Docs Packages
  1. Packages
  2. Google Cloud Native
  3. API Docs
  4. aiplatform
  5. aiplatform/v1
  6. Endpoint

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.aiplatform/v1.Endpoint

Explore with Pulumi AI

google-native logo

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 an Endpoint. Auto-naming is currently not supported for this resource.

    Create Endpoint Resource

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

    Constructor syntax

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

@overload
def Endpoint(resource_name: str,
             opts: Optional[ResourceOptions] = None,
             display_name: Optional[str] = None,
             description: Optional[str] = None,
             enable_private_service_connect: Optional[bool] = None,
             encryption_spec: Optional[GoogleCloudAiplatformV1EncryptionSpecArgs] = None,
             endpoint_id: Optional[str] = None,
             etag: Optional[str] = None,
             labels: Optional[Mapping[str, str]] = None,
             location: Optional[str] = None,
             network: Optional[str] = None,
             predict_request_response_logging_config: Optional[GoogleCloudAiplatformV1PredictRequestResponseLoggingConfigArgs] = None,
             project: Optional[str] = None,
             traffic_split: Optional[Mapping[str, str]] = None)
    func NewEndpoint(ctx *Context, name string, args EndpointArgs, opts ...ResourceOption) (*Endpoint, error)
    public Endpoint(string name, EndpointArgs args, CustomResourceOptions? opts = null)
    public Endpoint(String name, EndpointArgs args)
public Endpoint(String name, EndpointArgs args, CustomResourceOptions options)

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

    Parameters

    name string
    The unique name of the resource.
    args EndpointArgs
    The arguments to resource properties.
    opts CustomResourceOptions
    Bag of options to control resource's behavior.
    resource_name str
    The unique name of the resource.
    args EndpointArgs
    The arguments to resource properties.
    opts ResourceOptions
    Bag of options to control resource's behavior.
    ctx Context
    Context object for the current deployment.
    name string
    The unique name of the resource.
    args EndpointArgs
    The arguments to resource properties.
    opts ResourceOption
    Bag of options to control resource's behavior.
    name string
    The unique name of the resource.
    args EndpointArgs
    The arguments to resource properties.
    opts CustomResourceOptions
    Bag of options to control resource's behavior.
    name String
    The unique name of the resource.
    args EndpointArgs
    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 endpointResource = new GoogleNative.Aiplatform.V1.Endpoint("endpointResource", new()
{
    DisplayName = "string",
    Description = "string",
    EncryptionSpec = new GoogleNative.Aiplatform.V1.Inputs.GoogleCloudAiplatformV1EncryptionSpecArgs
    {
        KmsKeyName = "string",
    },
    EndpointId = "string",
    Etag = "string",
    Labels = 
    {
        { "string", "string" },
    },
    Location = "string",
    Network = "string",
    PredictRequestResponseLoggingConfig = new GoogleNative.Aiplatform.V1.Inputs.GoogleCloudAiplatformV1PredictRequestResponseLoggingConfigArgs
    {
        BigqueryDestination = new GoogleNative.Aiplatform.V1.Inputs.GoogleCloudAiplatformV1BigQueryDestinationArgs
        {
            OutputUri = "string",
        },
        Enabled = false,
        SamplingRate = 0,
    },
    Project = "string",
    TrafficSplit = 
    {
        { "string", "string" },
    },
});

    example, err := aiplatform.NewEndpoint(ctx, "endpointResource", &aiplatform.EndpointArgs{
DisplayName: pulumi.String("string"),
Description: pulumi.String("string"),
EncryptionSpec: &aiplatform.GoogleCloudAiplatformV1EncryptionSpecArgs{
KmsKeyName: pulumi.String("string"),
},
EndpointId: pulumi.String("string"),
Etag: pulumi.String("string"),
Labels: pulumi.StringMap{
"string": pulumi.String("string"),
},
Location: pulumi.String("string"),
Network: pulumi.String("string"),
PredictRequestResponseLoggingConfig: &aiplatform.GoogleCloudAiplatformV1PredictRequestResponseLoggingConfigArgs{
BigqueryDestination: &aiplatform.GoogleCloudAiplatformV1BigQueryDestinationArgs{
OutputUri: pulumi.String("string"),
},
Enabled: pulumi.Bool(false),
SamplingRate: pulumi.Float64(0),
},
Project: pulumi.String("string"),
TrafficSplit: pulumi.StringMap{
"string": pulumi.String("string"),
},
})

    var endpointResource = new Endpoint("endpointResource", EndpointArgs.builder()
    .displayName("string")
    .description("string")
    .encryptionSpec(GoogleCloudAiplatformV1EncryptionSpecArgs.builder()
        .kmsKeyName("string")
        .build())
    .endpointId("string")
    .etag("string")
    .labels(Map.of("string", "string"))
    .location("string")
    .network("string")
    .predictRequestResponseLoggingConfig(GoogleCloudAiplatformV1PredictRequestResponseLoggingConfigArgs.builder()
        .bigqueryDestination(GoogleCloudAiplatformV1BigQueryDestinationArgs.builder()
            .outputUri("string")
            .build())
        .enabled(false)
        .samplingRate(0)
        .build())
    .project("string")
    .trafficSplit(Map.of("string", "string"))
    .build());

    endpoint_resource = google_native.aiplatform.v1.Endpoint("endpointResource",
    display_name="string",
    description="string",
    encryption_spec=google_native.aiplatform.v1.GoogleCloudAiplatformV1EncryptionSpecArgs(
        kms_key_name="string",
    ),
    endpoint_id="string",
    etag="string",
    labels={
        "string": "string",
    },
    location="string",
    network="string",
    predict_request_response_logging_config=google_native.aiplatform.v1.GoogleCloudAiplatformV1PredictRequestResponseLoggingConfigArgs(
        bigquery_destination=google_native.aiplatform.v1.GoogleCloudAiplatformV1BigQueryDestinationArgs(
            output_uri="string",
        ),
        enabled=False,
        sampling_rate=0,
    ),
    project="string",
    traffic_split={
        "string": "string",
    })

    const endpointResource = new google_native.aiplatform.v1.Endpoint("endpointResource", {
    displayName: "string",
    description: "string",
    encryptionSpec: {
        kmsKeyName: "string",
    },
    endpointId: "string",
    etag: "string",
    labels: {
        string: "string",
    },
    location: "string",
    network: "string",
    predictRequestResponseLoggingConfig: {
        bigqueryDestination: {
            outputUri: "string",
        },
        enabled: false,
        samplingRate: 0,
    },
    project: "string",
    trafficSplit: {
        string: "string",
    },
});

    type: google-native:aiplatform/v1:Endpoint
properties:
    description: string
    displayName: string
    encryptionSpec:
        kmsKeyName: string
    endpointId: string
    etag: string
    labels:
        string: string
    location: string
    network: string
    predictRequestResponseLoggingConfig:
        bigqueryDestination:
            outputUri: string
        enabled: false
        samplingRate: 0
    project: string
    trafficSplit:
        string: string

    Endpoint Resource Properties

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

    Inputs

    The Endpoint resource accepts the following input properties:

    DisplayName string
    The display name of the Endpoint. The name can be up to 128 characters long and can consist of any UTF-8 characters.
    Description string
    The description of the Endpoint.
    EnablePrivateServiceConnect bool
    Deprecated: If true, expose the Endpoint via private service connect. Only one of the fields, network or enable_private_service_connect, can be set.

    Deprecated: Deprecated: If true, expose the Endpoint via private service connect. Only one of the fields, network or enable_private_service_connect, can be set.

    EncryptionSpec Pulumi.GoogleNative.Aiplatform.V1.Inputs.GoogleCloudAiplatformV1EncryptionSpec
    Customer-managed encryption key spec for an Endpoint. If set, this Endpoint and all sub-resources of this Endpoint will be secured by this key.
    EndpointId string
    Immutable. The ID to use for endpoint, which will become the final component of the endpoint resource name. If not provided, Vertex AI will generate a value for this ID. If the first character is a letter, this value may be up to 63 characters, and valid characters are [a-z0-9-]. The last character must be a letter or number. If the first character is a number, this value may be up to 9 characters, and valid characters are [0-9] with no leading zeros. When using HTTP/JSON, this field is populated based on a query string argument, such as ?endpoint_id=12345. This is the fallback for fields that are not included in either the URI or the body.
    Etag string
    Used to perform consistent read-modify-write updates. If not set, a blind "overwrite" update happens.
    Labels Dictionary<string, string>
    The labels with user-defined metadata to organize your Endpoints. Label keys and values can be no longer than 64 characters (Unicode codepoints), can only contain lowercase letters, numeric characters, underscores and dashes. International characters are allowed. See https://goo.gl/xmQnxf for more information and examples of labels.
    Location string
    Network string
    Optional. The full name of the Google Compute Engine network to which the Endpoint should be peered. Private services access must already be configured for the network. If left unspecified, the Endpoint is not peered with any network. Only one of the fields, network or enable_private_service_connect, can be set. Format: projects/{project}/global/networks/{network}. Where {project} is a project number, as in 12345, and {network} is network name.
    PredictRequestResponseLoggingConfig Pulumi.GoogleNative.Aiplatform.V1.Inputs.GoogleCloudAiplatformV1PredictRequestResponseLoggingConfig
    Configures the request-response logging for online prediction.
    Project string
    TrafficSplit Dictionary<string, string>
    A map from a DeployedModel's ID to the percentage of this Endpoint's traffic that should be forwarded to that DeployedModel. If a DeployedModel's ID is not listed in this map, then it receives no traffic. The traffic percentage values must add up to 100, or map must be empty if the Endpoint is to not accept any traffic at a moment.
    DisplayName string
    The display name of the Endpoint. The name can be up to 128 characters long and can consist of any UTF-8 characters.
    Description string
    The description of the Endpoint.
    EnablePrivateServiceConnect bool
    Deprecated: If true, expose the Endpoint via private service connect. Only one of the fields, network or enable_private_service_connect, can be set.

    Deprecated: Deprecated: If true, expose the Endpoint via private service connect. Only one of the fields, network or enable_private_service_connect, can be set.

    EncryptionSpec GoogleCloudAiplatformV1EncryptionSpecArgs
    Customer-managed encryption key spec for an Endpoint. If set, this Endpoint and all sub-resources of this Endpoint will be secured by this key.
    EndpointId string
    Immutable. The ID to use for endpoint, which will become the final component of the endpoint resource name. If not provided, Vertex AI will generate a value for this ID. If the first character is a letter, this value may be up to 63 characters, and valid characters are [a-z0-9-]. The last character must be a letter or number. If the first character is a number, this value may be up to 9 characters, and valid characters are [0-9] with no leading zeros. When using HTTP/JSON, this field is populated based on a query string argument, such as ?endpoint_id=12345. This is the fallback for fields that are not included in either the URI or the body.
    Etag string
    Used to perform consistent read-modify-write updates. If not set, a blind "overwrite" update happens.
    Labels map[string]string
    The labels with user-defined metadata to organize your Endpoints. Label keys and values can be no longer than 64 characters (Unicode codepoints), can only contain lowercase letters, numeric characters, underscores and dashes. International characters are allowed. See https://goo.gl/xmQnxf for more information and examples of labels.
    Location string
    Network string
    Optional. The full name of the Google Compute Engine network to which the Endpoint should be peered. Private services access must already be configured for the network. If left unspecified, the Endpoint is not peered with any network. Only one of the fields, network or enable_private_service_connect, can be set. Format: projects/{project}/global/networks/{network}. Where {project} is a project number, as in 12345, and {network} is network name.
    PredictRequestResponseLoggingConfig GoogleCloudAiplatformV1PredictRequestResponseLoggingConfigArgs
    Configures the request-response logging for online prediction.
    Project string
    TrafficSplit map[string]string
    A map from a DeployedModel's ID to the percentage of this Endpoint's traffic that should be forwarded to that DeployedModel. If a DeployedModel's ID is not listed in this map, then it receives no traffic. The traffic percentage values must add up to 100, or map must be empty if the Endpoint is to not accept any traffic at a moment.
    displayName String
    The display name of the Endpoint. The name can be up to 128 characters long and can consist of any UTF-8 characters.
    description String
    The description of the Endpoint.
    enablePrivateServiceConnect Boolean
    Deprecated: If true, expose the Endpoint via private service connect. Only one of the fields, network or enable_private_service_connect, can be set.

    Deprecated: Deprecated: If true, expose the Endpoint via private service connect. Only one of the fields, network or enable_private_service_connect, can be set.

    encryptionSpec GoogleCloudAiplatformV1EncryptionSpec
    Customer-managed encryption key spec for an Endpoint. If set, this Endpoint and all sub-resources of this Endpoint will be secured by this key.
    endpointId String
    Immutable. The ID to use for endpoint, which will become the final component of the endpoint resource name. If not provided, Vertex AI will generate a value for this ID. If the first character is a letter, this value may be up to 63 characters, and valid characters are [a-z0-9-]. The last character must be a letter or number. If the first character is a number, this value may be up to 9 characters, and valid characters are [0-9] with no leading zeros. When using HTTP/JSON, this field is populated based on a query string argument, such as ?endpoint_id=12345. This is the fallback for fields that are not included in either the URI or the body.
    etag String
    Used to perform consistent read-modify-write updates. If not set, a blind "overwrite" update happens.
    labels Map<String,String>
    The labels with user-defined metadata to organize your Endpoints. Label keys and values can be no longer than 64 characters (Unicode codepoints), can only contain lowercase letters, numeric characters, underscores and dashes. International characters are allowed. See https://goo.gl/xmQnxf for more information and examples of labels.
    location String
    network String
    Optional. The full name of the Google Compute Engine network to which the Endpoint should be peered. Private services access must already be configured for the network. If left unspecified, the Endpoint is not peered with any network. Only one of the fields, network or enable_private_service_connect, can be set. Format: projects/{project}/global/networks/{network}. Where {project} is a project number, as in 12345, and {network} is network name.
    predictRequestResponseLoggingConfig GoogleCloudAiplatformV1PredictRequestResponseLoggingConfig
    Configures the request-response logging for online prediction.
    project String
    trafficSplit Map<String,String>
    A map from a DeployedModel's ID to the percentage of this Endpoint's traffic that should be forwarded to that DeployedModel. If a DeployedModel's ID is not listed in this map, then it receives no traffic. The traffic percentage values must add up to 100, or map must be empty if the Endpoint is to not accept any traffic at a moment.
    displayName string
    The display name of the Endpoint. The name can be up to 128 characters long and can consist of any UTF-8 characters.
    description string
    The description of the Endpoint.
    enablePrivateServiceConnect boolean
    Deprecated: If true, expose the Endpoint via private service connect. Only one of the fields, network or enable_private_service_connect, can be set.

