google-native.aiplatform/v1beta1.getEndpoint

func LookupEndpoint(ctx *Context, args *LookupEndpointArgs, opts ...InvokeOption) (*LookupEndpointResult, error)
func LookupEndpointOutput(ctx *Context, args *LookupEndpointOutputArgs, opts ...InvokeOption) LookupEndpointResultOutput

> Note: This function is named LookupEndpoint in the Go SDK.

EndpointId This property is required. string

Location This property is required. string

Project string

EndpointId This property is required. string

Location This property is required. string

Project string

endpointId This property is required. String

location This property is required. String

project String

endpoint_id This property is required. str

location This property is required. str

project str

endpointId This property is required. String

location This property is required. String

project String

CreateTime string

Timestamp when this Endpoint was created.

DeployedModels List<Pulumi.GoogleNative.Aiplatform.V1Beta1.Outputs.GoogleCloudAiplatformV1beta1DeployedModelResponse>

The models deployed in this Endpoint. To add or remove DeployedModels use EndpointService.DeployModel and EndpointService.UndeployModel respectively.

Description string

The description of the Endpoint.

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.

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.V1Beta1.Outputs.GoogleCloudAiplatformV1beta1EncryptionSpecResponse

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.

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.

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.

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.V1Beta1.Outputs.GoogleCloudAiplatformV1beta1PredictRequestResponseLoggingConfigResponse

Configures the request-response logging for online prediction.

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.

UpdateTime string

Timestamp when this Endpoint was last updated.

CreateTime string

Timestamp when this Endpoint was created.

DeployedModels []GoogleCloudAiplatformV1beta1DeployedModelResponse

The models deployed in this Endpoint. To add or remove DeployedModels use EndpointService.DeployModel and EndpointService.UndeployModel respectively.

Description string

The description of the Endpoint.

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.

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 GoogleCloudAiplatformV1beta1EncryptionSpecResponse

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.

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.

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.

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 GoogleCloudAiplatformV1beta1PredictRequestResponseLoggingConfigResponse

Configures the request-response logging for online prediction.

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.

UpdateTime string

Timestamp when this Endpoint was last updated.

createTime String

Timestamp when this Endpoint was created.

deployedModels List<GoogleCloudAiplatformV1beta1DeployedModelResponse>

The models deployed in this Endpoint. To add or remove DeployedModels use EndpointService.DeployModel and EndpointService.UndeployModel respectively.

description String

The description of the Endpoint.

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.

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 GoogleCloudAiplatformV1beta1EncryptionSpecResponse

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.

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.

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.

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 GoogleCloudAiplatformV1beta1PredictRequestResponseLoggingConfigResponse

Configures the request-response logging for online prediction.

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.

updateTime String

Timestamp when this Endpoint was last updated.

create_time str

Timestamp when this Endpoint was created.

deployed_models Sequence[GoogleCloudAiplatformV1beta1DeployedModelResponse]

The models deployed in this Endpoint. To add or remove DeployedModels use EndpointService.DeployModel and EndpointService.UndeployModel respectively.

description str

The description of the Endpoint.

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.

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 GoogleCloudAiplatformV1beta1EncryptionSpecResponse

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.

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.

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.

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 GoogleCloudAiplatformV1beta1PredictRequestResponseLoggingConfigResponse

Configures the request-response logging for online prediction.

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.

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.

description String

The description of the Endpoint.

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.

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.

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.

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.

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.

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.

updateTime String

Timestamp when this Endpoint was last updated.

MaxReplicaCount This property is required. 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 This property is required. 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 This property is required. 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 This property is required. 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 This property is required. 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 This property is required. 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.

max_replica_count This property is required. 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 This property is required. 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 This property is required. 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 This property is required. 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.

MetricName This property is required. 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 This property is required. 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 This property is required. 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 This property is required. 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 This property is required. 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 This property is required. 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.

metric_name This property is required. 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 This property is required. 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 This property is required. 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 This property is required. 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.

OutputUri This property is required. 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 This property is required. 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 This property is required. 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 This property is required. 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 This property is required. 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.

MaxBlurSigma This property is required. 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 This property is required. 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 This property is required. 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.

max_blur_sigma This property is required. 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 This property is required. 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.

