Google Cloud Native is in preview. Google Cloud Classic is fully supported.
google-native.aiplatform/v1.BatchPredictionJob
Explore with Pulumi AI
Google Cloud Native is in preview. Google Cloud Classic is fully supported.
Creates a BatchPredictionJob. A BatchPredictionJob once created will right away be attempted to start. Auto-naming is currently not supported for this resource.
Create BatchPredictionJob Resource
Resources are created with functions called constructors. To learn more about declaring and configuring resources, see Resources.
Constructor syntax
new BatchPredictionJob(name: string, args: BatchPredictionJobArgs, opts?: CustomResourceOptions);
@overload
def BatchPredictionJob(resource_name: str,
args: BatchPredictionJobArgs,
opts: Optional[ResourceOptions] = None)
@overload
def BatchPredictionJob(resource_name: str,
opts: Optional[ResourceOptions] = None,
input_config: Optional[GoogleCloudAiplatformV1BatchPredictionJobInputConfigArgs] = None,
output_config: Optional[GoogleCloudAiplatformV1BatchPredictionJobOutputConfigArgs] = None,
display_name: Optional[str] = None,
labels: Optional[Mapping[str, str]] = None,
manual_batch_tuning_parameters: Optional[GoogleCloudAiplatformV1ManualBatchTuningParametersArgs] = None,
generate_explanation: Optional[bool] = None,
encryption_spec: Optional[GoogleCloudAiplatformV1EncryptionSpecArgs] = None,
instance_config: Optional[GoogleCloudAiplatformV1BatchPredictionJobInstanceConfigArgs] = None,
dedicated_resources: Optional[GoogleCloudAiplatformV1BatchDedicatedResourcesArgs] = None,
location: Optional[str] = None,
explanation_spec: Optional[GoogleCloudAiplatformV1ExplanationSpecArgs] = None,
model: Optional[str] = None,
model_parameters: Optional[Any] = None,
disable_container_logging: Optional[bool] = None,
project: Optional[str] = None,
service_account: Optional[str] = None,
unmanaged_container_model: Optional[GoogleCloudAiplatformV1UnmanagedContainerModelArgs] = None)
func NewBatchPredictionJob(ctx *Context, name string, args BatchPredictionJobArgs, opts ...ResourceOption) (*BatchPredictionJob, error)
public BatchPredictionJob(string name, BatchPredictionJobArgs args, CustomResourceOptions? opts = null)
public BatchPredictionJob(String name, BatchPredictionJobArgs args)
public BatchPredictionJob(String name, BatchPredictionJobArgs args, CustomResourceOptions options)
type: google-native:aiplatform/v1:BatchPredictionJob
properties: # The arguments to resource properties.
options: # Bag of options to control resource's behavior.
Parameters
- name string
- The unique name of the resource.
- args BatchPredictionJobArgs
- The arguments to resource properties.
- opts CustomResourceOptions
- Bag of options to control resource's behavior.
- resource_name str
- The unique name of the resource.
- args BatchPredictionJobArgs
- The arguments to resource properties.
- opts ResourceOptions
- Bag of options to control resource's behavior.
- ctx Context
- Context object for the current deployment.
- name string
- The unique name of the resource.
- args BatchPredictionJobArgs
- The arguments to resource properties.
- opts ResourceOption
- Bag of options to control resource's behavior.
- name string
- The unique name of the resource.
- args BatchPredictionJobArgs
- The arguments to resource properties.
- opts CustomResourceOptions
- Bag of options to control resource's behavior.
- name String
- The unique name of the resource.
- args BatchPredictionJobArgs
- The arguments to resource properties.
- options CustomResourceOptions
- Bag of options to control resource's behavior.
Constructor example
The following reference example uses placeholder values for all input properties.
var batchPredictionJobResource = new GoogleNative.Aiplatform.V1.BatchPredictionJob("batchPredictionJobResource", new()
{
InputConfig = new GoogleNative.Aiplatform.V1.Inputs.GoogleCloudAiplatformV1BatchPredictionJobInputConfigArgs
{
InstancesFormat = "string",
BigquerySource = new GoogleNative.Aiplatform.V1.Inputs.GoogleCloudAiplatformV1BigQuerySourceArgs
{
InputUri = "string",
},
GcsSource = new GoogleNative.Aiplatform.V1.Inputs.GoogleCloudAiplatformV1GcsSourceArgs
{
Uris = new[]
{
"string",
},
},
},
OutputConfig = new GoogleNative.Aiplatform.V1.Inputs.GoogleCloudAiplatformV1BatchPredictionJobOutputConfigArgs
{
PredictionsFormat = "string",
BigqueryDestination = new GoogleNative.Aiplatform.V1.Inputs.GoogleCloudAiplatformV1BigQueryDestinationArgs
{
OutputUri = "string",
},
GcsDestination = new GoogleNative.Aiplatform.V1.Inputs.GoogleCloudAiplatformV1GcsDestinationArgs
{
OutputUriPrefix = "string",
},
},
DisplayName = "string",
Labels =
{
{ "string", "string" },
},
ManualBatchTuningParameters = new GoogleNative.Aiplatform.V1.Inputs.GoogleCloudAiplatformV1ManualBatchTuningParametersArgs
{
BatchSize = 0,
},
GenerateExplanation = false,
EncryptionSpec = new GoogleNative.Aiplatform.V1.Inputs.GoogleCloudAiplatformV1EncryptionSpecArgs
{
KmsKeyName = "string",
},
InstanceConfig = new GoogleNative.Aiplatform.V1.Inputs.GoogleCloudAiplatformV1BatchPredictionJobInstanceConfigArgs
{
ExcludedFields = new[]
{
"string",
},
IncludedFields = new[]
{
"string",
},
InstanceType = "string",
KeyField = "string",
},
DedicatedResources = new GoogleNative.Aiplatform.V1.Inputs.GoogleCloudAiplatformV1BatchDedicatedResourcesArgs
{
MachineSpec = new GoogleNative.Aiplatform.V1.Inputs.GoogleCloudAiplatformV1MachineSpecArgs
{
AcceleratorCount = 0,
AcceleratorType = GoogleNative.Aiplatform.V1.GoogleCloudAiplatformV1MachineSpecAcceleratorType.AcceleratorTypeUnspecified,
MachineType = "string",
TpuTopology = "string",
},
MaxReplicaCount = 0,
StartingReplicaCount = 0,
},
Location = "string",
ExplanationSpec = new GoogleNative.Aiplatform.V1.Inputs.GoogleCloudAiplatformV1ExplanationSpecArgs
{
Parameters = new GoogleNative.Aiplatform.V1.Inputs.GoogleCloudAiplatformV1ExplanationParametersArgs
{
Examples = new GoogleNative.Aiplatform.V1.Inputs.GoogleCloudAiplatformV1ExamplesArgs
{
ExampleGcsSource = new GoogleNative.Aiplatform.V1.Inputs.GoogleCloudAiplatformV1ExamplesExampleGcsSourceArgs
{
DataFormat = GoogleNative.Aiplatform.V1.GoogleCloudAiplatformV1ExamplesExampleGcsSourceDataFormat.DataFormatUnspecified,
GcsSource = new GoogleNative.Aiplatform.V1.Inputs.GoogleCloudAiplatformV1GcsSourceArgs
{
Uris = new[]
{
"string",
},
},
},
NearestNeighborSearchConfig = "any",
NeighborCount = 0,
Presets = new GoogleNative.Aiplatform.V1.Inputs.GoogleCloudAiplatformV1PresetsArgs
{
Modality = GoogleNative.Aiplatform.V1.GoogleCloudAiplatformV1PresetsModality.ModalityUnspecified,
Query = GoogleNative.Aiplatform.V1.GoogleCloudAiplatformV1PresetsQuery.Precise,
},
},
IntegratedGradientsAttribution = new GoogleNative.Aiplatform.V1.Inputs.GoogleCloudAiplatformV1IntegratedGradientsAttributionArgs
{
StepCount = 0,
BlurBaselineConfig = new GoogleNative.Aiplatform.V1.Inputs.GoogleCloudAiplatformV1BlurBaselineConfigArgs
{
MaxBlurSigma = 0,
},
SmoothGradConfig = new GoogleNative.Aiplatform.V1.Inputs.GoogleCloudAiplatformV1SmoothGradConfigArgs
{
FeatureNoiseSigma = new GoogleNative.Aiplatform.V1.Inputs.GoogleCloudAiplatformV1FeatureNoiseSigmaArgs
{
NoiseSigma = new[]
{
new GoogleNative.Aiplatform.V1.Inputs.GoogleCloudAiplatformV1FeatureNoiseSigmaNoiseSigmaForFeatureArgs
{
Name = "string",
Sigma = 0,
},
},
},
NoiseSigma = 0,
NoisySampleCount = 0,
},
},
OutputIndices = new[]
{
"any",
},
SampledShapleyAttribution = new GoogleNative.Aiplatform.V1.Inputs.GoogleCloudAiplatformV1SampledShapleyAttributionArgs
{
PathCount = 0,
},
TopK = 0,
XraiAttribution = new GoogleNative.Aiplatform.V1.Inputs.GoogleCloudAiplatformV1XraiAttributionArgs
{
StepCount = 0,
BlurBaselineConfig = new GoogleNative.Aiplatform.V1.Inputs.GoogleCloudAiplatformV1BlurBaselineConfigArgs
{
MaxBlurSigma = 0,
},
SmoothGradConfig = new GoogleNative.Aiplatform.V1.Inputs.GoogleCloudAiplatformV1SmoothGradConfigArgs
{
FeatureNoiseSigma = new GoogleNative.Aiplatform.V1.Inputs.GoogleCloudAiplatformV1FeatureNoiseSigmaArgs
{
NoiseSigma = new[]
{
new GoogleNative.Aiplatform.V1.Inputs.GoogleCloudAiplatformV1FeatureNoiseSigmaNoiseSigmaForFeatureArgs
{
Name = "string",
Sigma = 0,
},
},
},
NoiseSigma = 0,
NoisySampleCount = 0,
},
},
},
Metadata = new GoogleNative.Aiplatform.V1.Inputs.GoogleCloudAiplatformV1ExplanationMetadataArgs
{
Inputs =
{
{ "string", "string" },
},
Outputs =
{
{ "string", "string" },
},
FeatureAttributionsSchemaUri = "string",
LatentSpaceSource = "string",
},
},
Model = "string",
ModelParameters = "any",
DisableContainerLogging = false,
Project = "string",
ServiceAccount = "string",
UnmanagedContainerModel = new GoogleNative.Aiplatform.V1.Inputs.GoogleCloudAiplatformV1UnmanagedContainerModelArgs
{
ArtifactUri = "string",
ContainerSpec = new GoogleNative.Aiplatform.V1.Inputs.GoogleCloudAiplatformV1ModelContainerSpecArgs
{
ImageUri = "string",
Args = new[]
{
"string",
},
Command = new[]
{
"string",
},
DeploymentTimeout = "string",
Env = new[]
{
new GoogleNative.Aiplatform.V1.Inputs.GoogleCloudAiplatformV1EnvVarArgs
{
Name = "string",
Value = "string",
},
},
HealthProbe = new GoogleNative.Aiplatform.V1.Inputs.GoogleCloudAiplatformV1ProbeArgs
{
Exec = new GoogleNative.Aiplatform.V1.Inputs.GoogleCloudAiplatformV1ProbeExecActionArgs
{
Command = new[]
{
"string",
},
},
PeriodSeconds = 0,
TimeoutSeconds = 0,
},
HealthRoute = "string",
Ports = new[]
{
new GoogleNative.Aiplatform.V1.Inputs.GoogleCloudAiplatformV1PortArgs
{
ContainerPort = 0,
},
},
PredictRoute = "string",
SharedMemorySizeMb = "string",
StartupProbe = new GoogleNative.Aiplatform.V1.Inputs.GoogleCloudAiplatformV1ProbeArgs
{
Exec = new GoogleNative.Aiplatform.V1.Inputs.GoogleCloudAiplatformV1ProbeExecActionArgs
{
Command = new[]
{
"string",
},
},
PeriodSeconds = 0,
TimeoutSeconds = 0,
},
},
PredictSchemata = new GoogleNative.Aiplatform.V1.Inputs.GoogleCloudAiplatformV1PredictSchemataArgs
{
InstanceSchemaUri = "string",
ParametersSchemaUri = "string",
PredictionSchemaUri = "string",
},
},
});
example, err := aiplatform.NewBatchPredictionJob(ctx, "batchPredictionJobResource", &aiplatform.BatchPredictionJobArgs{
InputConfig: &aiplatform.GoogleCloudAiplatformV1BatchPredictionJobInputConfigArgs{
InstancesFormat: pulumi.String("string"),
BigquerySource: &aiplatform.GoogleCloudAiplatformV1BigQuerySourceArgs{
InputUri: pulumi.String("string"),
},
GcsSource: &aiplatform.GoogleCloudAiplatformV1GcsSourceArgs{
Uris: pulumi.StringArray{
pulumi.String("string"),
},
},
},
OutputConfig: &aiplatform.GoogleCloudAiplatformV1BatchPredictionJobOutputConfigArgs{
PredictionsFormat: pulumi.String("string"),
BigqueryDestination: &aiplatform.GoogleCloudAiplatformV1BigQueryDestinationArgs{
OutputUri: pulumi.String("string"),
},
GcsDestination: &aiplatform.GoogleCloudAiplatformV1GcsDestinationArgs{
OutputUriPrefix: pulumi.String("string"),
},
},
DisplayName: pulumi.String("string"),
Labels: pulumi.StringMap{
"string": pulumi.String("string"),
},
ManualBatchTuningParameters: &aiplatform.GoogleCloudAiplatformV1ManualBatchTuningParametersArgs{
BatchSize: pulumi.Int(0),
},
GenerateExplanation: pulumi.Bool(false),
EncryptionSpec: &aiplatform.GoogleCloudAiplatformV1EncryptionSpecArgs{
KmsKeyName: pulumi.String("string"),
},
InstanceConfig: &aiplatform.GoogleCloudAiplatformV1BatchPredictionJobInstanceConfigArgs{
ExcludedFields: pulumi.StringArray{
pulumi.String("string"),
},
IncludedFields: pulumi.StringArray{
pulumi.String("string"),
},
InstanceType: pulumi.String("string"),
KeyField: pulumi.String("string"),
},
DedicatedResources: &aiplatform.GoogleCloudAiplatformV1BatchDedicatedResourcesArgs{
MachineSpec: &aiplatform.GoogleCloudAiplatformV1MachineSpecArgs{
AcceleratorCount: pulumi.Int(0),
AcceleratorType: aiplatform.GoogleCloudAiplatformV1MachineSpecAcceleratorTypeAcceleratorTypeUnspecified,
MachineType: pulumi.String("string"),
TpuTopology: pulumi.String("string"),
},
MaxReplicaCount: pulumi.Int(0),
StartingReplicaCount: pulumi.Int(0),
},
Location: pulumi.String("string"),
ExplanationSpec: &aiplatform.GoogleCloudAiplatformV1ExplanationSpecArgs{
Parameters: &aiplatform.GoogleCloudAiplatformV1ExplanationParametersArgs{
Examples: &aiplatform.GoogleCloudAiplatformV1ExamplesArgs{
ExampleGcsSource: &aiplatform.GoogleCloudAiplatformV1ExamplesExampleGcsSourceArgs{
DataFormat: aiplatform.GoogleCloudAiplatformV1ExamplesExampleGcsSourceDataFormatDataFormatUnspecified,
GcsSource: &aiplatform.GoogleCloudAiplatformV1GcsSourceArgs{
Uris: pulumi.StringArray{
pulumi.String("string"),
},
},
},
NearestNeighborSearchConfig: pulumi.Any("any"),
NeighborCount: pulumi.Int(0),
Presets: &aiplatform.GoogleCloudAiplatformV1PresetsArgs{
Modality: aiplatform.GoogleCloudAiplatformV1PresetsModalityModalityUnspecified,
Query: aiplatform.GoogleCloudAiplatformV1PresetsQueryPrecise,
},
},
IntegratedGradientsAttribution: &aiplatform.GoogleCloudAiplatformV1IntegratedGradientsAttributionArgs{
StepCount: pulumi.Int(0),
BlurBaselineConfig: &aiplatform.GoogleCloudAiplatformV1BlurBaselineConfigArgs{
MaxBlurSigma: pulumi.Float64(0),
},
SmoothGradConfig: &aiplatform.GoogleCloudAiplatformV1SmoothGradConfigArgs{
FeatureNoiseSigma: &aiplatform.GoogleCloudAiplatformV1FeatureNoiseSigmaArgs{
NoiseSigma: aiplatform.GoogleCloudAiplatformV1FeatureNoiseSigmaNoiseSigmaForFeatureArray{
&aiplatform.GoogleCloudAiplatformV1FeatureNoiseSigmaNoiseSigmaForFeatureArgs{
Name: pulumi.String("string"),
Sigma: pulumi.Float64(0),
},
},
},
NoiseSigma: pulumi.Float64(0),
NoisySampleCount: pulumi.Int(0),
},
},
OutputIndices: pulumi.Array{
pulumi.Any("any"),
},
SampledShapleyAttribution: &aiplatform.GoogleCloudAiplatformV1SampledShapleyAttributionArgs{
PathCount: pulumi.Int(0),
},
TopK: pulumi.Int(0),
XraiAttribution: &aiplatform.GoogleCloudAiplatformV1XraiAttributionArgs{
StepCount: pulumi.Int(0),
BlurBaselineConfig: &aiplatform.GoogleCloudAiplatformV1BlurBaselineConfigArgs{
MaxBlurSigma: pulumi.Float64(0),
},
SmoothGradConfig: &aiplatform.GoogleCloudAiplatformV1SmoothGradConfigArgs{
FeatureNoiseSigma: &aiplatform.GoogleCloudAiplatformV1FeatureNoiseSigmaArgs{
NoiseSigma: aiplatform.GoogleCloudAiplatformV1FeatureNoiseSigmaNoiseSigmaForFeatureArray{
&aiplatform.GoogleCloudAiplatformV1FeatureNoiseSigmaNoiseSigmaForFeatureArgs{
Name: pulumi.String("string"),
Sigma: pulumi.Float64(0),
},
},
},
NoiseSigma: pulumi.Float64(0),
NoisySampleCount: pulumi.Int(0),
},
},
},
Metadata: &aiplatform.GoogleCloudAiplatformV1ExplanationMetadataArgs{
Inputs: pulumi.StringMap{
"string": pulumi.String("string"),
},
Outputs: pulumi.StringMap{
"string": pulumi.String("string"),
},
FeatureAttributionsSchemaUri: pulumi.String("string"),
LatentSpaceSource: pulumi.String("string"),
},
},
Model: pulumi.String("string"),
ModelParameters: pulumi.Any("any"),
DisableContainerLogging: pulumi.Bool(false),
Project: pulumi.String("string"),
ServiceAccount: pulumi.String("string"),
UnmanagedContainerModel: &aiplatform.GoogleCloudAiplatformV1UnmanagedContainerModelArgs{
ArtifactUri: pulumi.String("string"),
ContainerSpec: &aiplatform.GoogleCloudAiplatformV1ModelContainerSpecArgs{
ImageUri: pulumi.String("string"),
Args: pulumi.StringArray{
pulumi.String("string"),
},
Command: pulumi.StringArray{
pulumi.String("string"),
},
DeploymentTimeout: pulumi.String("string"),
Env: aiplatform.GoogleCloudAiplatformV1EnvVarArray{
&aiplatform.GoogleCloudAiplatformV1EnvVarArgs{
Name: pulumi.String("string"),
Value: pulumi.String("string"),
},
},
HealthProbe: &aiplatform.GoogleCloudAiplatformV1ProbeArgs{
Exec: &aiplatform.GoogleCloudAiplatformV1ProbeExecActionArgs{
Command: pulumi.StringArray{
pulumi.String("string"),
},
},
PeriodSeconds: pulumi.Int(0),
TimeoutSeconds: pulumi.Int(0),
},
HealthRoute: pulumi.String("string"),
Ports: aiplatform.GoogleCloudAiplatformV1PortArray{
&aiplatform.GoogleCloudAiplatformV1PortArgs{
ContainerPort: pulumi.Int(0),
},
},
PredictRoute: pulumi.String("string"),
SharedMemorySizeMb: pulumi.String("string"),
StartupProbe: &aiplatform.GoogleCloudAiplatformV1ProbeArgs{
Exec: &aiplatform.GoogleCloudAiplatformV1ProbeExecActionArgs{
Command: pulumi.StringArray{
pulumi.String("string"),
},
},
PeriodSeconds: pulumi.Int(0),
TimeoutSeconds: pulumi.Int(0),
},
},
PredictSchemata: &aiplatform.GoogleCloudAiplatformV1PredictSchemataArgs{
InstanceSchemaUri: pulumi.String("string"),
ParametersSchemaUri: pulumi.String("string"),
PredictionSchemaUri: pulumi.String("string"),
},
},
})
var batchPredictionJobResource = new BatchPredictionJob("batchPredictionJobResource", BatchPredictionJobArgs.builder()
.inputConfig(GoogleCloudAiplatformV1BatchPredictionJobInputConfigArgs.builder()
.instancesFormat("string")
.bigquerySource(GoogleCloudAiplatformV1BigQuerySourceArgs.builder()
.inputUri("string")
.build())
.gcsSource(GoogleCloudAiplatformV1GcsSourceArgs.builder()
.uris("string")
.build())
.build())
.outputConfig(GoogleCloudAiplatformV1BatchPredictionJobOutputConfigArgs.builder()
.predictionsFormat("string")
.bigqueryDestination(GoogleCloudAiplatformV1BigQueryDestinationArgs.builder()
.outputUri("string")
.build())
.gcsDestination(GoogleCloudAiplatformV1GcsDestinationArgs.builder()
.outputUriPrefix("string")
.build())
.build())
.displayName("string")
.labels(Map.of("string", "string"))
.manualBatchTuningParameters(GoogleCloudAiplatformV1ManualBatchTuningParametersArgs.builder()
.batchSize(0)
.build())
.generateExplanation(false)
.encryptionSpec(GoogleCloudAiplatformV1EncryptionSpecArgs.builder()
.kmsKeyName("string")
.build())
.instanceConfig(GoogleCloudAiplatformV1BatchPredictionJobInstanceConfigArgs.builder()
.excludedFields("string")
.includedFields("string")
.instanceType("string")
.keyField("string")
.build())
.dedicatedResources(GoogleCloudAiplatformV1BatchDedicatedResourcesArgs.builder()
.machineSpec(GoogleCloudAiplatformV1MachineSpecArgs.builder()
.acceleratorCount(0)
.acceleratorType("ACCELERATOR_TYPE_UNSPECIFIED")
.machineType("string")
.tpuTopology("string")
.build())
.maxReplicaCount(0)
.startingReplicaCount(0)
.build())
.location("string")
.explanationSpec(GoogleCloudAiplatformV1ExplanationSpecArgs.builder()
.parameters(GoogleCloudAiplatformV1ExplanationParametersArgs.builder()
.examples(GoogleCloudAiplatformV1ExamplesArgs.builder()
.exampleGcsSource(GoogleCloudAiplatformV1ExamplesExampleGcsSourceArgs.builder()
.dataFormat("DATA_FORMAT_UNSPECIFIED")
.gcsSource(GoogleCloudAiplatformV1GcsSourceArgs.builder()
.uris("string")
.build())
.build())
.nearestNeighborSearchConfig("any")
.neighborCount(0)
.presets(GoogleCloudAiplatformV1PresetsArgs.builder()
.modality("MODALITY_UNSPECIFIED")
.query("PRECISE")
.build())
.build())
.integratedGradientsAttribution(GoogleCloudAiplatformV1IntegratedGradientsAttributionArgs.builder()
.stepCount(0)
.blurBaselineConfig(GoogleCloudAiplatformV1BlurBaselineConfigArgs.builder()
.maxBlurSigma(0)
.build())
.smoothGradConfig(GoogleCloudAiplatformV1SmoothGradConfigArgs.builder()
.featureNoiseSigma(GoogleCloudAiplatformV1FeatureNoiseSigmaArgs.builder()
.noiseSigma(GoogleCloudAiplatformV1FeatureNoiseSigmaNoiseSigmaForFeatureArgs.builder()
.name("string")
.sigma(0)
.build())
.build())
.noiseSigma(0)
.noisySampleCount(0)
.build())
.build())
.outputIndices("any")
.sampledShapleyAttribution(GoogleCloudAiplatformV1SampledShapleyAttributionArgs.builder()
.pathCount(0)
.build())
.topK(0)
.xraiAttribution(GoogleCloudAiplatformV1XraiAttributionArgs.builder()
.stepCount(0)
.blurBaselineConfig(GoogleCloudAiplatformV1BlurBaselineConfigArgs.builder()
.maxBlurSigma(0)
.build())
.smoothGradConfig(GoogleCloudAiplatformV1SmoothGradConfigArgs.builder()
.featureNoiseSigma(GoogleCloudAiplatformV1FeatureNoiseSigmaArgs.builder()
.noiseSigma(GoogleCloudAiplatformV1FeatureNoiseSigmaNoiseSigmaForFeatureArgs.builder()
.name("string")
.sigma(0)
.build())
.build())
.noiseSigma(0)
.noisySampleCount(0)
.build())
.build())
.build())
.metadata(GoogleCloudAiplatformV1ExplanationMetadataArgs.builder()
.inputs(Map.of("string", "string"))
.outputs(Map.of("string", "string"))
.featureAttributionsSchemaUri("string")
.latentSpaceSource("string")
.build())
.build())
.model("string")
.modelParameters("any")
.disableContainerLogging(false)
.project("string")
.serviceAccount("string")
.unmanagedContainerModel(GoogleCloudAiplatformV1UnmanagedContainerModelArgs.builder()
.artifactUri("string")
.containerSpec(GoogleCloudAiplatformV1ModelContainerSpecArgs.builder()
.imageUri("string")
.args("string")
.command("string")
.deploymentTimeout("string")
.env(GoogleCloudAiplatformV1EnvVarArgs.builder()
.name("string")
.value("string")
.build())
.healthProbe(GoogleCloudAiplatformV1ProbeArgs.builder()
.exec(GoogleCloudAiplatformV1ProbeExecActionArgs.builder()
.command("string")
.build())
.periodSeconds(0)
.timeoutSeconds(0)
.build())
.healthRoute("string")
.ports(GoogleCloudAiplatformV1PortArgs.builder()
.containerPort(0)
.build())
.predictRoute("string")
.sharedMemorySizeMb("string")
.startupProbe(GoogleCloudAiplatformV1ProbeArgs.builder()
.exec(GoogleCloudAiplatformV1ProbeExecActionArgs.builder()
.command("string")
.build())
.periodSeconds(0)
.timeoutSeconds(0)
.build())
.build())
.predictSchemata(GoogleCloudAiplatformV1PredictSchemataArgs.builder()
.instanceSchemaUri("string")
.parametersSchemaUri("string")
.predictionSchemaUri("string")
.build())
.build())
.build());
batch_prediction_job_resource = google_native.aiplatform.v1.BatchPredictionJob("batchPredictionJobResource",
input_config=google_native.aiplatform.v1.GoogleCloudAiplatformV1BatchPredictionJobInputConfigArgs(
instances_format="string",
bigquery_source=google_native.aiplatform.v1.GoogleCloudAiplatformV1BigQuerySourceArgs(
input_uri="string",
),
gcs_source=google_native.aiplatform.v1.GoogleCloudAiplatformV1GcsSourceArgs(
uris=["string"],
),
),
output_config=google_native.aiplatform.v1.GoogleCloudAiplatformV1BatchPredictionJobOutputConfigArgs(
predictions_format="string",
bigquery_destination=google_native.aiplatform.v1.GoogleCloudAiplatformV1BigQueryDestinationArgs(
output_uri="string",
),
gcs_destination=google_native.aiplatform.v1.GoogleCloudAiplatformV1GcsDestinationArgs(
output_uri_prefix="string",
),
),
display_name="string",
labels={
"string": "string",
},
manual_batch_tuning_parameters=google_native.aiplatform.v1.GoogleCloudAiplatformV1ManualBatchTuningParametersArgs(
batch_size=0,
),
generate_explanation=False,
encryption_spec=google_native.aiplatform.v1.GoogleCloudAiplatformV1EncryptionSpecArgs(
kms_key_name="string",
),
instance_config=google_native.aiplatform.v1.GoogleCloudAiplatformV1BatchPredictionJobInstanceConfigArgs(
excluded_fields=["string"],
included_fields=["string"],
instance_type="string",
key_field="string",
),
dedicated_resources=google_native.aiplatform.v1.GoogleCloudAiplatformV1BatchDedicatedResourcesArgs(
machine_spec=google_native.aiplatform.v1.GoogleCloudAiplatformV1MachineSpecArgs(
accelerator_count=0,
accelerator_type=google_native.aiplatform.v1.GoogleCloudAiplatformV1MachineSpecAcceleratorType.ACCELERATOR_TYPE_UNSPECIFIED,
machine_type="string",
tpu_topology="string",
),
max_replica_count=0,
starting_replica_count=0,
),
location="string",
explanation_spec=google_native.aiplatform.v1.GoogleCloudAiplatformV1ExplanationSpecArgs(
parameters=google_native.aiplatform.v1.GoogleCloudAiplatformV1ExplanationParametersArgs(
examples=google_native.aiplatform.v1.GoogleCloudAiplatformV1ExamplesArgs(
example_gcs_source=google_native.aiplatform.v1.GoogleCloudAiplatformV1ExamplesExampleGcsSourceArgs(
data_format=google_native.aiplatform.v1.GoogleCloudAiplatformV1ExamplesExampleGcsSourceDataFormat.DATA_FORMAT_UNSPECIFIED,
gcs_source=google_native.aiplatform.v1.GoogleCloudAiplatformV1GcsSourceArgs(
uris=["string"],
),
),
nearest_neighbor_search_config="any",
neighbor_count=0,
presets=google_native.aiplatform.v1.GoogleCloudAiplatformV1PresetsArgs(
modality=google_native.aiplatform.v1.GoogleCloudAiplatformV1PresetsModality.MODALITY_UNSPECIFIED,
query=google_native.aiplatform.v1.GoogleCloudAiplatformV1PresetsQuery.PRECISE,
),
),
integrated_gradients_attribution=google_native.aiplatform.v1.GoogleCloudAiplatformV1IntegratedGradientsAttributionArgs(
step_count=0,
blur_baseline_config=google_native.aiplatform.v1.GoogleCloudAiplatformV1BlurBaselineConfigArgs(
max_blur_sigma=0,
),
smooth_grad_config=google_native.aiplatform.v1.GoogleCloudAiplatformV1SmoothGradConfigArgs(
feature_noise_sigma=google_native.aiplatform.v1.GoogleCloudAiplatformV1FeatureNoiseSigmaArgs(
noise_sigma=[google_native.aiplatform.v1.GoogleCloudAiplatformV1FeatureNoiseSigmaNoiseSigmaForFeatureArgs(
name="string",
sigma=0,
)],
),
noise_sigma=0,
noisy_sample_count=0,
),
),
output_indices=["any"],
sampled_shapley_attribution=google_native.aiplatform.v1.GoogleCloudAiplatformV1SampledShapleyAttributionArgs(
path_count=0,
),
top_k=0,
xrai_attribution=google_native.aiplatform.v1.GoogleCloudAiplatformV1XraiAttributionArgs(
step_count=0,
blur_baseline_config=google_native.aiplatform.v1.GoogleCloudAiplatformV1BlurBaselineConfigArgs(
max_blur_sigma=0,
),
smooth_grad_config=google_native.aiplatform.v1.GoogleCloudAiplatformV1SmoothGradConfigArgs(
feature_noise_sigma=google_native.aiplatform.v1.GoogleCloudAiplatformV1FeatureNoiseSigmaArgs(
noise_sigma=[google_native.aiplatform.v1.GoogleCloudAiplatformV1FeatureNoiseSigmaNoiseSigmaForFeatureArgs(
name="string",
sigma=0,
)],
),
noise_sigma=0,
noisy_sample_count=0,
),
),
),
metadata=google_native.aiplatform.v1.GoogleCloudAiplatformV1ExplanationMetadataArgs(
inputs={
"string": "string",
},
outputs={
"string": "string",
},
feature_attributions_schema_uri="string",
latent_space_source="string",
),
),
model="string",
model_parameters="any",
disable_container_logging=False,
project="string",
service_account="string",
unmanaged_container_model=google_native.aiplatform.v1.GoogleCloudAiplatformV1UnmanagedContainerModelArgs(
artifact_uri="string",
container_spec=google_native.aiplatform.v1.GoogleCloudAiplatformV1ModelContainerSpecArgs(
image_uri="string",
args=["string"],
command=["string"],
deployment_timeout="string",
env=[google_native.aiplatform.v1.GoogleCloudAiplatformV1EnvVarArgs(
name="string",
value="string",
)],
health_probe=google_native.aiplatform.v1.GoogleCloudAiplatformV1ProbeArgs(
exec_=google_native.aiplatform.v1.GoogleCloudAiplatformV1ProbeExecActionArgs(
command=["string"],
),
period_seconds=0,
timeout_seconds=0,
),
health_route="string",
ports=[google_native.aiplatform.v1.GoogleCloudAiplatformV1PortArgs(
container_port=0,
)],
predict_route="string",
shared_memory_size_mb="string",
startup_probe=google_native.aiplatform.v1.GoogleCloudAiplatformV1ProbeArgs(
exec_=google_native.aiplatform.v1.GoogleCloudAiplatformV1ProbeExecActionArgs(
command=["string"],
),
period_seconds=0,
timeout_seconds=0,
),
),
predict_schemata=google_native.aiplatform.v1.GoogleCloudAiplatformV1PredictSchemataArgs(
instance_schema_uri="string",
parameters_schema_uri="string",
prediction_schema_uri="string",
),
))
const batchPredictionJobResource = new google_native.aiplatform.v1.BatchPredictionJob("batchPredictionJobResource", {
inputConfig: {
instancesFormat: "string",
bigquerySource: {
inputUri: "string",
},
gcsSource: {
uris: ["string"],
},
},
outputConfig: {
predictionsFormat: "string",
bigqueryDestination: {
outputUri: "string",
},
gcsDestination: {
outputUriPrefix: "string",
},
},
displayName: "string",
labels: {
string: "string",
},
manualBatchTuningParameters: {
batchSize: 0,
},
generateExplanation: false,
encryptionSpec: {
kmsKeyName: "string",
},
instanceConfig: {
excludedFields: ["string"],
includedFields: ["string"],
instanceType: "string",
keyField: "string",
},
dedicatedResources: {
machineSpec: {
acceleratorCount: 0,
acceleratorType: google_native.aiplatform.v1.GoogleCloudAiplatformV1MachineSpecAcceleratorType.AcceleratorTypeUnspecified,
machineType: "string",
tpuTopology: "string",
},
maxReplicaCount: 0,
startingReplicaCount: 0,
},
location: "string",
explanationSpec: {
parameters: {
examples: {
exampleGcsSource: {
dataFormat: google_native.aiplatform.v1.GoogleCloudAiplatformV1ExamplesExampleGcsSourceDataFormat.DataFormatUnspecified,
gcsSource: {
uris: ["string"],
},
},
nearestNeighborSearchConfig: "any",
neighborCount: 0,
presets: {
modality: google_native.aiplatform.v1.GoogleCloudAiplatformV1PresetsModality.ModalityUnspecified,
query: google_native.aiplatform.v1.GoogleCloudAiplatformV1PresetsQuery.Precise,
},
},
integratedGradientsAttribution: {
stepCount: 0,
blurBaselineConfig: {
maxBlurSigma: 0,
},
smoothGradConfig: {
featureNoiseSigma: {
noiseSigma: [{
name: "string",
sigma: 0,
}],
},
noiseSigma: 0,
noisySampleCount: 0,
},
},
outputIndices: ["any"],
sampledShapleyAttribution: {
pathCount: 0,
},
topK: 0,
xraiAttribution: {
stepCount: 0,
blurBaselineConfig: {
maxBlurSigma: 0,
},
smoothGradConfig: {
featureNoiseSigma: {
noiseSigma: [{
name: "string",
sigma: 0,
}],
},
noiseSigma: 0,
noisySampleCount: 0,
},
},
},
metadata: {
inputs: {
string: "string",
},
outputs: {
string: "string",
},
featureAttributionsSchemaUri: "string",
latentSpaceSource: "string",
},
},
model: "string",
modelParameters: "any",
disableContainerLogging: false,
project: "string",
serviceAccount: "string",
unmanagedContainerModel: {
artifactUri: "string",
containerSpec: {
imageUri: "string",
args: ["string"],
command: ["string"],
deploymentTimeout: "string",
env: [{
name: "string",
value: "string",
}],
healthProbe: {
exec: {
command: ["string"],
},
periodSeconds: 0,
timeoutSeconds: 0,
},
healthRoute: "string",
ports: [{
containerPort: 0,
}],
predictRoute: "string",
sharedMemorySizeMb: "string",
startupProbe: {
exec: {
command: ["string"],
},
periodSeconds: 0,
timeoutSeconds: 0,
},
},
predictSchemata: {
instanceSchemaUri: "string",
parametersSchemaUri: "string",
predictionSchemaUri: "string",
},
},
});
type: google-native:aiplatform/v1:BatchPredictionJob
properties:
dedicatedResources:
machineSpec:
acceleratorCount: 0
acceleratorType: ACCELERATOR_TYPE_UNSPECIFIED
machineType: string
tpuTopology: string
maxReplicaCount: 0
startingReplicaCount: 0
disableContainerLogging: false
displayName: string
encryptionSpec:
kmsKeyName: string
explanationSpec:
metadata:
featureAttributionsSchemaUri: string
inputs:
string: string
latentSpaceSource: string
outputs:
string: string
parameters:
examples:
exampleGcsSource:
dataFormat: DATA_FORMAT_UNSPECIFIED
gcsSource:
uris:
- string
nearestNeighborSearchConfig: any
neighborCount: 0
presets:
modality: MODALITY_UNSPECIFIED
query: PRECISE
integratedGradientsAttribution:
blurBaselineConfig:
maxBlurSigma: 0
smoothGradConfig:
featureNoiseSigma:
noiseSigma:
- name: string
sigma: 0
noiseSigma: 0
noisySampleCount: 0
stepCount: 0
outputIndices:
- any
sampledShapleyAttribution:
pathCount: 0
topK: 0
xraiAttribution:
blurBaselineConfig:
maxBlurSigma: 0
smoothGradConfig:
featureNoiseSigma:
noiseSigma:
- name: string
sigma: 0
noiseSigma: 0
noisySampleCount: 0
stepCount: 0
generateExplanation: false
inputConfig:
bigquerySource:
inputUri: string
gcsSource:
uris:
- string
instancesFormat: string
instanceConfig:
excludedFields:
- string
includedFields:
- string
instanceType: string
keyField: string
labels:
string: string
location: string
manualBatchTuningParameters:
batchSize: 0
model: string
modelParameters: any
outputConfig:
bigqueryDestination:
outputUri: string
gcsDestination:
outputUriPrefix: string
predictionsFormat: string
project: string
serviceAccount: string
unmanagedContainerModel:
artifactUri: string
containerSpec:
args:
- string
command:
- string
deploymentTimeout: string
env:
- name: string
value: string
healthProbe:
exec:
command:
- string
periodSeconds: 0
timeoutSeconds: 0
healthRoute: string
imageUri: string
ports:
- containerPort: 0
predictRoute: string
sharedMemorySizeMb: string
startupProbe:
exec:
command:
- string
periodSeconds: 0
timeoutSeconds: 0
predictSchemata:
instanceSchemaUri: string
parametersSchemaUri: string
predictionSchemaUri: string
BatchPredictionJob Resource Properties
To learn more about resource properties and how to use them, see Inputs and Outputs in the Architecture and Concepts docs.
Inputs
The BatchPredictionJob resource accepts the following input properties:
- Display
Name string - The user-defined name of this BatchPredictionJob.
- Input
Config Pulumi.Google Native. Aiplatform. V1. Inputs. Google Cloud Aiplatform V1Batch Prediction Job Input Config - Input configuration of the instances on which predictions are performed. The schema of any single instance may be specified via the Model's PredictSchemata's instance_schema_uri.
- Output
Config Pulumi.Google Native. Aiplatform. V1. Inputs. Google Cloud Aiplatform V1Batch Prediction Job Output Config - The Configuration specifying where output predictions should be written. The schema of any single prediction may be specified as a concatenation of Model's PredictSchemata's instance_schema_uri and prediction_schema_uri.
- Dedicated
Resources Pulumi.Google Native. Aiplatform. V1. Inputs. Google Cloud Aiplatform V1Batch Dedicated Resources - The config of resources used by the Model during the batch prediction. If the Model supports DEDICATED_RESOURCES this config may be provided (and the job will use these resources), if the Model doesn't support AUTOMATIC_RESOURCES, this config must be provided.
- Disable
Container boolLogging - For custom-trained Models and AutoML Tabular Models, the container of the DeployedModel instances will send
stderr
andstdout
streams to Cloud Logging by default. Please note that the logs incur cost, which are subject to Cloud Logging pricing. User can disable container logging by setting this flag to true. - Encryption
Spec Pulumi.Google Native. Aiplatform. V1. Inputs. Google Cloud Aiplatform V1Encryption Spec - Customer-managed encryption key options for a BatchPredictionJob. If this is set, then all resources created by the BatchPredictionJob will be encrypted with the provided encryption key.
- Explanation
Spec Pulumi.Google Native. Aiplatform. V1. Inputs. Google Cloud Aiplatform V1Explanation Spec - Explanation configuration for this BatchPredictionJob. Can be specified only if generate_explanation is set to
true
. This value overrides the value of Model.explanation_spec. All fields of explanation_spec are optional in the request. If a field of the explanation_spec object is not populated, the corresponding field of the Model.explanation_spec object is inherited. - Generate
Explanation bool - Generate explanation with the batch prediction results. When set to
true
, the batch prediction output changes based on thepredictions_format
field of the BatchPredictionJob.output_config object: *bigquery
: output includes a column namedexplanation
. The value is a struct that conforms to the Explanation object. *jsonl
: The JSON objects on each line include an additional entry keyedexplanation
. The value of the entry is a JSON object that conforms to the Explanation object. *csv
: Generating explanations for CSV format is not supported. If this field is set to true, either the Model.explanation_spec or explanation_spec must be populated. - Instance
Config Pulumi.Google Native. Aiplatform. V1. Inputs. Google Cloud Aiplatform V1Batch Prediction Job Instance Config - Configuration for how to convert batch prediction input instances to the prediction instances that are sent to the Model.
- Labels Dictionary<string, string>
- The labels with user-defined metadata to organize BatchPredictionJobs. 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.
- Location string
- Manual
Batch Pulumi.Tuning Parameters Google Native. Aiplatform. V1. Inputs. Google Cloud Aiplatform V1Manual Batch Tuning Parameters - Immutable. Parameters configuring the batch behavior. Currently only applicable when dedicated_resources are used (in other cases Vertex AI does the tuning itself).
