first one listed. This field corresponds to the ports field of the Kubernetes Containers v1 core API.

GoogleCloudMlV1__EnvVar
, GoogleCloudMlV1__EnvVarArgs

Name string
Name of the environment variable. Must be a valid C identifier and must not begin with the prefix AIP_.
Value string
Value of the environment variable. Defaults to an empty string. In this field, you can reference environment variables set by AI Platform Prediction and environment variables set earlier in the same env field as where this message occurs. You cannot reference environment variables set in the Docker image. In order for environment variables to be expanded, reference them by using the following syntax: $(VARIABLE_NAME) Note that this differs from Bash variable expansion, which does not use parentheses. If a variable cannot be resolved, the reference in the input string is used unchanged. To avoid variable expansion, you can escape this syntax with $$; for example: $$(VARIABLE_NAME)
Name string
Name of the environment variable. Must be a valid C identifier and must not begin with the prefix AIP_.
Value string
Value of the environment variable. Defaults to an empty string. In this field, you can reference environment variables set by AI Platform Prediction and environment variables set earlier in the same env field as where this message occurs. You cannot reference environment variables set in the Docker image. In order for environment variables to be expanded, reference them by using the following syntax: $(VARIABLE_NAME) Note that this differs from Bash variable expansion, which does not use parentheses. If a variable cannot be resolved, the reference in the input string is used unchanged. To avoid variable expansion, you can escape this syntax with $$; for example: $$(VARIABLE_NAME)
name String
Name of the environment variable. Must be a valid C identifier and must not begin with the prefix AIP_.
value String
Value of the environment variable. Defaults to an empty string. In this field, you can reference environment variables set by AI Platform Prediction and environment variables set earlier in the same env field as where this message occurs. You cannot reference environment variables set in the Docker image. In order for environment variables to be expanded, reference them by using the following syntax: $(VARIABLE_NAME) Note that this differs from Bash variable expansion, which does not use parentheses. If a variable cannot be resolved, the reference in the input string is used unchanged. To avoid variable expansion, you can escape this syntax with $$; for example: $$(VARIABLE_NAME)
name string
Name of the environment variable. Must be a valid C identifier and must not begin with the prefix AIP_.
value string
Value of the environment variable. Defaults to an empty string. In this field, you can reference environment variables set by AI Platform Prediction and environment variables set earlier in the same env field as where this message occurs. You cannot reference environment variables set in the Docker image. In order for environment variables to be expanded, reference them by using the following syntax: $(VARIABLE_NAME) Note that this differs from Bash variable expansion, which does not use parentheses. If a variable cannot be resolved, the reference in the input string is used unchanged. To avoid variable expansion, you can escape this syntax with $$; for example: $$(VARIABLE_NAME)
name str
Name of the environment variable. Must be a valid C identifier and must not begin with the prefix AIP_.
value str
Value of the environment variable. Defaults to an empty string. In this field, you can reference environment variables set by AI Platform Prediction and environment variables set earlier in the same env field as where this message occurs. You cannot reference environment variables set in the Docker image. In order for environment variables to be expanded, reference them by using the following syntax: $(VARIABLE_NAME) Note that this differs from Bash variable expansion, which does not use parentheses. If a variable cannot be resolved, the reference in the input string is used unchanged. To avoid variable expansion, you can escape this syntax with $$; for example: $$(VARIABLE_NAME)
name String
Name of the environment variable. Must be a valid C identifier and must not begin with the prefix AIP_.
value String
Value of the environment variable. Defaults to an empty string. In this field, you can reference environment variables set by AI Platform Prediction and environment variables set earlier in the same env field as where this message occurs. You cannot reference environment variables set in the Docker image. In order for environment variables to be expanded, reference them by using the following syntax: $(VARIABLE_NAME) Note that this differs from Bash variable expansion, which does not use parentheses. If a variable cannot be resolved, the reference in the input string is used unchanged. To avoid variable expansion, you can escape this syntax with $$; for example: $$(VARIABLE_NAME)

GoogleCloudMlV1__EnvVarResponse
, GoogleCloudMlV1__EnvVarResponseArgs

Name This property is required. string
Name of the environment variable. Must be a valid C identifier and must not begin with the prefix AIP_.
Value This property is required. string
Value of the environment variable. Defaults to an empty string. In this field, you can reference environment variables set by AI Platform Prediction and environment variables set earlier in the same env field as where this message occurs. You cannot reference environment variables set in the Docker image. In order for environment variables to be expanded, reference them by using the following syntax: $(VARIABLE_NAME) Note that this differs from Bash variable expansion, which does not use parentheses. If a variable cannot be resolved, the reference in the input string is used unchanged. To avoid variable expansion, you can escape this syntax with $$; for example: $$(VARIABLE_NAME)
Name This property is required. string
Name of the environment variable. Must be a valid C identifier and must not begin with the prefix AIP_.
Value This property is required. string
Value of the environment variable. Defaults to an empty string. In this field, you can reference environment variables set by AI Platform Prediction and environment variables set earlier in the same env field as where this message occurs. You cannot reference environment variables set in the Docker image. In order for environment variables to be expanded, reference them by using the following syntax: $(VARIABLE_NAME) Note that this differs from Bash variable expansion, which does not use parentheses. If a variable cannot be resolved, the reference in the input string is used unchanged. To avoid variable expansion, you can escape this syntax with $$; for example: $$(VARIABLE_NAME)
name This property is required. String
Name of the environment variable. Must be a valid C identifier and must not begin with the prefix AIP_.
value This property is required. String
Value of the environment variable. Defaults to an empty string. In this field, you can reference environment variables set by AI Platform Prediction and environment variables set earlier in the same env field as where this message occurs. You cannot reference environment variables set in the Docker image. In order for environment variables to be expanded, reference them by using the following syntax: $(VARIABLE_NAME) Note that this differs from Bash variable expansion, which does not use parentheses. If a variable cannot be resolved, the reference in the input string is used unchanged. To avoid variable expansion, you can escape this syntax with $$; for example: $$(VARIABLE_NAME)
name This property is required. string
Name of the environment variable. Must be a valid C identifier and must not begin with the prefix AIP_.
value This property is required. string
Value of the environment variable. Defaults to an empty string. In this field, you can reference environment variables set by AI Platform Prediction and environment variables set earlier in the same env field as where this message occurs. You cannot reference environment variables set in the Docker image. In order for environment variables to be expanded, reference them by using the following syntax: $(VARIABLE_NAME) Note that this differs from Bash variable expansion, which does not use parentheses. If a variable cannot be resolved, the reference in the input string is used unchanged. To avoid variable expansion, you can escape this syntax with $$; for example: $$(VARIABLE_NAME)
name This property is required. str
Name of the environment variable. Must be a valid C identifier and must not begin with the prefix AIP_.
value This property is required. str
Value of the environment variable. Defaults to an empty string. In this field, you can reference environment variables set by AI Platform Prediction and environment variables set earlier in the same env field as where this message occurs. You cannot reference environment variables set in the Docker image. In order for environment variables to be expanded, reference them by using the following syntax: $(VARIABLE_NAME) Note that this differs from Bash variable expansion, which does not use parentheses. If a variable cannot be resolved, the reference in the input string is used unchanged. To avoid variable expansion, you can escape this syntax with $$; for example: $$(VARIABLE_NAME)
name This property is required. String
Name of the environment variable. Must be a valid C identifier and must not begin with the prefix AIP_.
value This property is required. String
Value of the environment variable. Defaults to an empty string. In this field, you can reference environment variables set by AI Platform Prediction and environment variables set earlier in the same env field as where this message occurs. You cannot reference environment variables set in the Docker image. In order for environment variables to be expanded, reference them by using the following syntax: $(VARIABLE_NAME) Note that this differs from Bash variable expansion, which does not use parentheses. If a variable cannot be resolved, the reference in the input string is used unchanged. To avoid variable expansion, you can escape this syntax with $$; for example: $$(VARIABLE_NAME)