AutoscalingMetricSpecs This property is required. List<Pulumi.GoogleNative.Aiplatform.V1Beta1.Inputs.GoogleCloudAiplatformV1beta1AutoscalingMetricSpecResponse>

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 This property is required. Pulumi.GoogleNative.Aiplatform.V1Beta1.Inputs.GoogleCloudAiplatformV1beta1MachineSpecResponse

Immutable. The specification of a single machine used by the prediction.

MaxReplicaCount This property is required. 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 This property is required. 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 This property is required. []GoogleCloudAiplatformV1beta1AutoscalingMetricSpecResponse

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 This property is required. GoogleCloudAiplatformV1beta1MachineSpecResponse

Immutable. The specification of a single machine used by the prediction.

MaxReplicaCount This property is required. 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 This property is required. 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 This property is required. List<GoogleCloudAiplatformV1beta1AutoscalingMetricSpecResponse>

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 This property is required. GoogleCloudAiplatformV1beta1MachineSpecResponse

Immutable. The specification of a single machine used by the prediction.

maxReplicaCount This property is required. 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 This property is required. 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.

autoscaling_metric_specs This property is required. Sequence[GoogleCloudAiplatformV1beta1AutoscalingMetricSpecResponse]

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 This property is required. GoogleCloudAiplatformV1beta1MachineSpecResponse

Immutable. The specification of a single machine used by the prediction.

max_replica_count This property is required. 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 This property is required. 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 This property is required. 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 This property is required. Property Map

Immutable. The specification of a single machine used by the prediction.

maxReplicaCount This property is required. 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 This property is required. 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.

AutomaticResources This property is required. Pulumi.GoogleNative.Aiplatform.V1Beta1.Inputs.GoogleCloudAiplatformV1beta1AutomaticResourcesResponse

A description of resources that to large degree are decided by Vertex AI, and require only a modest additional configuration.

CreateTime This property is required. string

Timestamp when the DeployedModel was created.

DedicatedResources This property is required. Pulumi.GoogleNative.Aiplatform.V1Beta1.Inputs.GoogleCloudAiplatformV1beta1DedicatedResourcesResponse

A description of resources that are dedicated to the DeployedModel, and that need a higher degree of manual configuration.

DisableExplanations This property is required. bool

If true, deploy the model without explainable feature, regardless the existence of Model.explanation_spec or explanation_spec.

DisplayName This property is required. string

The display name of the DeployedModel. If not provided upon creation, the Model's display_name is used.

EnableAccessLogging This property is required. 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.

EnableContainerLogging This property is required. bool

If true, the container of the DeployedModel instances will send stderr and stdout streams to Cloud Logging. Only supported for custom-trained Models and AutoML Tabular Models.

ExplanationSpec This property is required. Pulumi.GoogleNative.Aiplatform.V1Beta1.Inputs.GoogleCloudAiplatformV1beta1ExplanationSpecResponse

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 This property is required. 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 This property is required. string

The version ID of the model that is deployed.

PrivateEndpoints This property is required. Pulumi.GoogleNative.Aiplatform.V1Beta1.Inputs.GoogleCloudAiplatformV1beta1PrivateEndpointsResponse

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 This property is required. 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.

SharedResources This property is required. string

The resource name of the shared DeploymentResourcePool to deploy on. Format: projects/{project}/locations/{location}/deploymentResourcePools/{deployment_resource_pool}

AutomaticResources This property is required. GoogleCloudAiplatformV1beta1AutomaticResourcesResponse

A description of resources that to large degree are decided by Vertex AI, and require only a modest additional configuration.

CreateTime This property is required. string

Timestamp when the DeployedModel was created.

DedicatedResources This property is required. GoogleCloudAiplatformV1beta1DedicatedResourcesResponse

A description of resources that are dedicated to the DeployedModel, and that need a higher degree of manual configuration.

DisableExplanations This property is required. bool

If true, deploy the model without explainable feature, regardless the existence of Model.explanation_spec or explanation_spec.

DisplayName This property is required. string

The display name of the DeployedModel. If not provided upon creation, the Model's display_name is used.

EnableAccessLogging This property is required. 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.

EnableContainerLogging This property is required. bool

If true, the container of the DeployedModel instances will send stderr and stdout streams to Cloud Logging. Only supported for custom-trained Models and AutoML Tabular Models.

