|
|
@ -204,6 +204,15 @@ message BatchPredictionJob { |
|
|
|
// must be provided. |
|
|
|
// must be provided. |
|
|
|
BatchDedicatedResources dedicated_resources = 7; |
|
|
|
BatchDedicatedResources dedicated_resources = 7; |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
// The service account that the DeployedModel's container runs as. If not |
|
|
|
|
|
|
|
// specified, a system generated one will be used, which |
|
|
|
|
|
|
|
// has minimal permissions and the custom container, if used, may not have |
|
|
|
|
|
|
|
// enough permission to access other GCP resources. |
|
|
|
|
|
|
|
// |
|
|
|
|
|
|
|
// Users deploying the Model must have the `iam.serviceAccounts.actAs` |
|
|
|
|
|
|
|
// permission on this service account. |
|
|
|
|
|
|
|
string service_account = 29; |
|
|
|
|
|
|
|
|
|
|
|
// Immutable. Parameters configuring the batch behavior. Currently only applicable when |
|
|
|
// Immutable. Parameters configuring the batch behavior. Currently only applicable when |
|
|
|
// [dedicated_resources][google.cloud.aiplatform.v1.BatchPredictionJob.dedicated_resources] are used (in other cases Vertex AI does |
|
|
|
// [dedicated_resources][google.cloud.aiplatform.v1.BatchPredictionJob.dedicated_resources] are used (in other cases Vertex AI does |
|
|
|
// the tuning itself). |
|
|
|
// the tuning itself). |
|
|
|