GoogleCloudMlV1__ExplanationConfig
, GoogleCloudMlV1__ExplanationConfigArgs

IntegratedGradientsAttribution Pulumi.GoogleNative.Ml.V1.Inputs.GoogleCloudMlV1__IntegratedGradientsAttribution
Attributes credit by computing the Aumann-Shapley value taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1703.01365
SampledShapleyAttribution Pulumi.GoogleNative.Ml.V1.Inputs.GoogleCloudMlV1__SampledShapleyAttribution
An attribution method that approximates Shapley values for features that contribute to the label being predicted. A sampling strategy is used to approximate the value rather than considering all subsets of features.
XraiAttribution Pulumi.GoogleNative.Ml.V1.Inputs.GoogleCloudMlV1__XraiAttribution
Attributes credit by computing the XRAI taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1906.02825 Currently only implemented for models with natural image inputs.
IntegratedGradientsAttribution GoogleCloudMlV1__IntegratedGradientsAttribution
Attributes credit by computing the Aumann-Shapley value taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1703.01365
SampledShapleyAttribution GoogleCloudMlV1__SampledShapleyAttribution
An attribution method that approximates Shapley values for features that contribute to the label being predicted. A sampling strategy is used to approximate the value rather than considering all subsets of features.
XraiAttribution GoogleCloudMlV1__XraiAttribution
Attributes credit by computing the XRAI taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1906.02825 Currently only implemented for models with natural image inputs.
integratedGradientsAttribution GoogleCloudMlV1__IntegratedGradientsAttribution
Attributes credit by computing the Aumann-Shapley value taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1703.01365
sampledShapleyAttribution GoogleCloudMlV1__SampledShapleyAttribution
An attribution method that approximates Shapley values for features that contribute to the label being predicted. A sampling strategy is used to approximate the value rather than considering all subsets of features.
xraiAttribution GoogleCloudMlV1__XraiAttribution
Attributes credit by computing the XRAI taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1906.02825 Currently only implemented for models with natural image inputs.
integratedGradientsAttribution GoogleCloudMlV1__IntegratedGradientsAttribution
Attributes credit by computing the Aumann-Shapley value taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1703.01365
sampledShapleyAttribution GoogleCloudMlV1__SampledShapleyAttribution
An attribution method that approximates Shapley values for features that contribute to the label being predicted. A sampling strategy is used to approximate the value rather than considering all subsets of features.
xraiAttribution GoogleCloudMlV1__XraiAttribution
Attributes credit by computing the XRAI taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1906.02825 Currently only implemented for models with natural image inputs.
integrated_gradients_attribution GoogleCloudMlV1IntegratedGradientsAttribution
Attributes credit by computing the Aumann-Shapley value taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1703.01365
sampled_shapley_attribution GoogleCloudMlV1SampledShapleyAttribution
An attribution method that approximates Shapley values for features that contribute to the label being predicted. A sampling strategy is used to approximate the value rather than considering all subsets of features.
xrai_attribution GoogleCloudMlV1XraiAttribution
Attributes credit by computing the XRAI taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1906.02825 Currently only implemented for models with natural image inputs.
integratedGradientsAttribution Property Map
Attributes credit by computing the Aumann-Shapley value taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1703.01365
sampledShapleyAttribution Property Map
An attribution method that approximates Shapley values for features that contribute to the label being predicted. A sampling strategy is used to approximate the value rather than considering all subsets of features.
xraiAttribution Property Map
Attributes credit by computing the XRAI taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1906.02825 Currently only implemented for models with natural image inputs.

GoogleCloudMlV1__ExplanationConfigResponse
, GoogleCloudMlV1__ExplanationConfigResponseArgs

IntegratedGradientsAttribution This property is required. Pulumi.GoogleNative.Ml.V1.Inputs.GoogleCloudMlV1__IntegratedGradientsAttributionResponse
Attributes credit by computing the Aumann-Shapley value taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1703.01365
SampledShapleyAttribution This property is required. Pulumi.GoogleNative.Ml.V1.Inputs.GoogleCloudMlV1__SampledShapleyAttributionResponse
An attribution method that approximates Shapley values for features that contribute to the label being predicted. A sampling strategy is used to approximate the value rather than considering all subsets of features.
XraiAttribution This property is required. Pulumi.GoogleNative.Ml.V1.Inputs.GoogleCloudMlV1__XraiAttributionResponse
Attributes credit by computing the XRAI taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1906.02825 Currently only implemented for models with natural image inputs.
IntegratedGradientsAttribution This property is required. GoogleCloudMlV1__IntegratedGradientsAttributionResponse
Attributes credit by computing the Aumann-Shapley value taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1703.01365
SampledShapleyAttribution This property is required. GoogleCloudMlV1__SampledShapleyAttributionResponse
An attribution method that approximates Shapley values for features that contribute to the label being predicted. A sampling strategy is used to approximate the value rather than considering all subsets of features.
XraiAttribution This property is required. GoogleCloudMlV1__XraiAttributionResponse
Attributes credit by computing the XRAI taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1906.02825 Currently only implemented for models with natural image inputs.
integratedGradientsAttribution This property is required. GoogleCloudMlV1__IntegratedGradientsAttributionResponse
Attributes credit by computing the Aumann-Shapley value taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1703.01365
sampledShapleyAttribution This property is required. GoogleCloudMlV1__SampledShapleyAttributionResponse
An attribution method that approximates Shapley values for features that contribute to the label being predicted. A sampling strategy is used to approximate the value rather than considering all subsets of features.
xraiAttribution This property is required. GoogleCloudMlV1__XraiAttributionResponse
Attributes credit by computing the XRAI taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1906.02825 Currently only implemented for models with natural image inputs.
integratedGradientsAttribution This property is required. GoogleCloudMlV1__IntegratedGradientsAttributionResponse
Attributes credit by computing the Aumann-Shapley value taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1703.01365
sampledShapleyAttribution This property is required. GoogleCloudMlV1__SampledShapleyAttributionResponse
An attribution method that approximates Shapley values for features that contribute to the label being predicted. A sampling strategy is used to approximate the value rather than considering all subsets of features.
xraiAttribution This property is required. GoogleCloudMlV1__XraiAttributionResponse
Attributes credit by computing the XRAI taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1906.02825 Currently only implemented for models with natural image inputs.
integrated_gradients_attribution This property is required. GoogleCloudMlV1IntegratedGradientsAttributionResponse
Attributes credit by computing the Aumann-Shapley value taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1703.01365
sampled_shapley_attribution This property is required. GoogleCloudMlV1SampledShapleyAttributionResponse
An attribution method that approximates Shapley values for features that contribute to the label being predicted. A sampling strategy is used to approximate the value rather than considering all subsets of features.
xrai_attribution This property is required. GoogleCloudMlV1XraiAttributionResponse
Attributes credit by computing the XRAI taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1906.02825 Currently only implemented for models with natural image inputs.
integratedGradientsAttribution This property is required. Property Map
Attributes credit by computing the Aumann-Shapley value taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1703.01365
sampledShapleyAttribution This property is required. Property Map
An attribution method that approximates Shapley values for features that contribute to the label being predicted. A sampling strategy is used to approximate the value rather than considering all subsets of features.
xraiAttribution This property is required. Property Map
Attributes credit by computing the XRAI taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1906.02825 Currently only implemented for models with natural image inputs.