ExplanationSpec This property is required. GoogleCloudAiplatformV1beta1ExplanationSpecResponse

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 This property is required. 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 This property is required. string

The version ID of the model that is deployed.

PrivateEndpoints This property is required. GoogleCloudAiplatformV1beta1PrivateEndpointsResponse

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 This property is required. 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.

SharedResources This property is required. string

The resource name of the shared DeploymentResourcePool to deploy on. Format: projects/{project}/locations/{location}/deploymentResourcePools/{deployment_resource_pool}

automaticResources This property is required. GoogleCloudAiplatformV1beta1AutomaticResourcesResponse

A description of resources that to large degree are decided by Vertex AI, and require only a modest additional configuration.

createTime This property is required. String

Timestamp when the DeployedModel was created.

dedicatedResources This property is required. GoogleCloudAiplatformV1beta1DedicatedResourcesResponse

A description of resources that are dedicated to the DeployedModel, and that need a higher degree of manual configuration.

disableExplanations This property is required. Boolean

If true, deploy the model without explainable feature, regardless the existence of Model.explanation_spec or explanation_spec.

displayName This property is required. String

The display name of the DeployedModel. If not provided upon creation, the Model's display_name is used.

enableAccessLogging This property is required. 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.

enableContainerLogging This property is required. Boolean

If true, the container of the DeployedModel instances will send stderr and stdout streams to Cloud Logging. Only supported for custom-trained Models and AutoML Tabular Models.

explanationSpec This property is required. GoogleCloudAiplatformV1beta1ExplanationSpecResponse

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 This property is required. 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 This property is required. String

The version ID of the model that is deployed.

privateEndpoints This property is required. GoogleCloudAiplatformV1beta1PrivateEndpointsResponse

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 This property is required. 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.

sharedResources This property is required. String

The resource name of the shared DeploymentResourcePool to deploy on. Format: projects/{project}/locations/{location}/deploymentResourcePools/{deployment_resource_pool}

automatic_resources This property is required. GoogleCloudAiplatformV1beta1AutomaticResourcesResponse

A description of resources that to large degree are decided by Vertex AI, and require only a modest additional configuration.

create_time This property is required. str

Timestamp when the DeployedModel was created.

dedicated_resources This property is required. GoogleCloudAiplatformV1beta1DedicatedResourcesResponse

A description of resources that are dedicated to the DeployedModel, and that need a higher degree of manual configuration.

disable_explanations This property is required. bool

If true, deploy the model without explainable feature, regardless the existence of Model.explanation_spec or explanation_spec.

display_name This property is required. str

The display name of the DeployedModel. If not provided upon creation, the Model's display_name is used.

enable_access_logging This property is required. 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.

enable_container_logging This property is required. bool

If true, the container of the DeployedModel instances will send stderr and stdout streams to Cloud Logging. Only supported for custom-trained Models and AutoML Tabular Models.

explanation_spec This property is required. GoogleCloudAiplatformV1beta1ExplanationSpecResponse

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 This property is required. 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 This property is required. str

The version ID of the model that is deployed.

private_endpoints This property is required. GoogleCloudAiplatformV1beta1PrivateEndpointsResponse

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 This property is required. 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.

shared_resources This property is required. str

The resource name of the shared DeploymentResourcePool to deploy on. Format: projects/{project}/locations/{location}/deploymentResourcePools/{deployment_resource_pool}

automaticResources This property is required. Property Map

A description of resources that to large degree are decided by Vertex AI, and require only a modest additional configuration.

createTime This property is required. String

Timestamp when the DeployedModel was created.

dedicatedResources This property is required. Property Map

A description of resources that are dedicated to the DeployedModel, and that need a higher degree of manual configuration.

disableExplanations This property is required. Boolean

If true, deploy the model without explainable feature, regardless the existence of Model.explanation_spec or explanation_spec.

displayName This property is required. String

The display name of the DeployedModel. If not provided upon creation, the Model's display_name is used.

enableAccessLogging This property is required. 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.

enableContainerLogging This property is required. Boolean

If true, the container of the DeployedModel instances will send stderr and stdout streams to Cloud Logging. Only supported for custom-trained Models and AutoML Tabular Models.

explanationSpec This property is required. 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 This property is required. 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 This property is required. String

The version ID of the model that is deployed.

privateEndpoints This property is required. 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 This property is required. 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.

sharedResources This property is required. String

The resource name of the shared DeploymentResourcePool to deploy on. Format: projects/{project}/locations/{location}/deploymentResourcePools/{deployment_resource_pool}

KmsKeyName This property is required. 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 This property is required. 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 This property is required. 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 This property is required. 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 This property is required. 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.