- Model string
- The name of the Model resource that produces the predictions via this job, must share the same ancestor Location. Starting this job has no impact on any existing deployments of the Model and their resources. Exactly one of model and unmanaged_container_model must be set. The model resource name may contain version id or version alias to specify the version. Example:
projects/{project}/locations/{location}/models/{model}@2
orprojects/{project}/locations/{location}/models/{model}@golden
if no version is specified, the default version will be deployed. The model resource could also be a publisher model. Example:publishers/{publisher}/models/{model}
orprojects/{project}/locations/{location}/publishers/{publisher}/models/{model}
- Model
Parameters object - The parameters that govern the predictions. The schema of the parameters may be specified via the Model's PredictSchemata's parameters_schema_uri.
- Project string
- Service
Account string - 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 Google Cloud resources. Users deploying the Model must have the
iam.serviceAccounts.actAs
permission on this service account. - Unmanaged
Container Pulumi.Model Google Native. Aiplatform. V1. Inputs. Google Cloud Aiplatform V1Unmanaged Container Model - Contains model information necessary to perform batch prediction without requiring uploading to model registry. Exactly one of model and unmanaged_container_model must be set.
- Display
Name string - The user-defined name of this BatchPredictionJob.
- Input
Config GoogleCloud Aiplatform V1Batch Prediction Job Input Config Args - Input configuration of the instances on which predictions are performed. The schema of any single instance may be specified via the Model's PredictSchemata's instance_schema_uri.
- Output
Config GoogleCloud Aiplatform V1Batch Prediction Job Output Config Args - The Configuration specifying where output predictions should be written. The schema of any single prediction may be specified as a concatenation of Model's PredictSchemata's instance_schema_uri and prediction_schema_uri.
- Dedicated
Resources GoogleCloud Aiplatform V1Batch Dedicated Resources Args - The config of resources used by the Model during the batch prediction. If the Model supports DEDICATED_RESOURCES this config may be provided (and the job will use these resources), if the Model doesn't support AUTOMATIC_RESOURCES, this config must be provided.
- Disable
Container boolLogging - For custom-trained Models and AutoML Tabular Models, the container of the DeployedModel instances will send
stderr
andstdout
streams to Cloud Logging by default. Please note that the logs incur cost, which are subject to Cloud Logging pricing. User can disable container logging by setting this flag to true. - Encryption
Spec GoogleCloud Aiplatform V1Encryption Spec Args - Customer-managed encryption key options for a BatchPredictionJob. If this is set, then all resources created by the BatchPredictionJob will be encrypted with the provided encryption key.
- Explanation
Spec GoogleCloud Aiplatform V1Explanation Spec Args - Explanation configuration for this BatchPredictionJob. Can be specified only if generate_explanation is set to
true
. This value overrides the value of Model.explanation_spec. All fields of explanation_spec are optional in the request. If a field of the explanation_spec object is not populated, the corresponding field of the Model.explanation_spec object is inherited. - Generate
Explanation bool - Generate explanation with the batch prediction results. When set to
true
, the batch prediction output changes based on thepredictions_format
field of the BatchPredictionJob.output_config object: *bigquery
: output includes a column namedexplanation
. The value is a struct that conforms to the Explanation object. *jsonl
: The JSON objects on each line include an additional entry keyedexplanation
. The value of the entry is a JSON object that conforms to the Explanation object. *csv
: Generating explanations for CSV format is not supported. If this field is set to true, either the Model.explanation_spec or explanation_spec must be populated. - Instance
Config GoogleCloud Aiplatform V1Batch Prediction Job Instance Config Args - Configuration for how to convert batch prediction input instances to the prediction instances that are sent to the Model.
- Labels map[string]string
- The labels with user-defined metadata to organize BatchPredictionJobs. 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.
- Location string
- Manual
Batch GoogleTuning Parameters Cloud Aiplatform V1Manual Batch Tuning Parameters Args - Immutable. Parameters configuring the batch behavior. Currently only applicable when dedicated_resources are used (in other cases Vertex AI does the tuning itself).
- Model string
- The name of the Model resource that produces the predictions via this job, must share the same ancestor Location. Starting this job has no impact on any existing deployments of the Model and their resources. Exactly one of model and unmanaged_container_model must be set. The model resource name may contain version id or version alias to specify the version. Example:
projects/{project}/locations/{location}/models/{model}@2
orprojects/{project}/locations/{location}/models/{model}@golden
if no version is specified, the default version will be deployed. The model resource could also be a publisher model. Example:publishers/{publisher}/models/{model}
orprojects/{project}/locations/{location}/publishers/{publisher}/models/{model}
- Model
Parameters interface{} - The parameters that govern the predictions. The schema of the parameters may be specified via the Model's PredictSchemata's parameters_schema_uri.
- Project string
- Service
Account string - 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 Google Cloud resources. Users deploying the Model must have the
iam.serviceAccounts.actAs
permission on this service account. - Unmanaged
Container GoogleModel Cloud Aiplatform V1Unmanaged Container Model Args - Contains model information necessary to perform batch prediction without requiring uploading to model registry. Exactly one of model and unmanaged_container_model must be set.
- display
Name String - The user-defined name of this BatchPredictionJob.
- input
Config GoogleCloud Aiplatform V1Batch Prediction Job Input Config - Input configuration of the instances on which predictions are performed. The schema of any single instance may be specified via the Model's PredictSchemata's instance_schema_uri.
- output
Config GoogleCloud Aiplatform V1Batch Prediction Job Output Config - The Configuration specifying where output predictions should be written. The schema of any single prediction may be specified as a concatenation of Model's PredictSchemata's instance_schema_uri and prediction_schema_uri.
- dedicated
Resources GoogleCloud Aiplatform V1Batch Dedicated Resources - The config of resources used by the Model during the batch prediction. If the Model supports DEDICATED_RESOURCES this config may be provided (and the job will use these resources), if the Model doesn't support AUTOMATIC_RESOURCES, this config must be provided.
- disable
Container BooleanLogging - For custom-trained Models and AutoML Tabular Models, the container of the DeployedModel instances will send
stderr
andstdout
streams to Cloud Logging by default. Please note that the logs incur cost, which are subject to Cloud Logging pricing. User can disable container logging by setting this flag to true. - encryption
Spec GoogleCloud Aiplatform V1Encryption Spec - Customer-managed encryption key options for a BatchPredictionJob. If this is set, then all resources created by the BatchPredictionJob will be encrypted with the provided encryption key.
- explanation
Spec GoogleCloud Aiplatform V1Explanation Spec - Explanation configuration for this BatchPredictionJob. Can be specified only if generate_explanation is set to
true
. This value overrides the value of Model.explanation_spec. All fields of explanation_spec are optional in the request. If a field of the explanation_spec object is not populated, the corresponding field of the Model.explanation_spec object is inherited. - generate
Explanation Boolean - Generate explanation with the batch prediction results. When set to
true
, the batch prediction output changes based on thepredictions_format
field of the BatchPredictionJob.output_config object: *bigquery
: output includes a column namedexplanation
. The value is a struct that conforms to the Explanation object. *jsonl
: The JSON objects on each line include an additional entry keyedexplanation
. The value of the entry is a JSON object that conforms to the Explanation object. *csv
: Generating explanations for CSV format is not supported. If this field is set to true, either the Model.explanation_spec or explanation_spec must be populated. - instance
Config GoogleCloud Aiplatform V1Batch Prediction Job Instance Config - Configuration for how to convert batch prediction input instances to the prediction instances that are sent to the Model.
- labels Map<String,String>
- The labels with user-defined metadata to organize BatchPredictionJobs. 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.
- location String
- manual
Batch GoogleTuning Parameters Cloud Aiplatform V1Manual Batch Tuning Parameters - Immutable. Parameters configuring the batch behavior. Currently only applicable when dedicated_resources are used (in other cases Vertex AI does the tuning itself).
- model String
- The name of the Model resource that produces the predictions via this job, must share the same ancestor Location. Starting this job has no impact on any existing deployments of the Model and their resources. Exactly one of model and unmanaged_container_model must be set. The model resource name may contain version id or version alias to specify the version. Example:
projects/{project}/locations/{location}/models/{model}@2
orprojects/{project}/locations/{location}/models/{model}@golden
if no version is specified, the default version will be deployed. The model resource could also be a publisher model. Example:publishers/{publisher}/models/{model}
orprojects/{project}/locations/{location}/publishers/{publisher}/models/{model}
- model
Parameters Object - The parameters that govern the predictions. The schema of the parameters may be specified via the Model's PredictSchemata's parameters_schema_uri.
- project String
- service
Account String - 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 Google Cloud resources. Users deploying the Model must have the
iam.serviceAccounts.actAs
permission on this service account. - unmanaged
Container GoogleModel Cloud Aiplatform V1Unmanaged Container Model - Contains model information necessary to perform batch prediction without requiring uploading to model registry. Exactly one of model and unmanaged_container_model must be set.
- display
Name string - The user-defined name of this BatchPredictionJob.
- input
Config GoogleCloud Aiplatform V1Batch Prediction Job Input Config - Input configuration of the instances on which predictions are performed. The schema of any single instance may be specified via the Model's PredictSchemata's instance_schema_uri.
- output
Config GoogleCloud Aiplatform V1Batch Prediction Job Output Config - The Configuration specifying where output predictions should be written. The schema of any single prediction may be specified as a concatenation of Model's PredictSchemata's instance_schema_uri and prediction_schema_uri.
- dedicated
Resources GoogleCloud Aiplatform V1Batch Dedicated Resources - The config of resources used by the Model during the batch prediction. If the Model supports DEDICATED_RESOURCES this config may be provided (and the job will use these resources), if the Model doesn't support AUTOMATIC_RESOURCES, this config must be provided.
- disable
Container booleanLogging - For custom-trained Models and AutoML Tabular Models, the container of the DeployedModel instances will send
stderr
andstdout
streams to Cloud Logging by default. Please note that the logs incur cost, which are subject to Cloud Logging pricing. User can disable container logging by setting this flag to true. - encryption
Spec GoogleCloud Aiplatform V1Encryption Spec - Customer-managed encryption key options for a BatchPredictionJob. If this is set, then all resources created by the BatchPredictionJob will be encrypted with the provided encryption key.
- explanation
Spec GoogleCloud Aiplatform V1Explanation Spec - Explanation configuration for this BatchPredictionJob. Can be specified only if generate_explanation is set to
true
. This value overrides the value of Model.explanation_spec. All fields of explanation_spec are optional in the request. If a field of the explanation_spec object is not populated, the corresponding field of the Model.explanation_spec object is inherited. - generate
Explanation boolean - Generate explanation with the batch prediction results. When set to
true
, the batch prediction output changes based on thepredictions_format
field of the BatchPredictionJob.output_config object: *bigquery
: output includes a column namedexplanation
. The value is a struct that conforms to the Explanation object. *jsonl
: The JSON objects on each line include an additional entry keyedexplanation
. The value of the entry is a JSON object that conforms to the Explanation object. *csv
: Generating explanations for CSV format is not supported. If this field is set to true, either the Model.explanation_spec or explanation_spec must be populated. - instance
Config GoogleCloud Aiplatform V1Batch Prediction Job Instance Config - Configuration for how to convert batch prediction input instances to the prediction instances that are sent to the Model.
- labels {[key: string]: string}
- The labels with user-defined metadata to organize BatchPredictionJobs. 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.
- location string
- manual
Batch GoogleTuning Parameters Cloud Aiplatform V1Manual Batch Tuning Parameters - Immutable. Parameters configuring the batch behavior. Currently only applicable when dedicated_resources are used (in other cases Vertex AI does the tuning itself).
- model string
- The name of the Model resource that produces the predictions via this job, must share the same ancestor Location. Starting this job has no impact on any existing deployments of the Model and their resources. Exactly one of model and unmanaged_container_model must be set. The model resource name may contain version id or version alias to specify the version. Example:
projects/{project}/locations/{location}/models/{model}@2
orprojects/{project}/locations/{location}/models/{model}@golden
if no version is specified, the default version will be deployed. The model resource could also be a publisher model. Example:publishers/{publisher}/models/{model}
orprojects/{project}/locations/{location}/publishers/{publisher}/models/{model}
- model
Parameters any - The parameters that govern the predictions. The schema of the parameters may be specified via the Model's PredictSchemata's parameters_schema_uri.
- project string
- service
Account string - 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 Google Cloud resources. Users deploying the Model must have the
iam.serviceAccounts.actAs
permission on this service account. - unmanaged
Container GoogleModel Cloud Aiplatform V1Unmanaged Container Model - Contains model information necessary to perform batch prediction without requiring uploading to model registry. Exactly one of model and unmanaged_container_model must be set.
- display_
name str - The user-defined name of this BatchPredictionJob.
- input_
config GoogleCloud Aiplatform V1Batch Prediction Job Input Config Args - Input configuration of the instances on which predictions are performed. The schema of any single instance may be specified via the Model's PredictSchemata's instance_schema_uri.
- output_
config GoogleCloud Aiplatform V1Batch Prediction Job Output Config Args - The Configuration specifying where output predictions should be written. The schema of any single prediction may be specified as a concatenation of Model's PredictSchemata's instance_schema_uri and prediction_schema_uri.
- dedicated_
resources GoogleCloud Aiplatform V1Batch Dedicated Resources Args - The config of resources used by the Model during the batch prediction. If the Model supports DEDICATED_RESOURCES this config may be provided (and the job will use these resources), if the Model doesn't support AUTOMATIC_RESOURCES, this config must be provided.
- disable_
container_ boollogging - For custom-trained Models and AutoML Tabular Models, the container of the DeployedModel instances will send
stderr
andstdout
streams to Cloud Logging by default. Please note that the logs incur cost, which are subject to Cloud Logging pricing. User can disable container logging by setting this flag to true. - encryption_
spec GoogleCloud Aiplatform V1Encryption Spec Args - Customer-managed encryption key options for a BatchPredictionJob. If this is set, then all resources created by the BatchPredictionJob will be encrypted with the provided encryption key.
- explanation_
spec GoogleCloud Aiplatform V1Explanation Spec Args - Explanation configuration for this BatchPredictionJob. Can be specified only if generate_explanation is set to
true
. This value overrides the value of Model.explanation_spec. All fields of explanation_spec are optional in the request. If a field of the explanation_spec object is not populated, the corresponding field of the Model.explanation_spec object is inherited. - generate_
explanation bool - Generate explanation with the batch prediction results. When set to
true
, the batch prediction output changes based on thepredictions_format
field of the BatchPredictionJob.output_config object: *bigquery
: output includes a column namedexplanation
. The value is a struct that conforms to the Explanation object. *jsonl
: The JSON objects on each line include an additional entry keyedexplanation
. The value of the entry is a JSON object that conforms to the Explanation object. *csv
: Generating explanations for CSV format is not supported. If this field is set to true, either the Model.explanation_spec or explanation_spec must be populated. - instance_
config GoogleCloud Aiplatform V1Batch Prediction Job Instance Config Args - Configuration for how to convert batch prediction input instances to the prediction instances that are sent to the Model.
- labels Mapping[str, str]
- The labels with user-defined metadata to organize BatchPredictionJobs. 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.
- location str
- manual_
batch_ Googletuning_ parameters Cloud Aiplatform V1Manual Batch Tuning Parameters Args - Immutable. Parameters configuring the batch behavior. Currently only applicable when dedicated_resources are used (in other cases Vertex AI does the tuning itself).
- model str
- The name of the Model resource that produces the predictions via this job, must share the same ancestor Location. Starting this job has no impact on any existing deployments of the Model and their resources. Exactly one of model and unmanaged_container_model must be set. The model resource name may contain version id or version alias to specify the version. Example:
projects/{project}/locations/{location}/models/{model}@2
orprojects/{project}/locations/{location}/models/{model}@golden
if no version is specified, the default version will be deployed. The model resource could also be a publisher model. Example:publishers/{publisher}/models/{model}
orprojects/{project}/locations/{location}/publishers/{publisher}/models/{model}
- model_
parameters Any - The parameters that govern the predictions. The schema of the parameters may be specified via the Model's PredictSchemata's parameters_schema_uri.
- project str
- service_
account str - 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 Google Cloud resources. Users deploying the Model must have the
iam.serviceAccounts.actAs
permission on this service account. - unmanaged_
container_ Googlemodel Cloud Aiplatform V1Unmanaged Container Model Args - Contains model information necessary to perform batch prediction without requiring uploading to model registry. Exactly one of model and unmanaged_container_model must be set.
- display
Name String - The user-defined name of this BatchPredictionJob.
- input
Config Property Map - Input configuration of the instances on which predictions are performed. The schema of any single instance may be specified via the Model's PredictSchemata's instance_schema_uri.
- output
Config Property Map - The Configuration specifying where output predictions should be written. The schema of any single prediction may be specified as a concatenation of Model's PredictSchemata's instance_schema_uri and prediction_schema_uri.
- dedicated
Resources Property Map - The config of resources used by the Model during the batch prediction. If the Model supports DEDICATED_RESOURCES this config may be provided (and the job will use these resources), if the Model doesn't support AUTOMATIC_RESOURCES, this config must be provided.
- disable
Container BooleanLogging - For custom-trained Models and AutoML Tabular Models, the container of the DeployedModel instances will send
stderr
andstdout
streams to Cloud Logging by default. Please note that the logs incur cost, which are subject to Cloud Logging pricing. User can disable container logging by setting this flag to true. - encryption
Spec Property Map - Customer-managed encryption key options for a BatchPredictionJob. If this is set, then all resources created by the BatchPredictionJob will be encrypted with the provided encryption key.
- explanation
Spec Property Map - Explanation configuration for this BatchPredictionJob. Can be specified only if generate_explanation is set to
true
. This value overrides the value of Model.explanation_spec. All fields of explanation_spec are optional in the request. If a field of the explanation_spec object is not populated, the corresponding field of the Model.explanation_spec object is inherited. - generate
Explanation Boolean - Generate explanation with the batch prediction results. When set to
true
, the batch prediction output changes based on thepredictions_format
field of the BatchPredictionJob.output_config object: *bigquery
: output includes a column namedexplanation
. The value is a struct that conforms to the Explanation object. *jsonl
: The JSON objects on each line include an additional entry keyedexplanation
. The value of the entry is a JSON object that conforms to the Explanation object. *csv
: Generating explanations for CSV format is not supported. If this field is set to true, either the Model.explanation_spec or explanation_spec must be populated. - instance
Config Property Map - Configuration for how to convert batch prediction input instances to the prediction instances that are sent to the Model.
- labels Map<String>
- The labels with user-defined metadata to organize BatchPredictionJobs. 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.
- location String
- manual
Batch Property MapTuning Parameters - Immutable. Parameters configuring the batch behavior. Currently only applicable when dedicated_resources are used (in other cases Vertex AI does the tuning itself).
- model String
- The name of the Model resource that produces the predictions via this job, must share the same ancestor Location. Starting this job has no impact on any existing deployments of the Model and their resources. Exactly one of model and unmanaged_container_model must be set. The model resource name may contain version id or version alias to specify the version. Example:
projects/{project}/locations/{location}/models/{model}@2
orprojects/{project}/locations/{location}/models/{model}@golden
if no version is specified, the default version will be deployed. The model resource could also be a publisher model. Example:publishers/{publisher}/models/{model}
orprojects/{project}/locations/{location}/publishers/{publisher}/models/{model}
- model
Parameters Any - The parameters that govern the predictions. The schema of the parameters may be specified via the Model's PredictSchemata's parameters_schema_uri.
- project String
- service
Account String - 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 Google Cloud resources. Users deploying the Model must have the
iam.serviceAccounts.actAs
permission on this service account. - unmanaged
Container Property MapModel - Contains model information necessary to perform batch prediction without requiring uploading to model registry. Exactly one of model and unmanaged_container_model must be set.
Outputs
All input properties are implicitly available as output properties. Additionally, the BatchPredictionJob resource produces the following output properties:
- Completion
Stats Pulumi.Google Native. Aiplatform. V1. Outputs. Google Cloud Aiplatform V1Completion Stats Response - Statistics on completed and failed prediction instances.
- Create
Time string - Time when the BatchPredictionJob was created.
- End
Time string - Time when the BatchPredictionJob entered any of the following states:
JOB_STATE_SUCCEEDED
,JOB_STATE_FAILED
,JOB_STATE_CANCELLED
. - Error
Pulumi.
Google Native. Aiplatform. V1. Outputs. Google Rpc Status Response - Only populated when the job's state is JOB_STATE_FAILED or JOB_STATE_CANCELLED.
- Id string
- The provider-assigned unique ID for this managed resource.
- Model
Version stringId - The version ID of the Model that produces the predictions via this job.
- Name string
- Resource name of the BatchPredictionJob.
- Output
Info Pulumi.Google Native. Aiplatform. V1. Outputs. Google Cloud Aiplatform V1Batch Prediction Job Output Info Response - Information further describing the output of this job.
- Partial
Failures List<Pulumi.Google Native. Aiplatform. V1. Outputs. Google Rpc Status Response> - Partial failures encountered. For example, single files that can't be read. This field never exceeds 20 entries. Status details fields contain standard Google Cloud error details.
- Resources
Consumed Pulumi.Google Native. Aiplatform. V1. Outputs. Google Cloud Aiplatform V1Resources Consumed Response - Information about resources that had been consumed by this job. Provided in real time at best effort basis, as well as a final value once the job completes. Note: This field currently may be not populated for batch predictions that use AutoML Models.
- Start
Time string - Time when the BatchPredictionJob for the first time entered the
JOB_STATE_RUNNING
state. - State string
- The detailed state of the job.
- Update
Time string - Time when the BatchPredictionJob was most recently updated.
- Completion
Stats GoogleCloud Aiplatform V1Completion Stats Response - Statistics on completed and failed prediction instances.
- Create
Time string - Time when the BatchPredictionJob was created.
- End
Time string - Time when the BatchPredictionJob entered any of the following states:
JOB_STATE_SUCCEEDED
,JOB_STATE_FAILED
,JOB_STATE_CANCELLED
. - Error
Google
Rpc Status Response - Only populated when the job's state is JOB_STATE_FAILED or JOB_STATE_CANCELLED.
- Id string
- The provider-assigned unique ID for this managed resource.
- Model
Version stringId - The version ID of the Model that produces the predictions via this job.
- Name string
- Resource name of the BatchPredictionJob.
- Output
Info GoogleCloud Aiplatform V1Batch Prediction Job Output Info Response - Information further describing the output of this job.
- Partial
Failures []GoogleRpc Status Response - Partial failures encountered. For example, single files that can't be read. This field never exceeds 20 entries. Status details fields contain standard Google Cloud error details.
- Resources
Consumed GoogleCloud Aiplatform V1Resources Consumed Response - Information about resources that had been consumed by this job. Provided in real time at best effort basis, as well as a final value once the job completes. Note: This field currently may be not populated for batch predictions that use AutoML Models.
- Start
Time string - Time when the BatchPredictionJob for the first time entered the
JOB_STATE_RUNNING
state. - State string
- The detailed state of the job.
- Update
Time string - Time when the BatchPredictionJob was most recently updated.
- completion
Stats GoogleCloud Aiplatform V1Completion Stats Response - Statistics on completed and failed prediction instances.
- create
Time String - Time when the BatchPredictionJob was created.
- end
Time String - Time when the BatchPredictionJob entered any of the following states:
JOB_STATE_SUCCEEDED
,JOB_STATE_FAILED
,JOB_STATE_CANCELLED
. - error
Google
Rpc Status Response - Only populated when the job's state is JOB_STATE_FAILED or JOB_STATE_CANCELLED.
- id String
- The provider-assigned unique ID for this managed resource.
- model
Version StringId - The version ID of the Model that produces the predictions via this job.
- name String
- Resource name of the BatchPredictionJob.
- output
Info GoogleCloud Aiplatform V1Batch Prediction Job Output Info Response - Information further describing the output of this job.
- partial
Failures List<GoogleRpc Status Response> - Partial failures encountered. For example, single files that can't be read. This field never exceeds 20 entries. Status details fields contain standard Google Cloud error details.
- resources
Consumed GoogleCloud Aiplatform V1Resources Consumed Response - Information about resources that had been consumed by this job. Provided in real time at best effort basis, as well as a final value once the job completes. Note: This field currently may be not populated for batch predictions that use AutoML Models.
- start
Time String - Time when the BatchPredictionJob for the first time entered the
JOB_STATE_RUNNING
state. - state String
- The detailed state of the job.
- update
Time String - Time when the BatchPredictionJob was most recently updated.
- completion
Stats GoogleCloud Aiplatform V1Completion Stats Response - Statistics on completed and failed prediction instances.
- create
Time string - Time when the BatchPredictionJob was created.
- end
Time string - Time when the BatchPredictionJob entered any of the following states:
JOB_STATE_SUCCEEDED
,JOB_STATE_FAILED
,JOB_STATE_CANCELLED
. - error
Google
Rpc Status Response - Only populated when the job's state is JOB_STATE_FAILED or JOB_STATE_CANCELLED.
- id string
- The provider-assigned unique ID for this managed resource.
- model
Version stringId - The version ID of the Model that produces the predictions via this job.
- name string
- Resource name of the BatchPredictionJob.
- output
Info GoogleCloud Aiplatform V1Batch Prediction Job Output Info Response - Information further describing the output of this job.
- partial
Failures GoogleRpc Status Response[] - Partial failures encountered. For example, single files that can't be read. This field never exceeds 20 entries. Status details fields contain standard Google Cloud error details.
- resources
Consumed GoogleCloud Aiplatform V1Resources Consumed Response - Information about resources that had been consumed by this job. Provided in real time at best effort basis, as well as a final value once the job completes. Note: This field currently may be not populated for batch predictions that use AutoML Models.
- start
Time string - Time when the BatchPredictionJob for the first time entered the
JOB_STATE_RUNNING
state. - state string
- The detailed state of the job.
- update
Time string - Time when the BatchPredictionJob was most recently updated.
- completion_
stats GoogleCloud Aiplatform V1Completion Stats Response - Statistics on completed and failed prediction instances.
- create_
time str - Time when the BatchPredictionJob was created.
- end_
time str - Time when the BatchPredictionJob entered any of the following states:
JOB_STATE_SUCCEEDED
,JOB_STATE_FAILED
,JOB_STATE_CANCELLED
. - error
Google
Rpc Status Response - Only populated when the job's state is JOB_STATE_FAILED or JOB_STATE_CANCELLED.
- id str
- The provider-assigned unique ID for this managed resource.
- model_
version_ strid - The version ID of the Model that produces the predictions via this job.
- name str
- Resource name of the BatchPredictionJob.
- output_
info GoogleCloud Aiplatform V1Batch Prediction Job Output Info Response - Information further describing the output of this job.
- partial_
failures Sequence[GoogleRpc Status Response] - Partial failures encountered. For example, single files that can't be read. This field never exceeds 20 entries. Status details fields contain standard Google Cloud error details.
- resources_
consumed GoogleCloud Aiplatform V1Resources Consumed Response - Information about resources that had been consumed by this job. Provided in real time at best effort basis, as well as a final value once the job completes. Note: This field currently may be not populated for batch predictions that use AutoML Models.
- start_
time str - Time when the BatchPredictionJob for the first time entered the
JOB_STATE_RUNNING
state. - state str
- The detailed state of the job.
- update_
time str - Time when the BatchPredictionJob was most recently updated.
- completion
Stats Property Map - Statistics on completed and failed prediction instances.
- create
Time String - Time when the BatchPredictionJob was created.
- end
Time String - Time when the BatchPredictionJob entered any of the following states:
JOB_STATE_SUCCEEDED
,JOB_STATE_FAILED
,JOB_STATE_CANCELLED
. - error Property Map
- Only populated when the job's state is JOB_STATE_FAILED or JOB_STATE_CANCELLED.
- id String
- The provider-assigned unique ID for this managed resource.
- model
Version StringId - The version ID of the Model that produces the predictions via this job.
- name String
- Resource name of the BatchPredictionJob.
- output
Info Property Map - Information further describing the output of this job.
- partial
Failures List<Property Map> - Partial failures encountered. For example, single files that can't be read. This field never exceeds 20 entries. Status details fields contain standard Google Cloud error details.
- resources
Consumed Property Map - Information about resources that had been consumed by this job. Provided in real time at best effort basis, as well as a final value once the job completes. Note: This field currently may be not populated for batch predictions that use AutoML Models.
- start
Time String - Time when the BatchPredictionJob for the first time entered the
JOB_STATE_RUNNING
state. - state String
- The detailed state of the job.
- update
Time String - Time when the BatchPredictionJob was most recently updated.
Supporting Types
GoogleCloudAiplatformV1BatchDedicatedResources, GoogleCloudAiplatformV1BatchDedicatedResourcesArgs
- Machine
Spec Pulumi.Google Native. Aiplatform. V1. Inputs. Google Cloud Aiplatform V1Machine Spec - Immutable. The specification of a single machine.
- Max
Replica intCount - Immutable. The maximum number of machine replicas the batch operation may be scaled to. The default value is 10.
- Starting
Replica intCount - Immutable. The number of machine replicas used at the start of the batch operation. If not set, Vertex AI decides starting number, not greater than max_replica_count
- Machine
Spec GoogleCloud Aiplatform V1Machine Spec - Immutable. The specification of a single machine.
- Max
Replica intCount - Immutable. The maximum number of machine replicas the batch operation may be scaled to. The default value is 10.
- Starting
Replica intCount - Immutable. The number of machine replicas used at the start of the batch operation. If not set, Vertex AI decides starting number, not greater than max_replica_count
- machine
Spec GoogleCloud Aiplatform V1Machine Spec - Immutable. The specification of a single machine.
- max
Replica IntegerCount - Immutable. The maximum number of machine replicas the batch operation may be scaled to. The default value is 10.
- starting
Replica IntegerCount - Immutable. The number of machine replicas used at the start of the batch operation. If not set, Vertex AI decides starting number, not greater than max_replica_count
- machine
Spec GoogleCloud Aiplatform V1Machine Spec - Immutable. The specification of a single machine.
- max
Replica numberCount - Immutable. The maximum number of machine replicas the batch operation may be scaled to. The default value is 10.
- starting
Replica numberCount - Immutable. The number of machine replicas used at the start of the batch operation. If not set, Vertex AI decides starting number, not greater than max_replica_count
- machine_
spec GoogleCloud Aiplatform V1Machine Spec - Immutable. The specification of a single machine.
- max_
replica_ intcount - Immutable. The maximum number of machine replicas the batch operation may be scaled to. The default value is 10.
- starting_
replica_ intcount - Immutable. The number of machine replicas used at the start of the batch operation. If not set, Vertex AI decides starting number, not greater than max_replica_count
- machine
Spec Property Map - Immutable. The specification of a single machine.
- max
Replica NumberCount - Immutable. The maximum number of machine replicas the batch operation may be scaled to. The default value is 10.
- starting
Replica NumberCount - Immutable. The number of machine replicas used at the start of the batch operation. If not set, Vertex AI decides starting number, not greater than max_replica_count
GoogleCloudAiplatformV1BatchDedicatedResourcesResponse, GoogleCloudAiplatformV1BatchDedicatedResourcesResponseArgs
- Machine
Spec Pulumi.Google Native. Aiplatform. V1. Inputs. Google Cloud Aiplatform V1Machine Spec Response - Immutable. The specification of a single machine.
- Max
Replica intCount - Immutable. The maximum number of machine replicas the batch operation may be scaled to. The default value is 10.
- Starting
Replica intCount - Immutable. The number of machine replicas used at the start of the batch operation. If not set, Vertex AI decides starting number, not greater than max_replica_count
- Machine
Spec GoogleCloud Aiplatform V1Machine Spec Response - Immutable. The specification of a single machine.
- Max
Replica intCount - Immutable. The maximum number of machine replicas the batch operation may be scaled to. The default value is 10.
- Starting
Replica intCount - Immutable. The number of machine replicas used at the start of the batch operation. If not set, Vertex AI decides starting number, not greater than max_replica_count
- machine
Spec GoogleCloud Aiplatform V1Machine Spec Response - Immutable. The specification of a single machine.
- max
Replica IntegerCount - Immutable. The maximum number of machine replicas the batch operation may be scaled to. The default value is 10.
- starting
Replica IntegerCount - Immutable. The number of machine replicas used at the start of the batch operation. If not set, Vertex AI decides starting number, not greater than max_replica_count
- machine
Spec GoogleCloud Aiplatform V1Machine Spec Response - Immutable. The specification of a single machine.
- max
Replica numberCount - Immutable. The maximum number of machine replicas the batch operation may be scaled to. The default value is 10.
- starting
Replica numberCount - Immutable. The number of machine replicas used at the start of the batch operation. If not set, Vertex AI decides starting number, not greater than max_replica_count
- machine_
spec GoogleCloud Aiplatform V1Machine Spec Response - Immutable. The specification of a single machine.
- max_
replica_ intcount - Immutable. The maximum number of machine replicas the batch operation may be scaled to. The default value is 10.
- starting_
replica_ intcount - Immutable. The number of machine replicas used at the start of the batch operation. If not set, Vertex AI decides starting number, not greater than max_replica_count
- machine
Spec Property Map - Immutable. The specification of a single machine.
- max
Replica NumberCount - Immutable. The maximum number of machine replicas the batch operation may be scaled to. The default value is 10.
- starting
Replica NumberCount - Immutable. The number of machine replicas used at the start of the batch operation. If not set, Vertex AI decides starting number, not greater than max_replica_count
GoogleCloudAiplatformV1BatchPredictionJobInputConfig, GoogleCloudAiplatformV1BatchPredictionJobInputConfigArgs
- Instances
Format string - The format in which instances are given, must be one of the Model's supported_input_storage_formats.
- Bigquery
Source Pulumi.Google Native. Aiplatform. V1. Inputs. Google Cloud Aiplatform V1Big Query Source - The BigQuery location of the input table. The schema of the table should be in the format described by the given context OpenAPI Schema, if one is provided. The table may contain additional columns that are not described by the schema, and they will be ignored.
- Gcs
Source Pulumi.Google Native. Aiplatform. V1. Inputs. Google Cloud Aiplatform V1Gcs Source - The Cloud Storage location for the input instances.
- Instances
Format string - The format in which instances are given, must be one of the Model's supported_input_storage_formats.
- Bigquery
Source GoogleCloud Aiplatform V1Big Query Source - The BigQuery location of the input table. The schema of the table should be in the format described by the given context OpenAPI Schema, if one is provided. The table may contain additional columns that are not described by the schema, and they will be ignored.
- Gcs
Source GoogleCloud Aiplatform V1Gcs Source - The Cloud Storage location for the input instances.
- instances
Format String - The format in which instances are given, must be one of the Model's supported_input_storage_formats.
- bigquery
Source GoogleCloud Aiplatform V1Big Query Source - The BigQuery location of the input table. The schema of the table should be in the format described by the given context OpenAPI Schema, if one is provided. The table may contain additional columns that are not described by the schema, and they will be ignored.
- gcs
Source GoogleCloud Aiplatform V1Gcs Source - The Cloud Storage location for the input instances.
- instances
Format string - The format in which instances are given, must be one of the Model's supported_input_storage_formats.
- bigquery
Source GoogleCloud Aiplatform V1Big Query Source - The BigQuery location of the input table. The schema of the table should be in the format described by the given context OpenAPI Schema, if one is provided. The table may contain additional columns that are not described by the schema, and they will be ignored.
- gcs
Source GoogleCloud Aiplatform V1Gcs Source - The Cloud Storage location for the input instances.
- instances_
format str - The format in which instances are given, must be one of the Model's supported_input_storage_formats.
- bigquery_
source GoogleCloud Aiplatform V1Big Query Source - The BigQuery location of the input table. The schema of the table should be in the format described by the given context OpenAPI Schema, if one is provided. The table may contain additional columns that are not described by the schema, and they will be ignored.
- gcs_
source GoogleCloud Aiplatform V1Gcs Source - The Cloud Storage location for the input instances.
- instances
Format String - The format in which instances are given, must be one of the Model's supported_input_storage_formats.
- bigquery
Source Property Map - The BigQuery location of the input table. The schema of the table should be in the format described by the given context OpenAPI Schema, if one is provided. The table may contain additional columns that are not described by the schema, and they will be ignored.
- gcs
Source Property Map - The Cloud Storage location for the input instances.
GoogleCloudAiplatformV1BatchPredictionJobInputConfigResponse, GoogleCloudAiplatformV1BatchPredictionJobInputConfigResponseArgs
- Bigquery
Source Pulumi.Google Native. Aiplatform. V1. Inputs. Google Cloud Aiplatform V1Big Query Source Response - The BigQuery location of the input table. The schema of the table should be in the format described by the given context OpenAPI Schema, if one is provided. The table may contain additional columns that are not described by the schema, and they will be ignored.
- Gcs
Source Pulumi.Google Native. Aiplatform. V1. Inputs. Google Cloud Aiplatform V1Gcs Source Response - The Cloud Storage location for the input instances.
- Instances
Format string - The format in which instances are given, must be one of the Model's supported_input_storage_formats.
- Bigquery
Source GoogleCloud Aiplatform V1Big Query Source Response - The BigQuery location of the input table. The schema of the table should be in the format described by the given context OpenAPI Schema, if one is provided. The table may contain additional columns that are not described by the schema, and they will be ignored.
- Gcs
Source GoogleCloud Aiplatform V1Gcs Source Response - The Cloud Storage location for the input instances.
- Instances
Format string - The format in which instances are given, must be one of the Model's supported_input_storage_formats.
- bigquery
Source GoogleCloud Aiplatform V1Big Query Source Response - The BigQuery location of the input table. The schema of the table should be in the format described by the given context OpenAPI Schema, if one is provided. The table may contain additional columns that are not described by the schema, and they will be ignored.
- gcs
Source GoogleCloud Aiplatform V1Gcs Source Response - The Cloud Storage location for the input instances.
- instances
Format String - The format in which instances are given, must be one of the Model's supported_input_storage_formats.
- bigquery
Source GoogleCloud Aiplatform V1Big Query Source Response - The BigQuery location of the input table. The schema of the table should be in the format described by the given context OpenAPI Schema, if one is provided. The table may contain additional columns that are not described by the schema, and they will be ignored.
- gcs
Source GoogleCloud Aiplatform V1Gcs Source Response - The Cloud Storage location for the input instances.
- instances
Format string - The format in which instances are given, must be one of the Model's supported_input_storage_formats.
- bigquery_
source GoogleCloud Aiplatform V1Big Query Source Response - The BigQuery location of the input table. The schema of the table should be in the format described by the given context OpenAPI Schema, if one is provided. The table may contain additional columns that are not described by the schema, and they will be ignored.
- gcs_
source GoogleCloud Aiplatform V1Gcs Source Response - The Cloud Storage location for the input instances.
- instances_
format str - The format in which instances are given, must be one of the Model's supported_input_storage_formats.
- bigquery
Source Property Map - The BigQuery location of the input table. The schema of the table should be in the format described by the given context OpenAPI Schema, if one is provided. The table may contain additional columns that are not described by the schema, and they will be ignored.
- gcs
Source Property Map - The Cloud Storage location for the input instances.
- instances
Format String - The format in which instances are given, must be one of the Model's supported_input_storage_formats.
GoogleCloudAiplatformV1BatchPredictionJobInstanceConfig, GoogleCloudAiplatformV1BatchPredictionJobInstanceConfigArgs
- Excluded
Fields List<string> - Fields that will be excluded in the prediction instance that is sent to the Model. Excluded will be attached to the batch prediction output if key_field is not specified. When excluded_fields is populated, included_fields must be empty. The input must be JSONL with objects at each line, CSV, BigQuery or TfRecord.
- Included
Fields List<string> - Fields that will be included in the prediction instance that is sent to the Model. If instance_type is
array
, the order of field names in included_fields also determines the order of the values in the array. When included_fields is populated, excluded_fields must be empty. The input must be JSONL with objects at each line, CSV, BigQuery or TfRecord. - Instance
Type string - The format of the instance that the Model accepts. Vertex AI will convert compatible batch prediction input instance formats to the specified format. Supported values are: *
object
: Each input is converted to JSON object format. * Forbigquery
, each row is converted to an object. * Forjsonl
, each line of the JSONL input must be an object. * Does not apply tocsv
,file-list
,tf-record
, ortf-record-gzip
. *array
: Each input is converted to JSON array format. * Forbigquery
, each row is converted to an array. The order of columns is determined by the BigQuery column order, unless included_fields is populated. included_fields must be populated for specifying field orders. * Forjsonl
, if each line of the JSONL input is an object, included_fields must be populated for specifying field orders. * Does not apply tocsv
,file-list
,tf-record
, ortf-record-gzip
. If not specified, Vertex AI converts the batch prediction input as follows: * Forbigquery
andcsv
, the behavior is the same asarray
. The order of columns is the same as defined in the file or table, unless included_fields is populated. * Forjsonl
, the prediction instance format is determined by each line of the input. * Fortf-record
/tf-record-gzip
, each record will be converted to an object in the format of{"b64": }
, whereis the Base64-encoded string of the content of the record. * For `file-list`, each file in the list will be converted to an object in the format of `{"b64": }`, where
is the Base64-encoded string of the content of the file. - Key
Field string - The name of the field that is considered as a key. The values identified by the key field is not included in the transformed instances that is sent to the Model. This is similar to specifying this name of the field in excluded_fields. In addition, the batch prediction output will not include the instances. Instead the output will only include the value of the key field, in a field named
key
in the output: * Forjsonl
output format, the output will have akey
field instead of theinstance
field. * Forcsv
/bigquery
output format, the output will have have akey
column instead of the instance feature columns. The input must be JSONL with objects at each line, CSV, BigQuery or TfRecord.
- Excluded
Fields []string - Fields that will be excluded in the prediction instance that is sent to the Model. Excluded will be attached to the batch prediction output if key_field is not specified. When excluded_fields is populated, included_fields must be empty. The input must be JSONL with objects at each line, CSV, BigQuery or TfRecord.
- Included
Fields []string - Fields that will be included in the prediction instance that is sent to the Model. If instance_type is
array
, the order of field names in included_fields also determines the order of the values in the array. When included_fields is populated, excluded_fields must be empty. The input must be JSONL with objects at each line, CSV, BigQuery or TfRecord. - Instance
Type string - The format of the instance that the Model accepts. Vertex AI will convert compatible batch prediction input instance formats to the specified format. Supported values are: *
object
: Each input is converted to JSON object format. * Forbigquery
, each row is converted to an object. * Forjsonl
, each line of the JSONL input must be an object. * Does not apply tocsv
,file-list
,tf-record
, ortf-record-gzip
. *array
: Each input is converted to JSON array format. * Forbigquery
, each row is converted to an array. The order of columns is determined by the BigQuery column order, unless included_fields is populated. included_fields must be populated for specifying field orders. * Forjsonl
, if each line of the JSONL input is an object, included_fields must be populated for specifying field orders. * Does not apply tocsv
,file-list
,tf-record
, ortf-record-gzip
. If not specified, Vertex AI converts the batch prediction input as follows: * Forbigquery
andcsv
, the behavior is the same asarray
. The order of columns is the same as defined in the file or table, unless included_fields is populated. * Forjsonl
, the prediction instance format is determined by each line of the input. * Fortf-record
/tf-record-gzip
, each record will be converted to an object in the format of{"b64": }
, whereis the Base64-encoded string of the content of the record. * For `file-list`, each file in the list will be converted to an object in the format of `{"b64": }`, where
is the Base64-encoded string of the content of the file. - Key
Field string - The name of the field that is considered as a key. The values identified by the key field is not included in the transformed instances that is sent to the Model. This is similar to specifying this name of the field in excluded_fields. In addition, the batch prediction output will not include the instances. Instead the output will only include the value of the key field, in a field named
key
in the output: * Forjsonl
output format, the output will have akey
field instead of theinstance
field. * Forcsv
/bigquery
output format, the output will have have akey
column instead of the instance feature columns. The input must be JSONL with objects at each line, CSV, BigQuery or TfRecord.
