Class ModelDeploymentMonitoringJob (3.30.0)

Represents a job that runs periodically to monitor the deployed models in an endpoint. It will analyze the logged training & prediction data to detect any abnormal behaviors.

Protobuf type google.cloud.aiplatform.v1.ModelDeploymentMonitoringJob

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.

map<string, string> labels = 11;

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.

string analysis_instance_schema_uri = 16;

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.

string analysis_instance_schema_uri = 16;

Output only. The created bigquery tables for the job under customer project. Customer could do their own query & analysis. There could be 4 log tables in maximum:

1. Training data logging predict request/response
2. Serving data logging predict request/response

repeated .google.cloud.aiplatform.v1.ModelDeploymentMonitoringBigQueryTable bigquery_tables = 10 [(.google.api.field_behavior) = OUTPUT_ONLY];

Output only. The created bigquery tables for the job under customer project. Customer could do their own query & analysis. There could be 4 log tables in maximum:

1. Training data logging predict request/response
2. Serving data logging predict request/response

repeated .google.cloud.aiplatform.v1.ModelDeploymentMonitoringBigQueryTable bigquery_tables = 10 [(.google.api.field_behavior) = OUTPUT_ONLY];

Output only. The created bigquery tables for the job under customer project. Customer could do their own query & analysis. There could be 4 log tables in maximum:

1. Training data logging predict request/response
2. Serving data logging predict request/response

repeated .google.cloud.aiplatform.v1.ModelDeploymentMonitoringBigQueryTable bigquery_tables = 10 [(.google.api.field_behavior) = OUTPUT_ONLY];

Output only. The created bigquery tables for the job under customer project. Customer could do their own query & analysis. There could be 4 log tables in maximum:

1. Training data logging predict request/response
2. Serving data logging predict request/response

repeated .google.cloud.aiplatform.v1.ModelDeploymentMonitoringBigQueryTable bigquery_tables = 10 [(.google.api.field_behavior) = OUTPUT_ONLY];

Output only. The created bigquery tables for the job under customer project. Customer could do their own query & analysis. There could be 4 log tables in maximum:

1. Training data logging predict request/response
2. Serving data logging predict request/response

repeated .google.cloud.aiplatform.v1.ModelDeploymentMonitoringBigQueryTable bigquery_tables = 10 [(.google.api.field_behavior) = OUTPUT_ONLY];

Output only. Timestamp when this ModelDeploymentMonitoringJob was created.

.google.protobuf.Timestamp create_time = 12 [(.google.api.field_behavior) = OUTPUT_ONLY];

Output only. Timestamp when this ModelDeploymentMonitoringJob was created.

.google.protobuf.Timestamp create_time = 12 [(.google.api.field_behavior) = OUTPUT_ONLY];

Required. 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.

string display_name = 2 [(.google.api.field_behavior) = REQUIRED];

Required. 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.

string display_name = 2 [(.google.api.field_behavior) = REQUIRED];

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.

bool enable_monitoring_pipeline_logs = 22;

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.

.google.cloud.aiplatform.v1.EncryptionSpec encryption_spec = 21;

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.

.google.cloud.aiplatform.v1.EncryptionSpec encryption_spec = 21;

Required. Endpoint resource name. Format: projects/{project}/locations/{location}/endpoints/{endpoint}

string endpoint = 3 [(.google.api.field_behavior) = REQUIRED, (.google.api.resource_reference) = { ... }

Required. Endpoint resource name. Format: projects/{project}/locations/{location}/endpoints/{endpoint}

string endpoint = 3 [(.google.api.field_behavior) = REQUIRED, (.google.api.resource_reference) = { ... }

Output only. Only populated when the job's state is JOB_STATE_FAILED or JOB_STATE_CANCELLED.

.google.rpc.Status error = 23 [(.google.api.field_behavior) = OUTPUT_ONLY];

Output only. Only populated when the job's state is JOB_STATE_FAILED or JOB_STATE_CANCELLED.

.google.rpc.Status error = 23 [(.google.api.field_behavior) = OUTPUT_ONLY];

Use #getLabelsMap() instead.

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.

map<string, string> labels = 11;

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.

map<string, string> labels = 11;

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.

map<string, string> labels = 11;

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.

map<string, string> labels = 11;

Output only. Latest triggered monitoring pipeline metadata.