DataFormat This property is required. string

The format in which instances are given, if not specified, assume it's JSONL format. Currently only JSONL format is supported.

GcsSource This property is required. Pulumi.GoogleNative.Aiplatform.V1Beta1.Inputs.GoogleCloudAiplatformV1beta1GcsSourceResponse

The Cloud Storage location for the input instances.

DataFormat This property is required. string

The format in which instances are given, if not specified, assume it's JSONL format. Currently only JSONL format is supported.

GcsSource This property is required. GoogleCloudAiplatformV1beta1GcsSourceResponse

The Cloud Storage location for the input instances.

dataFormat This property is required. String

The format in which instances are given, if not specified, assume it's JSONL format. Currently only JSONL format is supported.

gcsSource This property is required. GoogleCloudAiplatformV1beta1GcsSourceResponse

The Cloud Storage location for the input instances.

data_format This property is required. str

The format in which instances are given, if not specified, assume it's JSONL format. Currently only JSONL format is supported.

gcs_source This property is required. GoogleCloudAiplatformV1beta1GcsSourceResponse

The Cloud Storage location for the input instances.

dataFormat This property is required. String

The format in which instances are given, if not specified, assume it's JSONL format. Currently only JSONL format is supported.

gcsSource This property is required. Property Map

The Cloud Storage location for the input instances.

ExampleGcsSource This property is required. Pulumi.GoogleNative.Aiplatform.V1Beta1.Inputs.GoogleCloudAiplatformV1beta1ExamplesExampleGcsSourceResponse

The Cloud Storage input instances.

GcsSource This property is required. Pulumi.GoogleNative.Aiplatform.V1Beta1.Inputs.GoogleCloudAiplatformV1beta1GcsSourceResponse

The Cloud Storage locations that contain the instances to be indexed for approximate nearest neighbor search.

NearestNeighborSearchConfig This property is required. object

The full configuration for the generated index, the semantics are the same as metadata and should match NearestNeighborSearchConfig.

NeighborCount This property is required. int

The number of neighbors to return when querying for examples.

Presets This property is required. Pulumi.GoogleNative.Aiplatform.V1Beta1.Inputs.GoogleCloudAiplatformV1beta1PresetsResponse

Simplified preset configuration, which automatically sets configuration values based on the desired query speed-precision trade-off and modality.

ExampleGcsSource This property is required. GoogleCloudAiplatformV1beta1ExamplesExampleGcsSourceResponse

The Cloud Storage input instances.

GcsSource This property is required. GoogleCloudAiplatformV1beta1GcsSourceResponse

The Cloud Storage locations that contain the instances to be indexed for approximate nearest neighbor search.

NearestNeighborSearchConfig This property is required. interface{}

The full configuration for the generated index, the semantics are the same as metadata and should match NearestNeighborSearchConfig.

NeighborCount This property is required. int

The number of neighbors to return when querying for examples.

Presets This property is required. GoogleCloudAiplatformV1beta1PresetsResponse

Simplified preset configuration, which automatically sets configuration values based on the desired query speed-precision trade-off and modality.

exampleGcsSource This property is required. GoogleCloudAiplatformV1beta1ExamplesExampleGcsSourceResponse

The Cloud Storage input instances.

gcsSource This property is required. GoogleCloudAiplatformV1beta1GcsSourceResponse

The Cloud Storage locations that contain the instances to be indexed for approximate nearest neighbor search.

nearestNeighborSearchConfig This property is required. Object

The full configuration for the generated index, the semantics are the same as metadata and should match NearestNeighborSearchConfig.

neighborCount This property is required. Integer

The number of neighbors to return when querying for examples.

presets This property is required. GoogleCloudAiplatformV1beta1PresetsResponse

Simplified preset configuration, which automatically sets configuration values based on the desired query speed-precision trade-off and modality.

