- 3.55.0 (latest)
- 3.54.0
- 3.53.0
- 3.52.0
- 3.50.0
- 3.49.0
- 3.48.0
- 3.47.0
- 3.46.0
- 3.45.0
- 3.44.0
- 3.43.0
- 3.42.0
- 3.41.0
- 3.40.0
- 3.38.0
- 3.37.0
- 3.36.0
- 3.35.0
- 3.34.0
- 3.33.0
- 3.32.0
- 3.31.0
- 3.30.0
- 3.29.0
- 3.28.0
- 3.25.0
- 3.24.0
- 3.23.0
- 3.22.0
- 3.21.0
- 3.20.0
- 3.19.0
- 3.18.0
- 3.17.0
- 3.16.0
- 3.15.0
- 3.14.0
- 3.13.0
- 3.12.0
- 3.11.0
- 3.10.0
- 3.9.0
- 3.8.0
- 3.7.0
- 3.6.0
- 3.5.0
- 3.4.2
- 3.3.0
- 3.2.0
- 3.0.0
- 2.9.8
- 2.8.9
- 2.7.4
- 2.5.3
- 2.4.0
public interface ModelOrBuilder extends MessageOrBuilder
Implements
MessageOrBuilderMethods
containsLabels(String key)
public abstract boolean containsLabels(String key)
The labels with user-defined metadata to organize your Models. 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 = 17;
Name | Description |
key | String |
Type | Description |
boolean |
getArtifactUri()
public abstract String getArtifactUri()
Immutable. The path to the directory containing the Model artifact and any of its supporting files. Not present for AutoML Models.
string artifact_uri = 26 [(.google.api.field_behavior) = IMMUTABLE];
Type | Description |
String | The artifactUri. |
getArtifactUriBytes()
public abstract ByteString getArtifactUriBytes()
Immutable. The path to the directory containing the Model artifact and any of its supporting files. Not present for AutoML Models.
string artifact_uri = 26 [(.google.api.field_behavior) = IMMUTABLE];
Type | Description |
ByteString | The bytes for artifactUri. |
getContainerSpec()
public abstract ModelContainerSpec getContainerSpec()
Input only. The specification of the container that is to be used when deploying this Model. The specification is ingested upon ModelService.UploadModel, and all binaries it contains are copied and stored internally by Vertex AI. Not present for AutoML Models.
.google.cloud.aiplatform.v1.ModelContainerSpec container_spec = 9 [(.google.api.field_behavior) = INPUT_ONLY];
Type | Description |
ModelContainerSpec | The containerSpec. |
getContainerSpecOrBuilder()
public abstract ModelContainerSpecOrBuilder getContainerSpecOrBuilder()
Input only. The specification of the container that is to be used when deploying this Model. The specification is ingested upon ModelService.UploadModel, and all binaries it contains are copied and stored internally by Vertex AI. Not present for AutoML Models.
.google.cloud.aiplatform.v1.ModelContainerSpec container_spec = 9 [(.google.api.field_behavior) = INPUT_ONLY];
Type | Description |
ModelContainerSpecOrBuilder |
getCreateTime()
public abstract Timestamp getCreateTime()
Output only. Timestamp when this Model was uploaded into Vertex AI.
.google.protobuf.Timestamp create_time = 13 [(.google.api.field_behavior) = OUTPUT_ONLY];
Type | Description |
Timestamp | The createTime. |
getCreateTimeOrBuilder()
public abstract TimestampOrBuilder getCreateTimeOrBuilder()
Output only. Timestamp when this Model was uploaded into Vertex AI.
.google.protobuf.Timestamp create_time = 13 [(.google.api.field_behavior) = OUTPUT_ONLY];
Type | Description |
TimestampOrBuilder |
getDeployedModels(int index)
public abstract DeployedModelRef getDeployedModels(int index)
Output only. The pointers to DeployedModels created from this Model. Note that Model could have been deployed to Endpoints in different Locations.
repeated .google.cloud.aiplatform.v1.DeployedModelRef deployed_models = 15 [(.google.api.field_behavior) = OUTPUT_ONLY];
Name | Description |
index | int |
Type | Description |
DeployedModelRef |
getDeployedModelsCount()
public abstract int getDeployedModelsCount()
Output only. The pointers to DeployedModels created from this Model. Note that Model could have been deployed to Endpoints in different Locations.
repeated .google.cloud.aiplatform.v1.DeployedModelRef deployed_models = 15 [(.google.api.field_behavior) = OUTPUT_ONLY];
Type | Description |
int |
getDeployedModelsList()
public abstract List<DeployedModelRef> getDeployedModelsList()
Output only. The pointers to DeployedModels created from this Model. Note that Model could have been deployed to Endpoints in different Locations.
repeated .google.cloud.aiplatform.v1.DeployedModelRef deployed_models = 15 [(.google.api.field_behavior) = OUTPUT_ONLY];
Type | Description |
List<DeployedModelRef> |
getDeployedModelsOrBuilder(int index)
public abstract DeployedModelRefOrBuilder getDeployedModelsOrBuilder(int index)
Output only. The pointers to DeployedModels created from this Model. Note that Model could have been deployed to Endpoints in different Locations.