    Deprecated: Deprecated: If true, expose the Endpoint via private service connect. Only one of the fields, network or enable_private_service_connect, can be set.

    encryptionSpec GoogleCloudAiplatformV1EncryptionSpec
    Customer-managed encryption key spec for an Endpoint. If set, this Endpoint and all sub-resources of this Endpoint will be secured by this key.
    endpointId string
    Immutable. The ID to use for endpoint, which will become the final component of the endpoint resource name. If not provided, Vertex AI will generate a value for this ID. If the first character is a letter, this value may be up to 63 characters, and valid characters are [a-z0-9-]. The last character must be a letter or number. If the first character is a number, this value may be up to 9 characters, and valid characters are [0-9] with no leading zeros. When using HTTP/JSON, this field is populated based on a query string argument, such as ?endpoint_id=12345. This is the fallback for fields that are not included in either the URI or the body.
    etag string
    Used to perform consistent read-modify-write updates. If not set, a blind "overwrite" update happens.
    labels {[key: string]: string}
    The labels with user-defined metadata to organize your Endpoints. Label keys and values can be no longer than 64 characters (Unicode codepoints), can only contain lowercase letters, numeric characters, underscores and dashes. International characters are allowed. See https://goo.gl/xmQnxf for more information and examples of labels.
    location string
    network string
    Optional. The full name of the Google Compute Engine network to which the Endpoint should be peered. Private services access must already be configured for the network. If left unspecified, the Endpoint is not peered with any network. Only one of the fields, network or enable_private_service_connect, can be set. Format: projects/{project}/global/networks/{network}. Where {project} is a project number, as in 12345, and {network} is network name.
    predictRequestResponseLoggingConfig GoogleCloudAiplatformV1PredictRequestResponseLoggingConfig
    Configures the request-response logging for online prediction.
    project string
    trafficSplit {[key: string]: string}
    A map from a DeployedModel's ID to the percentage of this Endpoint's traffic that should be forwarded to that DeployedModel. If a DeployedModel's ID is not listed in this map, then it receives no traffic. The traffic percentage values must add up to 100, or map must be empty if the Endpoint is to not accept any traffic at a moment.
    display_name str
    The display name of the Endpoint. The name can be up to 128 characters long and can consist of any UTF-8 characters.
    description str
    The description of the Endpoint.
    enable_private_service_connect bool
    Deprecated: If true, expose the Endpoint via private service connect. Only one of the fields, network or enable_private_service_connect, can be set.

    Deprecated: Deprecated: If true, expose the Endpoint via private service connect. Only one of the fields, network or enable_private_service_connect, can be set.

    encryption_spec GoogleCloudAiplatformV1EncryptionSpecArgs
    Customer-managed encryption key spec for an Endpoint. If set, this Endpoint and all sub-resources of this Endpoint will be secured by this key.
    endpoint_id str
    Immutable. The ID to use for endpoint, which will become the final component of the endpoint resource name. If not provided, Vertex AI will generate a value for this ID. If the first character is a letter, this value may be up to 63 characters, and valid characters are [a-z0-9-]. The last character must be a letter or number. If the first character is a number, this value may be up to 9 characters, and valid characters are [0-9] with no leading zeros. When using HTTP/JSON, this field is populated based on a query string argument, such as ?endpoint_id=12345. This is the fallback for fields that are not included in either the URI or the body.
    etag str
    Used to perform consistent read-modify-write updates. If not set, a blind "overwrite" update happens.
    labels Mapping[str, str]
    The labels with user-defined metadata to organize your Endpoints. Label keys and values can be no longer than 64 characters (Unicode codepoints), can only contain lowercase letters, numeric characters, underscores and dashes. International characters are allowed. See https://goo.gl/xmQnxf for more information and examples of labels.
    location str
    network str
    Optional. The full name of the Google Compute Engine network to which the Endpoint should be peered. Private services access must already be configured for the network. If left unspecified, the Endpoint is not peered with any network. Only one of the fields, network or enable_private_service_connect, can be set. Format: projects/{project}/global/networks/{network}. Where {project} is a project number, as in 12345, and {network} is network name.
    predict_request_response_logging_config GoogleCloudAiplatformV1PredictRequestResponseLoggingConfigArgs
    Configures the request-response logging for online prediction.
    project str
    traffic_split Mapping[str, str]
    A map from a DeployedModel's ID to the percentage of this Endpoint's traffic that should be forwarded to that DeployedModel. If a DeployedModel's ID is not listed in this map, then it receives no traffic. The traffic percentage values must add up to 100, or map must be empty if the Endpoint is to not accept any traffic at a moment.
    displayName String
    The display name of the Endpoint. The name can be up to 128 characters long and can consist of any UTF-8 characters.
    description String
    The description of the Endpoint.
    enablePrivateServiceConnect Boolean
    Deprecated: If true, expose the Endpoint via private service connect. Only one of the fields, network or enable_private_service_connect, can be set.

    Deprecated: Deprecated: If true, expose the Endpoint via private service connect. Only one of the fields, network or enable_private_service_connect, can be set.

    encryptionSpec Property Map
    Customer-managed encryption key spec for an Endpoint. If set, this Endpoint and all sub-resources of this Endpoint will be secured by this key.
    endpointId String
    Immutable. The ID to use for endpoint, which will become the final component of the endpoint resource name. If not provided, Vertex AI will generate a value for this ID. If the first character is a letter, this value may be up to 63 characters, and valid characters are [a-z0-9-]. The last character must be a letter or number. If the first character is a number, this value may be up to 9 characters, and valid characters are [0-9] with no leading zeros. When using HTTP/JSON, this field is populated based on a query string argument, such as ?endpoint_id=12345. This is the fallback for fields that are not included in either the URI or the body.
    etag String
    Used to perform consistent read-modify-write updates. If not set, a blind "overwrite" update happens.
    labels Map<String>
    The labels with user-defined metadata to organize your Endpoints. Label keys and values can be no longer than 64 characters (Unicode codepoints), can only contain lowercase letters, numeric characters, underscores and dashes. International characters are allowed. See https://goo.gl/xmQnxf for more information and examples of labels.
    location String
    network String
    Optional. The full name of the Google Compute Engine network to which the Endpoint should be peered. Private services access must already be configured for the network. If left unspecified, the Endpoint is not peered with any network. Only one of the fields, network or enable_private_service_connect, can be set. Format: projects/{project}/global/networks/{network}. Where {project} is a project number, as in 12345, and {network} is network name.
    predictRequestResponseLoggingConfig Property Map
    Configures the request-response logging for online prediction.
    project String
    trafficSplit Map<String>
    A map from a DeployedModel's ID to the percentage of this Endpoint's traffic that should be forwarded to that DeployedModel. If a DeployedModel's ID is not listed in this map, then it receives no traffic. The traffic percentage values must add up to 100, or map must be empty if the Endpoint is to not accept any traffic at a moment.

    Outputs

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

    CreateTime string
    Timestamp when this Endpoint was created.
    DeployedModels List<Pulumi.GoogleNative.Aiplatform.V1.Outputs.GoogleCloudAiplatformV1DeployedModelResponse>
    The models deployed in this Endpoint. To add or remove DeployedModels use EndpointService.DeployModel and EndpointService.UndeployModel respectively.
    Id string
    The provider-assigned unique ID for this managed resource.
    ModelDeploymentMonitoringJob string
    Resource name of the Model Monitoring job associated with this Endpoint if monitoring is enabled by JobService.CreateModelDeploymentMonitoringJob. Format: projects/{project}/locations/{location}/modelDeploymentMonitoringJobs/{model_deployment_monitoring_job}
    Name string
    The resource name of the Endpoint.
    UpdateTime string
    Timestamp when this Endpoint was last updated.
    CreateTime string
    Timestamp when this Endpoint was created.
    DeployedModels []GoogleCloudAiplatformV1DeployedModelResponse
    The models deployed in this Endpoint. To add or remove DeployedModels use EndpointService.DeployModel and EndpointService.UndeployModel respectively.
    Id string
    The provider-assigned unique ID for this managed resource.
    ModelDeploymentMonitoringJob string
    Resource name of the Model Monitoring job associated with this Endpoint if monitoring is enabled by JobService.CreateModelDeploymentMonitoringJob. Format: projects/{project}/locations/{location}/modelDeploymentMonitoringJobs/{model_deployment_monitoring_job}
    Name string
    The resource name of the Endpoint.
    UpdateTime string
    Timestamp when this Endpoint was last updated.
    createTime String
    Timestamp when this Endpoint was created.
    deployedModels List<GoogleCloudAiplatformV1DeployedModelResponse>
    The models deployed in this Endpoint. To add or remove DeployedModels use EndpointService.DeployModel and EndpointService.UndeployModel respectively.
    id String
    The provider-assigned unique ID for this managed resource.
    modelDeploymentMonitoringJob String
    Resource name of the Model Monitoring job associated with this Endpoint if monitoring is enabled by JobService.CreateModelDeploymentMonitoringJob. Format: projects/{project}/locations/{location}/modelDeploymentMonitoringJobs/{model_deployment_monitoring_job}
    name String
    The resource name of the Endpoint.
    updateTime String
    Timestamp when this Endpoint was last updated.
    createTime string
    Timestamp when this Endpoint was created.
    deployedModels GoogleCloudAiplatformV1DeployedModelResponse[]
    The models deployed in this Endpoint. To add or remove DeployedModels use EndpointService.DeployModel and EndpointService.UndeployModel respectively.
    id string
    The provider-assigned unique ID for this managed resource.
    modelDeploymentMonitoringJob string
    Resource name of the Model Monitoring job associated with this Endpoint if monitoring is enabled by JobService.CreateModelDeploymentMonitoringJob. Format: projects/{project}/locations/{location}/modelDeploymentMonitoringJobs/{model_deployment_monitoring_job}
    name string
    The resource name of the Endpoint.
    updateTime string
    Timestamp when this Endpoint was last updated.
    create_time str
    Timestamp when this Endpoint was created.
    deployed_models Sequence[GoogleCloudAiplatformV1DeployedModelResponse]
    The models deployed in this Endpoint. To add or remove DeployedModels use EndpointService.DeployModel and EndpointService.UndeployModel respectively.
    id str
    The provider-assigned unique ID for this managed resource.
    model_deployment_monitoring_job str
    Resource name of the Model Monitoring job associated with this Endpoint if monitoring is enabled by JobService.CreateModelDeploymentMonitoringJob. Format: projects/{project}/locations/{location}/modelDeploymentMonitoringJobs/{model_deployment_monitoring_job}
    name str
    The resource name of the Endpoint.
    update_time str
    Timestamp when this Endpoint was last updated.
    createTime String
    Timestamp when this Endpoint was created.
    deployedModels List<Property Map>
    The models deployed in this Endpoint. To add or remove DeployedModels use EndpointService.DeployModel and EndpointService.UndeployModel respectively.
    id String
    The provider-assigned unique ID for this managed resource.
    modelDeploymentMonitoringJob String
    Resource name of the Model Monitoring job associated with this Endpoint if monitoring is enabled by JobService.CreateModelDeploymentMonitoringJob. Format: projects/{project}/locations/{location}/modelDeploymentMonitoringJobs/{model_deployment_monitoring_job}
    name String
    The resource name of the Endpoint.
    updateTime String
    Timestamp when this Endpoint was last updated.

    Supporting Types

    GoogleCloudAiplatformV1AutomaticResourcesResponse, GoogleCloudAiplatformV1AutomaticResourcesResponseArgs

    MaxReplicaCount int
    Immutable. The maximum number of replicas this DeployedModel may be deployed on when the traffic against it increases. If the requested value is too large, the deployment will error, but if deployment succeeds then the ability to scale the model to that many replicas is guaranteed (barring service outages). If traffic against the DeployedModel increases beyond what its replicas at maximum may handle, a portion of the traffic will be dropped. If this value is not provided, a no upper bound for scaling under heavy traffic will be assume, though Vertex AI may be unable to scale beyond certain replica number.
    MinReplicaCount int
    Immutable. The minimum number of replicas this DeployedModel will be always deployed on. If traffic against it increases, it may dynamically be deployed onto more replicas up to max_replica_count, and as traffic decreases, some of these extra replicas may be freed. If the requested value is too large, the deployment will error.
    MaxReplicaCount int
    Immutable. The maximum number of replicas this DeployedModel may be deployed on when the traffic against it increases. If the requested value is too large, the deployment will error, but if deployment succeeds then the ability to scale the model to that many replicas is guaranteed (barring service outages). If traffic against the DeployedModel increases beyond what its replicas at maximum may handle, a portion of the traffic will be dropped. If this value is not provided, a no upper bound for scaling under heavy traffic will be assume, though Vertex AI may be unable to scale beyond certain replica number.
    MinReplicaCount int
    Immutable. The minimum number of replicas this DeployedModel will be always deployed on. If traffic against it increases, it may dynamically be deployed onto more replicas up to max_replica_count, and as traffic decreases, some of these extra replicas may be freed. If the requested value is too large, the deployment will error.
    maxReplicaCount Integer
    Immutable. The maximum number of replicas this DeployedModel may be deployed on when the traffic against it increases. If the requested value is too large, the deployment will error, but if deployment succeeds then the ability to scale the model to that many replicas is guaranteed (barring service outages). If traffic against the DeployedModel increases beyond what its replicas at maximum may handle, a portion of the traffic will be dropped. If this value is not provided, a no upper bound for scaling under heavy traffic will be assume, though Vertex AI may be unable to scale beyond certain replica number.
    minReplicaCount Integer
    Immutable. The minimum number of replicas this DeployedModel will be always deployed on. If traffic against it increases, it may dynamically be deployed onto more replicas up to max_replica_count, and as traffic decreases, some of these extra replicas may be freed. If the requested value is too large, the deployment will error.
    maxReplicaCount number
    Immutable. The maximum number of replicas this DeployedModel may be deployed on when the traffic against it increases. If the requested value is too large, the deployment will error, but if deployment succeeds then the ability to scale the model to that many replicas is guaranteed (barring service outages). If traffic against the DeployedModel increases beyond what its replicas at maximum may handle, a portion of the traffic will be dropped. If this value is not provided, a no upper bound for scaling under heavy traffic will be assume, though Vertex AI may be unable to scale beyond certain replica number.
    minReplicaCount number
    Immutable. The minimum number of replicas this DeployedModel will be always deployed on. If traffic against it increases, it may dynamically be deployed onto more replicas up to max_replica_count, and as traffic decreases, some of these extra replicas may be freed. If the requested value is too large, the deployment will error.
    max_replica_count int
    Immutable. The maximum number of replicas this DeployedModel may be deployed on when the traffic against it increases. If the requested value is too large, the deployment will error, but if deployment succeeds then the ability to scale the model to that many replicas is guaranteed (barring service outages). If traffic against the DeployedModel increases beyond what its replicas at maximum may handle, a portion of the traffic will be dropped. If this value is not provided, a no upper bound for scaling under heavy traffic will be assume, though Vertex AI may be unable to scale beyond certain replica number.
    min_replica_count int
    Immutable. The minimum number of replicas this DeployedModel will be always deployed on. If traffic against it increases, it may dynamically be deployed onto more replicas up to max_replica_count, and as traffic decreases, some of these extra replicas may be freed. If the requested value is too large, the deployment will error.
    maxReplicaCount Number
    Immutable. The maximum number of replicas this DeployedModel may be deployed on when the traffic against it increases. If the requested value is too large, the deployment will error, but if deployment succeeds then the ability to scale the model to that many replicas is guaranteed (barring service outages). If traffic against the DeployedModel increases beyond what its replicas at maximum may handle, a portion of the traffic will be dropped. If this value is not provided, a no upper bound for scaling under heavy traffic will be assume, though Vertex AI may be unable to scale beyond certain replica number.
    minReplicaCount Number
    Immutable. The minimum number of replicas this DeployedModel will be always deployed on. If traffic against it increases, it may dynamically be deployed onto more replicas up to max_replica_count, and as traffic decreases, some of these extra replicas may be freed. If the requested value is too large, the deployment will error.