- excluded
Fields List<String> - Fields that will be excluded in the prediction instance that is sent to the Model. Excluded will be attached to the batch prediction output if key_field is not specified. When excluded_fields is populated, included_fields must be empty. The input must be JSONL with objects at each line, CSV, BigQuery or TfRecord.
- included
Fields List<String> - Fields that will be included in the prediction instance that is sent to the Model. If instance_type is
array
, the order of field names in included_fields also determines the order of the values in the array. When included_fields is populated, excluded_fields must be empty. The input must be JSONL with objects at each line, CSV, BigQuery or TfRecord. - instance
Type String - The format of the instance that the Model accepts. Vertex AI will convert compatible batch prediction input instance formats to the specified format. Supported values are: *
object
: Each input is converted to JSON object format. * Forbigquery
, each row is converted to an object. * Forjsonl
, each line of the JSONL input must be an object. * Does not apply tocsv
,file-list
,tf-record
, ortf-record-gzip
. *array
: Each input is converted to JSON array format. * Forbigquery
, each row is converted to an array. The order of columns is determined by the BigQuery column order, unless included_fields is populated. included_fields must be populated for specifying field orders. * Forjsonl
, if each line of the JSONL input is an object, included_fields must be populated for specifying field orders. * Does not apply tocsv
,file-list
,tf-record
, ortf-record-gzip
. If not specified, Vertex AI converts the batch prediction input as follows: * Forbigquery
andcsv
, the behavior is the same asarray
. The order of columns is the same as defined in the file or table, unless included_fields is populated. * Forjsonl
, the prediction instance format is determined by each line of the input. * Fortf-record
/tf-record-gzip
, each record will be converted to an object in the format of{"b64": }
, whereis the Base64-encoded string of the content of the record. * For `file-list`, each file in the list will be converted to an object in the format of `{"b64": }`, where
is the Base64-encoded string of the content of the file. - key
Field String - The name of the field that is considered as a key. The values identified by the key field is not included in the transformed instances that is sent to the Model. This is similar to specifying this name of the field in excluded_fields. In addition, the batch prediction output will not include the instances. Instead the output will only include the value of the key field, in a field named
key
in the output: * Forjsonl
output format, the output will have akey
field instead of theinstance
field. * Forcsv
/bigquery
output format, the output will have have akey
column instead of the instance feature columns. The input must be JSONL with objects at each line, CSV, BigQuery or TfRecord.
- excluded
Fields string[] - Fields that will be excluded in the prediction instance that is sent to the Model. Excluded will be attached to the batch prediction output if key_field is not specified. When excluded_fields is populated, included_fields must be empty. The input must be JSONL with objects at each line, CSV, BigQuery or TfRecord.
- included
Fields string[] - Fields that will be included in the prediction instance that is sent to the Model. If instance_type is
array
, the order of field names in included_fields also determines the order of the values in the array. When included_fields is populated, excluded_fields must be empty. The input must be JSONL with objects at each line, CSV, BigQuery or TfRecord. - instance
Type string - The format of the instance that the Model accepts. Vertex AI will convert compatible batch prediction input instance formats to the specified format. Supported values are: *
object
: Each input is converted to JSON object format. * Forbigquery
, each row is converted to an object. * Forjsonl
, each line of the JSONL input must be an object. * Does not apply tocsv
,file-list
,tf-record
, ortf-record-gzip
. *array
: Each input is converted to JSON array format. * Forbigquery
, each row is converted to an array. The order of columns is determined by the BigQuery column order, unless included_fields is populated. included_fields must be populated for specifying field orders. * Forjsonl
, if each line of the JSONL input is an object, included_fields must be populated for specifying field orders. * Does not apply tocsv
,file-list
,tf-record
, ortf-record-gzip
. If not specified, Vertex AI converts the batch prediction input as follows: * Forbigquery
andcsv
, the behavior is the same asarray
. The order of columns is the same as defined in the file or table, unless included_fields is populated. * Forjsonl
, the prediction instance format is determined by each line of the input. * Fortf-record
/tf-record-gzip
, each record will be converted to an object in the format of{"b64": }
, whereis the Base64-encoded string of the content of the record. * For `file-list`, each file in the list will be converted to an object in the format of `{"b64": }`, where
is the Base64-encoded string of the content of the file. - key
Field string - The name of the field that is considered as a key. The values identified by the key field is not included in the transformed instances that is sent to the Model. This is similar to specifying this name of the field in excluded_fields. In addition, the batch prediction output will not include the instances. Instead the output will only include the value of the key field, in a field named
key
in the output: * Forjsonl
output format, the output will have akey
field instead of theinstance
field. * Forcsv
/bigquery
output format, the output will have have akey
column instead of the instance feature columns. The input must be JSONL with objects at each line, CSV, BigQuery or TfRecord.
- excluded_
fields Sequence[str] - Fields that will be excluded in the prediction instance that is sent to the Model. Excluded will be attached to the batch prediction output if key_field is not specified. When excluded_fields is populated, included_fields must be empty. The input must be JSONL with objects at each line, CSV, BigQuery or TfRecord.
- included_
fields Sequence[str] - Fields that will be included in the prediction instance that is sent to the Model. If instance_type is
array
, the order of field names in included_fields also determines the order of the values in the array. When included_fields is populated, excluded_fields must be empty. The input must be JSONL with objects at each line, CSV, BigQuery or TfRecord. - instance_
type str - The format of the instance that the Model accepts. Vertex AI will convert compatible batch prediction input instance formats to the specified format. Supported values are: *
object
: Each input is converted to JSON object format. * Forbigquery
, each row is converted to an object. * Forjsonl
, each line of the JSONL input must be an object. * Does not apply tocsv
,file-list
,tf-record
, ortf-record-gzip
. *array
: Each input is converted to JSON array format. * Forbigquery
, each row is converted to an array. The order of columns is determined by the BigQuery column order, unless included_fields is populated. included_fields must be populated for specifying field orders. * Forjsonl
, if each line of the JSONL input is an object, included_fields must be populated for specifying field orders. * Does not apply tocsv
,file-list
,tf-record
, ortf-record-gzip
. If not specified, Vertex AI converts the batch prediction input as follows: * Forbigquery
andcsv
, the behavior is the same asarray
. The order of columns is the same as defined in the file or table, unless included_fields is populated. * Forjsonl
, the prediction instance format is determined by each line of the input. * Fortf-record
/tf-record-gzip
, each record will be converted to an object in the format of{"b64": }
, whereis the Base64-encoded string of the content of the record. * For `file-list`, each file in the list will be converted to an object in the format of `{"b64": }`, where
is the Base64-encoded string of the content of the file. - key_
field str - The name of the field that is considered as a key. The values identified by the key field is not included in the transformed instances that is sent to the Model. This is similar to specifying this name of the field in excluded_fields. In addition, the batch prediction output will not include the instances. Instead the output will only include the value of the key field, in a field named
key
in the output: * Forjsonl
output format, the output will have akey
field instead of theinstance
field. * Forcsv
/bigquery
output format, the output will have have akey
column instead of the instance feature columns. The input must be JSONL with objects at each line, CSV, BigQuery or TfRecord.
- excluded
Fields List<String> - Fields that will be excluded in the prediction instance that is sent to the Model. Excluded will be attached to the batch prediction output if key_field is not specified. When excluded_fields is populated, included_fields must be empty. The input must be JSONL with objects at each line, CSV, BigQuery or TfRecord.
- included
Fields List<String> - Fields that will be included in the prediction instance that is sent to the Model. If instance_type is
array
, the order of field names in included_fields also determines the order of the values in the array. When included_fields is populated, excluded_fields must be empty. The input must be JSONL with objects at each line, CSV, BigQuery or TfRecord. - instance
Type String - The format of the instance that the Model accepts. Vertex AI will convert compatible batch prediction input instance formats to the specified format. Supported values are: *
object
: Each input is converted to JSON object format. * Forbigquery
, each row is converted to an object. * Forjsonl
, each line of the JSONL input must be an object. * Does not apply tocsv
,file-list
,tf-record
, ortf-record-gzip
. *array
: Each input is converted to JSON array format. * Forbigquery
, each row is converted to an array. The order of columns is determined by the BigQuery column order, unless included_fields is populated. included_fields must be populated for specifying field orders. * Forjsonl
, if each line of the JSONL input is an object, included_fields must be populated for specifying field orders. * Does not apply tocsv
,file-list
,tf-record
, ortf-record-gzip
. If not specified, Vertex AI converts the batch prediction input as follows: * Forbigquery
andcsv
, the behavior is the same asarray
. The order of columns is the same as defined in the file or table, unless included_fields is populated. * Forjsonl
, the prediction instance format is determined by each line of the input. * Fortf-record
/tf-record-gzip
, each record will be converted to an object in the format of{"b64": }
, whereis the Base64-encoded string of the content of the record. * For `file-list`, each file in the list will be converted to an object in the format of `{"b64": }`, where
is the Base64-encoded string of the content of the file. - key
Field String - The name of the field that is considered as a key. The values identified by the key field is not included in the transformed instances that is sent to the Model. This is similar to specifying this name of the field in excluded_fields. In addition, the batch prediction output will not include the instances. Instead the output will only include the value of the key field, in a field named
key
in the output: * Forjsonl
output format, the output will have akey
field instead of theinstance
field. * Forcsv
/bigquery
output format, the output will have have akey
column instead of the instance feature columns. The input must be JSONL with objects at each line, CSV, BigQuery or TfRecord.
GoogleCloudAiplatformV1BatchPredictionJobInstanceConfigResponse, GoogleCloudAiplatformV1BatchPredictionJobInstanceConfigResponseArgs
- Excluded
Fields List<string> - Fields that will be excluded in the prediction instance that is sent to the Model. Excluded will be attached to the batch prediction output if key_field is not specified. When excluded_fields is populated, included_fields must be empty. The input must be JSONL with objects at each line, CSV, BigQuery or TfRecord.
- Included
Fields List<string> - Fields that will be included in the prediction instance that is sent to the Model. If instance_type is
array
, the order of field names in included_fields also determines the order of the values in the array. When included_fields is populated, excluded_fields must be empty. The input must be JSONL with objects at each line, CSV, BigQuery or TfRecord. - Instance
Type string - The format of the instance that the Model accepts. Vertex AI will convert compatible batch prediction input instance formats to the specified format. Supported values are: *
object
: Each input is converted to JSON object format. * Forbigquery
, each row is converted to an object. * Forjsonl
, each line of the JSONL input must be an object. * Does not apply tocsv
,file-list
,tf-record
, ortf-record-gzip
. *array
: Each input is converted to JSON array format. * Forbigquery
, each row is converted to an array. The order of columns is determined by the BigQuery column order, unless included_fields is populated. included_fields must be populated for specifying field orders. * Forjsonl
, if each line of the JSONL input is an object, included_fields must be populated for specifying field orders. * Does not apply tocsv
,file-list
,tf-record
, ortf-record-gzip
. If not specified, Vertex AI converts the batch prediction input as follows: * Forbigquery
andcsv
, the behavior is the same asarray
. The order of columns is the same as defined in the file or table, unless included_fields is populated. * Forjsonl
, the prediction instance format is determined by each line of the input. * Fortf-record
/tf-record-gzip
, each record will be converted to an object in the format of{"b64": }
, whereis the Base64-encoded string of the content of the record. * For `file-list`, each file in the list will be converted to an object in the format of `{"b64": }`, where
is the Base64-encoded string of the content of the file. - Key
Field string - The name of the field that is considered as a key. The values identified by the key field is not included in the transformed instances that is sent to the Model. This is similar to specifying this name of the field in excluded_fields. In addition, the batch prediction output will not include the instances. Instead the output will only include the value of the key field, in a field named
key
in the output: * Forjsonl
output format, the output will have akey
field instead of theinstance
field. * Forcsv
/bigquery
output format, the output will have have akey
column instead of the instance feature columns. The input must be JSONL with objects at each line, CSV, BigQuery or TfRecord.
- Excluded
Fields []string - Fields that will be excluded in the prediction instance that is sent to the Model. Excluded will be attached to the batch prediction output if key_field is not specified. When excluded_fields is populated, included_fields must be empty. The input must be JSONL with objects at each line, CSV, BigQuery or TfRecord.
- Included
Fields []string - Fields that will be included in the prediction instance that is sent to the Model. If instance_type is
array
, the order of field names in included_fields also determines the order of the values in the array. When included_fields is populated, excluded_fields must be empty. The input must be JSONL with objects at each line, CSV, BigQuery or TfRecord. - Instance
Type string - The format of the instance that the Model accepts. Vertex AI will convert compatible batch prediction input instance formats to the specified format. Supported values are: *
object
: Each input is converted to JSON object format. * Forbigquery
, each row is converted to an object. * Forjsonl
, each line of the JSONL input must be an object. * Does not apply tocsv
,file-list
,tf-record
, ortf-record-gzip
. *array
: Each input is converted to JSON array format. * Forbigquery
, each row is converted to an array. The order of columns is determined by the BigQuery column order, unless included_fields is populated. included_fields must be populated for specifying field orders. * Forjsonl
, if each line of the JSONL input is an object, included_fields must be populated for specifying field orders. * Does not apply tocsv
,file-list
,tf-record
, ortf-record-gzip
. If not specified, Vertex AI converts the batch prediction input as follows: * Forbigquery
andcsv
, the behavior is the same asarray
. The order of columns is the same as defined in the file or table, unless included_fields is populated. * Forjsonl
, the prediction instance format is determined by each line of the input. * Fortf-record
/tf-record-gzip
, each record will be converted to an object in the format of{"b64": }
, whereis the Base64-encoded string of the content of the record. * For `file-list`, each file in the list will be converted to an object in the format of `{"b64": }`, where
is the Base64-encoded string of the content of the file. - Key
Field string - The name of the field that is considered as a key. The values identified by the key field is not included in the transformed instances that is sent to the Model. This is similar to specifying this name of the field in excluded_fields. In addition, the batch prediction output will not include the instances. Instead the output will only include the value of the key field, in a field named
key
in the output: * Forjsonl
output format, the output will have akey
field instead of theinstance
field. * Forcsv
/bigquery
output format, the output will have have akey
column instead of the instance feature columns. The input must be JSONL with objects at each line, CSV, BigQuery or TfRecord.
- excluded
Fields List<String> - Fields that will be excluded in the prediction instance that is sent to the Model. Excluded will be attached to the batch prediction output if key_field is not specified. When excluded_fields is populated, included_fields must be empty. The input must be JSONL with objects at each line, CSV, BigQuery or TfRecord.
- included
Fields List<String> - Fields that will be included in the prediction instance that is sent to the Model. If instance_type is
array
, the order of field names in included_fields also determines the order of the values in the array. When included_fields is populated, excluded_fields must be empty. The input must be JSONL with objects at each line, CSV, BigQuery or TfRecord. - instance
Type String - The format of the instance that the Model accepts. Vertex AI will convert compatible batch prediction input instance formats to the specified format. Supported values are: *
object
: Each input is converted to JSON object format. * Forbigquery
, each row is converted to an object. * Forjsonl
, each line of the JSONL input must be an object. * Does not apply tocsv
,file-list
,tf-record
, ortf-record-gzip
. *array
: Each input is converted to JSON array format. * Forbigquery
, each row is converted to an array. The order of columns is determined by the BigQuery column order, unless included_fields is populated. included_fields must be populated for specifying field orders. * Forjsonl
, if each line of the JSONL input is an object, included_fields must be populated for specifying field orders. * Does not apply tocsv
,file-list
,tf-record
, ortf-record-gzip
. If not specified, Vertex AI converts the batch prediction input as follows: * Forbigquery
andcsv
, the behavior is the same asarray
. The order of columns is the same as defined in the file or table, unless included_fields is populated. * Forjsonl
, the prediction instance format is determined by each line of the input. * Fortf-record
/tf-record-gzip
, each record will be converted to an object in the format of{"b64": }
, whereis the Base64-encoded string of the content of the record. * For `file-list`, each file in the list will be converted to an object in the format of `{"b64": }`, where
is the Base64-encoded string of the content of the file. - key
Field String - The name of the field that is considered as a key. The values identified by the key field is not included in the transformed instances that is sent to the Model. This is similar to specifying this name of the field in excluded_fields. In addition, the batch prediction output will not include the instances. Instead the output will only include the value of the key field, in a field named
key
in the output: * Forjsonl
output format, the output will have akey
field instead of theinstance
field. * Forcsv
/bigquery
output format, the output will have have akey
column instead of the instance feature columns. The input must be JSONL with objects at each line, CSV, BigQuery or TfRecord.
- excluded
Fields string[] - Fields that will be excluded in the prediction instance that is sent to the Model. Excluded will be attached to the batch prediction output if key_field is not specified. When excluded_fields is populated, included_fields must be empty. The input must be JSONL with objects at each line, CSV, BigQuery or TfRecord.
- included
Fields string[] - Fields that will be included in the prediction instance that is sent to the Model. If instance_type is
array
, the order of field names in included_fields also determines the order of the values in the array. When included_fields is populated, excluded_fields must be empty. The input must be JSONL with objects at each line, CSV, BigQuery or TfRecord. - instance
Type string - The format of the instance that the Model accepts. Vertex AI will convert compatible batch prediction input instance formats to the specified format. Supported values are: *
object
: Each input is converted to JSON object format. * Forbigquery
, each row is converted to an object. * Forjsonl
, each line of the JSONL input must be an object. * Does not apply tocsv
,file-list
,tf-record
, ortf-record-gzip
. *array
: Each input is converted to JSON array format. * Forbigquery
, each row is converted to an array. The order of columns is determined by the BigQuery column order, unless included_fields is populated. included_fields must be populated for specifying field orders. * Forjsonl
, if each line of the JSONL input is an object, included_fields must be populated for specifying field orders. * Does not apply tocsv
,file-list
,tf-record
, ortf-record-gzip
. If not specified, Vertex AI converts the batch prediction input as follows: * Forbigquery
andcsv
, the behavior is the same asarray
. The order of columns is the same as defined in the file or table, unless included_fields is populated. * Forjsonl
, the prediction instance format is determined by each line of the input. * Fortf-record
/tf-record-gzip
, each record will be converted to an object in the format of{"b64": }
, whereis the Base64-encoded string of the content of the record. * For `file-list`, each file in the list will be converted to an object in the format of `{"b64": }`, where
is the Base64-encoded string of the content of the file. - key
Field string - The name of the field that is considered as a key. The values identified by the key field is not included in the transformed instances that is sent to the Model. This is similar to specifying this name of the field in excluded_fields. In addition, the batch prediction output will not include the instances. Instead the output will only include the value of the key field, in a field named
key
in the output: * Forjsonl
output format, the output will have akey
field instead of theinstance
field. * Forcsv
/bigquery
output format, the output will have have akey
column instead of the instance feature columns. The input must be JSONL with objects at each line, CSV, BigQuery or TfRecord.
- excluded_
fields Sequence[str] - Fields that will be excluded in the prediction instance that is sent to the Model. Excluded will be attached to the batch prediction output if key_field is not specified. When excluded_fields is populated, included_fields must be empty. The input must be JSONL with objects at each line, CSV, BigQuery or TfRecord.
- included_
fields Sequence[str] - Fields that will be included in the prediction instance that is sent to the Model. If instance_type is
array
, the order of field names in included_fields also determines the order of the values in the array. When included_fields is populated, excluded_fields must be empty. The input must be JSONL with objects at each line, CSV, BigQuery or TfRecord. - instance_
type str - The format of the instance that the Model accepts. Vertex AI will convert compatible batch prediction input instance formats to the specified format. Supported values are: *
object
: Each input is converted to JSON object format. * Forbigquery
, each row is converted to an object. * Forjsonl
, each line of the JSONL input must be an object. * Does not apply tocsv
,file-list
,tf-record
, ortf-record-gzip
. *array
: Each input is converted to JSON array format. * Forbigquery
, each row is converted to an array. The order of columns is determined by the BigQuery column order, unless included_fields is populated. included_fields must be populated for specifying field orders. * Forjsonl
, if each line of the JSONL input is an object, included_fields must be populated for specifying field orders. * Does not apply tocsv
,file-list
,tf-record
, ortf-record-gzip
. If not specified, Vertex AI converts the batch prediction input as follows: * Forbigquery
andcsv
, the behavior is the same asarray
. The order of columns is the same as defined in the file or table, unless included_fields is populated. * Forjsonl
, the prediction instance format is determined by each line of the input. * Fortf-record
/tf-record-gzip
, each record will be converted to an object in the format of{"b64": }
, whereis the Base64-encoded string of the content of the record. * For `file-list`, each file in the list will be converted to an object in the format of `{"b64": }`, where
is the Base64-encoded string of the content of the file. - key_
field str - The name of the field that is considered as a key. The values identified by the key field is not included in the transformed instances that is sent to the Model. This is similar to specifying this name of the field in excluded_fields. In addition, the batch prediction output will not include the instances. Instead the output will only include the value of the key field, in a field named
key
in the output: * Forjsonl
output format, the output will have akey
field instead of theinstance
field. * Forcsv
/bigquery
output format, the output will have have akey
column instead of the instance feature columns. The input must be JSONL with objects at each line, CSV, BigQuery or TfRecord.
- excluded
Fields List<String> - Fields that will be excluded in the prediction instance that is sent to the Model. Excluded will be attached to the batch prediction output if key_field is not specified. When excluded_fields is populated, included_fields must be empty. The input must be JSONL with objects at each line, CSV, BigQuery or TfRecord.
- included
Fields List<String> - Fields that will be included in the prediction instance that is sent to the Model. If instance_type is
array
, the order of field names in included_fields also determines the order of the values in the array. When included_fields is populated, excluded_fields must be empty. The input must be JSONL with objects at each line, CSV, BigQuery or TfRecord. - instance
Type String - The format of the instance that the Model accepts. Vertex AI will convert compatible batch prediction input instance formats to the specified format. Supported values are: *
object
: Each input is converted to JSON object format. * Forbigquery
, each row is converted to an object. * Forjsonl
, each line of the JSONL input must be an object. * Does not apply tocsv
,file-list
,tf-record
, ortf-record-gzip
. *array
: Each input is converted to JSON array format. * Forbigquery
, each row is converted to an array. The order of columns is determined by the BigQuery column order, unless included_fields is populated. included_fields must be populated for specifying field orders. * Forjsonl
, if each line of the JSONL input is an object, included_fields must be populated for specifying field orders. * Does not apply tocsv
,file-list
,tf-record
, ortf-record-gzip
. If not specified, Vertex AI converts the batch prediction input as follows: * Forbigquery
andcsv
, the behavior is the same asarray
. The order of columns is the same as defined in the file or table, unless included_fields is populated. * Forjsonl
, the prediction instance format is determined by each line of the input. * Fortf-record
/tf-record-gzip
, each record will be converted to an object in the format of{"b64": }
, whereis the Base64-encoded string of the content of the record. * For `file-list`, each file in the list will be converted to an object in the format of `{"b64": }`, where
is the Base64-encoded string of the content of the file. - key
Field String - The name of the field that is considered as a key. The values identified by the key field is not included in the transformed instances that is sent to the Model. This is similar to specifying this name of the field in excluded_fields. In addition, the batch prediction output will not include the instances. Instead the output will only include the value of the key field, in a field named
key
in the output: * Forjsonl
output format, the output will have akey
field instead of theinstance
field. * Forcsv
/bigquery
output format, the output will have have akey
column instead of the instance feature columns. The input must be JSONL with objects at each line, CSV, BigQuery or TfRecord.
GoogleCloudAiplatformV1BatchPredictionJobOutputConfig, GoogleCloudAiplatformV1BatchPredictionJobOutputConfigArgs
- Predictions
Format string - The format in which Vertex AI gives the predictions, must be one of the Model's supported_output_storage_formats.
- Bigquery
Destination Pulumi.Google Native. Aiplatform. V1. Inputs. Google Cloud Aiplatform V1Big Query Destination - The BigQuery project or dataset location where the output is to be written to. If project is provided, a new dataset is created with name
prediction__
where is made BigQuery-dataset-name compatible (for example, most special characters become underscores), and timestamp is in YYYY_MM_DDThh_mm_ss_sssZ "based on ISO-8601" format. In the dataset two tables will be created,predictions
, anderrors
. If the Model has both instance and prediction schemata defined then the tables have columns as follows: Thepredictions
table contains instances for which the prediction succeeded, it has columns as per a concatenation of the Model's instance and prediction schemata. Theerrors
table contains rows for which the prediction has failed, it has instance columns, as per the instance schema, followed by a single "errors" column, which as values has google.rpc.Status represented as a STRUCT, and containing onlycode
andmessage
. - Gcs
Destination Pulumi.Google Native. Aiplatform. V1. Inputs. Google Cloud Aiplatform V1Gcs Destination - The Cloud Storage location of the directory where the output is to be written to. In the given directory a new directory is created. Its name is
prediction--
, where timestamp is in YYYY-MM-DDThh:mm:ss.sssZ ISO-8601 format. Inside of it filespredictions_0001.
,predictions_0002.
, ...,predictions_N.
are created where `` depends on chosen predictions_format, and N may equal 0001 and depends on the total number of successfully predicted instances. If the Model has both instance and prediction schemata defined then each such file contains predictions as per the predictions_format. If prediction for any instance failed (partially or completely), then an additionalerrors_0001.
,errors_0002.
,...,errors_N.
files are created (N depends on total number of failed predictions). These files contain the failed instances, as per their schema, followed by an additionalerror
field which as value has google.rpc.Status containing onlycode
andmessage
fields.
- Predictions
Format string - The format in which Vertex AI gives the predictions, must be one of the Model's supported_output_storage_formats.
- Bigquery
Destination GoogleCloud Aiplatform V1Big Query Destination - The BigQuery project or dataset location where the output is to be written to. If project is provided, a new dataset is created with name
prediction__
where is made BigQuery-dataset-name compatible (for example, most special characters become underscores), and timestamp is in YYYY_MM_DDThh_mm_ss_sssZ "based on ISO-8601" format. In the dataset two tables will be created,predictions
, anderrors
. If the Model has both instance and prediction schemata defined then the tables have columns as follows: Thepredictions
table contains instances for which the prediction succeeded, it has columns as per a concatenation of the Model's instance and prediction schemata. Theerrors
table contains rows for which the prediction has failed, it has instance columns, as per the instance schema, followed by a single "errors" column, which as values has google.rpc.Status represented as a STRUCT, and containing onlycode
andmessage
. - Gcs
Destination GoogleCloud Aiplatform V1Gcs Destination - The Cloud Storage location of the directory where the output is to be written to. In the given directory a new directory is created. Its name is
prediction--
, where timestamp is in YYYY-MM-DDThh:mm:ss.sssZ ISO-8601 format. Inside of it filespredictions_0001.
,predictions_0002.
, ...,predictions_N.
are created where `` depends on chosen predictions_format, and N may equal 0001 and depends on the total number of successfully predicted instances. If the Model has both instance and prediction schemata defined then each such file contains predictions as per the predictions_format. If prediction for any instance failed (partially or completely), then an additionalerrors_0001.
,errors_0002.
,...,errors_N.
files are created (N depends on total number of failed predictions). These files contain the failed instances, as per their schema, followed by an additionalerror
field which as value has google.rpc.Status containing onlycode
andmessage
fields.
- predictions
Format String - The format in which Vertex AI gives the predictions, must be one of the Model's supported_output_storage_formats.
- bigquery
Destination GoogleCloud Aiplatform V1Big Query Destination - The BigQuery project or dataset location where the output is to be written to. If project is provided, a new dataset is created with name
prediction__
where is made BigQuery-dataset-name compatible (for example, most special characters become underscores), and timestamp is in YYYY_MM_DDThh_mm_ss_sssZ "based on ISO-8601" format. In the dataset two tables will be created,predictions
, anderrors
. If the Model has both instance and prediction schemata defined then the tables have columns as follows: Thepredictions
table contains instances for which the prediction succeeded, it has columns as per a concatenation of the Model's instance and prediction schemata. Theerrors
table contains rows for which the prediction has failed, it has instance columns, as per the instance schema, followed by a single "errors" column, which as values has google.rpc.Status represented as a STRUCT, and containing onlycode
andmessage
. - gcs
Destination GoogleCloud Aiplatform V1Gcs Destination - The Cloud Storage location of the directory where the output is to be written to. In the given directory a new directory is created. Its name is
prediction--
, where timestamp is in YYYY-MM-DDThh:mm:ss.sssZ ISO-8601 format. Inside of it filespredictions_0001.
,predictions_0002.
, ...,predictions_N.
are created where `` depends on chosen predictions_format, and N may equal 0001 and depends on the total number of successfully predicted instances. If the Model has both instance and prediction schemata defined then each such file contains predictions as per the predictions_format. If prediction for any instance failed (partially or completely), then an additionalerrors_0001.
,errors_0002.
,...,errors_N.
files are created (N depends on total number of failed predictions). These files contain the failed instances, as per their schema, followed by an additionalerror
field which as value has google.rpc.Status containing onlycode
andmessage
fields.
- predictions
Format string - The format in which Vertex AI gives the predictions, must be one of the Model's supported_output_storage_formats.
- bigquery
Destination GoogleCloud Aiplatform V1Big Query Destination - The BigQuery project or dataset location where the output is to be written to. If project is provided, a new dataset is created with name
prediction__
where is made BigQuery-dataset-name compatible (for example, most special characters become underscores), and timestamp is in YYYY_MM_DDThh_mm_ss_sssZ "based on ISO-8601" format. In the dataset two tables will be created,predictions
, anderrors
. If the Model has both instance and prediction schemata defined then the tables have columns as follows: Thepredictions
table contains instances for which the prediction succeeded, it has columns as per a concatenation of the Model's instance and prediction schemata. Theerrors
table contains rows for which the prediction has failed, it has instance columns, as per the instance schema, followed by a single "errors" column, which as values has google.rpc.Status represented as a STRUCT, and containing onlycode
andmessage
. - gcs
Destination GoogleCloud Aiplatform V1Gcs Destination - The Cloud Storage location of the directory where the output is to be written to. In the given directory a new directory is created. Its name is
prediction--
, where timestamp is in YYYY-MM-DDThh:mm:ss.sssZ ISO-8601 format. Inside of it filespredictions_0001.
,predictions_0002.
, ...,predictions_N.
are created where `` depends on chosen predictions_format, and N may equal 0001 and depends on the total number of successfully predicted instances. If the Model has both instance and prediction schemata defined then each such file contains predictions as per the predictions_format. If prediction for any instance failed (partially or completely), then an additionalerrors_0001.
,errors_0002.
,...,errors_N.
files are created (N depends on total number of failed predictions). These files contain the failed instances, as per their schema, followed by an additionalerror
field which as value has google.rpc.Status containing onlycode
andmessage
fields.
- predictions_
format str - The format in which Vertex AI gives the predictions, must be one of the Model's supported_output_storage_formats.
- bigquery_
destination GoogleCloud Aiplatform V1Big Query Destination - The BigQuery project or dataset location where the output is to be written to. If project is provided, a new dataset is created with name
prediction__
where is made BigQuery-dataset-name compatible (for example, most special characters become underscores), and timestamp is in YYYY_MM_DDThh_mm_ss_sssZ "based on ISO-8601" format. In the dataset two tables will be created,predictions
, anderrors
. If the Model has both instance and prediction schemata defined then the tables have columns as follows: Thepredictions
table contains instances for which the prediction succeeded, it has columns as per a concatenation of the Model's instance and prediction schemata. Theerrors
table contains rows for which the prediction has failed, it has instance columns, as per the instance schema, followed by a single "errors" column, which as values has google.rpc.Status represented as a STRUCT, and containing onlycode
andmessage
. - gcs_
destination GoogleCloud Aiplatform V1Gcs Destination - The Cloud Storage location of the directory where the output is to be written to. In the given directory a new directory is created. Its name is
prediction--
, where timestamp is in YYYY-MM-DDThh:mm:ss.sssZ ISO-8601 format. Inside of it filespredictions_0001.
,predictions_0002.
, ...,predictions_N.
are created where `` depends on chosen predictions_format, and N may equal 0001 and depends on the total number of successfully predicted instances. If the Model has both instance and prediction schemata defined then each such file contains predictions as per the predictions_format. If prediction for any instance failed (partially or completely), then an additionalerrors_0001.
,errors_0002.
,...,errors_N.
files are created (N depends on total number of failed predictions). These files contain the failed instances, as per their schema, followed by an additionalerror
field which as value has google.rpc.Status containing onlycode
andmessage
fields.
- predictions
Format String - The format in which Vertex AI gives the predictions, must be one of the Model's supported_output_storage_formats.
- bigquery
Destination Property Map - The BigQuery project or dataset location where the output is to be written to. If project is provided, a new dataset is created with name
prediction__
where is made BigQuery-dataset-name compatible (for example, most special characters become underscores), and timestamp is in YYYY_MM_DDThh_mm_ss_sssZ "based on ISO-8601" format. In the dataset two tables will be created,predictions
, anderrors
. If the Model has both instance and prediction schemata defined then the tables have columns as follows: Thepredictions
table contains instances for which the prediction succeeded, it has columns as per a concatenation of the Model's instance and prediction schemata. Theerrors
table contains rows for which the prediction has failed, it has instance columns, as per the instance schema, followed by a single "errors" column, which as values has google.rpc.Status represented as a STRUCT, and containing onlycode
andmessage
. - gcs
Destination Property Map - The Cloud Storage location of the directory where the output is to be written to. In the given directory a new directory is created. Its name is
prediction--
, where timestamp is in YYYY-MM-DDThh:mm:ss.sssZ ISO-8601 format. Inside of it filespredictions_0001.
,predictions_0002.
, ...,predictions_N.
are created where `` depends on chosen predictions_format, and N may equal 0001 and depends on the total number of successfully predicted instances. If the Model has both instance and prediction schemata defined then each such file contains predictions as per the predictions_format. If prediction for any instance failed (partially or completely), then an additionalerrors_0001.
,errors_0002.
,...,errors_N.
files are created (N depends on total number of failed predictions). These files contain the failed instances, as per their schema, followed by an additionalerror
field which as value has google.rpc.Status containing onlycode
andmessage
fields.
GoogleCloudAiplatformV1BatchPredictionJobOutputConfigResponse, GoogleCloudAiplatformV1BatchPredictionJobOutputConfigResponseArgs
- Bigquery
Destination Pulumi.Google Native. Aiplatform. V1. Inputs. Google Cloud Aiplatform V1Big Query Destination Response - The BigQuery project or dataset location where the output is to be written to. If project is provided, a new dataset is created with name
prediction__
where is made BigQuery-dataset-name compatible (for example, most special characters become underscores), and timestamp is in YYYY_MM_DDThh_mm_ss_sssZ "based on ISO-8601" format. In the dataset two tables will be created,predictions
, anderrors
. If the Model has both instance and prediction schemata defined then the tables have columns as follows: Thepredictions
table contains instances for which the prediction succeeded, it has columns as per a concatenation of the Model's instance and prediction schemata. Theerrors
table contains rows for which the prediction has failed, it has instance columns, as per the instance schema, followed by a single "errors" column, which as values has google.rpc.Status represented as a STRUCT, and containing onlycode
andmessage
. - Gcs
Destination Pulumi.Google Native. Aiplatform. V1. Inputs. Google Cloud Aiplatform V1Gcs Destination Response - The Cloud Storage location of the directory where the output is to be written to. In the given directory a new directory is created. Its name is
prediction--
, where timestamp is in YYYY-MM-DDThh:mm:ss.sssZ ISO-8601 format. Inside of it filespredictions_0001.
,predictions_0002.
, ...,predictions_N.
are created where `` depends on chosen predictions_format, and N may equal 0001 and depends on the total number of successfully predicted instances. If the Model has both instance and prediction schemata defined then each such file contains predictions as per the predictions_format. If prediction for any instance failed (partially or completely), then an additionalerrors_0001.
,errors_0002.
,...,errors_N.
files are created (N depends on total number of failed predictions). These files contain the failed instances, as per their schema, followed by an additionalerror
field which as value has google.rpc.Status containing onlycode
andmessage
fields. - Predictions
Format string - The format in which Vertex AI gives the predictions, must be one of the Model's supported_output_storage_formats.
- Bigquery
Destination GoogleCloud Aiplatform V1Big Query Destination Response - The BigQuery project or dataset location where the output is to be written to. If project is provided, a new dataset is created with name
prediction__
where is made BigQuery-dataset-name compatible (for example, most special characters become underscores), and timestamp is in YYYY_MM_DDThh_mm_ss_sssZ "based on ISO-8601" format. In the dataset two tables will be created,predictions
, anderrors
. If the Model has both instance and prediction schemata defined then the tables have columns as follows: Thepredictions
table contains instances for which the prediction succeeded, it has columns as per a concatenation of the Model's instance and prediction schemata. Theerrors
table contains rows for which the prediction has failed, it has instance columns, as per the instance schema, followed by a single "errors" column, which as values has google.rpc.Status represented as a STRUCT, and containing onlycode
andmessage
. - Gcs
Destination GoogleCloud Aiplatform V1Gcs Destination Response - The Cloud Storage location of the directory where the output is to be written to. In the given directory a new directory is created. Its name is
prediction--
, where timestamp is in YYYY-MM-DDThh:mm:ss.sssZ ISO-8601 format. Inside of it filespredictions_0001.
,predictions_0002.
, ...,predictions_N.
are created where `` depends on chosen predictions_format, and N may equal 0001 and depends on the total number of successfully predicted instances. If the Model has both instance and prediction schemata defined then each such file contains predictions as per the predictions_format. If prediction for any instance failed (partially or completely), then an additionalerrors_0001.
,errors_0002.
,...,errors_N.
files are created (N depends on total number of failed predictions). These files contain the failed instances, as per their schema, followed by an additionalerror
field which as value has google.rpc.Status containing onlycode
andmessage
fields. - Predictions
Format string - The format in which Vertex AI gives the predictions, must be one of the Model's supported_output_storage_formats.
- bigquery
Destination GoogleCloud Aiplatform V1Big Query Destination Response - The BigQuery project or dataset location where the output is to be written to. If project is provided, a new dataset is created with name
prediction__
where is made BigQuery-dataset-name compatible (for example, most special characters become underscores), and timestamp is in YYYY_MM_DDThh_mm_ss_sssZ "based on ISO-8601" format. In the dataset two tables will be created,predictions
, anderrors
. If the Model has both instance and prediction schemata defined then the tables have columns as follows: Thepredictions
table contains instances for which the prediction succeeded, it has columns as per a concatenation of the Model's instance and prediction schemata. Theerrors
table contains rows for which the prediction has failed, it has instance columns, as per the instance schema, followed by a single "errors" column, which as values has google.rpc.Status represented as a STRUCT, and containing onlycode
andmessage
. - gcs
Destination GoogleCloud Aiplatform V1Gcs Destination Response - The Cloud Storage location of the directory where the output is to be written to. In the given directory a new directory is created. Its name is
prediction--
, where timestamp is in YYYY-MM-DDThh:mm:ss.sssZ ISO-8601 format. Inside of it filespredictions_0001.
,predictions_0002.
, ...,predictions_N.
are created where `` depends on chosen predictions_format, and N may equal 0001 and depends on the total number of successfully predicted instances. If the Model has both instance and prediction schemata defined then each such file contains predictions as per the predictions_format. If prediction for any instance failed (partially or completely), then an additionalerrors_0001.
,errors_0002.
,...,errors_N.
files are created (N depends on total number of failed predictions). These files contain the failed instances, as per their schema, followed by an additionalerror
field which as value has google.rpc.Status containing onlycode
andmessage
fields. - predictions
Format String - The format in which Vertex AI gives the predictions, must be one of the Model's supported_output_storage_formats.
- bigquery
Destination GoogleCloud Aiplatform V1Big Query Destination Response - The BigQuery project or dataset location where the output is to be written to. If project is provided, a new dataset is created with name
prediction__
where is made BigQuery-dataset-name compatible (for example, most special characters become underscores), and timestamp is in YYYY_MM_DDThh_mm_ss_sssZ "based on ISO-8601" format. In the dataset two tables will be created,predictions
, anderrors
. If the Model has both instance and prediction schemata defined then the tables have columns as follows: Thepredictions
table contains instances for which the prediction succeeded, it has columns as per a concatenation of the Model's instance and prediction schemata. Theerrors
table contains rows for which the prediction has failed, it has instance columns, as per the instance schema, followed by a single "errors" column, which as values has google.rpc.Status represented as a STRUCT, and containing onlycode
andmessage
. - gcs
Destination GoogleCloud Aiplatform V1Gcs Destination Response - The Cloud Storage location of the directory where the output is to be written to. In the given directory a new directory is created. Its name is
prediction--
, where timestamp is in YYYY-MM-DDThh:mm:ss.sssZ ISO-8601 format. Inside of it filespredictions_0001.
,predictions_0002.
, ...,predictions_N.
are created where `` depends on chosen predictions_format, and N may equal 0001 and depends on the total number of successfully predicted instances. If the Model has both instance and prediction schemata defined then each such file contains predictions as per the predictions_format. If prediction for any instance failed (partially or completely), then an additionalerrors_0001.
,errors_0002.
,...,errors_N.
files are created (N depends on total number of failed predictions). These files contain the failed instances, as per their schema, followed by an additionalerror
field which as value has google.rpc.Status containing onlycode
andmessage
fields. - predictions
Format string - The format in which Vertex AI gives the predictions, must be one of the Model's supported_output_storage_formats.
- bigquery_
destination GoogleCloud Aiplatform V1Big Query Destination Response - The BigQuery project or dataset location where the output is to be written to. If project is provided, a new dataset is created with name
prediction__
where is made BigQuery-dataset-name compatible (for example, most special characters become underscores), and timestamp is in YYYY_MM_DDThh_mm_ss_sssZ "based on ISO-8601" format. In the dataset two tables will be created,predictions
, anderrors
. If the Model has both instance and prediction schemata defined then the tables have columns as follows: Thepredictions
table contains instances for which the prediction succeeded, it has columns as per a concatenation of the Model's instance and prediction schemata. Theerrors
table contains rows for which the prediction has failed, it has instance columns, as per the instance schema, followed by a single "errors" column, which as values has google.rpc.Status represented as a STRUCT, and containing onlycode
andmessage
. - gcs_
destination GoogleCloud Aiplatform V1Gcs Destination Response - The Cloud Storage location of the directory where the output is to be written to. In the given directory a new directory is created. Its name is
prediction--
, where timestamp is in YYYY-MM-DDThh:mm:ss.sssZ ISO-8601 format. Inside of it filespredictions_0001.
,predictions_0002.
, ...,predictions_N.
are created where `` depends on chosen predictions_format, and N may equal 0001 and depends on the total number of successfully predicted instances. If the Model has both instance and prediction schemata defined then each such file contains predictions as per the predictions_format. If prediction for any instance failed (partially or completely), then an additionalerrors_0001.
,errors_0002.
,...,errors_N.
files are created (N depends on total number of failed predictions). These files contain the failed instances, as per their schema, followed by an additionalerror
field which as value has google.rpc.Status containing onlycode
andmessage
fields. - predictions_
format str - The format in which Vertex AI gives the predictions, must be one of the Model's supported_output_storage_formats.