example_gcs_source This property is required. GoogleCloudAiplatformV1beta1ExamplesExampleGcsSourceResponse

The Cloud Storage input instances.

gcs_source This property is required. GoogleCloudAiplatformV1beta1GcsSourceResponse

The Cloud Storage locations that contain the instances to be indexed for approximate nearest neighbor search.

nearest_neighbor_search_config This property is required. Any

The full configuration for the generated index, the semantics are the same as metadata and should match NearestNeighborSearchConfig.

neighbor_count This property is required. int

The number of neighbors to return when querying for examples.

presets This property is required. GoogleCloudAiplatformV1beta1PresetsResponse

Simplified preset configuration, which automatically sets configuration values based on the desired query speed-precision trade-off and modality.

exampleGcsSource This property is required. Property Map

The Cloud Storage input instances.

gcsSource This property is required. Property Map

The Cloud Storage locations that contain the instances to be indexed for approximate nearest neighbor search.

nearestNeighborSearchConfig This property is required. Any

The full configuration for the generated index, the semantics are the same as metadata and should match NearestNeighborSearchConfig.

neighborCount This property is required. Number

The number of neighbors to return when querying for examples.

presets This property is required. Property Map

Simplified preset configuration, which automatically sets configuration values based on the desired query speed-precision trade-off and modality.

FeatureAttributionsSchemaUri This property is required. 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 This property is required. 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 This property is required. string

Name of the source to generate embeddings for example based explanations.

Outputs This property is required. 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 This property is required. 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 This property is required. 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 This property is required. string

Name of the source to generate embeddings for example based explanations.

Outputs This property is required. 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 This property is required. 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 This property is required. 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 This property is required. String

Name of the source to generate embeddings for example based explanations.

outputs This property is required. 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.

feature_attributions_schema_uri This property is required. 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 This property is required. 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 This property is required. str

Name of the source to generate embeddings for example based explanations.

outputs This property is required. 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 This property is required. 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 This property is required. 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 This property is required. String

Name of the source to generate embeddings for example based explanations.

outputs This property is required. 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.

Examples This property is required. Pulumi.GoogleNative.Aiplatform.V1Beta1.Inputs.GoogleCloudAiplatformV1beta1ExamplesResponse

Example-based explanations that returns the nearest neighbors from the provided dataset.

IntegratedGradientsAttribution This property is required. Pulumi.GoogleNative.Aiplatform.V1Beta1.Inputs.GoogleCloudAiplatformV1beta1IntegratedGradientsAttributionResponse

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 This property is required. 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 This property is required. Pulumi.GoogleNative.Aiplatform.V1Beta1.Inputs.GoogleCloudAiplatformV1beta1SampledShapleyAttributionResponse

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 This property is required. 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 This property is required. Pulumi.GoogleNative.Aiplatform.V1Beta1.Inputs.GoogleCloudAiplatformV1beta1XraiAttributionResponse

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 This property is required. GoogleCloudAiplatformV1beta1ExamplesResponse

Example-based explanations that returns the nearest neighbors from the provided dataset.

IntegratedGradientsAttribution This property is required. GoogleCloudAiplatformV1beta1IntegratedGradientsAttributionResponse

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 This property is required. []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 This property is required. GoogleCloudAiplatformV1beta1SampledShapleyAttributionResponse

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 This property is required. 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 This property is required. GoogleCloudAiplatformV1beta1XraiAttributionResponse

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 This property is required. GoogleCloudAiplatformV1beta1ExamplesResponse

Example-based explanations that returns the nearest neighbors from the provided dataset.

integratedGradientsAttribution This property is required. GoogleCloudAiplatformV1beta1IntegratedGradientsAttributionResponse

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 This property is required. 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 This property is required. GoogleCloudAiplatformV1beta1SampledShapleyAttributionResponse

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 This property is required. 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 This property is required. GoogleCloudAiplatformV1beta1XraiAttributionResponse

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 This property is required. GoogleCloudAiplatformV1beta1ExamplesResponse

Example-based explanations that returns the nearest neighbors from the provided dataset.

integrated_gradients_attribution This property is required. GoogleCloudAiplatformV1beta1IntegratedGradientsAttributionResponse