    GoogleCloudAiplatformV1AutoscalingMetricSpecResponse, GoogleCloudAiplatformV1AutoscalingMetricSpecResponseArgs

    MetricName string
    The resource metric name. Supported metrics: * For Online Prediction: * aiplatform.googleapis.com/prediction/online/accelerator/duty_cycle * aiplatform.googleapis.com/prediction/online/cpu/utilization
    Target int
    The target resource utilization in percentage (1% - 100%) for the given metric; once the real usage deviates from the target by a certain percentage, the machine replicas change. The default value is 60 (representing 60%) if not provided.
    MetricName string
    The resource metric name. Supported metrics: * For Online Prediction: * aiplatform.googleapis.com/prediction/online/accelerator/duty_cycle * aiplatform.googleapis.com/prediction/online/cpu/utilization
    Target int
    The target resource utilization in percentage (1% - 100%) for the given metric; once the real usage deviates from the target by a certain percentage, the machine replicas change. The default value is 60 (representing 60%) if not provided.
    metricName String
    The resource metric name. Supported metrics: * For Online Prediction: * aiplatform.googleapis.com/prediction/online/accelerator/duty_cycle * aiplatform.googleapis.com/prediction/online/cpu/utilization
    target Integer
    The target resource utilization in percentage (1% - 100%) for the given metric; once the real usage deviates from the target by a certain percentage, the machine replicas change. The default value is 60 (representing 60%) if not provided.
    metricName string
    The resource metric name. Supported metrics: * For Online Prediction: * aiplatform.googleapis.com/prediction/online/accelerator/duty_cycle * aiplatform.googleapis.com/prediction/online/cpu/utilization
    target number
    The target resource utilization in percentage (1% - 100%) for the given metric; once the real usage deviates from the target by a certain percentage, the machine replicas change. The default value is 60 (representing 60%) if not provided.
    metric_name str
    The resource metric name. Supported metrics: * For Online Prediction: * aiplatform.googleapis.com/prediction/online/accelerator/duty_cycle * aiplatform.googleapis.com/prediction/online/cpu/utilization
    target int
    The target resource utilization in percentage (1% - 100%) for the given metric; once the real usage deviates from the target by a certain percentage, the machine replicas change. The default value is 60 (representing 60%) if not provided.
    metricName String
    The resource metric name. Supported metrics: * For Online Prediction: * aiplatform.googleapis.com/prediction/online/accelerator/duty_cycle * aiplatform.googleapis.com/prediction/online/cpu/utilization
    target Number
    The target resource utilization in percentage (1% - 100%) for the given metric; once the real usage deviates from the target by a certain percentage, the machine replicas change. The default value is 60 (representing 60%) if not provided.

    GoogleCloudAiplatformV1BigQueryDestination, GoogleCloudAiplatformV1BigQueryDestinationArgs

    OutputUri string
    BigQuery URI to a project or table, up to 2000 characters long. When only the project is specified, the Dataset and Table is created. When the full table reference is specified, the Dataset must exist and table must not exist. Accepted forms: * BigQuery path. For example: bq://projectId or bq://projectId.bqDatasetId or bq://projectId.bqDatasetId.bqTableId.
    OutputUri string
    BigQuery URI to a project or table, up to 2000 characters long. When only the project is specified, the Dataset and Table is created. When the full table reference is specified, the Dataset must exist and table must not exist. Accepted forms: * BigQuery path. For example: bq://projectId or bq://projectId.bqDatasetId or bq://projectId.bqDatasetId.bqTableId.
    outputUri String
    BigQuery URI to a project or table, up to 2000 characters long. When only the project is specified, the Dataset and Table is created. When the full table reference is specified, the Dataset must exist and table must not exist. Accepted forms: * BigQuery path. For example: bq://projectId or bq://projectId.bqDatasetId or bq://projectId.bqDatasetId.bqTableId.
    outputUri string
    BigQuery URI to a project or table, up to 2000 characters long. When only the project is specified, the Dataset and Table is created. When the full table reference is specified, the Dataset must exist and table must not exist. Accepted forms: * BigQuery path. For example: bq://projectId or bq://projectId.bqDatasetId or bq://projectId.bqDatasetId.bqTableId.
    output_uri str
    BigQuery URI to a project or table, up to 2000 characters long. When only the project is specified, the Dataset and Table is created. When the full table reference is specified, the Dataset must exist and table must not exist. Accepted forms: * BigQuery path. For example: bq://projectId or bq://projectId.bqDatasetId or bq://projectId.bqDatasetId.bqTableId.
    outputUri String
    BigQuery URI to a project or table, up to 2000 characters long. When only the project is specified, the Dataset and Table is created. When the full table reference is specified, the Dataset must exist and table must not exist. Accepted forms: * BigQuery path. For example: bq://projectId or bq://projectId.bqDatasetId or bq://projectId.bqDatasetId.bqTableId.

    GoogleCloudAiplatformV1BigQueryDestinationResponse, GoogleCloudAiplatformV1BigQueryDestinationResponseArgs

    OutputUri string
    BigQuery URI to a project or table, up to 2000 characters long. When only the project is specified, the Dataset and Table is created. When the full table reference is specified, the Dataset must exist and table must not exist. Accepted forms: * BigQuery path. For example: bq://projectId or bq://projectId.bqDatasetId or bq://projectId.bqDatasetId.bqTableId.
    OutputUri string
    BigQuery URI to a project or table, up to 2000 characters long. When only the project is specified, the Dataset and Table is created. When the full table reference is specified, the Dataset must exist and table must not exist. Accepted forms: * BigQuery path. For example: bq://projectId or bq://projectId.bqDatasetId or bq://projectId.bqDatasetId.bqTableId.
    outputUri String
    BigQuery URI to a project or table, up to 2000 characters long. When only the project is specified, the Dataset and Table is created. When the full table reference is specified, the Dataset must exist and table must not exist. Accepted forms: * BigQuery path. For example: bq://projectId or bq://projectId.bqDatasetId or bq://projectId.bqDatasetId.bqTableId.
    outputUri string
    BigQuery URI to a project or table, up to 2000 characters long. When only the project is specified, the Dataset and Table is created. When the full table reference is specified, the Dataset must exist and table must not exist. Accepted forms: * BigQuery path. For example: bq://projectId or bq://projectId.bqDatasetId or bq://projectId.bqDatasetId.bqTableId.
    output_uri str
    BigQuery URI to a project or table, up to 2000 characters long. When only the project is specified, the Dataset and Table is created. When the full table reference is specified, the Dataset must exist and table must not exist. Accepted forms: * BigQuery path. For example: bq://projectId or bq://projectId.bqDatasetId or bq://projectId.bqDatasetId.bqTableId.
    outputUri String
    BigQuery URI to a project or table, up to 2000 characters long. When only the project is specified, the Dataset and Table is created. When the full table reference is specified, the Dataset must exist and table must not exist. Accepted forms: * BigQuery path. For example: bq://projectId or bq://projectId.bqDatasetId or bq://projectId.bqDatasetId.bqTableId.

    GoogleCloudAiplatformV1BlurBaselineConfigResponse, GoogleCloudAiplatformV1BlurBaselineConfigResponseArgs

    MaxBlurSigma double
    The standard deviation of the blur kernel for the blurred baseline. The same blurring parameter is used for both the height and the width dimension. If not set, the method defaults to the zero (i.e. black for images) baseline.
    MaxBlurSigma float64
    The standard deviation of the blur kernel for the blurred baseline. The same blurring parameter is used for both the height and the width dimension. If not set, the method defaults to the zero (i.e. black for images) baseline.
    maxBlurSigma Double
    The standard deviation of the blur kernel for the blurred baseline. The same blurring parameter is used for both the height and the width dimension. If not set, the method defaults to the zero (i.e. black for images) baseline.
    maxBlurSigma number
    The standard deviation of the blur kernel for the blurred baseline. The same blurring parameter is used for both the height and the width dimension. If not set, the method defaults to the zero (i.e. black for images) baseline.
    max_blur_sigma float
    The standard deviation of the blur kernel for the blurred baseline. The same blurring parameter is used for both the height and the width dimension. If not set, the method defaults to the zero (i.e. black for images) baseline.
    maxBlurSigma Number
    The standard deviation of the blur kernel for the blurred baseline. The same blurring parameter is used for both the height and the width dimension. If not set, the method defaults to the zero (i.e. black for images) baseline.

    GoogleCloudAiplatformV1DedicatedResourcesResponse, GoogleCloudAiplatformV1DedicatedResourcesResponseArgs

    AutoscalingMetricSpecs List<Pulumi.GoogleNative.Aiplatform.V1.Inputs.GoogleCloudAiplatformV1AutoscalingMetricSpecResponse>
    Immutable. The metric specifications that overrides a resource utilization metric (CPU utilization, accelerator's duty cycle, and so on) target value (default to 60 if not set). At most one entry is allowed per metric. If machine_spec.accelerator_count is above 0, the autoscaling will be based on both CPU utilization and accelerator's duty cycle metrics and scale up when either metrics exceeds its target value while scale down if both metrics are under their target value. The default target value is 60 for both metrics. If machine_spec.accelerator_count is 0, the autoscaling will be based on CPU utilization metric only with default target value 60 if not explicitly set. For example, in the case of Online Prediction, if you want to override target CPU utilization to 80, you should set autoscaling_metric_specs.metric_name to aiplatform.googleapis.com/prediction/online/cpu/utilization and autoscaling_metric_specs.target to 80.
    MachineSpec Pulumi.GoogleNative.Aiplatform.V1.Inputs.GoogleCloudAiplatformV1MachineSpecResponse
    Immutable. The specification of a single machine used by the prediction.
    MaxReplicaCount int
    Immutable. The maximum number of replicas this DeployedModel may be deployed on when the traffic against it increases. If the requested value is too large, the deployment will error, but if deployment succeeds then the ability to scale the model to that many replicas is guaranteed (barring service outages). If traffic against the DeployedModel increases beyond what its replicas at maximum may handle, a portion of the traffic will be dropped. If this value is not provided, will use min_replica_count as the default value. The value of this field impacts the charge against Vertex CPU and GPU quotas. Specifically, you will be charged for (max_replica_count * number of cores in the selected machine type) and (max_replica_count * number of GPUs per replica in the selected machine type).
    MinReplicaCount int
    Immutable. The minimum number of machine replicas this DeployedModel will be always deployed on. This value must be greater than or equal to 1. If traffic against the DeployedModel increases, it may dynamically be deployed onto more replicas, and as traffic decreases, some of these extra replicas may be freed.
    AutoscalingMetricSpecs []GoogleCloudAiplatformV1AutoscalingMetricSpecResponse
    Immutable. The metric specifications that overrides a resource utilization metric (CPU utilization, accelerator's duty cycle, and so on) target value (default to 60 if not set). At most one entry is allowed per metric. If machine_spec.accelerator_count is above 0, the autoscaling will be based on both CPU utilization and accelerator's duty cycle metrics and scale up when either metrics exceeds its target value while scale down if both metrics are under their target value. The default target value is 60 for both metrics. If machine_spec.accelerator_count is 0, the autoscaling will be based on CPU utilization metric only with default target value 60 if not explicitly set. For example, in the case of Online Prediction, if you want to override target CPU utilization to 80, you should set autoscaling_metric_specs.metric_name to aiplatform.googleapis.com/prediction/online/cpu/utilization and autoscaling_metric_specs.target to 80.
    MachineSpec GoogleCloudAiplatformV1MachineSpecResponse
    Immutable. The specification of a single machine used by the prediction.
    MaxReplicaCount int
    Immutable. The maximum number of replicas this DeployedModel may be deployed on when the traffic against it increases. If the requested value is too large, the deployment will error, but if deployment succeeds then the ability to scale the model to that many replicas is guaranteed (barring service outages). If traffic against the DeployedModel increases beyond what its replicas at maximum may handle, a portion of the traffic will be dropped. If this value is not provided, will use min_replica_count as the default value. The value of this field impacts the charge against Vertex CPU and GPU quotas. Specifically, you will be charged for (max_replica_count * number of cores in the selected machine type) and (max_replica_count * number of GPUs per replica in the selected machine type).
    MinReplicaCount int
    Immutable. The minimum number of machine replicas this DeployedModel will be always deployed on. This value must be greater than or equal to 1. If traffic against the DeployedModel increases, it may dynamically be deployed onto more replicas, and as traffic decreases, some of these extra replicas may be freed.
    autoscalingMetricSpecs List<GoogleCloudAiplatformV1AutoscalingMetricSpecResponse>
    Immutable. The metric specifications that overrides a resource utilization metric (CPU utilization, accelerator's duty cycle, and so on) target value (default to 60 if not set). At most one entry is allowed per metric. If machine_spec.accelerator_count is above 0, the autoscaling will be based on both CPU utilization and accelerator's duty cycle metrics and scale up when either metrics exceeds its target value while scale down if both metrics are under their target value. The default target value is 60 for both metrics. If machine_spec.accelerator_count is 0, the autoscaling will be based on CPU utilization metric only with default target value 60 if not explicitly set. For example, in the case of Online Prediction, if you want to override target CPU utilization to 80, you should set autoscaling_metric_specs.metric_name to aiplatform.googleapis.com/prediction/online/cpu/utilization and autoscaling_metric_specs.target to 80.
    machineSpec GoogleCloudAiplatformV1MachineSpecResponse
    Immutable. The specification of a single machine used by the prediction.
    maxReplicaCount Integer
    Immutable. The maximum number of replicas this DeployedModel may be deployed on when the traffic against it increases. If the requested value is too large, the deployment will error, but if deployment succeeds then the ability to scale the model to that many replicas is guaranteed (barring service outages). If traffic against the DeployedModel increases beyond what its replicas at maximum may handle, a portion of the traffic will be dropped. If this value is not provided, will use min_replica_count as the default value. The value of this field impacts the charge against Vertex CPU and GPU quotas. Specifically, you will be charged for (max_replica_count * number of cores in the selected machine type) and (max_replica_count * number of GPUs per replica in the selected machine type).
    minReplicaCount Integer
    Immutable. The minimum number of machine replicas this DeployedModel will be always deployed on. This value must be greater than or equal to 1. If traffic against the DeployedModel increases, it may dynamically be deployed onto more replicas, and as traffic decreases, some of these extra replicas may be freed.
    autoscalingMetricSpecs GoogleCloudAiplatformV1AutoscalingMetricSpecResponse[]
    Immutable. The metric specifications that overrides a resource utilization metric (CPU utilization, accelerator's duty cycle, and so on) target value (default to 60 if not set). At most one entry is allowed per metric. If machine_spec.accelerator_count is above 0, the autoscaling will be based on both CPU utilization and accelerator's duty cycle metrics and scale up when either metrics exceeds its target value while scale down if both metrics are under their target value. The default target value is 60 for both metrics. If machine_spec.accelerator_count is 0, the autoscaling will be based on CPU utilization metric only with default target value 60 if not explicitly set. For example, in the case of Online Prediction, if you want to override target CPU utilization to 80, you should set autoscaling_metric_specs.metric_name to aiplatform.googleapis.com/prediction/online/cpu/utilization and autoscaling_metric_specs.target to 80.
    machineSpec GoogleCloudAiplatformV1MachineSpecResponse
    Immutable. The specification of a single machine used by the prediction.
    maxReplicaCount number
    Immutable. The maximum number of replicas this DeployedModel may be deployed on when the traffic against it increases. If the requested value is too large, the deployment will error, but if deployment succeeds then the ability to scale the model to that many replicas is guaranteed (barring service outages). If traffic against the DeployedModel increases beyond what its replicas at maximum may handle, a portion of the traffic will be dropped. If this value is not provided, will use min_replica_count as the default value. The value of this field impacts the charge against Vertex CPU and GPU quotas. Specifically, you will be charged for (max_replica_count * number of cores in the selected machine type) and (max_replica_count * number of GPUs per replica in the selected machine type).
    minReplicaCount number
    Immutable. The minimum number of machine replicas this DeployedModel will be always deployed on. This value must be greater than or equal to 1. If traffic against the DeployedModel increases, it may dynamically be deployed onto more replicas, and as traffic decreases, some of these extra replicas may be freed.
    autoscaling_metric_specs Sequence[GoogleCloudAiplatformV1AutoscalingMetricSpecResponse]
    Immutable. The metric specifications that overrides a resource utilization metric (CPU utilization, accelerator's duty cycle, and so on) target value (default to 60 if not set). At most one entry is allowed per metric. If machine_spec.accelerator_count is above 0, the autoscaling will be based on both CPU utilization and accelerator's duty cycle metrics and scale up when either metrics exceeds its target value while scale down if both metrics are under their target value. The default target value is 60 for both metrics. If machine_spec.accelerator_count is 0, the autoscaling will be based on CPU utilization metric only with default target value 60 if not explicitly set. For example, in the case of Online Prediction, if you want to override target CPU utilization to 80, you should set autoscaling_metric_specs.metric_name to aiplatform.googleapis.com/prediction/online/cpu/utilization and autoscaling_metric_specs.target to 80.
    machine_spec GoogleCloudAiplatformV1MachineSpecResponse
    Immutable. The specification of a single machine used by the prediction.
    max_replica_count int
    Immutable. The maximum number of replicas this DeployedModel may be deployed on when the traffic against it increases. If the requested value is too large, the deployment will error, but if deployment succeeds then the ability to scale the model to that many replicas is guaranteed (barring service outages). If traffic against the DeployedModel increases beyond what its replicas at maximum may handle, a portion of the traffic will be dropped. If this value is not provided, will use min_replica_count as the default value. The value of this field impacts the charge against Vertex CPU and GPU quotas. Specifically, you will be charged for (max_replica_count * number of cores in the selected machine type) and (max_replica_count * number of GPUs per replica in the selected machine type).
    min_replica_count int
    Immutable. The minimum number of machine replicas this DeployedModel will be always deployed on. This value must be greater than or equal to 1. If traffic against the DeployedModel increases, it may dynamically be deployed onto more replicas, and as traffic decreases, some of these extra replicas may be freed.
    autoscalingMetricSpecs List<Property Map>
    Immutable. The metric specifications that overrides a resource utilization metric (CPU utilization, accelerator's duty cycle, and so on) target value (default to 60 if not set). At most one entry is allowed per metric. If machine_spec.accelerator_count is above 0, the autoscaling will be based on both CPU utilization and accelerator's duty cycle metrics and scale up when either metrics exceeds its target value while scale down if both metrics are under their target value. The default target value is 60 for both metrics. If machine_spec.accelerator_count is 0, the autoscaling will be based on CPU utilization metric only with default target value 60 if not explicitly set. For example, in the case of Online Prediction, if you want to override target CPU utilization to 80, you should set autoscaling_metric_specs.metric_name to aiplatform.googleapis.com/prediction/online/cpu/utilization and autoscaling_metric_specs.target to 80.
    machineSpec Property Map
    Immutable. The specification of a single machine used by the prediction.
    maxReplicaCount Number
    Immutable. The maximum number of replicas this DeployedModel may be deployed on when the traffic against it increases. If the requested value is too large, the deployment will error, but if deployment succeeds then the ability to scale the model to that many replicas is guaranteed (barring service outages). If traffic against the DeployedModel increases beyond what its replicas at maximum may handle, a portion of the traffic will be dropped. If this value is not provided, will use min_replica_count as the default value. The value of this field impacts the charge against Vertex CPU and GPU quotas. Specifically, you will be charged for (max_replica_count * number of cores in the selected machine type) and (max_replica_count * number of GPUs per replica in the selected machine type).
    minReplicaCount Number
    Immutable. The minimum number of machine replicas this DeployedModel will be always deployed on. This value must be greater than or equal to 1. If traffic against the DeployedModel increases, it may dynamically be deployed onto more replicas, and as traffic decreases, some of these extra replicas may be freed.