- bigquery
Destination Property Map - The BigQuery project or dataset location where the output is to be written to. If project is provided, a new dataset is created with name
prediction__
where is made BigQuery-dataset-name compatible (for example, most special characters become underscores), and timestamp is in YYYY_MM_DDThh_mm_ss_sssZ "based on ISO-8601" format. In the dataset two tables will be created,predictions
, anderrors
. If the Model has both instance and prediction schemata defined then the tables have columns as follows: Thepredictions
table contains instances for which the prediction succeeded, it has columns as per a concatenation of the Model's instance and prediction schemata. Theerrors
table contains rows for which the prediction has failed, it has instance columns, as per the instance schema, followed by a single "errors" column, which as values has google.rpc.Status represented as a STRUCT, and containing onlycode
andmessage
. - gcs
Destination Property Map - The Cloud Storage location of the directory where the output is to be written to. In the given directory a new directory is created. Its name is
prediction--
, where timestamp is in YYYY-MM-DDThh:mm:ss.sssZ ISO-8601 format. Inside of it filespredictions_0001.
,predictions_0002.
, ...,predictions_N.
are created where `` depends on chosen predictions_format, and N may equal 0001 and depends on the total number of successfully predicted instances. If the Model has both instance and prediction schemata defined then each such file contains predictions as per the predictions_format. If prediction for any instance failed (partially or completely), then an additionalerrors_0001.
,errors_0002.
,...,errors_N.
files are created (N depends on total number of failed predictions). These files contain the failed instances, as per their schema, followed by an additionalerror
field which as value has google.rpc.Status containing onlycode
andmessage
fields. - predictions
Format String - The format in which Vertex AI gives the predictions, must be one of the Model's supported_output_storage_formats.
GoogleCloudAiplatformV1BatchPredictionJobOutputInfoResponse, GoogleCloudAiplatformV1BatchPredictionJobOutputInfoResponseArgs
- Bigquery
Output stringDataset - The path of the BigQuery dataset created, in
bq://projectId.bqDatasetId
format, into which the prediction output is written. - Bigquery
Output stringTable - The name of the BigQuery table created, in
predictions_
format, into which the prediction output is written. Can be used by UI to generate the BigQuery output path, for example. - Gcs
Output stringDirectory - The full path of the Cloud Storage directory created, into which the prediction output is written.
- Bigquery
Output stringDataset - The path of the BigQuery dataset created, in
bq://projectId.bqDatasetId
format, into which the prediction output is written. - Bigquery
Output stringTable - The name of the BigQuery table created, in
predictions_
format, into which the prediction output is written. Can be used by UI to generate the BigQuery output path, for example. - Gcs
Output stringDirectory - The full path of the Cloud Storage directory created, into which the prediction output is written.
- bigquery
Output StringDataset - The path of the BigQuery dataset created, in
bq://projectId.bqDatasetId
format, into which the prediction output is written. - bigquery
Output StringTable - The name of the BigQuery table created, in
predictions_
format, into which the prediction output is written. Can be used by UI to generate the BigQuery output path, for example. - gcs
Output StringDirectory - The full path of the Cloud Storage directory created, into which the prediction output is written.
- bigquery
Output stringDataset - The path of the BigQuery dataset created, in
bq://projectId.bqDatasetId
format, into which the prediction output is written. - bigquery
Output stringTable - The name of the BigQuery table created, in
predictions_
format, into which the prediction output is written. Can be used by UI to generate the BigQuery output path, for example. - gcs
Output stringDirectory - The full path of the Cloud Storage directory created, into which the prediction output is written.
- bigquery_
output_ strdataset - The path of the BigQuery dataset created, in
bq://projectId.bqDatasetId
format, into which the prediction output is written. - bigquery_
output_ strtable - The name of the BigQuery table created, in
predictions_
format, into which the prediction output is written. Can be used by UI to generate the BigQuery output path, for example. - gcs_
output_ strdirectory - The full path of the Cloud Storage directory created, into which the prediction output is written.
- bigquery
Output StringDataset - The path of the BigQuery dataset created, in
bq://projectId.bqDatasetId
format, into which the prediction output is written. - bigquery
Output StringTable - The name of the BigQuery table created, in
predictions_
format, into which the prediction output is written. Can be used by UI to generate the BigQuery output path, for example. - gcs
Output StringDirectory - The full path of the Cloud Storage directory created, into which the prediction output is written.
GoogleCloudAiplatformV1BigQueryDestination, GoogleCloudAiplatformV1BigQueryDestinationArgs
- Output
Uri string - BigQuery URI to a project or table, up to 2000 characters long. When only the project is specified, the Dataset and Table is created. When the full table reference is specified, the Dataset must exist and table must not exist. Accepted forms: * BigQuery path. For example:
bq://projectId
orbq://projectId.bqDatasetId
orbq://projectId.bqDatasetId.bqTableId
.
- Output
Uri string - BigQuery URI to a project or table, up to 2000 characters long. When only the project is specified, the Dataset and Table is created. When the full table reference is specified, the Dataset must exist and table must not exist. Accepted forms: * BigQuery path. For example:
bq://projectId
orbq://projectId.bqDatasetId
orbq://projectId.bqDatasetId.bqTableId
.
- output
Uri String - BigQuery URI to a project or table, up to 2000 characters long. When only the project is specified, the Dataset and Table is created. When the full table reference is specified, the Dataset must exist and table must not exist. Accepted forms: * BigQuery path. For example:
bq://projectId
orbq://projectId.bqDatasetId
orbq://projectId.bqDatasetId.bqTableId
.
- output
Uri string - BigQuery URI to a project or table, up to 2000 characters long. When only the project is specified, the Dataset and Table is created. When the full table reference is specified, the Dataset must exist and table must not exist. Accepted forms: * BigQuery path. For example:
bq://projectId
orbq://projectId.bqDatasetId
orbq://projectId.bqDatasetId.bqTableId
.
- output_
uri str - BigQuery URI to a project or table, up to 2000 characters long. When only the project is specified, the Dataset and Table is created. When the full table reference is specified, the Dataset must exist and table must not exist. Accepted forms: * BigQuery path. For example:
bq://projectId
orbq://projectId.bqDatasetId
orbq://projectId.bqDatasetId.bqTableId
.
- output
Uri String - BigQuery URI to a project or table, up to 2000 characters long. When only the project is specified, the Dataset and Table is created. When the full table reference is specified, the Dataset must exist and table must not exist. Accepted forms: * BigQuery path. For example:
bq://projectId
orbq://projectId.bqDatasetId
orbq://projectId.bqDatasetId.bqTableId
.
GoogleCloudAiplatformV1BigQueryDestinationResponse, GoogleCloudAiplatformV1BigQueryDestinationResponseArgs
- Output
Uri string - BigQuery URI to a project or table, up to 2000 characters long. When only the project is specified, the Dataset and Table is created. When the full table reference is specified, the Dataset must exist and table must not exist. Accepted forms: * BigQuery path. For example:
bq://projectId
orbq://projectId.bqDatasetId
orbq://projectId.bqDatasetId.bqTableId
.
- Output
Uri string - BigQuery URI to a project or table, up to 2000 characters long. When only the project is specified, the Dataset and Table is created. When the full table reference is specified, the Dataset must exist and table must not exist. Accepted forms: * BigQuery path. For example:
bq://projectId
orbq://projectId.bqDatasetId
orbq://projectId.bqDatasetId.bqTableId
.
- output
Uri String - BigQuery URI to a project or table, up to 2000 characters long. When only the project is specified, the Dataset and Table is created. When the full table reference is specified, the Dataset must exist and table must not exist. Accepted forms: * BigQuery path. For example:
bq://projectId
orbq://projectId.bqDatasetId
orbq://projectId.bqDatasetId.bqTableId
.
- output
Uri string - BigQuery URI to a project or table, up to 2000 characters long. When only the project is specified, the Dataset and Table is created. When the full table reference is specified, the Dataset must exist and table must not exist. Accepted forms: * BigQuery path. For example:
bq://projectId
orbq://projectId.bqDatasetId
orbq://projectId.bqDatasetId.bqTableId
.
- output_
uri str - BigQuery URI to a project or table, up to 2000 characters long. When only the project is specified, the Dataset and Table is created. When the full table reference is specified, the Dataset must exist and table must not exist. Accepted forms: * BigQuery path. For example:
bq://projectId
orbq://projectId.bqDatasetId
orbq://projectId.bqDatasetId.bqTableId
.
- output
Uri String - BigQuery URI to a project or table, up to 2000 characters long. When only the project is specified, the Dataset and Table is created. When the full table reference is specified, the Dataset must exist and table must not exist. Accepted forms: * BigQuery path. For example:
bq://projectId
orbq://projectId.bqDatasetId
orbq://projectId.bqDatasetId.bqTableId
.
GoogleCloudAiplatformV1BigQuerySource, GoogleCloudAiplatformV1BigQuerySourceArgs
- Input
Uri string - BigQuery URI to a table, up to 2000 characters long. Accepted forms: * BigQuery path. For example:
bq://projectId.bqDatasetId.bqTableId
.
- Input
Uri string - BigQuery URI to a table, up to 2000 characters long. Accepted forms: * BigQuery path. For example:
bq://projectId.bqDatasetId.bqTableId
.
- input
Uri String - BigQuery URI to a table, up to 2000 characters long. Accepted forms: * BigQuery path. For example:
bq://projectId.bqDatasetId.bqTableId
.
- input
Uri string - BigQuery URI to a table, up to 2000 characters long. Accepted forms: * BigQuery path. For example:
bq://projectId.bqDatasetId.bqTableId
.
- input_
uri str - BigQuery URI to a table, up to 2000 characters long. Accepted forms: * BigQuery path. For example:
bq://projectId.bqDatasetId.bqTableId
.
- input
Uri String - BigQuery URI to a table, up to 2000 characters long. Accepted forms: * BigQuery path. For example:
bq://projectId.bqDatasetId.bqTableId
.
GoogleCloudAiplatformV1BigQuerySourceResponse, GoogleCloudAiplatformV1BigQuerySourceResponseArgs
- Input
Uri string - BigQuery URI to a table, up to 2000 characters long. Accepted forms: * BigQuery path. For example:
bq://projectId.bqDatasetId.bqTableId
.
- Input
Uri string - BigQuery URI to a table, up to 2000 characters long. Accepted forms: * BigQuery path. For example:
bq://projectId.bqDatasetId.bqTableId
.
- input
Uri String - BigQuery URI to a table, up to 2000 characters long. Accepted forms: * BigQuery path. For example:
bq://projectId.bqDatasetId.bqTableId
.
- input
Uri string - BigQuery URI to a table, up to 2000 characters long. Accepted forms: * BigQuery path. For example:
bq://projectId.bqDatasetId.bqTableId
.
- input_
uri str - BigQuery URI to a table, up to 2000 characters long. Accepted forms: * BigQuery path. For example:
bq://projectId.bqDatasetId.bqTableId
.
- input
Uri String - BigQuery URI to a table, up to 2000 characters long. Accepted forms: * BigQuery path. For example:
bq://projectId.bqDatasetId.bqTableId
.
GoogleCloudAiplatformV1BlurBaselineConfig, GoogleCloudAiplatformV1BlurBaselineConfigArgs
- Max
Blur doubleSigma - The standard deviation of the blur kernel for the blurred baseline. The same blurring parameter is used for both the height and the width dimension. If not set, the method defaults to the zero (i.e. black for images) baseline.
- Max
Blur float64Sigma - The standard deviation of the blur kernel for the blurred baseline. The same blurring parameter is used for both the height and the width dimension. If not set, the method defaults to the zero (i.e. black for images) baseline.
- max
Blur DoubleSigma - The standard deviation of the blur kernel for the blurred baseline. The same blurring parameter is used for both the height and the width dimension. If not set, the method defaults to the zero (i.e. black for images) baseline.
- max
Blur numberSigma - The standard deviation of the blur kernel for the blurred baseline. The same blurring parameter is used for both the height and the width dimension. If not set, the method defaults to the zero (i.e. black for images) baseline.
- max_
blur_ floatsigma - The standard deviation of the blur kernel for the blurred baseline. The same blurring parameter is used for both the height and the width dimension. If not set, the method defaults to the zero (i.e. black for images) baseline.
- max
Blur NumberSigma - The standard deviation of the blur kernel for the blurred baseline. The same blurring parameter is used for both the height and the width dimension. If not set, the method defaults to the zero (i.e. black for images) baseline.
GoogleCloudAiplatformV1BlurBaselineConfigResponse, GoogleCloudAiplatformV1BlurBaselineConfigResponseArgs
- Max
Blur doubleSigma - The standard deviation of the blur kernel for the blurred baseline. The same blurring parameter is used for both the height and the width dimension. If not set, the method defaults to the zero (i.e. black for images) baseline.
- Max
Blur float64Sigma - The standard deviation of the blur kernel for the blurred baseline. The same blurring parameter is used for both the height and the width dimension. If not set, the method defaults to the zero (i.e. black for images) baseline.
- max
Blur DoubleSigma - The standard deviation of the blur kernel for the blurred baseline. The same blurring parameter is used for both the height and the width dimension. If not set, the method defaults to the zero (i.e. black for images) baseline.
- max
Blur numberSigma - The standard deviation of the blur kernel for the blurred baseline. The same blurring parameter is used for both the height and the width dimension. If not set, the method defaults to the zero (i.e. black for images) baseline.
- max_
blur_ floatsigma - The standard deviation of the blur kernel for the blurred baseline. The same blurring parameter is used for both the height and the width dimension. If not set, the method defaults to the zero (i.e. black for images) baseline.
- max
Blur NumberSigma - The standard deviation of the blur kernel for the blurred baseline. The same blurring parameter is used for both the height and the width dimension. If not set, the method defaults to the zero (i.e. black for images) baseline.
GoogleCloudAiplatformV1CompletionStatsResponse, GoogleCloudAiplatformV1CompletionStatsResponseArgs
- Failed
Count string - The number of entities for which any error was encountered.
- Incomplete
Count string - In cases when enough errors are encountered a job, pipeline, or operation may be failed as a whole. Below is the number of entities for which the processing had not been finished (either in successful or failed state). Set to -1 if the number is unknown (for example, the operation failed before the total entity number could be collected).
- Successful
Count string - The number of entities that had been processed successfully.
- Successful
Forecast stringPoint Count - The number of the successful forecast points that are generated by the forecasting model. This is ONLY used by the forecasting batch prediction.
- Failed
Count string - The number of entities for which any error was encountered.
- Incomplete
Count string - In cases when enough errors are encountered a job, pipeline, or operation may be failed as a whole. Below is the number of entities for which the processing had not been finished (either in successful or failed state). Set to -1 if the number is unknown (for example, the operation failed before the total entity number could be collected).
- Successful
Count string - The number of entities that had been processed successfully.
- Successful
Forecast stringPoint Count - The number of the successful forecast points that are generated by the forecasting model. This is ONLY used by the forecasting batch prediction.
- failed
Count String - The number of entities for which any error was encountered.
- incomplete
Count String - In cases when enough errors are encountered a job, pipeline, or operation may be failed as a whole. Below is the number of entities for which the processing had not been finished (either in successful or failed state). Set to -1 if the number is unknown (for example, the operation failed before the total entity number could be collected).
- successful
Count String - The number of entities that had been processed successfully.
- successful
Forecast StringPoint Count - The number of the successful forecast points that are generated by the forecasting model. This is ONLY used by the forecasting batch prediction.
- failed
Count string - The number of entities for which any error was encountered.
- incomplete
Count string - In cases when enough errors are encountered a job, pipeline, or operation may be failed as a whole. Below is the number of entities for which the processing had not been finished (either in successful or failed state). Set to -1 if the number is unknown (for example, the operation failed before the total entity number could be collected).
- successful
Count string - The number of entities that had been processed successfully.
- successful
Forecast stringPoint Count - The number of the successful forecast points that are generated by the forecasting model. This is ONLY used by the forecasting batch prediction.
- failed_
count str - The number of entities for which any error was encountered.
- incomplete_
count str - In cases when enough errors are encountered a job, pipeline, or operation may be failed as a whole. Below is the number of entities for which the processing had not been finished (either in successful or failed state). Set to -1 if the number is unknown (for example, the operation failed before the total entity number could be collected).
- successful_
count str - The number of entities that had been processed successfully.
- successful_
forecast_ strpoint_ count - The number of the successful forecast points that are generated by the forecasting model. This is ONLY used by the forecasting batch prediction.
- failed
Count String - The number of entities for which any error was encountered.
- incomplete
Count String - In cases when enough errors are encountered a job, pipeline, or operation may be failed as a whole. Below is the number of entities for which the processing had not been finished (either in successful or failed state). Set to -1 if the number is unknown (for example, the operation failed before the total entity number could be collected).
- successful
Count String - The number of entities that had been processed successfully.
- successful
Forecast StringPoint Count - The number of the successful forecast points that are generated by the forecasting model. This is ONLY used by the forecasting batch prediction.
GoogleCloudAiplatformV1EncryptionSpec, GoogleCloudAiplatformV1EncryptionSpecArgs
- Kms
Key stringName - The Cloud KMS resource identifier of the customer managed encryption key used to protect a resource. Has the form:
projects/my-project/locations/my-region/keyRings/my-kr/cryptoKeys/my-key
. The key needs to be in the same region as where the compute resource is created.
- Kms
Key stringName - The Cloud KMS resource identifier of the customer managed encryption key used to protect a resource. Has the form:
projects/my-project/locations/my-region/keyRings/my-kr/cryptoKeys/my-key
. The key needs to be in the same region as where the compute resource is created.
- kms
Key StringName - The Cloud KMS resource identifier of the customer managed encryption key used to protect a resource. Has the form:
projects/my-project/locations/my-region/keyRings/my-kr/cryptoKeys/my-key
. The key needs to be in the same region as where the compute resource is created.
- kms
Key stringName - The Cloud KMS resource identifier of the customer managed encryption key used to protect a resource. Has the form:
projects/my-project/locations/my-region/keyRings/my-kr/cryptoKeys/my-key
. The key needs to be in the same region as where the compute resource is created.
- kms_
key_ strname - The Cloud KMS resource identifier of the customer managed encryption key used to protect a resource. Has the form:
projects/my-project/locations/my-region/keyRings/my-kr/cryptoKeys/my-key
. The key needs to be in the same region as where the compute resource is created.
- kms
Key StringName - The Cloud KMS resource identifier of the customer managed encryption key used to protect a resource. Has the form:
projects/my-project/locations/my-region/keyRings/my-kr/cryptoKeys/my-key
. The key needs to be in the same region as where the compute resource is created.
GoogleCloudAiplatformV1EncryptionSpecResponse, GoogleCloudAiplatformV1EncryptionSpecResponseArgs
- Kms
Key stringName - The Cloud KMS resource identifier of the customer managed encryption key used to protect a resource. Has the form:
projects/my-project/locations/my-region/keyRings/my-kr/cryptoKeys/my-key
. The key needs to be in the same region as where the compute resource is created.
- Kms
Key stringName - The Cloud KMS resource identifier of the customer managed encryption key used to protect a resource. Has the form:
projects/my-project/locations/my-region/keyRings/my-kr/cryptoKeys/my-key
. The key needs to be in the same region as where the compute resource is created.
- kms
Key StringName - The Cloud KMS resource identifier of the customer managed encryption key used to protect a resource. Has the form:
projects/my-project/locations/my-region/keyRings/my-kr/cryptoKeys/my-key
. The key needs to be in the same region as where the compute resource is created.
- kms
Key stringName - The Cloud KMS resource identifier of the customer managed encryption key used to protect a resource. Has the form:
projects/my-project/locations/my-region/keyRings/my-kr/cryptoKeys/my-key
. The key needs to be in the same region as where the compute resource is created.
- kms_
key_ strname - The Cloud KMS resource identifier of the customer managed encryption key used to protect a resource. Has the form:
projects/my-project/locations/my-region/keyRings/my-kr/cryptoKeys/my-key
. The key needs to be in the same region as where the compute resource is created.
- kms
Key StringName - The Cloud KMS resource identifier of the customer managed encryption key used to protect a resource. Has the form:
projects/my-project/locations/my-region/keyRings/my-kr/cryptoKeys/my-key
. The key needs to be in the same region as where the compute resource is created.
GoogleCloudAiplatformV1EnvVar, GoogleCloudAiplatformV1EnvVarArgs
- Name string
- Name of the environment variable. Must be a valid C identifier.
- Value string
- Variables that reference a $(VAR_NAME) are expanded using the previous defined environment variables in the container and any service environment variables. If a variable cannot be resolved, the reference in the input string will be unchanged. The $(VAR_NAME) syntax can be escaped with a double $$, ie: $$(VAR_NAME). Escaped references will never be expanded, regardless of whether the variable exists or not.
- Name string
- Name of the environment variable. Must be a valid C identifier.
- Value string
- Variables that reference a $(VAR_NAME) are expanded using the previous defined environment variables in the container and any service environment variables. If a variable cannot be resolved, the reference in the input string will be unchanged. The $(VAR_NAME) syntax can be escaped with a double $$, ie: $$(VAR_NAME). Escaped references will never be expanded, regardless of whether the variable exists or not.
- name String
- Name of the environment variable. Must be a valid C identifier.
- value String
- Variables that reference a $(VAR_NAME) are expanded using the previous defined environment variables in the container and any service environment variables. If a variable cannot be resolved, the reference in the input string will be unchanged. The $(VAR_NAME) syntax can be escaped with a double $$, ie: $$(VAR_NAME). Escaped references will never be expanded, regardless of whether the variable exists or not.
- name string
- Name of the environment variable. Must be a valid C identifier.
- value string
- Variables that reference a $(VAR_NAME) are expanded using the previous defined environment variables in the container and any service environment variables. If a variable cannot be resolved, the reference in the input string will be unchanged. The $(VAR_NAME) syntax can be escaped with a double $$, ie: $$(VAR_NAME). Escaped references will never be expanded, regardless of whether the variable exists or not.
- name str
- Name of the environment variable. Must be a valid C identifier.
- value str
- Variables that reference a $(VAR_NAME) are expanded using the previous defined environment variables in the container and any service environment variables. If a variable cannot be resolved, the reference in the input string will be unchanged. The $(VAR_NAME) syntax can be escaped with a double $$, ie: $$(VAR_NAME). Escaped references will never be expanded, regardless of whether the variable exists or not.
- name String
- Name of the environment variable. Must be a valid C identifier.
- value String
- Variables that reference a $(VAR_NAME) are expanded using the previous defined environment variables in the container and any service environment variables. If a variable cannot be resolved, the reference in the input string will be unchanged. The $(VAR_NAME) syntax can be escaped with a double $$, ie: $$(VAR_NAME). Escaped references will never be expanded, regardless of whether the variable exists or not.
GoogleCloudAiplatformV1EnvVarResponse, GoogleCloudAiplatformV1EnvVarResponseArgs
- Name string
- Name of the environment variable. Must be a valid C identifier.
- Value string
- Variables that reference a $(VAR_NAME) are expanded using the previous defined environment variables in the container and any service environment variables. If a variable cannot be resolved, the reference in the input string will be unchanged. The $(VAR_NAME) syntax can be escaped with a double $$, ie: $$(VAR_NAME). Escaped references will never be expanded, regardless of whether the variable exists or not.
- Name string
- Name of the environment variable. Must be a valid C identifier.
- Value string
- Variables that reference a $(VAR_NAME) are expanded using the previous defined environment variables in the container and any service environment variables. If a variable cannot be resolved, the reference in the input string will be unchanged. The $(VAR_NAME) syntax can be escaped with a double $$, ie: $$(VAR_NAME). Escaped references will never be expanded, regardless of whether the variable exists or not.
- name String
- Name of the environment variable. Must be a valid C identifier.
- value String
- Variables that reference a $(VAR_NAME) are expanded using the previous defined environment variables in the container and any service environment variables. If a variable cannot be resolved, the reference in the input string will be unchanged. The $(VAR_NAME) syntax can be escaped with a double $$, ie: $$(VAR_NAME). Escaped references will never be expanded, regardless of whether the variable exists or not.
- name string
- Name of the environment variable. Must be a valid C identifier.
- value string
- Variables that reference a $(VAR_NAME) are expanded using the previous defined environment variables in the container and any service environment variables. If a variable cannot be resolved, the reference in the input string will be unchanged. The $(VAR_NAME) syntax can be escaped with a double $$, ie: $$(VAR_NAME). Escaped references will never be expanded, regardless of whether the variable exists or not.
- name str
- Name of the environment variable. Must be a valid C identifier.
- value str
- Variables that reference a $(VAR_NAME) are expanded using the previous defined environment variables in the container and any service environment variables. If a variable cannot be resolved, the reference in the input string will be unchanged. The $(VAR_NAME) syntax can be escaped with a double $$, ie: $$(VAR_NAME). Escaped references will never be expanded, regardless of whether the variable exists or not.
- name String
- Name of the environment variable. Must be a valid C identifier.
- value String
- Variables that reference a $(VAR_NAME) are expanded using the previous defined environment variables in the container and any service environment variables. If a variable cannot be resolved, the reference in the input string will be unchanged. The $(VAR_NAME) syntax can be escaped with a double $$, ie: $$(VAR_NAME). Escaped references will never be expanded, regardless of whether the variable exists or not.
GoogleCloudAiplatformV1Examples, GoogleCloudAiplatformV1ExamplesArgs
- Example
Gcs Pulumi.Source Google Native. Aiplatform. V1. Inputs. Google Cloud Aiplatform V1Examples Example Gcs Source - The Cloud Storage input instances.
- Nearest
Neighbor objectSearch Config - The full configuration for the generated index, the semantics are the same as metadata and should match NearestNeighborSearchConfig.
- Neighbor
Count int - The number of neighbors to return when querying for examples.
- Presets
Pulumi.
Google Native. Aiplatform. V1. Inputs. Google Cloud Aiplatform V1Presets - Simplified preset configuration, which automatically sets configuration values based on the desired query speed-precision trade-off and modality.
- Example
Gcs GoogleSource Cloud Aiplatform V1Examples Example Gcs Source - The Cloud Storage input instances.
- Nearest
Neighbor interface{}Search Config - The full configuration for the generated index, the semantics are the same as metadata and should match NearestNeighborSearchConfig.
- Neighbor
Count int - The number of neighbors to return when querying for examples.
- Presets
Google
Cloud Aiplatform V1Presets - Simplified preset configuration, which automatically sets configuration values based on the desired query speed-precision trade-off and modality.
- example
Gcs GoogleSource Cloud Aiplatform V1Examples Example Gcs Source - The Cloud Storage input instances.
- nearest
Neighbor ObjectSearch Config - The full configuration for the generated index, the semantics are the same as metadata and should match NearestNeighborSearchConfig.
- neighbor
Count Integer - The number of neighbors to return when querying for examples.
- presets
Google
Cloud Aiplatform V1Presets - Simplified preset configuration, which automatically sets configuration values based on the desired query speed-precision trade-off and modality.
- example
Gcs GoogleSource Cloud Aiplatform V1Examples Example Gcs Source - The Cloud Storage input instances.
- nearest
Neighbor anySearch Config - The full configuration for the generated index, the semantics are the same as metadata and should match NearestNeighborSearchConfig.
- neighbor
Count number - The number of neighbors to return when querying for examples.
- presets
Google
Cloud Aiplatform V1Presets - Simplified preset configuration, which automatically sets configuration values based on the desired query speed-precision trade-off and modality.
- example_
gcs_ Googlesource Cloud Aiplatform V1Examples Example Gcs Source - The Cloud Storage input instances.
- nearest_
neighbor_ Anysearch_ config - The full configuration for the generated index, the semantics are the same as metadata and should match NearestNeighborSearchConfig.
- neighbor_
count int - The number of neighbors to return when querying for examples.
- presets
Google
Cloud Aiplatform V1Presets - Simplified preset configuration, which automatically sets configuration values based on the desired query speed-precision trade-off and modality.
- example
Gcs Property MapSource - The Cloud Storage input instances.
- nearest
Neighbor AnySearch Config - The full configuration for the generated index, the semantics are the same as metadata and should match NearestNeighborSearchConfig.
- neighbor
Count Number - The number of neighbors to return when querying for examples.
- presets Property Map
- Simplified preset configuration, which automatically sets configuration values based on the desired query speed-precision trade-off and modality.
GoogleCloudAiplatformV1ExamplesExampleGcsSource, GoogleCloudAiplatformV1ExamplesExampleGcsSourceArgs
- Data
Format Pulumi.Google Native. Aiplatform. V1. Google Cloud Aiplatform V1Examples Example Gcs Source Data Format - The format in which instances are given, if not specified, assume it's JSONL format. Currently only JSONL format is supported.
- Gcs
Source Pulumi.Google Native. Aiplatform. V1. Inputs. Google Cloud Aiplatform V1Gcs Source - The Cloud Storage location for the input instances.
- Data
Format GoogleCloud Aiplatform V1Examples Example Gcs Source Data Format - The format in which instances are given, if not specified, assume it's JSONL format. Currently only JSONL format is supported.
- Gcs
Source GoogleCloud Aiplatform V1Gcs Source - The Cloud Storage location for the input instances.
- data
Format GoogleCloud Aiplatform V1Examples Example Gcs Source Data Format - The format in which instances are given, if not specified, assume it's JSONL format. Currently only JSONL format is supported.
- gcs
Source GoogleCloud Aiplatform V1Gcs Source - The Cloud Storage location for the input instances.
- data
Format GoogleCloud Aiplatform V1Examples Example Gcs Source Data Format - The format in which instances are given, if not specified, assume it's JSONL format. Currently only JSONL format is supported.
- gcs
Source GoogleCloud Aiplatform V1Gcs Source - The Cloud Storage location for the input instances.
- data_
format GoogleCloud Aiplatform V1Examples Example Gcs Source Data Format - The format in which instances are given, if not specified, assume it's JSONL format. Currently only JSONL format is supported.
- gcs_
source GoogleCloud Aiplatform V1Gcs Source - The Cloud Storage location for the input instances.
- data
Format "DATA_FORMAT_UNSPECIFIED" | "JSONL" - The format in which instances are given, if not specified, assume it's JSONL format. Currently only JSONL format is supported.
- gcs
Source Property Map - The Cloud Storage location for the input instances.
GoogleCloudAiplatformV1ExamplesExampleGcsSourceDataFormat, GoogleCloudAiplatformV1ExamplesExampleGcsSourceDataFormatArgs
- Data
Format Unspecified - DATA_FORMAT_UNSPECIFIEDFormat unspecified, used when unset.
- Jsonl
- JSONLExamples are stored in JSONL files.
- Google
Cloud Aiplatform V1Examples Example Gcs Source Data Format Data Format Unspecified - DATA_FORMAT_UNSPECIFIEDFormat unspecified, used when unset.
- Google
Cloud Aiplatform V1Examples Example Gcs Source Data Format Jsonl - JSONLExamples are stored in JSONL files.
- Data
Format Unspecified - DATA_FORMAT_UNSPECIFIEDFormat unspecified, used when unset.
- Jsonl
- JSONLExamples are stored in JSONL files.
- Data
Format Unspecified - DATA_FORMAT_UNSPECIFIEDFormat unspecified, used when unset.
- Jsonl
- JSONLExamples are stored in JSONL files.
- DATA_FORMAT_UNSPECIFIED
- DATA_FORMAT_UNSPECIFIEDFormat unspecified, used when unset.
- JSONL
- JSONLExamples are stored in JSONL files.
- "DATA_FORMAT_UNSPECIFIED"
- DATA_FORMAT_UNSPECIFIEDFormat unspecified, used when unset.
- "JSONL"
- JSONLExamples are stored in JSONL files.
GoogleCloudAiplatformV1ExamplesExampleGcsSourceResponse, GoogleCloudAiplatformV1ExamplesExampleGcsSourceResponseArgs
- Data
Format string - The format in which instances are given, if not specified, assume it's JSONL format. Currently only JSONL format is supported.
- Gcs
Source Pulumi.Google Native. Aiplatform. V1. Inputs. Google Cloud Aiplatform V1Gcs Source Response - The Cloud Storage location for the input instances.
- Data
Format string - The format in which instances are given, if not specified, assume it's JSONL format. Currently only JSONL format is supported.
- Gcs
Source GoogleCloud Aiplatform V1Gcs Source Response - The Cloud Storage location for the input instances.
- data
Format String - The format in which instances are given, if not specified, assume it's JSONL format. Currently only JSONL format is supported.
- gcs
Source GoogleCloud Aiplatform V1Gcs Source Response - The Cloud Storage location for the input instances.
- data
Format string - The format in which instances are given, if not specified, assume it's JSONL format. Currently only JSONL format is supported.
- gcs
Source GoogleCloud Aiplatform V1Gcs Source Response - The Cloud Storage location for the input instances.
- data_
format str - The format in which instances are given, if not specified, assume it's JSONL format. Currently only JSONL format is supported.
- gcs_
source GoogleCloud Aiplatform V1Gcs Source Response - The Cloud Storage location for the input instances.
- data
Format String - The format in which instances are given, if not specified, assume it's JSONL format. Currently only JSONL format is supported.
- gcs
Source Property Map - The Cloud Storage location for the input instances.
GoogleCloudAiplatformV1ExamplesResponse, GoogleCloudAiplatformV1ExamplesResponseArgs
- Example
Gcs Pulumi.Source Google Native. Aiplatform. V1. Inputs. Google Cloud Aiplatform V1Examples Example Gcs Source Response - The Cloud Storage input instances.
- Nearest
Neighbor objectSearch Config - The full configuration for the generated index, the semantics are the same as metadata and should match NearestNeighborSearchConfig.
- Neighbor
Count int - The number of neighbors to return when querying for examples.
- Presets
Pulumi.
Google Native. Aiplatform. V1. Inputs. Google Cloud Aiplatform V1Presets Response - Simplified preset configuration, which automatically sets configuration values based on the desired query speed-precision trade-off and modality.
- Example
Gcs GoogleSource Cloud Aiplatform V1Examples Example Gcs Source Response - The Cloud Storage input instances.
- Nearest
Neighbor interface{}Search Config - The full configuration for the generated index, the semantics are the same as metadata and should match NearestNeighborSearchConfig.
- Neighbor
Count int - The number of neighbors to return when querying for examples.
- Presets
Google
Cloud Aiplatform V1Presets Response - Simplified preset configuration, which automatically sets configuration values based on the desired query speed-precision trade-off and modality.
- example
Gcs GoogleSource Cloud Aiplatform V1Examples Example Gcs Source Response - The Cloud Storage input instances.
- nearest
Neighbor ObjectSearch Config - The full configuration for the generated index, the semantics are the same as metadata and should match NearestNeighborSearchConfig.
- neighbor
Count Integer - The number of neighbors to return when querying for examples.
- presets
Google
Cloud Aiplatform V1Presets Response - Simplified preset configuration, which automatically sets configuration values based on the desired query speed-precision trade-off and modality.
- example
Gcs GoogleSource Cloud Aiplatform V1Examples Example Gcs Source Response - The Cloud Storage input instances.
- nearest
Neighbor anySearch Config - The full configuration for the generated index, the semantics are the same as metadata and should match NearestNeighborSearchConfig.
- neighbor
Count number - The number of neighbors to return when querying for examples.
- presets
Google
Cloud Aiplatform V1Presets Response - Simplified preset configuration, which automatically sets configuration values based on the desired query speed-precision trade-off and modality.
- example_
gcs_ Googlesource Cloud Aiplatform V1Examples Example Gcs Source Response - The Cloud Storage input instances.
- nearest_
neighbor_ Anysearch_ config - The full configuration for the generated index, the semantics are the same as metadata and should match NearestNeighborSearchConfig.
- neighbor_
count int - The number of neighbors to return when querying for examples.
- presets
Google
Cloud Aiplatform V1Presets Response - Simplified preset configuration, which automatically sets configuration values based on the desired query speed-precision trade-off and modality.
- example
Gcs Property MapSource - The Cloud Storage input instances.
- nearest
Neighbor AnySearch Config - The full configuration for the generated index, the semantics are the same as metadata and should match NearestNeighborSearchConfig.
- neighbor
Count Number - The number of neighbors to return when querying for examples.
- presets Property Map
- Simplified preset configuration, which automatically sets configuration values based on the desired query speed-precision trade-off and modality.
GoogleCloudAiplatformV1ExplanationMetadata, GoogleCloudAiplatformV1ExplanationMetadataArgs
- Inputs Dictionary<string, string>
- Map from feature names to feature input metadata. Keys are the name of the features. Values are the specification of the feature. An empty InputMetadata is valid. It describes a text feature which has the name specified as the key in ExplanationMetadata.inputs. The baseline of the empty feature is chosen by Vertex AI. For Vertex AI-provided Tensorflow images, the key can be any friendly name of the feature. Once specified, featureAttributions are keyed by this key (if not grouped with another feature). For custom images, the key must match with the key in instance.
- Outputs Dictionary<string, string>
- Map from output names to output metadata. For Vertex AI-provided Tensorflow images, keys can be any user defined string that consists of any UTF-8 characters. For custom images, keys are the name of the output field in the prediction to be explained. Currently only one key is allowed.
- Feature
Attributions stringSchema Uri - Points to a YAML file stored on Google Cloud Storage describing the format of the feature attributions. The schema is defined as an OpenAPI 3.0.2 Schema Object. AutoML tabular Models always have this field populated by Vertex AI. Note: The URI given on output may be 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.
- Latent
Space stringSource - Name of the source to generate embeddings for example based explanations.
- Inputs map[string]string
- Map from feature names to feature input metadata. Keys are the name of the features. Values are the specification of the feature. An empty InputMetadata is valid. It describes a text feature which has the name specified as the key in ExplanationMetadata.inputs. The baseline of the empty feature is chosen by Vertex AI. For Vertex AI-provided Tensorflow images, the key can be any friendly name of the feature. Once specified, featureAttributions are keyed by this key (if not grouped with another feature). For custom images, the key must match with the key in instance.
- Outputs map[string]string
- Map from output names to output metadata. For Vertex AI-provided Tensorflow images, keys can be any user defined string that consists of any UTF-8 characters. For custom images, keys are the name of the output field in the prediction to be explained. Currently only one key is allowed.
- Feature
Attributions stringSchema Uri - Points to a YAML file stored on Google Cloud Storage describing the format of the feature attributions. The schema is defined as an OpenAPI 3.0.2 Schema Object. AutoML tabular Models always have this field populated by Vertex AI. Note: The URI given on output may be 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.
- Latent
Space stringSource - Name of the source to generate embeddings for example based explanations.
- inputs Map<String,String>
- Map from feature names to feature input metadata. Keys are the name of the features. Values are the specification of the feature. An empty InputMetadata is valid. It describes a text feature which has the name specified as the key in ExplanationMetadata.inputs. The baseline of the empty feature is chosen by Vertex AI. For Vertex AI-provided Tensorflow images, the key can be any friendly name of the feature. Once specified, featureAttributions are keyed by this key (if not grouped with another feature). For custom images, the key must match with the key in instance.
- outputs Map<String,String>
- Map from output names to output metadata. For Vertex AI-provided Tensorflow images, keys can be any user defined string that consists of any UTF-8 characters. For custom images, keys are the name of the output field in the prediction to be explained. Currently only one key is allowed.
- feature
Attributions StringSchema Uri - Points to a YAML file stored on Google Cloud Storage describing the format of the feature attributions. The schema is defined as an OpenAPI 3.0.2 Schema Object. AutoML tabular Models always have this field populated by Vertex AI. Note: The URI given on output may be 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.
- latent
Space StringSource - Name of the source to generate embeddings for example based explanations.
- inputs {[key: string]: string}
- Map from feature names to feature input metadata. Keys are the name of the features. Values are the specification of the feature. An empty InputMetadata is valid. It describes a text feature which has the name specified as the key in ExplanationMetadata.inputs. The baseline of the empty feature is chosen by Vertex AI. For Vertex AI-provided Tensorflow images, the key can be any friendly name of the feature. Once specified, featureAttributions are keyed by this key (if not grouped with another feature). For custom images, the key must match with the key in instance.
- outputs {[key: string]: string}
- Map from output names to output metadata. For Vertex AI-provided Tensorflow images, keys can be any user defined string that consists of any UTF-8 characters. For custom images, keys are the name of the output field in the prediction to be explained. Currently only one key is allowed.
- feature
Attributions stringSchema Uri - Points to a YAML file stored on Google Cloud Storage describing the format of the feature attributions. The schema is defined as an OpenAPI 3.0.2 Schema Object. AutoML tabular Models always have this field populated by Vertex AI. Note: The URI given on output may be 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.
- latent
Space stringSource - Name of the source to generate embeddings for example based explanations.
- inputs Mapping[str, str]
- Map from feature names to feature input metadata. Keys are the name of the features. Values are the specification of the feature. An empty InputMetadata is valid. It describes a text feature which has the name specified as the key in ExplanationMetadata.inputs. The baseline of the empty feature is chosen by Vertex AI. For Vertex AI-provided Tensorflow images, the key can be any friendly name of the feature. Once specified, featureAttributions are keyed by this key (if not grouped with another feature). For custom images, the key must match with the key in instance.
- outputs Mapping[str, str]
- Map from output names to output metadata. For Vertex AI-provided Tensorflow images, keys can be any user defined string that consists of any UTF-8 characters. For custom images, keys are the name of the output field in the prediction to be explained. Currently only one key is allowed.
- feature_
attributions_ strschema_ uri - Points to a YAML file stored on Google Cloud Storage describing the format of the feature attributions. The schema is defined as an OpenAPI 3.0.2 Schema Object. AutoML tabular Models always have this field populated by Vertex AI. Note: The URI given on output may be 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.
- latent_
space_ strsource - Name of the source to generate embeddings for example based explanations.
- inputs Map<String>
- Map from feature names to feature input metadata. Keys are the name of the features. Values are the specification of the feature. An empty InputMetadata is valid. It describes a text feature which has the name specified as the key in ExplanationMetadata.inputs. The baseline of the empty feature is chosen by Vertex AI. For Vertex AI-provided Tensorflow images, the key can be any friendly name of the feature. Once specified, featureAttributions are keyed by this key (if not grouped with another feature). For custom images, the key must match with the key in instance.
- outputs Map<String>
- Map from output names to output metadata. For Vertex AI-provided Tensorflow images, keys can be any user defined string that consists of any UTF-8 characters. For custom images, keys are the name of the output field in the prediction to be explained. Currently only one key is allowed.
- feature
Attributions StringSchema Uri - Points to a YAML file stored on Google Cloud Storage describing the format of the feature attributions. The schema is defined as an OpenAPI 3.0.2 Schema Object. AutoML tabular Models always have this field populated by Vertex AI. Note: The URI given on output may be 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.
- latent
Space StringSource - Name of the source to generate embeddings for example based explanations.
GoogleCloudAiplatformV1ExplanationMetadataResponse, GoogleCloudAiplatformV1ExplanationMetadataResponseArgs
- Feature
Attributions stringSchema Uri - Points to a YAML file stored on Google Cloud Storage describing the format of the feature attributions. The schema is defined as an OpenAPI 3.0.2 Schema Object. AutoML tabular Models always have this field populated by Vertex AI. Note: The URI given on output may be 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.
- Inputs Dictionary<string, string>
- Map from feature names to feature input metadata. Keys are the name of the features. Values are the specification of the feature. An empty InputMetadata is valid. It describes a text feature which has the name specified as the key in ExplanationMetadata.inputs. The baseline of the empty feature is chosen by Vertex AI. For Vertex AI-provided Tensorflow images, the key can be any friendly name of the feature. Once specified, featureAttributions are keyed by this key (if not grouped with another feature). For custom images, the key must match with the key in instance.