.google.cloud.aiplatform.v1.ModelDeploymentMonitoringJob.LatestMonitoringPipelineMetadata latest_monitoring_pipeline_metadata = 25 [(.google.api.field_behavior) = OUTPUT_ONLY];

Output only. Latest triggered monitoring pipeline metadata.

.google.cloud.aiplatform.v1.ModelDeploymentMonitoringJob.LatestMonitoringPipelineMetadata latest_monitoring_pipeline_metadata = 25 [(.google.api.field_behavior) = OUTPUT_ONLY];

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.

.google.protobuf.Duration log_ttl = 17;

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.

.google.protobuf.Duration log_ttl = 17;

Required. Sample Strategy for logging.

.google.cloud.aiplatform.v1.SamplingStrategy logging_sampling_strategy = 8 [(.google.api.field_behavior) = REQUIRED];

Required. Sample Strategy for logging.

.google.cloud.aiplatform.v1.SamplingStrategy logging_sampling_strategy = 8 [(.google.api.field_behavior) = REQUIRED];

Required. The config for monitoring objectives. This is a per DeployedModel config. Each DeployedModel needs to be configured separately.

repeated .google.cloud.aiplatform.v1.ModelDeploymentMonitoringObjectiveConfig model_deployment_monitoring_objective_configs = 6 [(.google.api.field_behavior) = REQUIRED];

Required. The config for monitoring objectives. This is a per DeployedModel config. Each DeployedModel needs to be configured separately.

repeated .google.cloud.aiplatform.v1.ModelDeploymentMonitoringObjectiveConfig model_deployment_monitoring_objective_configs = 6 [(.google.api.field_behavior) = REQUIRED];

Required. The config for monitoring objectives. This is a per DeployedModel config. Each DeployedModel needs to be configured separately.

repeated .google.cloud.aiplatform.v1.ModelDeploymentMonitoringObjectiveConfig model_deployment_monitoring_objective_configs = 6 [(.google.api.field_behavior) = REQUIRED];

Required. The config for monitoring objectives. This is a per DeployedModel config. Each DeployedModel needs to be configured separately.

repeated .google.cloud.aiplatform.v1.ModelDeploymentMonitoringObjectiveConfig model_deployment_monitoring_objective_configs = 6 [(.google.api.field_behavior) = REQUIRED];

Required. The config for monitoring objectives. This is a per DeployedModel config. Each DeployedModel needs to be configured separately.

repeated .google.cloud.aiplatform.v1.ModelDeploymentMonitoringObjectiveConfig model_deployment_monitoring_objective_configs = 6 [(.google.api.field_behavior) = REQUIRED];

Required. Schedule config for running the monitoring job.

.google.cloud.aiplatform.v1.ModelDeploymentMonitoringScheduleConfig model_deployment_monitoring_schedule_config = 7 [(.google.api.field_behavior) = REQUIRED];

Required. Schedule config for running the monitoring job.

.google.cloud.aiplatform.v1.ModelDeploymentMonitoringScheduleConfig model_deployment_monitoring_schedule_config = 7 [(.google.api.field_behavior) = REQUIRED];

Alert config for model monitoring.

.google.cloud.aiplatform.v1.ModelMonitoringAlertConfig model_monitoring_alert_config = 15;

Alert config for model monitoring.

.google.cloud.aiplatform.v1.ModelMonitoringAlertConfig model_monitoring_alert_config = 15;

Output only. Resource name of a ModelDeploymentMonitoringJob.

string name = 1 [(.google.api.field_behavior) = OUTPUT_ONLY];

Output only. Resource name of a ModelDeploymentMonitoringJob.

string name = 1 [(.google.api.field_behavior) = OUTPUT_ONLY];

Output only. Timestamp when this monitoring pipeline will be scheduled to run for the next round.

.google.protobuf.Timestamp next_schedule_time = 14 [(.google.api.field_behavior) = OUTPUT_ONLY];

Output only. Timestamp when this monitoring pipeline will be scheduled to run for the next round.

.google.protobuf.Timestamp next_schedule_time = 14 [(.google.api.field_behavior) = OUTPUT_ONLY];

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.

string predict_instance_schema_uri = 9;

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.

string predict_instance_schema_uri = 9;

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.