    GoogleCloudAiplatformV1DeployedModelResponse, GoogleCloudAiplatformV1DeployedModelResponseArgs

    AutomaticResources Pulumi.GoogleNative.Aiplatform.V1.Inputs.GoogleCloudAiplatformV1AutomaticResourcesResponse
    A description of resources that to large degree are decided by Vertex AI, and require only a modest additional configuration.
    CreateTime string
    Timestamp when the DeployedModel was created.
    DedicatedResources Pulumi.GoogleNative.Aiplatform.V1.Inputs.GoogleCloudAiplatformV1DedicatedResourcesResponse
    A description of resources that are dedicated to the DeployedModel, and that need a higher degree of manual configuration.
    DisableContainerLogging bool
    For custom-trained Models and AutoML Tabular Models, the container of the DeployedModel instances will send stderr and stdout streams to Cloud Logging by default. Please note that the logs incur cost, which are subject to Cloud Logging pricing. User can disable container logging by setting this flag to true.
    DisplayName string
    The display name of the DeployedModel. If not provided upon creation, the Model's display_name is used.
    EnableAccessLogging bool
    If true, online prediction access logs are sent to Cloud Logging. These logs are like standard server access logs, containing information like timestamp and latency for each prediction request. Note that logs may incur a cost, especially if your project receives prediction requests at a high queries per second rate (QPS). Estimate your costs before enabling this option.
    ExplanationSpec Pulumi.GoogleNative.Aiplatform.V1.Inputs.GoogleCloudAiplatformV1ExplanationSpecResponse
    Explanation configuration for this DeployedModel. When deploying a Model using EndpointService.DeployModel, this value overrides the value of Model.explanation_spec. All fields of explanation_spec are optional in the request. If a field of explanation_spec is not populated, the value of the same field of Model.explanation_spec is inherited. If the corresponding Model.explanation_spec is not populated, all fields of the explanation_spec will be used for the explanation configuration.
    Model string
    The resource name of the Model that this is the deployment of. Note that the Model may be in a different location than the DeployedModel's Endpoint. The resource name may contain version id or version alias to specify the version. Example: projects/{project}/locations/{location}/models/{model}@2 or projects/{project}/locations/{location}/models/{model}@golden if no version is specified, the default version will be deployed.
    ModelVersionId string
    The version ID of the model that is deployed.
    PrivateEndpoints Pulumi.GoogleNative.Aiplatform.V1.Inputs.GoogleCloudAiplatformV1PrivateEndpointsResponse
    Provide paths for users to send predict/explain/health requests directly to the deployed model services running on Cloud via private services access. This field is populated if network is configured.
    ServiceAccount string
    The service account that the DeployedModel's container runs as. Specify the email address of the service account. If this service account is not specified, the container runs as a service account that doesn't have access to the resource project. Users deploying the Model must have the iam.serviceAccounts.actAs permission on this service account.
    AutomaticResources GoogleCloudAiplatformV1AutomaticResourcesResponse
    A description of resources that to large degree are decided by Vertex AI, and require only a modest additional configuration.
    CreateTime string
    Timestamp when the DeployedModel was created.
    DedicatedResources GoogleCloudAiplatformV1DedicatedResourcesResponse
    A description of resources that are dedicated to the DeployedModel, and that need a higher degree of manual configuration.
    DisableContainerLogging bool
    For custom-trained Models and AutoML Tabular Models, the container of the DeployedModel instances will send stderr and stdout streams to Cloud Logging by default. Please note that the logs incur cost, which are subject to Cloud Logging pricing. User can disable container logging by setting this flag to true.
    DisplayName string
    The display name of the DeployedModel. If not provided upon creation, the Model's display_name is used.
    EnableAccessLogging bool
    If true, online prediction access logs are sent to Cloud Logging. These logs are like standard server access logs, containing information like timestamp and latency for each prediction request. Note that logs may incur a cost, especially if your project receives prediction requests at a high queries per second rate (QPS). Estimate your costs before enabling this option.
    ExplanationSpec GoogleCloudAiplatformV1ExplanationSpecResponse
    Explanation configuration for this DeployedModel. When deploying a Model using EndpointService.DeployModel, this value overrides the value of Model.explanation_spec. All fields of explanation_spec are optional in the request. If a field of explanation_spec is not populated, the value of the same field of Model.explanation_spec is inherited. If the corresponding Model.explanation_spec is not populated, all fields of the explanation_spec will be used for the explanation configuration.
    Model string
    The resource name of the Model that this is the deployment of. Note that the Model may be in a different location than the DeployedModel's Endpoint. The resource name may contain version id or version alias to specify the version. Example: projects/{project}/locations/{location}/models/{model}@2 or projects/{project}/locations/{location}/models/{model}@golden if no version is specified, the default version will be deployed.
    ModelVersionId string
    The version ID of the model that is deployed.
    PrivateEndpoints GoogleCloudAiplatformV1PrivateEndpointsResponse
    Provide paths for users to send predict/explain/health requests directly to the deployed model services running on Cloud via private services access. This field is populated if network is configured.
    ServiceAccount string
    The service account that the DeployedModel's container runs as. Specify the email address of the service account. If this service account is not specified, the container runs as a service account that doesn't have access to the resource project. Users deploying the Model must have the iam.serviceAccounts.actAs permission on this service account.
    automaticResources GoogleCloudAiplatformV1AutomaticResourcesResponse
    A description of resources that to large degree are decided by Vertex AI, and require only a modest additional configuration.
    createTime String
    Timestamp when the DeployedModel was created.
    dedicatedResources GoogleCloudAiplatformV1DedicatedResourcesResponse
    A description of resources that are dedicated to the DeployedModel, and that need a higher degree of manual configuration.
    disableContainerLogging Boolean
    For custom-trained Models and AutoML Tabular Models, the container of the DeployedModel instances will send stderr and stdout streams to Cloud Logging by default. Please note that the logs incur cost, which are subject to Cloud Logging pricing. User can disable container logging by setting this flag to true.
    displayName String
    The display name of the DeployedModel. If not provided upon creation, the Model's display_name is used.
    enableAccessLogging Boolean
    If true, online prediction access logs are sent to Cloud Logging. These logs are like standard server access logs, containing information like timestamp and latency for each prediction request. Note that logs may incur a cost, especially if your project receives prediction requests at a high queries per second rate (QPS). Estimate your costs before enabling this option.
    explanationSpec GoogleCloudAiplatformV1ExplanationSpecResponse
    Explanation configuration for this DeployedModel. When deploying a Model using EndpointService.DeployModel, this value overrides the value of Model.explanation_spec. All fields of explanation_spec are optional in the request. If a field of explanation_spec is not populated, the value of the same field of Model.explanation_spec is inherited. If the corresponding Model.explanation_spec is not populated, all fields of the explanation_spec will be used for the explanation configuration.
    model String
    The resource name of the Model that this is the deployment of. Note that the Model may be in a different location than the DeployedModel's Endpoint. The resource name may contain version id or version alias to specify the version. Example: projects/{project}/locations/{location}/models/{model}@2 or projects/{project}/locations/{location}/models/{model}@golden if no version is specified, the default version will be deployed.
    modelVersionId String
    The version ID of the model that is deployed.
    privateEndpoints GoogleCloudAiplatformV1PrivateEndpointsResponse
    Provide paths for users to send predict/explain/health requests directly to the deployed model services running on Cloud via private services access. This field is populated if network is configured.
    serviceAccount String
    The service account that the DeployedModel's container runs as. Specify the email address of the service account. If this service account is not specified, the container runs as a service account that doesn't have access to the resource project. Users deploying the Model must have the iam.serviceAccounts.actAs permission on this service account.
    automaticResources GoogleCloudAiplatformV1AutomaticResourcesResponse
    A description of resources that to large degree are decided by Vertex AI, and require only a modest additional configuration.
    createTime string
    Timestamp when the DeployedModel was created.
    dedicatedResources GoogleCloudAiplatformV1DedicatedResourcesResponse
    A description of resources that are dedicated to the DeployedModel, and that need a higher degree of manual configuration.
    disableContainerLogging boolean
    For custom-trained Models and AutoML Tabular Models, the container of the DeployedModel instances will send stderr and stdout streams to Cloud Logging by default. Please note that the logs incur cost, which are subject to Cloud Logging pricing. User can disable container logging by setting this flag to true.
    displayName string
    The display name of the DeployedModel. If not provided upon creation, the Model's display_name is used.
    enableAccessLogging boolean
    If true, online prediction access logs are sent to Cloud Logging. These logs are like standard server access logs, containing information like timestamp and latency for each prediction request. Note that logs may incur a cost, especially if your project receives prediction requests at a high queries per second rate (QPS). Estimate your costs before enabling this option.
    explanationSpec GoogleCloudAiplatformV1ExplanationSpecResponse
    Explanation configuration for this DeployedModel. When deploying a Model using EndpointService.DeployModel, this value overrides the value of Model.explanation_spec. All fields of explanation_spec are optional in the request. If a field of explanation_spec is not populated, the value of the same field of Model.explanation_spec is inherited. If the corresponding Model.explanation_spec is not populated, all fields of the explanation_spec will be used for the explanation configuration.
    model string
    The resource name of the Model that this is the deployment of. Note that the Model may be in a different location than the DeployedModel's Endpoint. The resource name may contain version id or version alias to specify the version. Example: projects/{project}/locations/{location}/models/{model}@2 or projects/{project}/locations/{location}/models/{model}@golden if no version is specified, the default version will be deployed.
    modelVersionId string
    The version ID of the model that is deployed.
    privateEndpoints GoogleCloudAiplatformV1PrivateEndpointsResponse
    Provide paths for users to send predict/explain/health requests directly to the deployed model services running on Cloud via private services access. This field is populated if network is configured.
    serviceAccount string
    The service account that the DeployedModel's container runs as. Specify the email address of the service account. If this service account is not specified, the container runs as a service account that doesn't have access to the resource project. Users deploying the Model must have the iam.serviceAccounts.actAs permission on this service account.
    automatic_resources GoogleCloudAiplatformV1AutomaticResourcesResponse
    A description of resources that to large degree are decided by Vertex AI, and require only a modest additional configuration.
    create_time str
    Timestamp when the DeployedModel was created.
    dedicated_resources GoogleCloudAiplatformV1DedicatedResourcesResponse
    A description of resources that are dedicated to the DeployedModel, and that need a higher degree of manual configuration.
    disable_container_logging bool
    For custom-trained Models and AutoML Tabular Models, the container of the DeployedModel instances will send stderr and stdout streams to Cloud Logging by default. Please note that the logs incur cost, which are subject to Cloud Logging pricing. User can disable container logging by setting this flag to true.
    display_name str
    The display name of the DeployedModel. If not provided upon creation, the Model's display_name is used.
    enable_access_logging bool
    If true, online prediction access logs are sent to Cloud Logging. These logs are like standard server access logs, containing information like timestamp and latency for each prediction request. Note that logs may incur a cost, especially if your project receives prediction requests at a high queries per second rate (QPS). Estimate your costs before enabling this option.
    explanation_spec GoogleCloudAiplatformV1ExplanationSpecResponse
    Explanation configuration for this DeployedModel. When deploying a Model using EndpointService.DeployModel, this value overrides the value of Model.explanation_spec. All fields of explanation_spec are optional in the request. If a field of explanation_spec is not populated, the value of the same field of Model.explanation_spec is inherited. If the corresponding Model.explanation_spec is not populated, all fields of the explanation_spec will be used for the explanation configuration.
    model str
    The resource name of the Model that this is the deployment of. Note that the Model may be in a different location than the DeployedModel's Endpoint. The resource name may contain version id or version alias to specify the version. Example: projects/{project}/locations/{location}/models/{model}@2 or projects/{project}/locations/{location}/models/{model}@golden if no version is specified, the default version will be deployed.
    model_version_id str
    The version ID of the model that is deployed.
    private_endpoints GoogleCloudAiplatformV1PrivateEndpointsResponse
    Provide paths for users to send predict/explain/health requests directly to the deployed model services running on Cloud via private services access. This field is populated if network is configured.
    service_account str
    The service account that the DeployedModel's container runs as. Specify the email address of the service account. If this service account is not specified, the container runs as a service account that doesn't have access to the resource project. Users deploying the Model must have the iam.serviceAccounts.actAs permission on this service account.
    automaticResources Property Map
    A description of resources that to large degree are decided by Vertex AI, and require only a modest additional configuration.
    createTime String
    Timestamp when the DeployedModel was created.
    dedicatedResources Property Map
    A description of resources that are dedicated to the DeployedModel, and that need a higher degree of manual configuration.
    disableContainerLogging Boolean
    For custom-trained Models and AutoML Tabular Models, the container of the DeployedModel instances will send stderr and stdout streams to Cloud Logging by default. Please note that the logs incur cost, which are subject to Cloud Logging pricing. User can disable container logging by setting this flag to true.
    displayName String
    The display name of the DeployedModel. If not provided upon creation, the Model's display_name is used.
    enableAccessLogging Boolean
    If true, online prediction access logs are sent to Cloud Logging. These logs are like standard server access logs, containing information like timestamp and latency for each prediction request. Note that logs may incur a cost, especially if your project receives prediction requests at a high queries per second rate (QPS). Estimate your costs before enabling this option.
    explanationSpec Property Map
    Explanation configuration for this DeployedModel. When deploying a Model using EndpointService.DeployModel, this value overrides the value of Model.explanation_spec. All fields of explanation_spec are optional in the request. If a field of explanation_spec is not populated, the value of the same field of Model.explanation_spec is inherited. If the corresponding Model.explanation_spec is not populated, all fields of the explanation_spec will be used for the explanation configuration.
    model String
    The resource name of the Model that this is the deployment of. Note that the Model may be in a different location than the DeployedModel's Endpoint. The resource name may contain version id or version alias to specify the version. Example: projects/{project}/locations/{location}/models/{model}@2 or projects/{project}/locations/{location}/models/{model}@golden if no version is specified, the default version will be deployed.
    modelVersionId String
    The version ID of the model that is deployed.
    privateEndpoints Property Map
    Provide paths for users to send predict/explain/health requests directly to the deployed model services running on Cloud via private services access. This field is populated if network is configured.
    serviceAccount String
    The service account that the DeployedModel's container runs as. Specify the email address of the service account. If this service account is not specified, the container runs as a service account that doesn't have access to the resource project. Users deploying the Model must have the iam.serviceAccounts.actAs permission on this service account.