- Latent
Space stringSource - Name of the source to generate embeddings for example based explanations.
- Outputs Dictionary<string, string>
- Map from output names to output metadata. For Vertex AI-provided Tensorflow images, keys can be any user defined string that consists of any UTF-8 characters. For custom images, keys are the name of the output field in the prediction to be explained. Currently only one key is allowed.
- Feature
Attributions stringSchema Uri - Points to a YAML file stored on Google Cloud Storage describing the format of the feature attributions. The schema is defined as an OpenAPI 3.0.2 Schema Object. AutoML tabular Models always have this field populated by Vertex AI. Note: The URI given on output may be 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.
- Inputs map[string]string
- Map from feature names to feature input metadata. Keys are the name of the features. Values are the specification of the feature. An empty InputMetadata is valid. It describes a text feature which has the name specified as the key in ExplanationMetadata.inputs. The baseline of the empty feature is chosen by Vertex AI. For Vertex AI-provided Tensorflow images, the key can be any friendly name of the feature. Once specified, featureAttributions are keyed by this key (if not grouped with another feature). For custom images, the key must match with the key in instance.
- Latent
Space stringSource - Name of the source to generate embeddings for example based explanations.
- Outputs map[string]string
- Map from output names to output metadata. For Vertex AI-provided Tensorflow images, keys can be any user defined string that consists of any UTF-8 characters. For custom images, keys are the name of the output field in the prediction to be explained. Currently only one key is allowed.
- feature
Attributions StringSchema Uri - Points to a YAML file stored on Google Cloud Storage describing the format of the feature attributions. The schema is defined as an OpenAPI 3.0.2 Schema Object. AutoML tabular Models always have this field populated by Vertex AI. Note: The URI given on output may be 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.
- inputs Map<String,String>
- Map from feature names to feature input metadata. Keys are the name of the features. Values are the specification of the feature. An empty InputMetadata is valid. It describes a text feature which has the name specified as the key in ExplanationMetadata.inputs. The baseline of the empty feature is chosen by Vertex AI. For Vertex AI-provided Tensorflow images, the key can be any friendly name of the feature. Once specified, featureAttributions are keyed by this key (if not grouped with another feature). For custom images, the key must match with the key in instance.
- latent
Space StringSource - Name of the source to generate embeddings for example based explanations.
- outputs Map<String,String>
- Map from output names to output metadata. For Vertex AI-provided Tensorflow images, keys can be any user defined string that consists of any UTF-8 characters. For custom images, keys are the name of the output field in the prediction to be explained. Currently only one key is allowed.
- feature
Attributions stringSchema Uri - Points to a YAML file stored on Google Cloud Storage describing the format of the feature attributions. The schema is defined as an OpenAPI 3.0.2 Schema Object. AutoML tabular Models always have this field populated by Vertex AI. Note: The URI given on output may be 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.
- inputs {[key: string]: string}
- Map from feature names to feature input metadata. Keys are the name of the features. Values are the specification of the feature. An empty InputMetadata is valid. It describes a text feature which has the name specified as the key in ExplanationMetadata.inputs. The baseline of the empty feature is chosen by Vertex AI. For Vertex AI-provided Tensorflow images, the key can be any friendly name of the feature. Once specified, featureAttributions are keyed by this key (if not grouped with another feature). For custom images, the key must match with the key in instance.
- latent
Space stringSource - Name of the source to generate embeddings for example based explanations.
- outputs {[key: string]: string}
- Map from output names to output metadata. For Vertex AI-provided Tensorflow images, keys can be any user defined string that consists of any UTF-8 characters. For custom images, keys are the name of the output field in the prediction to be explained. Currently only one key is allowed.
- feature_
attributions_ strschema_ uri - Points to a YAML file stored on Google Cloud Storage describing the format of the feature attributions. The schema is defined as an OpenAPI 3.0.2 Schema Object. AutoML tabular Models always have this field populated by Vertex AI. Note: The URI given on output may be 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.
- inputs Mapping[str, str]
- Map from feature names to feature input metadata. Keys are the name of the features. Values are the specification of the feature. An empty InputMetadata is valid. It describes a text feature which has the name specified as the key in ExplanationMetadata.inputs. The baseline of the empty feature is chosen by Vertex AI. For Vertex AI-provided Tensorflow images, the key can be any friendly name of the feature. Once specified, featureAttributions are keyed by this key (if not grouped with another feature). For custom images, the key must match with the key in instance.
- latent_
space_ strsource - Name of the source to generate embeddings for example based explanations.
- outputs Mapping[str, str]
- Map from output names to output metadata. For Vertex AI-provided Tensorflow images, keys can be any user defined string that consists of any UTF-8 characters. For custom images, keys are the name of the output field in the prediction to be explained. Currently only one key is allowed.
- feature
Attributions StringSchema Uri - Points to a YAML file stored on Google Cloud Storage describing the format of the feature attributions. The schema is defined as an OpenAPI 3.0.2 Schema Object. AutoML tabular Models always have this field populated by Vertex AI. Note: The URI given on output may be 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.
- inputs Map<String>
- Map from feature names to feature input metadata. Keys are the name of the features. Values are the specification of the feature. An empty InputMetadata is valid. It describes a text feature which has the name specified as the key in ExplanationMetadata.inputs. The baseline of the empty feature is chosen by Vertex AI. For Vertex AI-provided Tensorflow images, the key can be any friendly name of the feature. Once specified, featureAttributions are keyed by this key (if not grouped with another feature). For custom images, the key must match with the key in instance.
- latent
Space StringSource - Name of the source to generate embeddings for example based explanations.
- outputs Map<String>
- Map from output names to output metadata. For Vertex AI-provided Tensorflow images, keys can be any user defined string that consists of any UTF-8 characters. For custom images, keys are the name of the output field in the prediction to be explained. Currently only one key is allowed.
GoogleCloudAiplatformV1ExplanationParameters, GoogleCloudAiplatformV1ExplanationParametersArgs
- Examples
Pulumi.
Google Native. Aiplatform. V1. Inputs. Google Cloud Aiplatform V1Examples - Example-based explanations that returns the nearest neighbors from the provided dataset.
- Integrated
Gradients Pulumi.Attribution Google Native. Aiplatform. V1. Inputs. Google Cloud Aiplatform V1Integrated Gradients Attribution - An attribution method that computes Aumann-Shapley values taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1703.01365
- Output
Indices List<object> - If populated, only returns attributions that have output_index contained in output_indices. It must be an ndarray of integers, with the same shape of the output it's explaining. If not populated, returns attributions for top_k indices of outputs. If neither top_k nor output_indices is populated, returns the argmax index of the outputs. Only applicable to Models that predict multiple outputs (e,g, multi-class Models that predict multiple classes).
- Sampled
Shapley Pulumi.Attribution Google Native. Aiplatform. V1. Inputs. Google Cloud Aiplatform V1Sampled Shapley Attribution - An attribution method that approximates Shapley values for features that contribute to the label being predicted. A sampling strategy is used to approximate the value rather than considering all subsets of features. Refer to this paper for model details: https://arxiv.org/abs/1306.4265.
- Top
K int - If populated, returns attributions for top K indices of outputs (defaults to 1). Only applies to Models that predicts more than one outputs (e,g, multi-class Models). When set to -1, returns explanations for all outputs.
- Xrai
Attribution Pulumi.Google Native. Aiplatform. V1. Inputs. Google Cloud Aiplatform V1Xrai Attribution - An attribution method that redistributes Integrated Gradients attribution to segmented regions, taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1906.02825 XRAI currently performs better on natural images, like a picture of a house or an animal. If the images are taken in artificial environments, like a lab or manufacturing line, or from diagnostic equipment, like x-rays or quality-control cameras, use Integrated Gradients instead.
- Examples
Google
Cloud Aiplatform V1Examples - Example-based explanations that returns the nearest neighbors from the provided dataset.
- Integrated
Gradients GoogleAttribution Cloud Aiplatform V1Integrated Gradients Attribution - An attribution method that computes Aumann-Shapley values taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1703.01365
- Output
Indices []interface{} - If populated, only returns attributions that have output_index contained in output_indices. It must be an ndarray of integers, with the same shape of the output it's explaining. If not populated, returns attributions for top_k indices of outputs. If neither top_k nor output_indices is populated, returns the argmax index of the outputs. Only applicable to Models that predict multiple outputs (e,g, multi-class Models that predict multiple classes).
- Sampled
Shapley GoogleAttribution Cloud Aiplatform V1Sampled Shapley Attribution - An attribution method that approximates Shapley values for features that contribute to the label being predicted. A sampling strategy is used to approximate the value rather than considering all subsets of features. Refer to this paper for model details: https://arxiv.org/abs/1306.4265.
- Top
K int - If populated, returns attributions for top K indices of outputs (defaults to 1). Only applies to Models that predicts more than one outputs (e,g, multi-class Models). When set to -1, returns explanations for all outputs.
- Xrai
Attribution GoogleCloud Aiplatform V1Xrai Attribution - An attribution method that redistributes Integrated Gradients attribution to segmented regions, taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1906.02825 XRAI currently performs better on natural images, like a picture of a house or an animal. If the images are taken in artificial environments, like a lab or manufacturing line, or from diagnostic equipment, like x-rays or quality-control cameras, use Integrated Gradients instead.
- examples
Google
Cloud Aiplatform V1Examples - Example-based explanations that returns the nearest neighbors from the provided dataset.
- integrated
Gradients GoogleAttribution Cloud Aiplatform V1Integrated Gradients Attribution - An attribution method that computes Aumann-Shapley values taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1703.01365
- output
Indices List<Object> - If populated, only returns attributions that have output_index contained in output_indices. It must be an ndarray of integers, with the same shape of the output it's explaining. If not populated, returns attributions for top_k indices of outputs. If neither top_k nor output_indices is populated, returns the argmax index of the outputs. Only applicable to Models that predict multiple outputs (e,g, multi-class Models that predict multiple classes).
- sampled
Shapley GoogleAttribution Cloud Aiplatform V1Sampled Shapley Attribution - An attribution method that approximates Shapley values for features that contribute to the label being predicted. A sampling strategy is used to approximate the value rather than considering all subsets of features. Refer to this paper for model details: https://arxiv.org/abs/1306.4265.
- top
K Integer - If populated, returns attributions for top K indices of outputs (defaults to 1). Only applies to Models that predicts more than one outputs (e,g, multi-class Models). When set to -1, returns explanations for all outputs.
- xrai
Attribution GoogleCloud Aiplatform V1Xrai Attribution - An attribution method that redistributes Integrated Gradients attribution to segmented regions, taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1906.02825 XRAI currently performs better on natural images, like a picture of a house or an animal. If the images are taken in artificial environments, like a lab or manufacturing line, or from diagnostic equipment, like x-rays or quality-control cameras, use Integrated Gradients instead.
- examples
Google
Cloud Aiplatform V1Examples - Example-based explanations that returns the nearest neighbors from the provided dataset.
- integrated
Gradients GoogleAttribution Cloud Aiplatform V1Integrated Gradients Attribution - An attribution method that computes Aumann-Shapley values taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1703.01365
- output
Indices any[] - If populated, only returns attributions that have output_index contained in output_indices. It must be an ndarray of integers, with the same shape of the output it's explaining. If not populated, returns attributions for top_k indices of outputs. If neither top_k nor output_indices is populated, returns the argmax index of the outputs. Only applicable to Models that predict multiple outputs (e,g, multi-class Models that predict multiple classes).
- sampled
Shapley GoogleAttribution Cloud Aiplatform V1Sampled Shapley Attribution - An attribution method that approximates Shapley values for features that contribute to the label being predicted. A sampling strategy is used to approximate the value rather than considering all subsets of features. Refer to this paper for model details: https://arxiv.org/abs/1306.4265.
- top
K number - If populated, returns attributions for top K indices of outputs (defaults to 1). Only applies to Models that predicts more than one outputs (e,g, multi-class Models). When set to -1, returns explanations for all outputs.
- xrai
Attribution GoogleCloud Aiplatform V1Xrai Attribution - An attribution method that redistributes Integrated Gradients attribution to segmented regions, taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1906.02825 XRAI currently performs better on natural images, like a picture of a house or an animal. If the images are taken in artificial environments, like a lab or manufacturing line, or from diagnostic equipment, like x-rays or quality-control cameras, use Integrated Gradients instead.
- examples
Google
Cloud Aiplatform V1Examples - Example-based explanations that returns the nearest neighbors from the provided dataset.
- integrated_
gradients_ Googleattribution Cloud Aiplatform V1Integrated Gradients Attribution - An attribution method that computes Aumann-Shapley values taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1703.01365
- output_
indices Sequence[Any] - If populated, only returns attributions that have output_index contained in output_indices. It must be an ndarray of integers, with the same shape of the output it's explaining. If not populated, returns attributions for top_k indices of outputs. If neither top_k nor output_indices is populated, returns the argmax index of the outputs. Only applicable to Models that predict multiple outputs (e,g, multi-class Models that predict multiple classes).
- sampled_
shapley_ Googleattribution Cloud Aiplatform V1Sampled Shapley Attribution - An attribution method that approximates Shapley values for features that contribute to the label being predicted. A sampling strategy is used to approximate the value rather than considering all subsets of features. Refer to this paper for model details: https://arxiv.org/abs/1306.4265.
- top_
k int - If populated, returns attributions for top K indices of outputs (defaults to 1). Only applies to Models that predicts more than one outputs (e,g, multi-class Models). When set to -1, returns explanations for all outputs.
- xrai_
attribution GoogleCloud Aiplatform V1Xrai Attribution - An attribution method that redistributes Integrated Gradients attribution to segmented regions, taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1906.02825 XRAI currently performs better on natural images, like a picture of a house or an animal. If the images are taken in artificial environments, like a lab or manufacturing line, or from diagnostic equipment, like x-rays or quality-control cameras, use Integrated Gradients instead.
- examples Property Map
- Example-based explanations that returns the nearest neighbors from the provided dataset.
- integrated
Gradients Property MapAttribution - An attribution method that computes Aumann-Shapley values taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1703.01365
- output
Indices List<Any> - If populated, only returns attributions that have output_index contained in output_indices. It must be an ndarray of integers, with the same shape of the output it's explaining. If not populated, returns attributions for top_k indices of outputs. If neither top_k nor output_indices is populated, returns the argmax index of the outputs. Only applicable to Models that predict multiple outputs (e,g, multi-class Models that predict multiple classes).
- sampled
Shapley Property MapAttribution - An attribution method that approximates Shapley values for features that contribute to the label being predicted. A sampling strategy is used to approximate the value rather than considering all subsets of features. Refer to this paper for model details: https://arxiv.org/abs/1306.4265.
- top
K Number - If populated, returns attributions for top K indices of outputs (defaults to 1). Only applies to Models that predicts more than one outputs (e,g, multi-class Models). When set to -1, returns explanations for all outputs.
- xrai
Attribution Property Map - An attribution method that redistributes Integrated Gradients attribution to segmented regions, taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1906.02825 XRAI currently performs better on natural images, like a picture of a house or an animal. If the images are taken in artificial environments, like a lab or manufacturing line, or from diagnostic equipment, like x-rays or quality-control cameras, use Integrated Gradients instead.
GoogleCloudAiplatformV1ExplanationParametersResponse, GoogleCloudAiplatformV1ExplanationParametersResponseArgs
- Examples
Pulumi.
Google Native. Aiplatform. V1. Inputs. Google Cloud Aiplatform V1Examples Response - Example-based explanations that returns the nearest neighbors from the provided dataset.
- Integrated
Gradients Pulumi.Attribution Google Native. Aiplatform. V1. Inputs. Google Cloud Aiplatform V1Integrated Gradients Attribution Response - An attribution method that computes Aumann-Shapley values taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1703.01365
- Output
Indices List<object> - If populated, only returns attributions that have output_index contained in output_indices. It must be an ndarray of integers, with the same shape of the output it's explaining. If not populated, returns attributions for top_k indices of outputs. If neither top_k nor output_indices is populated, returns the argmax index of the outputs. Only applicable to Models that predict multiple outputs (e,g, multi-class Models that predict multiple classes).
- Sampled
Shapley Pulumi.Attribution Google Native. Aiplatform. V1. Inputs. Google Cloud Aiplatform V1Sampled Shapley Attribution Response - An attribution method that approximates Shapley values for features that contribute to the label being predicted. A sampling strategy is used to approximate the value rather than considering all subsets of features. Refer to this paper for model details: https://arxiv.org/abs/1306.4265.
- Top
K int - If populated, returns attributions for top K indices of outputs (defaults to 1). Only applies to Models that predicts more than one outputs (e,g, multi-class Models). When set to -1, returns explanations for all outputs.
- Xrai
Attribution Pulumi.Google Native. Aiplatform. V1. Inputs. Google Cloud Aiplatform V1Xrai Attribution Response - An attribution method that redistributes Integrated Gradients attribution to segmented regions, taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1906.02825 XRAI currently performs better on natural images, like a picture of a house or an animal. If the images are taken in artificial environments, like a lab or manufacturing line, or from diagnostic equipment, like x-rays or quality-control cameras, use Integrated Gradients instead.
- Examples
Google
Cloud Aiplatform V1Examples Response - Example-based explanations that returns the nearest neighbors from the provided dataset.
- Integrated
Gradients GoogleAttribution Cloud Aiplatform V1Integrated Gradients Attribution Response - An attribution method that computes Aumann-Shapley values taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1703.01365
- Output
Indices []interface{} - If populated, only returns attributions that have output_index contained in output_indices. It must be an ndarray of integers, with the same shape of the output it's explaining. If not populated, returns attributions for top_k indices of outputs. If neither top_k nor output_indices is populated, returns the argmax index of the outputs. Only applicable to Models that predict multiple outputs (e,g, multi-class Models that predict multiple classes).
- Sampled
Shapley GoogleAttribution Cloud Aiplatform V1Sampled Shapley Attribution Response - An attribution method that approximates Shapley values for features that contribute to the label being predicted. A sampling strategy is used to approximate the value rather than considering all subsets of features. Refer to this paper for model details: https://arxiv.org/abs/1306.4265.
- Top
K int - If populated, returns attributions for top K indices of outputs (defaults to 1). Only applies to Models that predicts more than one outputs (e,g, multi-class Models). When set to -1, returns explanations for all outputs.
- Xrai
Attribution GoogleCloud Aiplatform V1Xrai Attribution Response - An attribution method that redistributes Integrated Gradients attribution to segmented regions, taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1906.02825 XRAI currently performs better on natural images, like a picture of a house or an animal. If the images are taken in artificial environments, like a lab or manufacturing line, or from diagnostic equipment, like x-rays or quality-control cameras, use Integrated Gradients instead.
- examples
Google
Cloud Aiplatform V1Examples Response - Example-based explanations that returns the nearest neighbors from the provided dataset.
- integrated
Gradients GoogleAttribution Cloud Aiplatform V1Integrated Gradients Attribution Response - An attribution method that computes Aumann-Shapley values taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1703.01365
- output
Indices List<Object> - If populated, only returns attributions that have output_index contained in output_indices. It must be an ndarray of integers, with the same shape of the output it's explaining. If not populated, returns attributions for top_k indices of outputs. If neither top_k nor output_indices is populated, returns the argmax index of the outputs. Only applicable to Models that predict multiple outputs (e,g, multi-class Models that predict multiple classes).
- sampled
Shapley GoogleAttribution Cloud Aiplatform V1Sampled Shapley Attribution Response - An attribution method that approximates Shapley values for features that contribute to the label being predicted. A sampling strategy is used to approximate the value rather than considering all subsets of features. Refer to this paper for model details: https://arxiv.org/abs/1306.4265.
- top
K Integer - If populated, returns attributions for top K indices of outputs (defaults to 1). Only applies to Models that predicts more than one outputs (e,g, multi-class Models). When set to -1, returns explanations for all outputs.
- xrai
Attribution GoogleCloud Aiplatform V1Xrai Attribution Response - An attribution method that redistributes Integrated Gradients attribution to segmented regions, taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1906.02825 XRAI currently performs better on natural images, like a picture of a house or an animal. If the images are taken in artificial environments, like a lab or manufacturing line, or from diagnostic equipment, like x-rays or quality-control cameras, use Integrated Gradients instead.
- examples
Google
Cloud Aiplatform V1Examples Response - Example-based explanations that returns the nearest neighbors from the provided dataset.
- integrated
Gradients GoogleAttribution Cloud Aiplatform V1Integrated Gradients Attribution Response - An attribution method that computes Aumann-Shapley values taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1703.01365
- output
Indices any[] - If populated, only returns attributions that have output_index contained in output_indices. It must be an ndarray of integers, with the same shape of the output it's explaining. If not populated, returns attributions for top_k indices of outputs. If neither top_k nor output_indices is populated, returns the argmax index of the outputs. Only applicable to Models that predict multiple outputs (e,g, multi-class Models that predict multiple classes).
- sampled
Shapley GoogleAttribution Cloud Aiplatform V1Sampled Shapley Attribution Response - An attribution method that approximates Shapley values for features that contribute to the label being predicted. A sampling strategy is used to approximate the value rather than considering all subsets of features. Refer to this paper for model details: https://arxiv.org/abs/1306.4265.
- top
K number - If populated, returns attributions for top K indices of outputs (defaults to 1). Only applies to Models that predicts more than one outputs (e,g, multi-class Models). When set to -1, returns explanations for all outputs.
- xrai
Attribution GoogleCloud Aiplatform V1Xrai Attribution Response - An attribution method that redistributes Integrated Gradients attribution to segmented regions, taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1906.02825 XRAI currently performs better on natural images, like a picture of a house or an animal. If the images are taken in artificial environments, like a lab or manufacturing line, or from diagnostic equipment, like x-rays or quality-control cameras, use Integrated Gradients instead.
- examples
Google
Cloud Aiplatform V1Examples Response - Example-based explanations that returns the nearest neighbors from the provided dataset.
- integrated_
gradients_ Googleattribution Cloud Aiplatform V1Integrated Gradients Attribution Response - An attribution method that computes Aumann-Shapley values taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1703.01365
- output_
indices Sequence[Any] - If populated, only returns attributions that have output_index contained in output_indices. It must be an ndarray of integers, with the same shape of the output it's explaining. If not populated, returns attributions for top_k indices of outputs. If neither top_k nor output_indices is populated, returns the argmax index of the outputs. Only applicable to Models that predict multiple outputs (e,g, multi-class Models that predict multiple classes).
- sampled_
shapley_ Googleattribution Cloud Aiplatform V1Sampled Shapley Attribution Response - An attribution method that approximates Shapley values for features that contribute to the label being predicted. A sampling strategy is used to approximate the value rather than considering all subsets of features. Refer to this paper for model details: https://arxiv.org/abs/1306.4265.
- top_
k int - If populated, returns attributions for top K indices of outputs (defaults to 1). Only applies to Models that predicts more than one outputs (e,g, multi-class Models). When set to -1, returns explanations for all outputs.
- xrai_
attribution GoogleCloud Aiplatform V1Xrai Attribution Response - An attribution method that redistributes Integrated Gradients attribution to segmented regions, taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1906.02825 XRAI currently performs better on natural images, like a picture of a house or an animal. If the images are taken in artificial environments, like a lab or manufacturing line, or from diagnostic equipment, like x-rays or quality-control cameras, use Integrated Gradients instead.
- examples Property Map
- Example-based explanations that returns the nearest neighbors from the provided dataset.
- integrated
Gradients Property MapAttribution - An attribution method that computes Aumann-Shapley values taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1703.01365
- output
Indices List<Any> - If populated, only returns attributions that have output_index contained in output_indices. It must be an ndarray of integers, with the same shape of the output it's explaining. If not populated, returns attributions for top_k indices of outputs. If neither top_k nor output_indices is populated, returns the argmax index of the outputs. Only applicable to Models that predict multiple outputs (e,g, multi-class Models that predict multiple classes).
- sampled
Shapley Property MapAttribution - An attribution method that approximates Shapley values for features that contribute to the label being predicted. A sampling strategy is used to approximate the value rather than considering all subsets of features. Refer to this paper for model details: https://arxiv.org/abs/1306.4265.
- top
K Number - If populated, returns attributions for top K indices of outputs (defaults to 1). Only applies to Models that predicts more than one outputs (e,g, multi-class Models). When set to -1, returns explanations for all outputs.
- xrai
Attribution Property Map - An attribution method that redistributes Integrated Gradients attribution to segmented regions, taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1906.02825 XRAI currently performs better on natural images, like a picture of a house or an animal. If the images are taken in artificial environments, like a lab or manufacturing line, or from diagnostic equipment, like x-rays or quality-control cameras, use Integrated Gradients instead.
GoogleCloudAiplatformV1ExplanationSpec, GoogleCloudAiplatformV1ExplanationSpecArgs
- Parameters
Pulumi.
Google Native. Aiplatform. V1. Inputs. Google Cloud Aiplatform V1Explanation Parameters - Parameters that configure explaining of the Model's predictions.
- Metadata
Pulumi.
Google Native. Aiplatform. V1. Inputs. Google Cloud Aiplatform V1Explanation Metadata - Optional. Metadata describing the Model's input and output for explanation.
- Parameters
Google
Cloud Aiplatform V1Explanation Parameters - Parameters that configure explaining of the Model's predictions.
- Metadata
Google
Cloud Aiplatform V1Explanation Metadata - Optional. Metadata describing the Model's input and output for explanation.
- parameters
Google
Cloud Aiplatform V1Explanation Parameters - Parameters that configure explaining of the Model's predictions.
- metadata
Google
Cloud Aiplatform V1Explanation Metadata - Optional. Metadata describing the Model's input and output for explanation.
- parameters
Google
Cloud Aiplatform V1Explanation Parameters - Parameters that configure explaining of the Model's predictions.
- metadata
Google
Cloud Aiplatform V1Explanation Metadata - Optional. Metadata describing the Model's input and output for explanation.
- parameters
Google
Cloud Aiplatform V1Explanation Parameters - Parameters that configure explaining of the Model's predictions.
- metadata
Google
Cloud Aiplatform V1Explanation Metadata - Optional. Metadata describing the Model's input and output for explanation.
- parameters Property Map
- Parameters that configure explaining of the Model's predictions.
- metadata Property Map
- Optional. Metadata describing the Model's input and output for explanation.
GoogleCloudAiplatformV1ExplanationSpecResponse, GoogleCloudAiplatformV1ExplanationSpecResponseArgs
- Metadata
Pulumi.
Google Native. Aiplatform. V1. Inputs. Google Cloud Aiplatform V1Explanation Metadata Response - Optional. Metadata describing the Model's input and output for explanation.
- Parameters
Pulumi.
Google Native. Aiplatform. V1. Inputs. Google Cloud Aiplatform V1Explanation Parameters Response - Parameters that configure explaining of the Model's predictions.
- Metadata
Google
Cloud Aiplatform V1Explanation Metadata Response - Optional. Metadata describing the Model's input and output for explanation.
- Parameters
Google
Cloud Aiplatform V1Explanation Parameters Response - Parameters that configure explaining of the Model's predictions.
- metadata
Google
Cloud Aiplatform V1Explanation Metadata Response - Optional. Metadata describing the Model's input and output for explanation.
- parameters
Google
Cloud Aiplatform V1Explanation Parameters Response - Parameters that configure explaining of the Model's predictions.
- metadata
Google
Cloud Aiplatform V1Explanation Metadata Response - Optional. Metadata describing the Model's input and output for explanation.
- parameters
Google
Cloud Aiplatform V1Explanation Parameters Response - Parameters that configure explaining of the Model's predictions.
- metadata
Google
Cloud Aiplatform V1Explanation Metadata Response - Optional. Metadata describing the Model's input and output for explanation.
- parameters
Google
Cloud Aiplatform V1Explanation Parameters Response - Parameters that configure explaining of the Model's predictions.
- metadata Property Map
- Optional. Metadata describing the Model's input and output for explanation.
- parameters Property Map
- Parameters that configure explaining of the Model's predictions.
GoogleCloudAiplatformV1FeatureNoiseSigma, GoogleCloudAiplatformV1FeatureNoiseSigmaArgs
- Noise
Sigma List<Pulumi.Google Native. Aiplatform. V1. Inputs. Google Cloud Aiplatform V1Feature Noise Sigma Noise Sigma For Feature> - Noise sigma per feature. No noise is added to features that are not set.
- Noise
Sigma []GoogleCloud Aiplatform V1Feature Noise Sigma Noise Sigma For Feature - Noise sigma per feature. No noise is added to features that are not set.
- noise
Sigma List<GoogleCloud Aiplatform V1Feature Noise Sigma Noise Sigma For Feature> - Noise sigma per feature. No noise is added to features that are not set.
- noise
Sigma GoogleCloud Aiplatform V1Feature Noise Sigma Noise Sigma For Feature[] - Noise sigma per feature. No noise is added to features that are not set.
- noise_
sigma Sequence[GoogleCloud Aiplatform V1Feature Noise Sigma Noise Sigma For Feature] - Noise sigma per feature. No noise is added to features that are not set.
- noise
Sigma List<Property Map> - Noise sigma per feature. No noise is added to features that are not set.
GoogleCloudAiplatformV1FeatureNoiseSigmaNoiseSigmaForFeature, GoogleCloudAiplatformV1FeatureNoiseSigmaNoiseSigmaForFeatureArgs
- Name string
- The name of the input feature for which noise sigma is provided. The features are defined in explanation metadata inputs.
- Sigma double
- This represents the standard deviation of the Gaussian kernel that will be used to add noise to the feature prior to computing gradients. Similar to noise_sigma but represents the noise added to the current feature. Defaults to 0.1.
- Name string
- The name of the input feature for which noise sigma is provided. The features are defined in explanation metadata inputs.
- Sigma float64
- This represents the standard deviation of the Gaussian kernel that will be used to add noise to the feature prior to computing gradients. Similar to noise_sigma but represents the noise added to the current feature. Defaults to 0.1.
- name String
- The name of the input feature for which noise sigma is provided. The features are defined in explanation metadata inputs.
- sigma Double
- This represents the standard deviation of the Gaussian kernel that will be used to add noise to the feature prior to computing gradients. Similar to noise_sigma but represents the noise added to the current feature. Defaults to 0.1.
- name string
- The name of the input feature for which noise sigma is provided. The features are defined in explanation metadata inputs.
- sigma number
- This represents the standard deviation of the Gaussian kernel that will be used to add noise to the feature prior to computing gradients. Similar to noise_sigma but represents the noise added to the current feature. Defaults to 0.1.
- name str
- The name of the input feature for which noise sigma is provided. The features are defined in explanation metadata inputs.
- sigma float
- This represents the standard deviation of the Gaussian kernel that will be used to add noise to the feature prior to computing gradients. Similar to noise_sigma but represents the noise added to the current feature. Defaults to 0.1.
- name String
- The name of the input feature for which noise sigma is provided. The features are defined in explanation metadata inputs.
- sigma Number
- This represents the standard deviation of the Gaussian kernel that will be used to add noise to the feature prior to computing gradients. Similar to noise_sigma but represents the noise added to the current feature. Defaults to 0.1.
GoogleCloudAiplatformV1FeatureNoiseSigmaNoiseSigmaForFeatureResponse, GoogleCloudAiplatformV1FeatureNoiseSigmaNoiseSigmaForFeatureResponseArgs
- Name string
- The name of the input feature for which noise sigma is provided. The features are defined in explanation metadata inputs.
- Sigma double
- This represents the standard deviation of the Gaussian kernel that will be used to add noise to the feature prior to computing gradients. Similar to noise_sigma but represents the noise added to the current feature. Defaults to 0.1.
- Name string
- The name of the input feature for which noise sigma is provided. The features are defined in explanation metadata inputs.
- Sigma float64
- This represents the standard deviation of the Gaussian kernel that will be used to add noise to the feature prior to computing gradients. Similar to noise_sigma but represents the noise added to the current feature. Defaults to 0.1.
- name String
- The name of the input feature for which noise sigma is provided. The features are defined in explanation metadata inputs.
- sigma Double
- This represents the standard deviation of the Gaussian kernel that will be used to add noise to the feature prior to computing gradients. Similar to noise_sigma but represents the noise added to the current feature. Defaults to 0.1.
- name string
- The name of the input feature for which noise sigma is provided. The features are defined in explanation metadata inputs.
- sigma number
- This represents the standard deviation of the Gaussian kernel that will be used to add noise to the feature prior to computing gradients. Similar to noise_sigma but represents the noise added to the current feature. Defaults to 0.1.
- name str
- The name of the input feature for which noise sigma is provided. The features are defined in explanation metadata inputs.
- sigma float
- This represents the standard deviation of the Gaussian kernel that will be used to add noise to the feature prior to computing gradients. Similar to noise_sigma but represents the noise added to the current feature. Defaults to 0.1.
- name String
- The name of the input feature for which noise sigma is provided. The features are defined in explanation metadata inputs.
- sigma Number
- This represents the standard deviation of the Gaussian kernel that will be used to add noise to the feature prior to computing gradients. Similar to noise_sigma but represents the noise added to the current feature. Defaults to 0.1.
GoogleCloudAiplatformV1FeatureNoiseSigmaResponse, GoogleCloudAiplatformV1FeatureNoiseSigmaResponseArgs
- Noise
Sigma List<Pulumi.Google Native. Aiplatform. V1. Inputs. Google Cloud Aiplatform V1Feature Noise Sigma Noise Sigma For Feature Response> - Noise sigma per feature. No noise is added to features that are not set.
- Noise
Sigma []GoogleCloud Aiplatform V1Feature Noise Sigma Noise Sigma For Feature Response - Noise sigma per feature. No noise is added to features that are not set.
- noise
Sigma List<GoogleCloud Aiplatform V1Feature Noise Sigma Noise Sigma For Feature Response> - Noise sigma per feature. No noise is added to features that are not set.
- noise
Sigma GoogleCloud Aiplatform V1Feature Noise Sigma Noise Sigma For Feature Response[] - Noise sigma per feature. No noise is added to features that are not set.
- noise_
sigma Sequence[GoogleCloud Aiplatform V1Feature Noise Sigma Noise Sigma For Feature Response] - Noise sigma per feature. No noise is added to features that are not set.
- noise
Sigma List<Property Map> - Noise sigma per feature. No noise is added to features that are not set.
GoogleCloudAiplatformV1GcsDestination, GoogleCloudAiplatformV1GcsDestinationArgs
- Output
Uri stringPrefix - Google Cloud Storage URI to output directory. If the uri doesn't end with '/', a '/' will be automatically appended. The directory is created if it doesn't exist.
- Output
Uri stringPrefix - Google Cloud Storage URI to output directory. If the uri doesn't end with '/', a '/' will be automatically appended. The directory is created if it doesn't exist.
- output
Uri StringPrefix - Google Cloud Storage URI to output directory. If the uri doesn't end with '/', a '/' will be automatically appended. The directory is created if it doesn't exist.
- output
Uri stringPrefix - Google Cloud Storage URI to output directory. If the uri doesn't end with '/', a '/' will be automatically appended. The directory is created if it doesn't exist.
- output_
uri_ strprefix - Google Cloud Storage URI to output directory. If the uri doesn't end with '/', a '/' will be automatically appended. The directory is created if it doesn't exist.
- output
Uri StringPrefix - Google Cloud Storage URI to output directory. If the uri doesn't end with '/', a '/' will be automatically appended. The directory is created if it doesn't exist.
GoogleCloudAiplatformV1GcsDestinationResponse, GoogleCloudAiplatformV1GcsDestinationResponseArgs
- Output
Uri stringPrefix - Google Cloud Storage URI to output directory. If the uri doesn't end with '/', a '/' will be automatically appended. The directory is created if it doesn't exist.
- Output
Uri stringPrefix - Google Cloud Storage URI to output directory. If the uri doesn't end with '/', a '/' will be automatically appended. The directory is created if it doesn't exist.
- output
Uri StringPrefix - Google Cloud Storage URI to output directory. If the uri doesn't end with '/', a '/' will be automatically appended. The directory is created if it doesn't exist.
- output
Uri stringPrefix - Google Cloud Storage URI to output directory. If the uri doesn't end with '/', a '/' will be automatically appended. The directory is created if it doesn't exist.
- output_
uri_ strprefix - Google Cloud Storage URI to output directory. If the uri doesn't end with '/', a '/' will be automatically appended. The directory is created if it doesn't exist.
- output
Uri StringPrefix - Google Cloud Storage URI to output directory. If the uri doesn't end with '/', a '/' will be automatically appended. The directory is created if it doesn't exist.
GoogleCloudAiplatformV1GcsSource, GoogleCloudAiplatformV1GcsSourceArgs
- Uris List<string>
- Google Cloud Storage URI(-s) to the input file(s). May contain wildcards. For more information on wildcards, see https://cloud.google.com/storage/docs/gsutil/addlhelp/WildcardNames.
- Uris []string
- Google Cloud Storage URI(-s) to the input file(s). May contain wildcards. For more information on wildcards, see https://cloud.google.com/storage/docs/gsutil/addlhelp/WildcardNames.
- uris List<String>
- Google Cloud Storage URI(-s) to the input file(s). May contain wildcards. For more information on wildcards, see https://cloud.google.com/storage/docs/gsutil/addlhelp/WildcardNames.
- uris string[]
- Google Cloud Storage URI(-s) to the input file(s). May contain wildcards. For more information on wildcards, see https://cloud.google.com/storage/docs/gsutil/addlhelp/WildcardNames.
- uris Sequence[str]
- Google Cloud Storage URI(-s) to the input file(s). May contain wildcards. For more information on wildcards, see https://cloud.google.com/storage/docs/gsutil/addlhelp/WildcardNames.
- uris List<String>
- Google Cloud Storage URI(-s) to the input file(s). May contain wildcards. For more information on wildcards, see https://cloud.google.com/storage/docs/gsutil/addlhelp/WildcardNames.
GoogleCloudAiplatformV1GcsSourceResponse, GoogleCloudAiplatformV1GcsSourceResponseArgs
- Uris List<string>
- Google Cloud Storage URI(-s) to the input file(s). May contain wildcards. For more information on wildcards, see https://cloud.google.com/storage/docs/gsutil/addlhelp/WildcardNames.
- Uris []string
- Google Cloud Storage URI(-s) to the input file(s). May contain wildcards. For more information on wildcards, see https://cloud.google.com/storage/docs/gsutil/addlhelp/WildcardNames.
- uris List<String>
- Google Cloud Storage URI(-s) to the input file(s). May contain wildcards. For more information on wildcards, see https://cloud.google.com/storage/docs/gsutil/addlhelp/WildcardNames.
- uris string[]
- Google Cloud Storage URI(-s) to the input file(s). May contain wildcards. For more information on wildcards, see https://cloud.google.com/storage/docs/gsutil/addlhelp/WildcardNames.
- uris Sequence[str]
- Google Cloud Storage URI(-s) to the input file(s). May contain wildcards. For more information on wildcards, see https://cloud.google.com/storage/docs/gsutil/addlhelp/WildcardNames.
- uris List<String>
- Google Cloud Storage URI(-s) to the input file(s). May contain wildcards. For more information on wildcards, see https://cloud.google.com/storage/docs/gsutil/addlhelp/WildcardNames.
GoogleCloudAiplatformV1IntegratedGradientsAttribution, GoogleCloudAiplatformV1IntegratedGradientsAttributionArgs
- Step
Count int - The number of steps for approximating the path integral. A good value to start is 50 and gradually increase until the sum to diff property is within the desired error range. Valid range of its value is [1, 100], inclusively.
- Blur
Baseline Pulumi.Config Google Native. Aiplatform. V1. Inputs. Google Cloud Aiplatform V1Blur Baseline Config - Config for IG with blur baseline. When enabled, a linear path from the maximally blurred image to the input image is created. Using a blurred baseline instead of zero (black image) is motivated by the BlurIG approach explained here: https://arxiv.org/abs/2004.03383
- Smooth
Grad Pulumi.Config Google Native. Aiplatform. V1. Inputs. Google Cloud Aiplatform V1Smooth Grad Config - Config for SmoothGrad approximation of gradients. When enabled, the gradients are approximated by averaging the gradients from noisy samples in the vicinity of the inputs. Adding noise can help improve the computed gradients. Refer to this paper for more details: https://arxiv.org/pdf/1706.03825.pdf
- Step
Count int - The number of steps for approximating the path integral. A good value to start is 50 and gradually increase until the sum to diff property is within the desired error range. Valid range of its value is [1, 100], inclusively.
- Blur
Baseline GoogleConfig Cloud Aiplatform V1Blur Baseline Config - Config for IG with blur baseline. When enabled, a linear path from the maximally blurred image to the input image is created. Using a blurred baseline instead of zero (black image) is motivated by the BlurIG approach explained here: https://arxiv.org/abs/2004.03383
- Smooth
Grad GoogleConfig Cloud Aiplatform V1Smooth Grad Config - Config for SmoothGrad approximation of gradients. When enabled, the gradients are approximated by averaging the gradients from noisy samples in the vicinity of the inputs. Adding noise can help improve the computed gradients. Refer to this paper for more details: https://arxiv.org/pdf/1706.03825.pdf
- step
Count Integer - The number of steps for approximating the path integral. A good value to start is 50 and gradually increase until the sum to diff property is within the desired error range. Valid range of its value is [1, 100], inclusively.
- blur
Baseline GoogleConfig Cloud Aiplatform V1Blur Baseline Config - Config for IG with blur baseline. When enabled, a linear path from the maximally blurred image to the input image is created. Using a blurred baseline instead of zero (black image) is motivated by the BlurIG approach explained here: https://arxiv.org/abs/2004.03383
- smooth
Grad GoogleConfig Cloud Aiplatform V1Smooth Grad Config - Config for SmoothGrad approximation of gradients. When enabled, the gradients are approximated by averaging the gradients from noisy samples in the vicinity of the inputs. Adding noise can help improve the computed gradients. Refer to this paper for more details: https://arxiv.org/pdf/1706.03825.pdf
- step
Count number - The number of steps for approximating the path integral. A good value to start is 50 and gradually increase until the sum to diff property is within the desired error range. Valid range of its value is [1, 100], inclusively.
- blur
Baseline GoogleConfig Cloud Aiplatform V1Blur Baseline Config - Config for IG with blur baseline. When enabled, a linear path from the maximally blurred image to the input image is created. Using a blurred baseline instead of zero (black image) is motivated by the BlurIG approach explained here: https://arxiv.org/abs/2004.03383
- smooth
Grad GoogleConfig Cloud Aiplatform V1Smooth Grad Config - Config for SmoothGrad approximation of gradients. When enabled, the gradients are approximated by averaging the gradients from noisy samples in the vicinity of the inputs. Adding noise can help improve the computed gradients. Refer to this paper for more details: https://arxiv.org/pdf/1706.03825.pdf
- step_
count int - The number of steps for approximating the path integral. A good value to start is 50 and gradually increase until the sum to diff property is within the desired error range. Valid range of its value is [1, 100], inclusively.
- blur_
baseline_ Googleconfig Cloud Aiplatform V1Blur Baseline Config - Config for IG with blur baseline. When enabled, a linear path from the maximally blurred image to the input image is created. Using a blurred baseline instead of zero (black image) is motivated by the BlurIG approach explained here: https://arxiv.org/abs/2004.03383
- smooth_
grad_ Googleconfig Cloud Aiplatform V1Smooth Grad Config - Config for SmoothGrad approximation of gradients. When enabled, the gradients are approximated by averaging the gradients from noisy samples in the vicinity of the inputs. Adding noise can help improve the computed gradients. Refer to this paper for more details: https://arxiv.org/pdf/1706.03825.pdf
- step
Count Number - The number of steps for approximating the path integral. A good value to start is 50 and gradually increase until the sum to diff property is within the desired error range. Valid range of its value is [1, 100], inclusively.