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 This property is required. 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 This property is required. GoogleCloudAiplatformV1beta1SampledShapleyAttributionResponse

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 This property is required. 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 This property is required. GoogleCloudAiplatformV1beta1XraiAttributionResponse

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 This property is required. Property Map

Example-based explanations that returns the nearest neighbors from the provided dataset.

integratedGradientsAttribution This property is required. 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 This property is required. 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 This property is required. Property Map

An attribution method that approximates Shapley values for features that contribute to the label being predicted. A sampling strategy is used to approximate the value rather than considering all subsets of features. Refer to this paper for model details: https://arxiv.org/abs/1306.4265.

topK This property is required. 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 This property is required. 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.

Metadata This property is required. Pulumi.GoogleNative.Aiplatform.V1Beta1.Inputs.GoogleCloudAiplatformV1beta1ExplanationMetadataResponse

Optional. Metadata describing the Model's input and output for explanation.

Parameters This property is required. Pulumi.GoogleNative.Aiplatform.V1Beta1.Inputs.GoogleCloudAiplatformV1beta1ExplanationParametersResponse

Parameters that configure explaining of the Model's predictions.

Metadata This property is required. GoogleCloudAiplatformV1beta1ExplanationMetadataResponse

Optional. Metadata describing the Model's input and output for explanation.

Parameters This property is required. GoogleCloudAiplatformV1beta1ExplanationParametersResponse

Parameters that configure explaining of the Model's predictions.

metadata This property is required. GoogleCloudAiplatformV1beta1ExplanationMetadataResponse

Optional. Metadata describing the Model's input and output for explanation.

parameters This property is required. GoogleCloudAiplatformV1beta1ExplanationParametersResponse

Parameters that configure explaining of the Model's predictions.

metadata This property is required. GoogleCloudAiplatformV1beta1ExplanationMetadataResponse

Optional. Metadata describing the Model's input and output for explanation.

parameters This property is required. GoogleCloudAiplatformV1beta1ExplanationParametersResponse

Parameters that configure explaining of the Model's predictions.

metadata This property is required. Property Map

Optional. Metadata describing the Model's input and output for explanation.

parameters This property is required. Property Map

Parameters that configure explaining of the Model's predictions.

Name This property is required. string

The name of the input feature for which noise sigma is provided. The features are defined in explanation metadata inputs.

Sigma This property is required. 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 This property is required. string

The name of the input feature for which noise sigma is provided. The features are defined in explanation metadata inputs.

Sigma This property is required. 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 This property is required. String

The name of the input feature for which noise sigma is provided. The features are defined in explanation metadata inputs.

sigma This property is required. 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 This property is required. str

The name of the input feature for which noise sigma is provided. The features are defined in explanation metadata inputs.

sigma This property is required. 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 This property is required. String

The name of the input feature for which noise sigma is provided. The features are defined in explanation metadata inputs.

sigma This property is required. 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.

NoiseSigma This property is required. List<Pulumi.GoogleNative.Aiplatform.V1Beta1.Inputs.GoogleCloudAiplatformV1beta1FeatureNoiseSigmaNoiseSigmaForFeatureResponse>

Noise sigma per feature. No noise is added to features that are not set.

NoiseSigma This property is required. []GoogleCloudAiplatformV1beta1FeatureNoiseSigmaNoiseSigmaForFeatureResponse

Noise sigma per feature. No noise is added to features that are not set.

noiseSigma This property is required. List<GoogleCloudAiplatformV1beta1FeatureNoiseSigmaNoiseSigmaForFeatureResponse>

Noise sigma per feature. No noise is added to features that are not set.

noise_sigma This property is required. Sequence[GoogleCloudAiplatformV1beta1FeatureNoiseSigmaNoiseSigmaForFeatureResponse]

Noise sigma per feature. No noise is added to features that are not set.

noiseSigma This property is required. List<Property Map>

Noise sigma per feature. No noise is added to features that are not set.

Uris This property is required. 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 This property is required. []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 This property is required. 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 This property is required. 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 This property is required. 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.