    GoogleCloudAiplatformV1EncryptionSpec, GoogleCloudAiplatformV1EncryptionSpecArgs

    KmsKeyName string
    The Cloud KMS resource identifier of the customer managed encryption key used to protect a resource. Has the form: projects/my-project/locations/my-region/keyRings/my-kr/cryptoKeys/my-key. The key needs to be in the same region as where the compute resource is created.
    KmsKeyName string
    The Cloud KMS resource identifier of the customer managed encryption key used to protect a resource. Has the form: projects/my-project/locations/my-region/keyRings/my-kr/cryptoKeys/my-key. The key needs to be in the same region as where the compute resource is created.
    kmsKeyName String
    The Cloud KMS resource identifier of the customer managed encryption key used to protect a resource. Has the form: projects/my-project/locations/my-region/keyRings/my-kr/cryptoKeys/my-key. The key needs to be in the same region as where the compute resource is created.
    kmsKeyName string
    The Cloud KMS resource identifier of the customer managed encryption key used to protect a resource. Has the form: projects/my-project/locations/my-region/keyRings/my-kr/cryptoKeys/my-key. The key needs to be in the same region as where the compute resource is created.
    kms_key_name str
    The Cloud KMS resource identifier of the customer managed encryption key used to protect a resource. Has the form: projects/my-project/locations/my-region/keyRings/my-kr/cryptoKeys/my-key. The key needs to be in the same region as where the compute resource is created.
    kmsKeyName String
    The Cloud KMS resource identifier of the customer managed encryption key used to protect a resource. Has the form: projects/my-project/locations/my-region/keyRings/my-kr/cryptoKeys/my-key. The key needs to be in the same region as where the compute resource is created.

    GoogleCloudAiplatformV1EncryptionSpecResponse, GoogleCloudAiplatformV1EncryptionSpecResponseArgs

    KmsKeyName string
    The Cloud KMS resource identifier of the customer managed encryption key used to protect a resource. Has the form: projects/my-project/locations/my-region/keyRings/my-kr/cryptoKeys/my-key. The key needs to be in the same region as where the compute resource is created.
    KmsKeyName string
    The Cloud KMS resource identifier of the customer managed encryption key used to protect a resource. Has the form: projects/my-project/locations/my-region/keyRings/my-kr/cryptoKeys/my-key. The key needs to be in the same region as where the compute resource is created.
    kmsKeyName String
    The Cloud KMS resource identifier of the customer managed encryption key used to protect a resource. Has the form: projects/my-project/locations/my-region/keyRings/my-kr/cryptoKeys/my-key. The key needs to be in the same region as where the compute resource is created.
    kmsKeyName string
    The Cloud KMS resource identifier of the customer managed encryption key used to protect a resource. Has the form: projects/my-project/locations/my-region/keyRings/my-kr/cryptoKeys/my-key. The key needs to be in the same region as where the compute resource is created.
    kms_key_name str
    The Cloud KMS resource identifier of the customer managed encryption key used to protect a resource. Has the form: projects/my-project/locations/my-region/keyRings/my-kr/cryptoKeys/my-key. The key needs to be in the same region as where the compute resource is created.
    kmsKeyName String
    The Cloud KMS resource identifier of the customer managed encryption key used to protect a resource. Has the form: projects/my-project/locations/my-region/keyRings/my-kr/cryptoKeys/my-key. The key needs to be in the same region as where the compute resource is created.

    GoogleCloudAiplatformV1ExamplesExampleGcsSourceResponse, GoogleCloudAiplatformV1ExamplesExampleGcsSourceResponseArgs

    DataFormat string
    The format in which instances are given, if not specified, assume it's JSONL format. Currently only JSONL format is supported.
    GcsSource Pulumi.GoogleNative.Aiplatform.V1.Inputs.GoogleCloudAiplatformV1GcsSourceResponse
    The Cloud Storage location for the input instances.
    DataFormat string
    The format in which instances are given, if not specified, assume it's JSONL format. Currently only JSONL format is supported.
    GcsSource GoogleCloudAiplatformV1GcsSourceResponse
    The Cloud Storage location for the input instances.
    dataFormat String
    The format in which instances are given, if not specified, assume it's JSONL format. Currently only JSONL format is supported.
    gcsSource GoogleCloudAiplatformV1GcsSourceResponse
    The Cloud Storage location for the input instances.
    dataFormat string
    The format in which instances are given, if not specified, assume it's JSONL format. Currently only JSONL format is supported.
    gcsSource GoogleCloudAiplatformV1GcsSourceResponse
    The Cloud Storage location for the input instances.
    data_format str
    The format in which instances are given, if not specified, assume it's JSONL format. Currently only JSONL format is supported.
    gcs_source GoogleCloudAiplatformV1GcsSourceResponse
    The Cloud Storage location for the input instances.
    dataFormat String
    The format in which instances are given, if not specified, assume it's JSONL format. Currently only JSONL format is supported.
    gcsSource Property Map
    The Cloud Storage location for the input instances.

    GoogleCloudAiplatformV1ExamplesResponse, GoogleCloudAiplatformV1ExamplesResponseArgs

    ExampleGcsSource Pulumi.GoogleNative.Aiplatform.V1.Inputs.GoogleCloudAiplatformV1ExamplesExampleGcsSourceResponse
    The Cloud Storage input instances.
    NearestNeighborSearchConfig object
    The full configuration for the generated index, the semantics are the same as metadata and should match NearestNeighborSearchConfig.
    NeighborCount int
    The number of neighbors to return when querying for examples.
    Presets Pulumi.GoogleNative.Aiplatform.V1.Inputs.GoogleCloudAiplatformV1PresetsResponse
    Simplified preset configuration, which automatically sets configuration values based on the desired query speed-precision trade-off and modality.
    ExampleGcsSource GoogleCloudAiplatformV1ExamplesExampleGcsSourceResponse
    The Cloud Storage input instances.
    NearestNeighborSearchConfig interface{}
    The full configuration for the generated index, the semantics are the same as metadata and should match NearestNeighborSearchConfig.
    NeighborCount int
    The number of neighbors to return when querying for examples.
    Presets GoogleCloudAiplatformV1PresetsResponse
    Simplified preset configuration, which automatically sets configuration values based on the desired query speed-precision trade-off and modality.
    exampleGcsSource GoogleCloudAiplatformV1ExamplesExampleGcsSourceResponse
    The Cloud Storage input instances.
    nearestNeighborSearchConfig Object
    The full configuration for the generated index, the semantics are the same as metadata and should match NearestNeighborSearchConfig.
    neighborCount Integer
    The number of neighbors to return when querying for examples.
    presets GoogleCloudAiplatformV1PresetsResponse
    Simplified preset configuration, which automatically sets configuration values based on the desired query speed-precision trade-off and modality.
    exampleGcsSource GoogleCloudAiplatformV1ExamplesExampleGcsSourceResponse
    The Cloud Storage input instances.
    nearestNeighborSearchConfig any
    The full configuration for the generated index, the semantics are the same as metadata and should match NearestNeighborSearchConfig.
    neighborCount number
    The number of neighbors to return when querying for examples.
    presets GoogleCloudAiplatformV1PresetsResponse
    Simplified preset configuration, which automatically sets configuration values based on the desired query speed-precision trade-off and modality.
    example_gcs_source GoogleCloudAiplatformV1ExamplesExampleGcsSourceResponse
    The Cloud Storage input instances.
    nearest_neighbor_search_config Any
    The full configuration for the generated index, the semantics are the same as metadata and should match NearestNeighborSearchConfig.
    neighbor_count int
    The number of neighbors to return when querying for examples.
    presets GoogleCloudAiplatformV1PresetsResponse
    Simplified preset configuration, which automatically sets configuration values based on the desired query speed-precision trade-off and modality.
    exampleGcsSource Property Map
    The Cloud Storage input instances.
    nearestNeighborSearchConfig Any
    The full configuration for the generated index, the semantics are the same as metadata and should match NearestNeighborSearchConfig.
    neighborCount Number
    The number of neighbors to return when querying for examples.
    presets Property Map
    Simplified preset configuration, which automatically sets configuration values based on the desired query speed-precision trade-off and modality.

    GoogleCloudAiplatformV1ExplanationMetadataResponse, GoogleCloudAiplatformV1ExplanationMetadataResponseArgs

    FeatureAttributionsSchemaUri string
    Points to a YAML file stored on Google Cloud Storage describing the format of the feature attributions. The schema is defined as an OpenAPI 3.0.2 Schema Object. AutoML tabular Models always have this field populated by Vertex AI. Note: The URI given on output may be different, including the URI scheme, than the one given on input. The output URI will point to a location where the user only has a read access.
    Inputs Dictionary<string, string>
    Map from feature names to feature input metadata. Keys are the name of the features. Values are the specification of the feature. An empty InputMetadata is valid. It describes a text feature which has the name specified as the key in ExplanationMetadata.inputs. The baseline of the empty feature is chosen by Vertex AI. For Vertex AI-provided Tensorflow images, the key can be any friendly name of the feature. Once specified, featureAttributions are keyed by this key (if not grouped with another feature). For custom images, the key must match with the key in instance.
    LatentSpaceSource string
    Name of the source to generate embeddings for example based explanations.
    Outputs Dictionary<string, string>
    Map from output names to output metadata. For Vertex AI-provided Tensorflow images, keys can be any user defined string that consists of any UTF-8 characters. For custom images, keys are the name of the output field in the prediction to be explained. Currently only one key is allowed.
    FeatureAttributionsSchemaUri string
    Points to a YAML file stored on Google Cloud Storage describing the format of the feature attributions. The schema is defined as an OpenAPI 3.0.2 Schema Object. AutoML tabular Models always have this field populated by Vertex AI. Note: The URI given on output may be different, including the URI scheme, than the one given on input. The output URI will point to a location where the user only has a read access.
    Inputs map[string]string
    Map from feature names to feature input metadata. Keys are the name of the features. Values are the specification of the feature. An empty InputMetadata is valid. It describes a text feature which has the name specified as the key in ExplanationMetadata.inputs. The baseline of the empty feature is chosen by Vertex AI. For Vertex AI-provided Tensorflow images, the key can be any friendly name of the feature. Once specified, featureAttributions are keyed by this key (if not grouped with another feature). For custom images, the key must match with the key in instance.
    LatentSpaceSource string
    Name of the source to generate embeddings for example based explanations.
    Outputs map[string]string
    Map from output names to output metadata. For Vertex AI-provided Tensorflow images, keys can be any user defined string that consists of any UTF-8 characters. For custom images, keys are the name of the output field in the prediction to be explained. Currently only one key is allowed.
    featureAttributionsSchemaUri String
    Points to a YAML file stored on Google Cloud Storage describing the format of the feature attributions. The schema is defined as an OpenAPI 3.0.2 Schema Object. AutoML tabular Models always have this field populated by Vertex AI. Note: The URI given on output may be different, including the URI scheme, than the one given on input. The output URI will point to a location where the user only has a read access.
    inputs Map<String,String>
    Map from feature names to feature input metadata. Keys are the name of the features. Values are the specification of the feature. An empty InputMetadata is valid. It describes a text feature which has the name specified as the key in ExplanationMetadata.inputs. The baseline of the empty feature is chosen by Vertex AI. For Vertex AI-provided Tensorflow images, the key can be any friendly name of the feature. Once specified, featureAttributions are keyed by this key (if not grouped with another feature). For custom images, the key must match with the key in instance.
    latentSpaceSource String
    Name of the source to generate embeddings for example based explanations.
    outputs Map<String,String>
    Map from output names to output metadata. For Vertex AI-provided Tensorflow images, keys can be any user defined string that consists of any UTF-8 characters. For custom images, keys are the name of the output field in the prediction to be explained. Currently only one key is allowed.
    featureAttributionsSchemaUri string
    Points to a YAML file stored on Google Cloud Storage describing the format of the feature attributions. The schema is defined as an OpenAPI 3.0.2 Schema Object. AutoML tabular Models always have this field populated by Vertex AI. Note: The URI given on output may be different, including the URI scheme, than the one given on input. The output URI will point to a location where the user only has a read access.
    inputs {[key: string]: string}
    Map from feature names to feature input metadata. Keys are the name of the features. Values are the specification of the feature. An empty InputMetadata is valid. It describes a text feature which has the name specified as the key in ExplanationMetadata.inputs. The baseline of the empty feature is chosen by Vertex AI. For Vertex AI-provided Tensorflow images, the key can be any friendly name of the feature. Once specified, featureAttributions are keyed by this key (if not grouped with another feature). For custom images, the key must match with the key in instance.
    latentSpaceSource string
    Name of the source to generate embeddings for example based explanations.
    outputs {[key: string]: string}
    Map from output names to output metadata. For Vertex AI-provided Tensorflow images, keys can be any user defined string that consists of any UTF-8 characters. For custom images, keys are the name of the output field in the prediction to be explained. Currently only one key is allowed.
    feature_attributions_schema_uri str
    Points to a YAML file stored on Google Cloud Storage describing the format of the feature attributions. The schema is defined as an OpenAPI 3.0.2 Schema Object. AutoML tabular Models always have this field populated by Vertex AI. Note: The URI given on output may be different, including the URI scheme, than the one given on input. The output URI will point to a location where the user only has a read access.
    inputs Mapping[str, str]
    Map from feature names to feature input metadata. Keys are the name of the features. Values are the specification of the feature. An empty InputMetadata is valid. It describes a text feature which has the name specified as the key in ExplanationMetadata.inputs. The baseline of the empty feature is chosen by Vertex AI. For Vertex AI-provided Tensorflow images, the key can be any friendly name of the feature. Once specified, featureAttributions are keyed by this key (if not grouped with another feature). For custom images, the key must match with the key in instance.
    latent_space_source str
    Name of the source to generate embeddings for example based explanations.
    outputs Mapping[str, str]
    Map from output names to output metadata. For Vertex AI-provided Tensorflow images, keys can be any user defined string that consists of any UTF-8 characters. For custom images, keys are the name of the output field in the prediction to be explained. Currently only one key is allowed.
    featureAttributionsSchemaUri String
    Points to a YAML file stored on Google Cloud Storage describing the format of the feature attributions. The schema is defined as an OpenAPI 3.0.2 Schema Object. AutoML tabular Models always have this field populated by Vertex AI. Note: The URI given on output may be different, including the URI scheme, than the one given on input. The output URI will point to a location where the user only has a read access.
    inputs Map<String>
    Map from feature names to feature input metadata. Keys are the name of the features. Values are the specification of the feature. An empty InputMetadata is valid. It describes a text feature which has the name specified as the key in ExplanationMetadata.inputs. The baseline of the empty feature is chosen by Vertex AI. For Vertex AI-provided Tensorflow images, the key can be any friendly name of the feature. Once specified, featureAttributions are keyed by this key (if not grouped with another feature). For custom images, the key must match with the key in instance.
    latentSpaceSource String
    Name of the source to generate embeddings for example based explanations.
    outputs Map<String>
    Map from output names to output metadata. For Vertex AI-provided Tensorflow images, keys can be any user defined string that consists of any UTF-8 characters. For custom images, keys are the name of the output field in the prediction to be explained. Currently only one key is allowed.