repeated .google.cloud.aiplatform.v1.DeployedModelRef deployed_models = 15 [(.google.api.field_behavior) = OUTPUT_ONLY];
Name | Description |
index | int |
Type | Description |
DeployedModelRefOrBuilder |
getDeployedModelsOrBuilderList()
public abstract List<? extends DeployedModelRefOrBuilder> getDeployedModelsOrBuilderList()
Output only. The pointers to DeployedModels created from this Model. Note that Model could have been deployed to Endpoints in different Locations.
repeated .google.cloud.aiplatform.v1.DeployedModelRef deployed_models = 15 [(.google.api.field_behavior) = OUTPUT_ONLY];
Type | Description |
List<? extends com.google.cloud.aiplatform.v1.DeployedModelRefOrBuilder> |
getDescription()
public abstract String getDescription()
The description of the Model.
string description = 3;
Type | Description |
String | The description. |
getDescriptionBytes()
public abstract ByteString getDescriptionBytes()
The description of the Model.
string description = 3;
Type | Description |
ByteString | The bytes for description. |
getDisplayName()
public abstract String getDisplayName()
Required. The display name of the Model. The name can be up to 128 characters long and can be consist of any UTF-8 characters.
string display_name = 2 [(.google.api.field_behavior) = REQUIRED];
Type | Description |
String | The displayName. |
getDisplayNameBytes()
public abstract ByteString getDisplayNameBytes()
Required. The display name of the Model. The name can be up to 128 characters long and can be consist of any UTF-8 characters.
string display_name = 2 [(.google.api.field_behavior) = REQUIRED];
Type | Description |
ByteString | The bytes for displayName. |
getEncryptionSpec()
public abstract EncryptionSpec getEncryptionSpec()
Customer-managed encryption key spec for a Model. If set, this Model and all sub-resources of this Model will be secured by this key.
.google.cloud.aiplatform.v1.EncryptionSpec encryption_spec = 24;
Type | Description |
EncryptionSpec | The encryptionSpec. |
getEncryptionSpecOrBuilder()
public abstract EncryptionSpecOrBuilder getEncryptionSpecOrBuilder()
Customer-managed encryption key spec for a Model. If set, this Model and all sub-resources of this Model will be secured by this key.
.google.cloud.aiplatform.v1.EncryptionSpec encryption_spec = 24;
Type | Description |
EncryptionSpecOrBuilder |
getEtag()
public abstract String getEtag()
Used to perform consistent read-modify-write updates. If not set, a blind "overwrite" update happens.
string etag = 16;
Type | Description |
String | The etag. |
getEtagBytes()
public abstract ByteString getEtagBytes()
Used to perform consistent read-modify-write updates. If not set, a blind "overwrite" update happens.
string etag = 16;
Type | Description |
ByteString | The bytes for etag. |
getExplanationSpec()
public abstract ExplanationSpec getExplanationSpec()
The default explanation specification for this Model. The Model can be used for requesting explanation after being deployed if it is populated. The Model can be used for batch explanation if it is populated. All fields of the explanation_spec can be overridden by explanation_spec of DeployModelRequest.deployed_model, or explanation_spec of BatchPredictionJob. If the default explanation specification is not set for this Model, this Model can still be used for requesting explanation by setting explanation_spec of DeployModelRequest.deployed_model and for batch explanation by setting explanation_spec of BatchPredictionJob.
.google.cloud.aiplatform.v1.ExplanationSpec explanation_spec = 23;
Type | Description |
ExplanationSpec | The explanationSpec. |
getExplanationSpecOrBuilder()
public abstract ExplanationSpecOrBuilder getExplanationSpecOrBuilder()
The default explanation specification for this Model. The Model can be used for requesting explanation after being deployed if it is populated. The Model can be used for batch explanation if it is populated. All fields of the explanation_spec can be overridden by explanation_spec of DeployModelRequest.deployed_model, or explanation_spec of BatchPredictionJob. If the default explanation specification is not set for this Model, this Model can still be used for requesting explanation by setting explanation_spec of DeployModelRequest.deployed_model and for batch explanation by setting explanation_spec of BatchPredictionJob.
.google.cloud.aiplatform.v1.ExplanationSpec explanation_spec = 23;
Type | Description |
ExplanationSpecOrBuilder |
getLabels()
public abstract Map<String,String> getLabels()
Use #getLabelsMap() instead.
Type | Description |
Map<String,String> |
getLabelsCount()
public abstract int getLabelsCount()
The labels with user-defined metadata to organize your Models. 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 = 17;
Type | Description |
int |
getLabelsMap()
public abstract Map<String,String> getLabelsMap()
The labels with user-defined metadata to organize your Models. 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 = 17;
Type | Description |
Map<String,String> |
getLabelsOrDefault(String key, String defaultValue)
public abstract String getLabelsOrDefault(String key, String defaultValue)
The labels with user-defined metadata to organize your Models. 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 = 17;
Name | Description |
key | String |
defaultValue | String |
Type | Description |
String |
getLabelsOrThrow(String key)
public abstract String getLabelsOrThrow(String key)
The labels with user-defined metadata to organize your Models. 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 = 17;
Name | Description |
key | String |
Type | Description |
String |
getMetadata()
public abstract Value getMetadata()
Immutable. An additional information about the Model; the schema of the metadata can be found in metadata_schema. Unset if the Model does not have any additional information.