GoogleCloudMlV1__IntegratedGradientsAttribution
, GoogleCloudMlV1__IntegratedGradientsAttributionArgs

NumIntegralSteps int
Number of steps for approximating the path integral. A good value to start is 50 and gradually increase until the sum to diff property is met within the desired error range.
NumIntegralSteps int
Number of steps for approximating the path integral. A good value to start is 50 and gradually increase until the sum to diff property is met within the desired error range.
numIntegralSteps Integer
Number of steps for approximating the path integral. A good value to start is 50 and gradually increase until the sum to diff property is met within the desired error range.
numIntegralSteps number
Number of steps for approximating the path integral. A good value to start is 50 and gradually increase until the sum to diff property is met within the desired error range.
num_integral_steps int
Number of steps for approximating the path integral. A good value to start is 50 and gradually increase until the sum to diff property is met within the desired error range.
numIntegralSteps Number
Number of steps for approximating the path integral. A good value to start is 50 and gradually increase until the sum to diff property is met within the desired error range.

GoogleCloudMlV1__IntegratedGradientsAttributionResponse
, GoogleCloudMlV1__IntegratedGradientsAttributionResponseArgs

NumIntegralSteps This property is required. int
Number of steps for approximating the path integral. A good value to start is 50 and gradually increase until the sum to diff property is met within the desired error range.
NumIntegralSteps This property is required. int
Number of steps for approximating the path integral. A good value to start is 50 and gradually increase until the sum to diff property is met within the desired error range.
numIntegralSteps This property is required. Integer
Number of steps for approximating the path integral. A good value to start is 50 and gradually increase until the sum to diff property is met within the desired error range.
numIntegralSteps This property is required. number
Number of steps for approximating the path integral. A good value to start is 50 and gradually increase until the sum to diff property is met within the desired error range.
num_integral_steps This property is required. int
Number of steps for approximating the path integral. A good value to start is 50 and gradually increase until the sum to diff property is met within the desired error range.
numIntegralSteps This property is required. Number
Number of steps for approximating the path integral. A good value to start is 50 and gradually increase until the sum to diff property is met within the desired error range.

GoogleCloudMlV1__ManualScaling
, GoogleCloudMlV1__ManualScalingArgs

Nodes int
The number of nodes to allocate for this model. These nodes are always up, starting from the time the model is deployed, so the cost of operating this model will be proportional to nodes * number of hours since last billing cycle plus the cost for each prediction performed.
Nodes int
The number of nodes to allocate for this model. These nodes are always up, starting from the time the model is deployed, so the cost of operating this model will be proportional to nodes * number of hours since last billing cycle plus the cost for each prediction performed.
nodes Integer
The number of nodes to allocate for this model. These nodes are always up, starting from the time the model is deployed, so the cost of operating this model will be proportional to nodes * number of hours since last billing cycle plus the cost for each prediction performed.
nodes number
The number of nodes to allocate for this model. These nodes are always up, starting from the time the model is deployed, so the cost of operating this model will be proportional to nodes * number of hours since last billing cycle plus the cost for each prediction performed.
nodes int
The number of nodes to allocate for this model. These nodes are always up, starting from the time the model is deployed, so the cost of operating this model will be proportional to nodes * number of hours since last billing cycle plus the cost for each prediction performed.
nodes Number
The number of nodes to allocate for this model. These nodes are always up, starting from the time the model is deployed, so the cost of operating this model will be proportional to nodes * number of hours since last billing cycle plus the cost for each prediction performed.

GoogleCloudMlV1__ManualScalingResponse
, GoogleCloudMlV1__ManualScalingResponseArgs

Nodes This property is required. int
The number of nodes to allocate for this model. These nodes are always up, starting from the time the model is deployed, so the cost of operating this model will be proportional to nodes * number of hours since last billing cycle plus the cost for each prediction performed.
Nodes This property is required. int
The number of nodes to allocate for this model. These nodes are always up, starting from the time the model is deployed, so the cost of operating this model will be proportional to nodes * number of hours since last billing cycle plus the cost for each prediction performed.
nodes This property is required. Integer
The number of nodes to allocate for this model. These nodes are always up, starting from the time the model is deployed, so the cost of operating this model will be proportional to nodes * number of hours since last billing cycle plus the cost for each prediction performed.
nodes This property is required. number
The number of nodes to allocate for this model. These nodes are always up, starting from the time the model is deployed, so the cost of operating this model will be proportional to nodes * number of hours since last billing cycle plus the cost for each prediction performed.
nodes This property is required. int
The number of nodes to allocate for this model. These nodes are always up, starting from the time the model is deployed, so the cost of operating this model will be proportional to nodes * number of hours since last billing cycle plus the cost for each prediction performed.
nodes This property is required. Number
The number of nodes to allocate for this model. These nodes are always up, starting from the time the model is deployed, so the cost of operating this model will be proportional to nodes * number of hours since last billing cycle plus the cost for each prediction performed.

GoogleCloudMlV1__MetricSpec
, GoogleCloudMlV1__MetricSpecArgs

Name Pulumi.GoogleNative.Ml.V1.GoogleCloudMlV1__MetricSpecName
metric name.
Target int
Target specifies the target value for the given metric; once real metric deviates from the threshold by a certain percentage, the node count changes.
Name GoogleCloudMlV1__MetricSpecName
metric name.
Target int
Target specifies the target value for the given metric; once real metric deviates from the threshold by a certain percentage, the node count changes.
name GoogleCloudMlV1__MetricSpecName
metric name.
target Integer
Target specifies the target value for the given metric; once real metric deviates from the threshold by a certain percentage, the node count changes.
name GoogleCloudMlV1__MetricSpecName
metric name.
target number
Target specifies the target value for the given metric; once real metric deviates from the threshold by a certain percentage, the node count changes.
name GoogleCloudMlV1MetricSpecName
metric name.
target int
Target specifies the target value for the given metric; once real metric deviates from the threshold by a certain percentage, the node count changes.
name "METRIC_NAME_UNSPECIFIED" | "CPU_USAGE" | "GPU_DUTY_CYCLE"
metric name.
target Number
Target specifies the target value for the given metric; once real metric deviates from the threshold by a certain percentage, the node count changes.

