model_deployment_monitoring_jobs

Creates, updates, deletes, gets or lists a model_deployment_monitoring_jobs resource.

Overview

Name	model_deployment_monitoring_jobs
Type	Resource
Id	google.aiplatform.model_deployment_monitoring_jobs

Fields

Name	Datatype	Description
name	string	Output only. Resource name of a ModelDeploymentMonitoringJob.
analysisInstanceSchemaUri	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.
bigqueryTables	array	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
createTime	string	Output only. Timestamp when this ModelDeploymentMonitoringJob was created.
displayName	string	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.
enableMonitoringPipelineLogs	boolean	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	object	Represents a customer-managed encryption key spec that can be applied to a top-level resource.
endpoint	string	Required. Endpoint resource name. Format: projects/{project}/locations/{location}/endpoints/{endpoint}
error	object	The Status type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by gRPC. Each Status message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the API Design Guide.
labels	object	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.
latestMonitoringPipelineMetadata	object	All metadata of most recent monitoring pipelines.
logTtl	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.
loggingSamplingStrategy	object	Sampling Strategy for logging, can be for both training and prediction dataset.
modelDeploymentMonitoringObjectiveConfigs	array	Required. The config for monitoring objectives. This is a per DeployedModel config. Each DeployedModel needs to be configured separately.
modelDeploymentMonitoringScheduleConfig	object	The config for scheduling monitoring job.
modelMonitoringAlertConfig	object	The alert config for model monitoring.
nextScheduleTime	string	Output only. Timestamp when this monitoring pipeline will be scheduled to run for the next round.
predictInstanceSchemaUri	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.
samplePredictInstance	any	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.
satisfiesPzi	boolean	Output only. Reserved for future use.
satisfiesPzs	boolean	Output only. Reserved for future use.
scheduleState	string	Output only. Schedule state when the monitoring job is in Running state.
state	string	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'.
statsAnomaliesBaseDirectory	object	The Google Cloud Storage location where the output is to be written to.
updateTime	string	Output only. Timestamp when this ModelDeploymentMonitoringJob was updated most recently.

Methods

Name	Accessible by	Required Params	Description
get	SELECT	locationsId, modelDeploymentMonitoringJobsId, projectsId	Gets a ModelDeploymentMonitoringJob.
list	SELECT	locationsId, projectsId	Lists ModelDeploymentMonitoringJobs in a Location.
create	INSERT	locationsId, projectsId	Creates a ModelDeploymentMonitoringJob. It will run periodically on a configured interval.
delete	DELETE	locationsId, modelDeploymentMonitoringJobsId, projectsId	Deletes a ModelDeploymentMonitoringJob.
patch	UPDATE	locationsId, modelDeploymentMonitoringJobsId, projectsId	Updates a ModelDeploymentMonitoringJob.
pause	EXEC	locationsId, modelDeploymentMonitoringJobsId, projectsId	Pauses a ModelDeploymentMonitoringJob. If the job is running, the server makes a best effort to cancel the job. Will mark ModelDeploymentMonitoringJob.state to 'PAUSED'.
resume	EXEC	locationsId, modelDeploymentMonitoringJobsId, projectsId	Resumes a paused ModelDeploymentMonitoringJob. It will start to run from next scheduled time. A deleted ModelDeploymentMonitoringJob can't be resumed.
search_model_deployment_monitoring_stats_anomalies	EXEC	locationsId, modelDeploymentMonitoringJobsId, projectsId	Searches Model Monitoring Statistics generated within a given time window.

SELECT examples

Lists ModelDeploymentMonitoringJobs in a Location.

SELECT
name,
analysisInstanceSchemaUri,
bigqueryTables,
createTime,
displayName,
enableMonitoringPipelineLogs,
encryptionSpec,
endpoint,
error,
labels,
latestMonitoringPipelineMetadata,
logTtl,
loggingSamplingStrategy,
modelDeploymentMonitoringObjectiveConfigs,
modelDeploymentMonitoringScheduleConfig,
modelMonitoringAlertConfig,
nextScheduleTime,
predictInstanceSchemaUri,
samplePredictInstance,
satisfiesPzi,
satisfiesPzs,
scheduleState,
state,
statsAnomaliesBaseDirectory,
updateTime
FROM google.aiplatform.model_deployment_monitoring_jobs
WHERE locationsId = '{{ locationsId }}'
AND projectsId = '{{ projectsId }}';

INSERT example

Use the following StackQL query and manifest file to create a new model_deployment_monitoring_jobs resource.

All Properties

/*+ create */
INSERT INTO google.aiplatform.model_deployment_monitoring_jobs (
locationsId,
projectsId,
logTtl,
statsAnomaliesBaseDirectory,
enableMonitoringPipelineLogs,
labels,
modelDeploymentMonitoringScheduleConfig,
encryptionSpec,
predictInstanceSchemaUri,
analysisInstanceSchemaUri,
modelDeploymentMonitoringObjectiveConfigs,
samplePredictInstance,
loggingSamplingStrategy,
displayName,
endpoint,
modelMonitoringAlertConfig
)
SELECT 
'{{ locationsId }}',
'{{ projectsId }}',
'{{ logTtl }}',
'{{ statsAnomaliesBaseDirectory }}',
{{ enableMonitoringPipelineLogs }},
'{{ labels }}',
'{{ modelDeploymentMonitoringScheduleConfig }}',
'{{ encryptionSpec }}',
'{{ predictInstanceSchemaUri }}',
'{{ analysisInstanceSchemaUri }}',
'{{ modelDeploymentMonitoringObjectiveConfigs }}',
'{{ samplePredictInstance }}',
'{{ loggingSamplingStrategy }}',
'{{ displayName }}',
'{{ endpoint }}',
'{{ modelMonitoringAlertConfig }}'
;