.google.protobuf.Value metadata = 6 [(.google.api.field_behavior) = IMMUTABLE];
Type | Description |
Value | The metadata. |
getMetadataOrBuilder()
public abstract ValueOrBuilder getMetadataOrBuilder()
Immutable. An additional information about the Model; the schema of the metadata can be found in metadata_schema. Unset if the Model does not have any additional information.
.google.protobuf.Value metadata = 6 [(.google.api.field_behavior) = IMMUTABLE];
Type | Description |
ValueOrBuilder |
getMetadataSchemaUri()
public abstract String getMetadataSchemaUri()
Immutable. Points to a YAML file stored on Google Cloud Storage describing additional information about the Model, that is specific to it. Unset if the Model does not have any additional information. The schema is defined as an OpenAPI 3.0.2 Schema Object. AutoML Models always have this field populated by Vertex AI, if no additional metadata is needed, this field is set to an empty string. Note: The URI given on output will be immutable and probably different, including the URI scheme, than the one given on input. The output URI will point to a location where the user only has a read access.
string metadata_schema_uri = 5 [(.google.api.field_behavior) = IMMUTABLE];
Type | Description |
String | The metadataSchemaUri. |
getMetadataSchemaUriBytes()
public abstract ByteString getMetadataSchemaUriBytes()
Immutable. Points to a YAML file stored on Google Cloud Storage describing additional information about the Model, that is specific to it. Unset if the Model does not have any additional information. The schema is defined as an OpenAPI 3.0.2 Schema Object. AutoML Models always have this field populated by Vertex AI, if no additional metadata is needed, this field is set to an empty string. Note: The URI given on output will be immutable and probably different, including the URI scheme, than the one given on input. The output URI will point to a location where the user only has a read access.
string metadata_schema_uri = 5 [(.google.api.field_behavior) = IMMUTABLE];
Type | Description |
ByteString | The bytes for metadataSchemaUri. |
getModelSourceInfo()
public abstract ModelSourceInfo getModelSourceInfo()
Output only. Source of a model. It can either be automl training pipeline, custom training pipeline, BigQuery ML, or existing Vertex AI Model.
.google.cloud.aiplatform.v1.ModelSourceInfo model_source_info = 38 [(.google.api.field_behavior) = OUTPUT_ONLY];
Type | Description |
ModelSourceInfo | The modelSourceInfo. |
getModelSourceInfoOrBuilder()
public abstract ModelSourceInfoOrBuilder getModelSourceInfoOrBuilder()
Output only. Source of a model. It can either be automl training pipeline, custom training pipeline, BigQuery ML, or existing Vertex AI Model.
.google.cloud.aiplatform.v1.ModelSourceInfo model_source_info = 38 [(.google.api.field_behavior) = OUTPUT_ONLY];
Type | Description |
ModelSourceInfoOrBuilder |
getName()
public abstract String getName()
The resource name of the Model.
string name = 1;
Type | Description |
String | The name. |
getNameBytes()
public abstract ByteString getNameBytes()
The resource name of the Model.
string name = 1;
Type | Description |
ByteString | The bytes for name. |
getPredictSchemata()
public abstract PredictSchemata getPredictSchemata()
The schemata that describe formats of the Model's predictions and explanations as given and returned via PredictionService.Predict and PredictionService.Explain.
.google.cloud.aiplatform.v1.PredictSchemata predict_schemata = 4;
Type | Description |
PredictSchemata | The predictSchemata. |
getPredictSchemataOrBuilder()
public abstract PredictSchemataOrBuilder getPredictSchemataOrBuilder()
The schemata that describe formats of the Model's predictions and explanations as given and returned via PredictionService.Predict and PredictionService.Explain.
.google.cloud.aiplatform.v1.PredictSchemata predict_schemata = 4;
Type | Description |
PredictSchemataOrBuilder |
getSupportedDeploymentResourcesTypes(int index)
public abstract Model.DeploymentResourcesType getSupportedDeploymentResourcesTypes(int index)
Output only. When this Model is deployed, its prediction resources are described by the
prediction_resources
field of the Endpoint.deployed_models object.
Because not all Models support all resource configuration types, the
configuration types this Model supports are listed here. If no
configuration types are listed, the Model cannot be deployed to an
Endpoint and does not support
online predictions (PredictionService.Predict or
PredictionService.Explain). Such a Model can serve predictions by
using a BatchPredictionJob, if it has at least one entry each in
supported_input_storage_formats and
supported_output_storage_formats.
repeated .google.cloud.aiplatform.v1.Model.DeploymentResourcesType supported_deployment_resources_types = 10 [(.google.api.field_behavior) = OUTPUT_ONLY];
Name | Description |
index | int The index of the element to return. |
Type | Description |
Model.DeploymentResourcesType | The supportedDeploymentResourcesTypes at the given index. |
getSupportedDeploymentResourcesTypesCount()
public abstract int getSupportedDeploymentResourcesTypesCount()
Output only. When this Model is deployed, its prediction resources are described by the
prediction_resources
field of the Endpoint.deployed_models object.