GoogleCloudMlV1__MetricSpecName
, GoogleCloudMlV1__MetricSpecNameArgs

MetricNameUnspecified
METRIC_NAME_UNSPECIFIEDUnspecified MetricName.
CpuUsage
CPU_USAGECPU usage.
GpuDutyCycle
GPU_DUTY_CYCLEGPU duty cycle.
GoogleCloudMlV1__MetricSpecNameMetricNameUnspecified
METRIC_NAME_UNSPECIFIEDUnspecified MetricName.
GoogleCloudMlV1__MetricSpecNameCpuUsage
CPU_USAGECPU usage.
GoogleCloudMlV1__MetricSpecNameGpuDutyCycle
GPU_DUTY_CYCLEGPU duty cycle.
MetricNameUnspecified
METRIC_NAME_UNSPECIFIEDUnspecified MetricName.
CpuUsage
CPU_USAGECPU usage.
GpuDutyCycle
GPU_DUTY_CYCLEGPU duty cycle.
MetricNameUnspecified
METRIC_NAME_UNSPECIFIEDUnspecified MetricName.
CpuUsage
CPU_USAGECPU usage.
GpuDutyCycle
GPU_DUTY_CYCLEGPU duty cycle.
METRIC_NAME_UNSPECIFIED
METRIC_NAME_UNSPECIFIEDUnspecified MetricName.
CPU_USAGE
CPU_USAGECPU usage.
GPU_DUTY_CYCLE
GPU_DUTY_CYCLEGPU duty cycle.
"METRIC_NAME_UNSPECIFIED"
METRIC_NAME_UNSPECIFIEDUnspecified MetricName.
"CPU_USAGE"
CPU_USAGECPU usage.
"GPU_DUTY_CYCLE"
GPU_DUTY_CYCLEGPU duty cycle.

GoogleCloudMlV1__MetricSpecResponse
, GoogleCloudMlV1__MetricSpecResponseArgs

Name This property is required. string
metric name.
Target This property is required. int
Target specifies the target value for the given metric; once real metric deviates from the threshold by a certain percentage, the node count changes.
Name This property is required. string
metric name.
Target This property is required. int
Target specifies the target value for the given metric; once real metric deviates from the threshold by a certain percentage, the node count changes.
name This property is required. String
metric name.
target This property is required. Integer
Target specifies the target value for the given metric; once real metric deviates from the threshold by a certain percentage, the node count changes.
name This property is required. string
metric name.
target This property is required. number
Target specifies the target value for the given metric; once real metric deviates from the threshold by a certain percentage, the node count changes.
name This property is required. str
metric name.
target This property is required. int
Target specifies the target value for the given metric; once real metric deviates from the threshold by a certain percentage, the node count changes.
name This property is required. String
metric name.
target This property is required. Number
Target specifies the target value for the given metric; once real metric deviates from the threshold by a certain percentage, the node count changes.

GoogleCloudMlV1__RequestLoggingConfig
, GoogleCloudMlV1__RequestLoggingConfigArgs

BigqueryTableName This property is required. string
Fully qualified BigQuery table name in the following format: " project_id.dataset_name.table_name" The specified table must already exist, and the "Cloud ML Service Agent" for your project must have permission to write to it. The table must have the following schema: Field nameType Mode model STRING REQUIRED model_version STRING REQUIRED time TIMESTAMP REQUIRED raw_data STRING REQUIRED raw_prediction STRING NULLABLE groundtruth STRING NULLABLE
SamplingPercentage double
Percentage of requests to be logged, expressed as a fraction from 0 to 1. For example, if you want to log 10% of requests, enter 0.1. The sampling window is the lifetime of the model version. Defaults to 0.
BigqueryTableName This property is required. string
Fully qualified BigQuery table name in the following format: " project_id.dataset_name.table_name" The specified table must already exist, and the "Cloud ML Service Agent" for your project must have permission to write to it. The table must have the following schema: Field nameType Mode model STRING REQUIRED model_version STRING REQUIRED time TIMESTAMP REQUIRED raw_data STRING REQUIRED raw_prediction STRING NULLABLE groundtruth STRING NULLABLE
SamplingPercentage float64
Percentage of requests to be logged, expressed as a fraction from 0 to 1. For example, if you want to log 10% of requests, enter 0.1. The sampling window is the lifetime of the model version. Defaults to 0.
bigqueryTableName This property is required. String
Fully qualified BigQuery table name in the following format: " project_id.dataset_name.table_name" The specified table must already exist, and the "Cloud ML Service Agent" for your project must have permission to write to it. The table must have the following schema: Field nameType Mode model STRING REQUIRED model_version STRING REQUIRED time TIMESTAMP REQUIRED raw_data STRING REQUIRED raw_prediction STRING NULLABLE groundtruth STRING NULLABLE
samplingPercentage Double
Percentage of requests to be logged, expressed as a fraction from 0 to 1. For example, if you want to log 10% of requests, enter 0.1. The sampling window is the lifetime of the model version. Defaults to 0.
bigqueryTableName This property is required. string
Fully qualified BigQuery table name in the following format: " project_id.dataset_name.table_name" The specified table must already exist, and the "Cloud ML Service Agent" for your project must have permission to write to it. The table must have the following schema: Field nameType Mode model STRING REQUIRED model_version STRING REQUIRED time TIMESTAMP REQUIRED raw_data STRING REQUIRED raw_prediction STRING NULLABLE groundtruth STRING NULLABLE
samplingPercentage number
Percentage of requests to be logged, expressed as a fraction from 0 to 1. For example, if you want to log 10% of requests, enter 0.1. The sampling window is the lifetime of the model version. Defaults to 0.
bigquery_table_name This property is required. str
Fully qualified BigQuery table name in the following format: " project_id.dataset_name.table_name" The specified table must already exist, and the "Cloud ML Service Agent" for your project must have permission to write to it. The table must have the following schema: Field nameType Mode model STRING REQUIRED model_version STRING REQUIRED time TIMESTAMP REQUIRED raw_data STRING REQUIRED raw_prediction STRING NULLABLE groundtruth STRING NULLABLE
sampling_percentage float
Percentage of requests to be logged, expressed as a fraction from 0 to 1. For example, if you want to log 10% of requests, enter 0.1. The sampling window is the lifetime of the model version. Defaults to 0.
bigqueryTableName This property is required. String
Fully qualified BigQuery table name in the following format: " project_id.dataset_name.table_name" The specified table must already exist, and the "Cloud ML Service Agent" for your project must have permission to write to it. The table must have the following schema: Field nameType Mode model STRING REQUIRED model_version STRING REQUIRED time TIMESTAMP REQUIRED raw_data STRING REQUIRED raw_prediction STRING NULLABLE groundtruth STRING NULLABLE
samplingPercentage Number
Percentage of requests to be logged, expressed as a fraction from 0 to 1. For example, if you want to log 10% of requests, enter 0.1. The sampling window is the lifetime of the model version. Defaults to 0.