Manifest

- name: your_resource_model_name
  props:
    - name: logTtl
      value: string
    - name: createTime
      value: string
    - name: statsAnomaliesBaseDirectory
      value:
        - name: outputUriPrefix
          value: string
    - name: enableMonitoringPipelineLogs
      value: boolean
    - name: latestMonitoringPipelineMetadata
      value:
        - name: runTime
          value: string
        - name: status
          value:
            - name: code
              value: integer
            - name: message
              value: string
            - name: details
              value:
                - object
    - name: labels
      value: object
    - name: modelDeploymentMonitoringScheduleConfig
      value:
        - name: monitorInterval
          value: string
        - name: monitorWindow
          value: string
    - name: encryptionSpec
      value:
        - name: kmsKeyName
          value: string
    - name: predictInstanceSchemaUri
      value: string
    - name: scheduleState
      value: string
    - name: satisfiesPzi
      value: boolean
    - name: analysisInstanceSchemaUri
      value: string
    - name: modelDeploymentMonitoringObjectiveConfigs
      value:
        - - name: objectiveConfig
            value:
              - name: trainingDataset
                value:
                  - name: dataset
                    value: string
                  - name: bigquerySource
                    value:
                      - name: inputUri
                        value: string
                  - name: loggingSamplingStrategy
                    value:
                      - name: randomSampleConfig
                        value:
                          - name: sampleRate
                            value: number
                  - name: gcsSource
                    value:
                      - name: uris
                        value:
                          - string
                  - name: targetField
                    value: string
                  - name: dataFormat
                    value: string
              - name: explanationConfig
                value:
                  - name: explanationBaseline
                    value:
                      - name: bigquery
                        value:
                          - name: outputUri
                            value: string
                      - name: predictionFormat
                        value: string
                  - name: enableFeatureAttributes
                    value: boolean
              - name: trainingPredictionSkewDetectionConfig
                value:
                  - name: attributionScoreSkewThresholds
                    value: object
                  - name: skewThresholds
                    value: object
                  - name: defaultSkewThreshold
                    value:
                      - name: value
                        value: number
              - name: predictionDriftDetectionConfig
                value:
                  - name: attributionScoreDriftThresholds
                    value: object
                  - name: driftThresholds
                    value: object
          - name: deployedModelId
            value: string
    - name: samplePredictInstance
      value: any
    - name: state
      value: string
    - name: displayName
      value: string
    - name: name
      value: string
    - name: satisfiesPzs
      value: boolean
    - name: endpoint
      value: string
    - name: nextScheduleTime
      value: string
    - name: modelMonitoringAlertConfig
      value:
        - name: enableLogging
          value: boolean
        - name: notificationChannels
          value:
            - string
        - name: emailAlertConfig
          value:
            - name: userEmails
              value:
                - string
    - name: bigqueryTables
      value:
        - - name: logSource
            value: string
          - name: requestResponseLoggingSchemaVersion
            value: string
          - name: logType
            value: string
          - name: bigqueryTablePath
            value: string
    - name: updateTime
      value: string

UPDATE example

Updates a model_deployment_monitoring_jobs resource.

/*+ update */
UPDATE google.aiplatform.model_deployment_monitoring_jobs
SET 
logTtl = '{{ logTtl }}',
statsAnomaliesBaseDirectory = '{{ statsAnomaliesBaseDirectory }}',
enableMonitoringPipelineLogs = true|false,
labels = '{{ labels }}',
modelDeploymentMonitoringScheduleConfig = '{{ modelDeploymentMonitoringScheduleConfig }}',
encryptionSpec = '{{ encryptionSpec }}',
predictInstanceSchemaUri = '{{ predictInstanceSchemaUri }}',
analysisInstanceSchemaUri = '{{ analysisInstanceSchemaUri }}',
modelDeploymentMonitoringObjectiveConfigs = '{{ modelDeploymentMonitoringObjectiveConfigs }}',
samplePredictInstance = '{{ samplePredictInstance }}',
loggingSamplingStrategy = '{{ loggingSamplingStrategy }}',
displayName = '{{ displayName }}',
endpoint = '{{ endpoint }}',
modelMonitoringAlertConfig = '{{ modelMonitoringAlertConfig }}'
WHERE 
locationsId = '{{ locationsId }}'
AND modelDeploymentMonitoringJobsId = '{{ modelDeploymentMonitoringJobsId }}'
AND projectsId = '{{ projectsId }}';

DELETE example

Deletes the specified model_deployment_monitoring_jobs resource.

/*+ delete */
DELETE FROM google.aiplatform.model_deployment_monitoring_jobs
WHERE locationsId = '{{ locationsId }}'
AND modelDeploymentMonitoringJobsId = '{{ modelDeploymentMonitoringJobsId }}'
AND projectsId = '{{ projectsId }}';