Because not all Models support all resource configuration types, the
configuration types this Model supports are listed here. If no
configuration types are listed, the Model cannot be deployed to an
Endpoint and does not support
online predictions (PredictionService.Predict or
PredictionService.Explain). Such a Model can serve predictions by
using a BatchPredictionJob, if it has at least one entry each in
supported_input_storage_formats and
supported_output_storage_formats.
repeated .google.cloud.aiplatform.v1.Model.DeploymentResourcesType supported_deployment_resources_types = 10 [(.google.api.field_behavior) = OUTPUT_ONLY];
Type | Description |
int | The count of supportedDeploymentResourcesTypes. |
getSupportedDeploymentResourcesTypesList()
public abstract List<Model.DeploymentResourcesType> getSupportedDeploymentResourcesTypesList()
Output only. When this Model is deployed, its prediction resources are described by the
prediction_resources
field of the Endpoint.deployed_models object.
Because not all Models support all resource configuration types, the
configuration types this Model supports are listed here. If no
configuration types are listed, the Model cannot be deployed to an
Endpoint and does not support
online predictions (PredictionService.Predict or
PredictionService.Explain). Such a Model can serve predictions by
using a BatchPredictionJob, if it has at least one entry each in
supported_input_storage_formats and
supported_output_storage_formats.
repeated .google.cloud.aiplatform.v1.Model.DeploymentResourcesType supported_deployment_resources_types = 10 [(.google.api.field_behavior) = OUTPUT_ONLY];
Type | Description |
List<DeploymentResourcesType> | A list containing the supportedDeploymentResourcesTypes. |
getSupportedDeploymentResourcesTypesValue(int index)
public abstract int getSupportedDeploymentResourcesTypesValue(int index)
Output only. When this Model is deployed, its prediction resources are described by the
prediction_resources
field of the Endpoint.deployed_models object.
Because not all Models support all resource configuration types, the
configuration types this Model supports are listed here. If no
configuration types are listed, the Model cannot be deployed to an
Endpoint and does not support
online predictions (PredictionService.Predict or
PredictionService.Explain). Such a Model can serve predictions by
using a BatchPredictionJob, if it has at least one entry each in
supported_input_storage_formats and
supported_output_storage_formats.
repeated .google.cloud.aiplatform.v1.Model.DeploymentResourcesType supported_deployment_resources_types = 10 [(.google.api.field_behavior) = OUTPUT_ONLY];
Name | Description |
index | int The index of the value to return. |
Type | Description |
int | The enum numeric value on the wire of supportedDeploymentResourcesTypes at the given index. |
getSupportedDeploymentResourcesTypesValueList()
public abstract List<Integer> getSupportedDeploymentResourcesTypesValueList()
Output only. When this Model is deployed, its prediction resources are described by the
prediction_resources
field of the Endpoint.deployed_models object.
Because not all Models support all resource configuration types, the
configuration types this Model supports are listed here. If no
configuration types are listed, the Model cannot be deployed to an
Endpoint and does not support
online predictions (PredictionService.Predict or
PredictionService.Explain). Such a Model can serve predictions by
using a BatchPredictionJob, if it has at least one entry each in
supported_input_storage_formats and
supported_output_storage_formats.
repeated .google.cloud.aiplatform.v1.Model.DeploymentResourcesType supported_deployment_resources_types = 10 [(.google.api.field_behavior) = OUTPUT_ONLY];
Type | Description |
List<Integer> | A list containing the enum numeric values on the wire for supportedDeploymentResourcesTypes. |
getSupportedExportFormats(int index)
public abstract Model.ExportFormat getSupportedExportFormats(int index)
Output only. The formats in which this Model may be exported. If empty, this Model is not available for export.
repeated .google.cloud.aiplatform.v1.Model.ExportFormat supported_export_formats = 20 [(.google.api.field_behavior) = OUTPUT_ONLY];
Name | Description |
index | int |
Type | Description |
Model.ExportFormat |
getSupportedExportFormatsCount()
public abstract int getSupportedExportFormatsCount()
Output only. The formats in which this Model may be exported. If empty, this Model is not available for export.
repeated .google.cloud.aiplatform.v1.Model.ExportFormat supported_export_formats = 20 [(.google.api.field_behavior) = OUTPUT_ONLY];
Type | Description |
int |
getSupportedExportFormatsList()
public abstract List<Model.ExportFormat> getSupportedExportFormatsList()
Output only. The formats in which this Model may be exported. If empty, this Model is not available for export.
repeated .google.cloud.aiplatform.v1.Model.ExportFormat supported_export_formats = 20 [(.google.api.field_behavior) = OUTPUT_ONLY];
Type | Description |
List<ExportFormat> |
getSupportedExportFormatsOrBuilder(int index)
public abstract Model.ExportFormatOrBuilder getSupportedExportFormatsOrBuilder(int index)
Output only. The formats in which this Model may be exported. If empty, this Model is not available for export.