    GoogleCloudAiplatformV1ExplanationParametersResponse, GoogleCloudAiplatformV1ExplanationParametersResponseArgs

    Examples Pulumi.GoogleNative.Aiplatform.V1.Inputs.GoogleCloudAiplatformV1ExamplesResponse
    Example-based explanations that returns the nearest neighbors from the provided dataset.
    IntegratedGradientsAttribution Pulumi.GoogleNative.Aiplatform.V1.Inputs.GoogleCloudAiplatformV1IntegratedGradientsAttributionResponse
    An attribution method that computes Aumann-Shapley values taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1703.01365
    OutputIndices List<object>
    If populated, only returns attributions that have output_index contained in output_indices. It must be an ndarray of integers, with the same shape of the output it's explaining. If not populated, returns attributions for top_k indices of outputs. If neither top_k nor output_indices is populated, returns the argmax index of the outputs. Only applicable to Models that predict multiple outputs (e,g, multi-class Models that predict multiple classes).
    SampledShapleyAttribution Pulumi.GoogleNative.Aiplatform.V1.Inputs.GoogleCloudAiplatformV1SampledShapleyAttributionResponse
    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. Refer to this paper for model details: https://arxiv.org/abs/1306.4265.
    TopK int
    If populated, returns attributions for top K indices of outputs (defaults to 1). Only applies to Models that predicts more than one outputs (e,g, multi-class Models). When set to -1, returns explanations for all outputs.
    XraiAttribution Pulumi.GoogleNative.Aiplatform.V1.Inputs.GoogleCloudAiplatformV1XraiAttributionResponse
    An attribution method that redistributes Integrated Gradients attribution to segmented regions, taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1906.02825 XRAI currently performs better on natural images, like a picture of a house or an animal. If the images are taken in artificial environments, like a lab or manufacturing line, or from diagnostic equipment, like x-rays or quality-control cameras, use Integrated Gradients instead.
    Examples GoogleCloudAiplatformV1ExamplesResponse
    Example-based explanations that returns the nearest neighbors from the provided dataset.
    IntegratedGradientsAttribution GoogleCloudAiplatformV1IntegratedGradientsAttributionResponse
    An attribution method that computes Aumann-Shapley values taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1703.01365
    OutputIndices []interface{}
    If populated, only returns attributions that have output_index contained in output_indices. It must be an ndarray of integers, with the same shape of the output it's explaining. If not populated, returns attributions for top_k indices of outputs. If neither top_k nor output_indices is populated, returns the argmax index of the outputs. Only applicable to Models that predict multiple outputs (e,g, multi-class Models that predict multiple classes).
    SampledShapleyAttribution GoogleCloudAiplatformV1SampledShapleyAttributionResponse
    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. Refer to this paper for model details: https://arxiv.org/abs/1306.4265.
    TopK int
    If populated, returns attributions for top K indices of outputs (defaults to 1). Only applies to Models that predicts more than one outputs (e,g, multi-class Models). When set to -1, returns explanations for all outputs.
    XraiAttribution GoogleCloudAiplatformV1XraiAttributionResponse
    An attribution method that redistributes Integrated Gradients attribution to segmented regions, taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1906.02825 XRAI currently performs better on natural images, like a picture of a house or an animal. If the images are taken in artificial environments, like a lab or manufacturing line, or from diagnostic equipment, like x-rays or quality-control cameras, use Integrated Gradients instead.
    examples GoogleCloudAiplatformV1ExamplesResponse
    Example-based explanations that returns the nearest neighbors from the provided dataset.
    integratedGradientsAttribution GoogleCloudAiplatformV1IntegratedGradientsAttributionResponse
    An attribution method that computes Aumann-Shapley values taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1703.01365
    outputIndices List<Object>
    If populated, only returns attributions that have output_index contained in output_indices. It must be an ndarray of integers, with the same shape of the output it's explaining. If not populated, returns attributions for top_k indices of outputs. If neither top_k nor output_indices is populated, returns the argmax index of the outputs. Only applicable to Models that predict multiple outputs (e,g, multi-class Models that predict multiple classes).
    sampledShapleyAttribution GoogleCloudAiplatformV1SampledShapleyAttributionResponse
    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. Refer to this paper for model details: https://arxiv.org/abs/1306.4265.
    topK Integer
    If populated, returns attributions for top K indices of outputs (defaults to 1). Only applies to Models that predicts more than one outputs (e,g, multi-class Models). When set to -1, returns explanations for all outputs.
    xraiAttribution GoogleCloudAiplatformV1XraiAttributionResponse
    An attribution method that redistributes Integrated Gradients attribution to segmented regions, taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1906.02825 XRAI currently performs better on natural images, like a picture of a house or an animal. If the images are taken in artificial environments, like a lab or manufacturing line, or from diagnostic equipment, like x-rays or quality-control cameras, use Integrated Gradients instead.
    examples GoogleCloudAiplatformV1ExamplesResponse
    Example-based explanations that returns the nearest neighbors from the provided dataset.
    integratedGradientsAttribution GoogleCloudAiplatformV1IntegratedGradientsAttributionResponse
    An attribution method that computes Aumann-Shapley values taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1703.01365
    outputIndices any[]
    If populated, only returns attributions that have output_index contained in output_indices. It must be an ndarray of integers, with the same shape of the output it's explaining. If not populated, returns attributions for top_k indices of outputs. If neither top_k nor output_indices is populated, returns the argmax index of the outputs. Only applicable to Models that predict multiple outputs (e,g, multi-class Models that predict multiple classes).
    sampledShapleyAttribution GoogleCloudAiplatformV1SampledShapleyAttributionResponse
    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. Refer to this paper for model details: https://arxiv.org/abs/1306.4265.
    topK number
    If populated, returns attributions for top K indices of outputs (defaults to 1). Only applies to Models that predicts more than one outputs (e,g, multi-class Models). When set to -1, returns explanations for all outputs.
    xraiAttribution GoogleCloudAiplatformV1XraiAttributionResponse
    An attribution method that redistributes Integrated Gradients attribution to segmented regions, taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1906.02825 XRAI currently performs better on natural images, like a picture of a house or an animal. If the images are taken in artificial environments, like a lab or manufacturing line, or from diagnostic equipment, like x-rays or quality-control cameras, use Integrated Gradients instead.
    examples GoogleCloudAiplatformV1ExamplesResponse
    Example-based explanations that returns the nearest neighbors from the provided dataset.
    integrated_gradients_attribution GoogleCloudAiplatformV1IntegratedGradientsAttributionResponse
    An attribution method that computes Aumann-Shapley values taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1703.01365
    output_indices Sequence[Any]
    If populated, only returns attributions that have output_index contained in output_indices. It must be an ndarray of integers, with the same shape of the output it's explaining. If not populated, returns attributions for top_k indices of outputs. If neither top_k nor output_indices is populated, returns the argmax index of the outputs. Only applicable to Models that predict multiple outputs (e,g, multi-class Models that predict multiple classes).
    sampled_shapley_attribution GoogleCloudAiplatformV1SampledShapleyAttributionResponse
    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. Refer to this paper for model details: https://arxiv.org/abs/1306.4265.
    top_k int
    If populated, returns attributions for top K indices of outputs (defaults to 1). Only applies to Models that predicts more than one outputs (e,g, multi-class Models). When set to -1, returns explanations for all outputs.
    xrai_attribution GoogleCloudAiplatformV1XraiAttributionResponse
    An attribution method that redistributes Integrated Gradients attribution to segmented regions, taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1906.02825 XRAI currently performs better on natural images, like a picture of a house or an animal. If the images are taken in artificial environments, like a lab or manufacturing line, or from diagnostic equipment, like x-rays or quality-control cameras, use Integrated Gradients instead.
    examples Property Map
    Example-based explanations that returns the nearest neighbors from the provided dataset.
    integratedGradientsAttribution Property Map
    An attribution method that computes Aumann-Shapley values taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1703.01365
    outputIndices List<Any>
    If populated, only returns attributions that have output_index contained in output_indices. It must be an ndarray of integers, with the same shape of the output it's explaining. If not populated, returns attributions for top_k indices of outputs. If neither top_k nor output_indices is populated, returns the argmax index of the outputs. Only applicable to Models that predict multiple outputs (e,g, multi-class Models that predict multiple classes).
    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. Refer to this paper for model details: https://arxiv.org/abs/1306.4265.
    topK Number
    If populated, returns attributions for top K indices of outputs (defaults to 1). Only applies to Models that predicts more than one outputs (e,g, multi-class Models). When set to -1, returns explanations for all outputs.
    xraiAttribution Property Map
    An attribution method that redistributes Integrated Gradients attribution to segmented regions, taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1906.02825 XRAI currently performs better on natural images, like a picture of a house or an animal. If the images are taken in artificial environments, like a lab or manufacturing line, or from diagnostic equipment, like x-rays or quality-control cameras, use Integrated Gradients instead.

    GoogleCloudAiplatformV1ExplanationSpecResponse, GoogleCloudAiplatformV1ExplanationSpecResponseArgs

    Metadata Pulumi.GoogleNative.Aiplatform.V1.Inputs.GoogleCloudAiplatformV1ExplanationMetadataResponse
    Optional. Metadata describing the Model's input and output for explanation.
    Parameters Pulumi.GoogleNative.Aiplatform.V1.Inputs.GoogleCloudAiplatformV1ExplanationParametersResponse
    Parameters that configure explaining of the Model's predictions.
    Metadata GoogleCloudAiplatformV1ExplanationMetadataResponse
    Optional. Metadata describing the Model's input and output for explanation.
    Parameters GoogleCloudAiplatformV1ExplanationParametersResponse
    Parameters that configure explaining of the Model's predictions.
    metadata GoogleCloudAiplatformV1ExplanationMetadataResponse
    Optional. Metadata describing the Model's input and output for explanation.
    parameters GoogleCloudAiplatformV1ExplanationParametersResponse
    Parameters that configure explaining of the Model's predictions.
    metadata GoogleCloudAiplatformV1ExplanationMetadataResponse
    Optional. Metadata describing the Model's input and output for explanation.
    parameters GoogleCloudAiplatformV1ExplanationParametersResponse
    Parameters that configure explaining of the Model's predictions.
    metadata GoogleCloudAiplatformV1ExplanationMetadataResponse
    Optional. Metadata describing the Model's input and output for explanation.
    parameters GoogleCloudAiplatformV1ExplanationParametersResponse
    Parameters that configure explaining of the Model's predictions.
    metadata Property Map
    Optional. Metadata describing the Model's input and output for explanation.
    parameters Property Map
    Parameters that configure explaining of the Model's predictions.

    GoogleCloudAiplatformV1FeatureNoiseSigmaNoiseSigmaForFeatureResponse, GoogleCloudAiplatformV1FeatureNoiseSigmaNoiseSigmaForFeatureResponseArgs

    Name string
    The name of the input feature for which noise sigma is provided. The features are defined in explanation metadata inputs.
    Sigma double
    This represents the standard deviation of the Gaussian kernel that will be used to add noise to the feature prior to computing gradients. Similar to noise_sigma but represents the noise added to the current feature. Defaults to 0.1.
    Name string
    The name of the input feature for which noise sigma is provided. The features are defined in explanation metadata inputs.
    Sigma float64
    This represents the standard deviation of the Gaussian kernel that will be used to add noise to the feature prior to computing gradients. Similar to noise_sigma but represents the noise added to the current feature. Defaults to 0.1.
    name String
    The name of the input feature for which noise sigma is provided. The features are defined in explanation metadata inputs.
    sigma Double
    This represents the standard deviation of the Gaussian kernel that will be used to add noise to the feature prior to computing gradients. Similar to noise_sigma but represents the noise added to the current feature. Defaults to 0.1.
    name string
    The name of the input feature for which noise sigma is provided. The features are defined in explanation metadata inputs.
    sigma number
    This represents the standard deviation of the Gaussian kernel that will be used to add noise to the feature prior to computing gradients. Similar to noise_sigma but represents the noise added to the current feature. Defaults to 0.1.
    name str
    The name of the input feature for which noise sigma is provided. The features are defined in explanation metadata inputs.
    sigma float
    This represents the standard deviation of the Gaussian kernel that will be used to add noise to the feature prior to computing gradients. Similar to noise_sigma but represents the noise added to the current feature. Defaults to 0.1.
    name String
    The name of the input feature for which noise sigma is provided. The features are defined in explanation metadata inputs.
    sigma Number
    This represents the standard deviation of the Gaussian kernel that will be used to add noise to the feature prior to computing gradients. Similar to noise_sigma but represents the noise added to the current feature. Defaults to 0.1.

    GoogleCloudAiplatformV1FeatureNoiseSigmaResponse, GoogleCloudAiplatformV1FeatureNoiseSigmaResponseArgs

    NoiseSigma []GoogleCloudAiplatformV1FeatureNoiseSigmaNoiseSigmaForFeatureResponse
    Noise sigma per feature. No noise is added to features that are not set.
    noiseSigma List<GoogleCloudAiplatformV1FeatureNoiseSigmaNoiseSigmaForFeatureResponse>
    Noise sigma per feature. No noise is added to features that are not set.
    noiseSigma GoogleCloudAiplatformV1FeatureNoiseSigmaNoiseSigmaForFeatureResponse[]
    Noise sigma per feature. No noise is added to features that are not set.
    noise_sigma Sequence[GoogleCloudAiplatformV1FeatureNoiseSigmaNoiseSigmaForFeatureResponse]
    Noise sigma per feature. No noise is added to features that are not set.
    noiseSigma List<Property Map>
    Noise sigma per feature. No noise is added to features that are not set.