- blur
Baseline Property MapConfig - Config for IG with blur baseline. When enabled, a linear path from the maximally blurred image to the input image is created. Using a blurred baseline instead of zero (black image) is motivated by the BlurIG approach explained here: https://arxiv.org/abs/2004.03383
- smooth
Grad Property MapConfig - Config for SmoothGrad approximation of gradients. When enabled, the gradients are approximated by averaging the gradients from noisy samples in the vicinity of the inputs. Adding noise can help improve the computed gradients. Refer to this paper for more details: https://arxiv.org/pdf/1706.03825.pdf
GoogleCloudAiplatformV1IntegratedGradientsAttributionResponse, GoogleCloudAiplatformV1IntegratedGradientsAttributionResponseArgs
- Blur
Baseline Pulumi.Config Google Native. Aiplatform. V1. Inputs. Google Cloud Aiplatform V1Blur Baseline Config Response - Config for IG with blur baseline. When enabled, a linear path from the maximally blurred image to the input image is created. Using a blurred baseline instead of zero (black image) is motivated by the BlurIG approach explained here: https://arxiv.org/abs/2004.03383
- Smooth
Grad Pulumi.Config Google Native. Aiplatform. V1. Inputs. Google Cloud Aiplatform V1Smooth Grad Config Response - Config for SmoothGrad approximation of gradients. When enabled, the gradients are approximated by averaging the gradients from noisy samples in the vicinity of the inputs. Adding noise can help improve the computed gradients. Refer to this paper for more details: https://arxiv.org/pdf/1706.03825.pdf
- Step
Count int - The number of steps for approximating the path integral. A good value to start is 50 and gradually increase until the sum to diff property is within the desired error range. Valid range of its value is [1, 100], inclusively.
- Blur
Baseline GoogleConfig Cloud Aiplatform V1Blur Baseline Config Response - Config for IG with blur baseline. When enabled, a linear path from the maximally blurred image to the input image is created. Using a blurred baseline instead of zero (black image) is motivated by the BlurIG approach explained here: https://arxiv.org/abs/2004.03383
- Smooth
Grad GoogleConfig Cloud Aiplatform V1Smooth Grad Config Response - Config for SmoothGrad approximation of gradients. When enabled, the gradients are approximated by averaging the gradients from noisy samples in the vicinity of the inputs. Adding noise can help improve the computed gradients. Refer to this paper for more details: https://arxiv.org/pdf/1706.03825.pdf
- Step
Count int - The number of steps for approximating the path integral. A good value to start is 50 and gradually increase until the sum to diff property is within the desired error range. Valid range of its value is [1, 100], inclusively.
- blur
Baseline GoogleConfig Cloud Aiplatform V1Blur Baseline Config Response - Config for IG with blur baseline. When enabled, a linear path from the maximally blurred image to the input image is created. Using a blurred baseline instead of zero (black image) is motivated by the BlurIG approach explained here: https://arxiv.org/abs/2004.03383
- smooth
Grad GoogleConfig Cloud Aiplatform V1Smooth Grad Config Response - Config for SmoothGrad approximation of gradients. When enabled, the gradients are approximated by averaging the gradients from noisy samples in the vicinity of the inputs. Adding noise can help improve the computed gradients. Refer to this paper for more details: https://arxiv.org/pdf/1706.03825.pdf
- step
Count Integer - The number of steps for approximating the path integral. A good value to start is 50 and gradually increase until the sum to diff property is within the desired error range. Valid range of its value is [1, 100], inclusively.
- blur
Baseline GoogleConfig Cloud Aiplatform V1Blur Baseline Config Response - Config for IG with blur baseline. When enabled, a linear path from the maximally blurred image to the input image is created. Using a blurred baseline instead of zero (black image) is motivated by the BlurIG approach explained here: https://arxiv.org/abs/2004.03383
- smooth
Grad GoogleConfig Cloud Aiplatform V1Smooth Grad Config Response - Config for SmoothGrad approximation of gradients. When enabled, the gradients are approximated by averaging the gradients from noisy samples in the vicinity of the inputs. Adding noise can help improve the computed gradients. Refer to this paper for more details: https://arxiv.org/pdf/1706.03825.pdf
- step
Count number - The number of steps for approximating the path integral. A good value to start is 50 and gradually increase until the sum to diff property is within the desired error range. Valid range of its value is [1, 100], inclusively.
- blur_
baseline_ Googleconfig Cloud Aiplatform V1Blur Baseline Config Response - Config for IG with blur baseline. When enabled, a linear path from the maximally blurred image to the input image is created. Using a blurred baseline instead of zero (black image) is motivated by the BlurIG approach explained here: https://arxiv.org/abs/2004.03383
- smooth_
grad_ Googleconfig Cloud Aiplatform V1Smooth Grad Config Response - Config for SmoothGrad approximation of gradients. When enabled, the gradients are approximated by averaging the gradients from noisy samples in the vicinity of the inputs. Adding noise can help improve the computed gradients. Refer to this paper for more details: https://arxiv.org/pdf/1706.03825.pdf
- step_
count int - The number of steps for approximating the path integral. A good value to start is 50 and gradually increase until the sum to diff property is within the desired error range. Valid range of its value is [1, 100], inclusively.
- blur
Baseline Property MapConfig - Config for IG with blur baseline. When enabled, a linear path from the maximally blurred image to the input image is created. Using a blurred baseline instead of zero (black image) is motivated by the BlurIG approach explained here: https://arxiv.org/abs/2004.03383
- smooth
Grad Property MapConfig - Config for SmoothGrad approximation of gradients. When enabled, the gradients are approximated by averaging the gradients from noisy samples in the vicinity of the inputs. Adding noise can help improve the computed gradients. Refer to this paper for more details: https://arxiv.org/pdf/1706.03825.pdf
- step
Count Number - The number of steps for approximating the path integral. A good value to start is 50 and gradually increase until the sum to diff property is within the desired error range. Valid range of its value is [1, 100], inclusively.
GoogleCloudAiplatformV1MachineSpec, GoogleCloudAiplatformV1MachineSpecArgs
- Accelerator
Count int - The number of accelerators to attach to the machine.
- Accelerator
Type Pulumi.Google Native. Aiplatform. V1. Google Cloud Aiplatform V1Machine Spec Accelerator Type - Immutable. The type of accelerator(s) that may be attached to the machine as per accelerator_count.
- Machine
Type string - Immutable. The type of the machine. See the list of machine types supported for prediction See the list of machine types supported for custom training. For DeployedModel this field is optional, and the default value is
n1-standard-2
. For BatchPredictionJob or as part of WorkerPoolSpec this field is required. - Tpu
Topology string - Immutable. The topology of the TPUs. Corresponds to the TPU topologies available from GKE. (Example: tpu_topology: "2x2x1").
- Accelerator
Count int - The number of accelerators to attach to the machine.
- Accelerator
Type GoogleCloud Aiplatform V1Machine Spec Accelerator Type - Immutable. The type of accelerator(s) that may be attached to the machine as per accelerator_count.
- Machine
Type string - Immutable. The type of the machine. See the list of machine types supported for prediction See the list of machine types supported for custom training. For DeployedModel this field is optional, and the default value is
n1-standard-2
. For BatchPredictionJob or as part of WorkerPoolSpec this field is required. - Tpu
Topology string - Immutable. The topology of the TPUs. Corresponds to the TPU topologies available from GKE. (Example: tpu_topology: "2x2x1").
- accelerator
Count Integer - The number of accelerators to attach to the machine.
- accelerator
Type GoogleCloud Aiplatform V1Machine Spec Accelerator Type - Immutable. The type of accelerator(s) that may be attached to the machine as per accelerator_count.
- machine
Type String - Immutable. The type of the machine. See the list of machine types supported for prediction See the list of machine types supported for custom training. For DeployedModel this field is optional, and the default value is
n1-standard-2
. For BatchPredictionJob or as part of WorkerPoolSpec this field is required. - tpu
Topology String - Immutable. The topology of the TPUs. Corresponds to the TPU topologies available from GKE. (Example: tpu_topology: "2x2x1").
- accelerator
Count number - The number of accelerators to attach to the machine.
- accelerator
Type GoogleCloud Aiplatform V1Machine Spec Accelerator Type - Immutable. The type of accelerator(s) that may be attached to the machine as per accelerator_count.
- machine
Type string - Immutable. The type of the machine. See the list of machine types supported for prediction See the list of machine types supported for custom training. For DeployedModel this field is optional, and the default value is
n1-standard-2
. For BatchPredictionJob or as part of WorkerPoolSpec this field is required. - tpu
Topology string - Immutable. The topology of the TPUs. Corresponds to the TPU topologies available from GKE. (Example: tpu_topology: "2x2x1").
- accelerator_
count int - The number of accelerators to attach to the machine.
- accelerator_
type GoogleCloud Aiplatform V1Machine Spec Accelerator Type - Immutable. The type of accelerator(s) that may be attached to the machine as per accelerator_count.
- machine_
type str - Immutable. The type of the machine. See the list of machine types supported for prediction See the list of machine types supported for custom training. For DeployedModel this field is optional, and the default value is
n1-standard-2
. For BatchPredictionJob or as part of WorkerPoolSpec this field is required. - tpu_
topology str - Immutable. The topology of the TPUs. Corresponds to the TPU topologies available from GKE. (Example: tpu_topology: "2x2x1").
- accelerator
Count Number - The number of accelerators to attach to the machine.
- accelerator
Type "ACCELERATOR_TYPE_UNSPECIFIED" | "NVIDIA_TESLA_K80" | "NVIDIA_TESLA_P100" | "NVIDIA_TESLA_V100" | "NVIDIA_TESLA_P4" | "NVIDIA_TESLA_T4" | "NVIDIA_TESLA_A100" | "NVIDIA_A100_80GB" | "NVIDIA_L4" | "TPU_V2" | "TPU_V3" | "TPU_V4_POD" - Immutable. The type of accelerator(s) that may be attached to the machine as per accelerator_count.
- machine
Type String - Immutable. The type of the machine. See the list of machine types supported for prediction See the list of machine types supported for custom training. For DeployedModel this field is optional, and the default value is
n1-standard-2
. For BatchPredictionJob or as part of WorkerPoolSpec this field is required. - tpu
Topology String - Immutable. The topology of the TPUs. Corresponds to the TPU topologies available from GKE. (Example: tpu_topology: "2x2x1").
GoogleCloudAiplatformV1MachineSpecAcceleratorType, GoogleCloudAiplatformV1MachineSpecAcceleratorTypeArgs
- Accelerator
Type Unspecified - ACCELERATOR_TYPE_UNSPECIFIEDUnspecified accelerator type, which means no accelerator.
- Nvidia
Tesla K80 - NVIDIA_TESLA_K80Nvidia Tesla K80 GPU.
- Nvidia
Tesla P100 - NVIDIA_TESLA_P100Nvidia Tesla P100 GPU.
- Nvidia
Tesla V100 - NVIDIA_TESLA_V100Nvidia Tesla V100 GPU.
- Nvidia
Tesla P4 - NVIDIA_TESLA_P4Nvidia Tesla P4 GPU.
- Nvidia
Tesla T4 - NVIDIA_TESLA_T4Nvidia Tesla T4 GPU.
- Nvidia
Tesla A100 - NVIDIA_TESLA_A100Nvidia Tesla A100 GPU.
- Nvidia
A10080gb - NVIDIA_A100_80GBNvidia A100 80GB GPU.
- Nvidia
L4 - NVIDIA_L4Nvidia L4 GPU.
- Tpu
V2 - TPU_V2TPU v2.
- Tpu
V3 - TPU_V3TPU v3.
- Tpu
V4Pod - TPU_V4_PODTPU v4.
- Google
Cloud Aiplatform V1Machine Spec Accelerator Type Accelerator Type Unspecified - ACCELERATOR_TYPE_UNSPECIFIEDUnspecified accelerator type, which means no accelerator.
- Google
Cloud Aiplatform V1Machine Spec Accelerator Type Nvidia Tesla K80 - NVIDIA_TESLA_K80Nvidia Tesla K80 GPU.
- Google
Cloud Aiplatform V1Machine Spec Accelerator Type Nvidia Tesla P100 - NVIDIA_TESLA_P100Nvidia Tesla P100 GPU.
- Google
Cloud Aiplatform V1Machine Spec Accelerator Type Nvidia Tesla V100 - NVIDIA_TESLA_V100Nvidia Tesla V100 GPU.
- Google
Cloud Aiplatform V1Machine Spec Accelerator Type Nvidia Tesla P4 - NVIDIA_TESLA_P4Nvidia Tesla P4 GPU.
- Google
Cloud Aiplatform V1Machine Spec Accelerator Type Nvidia Tesla T4 - NVIDIA_TESLA_T4Nvidia Tesla T4 GPU.
- Google
Cloud Aiplatform V1Machine Spec Accelerator Type Nvidia Tesla A100 - NVIDIA_TESLA_A100Nvidia Tesla A100 GPU.
- Google
Cloud Aiplatform V1Machine Spec Accelerator Type Nvidia A10080gb - NVIDIA_A100_80GBNvidia A100 80GB GPU.
- Google
Cloud Aiplatform V1Machine Spec Accelerator Type Nvidia L4 - NVIDIA_L4Nvidia L4 GPU.
- Google
Cloud Aiplatform V1Machine Spec Accelerator Type Tpu V2 - TPU_V2TPU v2.
- Google
Cloud Aiplatform V1Machine Spec Accelerator Type Tpu V3 - TPU_V3TPU v3.
- Google
Cloud Aiplatform V1Machine Spec Accelerator Type Tpu V4Pod - TPU_V4_PODTPU v4.
- Accelerator
Type Unspecified - ACCELERATOR_TYPE_UNSPECIFIEDUnspecified accelerator type, which means no accelerator.
- Nvidia
Tesla K80 - NVIDIA_TESLA_K80Nvidia Tesla K80 GPU.
- Nvidia
Tesla P100 - NVIDIA_TESLA_P100Nvidia Tesla P100 GPU.
- Nvidia
Tesla V100 - NVIDIA_TESLA_V100Nvidia Tesla V100 GPU.
- Nvidia
Tesla P4 - NVIDIA_TESLA_P4Nvidia Tesla P4 GPU.
- Nvidia
Tesla T4 - NVIDIA_TESLA_T4Nvidia Tesla T4 GPU.
- Nvidia
Tesla A100 - NVIDIA_TESLA_A100Nvidia Tesla A100 GPU.
- Nvidia
A10080gb - NVIDIA_A100_80GBNvidia A100 80GB GPU.
- Nvidia
L4 - NVIDIA_L4Nvidia L4 GPU.
- Tpu
V2 - TPU_V2TPU v2.
- Tpu
V3 - TPU_V3TPU v3.
- Tpu
V4Pod - TPU_V4_PODTPU v4.
- Accelerator
Type Unspecified - ACCELERATOR_TYPE_UNSPECIFIEDUnspecified accelerator type, which means no accelerator.
- Nvidia
Tesla K80 - NVIDIA_TESLA_K80Nvidia Tesla K80 GPU.
- Nvidia
Tesla P100 - NVIDIA_TESLA_P100Nvidia Tesla P100 GPU.
- Nvidia
Tesla V100 - NVIDIA_TESLA_V100Nvidia Tesla V100 GPU.
- Nvidia
Tesla P4 - NVIDIA_TESLA_P4Nvidia Tesla P4 GPU.
- Nvidia
Tesla T4 - NVIDIA_TESLA_T4Nvidia Tesla T4 GPU.
- Nvidia
Tesla A100 - NVIDIA_TESLA_A100Nvidia Tesla A100 GPU.
- Nvidia
A10080gb - NVIDIA_A100_80GBNvidia A100 80GB GPU.
- Nvidia
L4 - NVIDIA_L4Nvidia L4 GPU.
- Tpu
V2 - TPU_V2TPU v2.
- Tpu
V3 - TPU_V3TPU v3.
- Tpu
V4Pod - TPU_V4_PODTPU v4.
- ACCELERATOR_TYPE_UNSPECIFIED
- ACCELERATOR_TYPE_UNSPECIFIEDUnspecified accelerator type, which means no accelerator.
- NVIDIA_TESLA_K80
- NVIDIA_TESLA_K80Nvidia Tesla K80 GPU.
- NVIDIA_TESLA_P100
- NVIDIA_TESLA_P100Nvidia Tesla P100 GPU.
- NVIDIA_TESLA_V100
- NVIDIA_TESLA_V100Nvidia Tesla V100 GPU.
- NVIDIA_TESLA_P4
- NVIDIA_TESLA_P4Nvidia Tesla P4 GPU.
- NVIDIA_TESLA_T4
- NVIDIA_TESLA_T4Nvidia Tesla T4 GPU.
- NVIDIA_TESLA_A100
- NVIDIA_TESLA_A100Nvidia Tesla A100 GPU.
- NVIDIA_A10080GB
- NVIDIA_A100_80GBNvidia A100 80GB GPU.
- NVIDIA_L4
- NVIDIA_L4Nvidia L4 GPU.
- TPU_V2
- TPU_V2TPU v2.
- TPU_V3
- TPU_V3TPU v3.
- TPU_V4_POD
- TPU_V4_PODTPU v4.
- "ACCELERATOR_TYPE_UNSPECIFIED"
- ACCELERATOR_TYPE_UNSPECIFIEDUnspecified accelerator type, which means no accelerator.
- "NVIDIA_TESLA_K80"
- NVIDIA_TESLA_K80Nvidia Tesla K80 GPU.
- "NVIDIA_TESLA_P100"
- NVIDIA_TESLA_P100Nvidia Tesla P100 GPU.
- "NVIDIA_TESLA_V100"
- NVIDIA_TESLA_V100Nvidia Tesla V100 GPU.
- "NVIDIA_TESLA_P4"
- NVIDIA_TESLA_P4Nvidia Tesla P4 GPU.
- "NVIDIA_TESLA_T4"
- NVIDIA_TESLA_T4Nvidia Tesla T4 GPU.
- "NVIDIA_TESLA_A100"
- NVIDIA_TESLA_A100Nvidia Tesla A100 GPU.
- "NVIDIA_A100_80GB"
- NVIDIA_A100_80GBNvidia A100 80GB GPU.
- "NVIDIA_L4"
- NVIDIA_L4Nvidia L4 GPU.
- "TPU_V2"
- TPU_V2TPU v2.
- "TPU_V3"
- TPU_V3TPU v3.
- "TPU_V4_POD"
- TPU_V4_PODTPU v4.
GoogleCloudAiplatformV1MachineSpecResponse, GoogleCloudAiplatformV1MachineSpecResponseArgs
- Accelerator
Count int - The number of accelerators to attach to the machine.
- Accelerator
Type string - Immutable. The type of accelerator(s) that may be attached to the machine as per accelerator_count.
- Machine
Type string - Immutable. The type of the machine. See the list of machine types supported for prediction See the list of machine types supported for custom training. For DeployedModel this field is optional, and the default value is
n1-standard-2
. For BatchPredictionJob or as part of WorkerPoolSpec this field is required. - Tpu
Topology string - Immutable. The topology of the TPUs. Corresponds to the TPU topologies available from GKE. (Example: tpu_topology: "2x2x1").
- Accelerator
Count int - The number of accelerators to attach to the machine.
- Accelerator
Type string - Immutable. The type of accelerator(s) that may be attached to the machine as per accelerator_count.
- Machine
Type string - Immutable. The type of the machine. See the list of machine types supported for prediction See the list of machine types supported for custom training. For DeployedModel this field is optional, and the default value is
n1-standard-2
. For BatchPredictionJob or as part of WorkerPoolSpec this field is required. - Tpu
Topology string - Immutable. The topology of the TPUs. Corresponds to the TPU topologies available from GKE. (Example: tpu_topology: "2x2x1").
- accelerator
Count Integer - The number of accelerators to attach to the machine.
- accelerator
Type String - Immutable. The type of accelerator(s) that may be attached to the machine as per accelerator_count.
- machine
Type String - Immutable. The type of the machine. See the list of machine types supported for prediction See the list of machine types supported for custom training. For DeployedModel this field is optional, and the default value is
n1-standard-2
. For BatchPredictionJob or as part of WorkerPoolSpec this field is required. - tpu
Topology String - Immutable. The topology of the TPUs. Corresponds to the TPU topologies available from GKE. (Example: tpu_topology: "2x2x1").
- accelerator
Count number - The number of accelerators to attach to the machine.
- accelerator
Type string - Immutable. The type of accelerator(s) that may be attached to the machine as per accelerator_count.
- machine
Type string - Immutable. The type of the machine. See the list of machine types supported for prediction See the list of machine types supported for custom training. For DeployedModel this field is optional, and the default value is
n1-standard-2
. For BatchPredictionJob or as part of WorkerPoolSpec this field is required. - tpu
Topology string - Immutable. The topology of the TPUs. Corresponds to the TPU topologies available from GKE. (Example: tpu_topology: "2x2x1").
- accelerator_
count int - The number of accelerators to attach to the machine.
- accelerator_
type str - Immutable. The type of accelerator(s) that may be attached to the machine as per accelerator_count.
- machine_
type str - Immutable. The type of the machine. See the list of machine types supported for prediction See the list of machine types supported for custom training. For DeployedModel this field is optional, and the default value is
n1-standard-2
. For BatchPredictionJob or as part of WorkerPoolSpec this field is required. - tpu_
topology str - Immutable. The topology of the TPUs. Corresponds to the TPU topologies available from GKE. (Example: tpu_topology: "2x2x1").
- accelerator
Count Number - The number of accelerators to attach to the machine.
- accelerator
Type String - Immutable. The type of accelerator(s) that may be attached to the machine as per accelerator_count.
- machine
Type String - Immutable. The type of the machine. See the list of machine types supported for prediction See the list of machine types supported for custom training. For DeployedModel this field is optional, and the default value is
n1-standard-2
. For BatchPredictionJob or as part of WorkerPoolSpec this field is required. - tpu
Topology String - Immutable. The topology of the TPUs. Corresponds to the TPU topologies available from GKE. (Example: tpu_topology: "2x2x1").
GoogleCloudAiplatformV1ManualBatchTuningParameters, GoogleCloudAiplatformV1ManualBatchTuningParametersArgs
- Batch
Size int - Immutable. The number of the records (e.g. instances) of the operation given in each batch to a machine replica. Machine type, and size of a single record should be considered when setting this parameter, higher value speeds up the batch operation's execution, but too high value will result in a whole batch not fitting in a machine's memory, and the whole operation will fail. The default value is 64.
- Batch
Size int - Immutable. The number of the records (e.g. instances) of the operation given in each batch to a machine replica. Machine type, and size of a single record should be considered when setting this parameter, higher value speeds up the batch operation's execution, but too high value will result in a whole batch not fitting in a machine's memory, and the whole operation will fail. The default value is 64.
- batch
Size Integer - Immutable. The number of the records (e.g. instances) of the operation given in each batch to a machine replica. Machine type, and size of a single record should be considered when setting this parameter, higher value speeds up the batch operation's execution, but too high value will result in a whole batch not fitting in a machine's memory, and the whole operation will fail. The default value is 64.
- batch
Size number - Immutable. The number of the records (e.g. instances) of the operation given in each batch to a machine replica. Machine type, and size of a single record should be considered when setting this parameter, higher value speeds up the batch operation's execution, but too high value will result in a whole batch not fitting in a machine's memory, and the whole operation will fail. The default value is 64.
- batch_
size int - Immutable. The number of the records (e.g. instances) of the operation given in each batch to a machine replica. Machine type, and size of a single record should be considered when setting this parameter, higher value speeds up the batch operation's execution, but too high value will result in a whole batch not fitting in a machine's memory, and the whole operation will fail. The default value is 64.
- batch
Size Number - Immutable. The number of the records (e.g. instances) of the operation given in each batch to a machine replica. Machine type, and size of a single record should be considered when setting this parameter, higher value speeds up the batch operation's execution, but too high value will result in a whole batch not fitting in a machine's memory, and the whole operation will fail. The default value is 64.
GoogleCloudAiplatformV1ManualBatchTuningParametersResponse, GoogleCloudAiplatformV1ManualBatchTuningParametersResponseArgs
- Batch
Size int - Immutable. The number of the records (e.g. instances) of the operation given in each batch to a machine replica. Machine type, and size of a single record should be considered when setting this parameter, higher value speeds up the batch operation's execution, but too high value will result in a whole batch not fitting in a machine's memory, and the whole operation will fail. The default value is 64.
- Batch
Size int - Immutable. The number of the records (e.g. instances) of the operation given in each batch to a machine replica. Machine type, and size of a single record should be considered when setting this parameter, higher value speeds up the batch operation's execution, but too high value will result in a whole batch not fitting in a machine's memory, and the whole operation will fail. The default value is 64.
- batch
Size Integer - Immutable. The number of the records (e.g. instances) of the operation given in each batch to a machine replica. Machine type, and size of a single record should be considered when setting this parameter, higher value speeds up the batch operation's execution, but too high value will result in a whole batch not fitting in a machine's memory, and the whole operation will fail. The default value is 64.
- batch
Size number - Immutable. The number of the records (e.g. instances) of the operation given in each batch to a machine replica. Machine type, and size of a single record should be considered when setting this parameter, higher value speeds up the batch operation's execution, but too high value will result in a whole batch not fitting in a machine's memory, and the whole operation will fail. The default value is 64.
- batch_
size int - Immutable. The number of the records (e.g. instances) of the operation given in each batch to a machine replica. Machine type, and size of a single record should be considered when setting this parameter, higher value speeds up the batch operation's execution, but too high value will result in a whole batch not fitting in a machine's memory, and the whole operation will fail. The default value is 64.
- batch
Size Number - Immutable. The number of the records (e.g. instances) of the operation given in each batch to a machine replica. Machine type, and size of a single record should be considered when setting this parameter, higher value speeds up the batch operation's execution, but too high value will result in a whole batch not fitting in a machine's memory, and the whole operation will fail. The default value is 64.
GoogleCloudAiplatformV1ModelContainerSpec, GoogleCloudAiplatformV1ModelContainerSpecArgs
- Image
Uri string - Immutable. URI of the Docker image to be used as the custom container for serving predictions. This URI must identify an image in Artifact Registry or Container Registry. Learn more about the container publishing requirements, including permissions requirements for the Vertex AI Service Agent. The container image is ingested upon ModelService.UploadModel, stored internally, and this original path is afterwards not used. To learn about the requirements for the Docker image itself, see Custom container requirements. You can use the URI to one of Vertex AI's pre-built container images for prediction in this field.
- Args List<string>
- Immutable. Specifies arguments for the command that runs when the container starts. This overrides the container's
CMD
. Specify this field as an array of executable and arguments, similar to a DockerCMD
's "default parameters" form. If you don't specify this field but do specify the command field, then the command from thecommand
field runs without any additional arguments. See the Kubernetes documentation about how thecommand
andargs
fields interact with a container'sENTRYPOINT
andCMD
. If you don't specify this field and don't specify thecommand
field, then the container'sENTRYPOINT
andCMD
determine what runs based on their default behavior. See the Docker documentation about howCMD
andENTRYPOINT
interact. In this field, you can reference environment variables set by Vertex AI and environment variables set in the env field. You cannot reference environment variables set in the Docker image. In order for environment variables to be expanded, reference them by using the following syntax: $( VARIABLE_NAME) Note that this differs from Bash variable expansion, which does not use parentheses. If a variable cannot be resolved, the reference in the input string is used unchanged. To avoid variable expansion, you can escape this syntax with$$
; for example: $$(VARIABLE_NAME) This field corresponds to theargs
field of the Kubernetes Containers v1 core API. - Command List<string>
- Immutable. Specifies the command that runs when the container starts. This overrides the container's ENTRYPOINT. Specify this field as an array of executable and arguments, similar to a Docker
ENTRYPOINT
's "exec" form, not its "shell" form. If you do not specify this field, then the container'sENTRYPOINT
runs, in conjunction with the args field or the container'sCMD
, if either exists. If this field is not specified and the container does not have anENTRYPOINT
, then refer to the Docker documentation about howCMD
andENTRYPOINT
interact. If you specify this field, then you can also specify theargs
field to provide additional arguments for this command. However, if you specify this field, then the container'sCMD
is ignored. See the Kubernetes documentation about how thecommand
andargs
fields interact with a container'sENTRYPOINT
andCMD
. In this field, you can reference environment variables set by Vertex AI and environment variables set in the env field. You cannot reference environment variables set in the Docker image. In order for environment variables to be expanded, reference them by using the following syntax: $( VARIABLE_NAME) Note that this differs from Bash variable expansion, which does not use parentheses. If a variable cannot be resolved, the reference in the input string is used unchanged. To avoid variable expansion, you can escape this syntax with$$
; for example: $$(VARIABLE_NAME) This field corresponds to thecommand
field of the Kubernetes Containers v1 core API. - Deployment
Timeout string - Immutable. Deployment timeout. TODO (b/306244185): Revise documentation before exposing.
- Env
List<Pulumi.
Google Native. Aiplatform. V1. Inputs. Google Cloud Aiplatform V1Env Var> - Immutable. List of environment variables to set in the container. After the container starts running, code running in the container can read these environment variables. Additionally, the command and args fields can reference these variables. Later entries in this list can also reference earlier entries. For example, the following example sets the variable
VAR_2
to have the valuefoo bar
:json [ { "name": "VAR_1", "value": "foo" }, { "name": "VAR_2", "value": "$(VAR_1) bar" } ]
If you switch the order of the variables in the example, then the expansion does not occur. This field corresponds to theenv
field of the Kubernetes Containers v1 core API. - Health
Probe Pulumi.Google Native. Aiplatform. V1. Inputs. Google Cloud Aiplatform V1Probe - Immutable. Specification for Kubernetes readiness probe. TODO (b/306244185): Revise documentation before exposing.
- Health
Route string - Immutable. HTTP path on the container to send health checks to. Vertex AI intermittently sends GET requests to this path on the container's IP address and port to check that the container is healthy. Read more about health checks. For example, if you set this field to
/bar
, then Vertex AI intermittently sends a GET request to the/bar
path on the port of your container specified by the first value of thisModelContainerSpec
's ports field. If you don't specify this field, it defaults to the following value when you deploy this Model to an Endpoint: /v1/endpoints/ENDPOINT/deployedModels/ DEPLOYED_MODEL:predict The placeholders in this value are replaced as follows: * ENDPOINT: The last segment (followingendpoints/
)of the Endpoint.name][] field of the Endpoint where this Model has been deployed. (Vertex AI makes this value available to your container code as theAIP_ENDPOINT_ID
environment variable.) * DEPLOYED_MODEL: DeployedModel.id of theDeployedModel
. (Vertex AI makes this value available to your container code as theAIP_DEPLOYED_MODEL_ID
environment variable.) - Ports
List<Pulumi.
Google Native. Aiplatform. V1. Inputs. Google Cloud Aiplatform V1Port> - Immutable. List of ports to expose from the container. Vertex AI sends any prediction requests that it receives to the first port on this list. Vertex AI also sends liveness and health checks to this port. If you do not specify this field, it defaults to following value:
json [ { "containerPort": 8080 } ]
Vertex AI does not use ports other than the first one listed. This field corresponds to theports
field of the Kubernetes Containers v1 core API. - Predict
Route string - Immutable. HTTP path on the container to send prediction requests to. Vertex AI forwards requests sent using projects.locations.endpoints.predict to this path on the container's IP address and port. Vertex AI then returns the container's response in the API response. For example, if you set this field to
/foo
, then when Vertex AI receives a prediction request, it forwards the request body in a POST request to the/foo
path on the port of your container specified by the first value of thisModelContainerSpec
's ports field. If you don't specify this field, it defaults to the following value when you deploy this Model to an Endpoint: /v1/endpoints/ENDPOINT/deployedModels/DEPLOYED_MODEL:predict The placeholders in this value are replaced as follows: * ENDPOINT: The last segment (followingendpoints/
)of the Endpoint.name][] field of the Endpoint where this Model has been deployed. (Vertex AI makes this value available to your container code as theAIP_ENDPOINT_ID
environment variable.) * DEPLOYED_MODEL: DeployedModel.id of theDeployedModel
. (Vertex AI makes this value available to your container code as theAIP_DEPLOYED_MODEL_ID
environment variable.) - string
- Immutable. The amount of the VM memory to reserve as the shared memory for the model in megabytes. TODO (b/306244185): Revise documentation before exposing.
- Startup
Probe Pulumi.Google Native. Aiplatform. V1. Inputs. Google Cloud Aiplatform V1Probe - Immutable. Specification for Kubernetes startup probe. TODO (b/306244185): Revise documentation before exposing.
- Image
Uri string - Immutable. URI of the Docker image to be used as the custom container for serving predictions. This URI must identify an image in Artifact Registry or Container Registry. Learn more about the container publishing requirements, including permissions requirements for the Vertex AI Service Agent. The container image is ingested upon ModelService.UploadModel, stored internally, and this original path is afterwards not used. To learn about the requirements for the Docker image itself, see Custom container requirements. You can use the URI to one of Vertex AI's pre-built container images for prediction in this field.
- Args []string
- Immutable. Specifies arguments for the command that runs when the container starts. This overrides the container's
CMD
. Specify this field as an array of executable and arguments, similar to a DockerCMD
's "default parameters" form. If you don't specify this field but do specify the command field, then the command from thecommand
field runs without any additional arguments. See the Kubernetes documentation about how thecommand
andargs
fields interact with a container'sENTRYPOINT
andCMD
. If you don't specify this field and don't specify thecommand
field, then the container'sENTRYPOINT
andCMD
determine what runs based on their default behavior. See the Docker documentation about howCMD
andENTRYPOINT
interact. In this field, you can reference environment variables set by Vertex AI and environment variables set in the env field. You cannot reference environment variables set in the Docker image. In order for environment variables to be expanded, reference them by using the following syntax: $( VARIABLE_NAME) Note that this differs from Bash variable expansion, which does not use parentheses. If a variable cannot be resolved, the reference in the input string is used unchanged. To avoid variable expansion, you can escape this syntax with$$
; for example: $$(VARIABLE_NAME) This field corresponds to theargs
field of the Kubernetes Containers v1 core API. - Command []string
- Immutable. Specifies the command that runs when the container starts. This overrides the container's ENTRYPOINT. Specify this field as an array of executable and arguments, similar to a Docker
ENTRYPOINT
's "exec" form, not its "shell" form. If you do not specify this field, then the container'sENTRYPOINT
runs, in conjunction with the args field or the container'sCMD
, if either exists. If this field is not specified and the container does not have anENTRYPOINT
, then refer to the Docker documentation about howCMD
andENTRYPOINT
interact. If you specify this field, then you can also specify theargs
field to provide additional arguments for this command. However, if you specify this field, then the container'sCMD
is ignored. See the Kubernetes documentation about how thecommand
andargs
fields interact with a container'sENTRYPOINT
andCMD
. In this field, you can reference environment variables set by Vertex AI and environment variables set in the env field. You cannot reference environment variables set in the Docker image. In order for environment variables to be expanded, reference them by using the following syntax: $( VARIABLE_NAME) Note that this differs from Bash variable expansion, which does not use parentheses. If a variable cannot be resolved, the reference in the input string is used unchanged. To avoid variable expansion, you can escape this syntax with$$
; for example: $$(VARIABLE_NAME) This field corresponds to thecommand
field of the Kubernetes Containers v1 core API. - Deployment
Timeout string - Immutable. Deployment timeout. TODO (b/306244185): Revise documentation before exposing.
- Env
[]Google
Cloud Aiplatform V1Env Var - Immutable. List of environment variables to set in the container. After the container starts running, code running in the container can read these environment variables. Additionally, the command and args fields can reference these variables. Later entries in this list can also reference earlier entries. For example, the following example sets the variable
VAR_2
to have the valuefoo bar
:json [ { "name": "VAR_1", "value": "foo" }, { "name": "VAR_2", "value": "$(VAR_1) bar" } ]
If you switch the order of the variables in the example, then the expansion does not occur. This field corresponds to theenv
field of the Kubernetes Containers v1 core API. - Health
Probe GoogleCloud Aiplatform V1Probe - Immutable. Specification for Kubernetes readiness probe. TODO (b/306244185): Revise documentation before exposing.
- Health
Route string - Immutable. HTTP path on the container to send health checks to. Vertex AI intermittently sends GET requests to this path on the container's IP address and port to check that the container is healthy. Read more about health checks. For example, if you set this field to
/bar
, then Vertex AI intermittently sends a GET request to the/bar
path on the port of your container specified by the first value of thisModelContainerSpec
's ports field. If you don't specify this field, it defaults to the following value when you deploy this Model to an Endpoint: /v1/endpoints/ENDPOINT/deployedModels/ DEPLOYED_MODEL:predict The placeholders in this value are replaced as follows: * ENDPOINT: The last segment (followingendpoints/
)of the Endpoint.name][] field of the Endpoint where this Model has been deployed. (Vertex AI makes this value available to your container code as theAIP_ENDPOINT_ID
environment variable.) * DEPLOYED_MODEL: DeployedModel.id of theDeployedModel
. (Vertex AI makes this value available to your container code as theAIP_DEPLOYED_MODEL_ID
environment variable.) - Ports
[]Google
Cloud Aiplatform V1Port - Immutable. List of ports to expose from the container. Vertex AI sends any prediction requests that it receives to the first port on this list. Vertex AI also sends liveness and health checks to this port. If you do not specify this field, it defaults to following value:
json [ { "containerPort": 8080 } ]
Vertex AI does not use ports other than the first one listed. This field corresponds to theports
field of the Kubernetes Containers v1 core API. - Predict
Route string - Immutable. HTTP path on the container to send prediction requests to. Vertex AI forwards requests sent using projects.locations.endpoints.predict to this path on the container's IP address and port. Vertex AI then returns the container's response in the API response. For example, if you set this field to
/foo
, then when Vertex AI receives a prediction request, it forwards the request body in a POST request to the/foo
path on the port of your container specified by the first value of thisModelContainerSpec
's ports field. If you don't specify this field, it defaults to the following value when you deploy this Model to an Endpoint: /v1/endpoints/ENDPOINT/deployedModels/DEPLOYED_MODEL:predict The placeholders in this value are replaced as follows: * ENDPOINT: The last segment (followingendpoints/
)of the Endpoint.name][] field of the Endpoint where this Model has been deployed. (Vertex AI makes this value available to your container code as theAIP_ENDPOINT_ID
environment variable.) * DEPLOYED_MODEL: DeployedModel.id of theDeployedModel
. (Vertex AI makes this value available to your container code as theAIP_DEPLOYED_MODEL_ID
environment variable.) - string
- Immutable. The amount of the VM memory to reserve as the shared memory for the model in megabytes. TODO (b/306244185): Revise documentation before exposing.
- Startup
Probe GoogleCloud Aiplatform V1Probe - Immutable. Specification for Kubernetes startup probe. TODO (b/306244185): Revise documentation before exposing.
- image
Uri String - Immutable. URI of the Docker image to be used as the custom container for serving predictions. This URI must identify an image in Artifact Registry or Container Registry. Learn more about the container publishing requirements, including permissions requirements for the Vertex AI Service Agent. The container image is ingested upon ModelService.UploadModel, stored internally, and this original path is afterwards not used. To learn about the requirements for the Docker image itself, see Custom container requirements. You can use the URI to one of Vertex AI's pre-built container images for prediction in this field.
- args List<String>
- Immutable. Specifies arguments for the command that runs when the container starts. This overrides the container's
CMD
. Specify this field as an array of executable and arguments, similar to a DockerCMD
's "default parameters" form. If you don't specify this field but do specify the command field, then the command from thecommand
field runs without any additional arguments. See the Kubernetes documentation about how thecommand
andargs
fields interact with a container'sENTRYPOINT
andCMD
. If you don't specify this field and don't specify thecommand
field, then the container'sENTRYPOINT
andCMD
determine what runs based on their default behavior. See the Docker documentation about howCMD
andENTRYPOINT
interact. In this field, you can reference environment variables set by Vertex AI and environment variables set in the env field. You cannot reference environment variables set in the Docker image. In order for environment variables to be expanded, reference them by using the following syntax: $( VARIABLE_NAME) Note that this differs from Bash variable expansion, which does not use parentheses. If a variable cannot be resolved, the reference in the input string is used unchanged. To avoid variable expansion, you can escape this syntax with$$
; for example: $$(VARIABLE_NAME) This field corresponds to theargs
field of the Kubernetes Containers v1 core API. - command List<String>
- Immutable. Specifies the command that runs when the container starts. This overrides the container's ENTRYPOINT. Specify this field as an array of executable and arguments, similar to a Docker
ENTRYPOINT
's "exec" form, not its "shell" form. If you do not specify this field, then the container'sENTRYPOINT
runs, in conjunction with the args field or the container'sCMD
, if either exists. If this field is not specified and the container does not have anENTRYPOINT
, then refer to the Docker documentation about howCMD
andENTRYPOINT
interact. If you specify this field, then you can also specify theargs
field to provide additional arguments for this command. However, if you specify this field, then the container'sCMD
is ignored. See the Kubernetes documentation about how thecommand
andargs
fields interact with a container'sENTRYPOINT
andCMD
. In this field, you can reference environment variables set by Vertex AI and environment variables set in the env field. You cannot reference environment variables set in the Docker image. In order for environment variables to be expanded, reference them by using the following syntax: $( VARIABLE_NAME) Note that this differs from Bash variable expansion, which does not use parentheses. If a variable cannot be resolved, the reference in the input string is used unchanged. To avoid variable expansion, you can escape this syntax with$$
; for example: $$(VARIABLE_NAME) This field corresponds to thecommand
field of the Kubernetes Containers v1 core API. - deployment
Timeout String - Immutable. Deployment timeout. TODO (b/306244185): Revise documentation before exposing.
- env
List<Google
Cloud Aiplatform V1Env Var> - Immutable. List of environment variables to set in the container. After the container starts running, code running in the container can read these environment variables. Additionally, the command and args fields can reference these variables. Later entries in this list can also reference earlier entries. For example, the following example sets the variable
VAR_2
to have the valuefoo bar
:json [ { "name": "VAR_1", "value": "foo" }, { "name": "VAR_2", "value": "$(VAR_1) bar" } ]
If you switch the order of the variables in the example, then the expansion does not occur. This field corresponds to theenv
field of the Kubernetes Containers v1 core API. - health
Probe GoogleCloud Aiplatform V1Probe - Immutable. Specification for Kubernetes readiness probe. TODO (b/306244185): Revise documentation before exposing.