repeated .google.cloud.aiplatform.v1.Model.ExportFormat supported_export_formats = 20 [(.google.api.field_behavior) = OUTPUT_ONLY];
Name | Description |
index | int |
Type | Description |
Model.ExportFormatOrBuilder |
getSupportedExportFormatsOrBuilderList()
public abstract List<? extends Model.ExportFormatOrBuilder> getSupportedExportFormatsOrBuilderList()
Output only. The formats in which this Model may be exported. If empty, this Model is not available for export.
repeated .google.cloud.aiplatform.v1.Model.ExportFormat supported_export_formats = 20 [(.google.api.field_behavior) = OUTPUT_ONLY];
Type | Description |
List<? extends com.google.cloud.aiplatform.v1.Model.ExportFormatOrBuilder> |
getSupportedInputStorageFormats(int index)
public abstract String getSupportedInputStorageFormats(int index)
Output only. The formats this Model supports in BatchPredictionJob.input_config. If PredictSchemata.instance_schema_uri exists, the instances should be given as per that schema. The possible formats are:
jsonl
The JSON Lines format, where each instance is a single line. Uses GcsSource.csv
The CSV format, where each instance is a single comma-separated line. The first line in the file is the header, containing comma-separated field names. Uses GcsSource.tf-record
The TFRecord format, where each instance is a single record in tfrecord syntax. Uses GcsSource.tf-record-gzip
Similar totf-record
, but the file is gzipped. Uses GcsSource.bigquery
Each instance is a single row in BigQuery. Uses BigQuerySource.file-list
Each line of the file is the location of an instance to process, usesgcs_source
field of the InputConfig object. If this Model doesn't support any of these formats it means it cannot be used with a BatchPredictionJob. However, if it has supported_deployment_resources_types, it could serve online predictions by using PredictionService.Predict or PredictionService.Explain.
repeated string supported_input_storage_formats = 11 [(.google.api.field_behavior) = OUTPUT_ONLY];
Name | Description |
index | int The index of the element to return. |
Type | Description |
String | The supportedInputStorageFormats at the given index. |
getSupportedInputStorageFormatsBytes(int index)
public abstract ByteString getSupportedInputStorageFormatsBytes(int index)
Output only. The formats this Model supports in BatchPredictionJob.input_config. If PredictSchemata.instance_schema_uri exists, the instances should be given as per that schema. The possible formats are:
jsonl
The JSON Lines format, where each instance is a single line. Uses GcsSource.csv
The CSV format, where each instance is a single comma-separated line. The first line in the file is the header, containing comma-separated field names. Uses GcsSource.tf-record
The TFRecord format, where each instance is a single record in tfrecord syntax. Uses GcsSource.tf-record-gzip
Similar totf-record
, but the file is gzipped. Uses GcsSource.bigquery
Each instance is a single row in BigQuery. Uses BigQuerySource.file-list
Each line of the file is the location of an instance to process, usesgcs_source
field of the InputConfig object. If this Model doesn't support any of these formats it means it cannot be used with a BatchPredictionJob. However, if it has supported_deployment_resources_types, it could serve online predictions by using PredictionService.Predict or PredictionService.Explain.
repeated string supported_input_storage_formats = 11 [(.google.api.field_behavior) = OUTPUT_ONLY];
Name | Description |
index | int The index of the value to return. |
Type | Description |
ByteString | The bytes of the supportedInputStorageFormats at the given index. |
getSupportedInputStorageFormatsCount()
public abstract int getSupportedInputStorageFormatsCount()
Output only. The formats this Model supports in BatchPredictionJob.input_config. If PredictSchemata.instance_schema_uri exists, the instances should be given as per that schema. The possible formats are:
jsonl
The JSON Lines format, where each instance is a single line. Uses GcsSource.csv
The CSV format, where each instance is a single comma-separated line. The first line in the file is the header, containing comma-separated field names. Uses GcsSource.tf-record
The TFRecord format, where each instance is a single record in tfrecord syntax. Uses GcsSource.tf-record-gzip
Similar totf-record
, but the file is gzipped. Uses GcsSource.bigquery
Each instance is a single row in BigQuery. Uses BigQuerySource.file-list
Each line of the file is the location of an instance to process, usesgcs_source
field of the InputConfig object. If this Model doesn't support any of these formats it means it cannot be used with a BatchPredictionJob. However, if it has supported_deployment_resources_types, it could serve online predictions by using PredictionService.Predict or PredictionService.Explain.
repeated string supported_input_storage_formats = 11 [(.google.api.field_behavior) = OUTPUT_ONLY];
Type | Description |
int | The count of supportedInputStorageFormats. |
getSupportedInputStorageFormatsList()
public abstract List<String> getSupportedInputStorageFormatsList()
Output only. The formats this Model supports in BatchPredictionJob.input_config. If PredictSchemata.instance_schema_uri exists, the instances should be given as per that schema. The possible formats are:
jsonl
The JSON Lines format, where each instance is a single line. Uses GcsSource.csv
The CSV format, where each instance is a single comma-separated line. The first line in the file is the header, containing comma-separated field names. Uses GcsSource.tf-record
The TFRecord format, where each instance is a single record in tfrecord syntax. Uses GcsSource.tf-record-gzip
Similar totf-record
, but the file is gzipped. Uses GcsSource.bigquery
Each instance is a single row in BigQuery. Uses BigQuerySource.file-list
Each line of the file is the location of an instance to process, usesgcs_source
field of the InputConfig object. If this Model doesn't support any of these formats it means it cannot be used with a BatchPredictionJob. However, if it has supported_deployment_resources_types, it could serve online predictions by using PredictionService.Predict or PredictionService.Explain.
