ModelMonitoringInput Stay organized with collections Save and categorize content based on your preferences.
Model monitoring data input spec.
datasetUnion typedataset can be only one of the following:columnizedDatasetobject (ModelMonitoringDataset)Columnized dataset.
batchPredictionOutputobject (BatchPredictionOutput)Vertex AI Batch prediction Job.
vertexEndpointLogsobject (VertexEndpointLogs)Vertex AI Endpoint request & response logging.
time_specUnion typetime_spec can be only one of the following:timeIntervalobject (Interval)The time interval (pair of startTime and endTime) for which results should be returned.
timeOffsetobject (TimeOffset)The time offset setting for which results should be returned.
| JSON representation |
|---|
{// dataset"columnizedDataset":{object ( |
ModelMonitoringDataset
Input dataset spec.
timestampFieldstringThe timestamp field. Usually for serving data.
data_locationUnion typedata_location can be only one of the following:vertexDatasetstringResource name of the Vertex AI managed dataset.
gcsSourceobject (ModelMonitoringGcsSource)Google Cloud Storage data source.
bigquerySourceobject (ModelMonitoringBigQuerySource)BigQuery data source.
| JSON representation |
|---|
{"timestampField":string,// data_location"vertexDataset":string,"gcsSource":{object ( |
ModelMonitoringGcsSource
Dataset spec for data stored in Google Cloud Storage.
gcsUristringGoogle Cloud Storage URI to the input file(s). May contain wildcards. For more information on wildcards, seehttps://cloud.google.com/storage/docs/wildcards.
formatenum (DataFormat)data format of the dataset.
| JSON representation |
|---|
{"gcsUri":string,"format":enum ( |
DataFormat
Supported data format.
| Enums | |
|---|---|
DATA_FORMAT_UNSPECIFIED | data format unspecified, used when this field is unset. |
CSV | CSV files. |
TF_RECORD | TfRecord files |
JSONL | JsonL files. |
ModelMonitoringBigQuerySource
Dataset spec for data sotred in BigQuery.
connectionUnion typeconnection can be only one of the following:tableUristringBigQuery URI to a table, up to 2000 characters long. All the columns in the table will be selected. Accepted forms:
- BigQuery path. For example:
bq://projectId.bqDatasetId.bqTableId.
querystringStandard SQL to be used instead of thetableUri.
| JSON representation |
|---|
{// connection"tableUri":string,"query":string// Union type} |
BatchPredictionOutput
data from Vertex AI Batch prediction job output.
batchPredictionJobstringVertex AI Batch prediction job resource name. The job must match the model version specified in [ModelMonitor].[modelMonitoringTarget].
| JSON representation |
|---|
{"batchPredictionJob":string} |
VertexEndpointLogs
data from Vertex AI Endpoint request response logging.
endpoints[]stringList of endpoint resource names. The endpoints must enable the logging with the [Endpoint].[requestResponseLoggingConfig], and must contain the deployed model corresponding to the model version specified in [ModelMonitor].[modelMonitoringTarget].
| JSON representation |
|---|
{"endpoints":[string]} |
TimeOffset
time offset setting.
offsetstring[offset] is the time difference from the cut-off time. For scheduled jobs, the cut-off time is the scheduled time. For non-scheduled jobs, it's the time when the job was created. Currently we support the following format: 'w|W': Week, 'd|D': Day, 'h|H': Hour E.g. '1h' stands for 1 hour, '2d' stands for 2 days.
windowstring[window] refers to the scope of data selected for analysis. It allows you to specify the quantity of data you wish to examine. Currently we support the following format: 'w|W': Week, 'd|D': Day, 'h|H': Hour E.g. '1h' stands for 1 hour, '2d' stands for 2 days.
| JSON representation |
|---|
{"offset":string,"window":string} |
Except as otherwise noted, the content of this page is licensed under theCreative Commons Attribution 4.0 License, and code samples are licensed under theApache 2.0 License. For details, see theGoogle Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates.
Last updated 2025-06-27 UTC.