    GoogleCloudAiplatformV1GcsSourceResponse, GoogleCloudAiplatformV1GcsSourceResponseArgs

    Uris List<string>
    Google Cloud Storage URI(-s) to the input file(s). May contain wildcards. For more information on wildcards, see https://cloud.google.com/storage/docs/gsutil/addlhelp/WildcardNames.
    Uris []string
    Google Cloud Storage URI(-s) to the input file(s). May contain wildcards. For more information on wildcards, see https://cloud.google.com/storage/docs/gsutil/addlhelp/WildcardNames.
    uris List<String>
    Google Cloud Storage URI(-s) to the input file(s). May contain wildcards. For more information on wildcards, see https://cloud.google.com/storage/docs/gsutil/addlhelp/WildcardNames.
    uris string[]
    Google Cloud Storage URI(-s) to the input file(s). May contain wildcards. For more information on wildcards, see https://cloud.google.com/storage/docs/gsutil/addlhelp/WildcardNames.
    uris Sequence[str]
    Google Cloud Storage URI(-s) to the input file(s). May contain wildcards. For more information on wildcards, see https://cloud.google.com/storage/docs/gsutil/addlhelp/WildcardNames.
    uris List<String>
    Google Cloud Storage URI(-s) to the input file(s). May contain wildcards. For more information on wildcards, see https://cloud.google.com/storage/docs/gsutil/addlhelp/WildcardNames.

    GoogleCloudAiplatformV1IntegratedGradientsAttributionResponse, GoogleCloudAiplatformV1IntegratedGradientsAttributionResponseArgs

    BlurBaselineConfig Pulumi.GoogleNative.Aiplatform.V1.Inputs.GoogleCloudAiplatformV1BlurBaselineConfigResponse
    Config for IG with blur baseline. When enabled, a linear path from the maximally blurred image to the input image is created. Using a blurred baseline instead of zero (black image) is motivated by the BlurIG approach explained here: https://arxiv.org/abs/2004.03383
    SmoothGradConfig Pulumi.GoogleNative.Aiplatform.V1.Inputs.GoogleCloudAiplatformV1SmoothGradConfigResponse
    Config for SmoothGrad approximation of gradients. When enabled, the gradients are approximated by averaging the gradients from noisy samples in the vicinity of the inputs. Adding noise can help improve the computed gradients. Refer to this paper for more details: https://arxiv.org/pdf/1706.03825.pdf
    StepCount int
    The 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 within the desired error range. Valid range of its value is [1, 100], inclusively.
    BlurBaselineConfig GoogleCloudAiplatformV1BlurBaselineConfigResponse
    Config for IG with blur baseline. When enabled, a linear path from the maximally blurred image to the input image is created. Using a blurred baseline instead of zero (black image) is motivated by the BlurIG approach explained here: https://arxiv.org/abs/2004.03383
    SmoothGradConfig GoogleCloudAiplatformV1SmoothGradConfigResponse
    Config for SmoothGrad approximation of gradients. When enabled, the gradients are approximated by averaging the gradients from noisy samples in the vicinity of the inputs. Adding noise can help improve the computed gradients. Refer to this paper for more details: https://arxiv.org/pdf/1706.03825.pdf
    StepCount int
    The 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 within the desired error range. Valid range of its value is [1, 100], inclusively.
    blurBaselineConfig GoogleCloudAiplatformV1BlurBaselineConfigResponse
    Config for IG with blur baseline. When enabled, a linear path from the maximally blurred image to the input image is created. Using a blurred baseline instead of zero (black image) is motivated by the BlurIG approach explained here: https://arxiv.org/abs/2004.03383
    smoothGradConfig GoogleCloudAiplatformV1SmoothGradConfigResponse
    Config for SmoothGrad approximation of gradients. When enabled, the gradients are approximated by averaging the gradients from noisy samples in the vicinity of the inputs. Adding noise can help improve the computed gradients. Refer to this paper for more details: https://arxiv.org/pdf/1706.03825.pdf
    stepCount Integer
    The 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 within the desired error range. Valid range of its value is [1, 100], inclusively.
    blurBaselineConfig GoogleCloudAiplatformV1BlurBaselineConfigResponse
    Config for IG with blur baseline. When enabled, a linear path from the maximally blurred image to the input image is created. Using a blurred baseline instead of zero (black image) is motivated by the BlurIG approach explained here: https://arxiv.org/abs/2004.03383
    smoothGradConfig GoogleCloudAiplatformV1SmoothGradConfigResponse
    Config for SmoothGrad approximation of gradients. When enabled, the gradients are approximated by averaging the gradients from noisy samples in the vicinity of the inputs. Adding noise can help improve the computed gradients. Refer to this paper for more details: https://arxiv.org/pdf/1706.03825.pdf
    stepCount number
    The 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 within the desired error range. Valid range of its value is [1, 100], inclusively.
    blur_baseline_config GoogleCloudAiplatformV1BlurBaselineConfigResponse
    Config for IG with blur baseline. When enabled, a linear path from the maximally blurred image to the input image is created. Using a blurred baseline instead of zero (black image) is motivated by the BlurIG approach explained here: https://arxiv.org/abs/2004.03383
    smooth_grad_config GoogleCloudAiplatformV1SmoothGradConfigResponse
    Config for SmoothGrad approximation of gradients. When enabled, the gradients are approximated by averaging the gradients from noisy samples in the vicinity of the inputs. Adding noise can help improve the computed gradients. Refer to this paper for more details: https://arxiv.org/pdf/1706.03825.pdf
    step_count int
    The 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 within the desired error range. Valid range of its value is [1, 100], inclusively.
    blurBaselineConfig Property Map
    Config for IG with blur baseline. When enabled, a linear path from the maximally blurred image to the input image is created. Using a blurred baseline instead of zero (black image) is motivated by the BlurIG approach explained here: https://arxiv.org/abs/2004.03383
    smoothGradConfig Property Map
    Config for SmoothGrad approximation of gradients. When enabled, the gradients are approximated by averaging the gradients from noisy samples in the vicinity of the inputs. Adding noise can help improve the computed gradients. Refer to this paper for more details: https://arxiv.org/pdf/1706.03825.pdf
    stepCount Number
    The 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 within the desired error range. Valid range of its value is [1, 100], inclusively.

    GoogleCloudAiplatformV1MachineSpecResponse, GoogleCloudAiplatformV1MachineSpecResponseArgs

    AcceleratorCount int
    The number of accelerators to attach to the machine.
    AcceleratorType string
    Immutable. The type of accelerator(s) that may be attached to the machine as per accelerator_count.
    MachineType string
    Immutable. The type of the machine. See the list of machine types supported for prediction See the list of machine types supported for custom training. For DeployedModel this field is optional, and the default value is n1-standard-2. For BatchPredictionJob or as part of WorkerPoolSpec this field is required.
    TpuTopology string
    Immutable. The topology of the TPUs. Corresponds to the TPU topologies available from GKE. (Example: tpu_topology: "2x2x1").
    AcceleratorCount int
    The number of accelerators to attach to the machine.
    AcceleratorType string
    Immutable. The type of accelerator(s) that may be attached to the machine as per accelerator_count.
    MachineType string
    Immutable. The type of the machine. See the list of machine types supported for prediction See the list of machine types supported for custom training. For DeployedModel this field is optional, and the default value is n1-standard-2. For BatchPredictionJob or as part of WorkerPoolSpec this field is required.
    TpuTopology string
    Immutable. The topology of the TPUs. Corresponds to the TPU topologies available from GKE. (Example: tpu_topology: "2x2x1").
    acceleratorCount Integer
    The number of accelerators to attach to the machine.
    acceleratorType String
    Immutable. The type of accelerator(s) that may be attached to the machine as per accelerator_count.
    machineType String
    Immutable. The type of the machine. See the list of machine types supported for prediction See the list of machine types supported for custom training. For DeployedModel this field is optional, and the default value is n1-standard-2. For BatchPredictionJob or as part of WorkerPoolSpec this field is required.
    tpuTopology String
    Immutable. The topology of the TPUs. Corresponds to the TPU topologies available from GKE. (Example: tpu_topology: "2x2x1").
    acceleratorCount number
    The number of accelerators to attach to the machine.
    acceleratorType string
    Immutable. The type of accelerator(s) that may be attached to the machine as per accelerator_count.
    machineType string
    Immutable. The type of the machine. See the list of machine types supported for prediction See the list of machine types supported for custom training. For DeployedModel this field is optional, and the default value is n1-standard-2. For BatchPredictionJob or as part of WorkerPoolSpec this field is required.
    tpuTopology string
    Immutable. The topology of the TPUs. Corresponds to the TPU topologies available from GKE. (Example: tpu_topology: "2x2x1").
    accelerator_count int
    The number of accelerators to attach to the machine.
    accelerator_type str
    Immutable. The type of accelerator(s) that may be attached to the machine as per accelerator_count.
    machine_type str
    Immutable. The type of the machine. See the list of machine types supported for prediction See the list of machine types supported for custom training. For DeployedModel this field is optional, and the default value is n1-standard-2. For BatchPredictionJob or as part of WorkerPoolSpec this field is required.
    tpu_topology str
    Immutable. The topology of the TPUs. Corresponds to the TPU topologies available from GKE. (Example: tpu_topology: "2x2x1").
    acceleratorCount Number
    The number of accelerators to attach to the machine.
    acceleratorType String
    Immutable. The type of accelerator(s) that may be attached to the machine as per accelerator_count.
    machineType String
    Immutable. The type of the machine. See the list of machine types supported for prediction See the list of machine types supported for custom training. For DeployedModel this field is optional, and the default value is n1-standard-2. For BatchPredictionJob or as part of WorkerPoolSpec this field is required.
    tpuTopology String
    Immutable. The topology of the TPUs. Corresponds to the TPU topologies available from GKE. (Example: tpu_topology: "2x2x1").

    GoogleCloudAiplatformV1PredictRequestResponseLoggingConfig, GoogleCloudAiplatformV1PredictRequestResponseLoggingConfigArgs

    BigqueryDestination Pulumi.GoogleNative.Aiplatform.V1.Inputs.GoogleCloudAiplatformV1BigQueryDestination
    BigQuery table for logging. If only given a project, a new dataset will be created with name logging__ where will be made BigQuery-dataset-name compatible (e.g. most special characters will become underscores). If no table name is given, a new table will be created with name request_response_logging
    Enabled bool
    If logging is enabled or not.
    SamplingRate double
    Percentage of requests to be logged, expressed as a fraction in range(0,1].
    BigqueryDestination GoogleCloudAiplatformV1BigQueryDestination
    BigQuery table for logging. If only given a project, a new dataset will be created with name logging__ where will be made BigQuery-dataset-name compatible (e.g. most special characters will become underscores). If no table name is given, a new table will be created with name request_response_logging
    Enabled bool
    If logging is enabled or not.
    SamplingRate float64
    Percentage of requests to be logged, expressed as a fraction in range(0,1].
    bigqueryDestination GoogleCloudAiplatformV1BigQueryDestination
    BigQuery table for logging. If only given a project, a new dataset will be created with name logging__ where will be made BigQuery-dataset-name compatible (e.g. most special characters will become underscores). If no table name is given, a new table will be created with name request_response_logging
    enabled Boolean
    If logging is enabled or not.
    samplingRate Double
    Percentage of requests to be logged, expressed as a fraction in range(0,1].
    bigqueryDestination GoogleCloudAiplatformV1BigQueryDestination
    BigQuery table for logging. If only given a project, a new dataset will be created with name logging__ where will be made BigQuery-dataset-name compatible (e.g. most special characters will become underscores). If no table name is given, a new table will be created with name request_response_logging
    enabled boolean
    If logging is enabled or not.
    samplingRate number
    Percentage of requests to be logged, expressed as a fraction in range(0,1].
    bigquery_destination GoogleCloudAiplatformV1BigQueryDestination
    BigQuery table for logging. If only given a project, a new dataset will be created with name logging__ where will be made BigQuery-dataset-name compatible (e.g. most special characters will become underscores). If no table name is given, a new table will be created with name request_response_logging
    enabled bool
    If logging is enabled or not.
    sampling_rate float
    Percentage of requests to be logged, expressed as a fraction in range(0,1].
    bigqueryDestination Property Map
    BigQuery table for logging. If only given a project, a new dataset will be created with name logging__ where will be made BigQuery-dataset-name compatible (e.g. most special characters will become underscores). If no table name is given, a new table will be created with name request_response_logging
    enabled Boolean
    If logging is enabled or not.
    samplingRate Number
    Percentage of requests to be logged, expressed as a fraction in range(0,1].

    GoogleCloudAiplatformV1PredictRequestResponseLoggingConfigResponse, GoogleCloudAiplatformV1PredictRequestResponseLoggingConfigResponseArgs

    BigqueryDestination Pulumi.GoogleNative.Aiplatform.V1.Inputs.GoogleCloudAiplatformV1BigQueryDestinationResponse
    BigQuery table for logging. If only given a project, a new dataset will be created with name logging__ where will be made BigQuery-dataset-name compatible (e.g. most special characters will become underscores). If no table name is given, a new table will be created with name request_response_logging
    Enabled bool
    If logging is enabled or not.
    SamplingRate double
    Percentage of requests to be logged, expressed as a fraction in range(0,1].
    BigqueryDestination GoogleCloudAiplatformV1BigQueryDestinationResponse
    BigQuery table for logging. If only given a project, a new dataset will be created with name logging__ where will be made BigQuery-dataset-name compatible (e.g. most special characters will become underscores). If no table name is given, a new table will be created with name request_response_logging
    Enabled bool
    If logging is enabled or not.
    SamplingRate float64
    Percentage of requests to be logged, expressed as a fraction in range(0,1].
    bigqueryDestination GoogleCloudAiplatformV1BigQueryDestinationResponse
    BigQuery table for logging. If only given a project, a new dataset will be created with name logging__ where will be made BigQuery-dataset-name compatible (e.g. most special characters will become underscores). If no table name is given, a new table will be created with name request_response_logging
    enabled Boolean
    If logging is enabled or not.
    samplingRate Double
    Percentage of requests to be logged, expressed as a fraction in range(0,1].
    bigqueryDestination GoogleCloudAiplatformV1BigQueryDestinationResponse
    BigQuery table for logging. If only given a project, a new dataset will be created with name logging__ where will be made BigQuery-dataset-name compatible (e.g. most special characters will become underscores). If no table name is given, a new table will be created with name request_response_logging
    enabled boolean
    If logging is enabled or not.
    samplingRate number
    Percentage of requests to be logged, expressed as a fraction in range(0,1].
    bigquery_destination GoogleCloudAiplatformV1BigQueryDestinationResponse
    BigQuery table for logging. If only given a project, a new dataset will be created with name logging__ where will be made BigQuery-dataset-name compatible (e.g. most special characters will become underscores). If no table name is given, a new table will be created with name request_response_logging
    enabled bool
    If logging is enabled or not.
    sampling_rate float
    Percentage of requests to be logged, expressed as a fraction in range(0,1].
    bigqueryDestination Property Map
    BigQuery table for logging. If only given a project, a new dataset will be created with name logging__ where will be made BigQuery-dataset-name compatible (e.g. most special characters will become underscores). If no table name is given, a new table will be created with name request_response_logging
    enabled Boolean
    If logging is enabled or not.
    samplingRate Number
    Percentage of requests to be logged, expressed as a fraction in range(0,1].