repeated string supported_input_storage_formats = 11 [(.google.api.field_behavior) = OUTPUT_ONLY];
Type | Description |
List<String> | A list containing the supportedInputStorageFormats. |
getSupportedOutputStorageFormats(int index)
public abstract String getSupportedOutputStorageFormats(int index)
Output only. The formats this Model supports in BatchPredictionJob.output_config. If both PredictSchemata.instance_schema_uri and PredictSchemata.prediction_schema_uri exist, the predictions are returned together with their instances. In other words, the prediction has the original instance data first, followed by the actual prediction content (as per the schema). The possible formats are:
jsonl
The JSON Lines format, where each prediction is a single line. Uses GcsDestination.csv
The CSV format, where each prediction is a single comma-separated line. The first line in the file is the header, containing comma-separated field names. Uses GcsDestination.bigquery
Each prediction is a single row in a BigQuery table, uses BigQueryDestination . If this Model doesn't support any of these formats it means it cannot be used with a BatchPredictionJob. However, if it has supported_deployment_resources_types, it could serve online predictions by using PredictionService.Predict or PredictionService.Explain.
repeated string supported_output_storage_formats = 12 [(.google.api.field_behavior) = OUTPUT_ONLY];
Name | Description |
index | int The index of the element to return. |
Type | Description |
String | The supportedOutputStorageFormats at the given index. |
getSupportedOutputStorageFormatsBytes(int index)
public abstract ByteString getSupportedOutputStorageFormatsBytes(int index)
Output only. The formats this Model supports in BatchPredictionJob.output_config. If both PredictSchemata.instance_schema_uri and PredictSchemata.prediction_schema_uri exist, the predictions are returned together with their instances. In other words, the prediction has the original instance data first, followed by the actual prediction content (as per the schema). The possible formats are:
jsonl
The JSON Lines format, where each prediction is a single line. Uses GcsDestination.csv
The CSV format, where each prediction is a single comma-separated line. The first line in the file is the header, containing comma-separated field names. Uses GcsDestination.bigquery
Each prediction is a single row in a BigQuery table, uses BigQueryDestination . If this Model doesn't support any of these formats it means it cannot be used with a BatchPredictionJob. However, if it has supported_deployment_resources_types, it could serve online predictions by using PredictionService.Predict or PredictionService.Explain.
repeated string supported_output_storage_formats = 12 [(.google.api.field_behavior) = OUTPUT_ONLY];
Name | Description |
index | int The index of the value to return. |
Type | Description |
ByteString | The bytes of the supportedOutputStorageFormats at the given index. |
getSupportedOutputStorageFormatsCount()
public abstract int getSupportedOutputStorageFormatsCount()
Output only. The formats this Model supports in BatchPredictionJob.output_config. If both PredictSchemata.instance_schema_uri and PredictSchemata.prediction_schema_uri exist, the predictions are returned together with their instances. In other words, the prediction has the original instance data first, followed by the actual prediction content (as per the schema). The possible formats are:
jsonl
The JSON Lines format, where each prediction is a single line. Uses GcsDestination.csv
The CSV format, where each prediction is a single comma-separated line. The first line in the file is the header, containing comma-separated field names. Uses GcsDestination.bigquery
Each prediction is a single row in a BigQuery table, uses BigQueryDestination . If this Model doesn't support any of these formats it means it cannot be used with a BatchPredictionJob. However, if it has supported_deployment_resources_types, it could serve online predictions by using PredictionService.Predict or PredictionService.Explain.
repeated string supported_output_storage_formats = 12 [(.google.api.field_behavior) = OUTPUT_ONLY];
Type | Description |
int | The count of supportedOutputStorageFormats. |
getSupportedOutputStorageFormatsList()
public abstract List<String> getSupportedOutputStorageFormatsList()
Output only. The formats this Model supports in BatchPredictionJob.output_config. If both PredictSchemata.instance_schema_uri and PredictSchemata.prediction_schema_uri exist, the predictions are returned together with their instances. In other words, the prediction has the original instance data first, followed by the actual prediction content (as per the schema). The possible formats are:
jsonl
The JSON Lines format, where each prediction is a single line. Uses GcsDestination.csv
The CSV format, where each prediction is a single comma-separated line. The first line in the file is the header, containing comma-separated field names. Uses GcsDestination.bigquery
Each prediction is a single row in a BigQuery table, uses BigQueryDestination . If this Model doesn't support any of these formats it means it cannot be used with a BatchPredictionJob. However, if it has supported_deployment_resources_types, it could serve online predictions by using PredictionService.Predict or PredictionService.Explain.