- health
Route String - Immutable. HTTP path on the container to send health checks to. Vertex AI intermittently sends GET requests to this path on the container's IP address and port to check that the container is healthy. Read more about health checks. For example, if you set this field to
/bar
, then Vertex AI intermittently sends a GET request to the/bar
path on the port of your container specified by the first value of thisModelContainerSpec
's ports field. If you don't specify this field, it defaults to the following value when you deploy this Model to an Endpoint: /v1/endpoints/ENDPOINT/deployedModels/ DEPLOYED_MODEL:predict The placeholders in this value are replaced as follows: * ENDPOINT: The last segment (followingendpoints/
)of the Endpoint.name][] field of the Endpoint where this Model has been deployed. (Vertex AI makes this value available to your container code as theAIP_ENDPOINT_ID
environment variable.) * DEPLOYED_MODEL: DeployedModel.id of theDeployedModel
. (Vertex AI makes this value available to your container code as theAIP_DEPLOYED_MODEL_ID
environment variable.) - ports
List<Google
Cloud Aiplatform V1Port> - Immutable. List of ports to expose from the container. Vertex AI sends any prediction requests that it receives to the first port on this list. Vertex AI also sends liveness and health checks to this port. If you do not specify this field, it defaults to following value:
json [ { "containerPort": 8080 } ]
Vertex AI does not use ports other than the first one listed. This field corresponds to theports
field of the Kubernetes Containers v1 core API. - predict
Route String - Immutable. HTTP path on the container to send prediction requests to. Vertex AI forwards requests sent using projects.locations.endpoints.predict to this path on the container's IP address and port. Vertex AI then returns the container's response in the API response. For example, if you set this field to
/foo
, then when Vertex AI receives a prediction request, it forwards the request body in a POST request to the/foo
path on the port of your container specified by the first value of thisModelContainerSpec
's ports field. If you don't specify this field, it defaults to the following value when you deploy this Model to an Endpoint: /v1/endpoints/ENDPOINT/deployedModels/DEPLOYED_MODEL:predict The placeholders in this value are replaced as follows: * ENDPOINT: The last segment (followingendpoints/
)of the Endpoint.name][] field of the Endpoint where this Model has been deployed. (Vertex AI makes this value available to your container code as theAIP_ENDPOINT_ID
environment variable.) * DEPLOYED_MODEL: DeployedModel.id of theDeployedModel
. (Vertex AI makes this value available to your container code as theAIP_DEPLOYED_MODEL_ID
environment variable.) - String
- Immutable. The amount of the VM memory to reserve as the shared memory for the model in megabytes. TODO (b/306244185): Revise documentation before exposing.
- startup
Probe GoogleCloud Aiplatform V1Probe - Immutable. Specification for Kubernetes startup probe. TODO (b/306244185): Revise documentation before exposing.
- image
Uri string - Immutable. URI of the Docker image to be used as the custom container for serving predictions. This URI must identify an image in Artifact Registry or Container Registry. Learn more about the container publishing requirements, including permissions requirements for the Vertex AI Service Agent. The container image is ingested upon ModelService.UploadModel, stored internally, and this original path is afterwards not used. To learn about the requirements for the Docker image itself, see Custom container requirements. You can use the URI to one of Vertex AI's pre-built container images for prediction in this field.
- args string[]
- Immutable. Specifies arguments for the command that runs when the container starts. This overrides the container's
CMD
. Specify this field as an array of executable and arguments, similar to a DockerCMD
's "default parameters" form. If you don't specify this field but do specify the command field, then the command from thecommand
field runs without any additional arguments. See the Kubernetes documentation about how thecommand
andargs
fields interact with a container'sENTRYPOINT
andCMD
. If you don't specify this field and don't specify thecommand
field, then the container'sENTRYPOINT
andCMD
determine what runs based on their default behavior. See the Docker documentation about howCMD
andENTRYPOINT
interact. In this field, you can reference environment variables set by Vertex AI and environment variables set in the env field. You cannot reference environment variables set in the Docker image. In order for environment variables to be expanded, reference them by using the following syntax: $( VARIABLE_NAME) Note that this differs from Bash variable expansion, which does not use parentheses. If a variable cannot be resolved, the reference in the input string is used unchanged. To avoid variable expansion, you can escape this syntax with$$
; for example: $$(VARIABLE_NAME) This field corresponds to theargs
field of the Kubernetes Containers v1 core API. - command string[]
- Immutable. Specifies the command that runs when the container starts. This overrides the container's ENTRYPOINT. Specify this field as an array of executable and arguments, similar to a Docker
ENTRYPOINT
's "exec" form, not its "shell" form. If you do not specify this field, then the container'sENTRYPOINT
runs, in conjunction with the args field or the container'sCMD
, if either exists. If this field is not specified and the container does not have anENTRYPOINT
, then refer to the Docker documentation about howCMD
andENTRYPOINT
interact. If you specify this field, then you can also specify theargs
field to provide additional arguments for this command. However, if you specify this field, then the container'sCMD
is ignored. See the Kubernetes documentation about how thecommand
andargs
fields interact with a container'sENTRYPOINT
andCMD
. In this field, you can reference environment variables set by Vertex AI and environment variables set in the env field. You cannot reference environment variables set in the Docker image. In order for environment variables to be expanded, reference them by using the following syntax: $( VARIABLE_NAME) Note that this differs from Bash variable expansion, which does not use parentheses. If a variable cannot be resolved, the reference in the input string is used unchanged. To avoid variable expansion, you can escape this syntax with$$
; for example: $$(VARIABLE_NAME) This field corresponds to thecommand
field of the Kubernetes Containers v1 core API. - deployment
Timeout string - Immutable. Deployment timeout. TODO (b/306244185): Revise documentation before exposing.
- env
Google
Cloud Aiplatform V1Env Var[] - Immutable. List of environment variables to set in the container. After the container starts running, code running in the container can read these environment variables. Additionally, the command and args fields can reference these variables. Later entries in this list can also reference earlier entries. For example, the following example sets the variable
VAR_2
to have the valuefoo bar
:json [ { "name": "VAR_1", "value": "foo" }, { "name": "VAR_2", "value": "$(VAR_1) bar" } ]
If you switch the order of the variables in the example, then the expansion does not occur. This field corresponds to theenv
field of the Kubernetes Containers v1 core API. - health
Probe GoogleCloud Aiplatform V1Probe - Immutable. Specification for Kubernetes readiness probe. TODO (b/306244185): Revise documentation before exposing.
- health
Route string - Immutable. HTTP path on the container to send health checks to. Vertex AI intermittently sends GET requests to this path on the container's IP address and port to check that the container is healthy. Read more about health checks. For example, if you set this field to
/bar
, then Vertex AI intermittently sends a GET request to the/bar
path on the port of your container specified by the first value of thisModelContainerSpec
's ports field. If you don't specify this field, it defaults to the following value when you deploy this Model to an Endpoint: /v1/endpoints/ENDPOINT/deployedModels/ DEPLOYED_MODEL:predict The placeholders in this value are replaced as follows: * ENDPOINT: The last segment (followingendpoints/
)of the Endpoint.name][] field of the Endpoint where this Model has been deployed. (Vertex AI makes this value available to your container code as theAIP_ENDPOINT_ID
environment variable.) * DEPLOYED_MODEL: DeployedModel.id of theDeployedModel
. (Vertex AI makes this value available to your container code as theAIP_DEPLOYED_MODEL_ID
environment variable.) - ports
Google
Cloud Aiplatform V1Port[] - Immutable. List of ports to expose from the container. Vertex AI sends any prediction requests that it receives to the first port on this list. Vertex AI also sends liveness and health checks to this port. If you do not specify this field, it defaults to following value:
json [ { "containerPort": 8080 } ]
Vertex AI does not use ports other than the first one listed. This field corresponds to theports
field of the Kubernetes Containers v1 core API. - predict
Route string - Immutable. HTTP path on the container to send prediction requests to. Vertex AI forwards requests sent using projects.locations.endpoints.predict to this path on the container's IP address and port. Vertex AI then returns the container's response in the API response. For example, if you set this field to
/foo
, then when Vertex AI receives a prediction request, it forwards the request body in a POST request to the/foo
path on the port of your container specified by the first value of thisModelContainerSpec
's ports field. If you don't specify this field, it defaults to the following value when you deploy this Model to an Endpoint: /v1/endpoints/ENDPOINT/deployedModels/DEPLOYED_MODEL:predict The placeholders in this value are replaced as follows: * ENDPOINT: The last segment (followingendpoints/
)of the Endpoint.name][] field of the Endpoint where this Model has been deployed. (Vertex AI makes this value available to your container code as theAIP_ENDPOINT_ID
environment variable.) * DEPLOYED_MODEL: DeployedModel.id of theDeployedModel
. (Vertex AI makes this value available to your container code as theAIP_DEPLOYED_MODEL_ID
environment variable.) - string
- Immutable. The amount of the VM memory to reserve as the shared memory for the model in megabytes. TODO (b/306244185): Revise documentation before exposing.
- startup
Probe GoogleCloud Aiplatform V1Probe - Immutable. Specification for Kubernetes startup probe. TODO (b/306244185): Revise documentation before exposing.
- image_
uri str - Immutable. URI of the Docker image to be used as the custom container for serving predictions. This URI must identify an image in Artifact Registry or Container Registry. Learn more about the container publishing requirements, including permissions requirements for the Vertex AI Service Agent. The container image is ingested upon ModelService.UploadModel, stored internally, and this original path is afterwards not used. To learn about the requirements for the Docker image itself, see Custom container requirements. You can use the URI to one of Vertex AI's pre-built container images for prediction in this field.
- args Sequence[str]
- Immutable. Specifies arguments for the command that runs when the container starts. This overrides the container's
CMD
. Specify this field as an array of executable and arguments, similar to a DockerCMD
's "default parameters" form. If you don't specify this field but do specify the command field, then the command from thecommand
field runs without any additional arguments. See the Kubernetes documentation about how thecommand
andargs
fields interact with a container'sENTRYPOINT
andCMD
. If you don't specify this field and don't specify thecommand
field, then the container'sENTRYPOINT
andCMD
determine what runs based on their default behavior. See the Docker documentation about howCMD
andENTRYPOINT
interact. In this field, you can reference environment variables set by Vertex AI and environment variables set in the env field. You cannot reference environment variables set in the Docker image. In order for environment variables to be expanded, reference them by using the following syntax: $( VARIABLE_NAME) Note that this differs from Bash variable expansion, which does not use parentheses. If a variable cannot be resolved, the reference in the input string is used unchanged. To avoid variable expansion, you can escape this syntax with$$
; for example: $$(VARIABLE_NAME) This field corresponds to theargs
field of the Kubernetes Containers v1 core API. - command Sequence[str]
- Immutable. Specifies the command that runs when the container starts. This overrides the container's ENTRYPOINT. Specify this field as an array of executable and arguments, similar to a Docker
ENTRYPOINT
's "exec" form, not its "shell" form. If you do not specify this field, then the container'sENTRYPOINT
runs, in conjunction with the args field or the container'sCMD
, if either exists. If this field is not specified and the container does not have anENTRYPOINT
, then refer to the Docker documentation about howCMD
andENTRYPOINT
interact. If you specify this field, then you can also specify theargs
field to provide additional arguments for this command. However, if you specify this field, then the container'sCMD
is ignored. See the Kubernetes documentation about how thecommand
andargs
fields interact with a container'sENTRYPOINT
andCMD
. In this field, you can reference environment variables set by Vertex AI and environment variables set in the env field. You cannot reference environment variables set in the Docker image. In order for environment variables to be expanded, reference them by using the following syntax: $( VARIABLE_NAME) Note that this differs from Bash variable expansion, which does not use parentheses. If a variable cannot be resolved, the reference in the input string is used unchanged. To avoid variable expansion, you can escape this syntax with$$
; for example: $$(VARIABLE_NAME) This field corresponds to thecommand
field of the Kubernetes Containers v1 core API. - deployment_
timeout str - Immutable. Deployment timeout. TODO (b/306244185): Revise documentation before exposing.
- env
Sequence[Google
Cloud Aiplatform V1Env Var] - Immutable. List of environment variables to set in the container. After the container starts running, code running in the container can read these environment variables. Additionally, the command and args fields can reference these variables. Later entries in this list can also reference earlier entries. For example, the following example sets the variable
VAR_2
to have the valuefoo bar
:json [ { "name": "VAR_1", "value": "foo" }, { "name": "VAR_2", "value": "$(VAR_1) bar" } ]
If you switch the order of the variables in the example, then the expansion does not occur. This field corresponds to theenv
field of the Kubernetes Containers v1 core API. - health_
probe GoogleCloud Aiplatform V1Probe - Immutable. Specification for Kubernetes readiness probe. TODO (b/306244185): Revise documentation before exposing.
- health_
route str - Immutable. HTTP path on the container to send health checks to. Vertex AI intermittently sends GET requests to this path on the container's IP address and port to check that the container is healthy. Read more about health checks. For example, if you set this field to
/bar
, then Vertex AI intermittently sends a GET request to the/bar
path on the port of your container specified by the first value of thisModelContainerSpec
's ports field. If you don't specify this field, it defaults to the following value when you deploy this Model to an Endpoint: /v1/endpoints/ENDPOINT/deployedModels/ DEPLOYED_MODEL:predict The placeholders in this value are replaced as follows: * ENDPOINT: The last segment (followingendpoints/
)of the Endpoint.name][] field of the Endpoint where this Model has been deployed. (Vertex AI makes this value available to your container code as theAIP_ENDPOINT_ID
environment variable.) * DEPLOYED_MODEL: DeployedModel.id of theDeployedModel
. (Vertex AI makes this value available to your container code as theAIP_DEPLOYED_MODEL_ID
environment variable.) - ports
Sequence[Google
Cloud Aiplatform V1Port] - Immutable. List of ports to expose from the container. Vertex AI sends any prediction requests that it receives to the first port on this list. Vertex AI also sends liveness and health checks to this port. If you do not specify this field, it defaults to following value:
json [ { "containerPort": 8080 } ]
Vertex AI does not use ports other than the first one listed. This field corresponds to theports
field of the Kubernetes Containers v1 core API. - predict_
route str - Immutable. HTTP path on the container to send prediction requests to. Vertex AI forwards requests sent using projects.locations.endpoints.predict to this path on the container's IP address and port. Vertex AI then returns the container's response in the API response. For example, if you set this field to
/foo
, then when Vertex AI receives a prediction request, it forwards the request body in a POST request to the/foo
path on the port of your container specified by the first value of thisModelContainerSpec
's ports field. If you don't specify this field, it defaults to the following value when you deploy this Model to an Endpoint: /v1/endpoints/ENDPOINT/deployedModels/DEPLOYED_MODEL:predict The placeholders in this value are replaced as follows: * ENDPOINT: The last segment (followingendpoints/
)of the Endpoint.name][] field of the Endpoint where this Model has been deployed. (Vertex AI makes this value available to your container code as theAIP_ENDPOINT_ID
environment variable.) * DEPLOYED_MODEL: DeployedModel.id of theDeployedModel
. (Vertex AI makes this value available to your container code as theAIP_DEPLOYED_MODEL_ID
environment variable.) - str
- Immutable. The amount of the VM memory to reserve as the shared memory for the model in megabytes. TODO (b/306244185): Revise documentation before exposing.
- startup_
probe GoogleCloud Aiplatform V1Probe - Immutable. Specification for Kubernetes startup probe. TODO (b/306244185): Revise documentation before exposing.
- image
Uri String - Immutable. URI of the Docker image to be used as the custom container for serving predictions. This URI must identify an image in Artifact Registry or Container Registry. Learn more about the container publishing requirements, including permissions requirements for the Vertex AI Service Agent. The container image is ingested upon ModelService.UploadModel, stored internally, and this original path is afterwards not used. To learn about the requirements for the Docker image itself, see Custom container requirements. You can use the URI to one of Vertex AI's pre-built container images for prediction in this field.
- args List<String>
- Immutable. Specifies arguments for the command that runs when the container starts. This overrides the container's
CMD
. Specify this field as an array of executable and arguments, similar to a DockerCMD
's "default parameters" form. If you don't specify this field but do specify the command field, then the command from thecommand
field runs without any additional arguments. See the Kubernetes documentation about how thecommand
andargs
fields interact with a container'sENTRYPOINT
andCMD
. If you don't specify this field and don't specify thecommand
field, then the container'sENTRYPOINT
andCMD
determine what runs based on their default behavior. See the Docker documentation about howCMD
andENTRYPOINT
interact. In this field, you can reference environment variables set by Vertex AI and environment variables set in the env field. You cannot reference environment variables set in the Docker image. In order for environment variables to be expanded, reference them by using the following syntax: $( VARIABLE_NAME) Note that this differs from Bash variable expansion, which does not use parentheses. If a variable cannot be resolved, the reference in the input string is used unchanged. To avoid variable expansion, you can escape this syntax with$$
; for example: $$(VARIABLE_NAME) This field corresponds to theargs
field of the Kubernetes Containers v1 core API. - command List<String>
- Immutable. Specifies the command that runs when the container starts. This overrides the container's ENTRYPOINT. Specify this field as an array of executable and arguments, similar to a Docker
ENTRYPOINT
's "exec" form, not its "shell" form. If you do not specify this field, then the container'sENTRYPOINT
runs, in conjunction with the args field or the container'sCMD
, if either exists. If this field is not specified and the container does not have anENTRYPOINT
, then refer to the Docker documentation about howCMD
andENTRYPOINT
interact. If you specify this field, then you can also specify theargs
field to provide additional arguments for this command. However, if you specify this field, then the container'sCMD
is ignored. See the Kubernetes documentation about how thecommand
andargs
fields interact with a container'sENTRYPOINT
andCMD
. In this field, you can reference environment variables set by Vertex AI and environment variables set in the env field. You cannot reference environment variables set in the Docker image. In order for environment variables to be expanded, reference them by using the following syntax: $( VARIABLE_NAME) Note that this differs from Bash variable expansion, which does not use parentheses. If a variable cannot be resolved, the reference in the input string is used unchanged. To avoid variable expansion, you can escape this syntax with$$
; for example: $$(VARIABLE_NAME) This field corresponds to thecommand
field of the Kubernetes Containers v1 core API. - deployment
Timeout String - Immutable. Deployment timeout. TODO (b/306244185): Revise documentation before exposing.
- env List<Property Map>
- Immutable. List of environment variables to set in the container. After the container starts running, code running in the container can read these environment variables. Additionally, the command and args fields can reference these variables. Later entries in this list can also reference earlier entries. For example, the following example sets the variable
VAR_2
to have the valuefoo bar
:json [ { "name": "VAR_1", "value": "foo" }, { "name": "VAR_2", "value": "$(VAR_1) bar" } ]
If you switch the order of the variables in the example, then the expansion does not occur. This field corresponds to theenv
field of the Kubernetes Containers v1 core API. - health
Probe Property Map - Immutable. Specification for Kubernetes readiness probe. TODO (b/306244185): Revise documentation before exposing.
- health
Route String - Immutable. HTTP path on the container to send health checks to. Vertex AI intermittently sends GET requests to this path on the container's IP address and port to check that the container is healthy. Read more about health checks. For example, if you set this field to
/bar
, then Vertex AI intermittently sends a GET request to the/bar
path on the port of your container specified by the first value of thisModelContainerSpec
's ports field. If you don't specify this field, it defaults to the following value when you deploy this Model to an Endpoint: /v1/endpoints/ENDPOINT/deployedModels/ DEPLOYED_MODEL:predict The placeholders in this value are replaced as follows: * ENDPOINT: The last segment (followingendpoints/
)of the Endpoint.name][] field of the Endpoint where this Model has been deployed. (Vertex AI makes this value available to your container code as theAIP_ENDPOINT_ID
environment variable.) * DEPLOYED_MODEL: DeployedModel.id of theDeployedModel
. (Vertex AI makes this value available to your container code as theAIP_DEPLOYED_MODEL_ID
environment variable.) - ports List<Property Map>
- Immutable. List of ports to expose from the container. Vertex AI sends any prediction requests that it receives to the first port on this list. Vertex AI also sends liveness and health checks to this port. If you do not specify this field, it defaults to following value:
json [ { "containerPort": 8080 } ]
Vertex AI does not use ports other than the first one listed. This field corresponds to theports
field of the Kubernetes Containers v1 core API. - predict
Route String - Immutable. HTTP path on the container to send prediction requests to. Vertex AI forwards requests sent using projects.locations.endpoints.predict to this path on the container's IP address and port. Vertex AI then returns the container's response in the API response. For example, if you set this field to
/foo
, then when Vertex AI receives a prediction request, it forwards the request body in a POST request to the/foo
path on the port of your container specified by the first value of thisModelContainerSpec
's ports field. If you don't specify this field, it defaults to the following value when you deploy this Model to an Endpoint: /v1/endpoints/ENDPOINT/deployedModels/DEPLOYED_MODEL:predict The placeholders in this value are replaced as follows: * ENDPOINT: The last segment (followingendpoints/
)of the Endpoint.name][] field of the Endpoint where this Model has been deployed. (Vertex AI makes this value available to your container code as theAIP_ENDPOINT_ID
environment variable.) * DEPLOYED_MODEL: DeployedModel.id of theDeployedModel
. (Vertex AI makes this value available to your container code as theAIP_DEPLOYED_MODEL_ID
environment variable.) - String
- Immutable. The amount of the VM memory to reserve as the shared memory for the model in megabytes. TODO (b/306244185): Revise documentation before exposing.
- startup
Probe Property Map - Immutable. Specification for Kubernetes startup probe. TODO (b/306244185): Revise documentation before exposing.
GoogleCloudAiplatformV1ModelContainerSpecResponse, GoogleCloudAiplatformV1ModelContainerSpecResponseArgs
- Args List<string>
- Immutable. Specifies arguments for the command that runs when the container starts. This overrides the container's
CMD
. Specify this field as an array of executable and arguments, similar to a DockerCMD
's "default parameters" form. If you don't specify this field but do specify the command field, then the command from thecommand
field runs without any additional arguments. See the Kubernetes documentation about how thecommand
andargs
fields interact with a container'sENTRYPOINT
andCMD
. If you don't specify this field and don't specify thecommand
field, then the container'sENTRYPOINT
andCMD
determine what runs based on their default behavior. See the Docker documentation about howCMD
andENTRYPOINT
interact. In this field, you can reference environment variables set by Vertex AI and environment variables set in the env field. You cannot reference environment variables set in the Docker image. In order for environment variables to be expanded, reference them by using the following syntax: $( VARIABLE_NAME) Note that this differs from Bash variable expansion, which does not use parentheses. If a variable cannot be resolved, the reference in the input string is used unchanged. To avoid variable expansion, you can escape this syntax with$$
; for example: $$(VARIABLE_NAME) This field corresponds to theargs
field of the Kubernetes Containers v1 core API. - Command List<string>
- Immutable. Specifies the command that runs when the container starts. This overrides the container's ENTRYPOINT. Specify this field as an array of executable and arguments, similar to a Docker
ENTRYPOINT
's "exec" form, not its "shell" form. If you do not specify this field, then the container'sENTRYPOINT
runs, in conjunction with the args field or the container'sCMD
, if either exists. If this field is not specified and the container does not have anENTRYPOINT
, then refer to the Docker documentation about howCMD
andENTRYPOINT
interact. If you specify this field, then you can also specify theargs
field to provide additional arguments for this command. However, if you specify this field, then the container'sCMD
is ignored. See the Kubernetes documentation about how thecommand
andargs
fields interact with a container'sENTRYPOINT
andCMD
. In this field, you can reference environment variables set by Vertex AI and environment variables set in the env field. You cannot reference environment variables set in the Docker image. In order for environment variables to be expanded, reference them by using the following syntax: $( VARIABLE_NAME) Note that this differs from Bash variable expansion, which does not use parentheses. If a variable cannot be resolved, the reference in the input string is used unchanged. To avoid variable expansion, you can escape this syntax with$$
; for example: $$(VARIABLE_NAME) This field corresponds to thecommand
field of the Kubernetes Containers v1 core API. - Deployment
Timeout string - Immutable. Deployment timeout. TODO (b/306244185): Revise documentation before exposing.
- Env
List<Pulumi.
Google Native. Aiplatform. V1. Inputs. Google Cloud Aiplatform V1Env Var Response> - Immutable. List of environment variables to set in the container. After the container starts running, code running in the container can read these environment variables. Additionally, the command and args fields can reference these variables. Later entries in this list can also reference earlier entries. For example, the following example sets the variable
VAR_2
to have the valuefoo bar
:json [ { "name": "VAR_1", "value": "foo" }, { "name": "VAR_2", "value": "$(VAR_1) bar" } ]
If you switch the order of the variables in the example, then the expansion does not occur. This field corresponds to theenv
field of the Kubernetes Containers v1 core API. - Health
Probe Pulumi.Google Native. Aiplatform. V1. Inputs. Google Cloud Aiplatform V1Probe Response - Immutable. Specification for Kubernetes readiness probe. TODO (b/306244185): Revise documentation before exposing.
- Health
Route string - Immutable. HTTP path on the container to send health checks to. Vertex AI intermittently sends GET requests to this path on the container's IP address and port to check that the container is healthy. Read more about health checks. For example, if you set this field to
/bar
, then Vertex AI intermittently sends a GET request to the/bar
path on the port of your container specified by the first value of thisModelContainerSpec
's ports field. If you don't specify this field, it defaults to the following value when you deploy this Model to an Endpoint: /v1/endpoints/ENDPOINT/deployedModels/ DEPLOYED_MODEL:predict The placeholders in this value are replaced as follows: * ENDPOINT: The last segment (followingendpoints/
)of the Endpoint.name][] field of the Endpoint where this Model has been deployed. (Vertex AI makes this value available to your container code as theAIP_ENDPOINT_ID
environment variable.) * DEPLOYED_MODEL: DeployedModel.id of theDeployedModel
. (Vertex AI makes this value available to your container code as theAIP_DEPLOYED_MODEL_ID
environment variable.) - Image
Uri string - Immutable. URI of the Docker image to be used as the custom container for serving predictions. This URI must identify an image in Artifact Registry or Container Registry. Learn more about the container publishing requirements, including permissions requirements for the Vertex AI Service Agent. The container image is ingested upon ModelService.UploadModel, stored internally, and this original path is afterwards not used. To learn about the requirements for the Docker image itself, see Custom container requirements. You can use the URI to one of Vertex AI's pre-built container images for prediction in this field.
- Ports
List<Pulumi.
Google Native. Aiplatform. V1. Inputs. Google Cloud Aiplatform V1Port Response> - Immutable. List of ports to expose from the container. Vertex AI sends any prediction requests that it receives to the first port on this list. Vertex AI also sends liveness and health checks to this port. If you do not specify this field, it defaults to following value:
json [ { "containerPort": 8080 } ]
Vertex AI does not use ports other than the first one listed. This field corresponds to theports
field of the Kubernetes Containers v1 core API. - Predict
Route string - Immutable. HTTP path on the container to send prediction requests to. Vertex AI forwards requests sent using projects.locations.endpoints.predict to this path on the container's IP address and port. Vertex AI then returns the container's response in the API response. For example, if you set this field to
/foo
, then when Vertex AI receives a prediction request, it forwards the request body in a POST request to the/foo
path on the port of your container specified by the first value of thisModelContainerSpec
's ports field. If you don't specify this field, it defaults to the following value when you deploy this Model to an Endpoint: /v1/endpoints/ENDPOINT/deployedModels/DEPLOYED_MODEL:predict The placeholders in this value are replaced as follows: * ENDPOINT: The last segment (followingendpoints/
)of the Endpoint.name][] field of the Endpoint where this Model has been deployed. (Vertex AI makes this value available to your container code as theAIP_ENDPOINT_ID
environment variable.) * DEPLOYED_MODEL: DeployedModel.id of theDeployedModel
. (Vertex AI makes this value available to your container code as theAIP_DEPLOYED_MODEL_ID
environment variable.) - string
- Immutable. The amount of the VM memory to reserve as the shared memory for the model in megabytes. TODO (b/306244185): Revise documentation before exposing.
- Startup
Probe Pulumi.Google Native. Aiplatform. V1. Inputs. Google Cloud Aiplatform V1Probe Response - Immutable. Specification for Kubernetes startup probe. TODO (b/306244185): Revise documentation before exposing.
- Args []string
- Immutable. Specifies arguments for the command that runs when the container starts. This overrides the container's
CMD
. Specify this field as an array of executable and arguments, similar to a DockerCMD
's "default parameters" form. If you don't specify this field but do specify the command field, then the command from thecommand
field runs without any additional arguments. See the Kubernetes documentation about how thecommand
andargs
fields interact with a container'sENTRYPOINT
andCMD
. If you don't specify this field and don't specify thecommand
field, then the container'sENTRYPOINT
andCMD
determine what runs based on their default behavior. See the Docker documentation about howCMD
andENTRYPOINT
interact. In this field, you can reference environment variables set by Vertex AI and environment variables set in the env field. You cannot reference environment variables set in the Docker image. In order for environment variables to be expanded, reference them by using the following syntax: $( VARIABLE_NAME) Note that this differs from Bash variable expansion, which does not use parentheses. If a variable cannot be resolved, the reference in the input string is used unchanged. To avoid variable expansion, you can escape this syntax with$$
; for example: $$(VARIABLE_NAME) This field corresponds to theargs
field of the Kubernetes Containers v1 core API. - Command []string
- Immutable. Specifies the command that runs when the container starts. This overrides the container's ENTRYPOINT. Specify this field as an array of executable and arguments, similar to a Docker
ENTRYPOINT
's "exec" form, not its "shell" form. If you do not specify this field, then the container'sENTRYPOINT
runs, in conjunction with the args field or the container'sCMD
, if either exists. If this field is not specified and the container does not have anENTRYPOINT
, then refer to the Docker documentation about howCMD
andENTRYPOINT
interact. If you specify this field, then you can also specify theargs
field to provide additional arguments for this command. However, if you specify this field, then the container'sCMD
is ignored. See the Kubernetes documentation about how thecommand
andargs
fields interact with a container'sENTRYPOINT
andCMD
. In this field, you can reference environment variables set by Vertex AI and environment variables set in the env field. You cannot reference environment variables set in the Docker image. In order for environment variables to be expanded, reference them by using the following syntax: $( VARIABLE_NAME) Note that this differs from Bash variable expansion, which does not use parentheses. If a variable cannot be resolved, the reference in the input string is used unchanged. To avoid variable expansion, you can escape this syntax with$$
; for example: $$(VARIABLE_NAME) This field corresponds to thecommand
field of the Kubernetes Containers v1 core API. - Deployment
Timeout string - Immutable. Deployment timeout. TODO (b/306244185): Revise documentation before exposing.
- Env
[]Google
Cloud Aiplatform V1Env Var Response - Immutable. List of environment variables to set in the container. After the container starts running, code running in the container can read these environment variables. Additionally, the command and args fields can reference these variables. Later entries in this list can also reference earlier entries. For example, the following example sets the variable
VAR_2
to have the valuefoo bar
:json [ { "name": "VAR_1", "value": "foo" }, { "name": "VAR_2", "value": "$(VAR_1) bar" } ]
If you switch the order of the variables in the example, then the expansion does not occur. This field corresponds to theenv
field of the Kubernetes Containers v1 core API. - Health
Probe GoogleCloud Aiplatform V1Probe Response - Immutable. Specification for Kubernetes readiness probe. TODO (b/306244185): Revise documentation before exposing.
- Health
Route string - Immutable. HTTP path on the container to send health checks to. Vertex AI intermittently sends GET requests to this path on the container's IP address and port to check that the container is healthy. Read more about health checks. For example, if you set this field to
/bar
, then Vertex AI intermittently sends a GET request to the/bar
path on the port of your container specified by the first value of thisModelContainerSpec
's ports field. If you don't specify this field, it defaults to the following value when you deploy this Model to an Endpoint: /v1/endpoints/ENDPOINT/deployedModels/ DEPLOYED_MODEL:predict The placeholders in this value are replaced as follows: * ENDPOINT: The last segment (followingendpoints/
)of the Endpoint.name][] field of the Endpoint where this Model has been deployed. (Vertex AI makes this value available to your container code as theAIP_ENDPOINT_ID
environment variable.) * DEPLOYED_MODEL: DeployedModel.id of theDeployedModel
. (Vertex AI makes this value available to your container code as theAIP_DEPLOYED_MODEL_ID
environment variable.) - Image
Uri string - Immutable. URI of the Docker image to be used as the custom container for serving predictions. This URI must identify an image in Artifact Registry or Container Registry. Learn more about the container publishing requirements, including permissions requirements for the Vertex AI Service Agent. The container image is ingested upon ModelService.UploadModel, stored internally, and this original path is afterwards not used. To learn about the requirements for the Docker image itself, see Custom container requirements. You can use the URI to one of Vertex AI's pre-built container images for prediction in this field.
- Ports
[]Google
Cloud Aiplatform V1Port Response - Immutable. List of ports to expose from the container. Vertex AI sends any prediction requests that it receives to the first port on this list. Vertex AI also sends liveness and health checks to this port. If you do not specify this field, it defaults to following value:
json [ { "containerPort": 8080 } ]
Vertex AI does not use ports other than the first one listed. This field corresponds to theports
field of the Kubernetes Containers v1 core API. - Predict
Route string - Immutable. HTTP path on the container to send prediction requests to. Vertex AI forwards requests sent using projects.locations.endpoints.predict to this path on the container's IP address and port. Vertex AI then returns the container's response in the API response. For example, if you set this field to
/foo
, then when Vertex AI receives a prediction request, it forwards the request body in a POST request to the/foo
path on the port of your container specified by the first value of thisModelContainerSpec
's ports field. If you don't specify this field, it defaults to the following value when you deploy this Model to an Endpoint: /v1/endpoints/ENDPOINT/deployedModels/DEPLOYED_MODEL:predict The placeholders in this value are replaced as follows: * ENDPOINT: The last segment (followingendpoints/
)of the Endpoint.name][] field of the Endpoint where this Model has been deployed. (Vertex AI makes this value available to your container code as theAIP_ENDPOINT_ID
environment variable.) * DEPLOYED_MODEL: DeployedModel.id of theDeployedModel
. (Vertex AI makes this value available to your container code as theAIP_DEPLOYED_MODEL_ID
environment variable.) - string
- Immutable. The amount of the VM memory to reserve as the shared memory for the model in megabytes. TODO (b/306244185): Revise documentation before exposing.
- Startup
Probe GoogleCloud Aiplatform V1Probe Response - Immutable. Specification for Kubernetes startup probe. TODO (b/306244185): Revise documentation before exposing.
- args List<String>
- Immutable. Specifies arguments for the command that runs when the container starts. This overrides the container's
CMD
. Specify this field as an array of executable and arguments, similar to a DockerCMD
's "default parameters" form. If you don't specify this field but do specify the command field, then the command from thecommand
field runs without any additional arguments. See the Kubernetes documentation about how thecommand
andargs
fields interact with a container'sENTRYPOINT
andCMD
. If you don't specify this field and don't specify thecommand
field, then the container'sENTRYPOINT
andCMD
determine what runs based on their default behavior. See the Docker documentation about howCMD
andENTRYPOINT
interact. In this field, you can reference environment variables set by Vertex AI and environment variables set in the env field. You cannot reference environment variables set in the Docker image. In order for environment variables to be expanded, reference them by using the following syntax: $( VARIABLE_NAME) Note that this differs from Bash variable expansion, which does not use parentheses. If a variable cannot be resolved, the reference in the input string is used unchanged. To avoid variable expansion, you can escape this syntax with$$
; for example: $$(VARIABLE_NAME) This field corresponds to theargs
field of the Kubernetes Containers v1 core API. - command List<String>
- Immutable. Specifies the command that runs when the container starts. This overrides the container's ENTRYPOINT. Specify this field as an array of executable and arguments, similar to a Docker
ENTRYPOINT
's "exec" form, not its "shell" form. If you do not specify this field, then the container'sENTRYPOINT
runs, in conjunction with the args field or the container'sCMD
, if either exists. If this field is not specified and the container does not have anENTRYPOINT
, then refer to the Docker documentation about howCMD
andENTRYPOINT
interact. If you specify this field, then you can also specify theargs
field to provide additional arguments for this command. However, if you specify this field, then the container'sCMD
is ignored. See the Kubernetes documentation about how thecommand
andargs
fields interact with a container'sENTRYPOINT
andCMD
. In this field, you can reference environment variables set by Vertex AI and environment variables set in the env field. You cannot reference environment variables set in the Docker image. In order for environment variables to be expanded, reference them by using the following syntax: $( VARIABLE_NAME) Note that this differs from Bash variable expansion, which does not use parentheses. If a variable cannot be resolved, the reference in the input string is used unchanged. To avoid variable expansion, you can escape this syntax with$$
; for example: $$(VARIABLE_NAME) This field corresponds to thecommand
field of the Kubernetes Containers v1 core API. - deployment
Timeout String - Immutable. Deployment timeout. TODO (b/306244185): Revise documentation before exposing.
- env
List<Google
Cloud Aiplatform V1Env Var Response> - Immutable. List of environment variables to set in the container. After the container starts running, code running in the container can read these environment variables. Additionally, the command and args fields can reference these variables. Later entries in this list can also reference earlier entries. For example, the following example sets the variable
VAR_2
to have the valuefoo bar
:json [ { "name": "VAR_1", "value": "foo" }, { "name": "VAR_2", "value": "$(VAR_1) bar" } ]
If you switch the order of the variables in the example, then the expansion does not occur. This field corresponds to theenv
field of the Kubernetes Containers v1 core API. - health
Probe GoogleCloud Aiplatform V1Probe Response - Immutable. Specification for Kubernetes readiness probe. TODO (b/306244185): Revise documentation before exposing.
- health
Route String - Immutable. HTTP path on the container to send health checks to. Vertex AI intermittently sends GET requests to this path on the container's IP address and port to check that the container is healthy. Read more about health checks. For example, if you set this field to
/bar
, then Vertex AI intermittently sends a GET request to the/bar
path on the port of your container specified by the first value of thisModelContainerSpec
's ports field. If you don't specify this field, it defaults to the following value when you deploy this Model to an Endpoint: /v1/endpoints/ENDPOINT/deployedModels/ DEPLOYED_MODEL:predict The placeholders in this value are replaced as follows: * ENDPOINT: The last segment (followingendpoints/
)of the Endpoint.name][] field of the Endpoint where this Model has been deployed. (Vertex AI makes this value available to your container code as theAIP_ENDPOINT_ID
environment variable.) * DEPLOYED_MODEL: DeployedModel.id of theDeployedModel
. (Vertex AI makes this value available to your container code as theAIP_DEPLOYED_MODEL_ID
environment variable.) - image
Uri String - Immutable. URI of the Docker image to be used as the custom container for serving predictions. This URI must identify an image in Artifact Registry or Container Registry. Learn more about the container publishing requirements, including permissions requirements for the Vertex AI Service Agent. The container image is ingested upon ModelService.UploadModel, stored internally, and this original path is afterwards not used. To learn about the requirements for the Docker image itself, see Custom container requirements. You can use the URI to one of Vertex AI's pre-built container images for prediction in this field.
- ports
List<Google
Cloud Aiplatform V1Port Response> - Immutable. List of ports to expose from the container. Vertex AI sends any prediction requests that it receives to the first port on this list. Vertex AI also sends liveness and health checks to this port. If you do not specify this field, it defaults to following value:
json [ { "containerPort": 8080 } ]
Vertex AI does not use ports other than the first one listed. This field corresponds to theports
field of the Kubernetes Containers v1 core API. - predict
Route String - Immutable. HTTP path on the container to send prediction requests to. Vertex AI forwards requests sent using projects.locations.endpoints.predict to this path on the container's IP address and port. Vertex AI then returns the container's response in the API response. For example, if you set this field to
/foo
, then when Vertex AI receives a prediction request, it forwards the request body in a POST request to the/foo
path on the port of your container specified by the first value of thisModelContainerSpec
's ports field. If you don't specify this field, it defaults to the following value when you deploy this Model to an Endpoint: /v1/endpoints/ENDPOINT/deployedModels/DEPLOYED_MODEL:predict The placeholders in this value are replaced as follows: * ENDPOINT: The last segment (followingendpoints/
)of the Endpoint.name][] field of the Endpoint where this Model has been deployed. (Vertex AI makes this value available to your container code as theAIP_ENDPOINT_ID
environment variable.) * DEPLOYED_MODEL: DeployedModel.id of theDeployedModel
. (Vertex AI makes this value available to your container code as theAIP_DEPLOYED_MODEL_ID
environment variable.) - String
- Immutable. The amount of the VM memory to reserve as the shared memory for the model in megabytes. TODO (b/306244185): Revise documentation before exposing.
- startup
Probe GoogleCloud Aiplatform V1Probe Response - Immutable. Specification for Kubernetes startup probe. TODO (b/306244185): Revise documentation before exposing.
- args string[]
- Immutable. Specifies arguments for the command that runs when the container starts. This overrides the container's
CMD
. Specify this field as an array of executable and arguments, similar to a DockerCMD
's "default parameters" form. If you don't specify this field but do specify the command field, then the command from thecommand
field runs without any additional arguments. See the Kubernetes documentation about how thecommand
andargs
fields interact with a container'sENTRYPOINT
andCMD
. If you don't specify this field and don't specify thecommand
field, then the container'sENTRYPOINT
andCMD
determine what runs based on their default behavior. See the Docker documentation about howCMD
andENTRYPOINT
interact. In this field, you can reference environment variables set by Vertex AI and environment variables set in the env field. You cannot reference environment variables set in the Docker image. In order for environment variables to be expanded, reference them by using the following syntax: $( VARIABLE_NAME) Note that this differs from Bash variable expansion, which does not use parentheses. If a variable cannot be resolved, the reference in the input string is used unchanged. To avoid variable expansion, you can escape this syntax with$$
; for example: $$(VARIABLE_NAME) This field corresponds to theargs
field of the Kubernetes Containers v1 core API. - command string[]
- Immutable. Specifies the command that runs when the container starts. This overrides the container's ENTRYPOINT. Specify this field as an array of executable and arguments, similar to a Docker
ENTRYPOINT
's "exec" form, not its "shell" form. If you do not specify this field, then the container'sENTRYPOINT
runs, in conjunction with the args field or the container'sCMD
, if either exists. If this field is not specified and the container does not have anENTRYPOINT
, then refer to the Docker documentation about howCMD
andENTRYPOINT
interact. If you specify this field, then you can also specify theargs
field to provide additional arguments for this command. However, if you specify this field, then the container'sCMD
is ignored. See the Kubernetes documentation about how thecommand
andargs
fields interact with a container'sENTRYPOINT
andCMD
. In this field, you can reference environment variables set by Vertex AI and environment variables set in the env field. You cannot reference environment variables set in the Docker image. In order for environment variables to be expanded, reference them by using the following syntax: $( VARIABLE_NAME) Note that this differs from Bash variable expansion, which does not use parentheses. If a variable cannot be resolved, the reference in the input string is used unchanged. To avoid variable expansion, you can escape this syntax with$$
; for example: $$(VARIABLE_NAME) This field corresponds to thecommand
field of the Kubernetes Containers v1 core API. - deployment
Timeout string - Immutable. Deployment timeout. TODO (b/306244185): Revise documentation before exposing.
- env
Google
Cloud Aiplatform V1Env Var Response[] - Immutable. List of environment variables to set in the container. After the container starts running, code running in the container can read these environment variables. Additionally, the command and args fields can reference these variables. Later entries in this list can also reference earlier entries. For example, the following example sets the variable
VAR_2
to have the valuefoo bar
:json [ { "name": "VAR_1", "value": "foo" }, { "name": "VAR_2", "value": "$(VAR_1) bar" } ]
If you switch the order of the variables in the example, then the expansion does not occur. This field corresponds to theenv
field of the Kubernetes Containers v1 core API. - health
Probe GoogleCloud Aiplatform V1Probe Response - Immutable. Specification for Kubernetes readiness probe. TODO (b/306244185): Revise documentation before exposing.