GoogleCloudMlV1__RequestLoggingConfigResponse
, GoogleCloudMlV1__RequestLoggingConfigResponseArgs

BigqueryTableName This property is required. string
Fully qualified BigQuery table name in the following format: " project_id.dataset_name.table_name" The specified table must already exist, and the "Cloud ML Service Agent" for your project must have permission to write to it. The table must have the following schema: Field nameType Mode model STRING REQUIRED model_version STRING REQUIRED time TIMESTAMP REQUIRED raw_data STRING REQUIRED raw_prediction STRING NULLABLE groundtruth STRING NULLABLE
SamplingPercentage This property is required. double
Percentage of requests to be logged, expressed as a fraction from 0 to 1. For example, if you want to log 10% of requests, enter 0.1. The sampling window is the lifetime of the model version. Defaults to 0.
BigqueryTableName This property is required. string
Fully qualified BigQuery table name in the following format: " project_id.dataset_name.table_name" The specified table must already exist, and the "Cloud ML Service Agent" for your project must have permission to write to it. The table must have the following schema: Field nameType Mode model STRING REQUIRED model_version STRING REQUIRED time TIMESTAMP REQUIRED raw_data STRING REQUIRED raw_prediction STRING NULLABLE groundtruth STRING NULLABLE
SamplingPercentage This property is required. float64
Percentage of requests to be logged, expressed as a fraction from 0 to 1. For example, if you want to log 10% of requests, enter 0.1. The sampling window is the lifetime of the model version. Defaults to 0.
bigqueryTableName This property is required. String
Fully qualified BigQuery table name in the following format: " project_id.dataset_name.table_name" The specified table must already exist, and the "Cloud ML Service Agent" for your project must have permission to write to it. The table must have the following schema: Field nameType Mode model STRING REQUIRED model_version STRING REQUIRED time TIMESTAMP REQUIRED raw_data STRING REQUIRED raw_prediction STRING NULLABLE groundtruth STRING NULLABLE
samplingPercentage This property is required. Double
Percentage of requests to be logged, expressed as a fraction from 0 to 1. For example, if you want to log 10% of requests, enter 0.1. The sampling window is the lifetime of the model version. Defaults to 0.
bigqueryTableName This property is required. string
Fully qualified BigQuery table name in the following format: " project_id.dataset_name.table_name" The specified table must already exist, and the "Cloud ML Service Agent" for your project must have permission to write to it. The table must have the following schema: Field nameType Mode model STRING REQUIRED model_version STRING REQUIRED time TIMESTAMP REQUIRED raw_data STRING REQUIRED raw_prediction STRING NULLABLE groundtruth STRING NULLABLE
samplingPercentage This property is required. number
Percentage of requests to be logged, expressed as a fraction from 0 to 1. For example, if you want to log 10% of requests, enter 0.1. The sampling window is the lifetime of the model version. Defaults to 0.
bigquery_table_name This property is required. str
Fully qualified BigQuery table name in the following format: " project_id.dataset_name.table_name" The specified table must already exist, and the "Cloud ML Service Agent" for your project must have permission to write to it. The table must have the following schema: Field nameType Mode model STRING REQUIRED model_version STRING REQUIRED time TIMESTAMP REQUIRED raw_data STRING REQUIRED raw_prediction STRING NULLABLE groundtruth STRING NULLABLE
sampling_percentage This property is required. float
Percentage of requests to be logged, expressed as a fraction from 0 to 1. For example, if you want to log 10% of requests, enter 0.1. The sampling window is the lifetime of the model version. Defaults to 0.
bigqueryTableName This property is required. String
Fully qualified BigQuery table name in the following format: " project_id.dataset_name.table_name" The specified table must already exist, and the "Cloud ML Service Agent" for your project must have permission to write to it. The table must have the following schema: Field nameType Mode model STRING REQUIRED model_version STRING REQUIRED time TIMESTAMP REQUIRED raw_data STRING REQUIRED raw_prediction STRING NULLABLE groundtruth STRING NULLABLE
samplingPercentage This property is required. Number
Percentage of requests to be logged, expressed as a fraction from 0 to 1. For example, if you want to log 10% of requests, enter 0.1. The sampling window is the lifetime of the model version. Defaults to 0.