repeated string supported_output_storage_formats = 12 [(.google.api.field_behavior) = OUTPUT_ONLY];
Type | Description |
List<String> | A list containing the supportedOutputStorageFormats. |
getTrainingPipeline()
public abstract String getTrainingPipeline()
Output only. The resource name of the TrainingPipeline that uploaded this Model, if any.
string training_pipeline = 7 [(.google.api.field_behavior) = OUTPUT_ONLY, (.google.api.resource_reference) = { ... }
Type | Description |
String | The trainingPipeline. |
getTrainingPipelineBytes()
public abstract ByteString getTrainingPipelineBytes()
Output only. The resource name of the TrainingPipeline that uploaded this Model, if any.
string training_pipeline = 7 [(.google.api.field_behavior) = OUTPUT_ONLY, (.google.api.resource_reference) = { ... }
Type | Description |
ByteString | The bytes for trainingPipeline. |
getUpdateTime()
public abstract Timestamp getUpdateTime()
Output only. Timestamp when this Model was most recently updated.
.google.protobuf.Timestamp update_time = 14 [(.google.api.field_behavior) = OUTPUT_ONLY];
Type | Description |
Timestamp | The updateTime. |
getUpdateTimeOrBuilder()
public abstract TimestampOrBuilder getUpdateTimeOrBuilder()
Output only. Timestamp when this Model was most recently updated.
.google.protobuf.Timestamp update_time = 14 [(.google.api.field_behavior) = OUTPUT_ONLY];
Type | Description |
TimestampOrBuilder |
getVersionAliases(int index)
public abstract String getVersionAliases(int index)
User provided version aliases so that a model version can be referenced via alias (i.e. projects/{project}/locations/{location}/models/{model_id}@{version_alias} instead of auto-generated version id (i.e. projects/{project}/locations/{location}/models/{model_id}@{version_id}). The format is a-z{0,126}[a-z0-9] to distinguish from version_id. A default version alias will be created for the first version of the model, and there must be exactly one default version alias for a model.
repeated string version_aliases = 29;
Name | Description |
index | int The index of the element to return. |
Type | Description |
String | The versionAliases at the given index. |
getVersionAliasesBytes(int index)
public abstract ByteString getVersionAliasesBytes(int index)
User provided version aliases so that a model version can be referenced via alias (i.e. projects/{project}/locations/{location}/models/{model_id}@{version_alias} instead of auto-generated version id (i.e. projects/{project}/locations/{location}/models/{model_id}@{version_id}). The format is a-z{0,126}[a-z0-9] to distinguish from version_id. A default version alias will be created for the first version of the model, and there must be exactly one default version alias for a model.
repeated string version_aliases = 29;
Name | Description |
index | int The index of the value to return. |
Type | Description |
ByteString | The bytes of the versionAliases at the given index. |
getVersionAliasesCount()
public abstract int getVersionAliasesCount()
User provided version aliases so that a model version can be referenced via alias (i.e. projects/{project}/locations/{location}/models/{model_id}@{version_alias} instead of auto-generated version id (i.e. projects/{project}/locations/{location}/models/{model_id}@{version_id}). The format is a-z{0,126}[a-z0-9] to distinguish from version_id. A default version alias will be created for the first version of the model, and there must be exactly one default version alias for a model.
repeated string version_aliases = 29;
Type | Description |
int | The count of versionAliases. |
getVersionAliasesList()
public abstract List<String> getVersionAliasesList()
User provided version aliases so that a model version can be referenced via alias (i.e. projects/{project}/locations/{location}/models/{model_id}@{version_alias} instead of auto-generated version id (i.e. projects/{project}/locations/{location}/models/{model_id}@{version_id}). The format is a-z{0,126}[a-z0-9] to distinguish from version_id. A default version alias will be created for the first version of the model, and there must be exactly one default version alias for a model.
repeated string version_aliases = 29;
Type | Description |
List<String> | A list containing the versionAliases. |
getVersionCreateTime()
public abstract Timestamp getVersionCreateTime()
Output only. Timestamp when this version was created.
.google.protobuf.Timestamp version_create_time = 31 [(.google.api.field_behavior) = OUTPUT_ONLY];
Type | Description |
Timestamp | The versionCreateTime. |
getVersionCreateTimeOrBuilder()
public abstract TimestampOrBuilder getVersionCreateTimeOrBuilder()
Output only. Timestamp when this version was created.
.google.protobuf.Timestamp version_create_time = 31 [(.google.api.field_behavior) = OUTPUT_ONLY];
Type | Description |
TimestampOrBuilder |
getVersionDescription()
public abstract String getVersionDescription()
The description of this version.
string version_description = 30;
Type | Description |
String | The versionDescription. |
getVersionDescriptionBytes()
public abstract ByteString getVersionDescriptionBytes()
The description of this version.
string version_description = 30;
Type | Description |
ByteString | The bytes for versionDescription. |
getVersionId()
public abstract String getVersionId()
Output only. Immutable. The version ID of the model. A new version is committed when a new model version is uploaded or trained under an existing model id. It is an auto-incrementing decimal number in string representation.
string version_id = 28 [(.google.api.field_behavior) = IMMUTABLE, (.google.api.field_behavior) = OUTPUT_ONLY];
Type | Description |
String | The versionId. |
getVersionIdBytes()
public abstract ByteString getVersionIdBytes()
Output only. Immutable. The version ID of the model. A new version is committed when a new model version is uploaded or trained under an existing model id. It is an auto-incrementing decimal number in string representation.
string version_id = 28 [(.google.api.field_behavior) = IMMUTABLE, (.google.api.field_behavior) = OUTPUT_ONLY];
Type | Description |
ByteString | The bytes for versionId. |
getVersionUpdateTime()
public abstract Timestamp getVersionUpdateTime()
Output only. Timestamp when this version was most recently updated.