BlurBaselineConfig This property is required. Pulumi.GoogleNative.Aiplatform.V1Beta1.Inputs.GoogleCloudAiplatformV1beta1BlurBaselineConfigResponse

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 This property is required. Pulumi.GoogleNative.Aiplatform.V1Beta1.Inputs.GoogleCloudAiplatformV1beta1SmoothGradConfigResponse

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 This property is required. 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 This property is required. GoogleCloudAiplatformV1beta1BlurBaselineConfigResponse

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 This property is required. GoogleCloudAiplatformV1beta1SmoothGradConfigResponse

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 This property is required. 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 This property is required. GoogleCloudAiplatformV1beta1BlurBaselineConfigResponse

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 This property is required. GoogleCloudAiplatformV1beta1SmoothGradConfigResponse

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 This property is required. 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.

blur_baseline_config This property is required. GoogleCloudAiplatformV1beta1BlurBaselineConfigResponse

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 This property is required. GoogleCloudAiplatformV1beta1SmoothGradConfigResponse

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 This property is required. 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 This property is required. 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 This property is required. 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 This property is required. 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.

AcceleratorCount This property is required. int

The number of accelerators to attach to the machine.

AcceleratorType This property is required. string

Immutable. The type of accelerator(s) that may be attached to the machine as per accelerator_count.

MachineType This property is required. 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 This property is required. string

Immutable. The topology of the TPUs. Corresponds to the TPU topologies available from GKE. (Example: tpu_topology: "2x2x1").

AcceleratorCount This property is required. int

The number of accelerators to attach to the machine.

AcceleratorType This property is required. string

Immutable. The type of accelerator(s) that may be attached to the machine as per accelerator_count.

MachineType This property is required. 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 This property is required. string

Immutable. The topology of the TPUs. Corresponds to the TPU topologies available from GKE. (Example: tpu_topology: "2x2x1").

acceleratorCount This property is required. Integer

The number of accelerators to attach to the machine.

acceleratorType This property is required. String

Immutable. The type of accelerator(s) that may be attached to the machine as per accelerator_count.

machineType This property is required. 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 This property is required. String

Immutable. The topology of the TPUs. Corresponds to the TPU topologies available from GKE. (Example: tpu_topology: "2x2x1").

accelerator_count This property is required. int

The number of accelerators to attach to the machine.

accelerator_type This property is required. str

Immutable. The type of accelerator(s) that may be attached to the machine as per accelerator_count.

machine_type This property is required. 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 This property is required. str

Immutable. The topology of the TPUs. Corresponds to the TPU topologies available from GKE. (Example: tpu_topology: "2x2x1").

acceleratorCount This property is required. Number

The number of accelerators to attach to the machine.

acceleratorType This property is required. String

Immutable. The type of accelerator(s) that may be attached to the machine as per accelerator_count.

machineType This property is required. 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 This property is required. String

Immutable. The topology of the TPUs. Corresponds to the TPU topologies available from GKE. (Example: tpu_topology: "2x2x1").

BigqueryDestination This property is required. Pulumi.GoogleNative.Aiplatform.V1Beta1.Inputs.GoogleCloudAiplatformV1beta1BigQueryDestinationResponse

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 This property is required. bool

If logging is enabled or not.

SamplingRate This property is required. double

Percentage of requests to be logged, expressed as a fraction in range(0,1].

BigqueryDestination This property is required. GoogleCloudAiplatformV1beta1BigQueryDestinationResponse

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 This property is required. bool

If logging is enabled or not.

SamplingRate This property is required. float64

Percentage of requests to be logged, expressed as a fraction in range(0,1].

bigqueryDestination This property is required. GoogleCloudAiplatformV1beta1BigQueryDestinationResponse

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 This property is required. Boolean

If logging is enabled or not.

samplingRate This property is required. Double

Percentage of requests to be logged, expressed as a fraction in range(0,1].

bigquery_destination This property is required. GoogleCloudAiplatformV1beta1BigQueryDestinationResponse

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 This property is required. bool

If logging is enabled or not.

sampling_rate This property is required. float

Percentage of requests to be logged, expressed as a fraction in range(0,1].

bigqueryDestination This property is required. 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 This property is required. Boolean

If logging is enabled or not.

samplingRate This property is required. Number

Percentage of requests to be logged, expressed as a fraction in range(0,1].

Modality This property is required. 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 This property is required. string

Preset option controlling parameters for speed-precision trade-off when querying for examples. If omitted, defaults to PRECISE.