GoogleCloudMlV1__RouteMap
, GoogleCloudMlV1__RouteMapArgs

Health string
HTTP path on the container to send health checkss to. AI Platform Prediction intermittently sends GET requests to this path on the container's IP address and port to check that the container is healthy. Read more about health checks. For example, if you set this field to /bar, then AI Platform Prediction intermittently sends a GET request to the /bar path on the port of your container specified by the first value of Version.container.ports. If you don't specify this field, it defaults to the following value: /v1/models/ MODEL/versions/VERSION The placeholders in this value are replaced as follows: * MODEL: The name of the parent Model. This does not include the "projects/PROJECT_ID/models/" prefix that the API returns in output; it is the bare model name, as provided to projects.models.create. * VERSION: The name of the model version. This does not include the "projects/PROJECT_ID /models/MODEL/versions/" prefix that the API returns in output; it is the bare version name, as provided to projects.models.versions.create.
Predict string
HTTP path on the container to send prediction requests to. AI Platform Prediction forwards requests sent using projects.predict to this path on the container's IP address and port. AI Platform Prediction then returns the container's response in the API response. For example, if you set this field to /foo, then when AI Platform Prediction receives a prediction request, it forwards the request body in a POST request to the /foo path on the port of your container specified by the first value of Version.container.ports. If you don't specify this field, it defaults to the following value: /v1/models/MODEL/versions/VERSION:predict The placeholders in this value are replaced as follows: * MODEL: The name of the parent Model. This does not include the "projects/PROJECT_ID/models/" prefix that the API returns in output; it is the bare model name, as provided to projects.models.create. * VERSION: The name of the model version. This does not include the "projects/PROJECT_ID/models/MODEL/versions/" prefix that the API returns in output; it is the bare version name, as provided to projects.models.versions.create.
Health string
HTTP path on the container to send health checkss to. AI Platform Prediction intermittently sends GET requests to this path on the container's IP address and port to check that the container is healthy. Read more about health checks. For example, if you set this field to /bar, then AI Platform Prediction intermittently sends a GET request to the /bar path on the port of your container specified by the first value of Version.container.ports. If you don't specify this field, it defaults to the following value: /v1/models/ MODEL/versions/VERSION The placeholders in this value are replaced as follows: * MODEL: The name of the parent Model. This does not include the "projects/PROJECT_ID/models/" prefix that the API returns in output; it is the bare model name, as provided to projects.models.create. * VERSION: The name of the model version. This does not include the "projects/PROJECT_ID /models/MODEL/versions/" prefix that the API returns in output; it is the bare version name, as provided to projects.models.versions.create.
Predict string
HTTP path on the container to send prediction requests to. AI Platform Prediction forwards requests sent using projects.predict to this path on the container's IP address and port. AI Platform Prediction then returns the container's response in the API response. For example, if you set this field to /foo, then when AI Platform Prediction receives a prediction request, it forwards the request body in a POST request to the /foo path on the port of your container specified by the first value of Version.container.ports. If you don't specify this field, it defaults to the following value: /v1/models/MODEL/versions/VERSION:predict The placeholders in this value are replaced as follows: * MODEL: The name of the parent Model. This does not include the "projects/PROJECT_ID/models/" prefix that the API returns in output; it is the bare model name, as provided to projects.models.create. * VERSION: The name of the model version. This does not include the "projects/PROJECT_ID/models/MODEL/versions/" prefix that the API returns in output; it is the bare version name, as provided to projects.models.versions.create.
health String
HTTP path on the container to send health checkss to. AI Platform Prediction intermittently sends GET requests to this path on the container's IP address and port to check that the container is healthy. Read more about health checks. For example, if you set this field to /bar, then AI Platform Prediction intermittently sends a GET request to the /bar path on the port of your container specified by the first value of Version.container.ports. If you don't specify this field, it defaults to the following value: /v1/models/ MODEL/versions/VERSION The placeholders in this value are replaced as follows: * MODEL: The name of the parent Model. This does not include the "projects/PROJECT_ID/models/" prefix that the API returns in output; it is the bare model name, as provided to projects.models.create. * VERSION: The name of the model version. This does not include the "projects/PROJECT_ID /models/MODEL/versions/" prefix that the API returns in output; it is the bare version name, as provided to projects.models.versions.create.
predict String
HTTP path on the container to send prediction requests to. AI Platform Prediction forwards requests sent using projects.predict to this path on the container's IP address and port. AI Platform Prediction then returns the container's response in the API response. For example, if you set this field to /foo, then when AI Platform Prediction receives a prediction request, it forwards the request body in a POST request to the /foo path on the port of your container specified by the first value of Version.container.ports. If you don't specify this field, it defaults to the following value: /v1/models/MODEL/versions/VERSION:predict The placeholders in this value are replaced as follows: * MODEL: The name of the parent Model. This does not include the "projects/PROJECT_ID/models/" prefix that the API returns in output; it is the bare model name, as provided to projects.models.create. * VERSION: The name of the model version. This does not include the "projects/PROJECT_ID/models/MODEL/versions/" prefix that the API returns in output; it is the bare version name, as provided to projects.models.versions.create.
health string
HTTP path on the container to send health checkss to. AI Platform Prediction intermittently sends GET requests to this path on the container's IP address and port to check that the container is healthy. Read more about health checks. For example, if you set this field to /bar, then AI Platform Prediction intermittently sends a GET request to the /bar path on the port of your container specified by the first value of Version.container.ports. If you don't specify this field, it defaults to the following value: /v1/models/ MODEL/versions/VERSION The placeholders in this value are replaced as follows: * MODEL: The name of the parent Model. This does not include the "projects/PROJECT_ID/models/" prefix that the API returns in output; it is the bare model name, as provided to projects.models.create. * VERSION: The name of the model version. This does not include the "projects/PROJECT_ID /models/MODEL/versions/" prefix that the API returns in output; it is the bare version name, as provided to projects.models.versions.create.
predict string
HTTP path on the container to send prediction requests to. AI Platform Prediction forwards requests sent using projects.predict to this path on the container's IP address and port. AI Platform Prediction then returns the container's response in the API response. For example, if you set this field to /foo, then when AI Platform Prediction receives a prediction request, it forwards the request body in a POST request to the /foo path on the port of your container specified by the first value of Version.container.ports. If you don't specify this field, it defaults to the following value: /v1/models/MODEL/versions/VERSION:predict The placeholders in this value are replaced as follows: * MODEL: The name of the parent Model. This does not include the "projects/PROJECT_ID/models/" prefix that the API returns in output; it is the bare model name, as provided to projects.models.create. * VERSION: The name of the model version. This does not include the "projects/PROJECT_ID/models/MODEL/versions/" prefix that the API returns in output; it is the bare version name, as provided to projects.models.versions.create.
health str
HTTP path on the container to send health checkss to. AI Platform Prediction intermittently sends GET requests to this path on the container's IP address and port to check that the container is healthy. Read more about health checks. For example, if you set this field to /bar, then AI Platform Prediction intermittently sends a GET request to the /bar path on the port of your container specified by the first value of Version.container.ports. If you don't specify this field, it defaults to the following value: /v1/models/ MODEL/versions/VERSION The placeholders in this value are replaced as follows: * MODEL: The name of the parent Model. This does not include the "projects/PROJECT_ID/models/" prefix that the API returns in output; it is the bare model name, as provided to projects.models.create. * VERSION: The name of the model version. This does not include the "projects/PROJECT_ID /models/MODEL/versions/" prefix that the API returns in output; it is the bare version name, as provided to projects.models.versions.create.
predict str
HTTP path on the container to send prediction requests to. AI Platform Prediction forwards requests sent using projects.predict to this path on the container's IP address and port. AI Platform Prediction then returns the container's response in the API response. For example, if you set this field to /foo, then when AI Platform Prediction receives a prediction request, it forwards the request body in a POST request to the /foo path on the port of your container specified by the first value of Version.container.ports. If you don't specify this field, it defaults to the following value: /v1/models/MODEL/versions/VERSION:predict The placeholders in this value are replaced as follows: * MODEL: The name of the parent Model. This does not include the "projects/PROJECT_ID/models/" prefix that the API returns in output; it is the bare model name, as provided to projects.models.create. * VERSION: The name of the model version. This does not include the "projects/PROJECT_ID/models/MODEL/versions/" prefix that the API returns in output; it is the bare version name, as provided to projects.models.versions.create.
health String
HTTP path on the container to send health checkss to. AI Platform Prediction intermittently sends GET requests to this path on the container's IP address and port to check that the container is healthy. Read more about health checks. For example, if you set this field to /bar, then AI Platform Prediction intermittently sends a GET request to the /bar path on the port of your container specified by the first value of Version.container.ports. If you don't specify this field, it defaults to the following value: /v1/models/ MODEL/versions/VERSION The placeholders in this value are replaced as follows: * MODEL: The name of the parent Model. This does not include the "projects/PROJECT_ID/models/" prefix that the API returns in output; it is the bare model name, as provided to projects.models.create. * VERSION: The name of the model version. This does not include the "projects/PROJECT_ID /models/MODEL/versions/" prefix that the API returns in output; it is the bare version name, as provided to projects.models.versions.create.
predict String
HTTP path on the container to send prediction requests to. AI Platform Prediction forwards requests sent using projects.predict to this path on the container's IP address and port. AI Platform Prediction then returns the container's response in the API response. For example, if you set this field to /foo, then when AI Platform Prediction receives a prediction request, it forwards the request body in a POST request to the /foo path on the port of your container specified by the first value of Version.container.ports. If you don't specify this field, it defaults to the following value: /v1/models/MODEL/versions/VERSION:predict The placeholders in this value are replaced as follows: * MODEL: The name of the parent Model. This does not include the "projects/PROJECT_ID/models/" prefix that the API returns in output; it is the bare model name, as provided to projects.models.create. * VERSION: The name of the model version. This does not include the "projects/PROJECT_ID/models/MODEL/versions/" prefix that the API returns in output; it is the bare version name, as provided to projects.models.versions.create.