.google.protobuf.Value sample_predict_instance = 19;

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.

.google.protobuf.Value sample_predict_instance = 19;

Output only. Schedule state when the monitoring job is in Running state.

.google.cloud.aiplatform.v1.ModelDeploymentMonitoringJob.MonitoringScheduleState schedule_state = 5 [(.google.api.field_behavior) = OUTPUT_ONLY];

Output only. Schedule state when the monitoring job is in Running state.

.google.cloud.aiplatform.v1.ModelDeploymentMonitoringJob.MonitoringScheduleState schedule_state = 5 [(.google.api.field_behavior) = OUTPUT_ONLY];

Output only. The detailed state of the monitoring job. When the job is still creating, the state will be 'PENDING'. Once the job is successfully created, the state will be 'RUNNING'. Pause the job, the state will be 'PAUSED'. Resume the job, the state will return to 'RUNNING'.

.google.cloud.aiplatform.v1.JobState state = 4 [(.google.api.field_behavior) = OUTPUT_ONLY];

Output only. The detailed state of the monitoring job. When the job is still creating, the state will be 'PENDING'. Once the job is successfully created, the state will be 'RUNNING'. Pause the job, the state will be 'PAUSED'. Resume the job, the state will return to 'RUNNING'.

.google.cloud.aiplatform.v1.JobState state = 4 [(.google.api.field_behavior) = OUTPUT_ONLY];

Stats anomalies base folder path.

.google.cloud.aiplatform.v1.GcsDestination stats_anomalies_base_directory = 20;

Stats anomalies base folder path.

.google.cloud.aiplatform.v1.GcsDestination stats_anomalies_base_directory = 20;

Output only. Timestamp when this ModelDeploymentMonitoringJob was updated most recently.

.google.protobuf.Timestamp update_time = 13 [(.google.api.field_behavior) = OUTPUT_ONLY];

Output only. Timestamp when this ModelDeploymentMonitoringJob was updated most recently.

.google.protobuf.Timestamp update_time = 13 [(.google.api.field_behavior) = OUTPUT_ONLY];

Output only. Timestamp when this ModelDeploymentMonitoringJob was created.

.google.protobuf.Timestamp create_time = 12 [(.google.api.field_behavior) = OUTPUT_ONLY];

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.

.google.cloud.aiplatform.v1.EncryptionSpec encryption_spec = 21;

Output only. Only populated when the job's state is JOB_STATE_FAILED or JOB_STATE_CANCELLED.

.google.rpc.Status error = 23 [(.google.api.field_behavior) = OUTPUT_ONLY];

Output only. Latest triggered monitoring pipeline metadata.

.google.cloud.aiplatform.v1.ModelDeploymentMonitoringJob.LatestMonitoringPipelineMetadata latest_monitoring_pipeline_metadata = 25 [(.google.api.field_behavior) = OUTPUT_ONLY];

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.

.google.protobuf.Duration log_ttl = 17;

Required. Sample Strategy for logging.

.google.cloud.aiplatform.v1.SamplingStrategy logging_sampling_strategy = 8 [(.google.api.field_behavior) = REQUIRED];

Required. Schedule config for running the monitoring job.

.google.cloud.aiplatform.v1.ModelDeploymentMonitoringScheduleConfig model_deployment_monitoring_schedule_config = 7 [(.google.api.field_behavior) = REQUIRED];

Alert config for model monitoring.

.google.cloud.aiplatform.v1.ModelMonitoringAlertConfig model_monitoring_alert_config = 15;

Output only. Timestamp when this monitoring pipeline will be scheduled to run for the next round.

.google.protobuf.Timestamp next_schedule_time = 14 [(.google.api.field_behavior) = OUTPUT_ONLY];

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.

.google.protobuf.Value sample_predict_instance = 19;

Stats anomalies base folder path.

.google.cloud.aiplatform.v1.GcsDestination stats_anomalies_base_directory = 20;

Output only. Timestamp when this ModelDeploymentMonitoringJob was updated most recently.

.google.protobuf.Timestamp update_time = 13 [(.google.api.field_behavior) = OUTPUT_ONLY];