- health
Route string - Immutable. HTTP path on the container to send health checks to. Vertex AI intermittently sends GET requests to this path on the container's IP address and port to check that the container is healthy. Read more about health checks. For example, if you set this field to
/bar
, then Vertex AI intermittently sends a GET request to the/bar
path on the port of your container specified by the first value of thisModelContainerSpec
's ports field. If you don't specify this field, it defaults to the following value when you deploy this Model to an Endpoint: /v1/endpoints/ENDPOINT/deployedModels/ DEPLOYED_MODEL:predict The placeholders in this value are replaced as follows: * ENDPOINT: The last segment (followingendpoints/
)of the Endpoint.name][] field of the Endpoint where this Model has been deployed. (Vertex AI makes this value available to your container code as theAIP_ENDPOINT_ID
environment variable.) * DEPLOYED_MODEL: DeployedModel.id of theDeployedModel
. (Vertex AI makes this value available to your container code as theAIP_DEPLOYED_MODEL_ID
environment variable.) - image
Uri string - Immutable. URI of the Docker image to be used as the custom container for serving predictions. This URI must identify an image in Artifact Registry or Container Registry. Learn more about the container publishing requirements, including permissions requirements for the Vertex AI Service Agent. The container image is ingested upon ModelService.UploadModel, stored internally, and this original path is afterwards not used. To learn about the requirements for the Docker image itself, see Custom container requirements. You can use the URI to one of Vertex AI's pre-built container images for prediction in this field.
- ports
Google
Cloud Aiplatform V1Port Response[] - Immutable. List of ports to expose from the container. Vertex AI sends any prediction requests that it receives to the first port on this list. Vertex AI also sends liveness and health checks to this port. If you do not specify this field, it defaults to following value:
json [ { "containerPort": 8080 } ]
Vertex AI does not use ports other than the first one listed. This field corresponds to theports
field of the Kubernetes Containers v1 core API. - predict
Route string - Immutable. HTTP path on the container to send prediction requests to. Vertex AI forwards requests sent using projects.locations.endpoints.predict to this path on the container's IP address and port. Vertex AI then returns the container's response in the API response. For example, if you set this field to
/foo
, then when Vertex AI receives a prediction request, it forwards the request body in a POST request to the/foo
path on the port of your container specified by the first value of thisModelContainerSpec
's ports field. If you don't specify this field, it defaults to the following value when you deploy this Model to an Endpoint: /v1/endpoints/ENDPOINT/deployedModels/DEPLOYED_MODEL:predict The placeholders in this value are replaced as follows: * ENDPOINT: The last segment (followingendpoints/
)of the Endpoint.name][] field of the Endpoint where this Model has been deployed. (Vertex AI makes this value available to your container code as theAIP_ENDPOINT_ID
environment variable.) * DEPLOYED_MODEL: DeployedModel.id of theDeployedModel
. (Vertex AI makes this value available to your container code as theAIP_DEPLOYED_MODEL_ID
environment variable.) - string
- Immutable. The amount of the VM memory to reserve as the shared memory for the model in megabytes. TODO (b/306244185): Revise documentation before exposing.
- startup
Probe GoogleCloud Aiplatform V1Probe Response - Immutable. Specification for Kubernetes startup probe. TODO (b/306244185): Revise documentation before exposing.
- args Sequence[str]
- Immutable. Specifies arguments for the command that runs when the container starts. This overrides the container's
CMD
. Specify this field as an array of executable and arguments, similar to a DockerCMD
's "default parameters" form. If you don't specify this field but do specify the command field, then the command from thecommand
field runs without any additional arguments. See the Kubernetes documentation about how thecommand
andargs
fields interact with a container'sENTRYPOINT
andCMD
. If you don't specify this field and don't specify thecommand
field, then the container'sENTRYPOINT
andCMD
determine what runs based on their default behavior. See the Docker documentation about howCMD
andENTRYPOINT
interact. In this field, you can reference environment variables set by Vertex AI and environment variables set in the env field. You cannot reference environment variables set in the Docker image. In order for environment variables to be expanded, reference them by using the following syntax: $( VARIABLE_NAME) Note that this differs from Bash variable expansion, which does not use parentheses. If a variable cannot be resolved, the reference in the input string is used unchanged. To avoid variable expansion, you can escape this syntax with$$
; for example: $$(VARIABLE_NAME) This field corresponds to theargs
field of the Kubernetes Containers v1 core API. - command Sequence[str]
- Immutable. Specifies the command that runs when the container starts. This overrides the container's ENTRYPOINT. Specify this field as an array of executable and arguments, similar to a Docker
ENTRYPOINT
's "exec" form, not its "shell" form. If you do not specify this field, then the container'sENTRYPOINT
runs, in conjunction with the args field or the container'sCMD
, if either exists. If this field is not specified and the container does not have anENTRYPOINT
, then refer to the Docker documentation about howCMD
andENTRYPOINT
interact. If you specify this field, then you can also specify theargs
field to provide additional arguments for this command. However, if you specify this field, then the container'sCMD
is ignored. See the Kubernetes documentation about how thecommand
andargs
fields interact with a container'sENTRYPOINT
andCMD
. In this field, you can reference environment variables set by Vertex AI and environment variables set in the env field. You cannot reference environment variables set in the Docker image. In order for environment variables to be expanded, reference them by using the following syntax: $( VARIABLE_NAME) Note that this differs from Bash variable expansion, which does not use parentheses. If a variable cannot be resolved, the reference in the input string is used unchanged. To avoid variable expansion, you can escape this syntax with$$
; for example: $$(VARIABLE_NAME) This field corresponds to thecommand
field of the Kubernetes Containers v1 core API. - deployment_
timeout str - Immutable. Deployment timeout. TODO (b/306244185): Revise documentation before exposing.
- env
Sequence[Google
Cloud Aiplatform V1Env Var Response] - Immutable. List of environment variables to set in the container. After the container starts running, code running in the container can read these environment variables. Additionally, the command and args fields can reference these variables. Later entries in this list can also reference earlier entries. For example, the following example sets the variable
VAR_2
to have the valuefoo bar
:json [ { "name": "VAR_1", "value": "foo" }, { "name": "VAR_2", "value": "$(VAR_1) bar" } ]
If you switch the order of the variables in the example, then the expansion does not occur. This field corresponds to theenv
field of the Kubernetes Containers v1 core API. - health_
probe GoogleCloud Aiplatform V1Probe Response - Immutable. Specification for Kubernetes readiness probe. TODO (b/306244185): Revise documentation before exposing.
- health_
route str - Immutable. HTTP path on the container to send health checks to. Vertex AI intermittently sends GET requests to this path on the container's IP address and port to check that the container is healthy. Read more about health checks. For example, if you set this field to
/bar
, then Vertex AI intermittently sends a GET request to the/bar
path on the port of your container specified by the first value of thisModelContainerSpec
's ports field. If you don't specify this field, it defaults to the following value when you deploy this Model to an Endpoint: /v1/endpoints/ENDPOINT/deployedModels/ DEPLOYED_MODEL:predict The placeholders in this value are replaced as follows: * ENDPOINT: The last segment (followingendpoints/
)of the Endpoint.name][] field of the Endpoint where this Model has been deployed. (Vertex AI makes this value available to your container code as theAIP_ENDPOINT_ID
environment variable.) * DEPLOYED_MODEL: DeployedModel.id of theDeployedModel
. (Vertex AI makes this value available to your container code as theAIP_DEPLOYED_MODEL_ID
environment variable.) - image_
uri str - Immutable. URI of the Docker image to be used as the custom container for serving predictions. This URI must identify an image in Artifact Registry or Container Registry. Learn more about the container publishing requirements, including permissions requirements for the Vertex AI Service Agent. The container image is ingested upon ModelService.UploadModel, stored internally, and this original path is afterwards not used. To learn about the requirements for the Docker image itself, see Custom container requirements. You can use the URI to one of Vertex AI's pre-built container images for prediction in this field.
- ports
Sequence[Google
Cloud Aiplatform V1Port Response] - Immutable. List of ports to expose from the container. Vertex AI sends any prediction requests that it receives to the first port on this list. Vertex AI also sends liveness and health checks to this port. If you do not specify this field, it defaults to following value:
json [ { "containerPort": 8080 } ]
Vertex AI does not use ports other than the first one listed. This field corresponds to theports
field of the Kubernetes Containers v1 core API. - predict_
route str - Immutable. HTTP path on the container to send prediction requests to. Vertex AI forwards requests sent using projects.locations.endpoints.predict to this path on the container's IP address and port. Vertex AI then returns the container's response in the API response. For example, if you set this field to
/foo
, then when Vertex AI receives a prediction request, it forwards the request body in a POST request to the/foo
path on the port of your container specified by the first value of thisModelContainerSpec
's ports field. If you don't specify this field, it defaults to the following value when you deploy this Model to an Endpoint: /v1/endpoints/ENDPOINT/deployedModels/DEPLOYED_MODEL:predict The placeholders in this value are replaced as follows: * ENDPOINT: The last segment (followingendpoints/
)of the Endpoint.name][] field of the Endpoint where this Model has been deployed. (Vertex AI makes this value available to your container code as theAIP_ENDPOINT_ID
environment variable.) * DEPLOYED_MODEL: DeployedModel.id of theDeployedModel
. (Vertex AI makes this value available to your container code as theAIP_DEPLOYED_MODEL_ID
environment variable.) - str
- Immutable. The amount of the VM memory to reserve as the shared memory for the model in megabytes. TODO (b/306244185): Revise documentation before exposing.
- startup_
probe GoogleCloud Aiplatform V1Probe Response - Immutable. Specification for Kubernetes startup probe. TODO (b/306244185): Revise documentation before exposing.
- args List<String>
- Immutable. Specifies arguments for the command that runs when the container starts. This overrides the container's
CMD
. Specify this field as an array of executable and arguments, similar to a DockerCMD
's "default parameters" form. If you don't specify this field but do specify the command field, then the command from thecommand
field runs without any additional arguments. See the Kubernetes documentation about how thecommand
andargs
fields interact with a container'sENTRYPOINT
andCMD
. If you don't specify this field and don't specify thecommand
field, then the container'sENTRYPOINT
andCMD
determine what runs based on their default behavior. See the Docker documentation about howCMD
andENTRYPOINT
interact. In this field, you can reference environment variables set by Vertex AI and environment variables set in the env field. You cannot reference environment variables set in the Docker image. In order for environment variables to be expanded, reference them by using the following syntax: $( VARIABLE_NAME) Note that this differs from Bash variable expansion, which does not use parentheses. If a variable cannot be resolved, the reference in the input string is used unchanged. To avoid variable expansion, you can escape this syntax with$$
; for example: $$(VARIABLE_NAME) This field corresponds to theargs
field of the Kubernetes Containers v1 core API. - command List<String>
- Immutable. Specifies the command that runs when the container starts. This overrides the container's ENTRYPOINT. Specify this field as an array of executable and arguments, similar to a Docker
ENTRYPOINT
's "exec" form, not its "shell" form. If you do not specify this field, then the container'sENTRYPOINT
runs, in conjunction with the args field or the container'sCMD
, if either exists. If this field is not specified and the container does not have anENTRYPOINT
, then refer to the Docker documentation about howCMD
andENTRYPOINT
interact. If you specify this field, then you can also specify theargs
field to provide additional arguments for this command. However, if you specify this field, then the container'sCMD
is ignored. See the Kubernetes documentation about how thecommand
andargs
fields interact with a container'sENTRYPOINT
andCMD
. In this field, you can reference environment variables set by Vertex AI and environment variables set in the env field. You cannot reference environment variables set in the Docker image. In order for environment variables to be expanded, reference them by using the following syntax: $( VARIABLE_NAME) Note that this differs from Bash variable expansion, which does not use parentheses. If a variable cannot be resolved, the reference in the input string is used unchanged. To avoid variable expansion, you can escape this syntax with$$
; for example: $$(VARIABLE_NAME) This field corresponds to thecommand
field of the Kubernetes Containers v1 core API. - deployment
Timeout String - Immutable. Deployment timeout. TODO (b/306244185): Revise documentation before exposing.
- env List<Property Map>
- Immutable. List of environment variables to set in the container. After the container starts running, code running in the container can read these environment variables. Additionally, the command and args fields can reference these variables. Later entries in this list can also reference earlier entries. For example, the following example sets the variable
VAR_2
to have the valuefoo bar
:json [ { "name": "VAR_1", "value": "foo" }, { "name": "VAR_2", "value": "$(VAR_1) bar" } ]
If you switch the order of the variables in the example, then the expansion does not occur. This field corresponds to theenv
field of the Kubernetes Containers v1 core API. - health
Probe Property Map - Immutable. Specification for Kubernetes readiness probe. TODO (b/306244185): Revise documentation before exposing.
- health
Route String - Immutable. HTTP path on the container to send health checks to. Vertex AI intermittently sends GET requests to this path on the container's IP address and port to check that the container is healthy. Read more about health checks. For example, if you set this field to
/bar
, then Vertex AI intermittently sends a GET request to the/bar
path on the port of your container specified by the first value of thisModelContainerSpec
's ports field. If you don't specify this field, it defaults to the following value when you deploy this Model to an Endpoint: /v1/endpoints/ENDPOINT/deployedModels/ DEPLOYED_MODEL:predict The placeholders in this value are replaced as follows: * ENDPOINT: The last segment (followingendpoints/
)of the Endpoint.name][] field of the Endpoint where this Model has been deployed. (Vertex AI makes this value available to your container code as theAIP_ENDPOINT_ID
environment variable.) * DEPLOYED_MODEL: DeployedModel.id of theDeployedModel
. (Vertex AI makes this value available to your container code as theAIP_DEPLOYED_MODEL_ID
environment variable.) - image
Uri String - Immutable. URI of the Docker image to be used as the custom container for serving predictions. This URI must identify an image in Artifact Registry or Container Registry. Learn more about the container publishing requirements, including permissions requirements for the Vertex AI Service Agent. The container image is ingested upon ModelService.UploadModel, stored internally, and this original path is afterwards not used. To learn about the requirements for the Docker image itself, see Custom container requirements. You can use the URI to one of Vertex AI's pre-built container images for prediction in this field.
- ports List<Property Map>
- Immutable. List of ports to expose from the container. Vertex AI sends any prediction requests that it receives to the first port on this list. Vertex AI also sends liveness and health checks to this port. If you do not specify this field, it defaults to following value:
json [ { "containerPort": 8080 } ]
Vertex AI does not use ports other than the first one listed. This field corresponds to theports
field of the Kubernetes Containers v1 core API. - predict
Route String - Immutable. HTTP path on the container to send prediction requests to. Vertex AI forwards requests sent using projects.locations.endpoints.predict to this path on the container's IP address and port. Vertex AI then returns the container's response in the API response. For example, if you set this field to
/foo
, then when Vertex AI receives a prediction request, it forwards the request body in a POST request to the/foo
path on the port of your container specified by the first value of thisModelContainerSpec
's ports field. If you don't specify this field, it defaults to the following value when you deploy this Model to an Endpoint: /v1/endpoints/ENDPOINT/deployedModels/DEPLOYED_MODEL:predict The placeholders in this value are replaced as follows: * ENDPOINT: The last segment (followingendpoints/
)of the Endpoint.name][] field of the Endpoint where this Model has been deployed. (Vertex AI makes this value available to your container code as theAIP_ENDPOINT_ID
environment variable.) * DEPLOYED_MODEL: DeployedModel.id of theDeployedModel
. (Vertex AI makes this value available to your container code as theAIP_DEPLOYED_MODEL_ID
environment variable.) - String
- Immutable. The amount of the VM memory to reserve as the shared memory for the model in megabytes. TODO (b/306244185): Revise documentation before exposing.
- startup
Probe Property Map - Immutable. Specification for Kubernetes startup probe. TODO (b/306244185): Revise documentation before exposing.
GoogleCloudAiplatformV1Port, GoogleCloudAiplatformV1PortArgs
- Container
Port int - The number of the port to expose on the pod's IP address. Must be a valid port number, between 1 and 65535 inclusive.
- Container
Port int - The number of the port to expose on the pod's IP address. Must be a valid port number, between 1 and 65535 inclusive.
- container
Port Integer - The number of the port to expose on the pod's IP address. Must be a valid port number, between 1 and 65535 inclusive.
- container
Port number - The number of the port to expose on the pod's IP address. Must be a valid port number, between 1 and 65535 inclusive.
- container_
port int - The number of the port to expose on the pod's IP address. Must be a valid port number, between 1 and 65535 inclusive.
- container
Port Number - The number of the port to expose on the pod's IP address. Must be a valid port number, between 1 and 65535 inclusive.
GoogleCloudAiplatformV1PortResponse, GoogleCloudAiplatformV1PortResponseArgs
- Container
Port int - The number of the port to expose on the pod's IP address. Must be a valid port number, between 1 and 65535 inclusive.
- Container
Port int - The number of the port to expose on the pod's IP address. Must be a valid port number, between 1 and 65535 inclusive.
- container
Port Integer - The number of the port to expose on the pod's IP address. Must be a valid port number, between 1 and 65535 inclusive.
- container
Port number - The number of the port to expose on the pod's IP address. Must be a valid port number, between 1 and 65535 inclusive.
- container_
port int - The number of the port to expose on the pod's IP address. Must be a valid port number, between 1 and 65535 inclusive.
- container
Port Number - The number of the port to expose on the pod's IP address. Must be a valid port number, between 1 and 65535 inclusive.
GoogleCloudAiplatformV1PredictSchemata, GoogleCloudAiplatformV1PredictSchemataArgs
- Instance
Schema stringUri - Immutable. Points to a YAML file stored on Google Cloud Storage describing the format of a single instance, which are used in PredictRequest.instances, ExplainRequest.instances and BatchPredictionJob.input_config. The schema is defined as an OpenAPI 3.0.2 Schema Object. AutoML Models always have this field populated by Vertex AI. 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.
- Parameters
Schema stringUri - Immutable. Points to a YAML file stored on Google Cloud Storage describing the parameters of prediction and explanation via PredictRequest.parameters, ExplainRequest.parameters and BatchPredictionJob.model_parameters. The schema is defined as an OpenAPI 3.0.2 Schema Object. AutoML Models always have this field populated by Vertex AI, if no parameters are supported, then it 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.
- Prediction
Schema stringUri - Immutable. Points to a YAML file stored on Google Cloud Storage describing the format of a single prediction produced by this Model, which are returned via PredictResponse.predictions, ExplainResponse.explanations, and BatchPredictionJob.output_config. The schema is defined as an OpenAPI 3.0.2 Schema Object. AutoML Models always have this field populated by Vertex AI. 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.
- Instance
Schema stringUri - Immutable. Points to a YAML file stored on Google Cloud Storage describing the format of a single instance, which are used in PredictRequest.instances, ExplainRequest.instances and BatchPredictionJob.input_config. The schema is defined as an OpenAPI 3.0.2 Schema Object. AutoML Models always have this field populated by Vertex AI. 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.
- Parameters
Schema stringUri - Immutable. Points to a YAML file stored on Google Cloud Storage describing the parameters of prediction and explanation via PredictRequest.parameters, ExplainRequest.parameters and BatchPredictionJob.model_parameters. The schema is defined as an OpenAPI 3.0.2 Schema Object. AutoML Models always have this field populated by Vertex AI, if no parameters are supported, then it 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.
- Prediction
Schema stringUri - Immutable. Points to a YAML file stored on Google Cloud Storage describing the format of a single prediction produced by this Model, which are returned via PredictResponse.predictions, ExplainResponse.explanations, and BatchPredictionJob.output_config. The schema is defined as an OpenAPI 3.0.2 Schema Object. AutoML Models always have this field populated by Vertex AI. 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.
- instance
Schema StringUri - Immutable. Points to a YAML file stored on Google Cloud Storage describing the format of a single instance, which are used in PredictRequest.instances, ExplainRequest.instances and BatchPredictionJob.input_config. The schema is defined as an OpenAPI 3.0.2 Schema Object. AutoML Models always have this field populated by Vertex AI. 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.
- parameters
Schema StringUri - Immutable. Points to a YAML file stored on Google Cloud Storage describing the parameters of prediction and explanation via PredictRequest.parameters, ExplainRequest.parameters and BatchPredictionJob.model_parameters. The schema is defined as an OpenAPI 3.0.2 Schema Object. AutoML Models always have this field populated by Vertex AI, if no parameters are supported, then it 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.
- prediction
Schema StringUri - Immutable. Points to a YAML file stored on Google Cloud Storage describing the format of a single prediction produced by this Model, which are returned via PredictResponse.predictions, ExplainResponse.explanations, and BatchPredictionJob.output_config. The schema is defined as an OpenAPI 3.0.2 Schema Object. AutoML Models always have this field populated by Vertex AI. 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.
- instance
Schema stringUri - Immutable. Points to a YAML file stored on Google Cloud Storage describing the format of a single instance, which are used in PredictRequest.instances, ExplainRequest.instances and BatchPredictionJob.input_config. The schema is defined as an OpenAPI 3.0.2 Schema Object. AutoML Models always have this field populated by Vertex AI. 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.
- parameters
Schema stringUri - Immutable. Points to a YAML file stored on Google Cloud Storage describing the parameters of prediction and explanation via PredictRequest.parameters, ExplainRequest.parameters and BatchPredictionJob.model_parameters. The schema is defined as an OpenAPI 3.0.2 Schema Object. AutoML Models always have this field populated by Vertex AI, if no parameters are supported, then it 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.
- prediction
Schema stringUri - Immutable. Points to a YAML file stored on Google Cloud Storage describing the format of a single prediction produced by this Model, which are returned via PredictResponse.predictions, ExplainResponse.explanations, and BatchPredictionJob.output_config. The schema is defined as an OpenAPI 3.0.2 Schema Object. AutoML Models always have this field populated by Vertex AI. 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.
- instance_
schema_ struri - Immutable. Points to a YAML file stored on Google Cloud Storage describing the format of a single instance, which are used in PredictRequest.instances, ExplainRequest.instances and BatchPredictionJob.input_config. The schema is defined as an OpenAPI 3.0.2 Schema Object. AutoML Models always have this field populated by Vertex AI. 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.
- parameters_
schema_ struri - Immutable. Points to a YAML file stored on Google Cloud Storage describing the parameters of prediction and explanation via PredictRequest.parameters, ExplainRequest.parameters and BatchPredictionJob.model_parameters. The schema is defined as an OpenAPI 3.0.2 Schema Object. AutoML Models always have this field populated by Vertex AI, if no parameters are supported, then it 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.
- prediction_
schema_ struri - Immutable. Points to a YAML file stored on Google Cloud Storage describing the format of a single prediction produced by this Model, which are returned via PredictResponse.predictions, ExplainResponse.explanations, and BatchPredictionJob.output_config. The schema is defined as an OpenAPI 3.0.2 Schema Object. AutoML Models always have this field populated by Vertex AI. 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.
- instance
Schema StringUri - Immutable. Points to a YAML file stored on Google Cloud Storage describing the format of a single instance, which are used in PredictRequest.instances, ExplainRequest.instances and BatchPredictionJob.input_config. The schema is defined as an OpenAPI 3.0.2 Schema Object. AutoML Models always have this field populated by Vertex AI. 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.
- parameters
Schema StringUri - Immutable. Points to a YAML file stored on Google Cloud Storage describing the parameters of prediction and explanation via PredictRequest.parameters, ExplainRequest.parameters and BatchPredictionJob.model_parameters. The schema is defined as an OpenAPI 3.0.2 Schema Object. AutoML Models always have this field populated by Vertex AI, if no parameters are supported, then it 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.
- prediction
Schema StringUri - Immutable. Points to a YAML file stored on Google Cloud Storage describing the format of a single prediction produced by this Model, which are returned via PredictResponse.predictions, ExplainResponse.explanations, and BatchPredictionJob.output_config. The schema is defined as an OpenAPI 3.0.2 Schema Object. AutoML Models always have this field populated by Vertex AI. 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.
GoogleCloudAiplatformV1PredictSchemataResponse, GoogleCloudAiplatformV1PredictSchemataResponseArgs
- Instance
Schema stringUri - Immutable. Points to a YAML file stored on Google Cloud Storage describing the format of a single instance, which are used in PredictRequest.instances, ExplainRequest.instances and BatchPredictionJob.input_config. The schema is defined as an OpenAPI 3.0.2 Schema Object. AutoML Models always have this field populated by Vertex AI. 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.
- Parameters
Schema stringUri - Immutable. Points to a YAML file stored on Google Cloud Storage describing the parameters of prediction and explanation via PredictRequest.parameters, ExplainRequest.parameters and BatchPredictionJob.model_parameters. The schema is defined as an OpenAPI 3.0.2 Schema Object. AutoML Models always have this field populated by Vertex AI, if no parameters are supported, then it 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.
- Prediction
Schema stringUri - Immutable. Points to a YAML file stored on Google Cloud Storage describing the format of a single prediction produced by this Model, which are returned via PredictResponse.predictions, ExplainResponse.explanations, and BatchPredictionJob.output_config. The schema is defined as an OpenAPI 3.0.2 Schema Object. AutoML Models always have this field populated by Vertex AI. 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.
- Instance
Schema stringUri - Immutable. Points to a YAML file stored on Google Cloud Storage describing the format of a single instance, which are used in PredictRequest.instances, ExplainRequest.instances and BatchPredictionJob.input_config. The schema is defined as an OpenAPI 3.0.2 Schema Object. AutoML Models always have this field populated by Vertex AI. 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.
- Parameters
Schema stringUri - Immutable. Points to a YAML file stored on Google Cloud Storage describing the parameters of prediction and explanation via PredictRequest.parameters, ExplainRequest.parameters and BatchPredictionJob.model_parameters. The schema is defined as an OpenAPI 3.0.2 Schema Object. AutoML Models always have this field populated by Vertex AI, if no parameters are supported, then it 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.
- Prediction
Schema stringUri - Immutable. Points to a YAML file stored on Google Cloud Storage describing the format of a single prediction produced by this Model, which are returned via PredictResponse.predictions, ExplainResponse.explanations, and BatchPredictionJob.output_config. The schema is defined as an OpenAPI 3.0.2 Schema Object. AutoML Models always have this field populated by Vertex AI. 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.
- instance
Schema StringUri - Immutable. Points to a YAML file stored on Google Cloud Storage describing the format of a single instance, which are used in PredictRequest.instances, ExplainRequest.instances and BatchPredictionJob.input_config. The schema is defined as an OpenAPI 3.0.2 Schema Object. AutoML Models always have this field populated by Vertex AI. 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.
- parameters
Schema StringUri - Immutable. Points to a YAML file stored on Google Cloud Storage describing the parameters of prediction and explanation via PredictRequest.parameters, ExplainRequest.parameters and BatchPredictionJob.model_parameters. The schema is defined as an OpenAPI 3.0.2 Schema Object. AutoML Models always have this field populated by Vertex AI, if no parameters are supported, then it 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.
- prediction
Schema StringUri - Immutable. Points to a YAML file stored on Google Cloud Storage describing the format of a single prediction produced by this Model, which are returned via PredictResponse.predictions, ExplainResponse.explanations, and BatchPredictionJob.output_config. The schema is defined as an OpenAPI 3.0.2 Schema Object. AutoML Models always have this field populated by Vertex AI. 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.
- instance
Schema stringUri - Immutable. Points to a YAML file stored on Google Cloud Storage describing the format of a single instance, which are used in PredictRequest.instances, ExplainRequest.instances and BatchPredictionJob.input_config. The schema is defined as an OpenAPI 3.0.2 Schema Object. AutoML Models always have this field populated by Vertex AI. 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.
- parameters
Schema stringUri - Immutable. Points to a YAML file stored on Google Cloud Storage describing the parameters of prediction and explanation via PredictRequest.parameters, ExplainRequest.parameters and BatchPredictionJob.model_parameters. The schema is defined as an OpenAPI 3.0.2 Schema Object. AutoML Models always have this field populated by Vertex AI, if no parameters are supported, then it 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.
- prediction
Schema stringUri - Immutable. Points to a YAML file stored on Google Cloud Storage describing the format of a single prediction produced by this Model, which are returned via PredictResponse.predictions, ExplainResponse.explanations, and BatchPredictionJob.output_config. The schema is defined as an OpenAPI 3.0.2 Schema Object. AutoML Models always have this field populated by Vertex AI. 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.
- instance_
schema_ struri - Immutable. Points to a YAML file stored on Google Cloud Storage describing the format of a single instance, which are used in PredictRequest.instances, ExplainRequest.instances and BatchPredictionJob.input_config. The schema is defined as an OpenAPI 3.0.2 Schema Object. AutoML Models always have this field populated by Vertex AI. 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.
- parameters_
schema_ struri - Immutable. Points to a YAML file stored on Google Cloud Storage describing the parameters of prediction and explanation via PredictRequest.parameters, ExplainRequest.parameters and BatchPredictionJob.model_parameters. The schema is defined as an OpenAPI 3.0.2 Schema Object. AutoML Models always have this field populated by Vertex AI, if no parameters are supported, then it 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.
- prediction_
schema_ struri - Immutable. Points to a YAML file stored on Google Cloud Storage describing the format of a single prediction produced by this Model, which are returned via PredictResponse.predictions, ExplainResponse.explanations, and BatchPredictionJob.output_config. The schema is defined as an OpenAPI 3.0.2 Schema Object. AutoML Models always have this field populated by Vertex AI. 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.
- instance
Schema StringUri - Immutable. Points to a YAML file stored on Google Cloud Storage describing the format of a single instance, which are used in PredictRequest.instances, ExplainRequest.instances and BatchPredictionJob.input_config. The schema is defined as an OpenAPI 3.0.2 Schema Object. AutoML Models always have this field populated by Vertex AI. 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.
- parameters
Schema StringUri - Immutable. Points to a YAML file stored on Google Cloud Storage describing the parameters of prediction and explanation via PredictRequest.parameters, ExplainRequest.parameters and BatchPredictionJob.model_parameters. The schema is defined as an OpenAPI 3.0.2 Schema Object. AutoML Models always have this field populated by Vertex AI, if no parameters are supported, then it 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.
- prediction
Schema StringUri - Immutable. Points to a YAML file stored on Google Cloud Storage describing the format of a single prediction produced by this Model, which are returned via PredictResponse.predictions, ExplainResponse.explanations, and BatchPredictionJob.output_config. The schema is defined as an OpenAPI 3.0.2 Schema Object. AutoML Models always have this field populated by Vertex AI. 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.
GoogleCloudAiplatformV1Presets, GoogleCloudAiplatformV1PresetsArgs
- Modality
Pulumi.
Google Native. Aiplatform. V1. Google Cloud Aiplatform V1Presets Modality - The modality of the uploaded model, which automatically configures the distance measurement and feature normalization for the underlying example index and queries. If your model does not precisely fit one of these types, it is okay to choose the closest type.
- Query
Pulumi.
Google Native. Aiplatform. V1. Google Cloud Aiplatform V1Presets Query - Preset option controlling parameters for speed-precision trade-off when querying for examples. If omitted, defaults to
PRECISE
.
- Modality
Google
Cloud Aiplatform V1Presets Modality - The modality of the uploaded model, which automatically configures the distance measurement and feature normalization for the underlying example index and queries. If your model does not precisely fit one of these types, it is okay to choose the closest type.
- Query
Google
Cloud Aiplatform V1Presets Query - Preset option controlling parameters for speed-precision trade-off when querying for examples. If omitted, defaults to
PRECISE
.
- modality
Google
Cloud Aiplatform V1Presets Modality - The modality of the uploaded model, which automatically configures the distance measurement and feature normalization for the underlying example index and queries. If your model does not precisely fit one of these types, it is okay to choose the closest type.
- query
Google
Cloud Aiplatform V1Presets Query - Preset option controlling parameters for speed-precision trade-off when querying for examples. If omitted, defaults to
PRECISE
.
- modality
Google
Cloud Aiplatform V1Presets Modality - The modality of the uploaded model, which automatically configures the distance measurement and feature normalization for the underlying example index and queries. If your model does not precisely fit one of these types, it is okay to choose the closest type.
- query
Google
Cloud Aiplatform V1Presets Query - Preset option controlling parameters for speed-precision trade-off when querying for examples. If omitted, defaults to
PRECISE
.
- modality
Google
Cloud Aiplatform V1Presets Modality - The modality of the uploaded model, which automatically configures the distance measurement and feature normalization for the underlying example index and queries. If your model does not precisely fit one of these types, it is okay to choose the closest type.
- query
Google
Cloud Aiplatform V1Presets Query - Preset option controlling parameters for speed-precision trade-off when querying for examples. If omitted, defaults to
PRECISE
.
- modality "MODALITY_UNSPECIFIED" | "IMAGE" | "TEXT" | "TABULAR"
- The modality of the uploaded model, which automatically configures the distance measurement and feature normalization for the underlying example index and queries. If your model does not precisely fit one of these types, it is okay to choose the closest type.
- query "PRECISE" | "FAST"
- Preset option controlling parameters for speed-precision trade-off when querying for examples. If omitted, defaults to
PRECISE
.
GoogleCloudAiplatformV1PresetsModality, GoogleCloudAiplatformV1PresetsModalityArgs
- Modality
Unspecified - MODALITY_UNSPECIFIEDShould not be set. Added as a recommended best practice for enums
- Image
- IMAGEIMAGE modality
- Text
- TEXTTEXT modality
- Tabular
- TABULARTABULAR modality
- Google
Cloud Aiplatform V1Presets Modality Modality Unspecified - MODALITY_UNSPECIFIEDShould not be set. Added as a recommended best practice for enums
- Google
Cloud Aiplatform V1Presets Modality Image - IMAGEIMAGE modality
- Google
Cloud Aiplatform V1Presets Modality Text - TEXTTEXT modality
- Google
Cloud Aiplatform V1Presets Modality Tabular - TABULARTABULAR modality
- Modality
Unspecified - MODALITY_UNSPECIFIEDShould not be set. Added as a recommended best practice for enums
- Image
- IMAGEIMAGE modality
- Text
- TEXTTEXT modality
- Tabular
- TABULARTABULAR modality
- Modality
Unspecified - MODALITY_UNSPECIFIEDShould not be set. Added as a recommended best practice for enums
- Image
- IMAGEIMAGE modality
- Text
- TEXTTEXT modality
- Tabular
- TABULARTABULAR modality
- MODALITY_UNSPECIFIED
- MODALITY_UNSPECIFIEDShould not be set. Added as a recommended best practice for enums
- IMAGE
- IMAGEIMAGE modality
- TEXT
- TEXTTEXT modality
- TABULAR
- TABULARTABULAR modality
- "MODALITY_UNSPECIFIED"
- MODALITY_UNSPECIFIEDShould not be set. Added as a recommended best practice for enums
- "IMAGE"
- IMAGEIMAGE modality
- "TEXT"
- TEXTTEXT modality
- "TABULAR"
- TABULARTABULAR modality
GoogleCloudAiplatformV1PresetsQuery, GoogleCloudAiplatformV1PresetsQueryArgs
- Precise
- PRECISEMore precise neighbors as a trade-off against slower response.
- Fast
- FASTFaster response as a trade-off against less precise neighbors.
- Google
Cloud Aiplatform V1Presets Query Precise - PRECISEMore precise neighbors as a trade-off against slower response.
- Google
Cloud Aiplatform V1Presets Query Fast - FASTFaster response as a trade-off against less precise neighbors.
- Precise
- PRECISEMore precise neighbors as a trade-off against slower response.
- Fast
- FASTFaster response as a trade-off against less precise neighbors.
- Precise
- PRECISEMore precise neighbors as a trade-off against slower response.
- Fast
- FASTFaster response as a trade-off against less precise neighbors.
- PRECISE
- PRECISEMore precise neighbors as a trade-off against slower response.
- FAST
- FASTFaster response as a trade-off against less precise neighbors.
- "PRECISE"
- PRECISEMore precise neighbors as a trade-off against slower response.
- "FAST"
- FASTFaster response as a trade-off against less precise neighbors.
GoogleCloudAiplatformV1PresetsResponse, GoogleCloudAiplatformV1PresetsResponseArgs
- Modality string
- The modality of the uploaded model, which automatically configures the distance measurement and feature normalization for the underlying example index and queries. If your model does not precisely fit one of these types, it is okay to choose the closest type.
- Query string
- Preset option controlling parameters for speed-precision trade-off when querying for examples. If omitted, defaults to
PRECISE
.
- Modality string
- The modality of the uploaded model, which automatically configures the distance measurement and feature normalization for the underlying example index and queries. If your model does not precisely fit one of these types, it is okay to choose the closest type.
- Query string
- Preset option controlling parameters for speed-precision trade-off when querying for examples. If omitted, defaults to
PRECISE
.
- modality String
- The modality of the uploaded model, which automatically configures the distance measurement and feature normalization for the underlying example index and queries. If your model does not precisely fit one of these types, it is okay to choose the closest type.
- query String
- Preset option controlling parameters for speed-precision trade-off when querying for examples. If omitted, defaults to
PRECISE
.
- modality string
- The modality of the uploaded model, which automatically configures the distance measurement and feature normalization for the underlying example index and queries. If your model does not precisely fit one of these types, it is okay to choose the closest type.
- query string
- Preset option controlling parameters for speed-precision trade-off when querying for examples. If omitted, defaults to
PRECISE
.
- modality str
- The modality of the uploaded model, which automatically configures the distance measurement and feature normalization for the underlying example index and queries. If your model does not precisely fit one of these types, it is okay to choose the closest type.
- query str
- Preset option controlling parameters for speed-precision trade-off when querying for examples. If omitted, defaults to
PRECISE
.
- modality String
- The modality of the uploaded model, which automatically configures the distance measurement and feature normalization for the underlying example index and queries. If your model does not precisely fit one of these types, it is okay to choose the closest type.
- query String
- Preset option controlling parameters for speed-precision trade-off when querying for examples. If omitted, defaults to
PRECISE
.
GoogleCloudAiplatformV1Probe, GoogleCloudAiplatformV1ProbeArgs
- Exec
Pulumi.
Google Native. Aiplatform. V1. Inputs. Google Cloud Aiplatform V1Probe Exec Action - Exec specifies the action to take.
- Period
Seconds int - How often (in seconds) to perform the probe. Default to 10 seconds. Minimum value is 1. Must be less than timeout_seconds. Maps to Kubernetes probe argument 'periodSeconds'.
- Timeout
Seconds int - Number of seconds after which the probe times out. Defaults to 1 second. Minimum value is 1. Must be greater or equal to period_seconds. Maps to Kubernetes probe argument 'timeoutSeconds'.
- Exec
Google
Cloud Aiplatform V1Probe Exec Action - Exec specifies the action to take.
- Period
Seconds int - How often (in seconds) to perform the probe. Default to 10 seconds. Minimum value is 1. Must be less than timeout_seconds. Maps to Kubernetes probe argument 'periodSeconds'.
- Timeout
Seconds int - Number of seconds after which the probe times out. Defaults to 1 second. Minimum value is 1. Must be greater or equal to period_seconds. Maps to Kubernetes probe argument 'timeoutSeconds'.
- exec
Google
Cloud Aiplatform V1Probe Exec Action - Exec specifies the action to take.
- period
Seconds Integer - How often (in seconds) to perform the probe. Default to 10 seconds. Minimum value is 1. Must be less than timeout_seconds. Maps to Kubernetes probe argument 'periodSeconds'.
- timeout
Seconds Integer - Number of seconds after which the probe times out. Defaults to 1 second. Minimum value is 1. Must be greater or equal to period_seconds. Maps to Kubernetes probe argument 'timeoutSeconds'.
- exec
Google
Cloud Aiplatform V1Probe Exec Action - Exec specifies the action to take.
- period
Seconds number - How often (in seconds) to perform the probe. Default to 10 seconds. Minimum value is 1. Must be less than timeout_seconds. Maps to Kubernetes probe argument 'periodSeconds'.
- timeout
Seconds number - Number of seconds after which the probe times out. Defaults to 1 second. Minimum value is 1. Must be greater or equal to period_seconds. Maps to Kubernetes probe argument 'timeoutSeconds'.
- exec_
Google
Cloud Aiplatform V1Probe Exec Action - Exec specifies the action to take.
- period_
seconds int - How often (in seconds) to perform the probe. Default to 10 seconds. Minimum value is 1. Must be less than timeout_seconds. Maps to Kubernetes probe argument 'periodSeconds'.
- timeout_
seconds int - Number of seconds after which the probe times out. Defaults to 1 second. Minimum value is 1. Must be greater or equal to period_seconds. Maps to Kubernetes probe argument 'timeoutSeconds'.
- exec Property Map
- Exec specifies the action to take.
- period
Seconds Number - How often (in seconds) to perform the probe. Default to 10 seconds. Minimum value is 1. Must be less than timeout_seconds. Maps to Kubernetes probe argument 'periodSeconds'.
- timeout
Seconds Number - Number of seconds after which the probe times out. Defaults to 1 second. Minimum value is 1. Must be greater or equal to period_seconds. Maps to Kubernetes probe argument 'timeoutSeconds'.
GoogleCloudAiplatformV1ProbeExecAction, GoogleCloudAiplatformV1ProbeExecActionArgs
- Command List<string>
- Command is the command line to execute inside the container, the working directory for the command is root ('/') in the container's filesystem. The command is simply exec'd, it is not run inside a shell, so traditional shell instructions ('|', etc) won't work. To use a shell, you need to explicitly call out to that shell. Exit status of 0 is treated as live/healthy and non-zero is unhealthy.
- Command []string
- Command is the command line to execute inside the container, the working directory for the command is root ('/') in the container's filesystem. The command is simply exec'd, it is not run inside a shell, so traditional shell instructions ('|', etc) won't work. To use a shell, you need to explicitly call out to that shell. Exit status of 0 is treated as live/healthy and non-zero is unhealthy.
- command List<String>
- Command is the command line to execute inside the container, the working directory for the command is root ('/') in the container's filesystem. The command is simply exec'd, it is not run inside a shell, so traditional shell instructions ('|', etc) won't work. To use a shell, you need to explicitly call out to that shell. Exit status of 0 is treated as live/healthy and non-zero is unhealthy.
- command string[]
- Command is the command line to execute inside the container, the working directory for the command is root ('/') in the container's filesystem. The command is simply exec'd, it is not run inside a shell, so traditional shell instructions ('|', etc) won't work. To use a shell, you need to explicitly call out to that shell. Exit status of 0 is treated as live/healthy and non-zero is unhealthy.
- command Sequence[str]
- Command is the command line to execute inside the container, the working directory for the command is root ('/') in the container's filesystem. The command is simply exec'd, it is not run inside a shell, so traditional shell instructions ('|', etc) won't work. To use a shell, you need to explicitly call out to that shell. Exit status of 0 is treated as live/healthy and non-zero is unhealthy.
- command List<String>
- Command is the command line to execute inside the container, the working directory for the command is root ('/') in the container's filesystem. The command is simply exec'd, it is not run inside a shell, so traditional shell instructions ('|', etc) won't work. To use a shell, you need to explicitly call out to that shell. Exit status of 0 is treated as live/healthy and non-zero is unhealthy.
GoogleCloudAiplatformV1ProbeExecActionResponse, GoogleCloudAiplatformV1ProbeExecActionResponseArgs
- Command List<string>
- Command is the command line to execute inside the container, the working directory for the command is root ('/') in the container's filesystem. The command is simply exec'd, it is not run inside a shell, so traditional shell instructions ('|', etc) won't work. To use a shell, you need to explicitly call out to that shell. Exit status of 0 is treated as live/healthy and non-zero is unhealthy.