GoogleCloudMlV1__RouteMapResponse
, GoogleCloudMlV1__RouteMapResponseArgs

Health This property is required. string
HTTP path on the container to send health checkss to. AI Platform Prediction intermittently sends GET requests to this path on the container's IP address and port to check that the container is healthy. Read more about health checks. For example, if you set this field to /bar, then AI Platform Prediction intermittently sends a GET request to the /bar path on the port of your container specified by the first value of Version.container.ports. If you don't specify this field, it defaults to the following value: /v1/models/ MODEL/versions/VERSION The placeholders in this value are replaced as follows: * MODEL: The name of the parent Model. This does not include the "projects/PROJECT_ID/models/" prefix that the API returns in output; it is the bare model name, as provided to projects.models.create. * VERSION: The name of the model version. This does not include the "projects/PROJECT_ID /models/MODEL/versions/" prefix that the API returns in output; it is the bare version name, as provided to projects.models.versions.create.
Predict This property is required. string
HTTP path on the container to send prediction requests to. AI Platform Prediction forwards requests sent using projects.predict to this path on the container's IP address and port. AI Platform Prediction then returns the container's response in the API response. For example, if you set this field to /foo, then when AI Platform Prediction receives a prediction request, it forwards the request body in a POST request to the /foo path on the port of your container specified by the first value of Version.container.ports. If you don't specify this field, it defaults to the following value: /v1/models/MODEL/versions/VERSION:predict The placeholders in this value are replaced as follows: * MODEL: The name of the parent Model. This does not include the "projects/PROJECT_ID/models/" prefix that the API returns in output; it is the bare model name, as provided to projects.models.create. * VERSION: The name of the model version. This does not include the "projects/PROJECT_ID/models/MODEL/versions/" prefix that the API returns in output; it is the bare version name, as provided to projects.models.versions.create.
Health This property is required. string
HTTP path on the container to send health checkss to. AI Platform Prediction intermittently sends GET requests to this path on the container's IP address and port to check that the container is healthy. Read more about health checks. For example, if you set this field to /bar, then AI Platform Prediction intermittently sends a GET request to the /bar path on the port of your container specified by the first value of Version.container.ports. If you don't specify this field, it defaults to the following value: /v1/models/ MODEL/versions/VERSION The placeholders in this value are replaced as follows: * MODEL: The name of the parent Model. This does not include the "projects/PROJECT_ID/models/" prefix that the API returns in output; it is the bare model name, as provided to projects.models.create. * VERSION: The name of the model version. This does not include the "projects/PROJECT_ID /models/MODEL/versions/" prefix that the API returns in output; it is the bare version name, as provided to projects.models.versions.create.
Predict This property is required. string
HTTP path on the container to send prediction requests to. AI Platform Prediction forwards requests sent using projects.predict to this path on the container's IP address and port. AI Platform Prediction then returns the container's response in the API response. For example, if you set this field to /foo, then when AI Platform Prediction receives a prediction request, it forwards the request body in a POST request to the /foo path on the port of your container specified by the first value of Version.container.ports. If you don't specify this field, it defaults to the following value: /v1/models/MODEL/versions/VERSION:predict The placeholders in this value are replaced as follows: * MODEL: The name of the parent Model. This does not include the "projects/PROJECT_ID/models/" prefix that the API returns in output; it is the bare model name, as provided to projects.models.create. * VERSION: The name of the model version. This does not include the "projects/PROJECT_ID/models/MODEL/versions/" prefix that the API returns in output; it is the bare version name, as provided to projects.models.versions.create.
health This property is required. String
HTTP path on the container to send health checkss to. AI Platform Prediction intermittently sends GET requests to this path on the container's IP address and port to check that the container is healthy. Read more about health checks. For example, if you set this field to /bar, then AI Platform Prediction intermittently sends a GET request to the /bar path on the port of your container specified by the first value of Version.container.ports. If you don't specify this field, it defaults to the following value: /v1/models/ MODEL/versions/VERSION The placeholders in this value are replaced as follows: * MODEL: The name of the parent Model. This does not include the "projects/PROJECT_ID/models/" prefix that the API returns in output; it is the bare model name, as provided to projects.models.create. * VERSION: The name of the model version. This does not include the "projects/PROJECT_ID /models/MODEL/versions/" prefix that the API returns in output; it is the bare version name, as provided to projects.models.versions.create.
predict This property is required. String
HTTP path on the container to send prediction requests to. AI Platform Prediction forwards requests sent using projects.predict to this path on the container's IP address and port. AI Platform Prediction then returns the container's response in the API response. For example, if you set this field to /foo, then when AI Platform Prediction receives a prediction request, it forwards the request body in a POST request to the /foo path on the port of your container specified by the first value of Version.container.ports. If you don't specify this field, it defaults to the following value: /v1/models/MODEL/versions/VERSION:predict The placeholders in this value are replaced as follows: * MODEL: The name of the parent Model. This does not include the "projects/PROJECT_ID/models/" prefix that the API returns in output; it is the bare model name, as provided to projects.models.create. * VERSION: The name of the model version. This does not include the "projects/PROJECT_ID/models/MODEL/versions/" prefix that the API returns in output; it is the bare version name, as provided to projects.models.versions.create.
health This property is required. string
HTTP path on the container to send health checkss to. AI Platform Prediction intermittently sends GET requests to this path on the container's IP address and port to check that the container is healthy. Read more about health checks. For example, if you set this field to /bar, then AI Platform Prediction intermittently sends a GET request to the /bar path on the port of your container specified by the first value of Version.container.ports. If you don't specify this field, it defaults to the following value: /v1/models/ MODEL/versions/VERSION The placeholders in this value are replaced as follows: * MODEL: The name of the parent Model. This does not include the "projects/PROJECT_ID/models/" prefix that the API returns in output; it is the bare model name, as provided to projects.models.create. * VERSION: The name of the model version. This does not include the "projects/PROJECT_ID /models/MODEL/versions/" prefix that the API returns in output; it is the bare version name, as provided to projects.models.versions.create.
predict This property is required. string
HTTP path on the container to send prediction requests to. AI Platform Prediction forwards requests sent using projects.predict to this path on the container's IP address and port. AI Platform Prediction then returns the container's response in the API response. For example, if you set this field to /foo, then when AI Platform Prediction receives a prediction request, it forwards the request body in a POST request to the /foo path on the port of your container specified by the first value of Version.container.ports. If you don't specify this field, it defaults to the following value: /v1/models/MODEL/versions/VERSION:predict The placeholders in this value are replaced as follows: * MODEL: The name of the parent Model. This does not include the "projects/PROJECT_ID/models/" prefix that the API returns in output; it is the bare model name, as provided to projects.models.create. * VERSION: The name of the model version. This does not include the "projects/PROJECT_ID/models/MODEL/versions/" prefix that the API returns in output; it is the bare version name, as provided to projects.models.versions.create.
health This property is required. str
HTTP path on the container to send health checkss to. AI Platform Prediction intermittently sends GET requests to this path on the container's IP address and port to check that the container is healthy. Read more about health checks. For example, if you set this field to /bar, then AI Platform Prediction intermittently sends a GET request to the /bar path on the port of your container specified by the first value of Version.container.ports. If you don't specify this field, it defaults to the following value: /v1/models/ MODEL/versions/VERSION The placeholders in this value are replaced as follows: * MODEL: The name of the parent Model. This does not include the "projects/PROJECT_ID/models/" prefix that the API returns in output; it is the bare model name, as provided to projects.models.create. * VERSION: The name of the model version. This does not include the "projects/PROJECT_ID /models/MODEL/versions/" prefix that the API returns in output; it is the bare version name, as provided to projects.models.versions.create.
predict This property is required. str
HTTP path on the container to send prediction requests to. AI Platform Prediction forwards requests sent using projects.predict to this path on the container's IP address and port. AI Platform Prediction then returns the container's response in the API response. For example, if you set this field to /foo, then when AI Platform Prediction receives a prediction request, it forwards the request body in a POST request to the /foo path on the port of your container specified by the first value of Version.container.ports. If you don't specify this field, it defaults to the following value: /v1/models/MODEL/versions/VERSION:predict The placeholders in this value are replaced as follows: * MODEL: The name of the parent Model. This does not include the "projects/PROJECT_ID/models/" prefix that the API returns in output; it is the bare model name, as provided to projects.models.create. * VERSION: The name of the model version. This does not include the "projects/PROJECT_ID/models/MODEL/versions/" prefix that the API returns in output; it is the bare version name, as provided to projects.models.versions.create.
health This property is required. String
HTTP path on the container to send health checkss to. AI Platform Prediction intermittently sends GET requests to this path on the container's IP address and port to check that the container is healthy. Read more about health checks. For example, if you set this field to /bar, then AI Platform Prediction intermittently sends a GET request to the /bar path on the port of your container specified by the first value of Version.container.ports. If you don't specify this field, it defaults to the following value: /v1/models/ MODEL/versions/VERSION The placeholders in this value are replaced as follows: * MODEL: The name of the parent Model. This does not include the "projects/PROJECT_ID/models/" prefix that the API returns in output; it is the bare model name, as provided to projects.models.create. * VERSION: The name of the model version. This does not include the "projects/PROJECT_ID /models/MODEL/versions/" prefix that the API returns in output; it is the bare version name, as provided to projects.models.versions.create.
predict This property is required. String
HTTP path on the container to send prediction requests to. AI Platform Prediction forwards requests sent using projects.predict to this path on the container's IP address and port. AI Platform Prediction then returns the container's response in the API response. For example, if you set this field to /foo, then when AI Platform Prediction receives a prediction request, it forwards the request body in a POST request to the /foo path on the port of your container specified by the first value of Version.container.ports. If you don't specify this field, it defaults to the following value: /v1/models/MODEL/versions/VERSION:predict The placeholders in this value are replaced as follows: * MODEL: The name of the parent Model. This does not include the "projects/PROJECT_ID/models/" prefix that the API returns in output; it is the bare model name, as provided to projects.models.create. * VERSION: The name of the model version. This does not include the "projects/PROJECT_ID/models/MODEL/versions/" prefix that the API returns in output; it is the bare version name, as provided to projects.models.versions.create.