Modality This property is required. 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 This property is required. string

Preset option controlling parameters for speed-precision trade-off when querying for examples. If omitted, defaults to PRECISE.

modality This property is required. 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 This property is required. String

Preset option controlling parameters for speed-precision trade-off when querying for examples. If omitted, defaults to PRECISE.

modality This property is required. 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 This property is required. str

Preset option controlling parameters for speed-precision trade-off when querying for examples. If omitted, defaults to PRECISE.

modality This property is required. 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 This property is required. String

Preset option controlling parameters for speed-precision trade-off when querying for examples. If omitted, defaults to PRECISE.

ExplainHttpUri This property is required. string

Http(s) path to send explain requests.

HealthHttpUri This property is required. string

Http(s) path to send health check requests.

PredictHttpUri This property is required. string

Http(s) path to send prediction requests.

ServiceAttachment This property is required. string

The name of the service attachment resource. Populated if private service connect is enabled.

ExplainHttpUri This property is required. string

Http(s) path to send explain requests.

HealthHttpUri This property is required. string

Http(s) path to send health check requests.

PredictHttpUri This property is required. string

Http(s) path to send prediction requests.

ServiceAttachment This property is required. string

The name of the service attachment resource. Populated if private service connect is enabled.

explainHttpUri This property is required. String

Http(s) path to send explain requests.

healthHttpUri This property is required. String

Http(s) path to send health check requests.

predictHttpUri This property is required. String

Http(s) path to send prediction requests.

serviceAttachment This property is required. String

The name of the service attachment resource. Populated if private service connect is enabled.

explain_http_uri This property is required. str

Http(s) path to send explain requests.

health_http_uri This property is required. str

Http(s) path to send health check requests.

predict_http_uri This property is required. str

Http(s) path to send prediction requests.

service_attachment This property is required. str

The name of the service attachment resource. Populated if private service connect is enabled.

explainHttpUri This property is required. String

Http(s) path to send explain requests.

healthHttpUri This property is required. String

Http(s) path to send health check requests.

predictHttpUri This property is required. String

Http(s) path to send prediction requests.

serviceAttachment This property is required. String

The name of the service attachment resource. Populated if private service connect is enabled.

PathCount This property is required. int

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

PathCount This property is required. int

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

pathCount This property is required. Integer

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

path_count This property is required. int

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

pathCount This property is required. Number

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

FeatureNoiseSigma This property is required. Pulumi.GoogleNative.Aiplatform.V1Beta1.Inputs.GoogleCloudAiplatformV1beta1FeatureNoiseSigmaResponse

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 This property is required. 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 This property is required. 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 This property is required. GoogleCloudAiplatformV1beta1FeatureNoiseSigmaResponse

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 This property is required. 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 This property is required. 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 This property is required. GoogleCloudAiplatformV1beta1FeatureNoiseSigmaResponse

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 This property is required. 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 This property is required. 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.

feature_noise_sigma This property is required. GoogleCloudAiplatformV1beta1FeatureNoiseSigmaResponse

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 This property is required. 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 This property is required. 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 This property is required. 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 This property is required. 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 This property is required. 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.

BlurBaselineConfig This property is required. Pulumi.GoogleNative.Aiplatform.V1Beta1.Inputs.GoogleCloudAiplatformV1beta1BlurBaselineConfigResponse

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 This property is required. Pulumi.GoogleNative.Aiplatform.V1Beta1.Inputs.GoogleCloudAiplatformV1beta1SmoothGradConfigResponse

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 This property is required. 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 This property is required. GoogleCloudAiplatformV1beta1BlurBaselineConfigResponse

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 This property is required. GoogleCloudAiplatformV1beta1SmoothGradConfigResponse

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 This property is required. 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 This property is required. GoogleCloudAiplatformV1beta1BlurBaselineConfigResponse

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 This property is required. GoogleCloudAiplatformV1beta1SmoothGradConfigResponse

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 This property is required. 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.

blur_baseline_config This property is required. GoogleCloudAiplatformV1beta1BlurBaselineConfigResponse

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 This property is required. GoogleCloudAiplatformV1beta1SmoothGradConfigResponse

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 This property is required. 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 This property is required. 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 This property is required. 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 This property is required. 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.