ModelDeploymentMonitoringJobArgs class

The set of arguments for ModelDeploymentMonitoringJob. The set of arguments for ModelDeploymentMonitoringJob.

Constructors

ModelDeploymentMonitoringJobArgs({Input<String>? analysisInstanceSchemaUri, required Input<String> displayName, Input<bool>? enableMonitoringPipelineLogs, Input<GoogleCloudAiplatformV1EncryptionSpec>? encryptionSpec, required Input<String> endpoint, Input<Map<String, String>>? labels, Input<String>? location, Input<String>? logTtl, required Input<GoogleCloudAiplatformV1SamplingStrategy> loggingSamplingStrategy, required Input<List<GoogleCloudAiplatformV1ModelDeploymentMonitoringObjectiveConfig>> modelDeploymentMonitoringObjectiveConfigs, required Input<GoogleCloudAiplatformV1ModelDeploymentMonitoringScheduleConfig> modelDeploymentMonitoringScheduleConfig, Input<GoogleCloudAiplatformV1ModelMonitoringAlertConfig>? modelMonitoringAlertConfig, Input<String>? predictInstanceSchemaUri, Input<String>? project, Input? samplePredictInstance, Input<GoogleCloudAiplatformV1GcsDestination>? statsAnomaliesBaseDirectory})
Creates a new ModelDeploymentMonitoringJobArgs. analysisInstanceSchemaUri YAML schema file uri describing the format of a single instance that you want Tensorflow Data Validation (TFDV) to analyze. If this field is empty, all the feature data types are inferred from predict_instance_schema_uri, meaning that TFDV will use the data in the exact format(data type) as prediction request/response. If there are any data type differences between predict instance and TFDV instance, this field can be used to override the schema. For models trained with Vertex AI, this field must be set as all the fields in predict instance formatted as string. displayName The user-defined name of the ModelDeploymentMonitoringJob. The name can be up to 128 characters long and can consist of any UTF-8 characters. Display name of a ModelDeploymentMonitoringJob. enableMonitoringPipelineLogs If true, the scheduled monitoring pipeline logs are sent to Google Cloud Logging, including pipeline status and anomalies detected. Please note the logs incur cost, which are subject to Cloud Logging pricing. encryptionSpec Customer-managed encryption key spec for a ModelDeploymentMonitoringJob. If set, this ModelDeploymentMonitoringJob and all sub-resources of this ModelDeploymentMonitoringJob will be secured by this key. endpoint Endpoint resource name. Format: projects/{project}/locations/{location}/endpoints/{endpoint} labels The labels with user-defined metadata to organize your ModelDeploymentMonitoringJob. Label keys and values can be no longer than 64 characters (Unicode codepoints), can only contain lowercase letters, numeric characters, underscores and dashes. International characters are allowed. See https://goo.gl/xmQnxf for more information and examples of labels. location Optional. logTtl The TTL of BigQuery tables in user projects which stores logs. A day is the basic unit of the TTL and we take the ceil of TTL/86400(a day). e.g. { second: 3600} indicates ttl = 1 day. loggingSamplingStrategy Sample Strategy for logging. modelDeploymentMonitoringObjectiveConfigs The config for monitoring objectives. This is a per DeployedModel config. Each DeployedModel needs to be configured separately. modelDeploymentMonitoringScheduleConfig Schedule config for running the monitoring job. modelMonitoringAlertConfig Alert config for model monitoring. predictInstanceSchemaUri YAML schema file uri describing the format of a single instance, which are given to format this Endpoint's prediction (and explanation). If not set, we will generate predict schema from collected predict requests. project Optional. samplePredictInstance Sample Predict instance, same format as PredictRequest.instances, this can be set as a replacement of ModelDeploymentMonitoringJob.predict_instance_schema_uri. If not set, we will generate predict schema from collected predict requests. statsAnomaliesBaseDirectory Stats anomalies base folder path.
const
ModelDeploymentMonitoringJobArgs.fromMap(Map<String, dynamic> map)
factory

Properties

analysisInstanceSchemaUri → Input<String>?
YAML schema file uri describing the format of a single instance that you want Tensorflow Data Validation (TFDV) to analyze. If this field is empty, all the feature data types are inferred from predict_instance_schema_uri, meaning that TFDV will use the data in the exact format(data type) as prediction request/response. If there are any data type differences between predict instance and TFDV instance, this field can be used to override the schema. For models trained with Vertex AI, this field must be set as all the fields in predict instance formatted as string.
final
displayName → Input<String>
The user-defined name of the ModelDeploymentMonitoringJob. The name can be up to 128 characters long and can consist of any UTF-8 characters. Display name of a ModelDeploymentMonitoringJob.
final
enableMonitoringPipelineLogs → Input<bool>?
If true, the scheduled monitoring pipeline logs are sent to Google Cloud Logging, including pipeline status and anomalies detected. Please note the logs incur cost, which are subject to Cloud Logging pricing.
final
encryptionSpec → Input<GoogleCloudAiplatformV1EncryptionSpec>?
Customer-managed encryption key spec for a ModelDeploymentMonitoringJob. If set, this ModelDeploymentMonitoringJob and all sub-resources of this ModelDeploymentMonitoringJob will be secured by this key.
final
endpoint → Input<String>
Endpoint resource name. Format: projects/{project}/locations/{location}/endpoints/{endpoint}
final
hashCode → int
The hash code for this object.
no setterinherited
labels → Input<Map<String, String>>?
The labels with user-defined metadata to organize your ModelDeploymentMonitoringJob. 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.
final
location → Input<String>?
final
loggingSamplingStrategy → Input<GoogleCloudAiplatformV1SamplingStrategy>
Sample Strategy for logging.
final
logTtl → Input<String>?
The TTL of BigQuery tables in user projects which stores logs. A day is the basic unit of the TTL and we take the ceil of TTL/86400(a day). e.g. { second: 3600} indicates ttl = 1 day.
final
modelDeploymentMonitoringObjectiveConfigs → Input<List<GoogleCloudAiplatformV1ModelDeploymentMonitoringObjectiveConfig>>
The config for monitoring objectives. This is a per DeployedModel config. Each DeployedModel needs to be configured separately.
final
modelDeploymentMonitoringScheduleConfig → Input<GoogleCloudAiplatformV1ModelDeploymentMonitoringScheduleConfig>
Schedule config for running the monitoring job.
final
modelMonitoringAlertConfig → Input<GoogleCloudAiplatformV1ModelMonitoringAlertConfig>?
Alert config for model monitoring.
final
predictInstanceSchemaUri → Input<String>?
YAML schema file uri describing the format of a single instance, which are given to format this Endpoint's prediction (and explanation). If not set, we will generate predict schema from collected predict requests.
final
project → Input<String>?
final
runtimeType → Type
A representation of the runtime type of the object.
no setterinherited
samplePredictInstance → Input?
Sample Predict instance, same format as PredictRequest.instances, this can be set as a replacement of ModelDeploymentMonitoringJob.predict_instance_schema_uri. If not set, we will generate predict schema from collected predict requests.
final
statsAnomaliesBaseDirectory → Input<GoogleCloudAiplatformV1GcsDestination>?
Stats anomalies base folder path.
final

Methods

noSuchMethod(Invocation invocation) → dynamic
Invoked when a nonexistent method or property is accessed.
inherited
toMap() → Map<String, dynamic>
toString() → String
A string representation of this object.
inherited

Operators

operator ==(Object other) → bool
The equality operator.
inherited