GoogleCloudMlV1__SampledShapleyAttribution
, GoogleCloudMlV1__SampledShapleyAttributionArgs

NumPaths int
The number of feature permutations to consider when approximating the Shapley values.
NumPaths int
The number of feature permutations to consider when approximating the Shapley values.
numPaths Integer
The number of feature permutations to consider when approximating the Shapley values.
numPaths number
The number of feature permutations to consider when approximating the Shapley values.
num_paths int
The number of feature permutations to consider when approximating the Shapley values.
numPaths Number
The number of feature permutations to consider when approximating the Shapley values.

GoogleCloudMlV1__SampledShapleyAttributionResponse
, GoogleCloudMlV1__SampledShapleyAttributionResponseArgs

NumPaths This property is required. int
The number of feature permutations to consider when approximating the Shapley values.
NumPaths This property is required. int
The number of feature permutations to consider when approximating the Shapley values.
numPaths This property is required. Integer
The number of feature permutations to consider when approximating the Shapley values.
numPaths This property is required. number
The number of feature permutations to consider when approximating the Shapley values.
num_paths This property is required. int
The number of feature permutations to consider when approximating the Shapley values.
numPaths This property is required. Number
The number of feature permutations to consider when approximating the Shapley values.

GoogleCloudMlV1__XraiAttribution
, GoogleCloudMlV1__XraiAttributionArgs

NumIntegralSteps int
Number of steps for approximating the path integral. A good value to start is 50 and gradually increase until the sum to diff property is met within the desired error range.
NumIntegralSteps int
Number of steps for approximating the path integral. A good value to start is 50 and gradually increase until the sum to diff property is met within the desired error range.
numIntegralSteps Integer
Number of steps for approximating the path integral. A good value to start is 50 and gradually increase until the sum to diff property is met within the desired error range.
numIntegralSteps number
Number of steps for approximating the path integral. A good value to start is 50 and gradually increase until the sum to diff property is met within the desired error range.
num_integral_steps int
Number of steps for approximating the path integral. A good value to start is 50 and gradually increase until the sum to diff property is met within the desired error range.
numIntegralSteps Number
Number of steps for approximating the path integral. A good value to start is 50 and gradually increase until the sum to diff property is met within the desired error range.

GoogleCloudMlV1__XraiAttributionResponse
, GoogleCloudMlV1__XraiAttributionResponseArgs

NumIntegralSteps This property is required. int
Number of steps for approximating the path integral. A good value to start is 50 and gradually increase until the sum to diff property is met within the desired error range.
NumIntegralSteps This property is required. int
Number of steps for approximating the path integral. A good value to start is 50 and gradually increase until the sum to diff property is met within the desired error range.
numIntegralSteps This property is required. Integer
Number of steps for approximating the path integral. A good value to start is 50 and gradually increase until the sum to diff property is met within the desired error range.
numIntegralSteps This property is required. number
Number of steps for approximating the path integral. A good value to start is 50 and gradually increase until the sum to diff property is met within the desired error range.
num_integral_steps This property is required. int
Number of steps for approximating the path integral. A good value to start is 50 and gradually increase until the sum to diff property is met within the desired error range.
numIntegralSteps This property is required. Number
Number of steps for approximating the path integral. A good value to start is 50 and gradually increase until the sum to diff property is met within the desired error range.

VersionFramework
, VersionFrameworkArgs

FrameworkUnspecified
FRAMEWORK_UNSPECIFIEDUnspecified framework. Assigns a value based on the file suffix.
Tensorflow
TENSORFLOWTensorflow framework.
ScikitLearn
SCIKIT_LEARNScikit-learn framework.
Xgboost
XGBOOSTXGBoost framework.
VersionFrameworkFrameworkUnspecified
FRAMEWORK_UNSPECIFIEDUnspecified framework. Assigns a value based on the file suffix.
VersionFrameworkTensorflow
TENSORFLOWTensorflow framework.
VersionFrameworkScikitLearn
SCIKIT_LEARNScikit-learn framework.
VersionFrameworkXgboost
XGBOOSTXGBoost framework.
FrameworkUnspecified
FRAMEWORK_UNSPECIFIEDUnspecified framework. Assigns a value based on the file suffix.
Tensorflow
TENSORFLOWTensorflow framework.
ScikitLearn
SCIKIT_LEARNScikit-learn framework.
Xgboost
XGBOOSTXGBoost framework.
FrameworkUnspecified
FRAMEWORK_UNSPECIFIEDUnspecified framework. Assigns a value based on the file suffix.
Tensorflow
TENSORFLOWTensorflow framework.
ScikitLearn
SCIKIT_LEARNScikit-learn framework.
Xgboost
XGBOOSTXGBoost framework.
FRAMEWORK_UNSPECIFIED
FRAMEWORK_UNSPECIFIEDUnspecified framework. Assigns a value based on the file suffix.
TENSORFLOW
TENSORFLOWTensorflow framework.
SCIKIT_LEARN
SCIKIT_LEARNScikit-learn framework.
XGBOOST
XGBOOSTXGBoost framework.
"FRAMEWORK_UNSPECIFIED"
FRAMEWORK_UNSPECIFIEDUnspecified framework. Assigns a value based on the file suffix.
"TENSORFLOW"
TENSORFLOWTensorflow framework.
"SCIKIT_LEARN"
SCIKIT_LEARNScikit-learn framework.
"XGBOOST"
XGBOOSTXGBoost framework.

Package Details

Repository
Google Cloud Native pulumi/pulumi-google-native
License
Apache-2.0

Google Cloud Native is in preview. Google Cloud Classic is fully supported.

Google Cloud Native v0.32.0 published on Wednesday, Nov 29, 2023 by Pulumi
pulumi/pulumi-google-native