    GoogleCloudAiplatformV1PresetsResponse, GoogleCloudAiplatformV1PresetsResponseArgs

    Modality string
    The modality of the uploaded model, which automatically configures the distance measurement and feature normalization for the underlying example index and queries. If your model does not precisely fit one of these types, it is okay to choose the closest type.
    Query string
    Preset option controlling parameters for speed-precision trade-off when querying for examples. If omitted, defaults to PRECISE.
    Modality string
    The modality of the uploaded model, which automatically configures the distance measurement and feature normalization for the underlying example index and queries. If your model does not precisely fit one of these types, it is okay to choose the closest type.
    Query string
    Preset option controlling parameters for speed-precision trade-off when querying for examples. If omitted, defaults to PRECISE.
    modality String
    The modality of the uploaded model, which automatically configures the distance measurement and feature normalization for the underlying example index and queries. If your model does not precisely fit one of these types, it is okay to choose the closest type.
    query String
    Preset option controlling parameters for speed-precision trade-off when querying for examples. If omitted, defaults to PRECISE.
    modality string
    The modality of the uploaded model, which automatically configures the distance measurement and feature normalization for the underlying example index and queries. If your model does not precisely fit one of these types, it is okay to choose the closest type.
    query string
    Preset option controlling parameters for speed-precision trade-off when querying for examples. If omitted, defaults to PRECISE.
    modality str
    The modality of the uploaded model, which automatically configures the distance measurement and feature normalization for the underlying example index and queries. If your model does not precisely fit one of these types, it is okay to choose the closest type.
    query str
    Preset option controlling parameters for speed-precision trade-off when querying for examples. If omitted, defaults to PRECISE.
    modality String
    The modality of the uploaded model, which automatically configures the distance measurement and feature normalization for the underlying example index and queries. If your model does not precisely fit one of these types, it is okay to choose the closest type.
    query String
    Preset option controlling parameters for speed-precision trade-off when querying for examples. If omitted, defaults to PRECISE.

    GoogleCloudAiplatformV1PrivateEndpointsResponse, GoogleCloudAiplatformV1PrivateEndpointsResponseArgs

    ExplainHttpUri string
    Http(s) path to send explain requests.
    HealthHttpUri string
    Http(s) path to send health check requests.
    PredictHttpUri string
    Http(s) path to send prediction requests.
    ServiceAttachment string
    The name of the service attachment resource. Populated if private service connect is enabled.
    ExplainHttpUri string
    Http(s) path to send explain requests.
    HealthHttpUri string
    Http(s) path to send health check requests.
    PredictHttpUri string
    Http(s) path to send prediction requests.
    ServiceAttachment string
    The name of the service attachment resource. Populated if private service connect is enabled.
    explainHttpUri String
    Http(s) path to send explain requests.
    healthHttpUri String
    Http(s) path to send health check requests.
    predictHttpUri String
    Http(s) path to send prediction requests.
    serviceAttachment String
    The name of the service attachment resource. Populated if private service connect is enabled.
    explainHttpUri string
    Http(s) path to send explain requests.
    healthHttpUri string
    Http(s) path to send health check requests.
    predictHttpUri string
    Http(s) path to send prediction requests.
    serviceAttachment string
    The name of the service attachment resource. Populated if private service connect is enabled.
    explain_http_uri str
    Http(s) path to send explain requests.
    health_http_uri str
    Http(s) path to send health check requests.
    predict_http_uri str
    Http(s) path to send prediction requests.
    service_attachment str
    The name of the service attachment resource. Populated if private service connect is enabled.
    explainHttpUri String
    Http(s) path to send explain requests.
    healthHttpUri String
    Http(s) path to send health check requests.
    predictHttpUri String
    Http(s) path to send prediction requests.
    serviceAttachment String
    The name of the service attachment resource. Populated if private service connect is enabled.

    GoogleCloudAiplatformV1SampledShapleyAttributionResponse, GoogleCloudAiplatformV1SampledShapleyAttributionResponseArgs

    PathCount int
    The number of feature permutations to consider when approximating the Shapley values. Valid range of its value is [1, 50], inclusively.
    PathCount int
    The number of feature permutations to consider when approximating the Shapley values. Valid range of its value is [1, 50], inclusively.
    pathCount Integer
    The number of feature permutations to consider when approximating the Shapley values. Valid range of its value is [1, 50], inclusively.
    pathCount number
    The number of feature permutations to consider when approximating the Shapley values. Valid range of its value is [1, 50], inclusively.
    path_count int
    The number of feature permutations to consider when approximating the Shapley values. Valid range of its value is [1, 50], inclusively.
    pathCount Number
    The number of feature permutations to consider when approximating the Shapley values. Valid range of its value is [1, 50], inclusively.

    GoogleCloudAiplatformV1SmoothGradConfigResponse, GoogleCloudAiplatformV1SmoothGradConfigResponseArgs

    FeatureNoiseSigma Pulumi.GoogleNative.Aiplatform.V1.Inputs.GoogleCloudAiplatformV1FeatureNoiseSigmaResponse
    This is similar to noise_sigma, but provides additional flexibility. A separate noise sigma can be provided for each feature, which is useful if their distributions are different. No noise is added to features that are not set. If this field is unset, noise_sigma will be used for all features.
    NoiseSigma double
    This is a single float value and will be used to add noise to all the features. Use this field when all features are normalized to have the same distribution: scale to range [0, 1], [-1, 1] or z-scoring, where features are normalized to have 0-mean and 1-variance. Learn more about normalization. For best results the recommended value is about 10% - 20% of the standard deviation of the input feature. Refer to section 3.2 of the SmoothGrad paper: https://arxiv.org/pdf/1706.03825.pdf. Defaults to 0.1. If the distribution is different per feature, set feature_noise_sigma instead for each feature.
    NoisySampleCount int
    The number of gradient samples to use for approximation. The higher this number, the more accurate the gradient is, but the runtime complexity increases by this factor as well. Valid range of its value is [1, 50]. Defaults to 3.
    FeatureNoiseSigma GoogleCloudAiplatformV1FeatureNoiseSigmaResponse
    This is similar to noise_sigma, but provides additional flexibility. A separate noise sigma can be provided for each feature, which is useful if their distributions are different. No noise is added to features that are not set. If this field is unset, noise_sigma will be used for all features.
    NoiseSigma float64
    This is a single float value and will be used to add noise to all the features. Use this field when all features are normalized to have the same distribution: scale to range [0, 1], [-1, 1] or z-scoring, where features are normalized to have 0-mean and 1-variance. Learn more about normalization. For best results the recommended value is about 10% - 20% of the standard deviation of the input feature. Refer to section 3.2 of the SmoothGrad paper: https://arxiv.org/pdf/1706.03825.pdf. Defaults to 0.1. If the distribution is different per feature, set feature_noise_sigma instead for each feature.
    NoisySampleCount int
    The number of gradient samples to use for approximation. The higher this number, the more accurate the gradient is, but the runtime complexity increases by this factor as well. Valid range of its value is [1, 50]. Defaults to 3.
    featureNoiseSigma GoogleCloudAiplatformV1FeatureNoiseSigmaResponse
    This is similar to noise_sigma, but provides additional flexibility. A separate noise sigma can be provided for each feature, which is useful if their distributions are different. No noise is added to features that are not set. If this field is unset, noise_sigma will be used for all features.
    noiseSigma Double
    This is a single float value and will be used to add noise to all the features. Use this field when all features are normalized to have the same distribution: scale to range [0, 1], [-1, 1] or z-scoring, where features are normalized to have 0-mean and 1-variance. Learn more about normalization. For best results the recommended value is about 10% - 20% of the standard deviation of the input feature. Refer to section 3.2 of the SmoothGrad paper: https://arxiv.org/pdf/1706.03825.pdf. Defaults to 0.1. If the distribution is different per feature, set feature_noise_sigma instead for each feature.
    noisySampleCount Integer
    The number of gradient samples to use for approximation. The higher this number, the more accurate the gradient is, but the runtime complexity increases by this factor as well. Valid range of its value is [1, 50]. Defaults to 3.
    featureNoiseSigma GoogleCloudAiplatformV1FeatureNoiseSigmaResponse
    This is similar to noise_sigma, but provides additional flexibility. A separate noise sigma can be provided for each feature, which is useful if their distributions are different. No noise is added to features that are not set. If this field is unset, noise_sigma will be used for all features.
    noiseSigma number
    This is a single float value and will be used to add noise to all the features. Use this field when all features are normalized to have the same distribution: scale to range [0, 1], [-1, 1] or z-scoring, where features are normalized to have 0-mean and 1-variance. Learn more about normalization. For best results the recommended value is about 10% - 20% of the standard deviation of the input feature. Refer to section 3.2 of the SmoothGrad paper: https://arxiv.org/pdf/1706.03825.pdf. Defaults to 0.1. If the distribution is different per feature, set feature_noise_sigma instead for each feature.
    noisySampleCount number
    The number of gradient samples to use for approximation. The higher this number, the more accurate the gradient is, but the runtime complexity increases by this factor as well. Valid range of its value is [1, 50]. Defaults to 3.
    feature_noise_sigma GoogleCloudAiplatformV1FeatureNoiseSigmaResponse
    This is similar to noise_sigma, but provides additional flexibility. A separate noise sigma can be provided for each feature, which is useful if their distributions are different. No noise is added to features that are not set. If this field is unset, noise_sigma will be used for all features.
    noise_sigma float
    This is a single float value and will be used to add noise to all the features. Use this field when all features are normalized to have the same distribution: scale to range [0, 1], [-1, 1] or z-scoring, where features are normalized to have 0-mean and 1-variance. Learn more about normalization. For best results the recommended value is about 10% - 20% of the standard deviation of the input feature. Refer to section 3.2 of the SmoothGrad paper: https://arxiv.org/pdf/1706.03825.pdf. Defaults to 0.1. If the distribution is different per feature, set feature_noise_sigma instead for each feature.
    noisy_sample_count int
    The number of gradient samples to use for approximation. The higher this number, the more accurate the gradient is, but the runtime complexity increases by this factor as well. Valid range of its value is [1, 50]. Defaults to 3.
    featureNoiseSigma Property Map
    This is similar to noise_sigma, but provides additional flexibility. A separate noise sigma can be provided for each feature, which is useful if their distributions are different. No noise is added to features that are not set. If this field is unset, noise_sigma will be used for all features.
    noiseSigma Number
    This is a single float value and will be used to add noise to all the features. Use this field when all features are normalized to have the same distribution: scale to range [0, 1], [-1, 1] or z-scoring, where features are normalized to have 0-mean and 1-variance. Learn more about normalization. For best results the recommended value is about 10% - 20% of the standard deviation of the input feature. Refer to section 3.2 of the SmoothGrad paper: https://arxiv.org/pdf/1706.03825.pdf. Defaults to 0.1. If the distribution is different per feature, set feature_noise_sigma instead for each feature.
    noisySampleCount Number
    The number of gradient samples to use for approximation. The higher this number, the more accurate the gradient is, but the runtime complexity increases by this factor as well. Valid range of its value is [1, 50]. Defaults to 3.

    GoogleCloudAiplatformV1XraiAttributionResponse, GoogleCloudAiplatformV1XraiAttributionResponseArgs

    BlurBaselineConfig Pulumi.GoogleNative.Aiplatform.V1.Inputs.GoogleCloudAiplatformV1BlurBaselineConfigResponse
    Config for XRAI with blur baseline. When enabled, a linear path from the maximally blurred image to the input image is created. Using a blurred baseline instead of zero (black image) is motivated by the BlurIG approach explained here: https://arxiv.org/abs/2004.03383
    SmoothGradConfig Pulumi.GoogleNative.Aiplatform.V1.Inputs.GoogleCloudAiplatformV1SmoothGradConfigResponse
    Config for SmoothGrad approximation of gradients. When enabled, the gradients are approximated by averaging the gradients from noisy samples in the vicinity of the inputs. Adding noise can help improve the computed gradients. Refer to this paper for more details: https://arxiv.org/pdf/1706.03825.pdf
    StepCount int
    The 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. Valid range of its value is [1, 100], inclusively.
    BlurBaselineConfig GoogleCloudAiplatformV1BlurBaselineConfigResponse
    Config for XRAI with blur baseline. When enabled, a linear path from the maximally blurred image to the input image is created. Using a blurred baseline instead of zero (black image) is motivated by the BlurIG approach explained here: https://arxiv.org/abs/2004.03383
    SmoothGradConfig GoogleCloudAiplatformV1SmoothGradConfigResponse
    Config for SmoothGrad approximation of gradients. When enabled, the gradients are approximated by averaging the gradients from noisy samples in the vicinity of the inputs. Adding noise can help improve the computed gradients. Refer to this paper for more details: https://arxiv.org/pdf/1706.03825.pdf
    StepCount int
    The 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. Valid range of its value is [1, 100], inclusively.
    blurBaselineConfig GoogleCloudAiplatformV1BlurBaselineConfigResponse
    Config for XRAI with blur baseline. When enabled, a linear path from the maximally blurred image to the input image is created. Using a blurred baseline instead of zero (black image) is motivated by the BlurIG approach explained here: https://arxiv.org/abs/2004.03383
    smoothGradConfig GoogleCloudAiplatformV1SmoothGradConfigResponse
    Config for SmoothGrad approximation of gradients. When enabled, the gradients are approximated by averaging the gradients from noisy samples in the vicinity of the inputs. Adding noise can help improve the computed gradients. Refer to this paper for more details: https://arxiv.org/pdf/1706.03825.pdf
    stepCount Integer
    The 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. Valid range of its value is [1, 100], inclusively.
    blurBaselineConfig GoogleCloudAiplatformV1BlurBaselineConfigResponse
    Config for XRAI with blur baseline. When enabled, a linear path from the maximally blurred image to the input image is created. Using a blurred baseline instead of zero (black image) is motivated by the BlurIG approach explained here: https://arxiv.org/abs/2004.03383
    smoothGradConfig GoogleCloudAiplatformV1SmoothGradConfigResponse
    Config for SmoothGrad approximation of gradients. When enabled, the gradients are approximated by averaging the gradients from noisy samples in the vicinity of the inputs. Adding noise can help improve the computed gradients. Refer to this paper for more details: https://arxiv.org/pdf/1706.03825.pdf
    stepCount number
    The 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. Valid range of its value is [1, 100], inclusively.
    blur_baseline_config GoogleCloudAiplatformV1BlurBaselineConfigResponse
    Config for XRAI with blur baseline. When enabled, a linear path from the maximally blurred image to the input image is created. Using a blurred baseline instead of zero (black image) is motivated by the BlurIG approach explained here: https://arxiv.org/abs/2004.03383
    smooth_grad_config GoogleCloudAiplatformV1SmoothGradConfigResponse
    Config for SmoothGrad approximation of gradients. When enabled, the gradients are approximated by averaging the gradients from noisy samples in the vicinity of the inputs. Adding noise can help improve the computed gradients. Refer to this paper for more details: https://arxiv.org/pdf/1706.03825.pdf
    step_count int
    The 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. Valid range of its value is [1, 100], inclusively.
    blurBaselineConfig Property Map
    Config for XRAI with blur baseline. When enabled, a linear path from the maximally blurred image to the input image is created. Using a blurred baseline instead of zero (black image) is motivated by the BlurIG approach explained here: https://arxiv.org/abs/2004.03383
    smoothGradConfig Property Map
    Config for SmoothGrad approximation of gradients. When enabled, the gradients are approximated by averaging the gradients from noisy samples in the vicinity of the inputs. Adding noise can help improve the computed gradients. Refer to this paper for more details: https://arxiv.org/pdf/1706.03825.pdf
    stepCount Number
    The 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. Valid range of its value is [1, 100], inclusively.

    Package Details

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

    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