.google.protobuf.Timestamp version_update_time = 32 [(.google.api.field_behavior) = OUTPUT_ONLY];
Type | Description |
Timestamp | The versionUpdateTime. |
getVersionUpdateTimeOrBuilder()
public abstract TimestampOrBuilder getVersionUpdateTimeOrBuilder()
Output only. Timestamp when this version was most recently updated.
.google.protobuf.Timestamp version_update_time = 32 [(.google.api.field_behavior) = OUTPUT_ONLY];
Type | Description |
TimestampOrBuilder |
hasContainerSpec()
public abstract boolean hasContainerSpec()
Input only. The specification of the container that is to be used when deploying this Model. The specification is ingested upon ModelService.UploadModel, and all binaries it contains are copied and stored internally by Vertex AI. Not present for AutoML Models.
.google.cloud.aiplatform.v1.ModelContainerSpec container_spec = 9 [(.google.api.field_behavior) = INPUT_ONLY];
Type | Description |
boolean | Whether the containerSpec field is set. |
hasCreateTime()
public abstract boolean hasCreateTime()
Output only. Timestamp when this Model was uploaded into Vertex AI.
.google.protobuf.Timestamp create_time = 13 [(.google.api.field_behavior) = OUTPUT_ONLY];
Type | Description |
boolean | Whether the createTime field is set. |
hasEncryptionSpec()
public abstract boolean hasEncryptionSpec()
Customer-managed encryption key spec for a Model. If set, this Model and all sub-resources of this Model will be secured by this key.
.google.cloud.aiplatform.v1.EncryptionSpec encryption_spec = 24;
Type | Description |
boolean | Whether the encryptionSpec field is set. |
hasExplanationSpec()
public abstract boolean hasExplanationSpec()
The default explanation specification for this Model. The Model can be used for requesting explanation after being deployed if it is populated. The Model can be used for batch explanation if it is populated. All fields of the explanation_spec can be overridden by explanation_spec of DeployModelRequest.deployed_model, or explanation_spec of BatchPredictionJob. If the default explanation specification is not set for this Model, this Model can still be used for requesting explanation by setting explanation_spec of DeployModelRequest.deployed_model and for batch explanation by setting explanation_spec of BatchPredictionJob.
.google.cloud.aiplatform.v1.ExplanationSpec explanation_spec = 23;
Type | Description |
boolean | Whether the explanationSpec field is set. |
hasMetadata()
public abstract boolean hasMetadata()
Immutable. An additional information about the Model; the schema of the metadata can be found in metadata_schema. Unset if the Model does not have any additional information.
.google.protobuf.Value metadata = 6 [(.google.api.field_behavior) = IMMUTABLE];
Type | Description |
boolean | Whether the metadata field is set. |
hasModelSourceInfo()
public abstract boolean hasModelSourceInfo()
Output only. Source of a model. It can either be automl training pipeline, custom training pipeline, BigQuery ML, or existing Vertex AI Model.
.google.cloud.aiplatform.v1.ModelSourceInfo model_source_info = 38 [(.google.api.field_behavior) = OUTPUT_ONLY];
Type | Description |
boolean | Whether the modelSourceInfo field is set. |
hasPredictSchemata()
public abstract boolean hasPredictSchemata()
The schemata that describe formats of the Model's predictions and explanations as given and returned via PredictionService.Predict and PredictionService.Explain.
.google.cloud.aiplatform.v1.PredictSchemata predict_schemata = 4;
Type | Description |
boolean | Whether the predictSchemata field is set. |
hasUpdateTime()
public abstract boolean hasUpdateTime()
Output only. Timestamp when this Model was most recently updated.
.google.protobuf.Timestamp update_time = 14 [(.google.api.field_behavior) = OUTPUT_ONLY];
Type | Description |
boolean | Whether the updateTime field is set. |
hasVersionCreateTime()
public abstract boolean hasVersionCreateTime()
Output only. Timestamp when this version was created.
.google.protobuf.Timestamp version_create_time = 31 [(.google.api.field_behavior) = OUTPUT_ONLY];
Type | Description |
boolean | Whether the versionCreateTime field is set. |
hasVersionUpdateTime()
public abstract boolean hasVersionUpdateTime()
Output only. Timestamp when this version was most recently updated.
.google.protobuf.Timestamp version_update_time = 32 [(.google.api.field_behavior) = OUTPUT_ONLY];
Type | Description |
boolean | Whether the versionUpdateTime field is set. |