Interface ExplainRequestOrBuilder (0.6.0)

public interface ExplainRequestOrBuilder extends MessageOrBuilder

Implements

MessageOrBuilder

Methods

getDeployedModelId()

public abstract String getDeployedModelId()

If specified, this ExplainRequest will be served by the chosen DeployedModel, overriding Endpoint.traffic_split.

string deployed_model_id = 3;

Returns
TypeDescription
String

The deployedModelId.

getDeployedModelIdBytes()

public abstract ByteString getDeployedModelIdBytes()

If specified, this ExplainRequest will be served by the chosen DeployedModel, overriding Endpoint.traffic_split.

string deployed_model_id = 3;

Returns
TypeDescription
ByteString

The bytes for deployedModelId.

getEndpoint()

public abstract String getEndpoint()

Required. The name of the Endpoint requested to serve the explanation. Format: projects/{project}/locations/{location}/endpoints/{endpoint}

string endpoint = 1 [(.google.api.field_behavior) = REQUIRED, (.google.api.resource_reference) = { ... }

Returns
TypeDescription
String

The endpoint.

getEndpointBytes()

public abstract ByteString getEndpointBytes()

Required. The name of the Endpoint requested to serve the explanation. Format: projects/{project}/locations/{location}/endpoints/{endpoint}

string endpoint = 1 [(.google.api.field_behavior) = REQUIRED, (.google.api.resource_reference) = { ... }

Returns
TypeDescription
ByteString

The bytes for endpoint.

getExplanationSpecOverride()

public abstract ExplanationSpecOverride getExplanationSpecOverride()

If specified, overrides the explanation_spec of the DeployedModel. Can be used for explaining prediction results with different configurations, such as:

  • Explaining top-5 predictions results as opposed to top-1;
  • Increasing path count or step count of the attribution methods to reduce approximate errors;
  • Using different baselines for explaining the prediction results.

.google.cloud.vertexai.v1.ExplanationSpecOverride explanation_spec_override = 5;

Returns
TypeDescription
ExplanationSpecOverride

The explanationSpecOverride.

getExplanationSpecOverrideOrBuilder()

public abstract ExplanationSpecOverrideOrBuilder getExplanationSpecOverrideOrBuilder()

If specified, overrides the explanation_spec of the DeployedModel. Can be used for explaining prediction results with different configurations, such as:

  • Explaining top-5 predictions results as opposed to top-1;
  • Increasing path count or step count of the attribution methods to reduce approximate errors;
  • Using different baselines for explaining the prediction results.

.google.cloud.vertexai.v1.ExplanationSpecOverride explanation_spec_override = 5;

Returns
TypeDescription
ExplanationSpecOverrideOrBuilder

getInstances(int index)

public abstract Value getInstances(int index)

Required. The instances that are the input to the explanation call. A DeployedModel may have an upper limit on the number of instances it supports per request, and when it is exceeded the explanation call errors in case of AutoML Models, or, in case of customer created Models, the behaviour is as documented by that Model. The schema of any single instance may be specified via Endpoint's DeployedModels' Model's PredictSchemata's instance_schema_uri.

repeated .google.protobuf.Value instances = 2 [(.google.api.field_behavior) = REQUIRED];

Parameter
NameDescription
indexint
Returns
TypeDescription
Value

getInstancesCount()

public abstract int getInstancesCount()

Required. The instances that are the input to the explanation call. A DeployedModel may have an upper limit on the number of instances it supports per request, and when it is exceeded the explanation call errors in case of AutoML Models, or, in case of customer created Models, the behaviour is as documented by that Model. The schema of any single instance may be specified via Endpoint's DeployedModels' Model's PredictSchemata's instance_schema_uri.

repeated .google.protobuf.Value instances = 2 [(.google.api.field_behavior) = REQUIRED];

Returns
TypeDescription
int

getInstancesList()

public abstract List<Value> getInstancesList()

Required. The instances that are the input to the explanation call. A DeployedModel may have an upper limit on the number of instances it supports per request, and when it is exceeded the explanation call errors in case of AutoML Models, or, in case of customer created Models, the behaviour is as documented by that Model. The schema of any single instance may be specified via Endpoint's DeployedModels' Model's PredictSchemata's instance_schema_uri.

repeated .google.protobuf.Value instances = 2 [(.google.api.field_behavior) = REQUIRED];

Returns
TypeDescription
List<Value>

getInstancesOrBuilder(int index)

public abstract ValueOrBuilder getInstancesOrBuilder(int index)

Required. The instances that are the input to the explanation call. A DeployedModel may have an upper limit on the number of instances it supports per request, and when it is exceeded the explanation call errors in case of AutoML Models, or, in case of customer created Models, the behaviour is as documented by that Model. The schema of any single instance may be specified via Endpoint's DeployedModels' Model's PredictSchemata's instance_schema_uri.

repeated .google.protobuf.Value instances = 2 [(.google.api.field_behavior) = REQUIRED];

Parameter
NameDescription
indexint
Returns
TypeDescription
ValueOrBuilder

getInstancesOrBuilderList()

public abstract List<? extends ValueOrBuilder> getInstancesOrBuilderList()

Required. The instances that are the input to the explanation call. A DeployedModel may have an upper limit on the number of instances it supports per request, and when it is exceeded the explanation call errors in case of AutoML Models, or, in case of customer created Models, the behaviour is as documented by that Model. The schema of any single instance may be specified via Endpoint's DeployedModels' Model's PredictSchemata's instance_schema_uri.

repeated .google.protobuf.Value instances = 2 [(.google.api.field_behavior) = REQUIRED];

Returns
TypeDescription
List<? extends com.google.protobuf.ValueOrBuilder>

getParameters()

public abstract Value getParameters()

The parameters that govern the prediction. The schema of the parameters may be specified via Endpoint's DeployedModels' Model's PredictSchemata's parameters_schema_uri.

.google.protobuf.Value parameters = 4;

Returns
TypeDescription
Value

The parameters.

getParametersOrBuilder()

public abstract ValueOrBuilder getParametersOrBuilder()

The parameters that govern the prediction. The schema of the parameters may be specified via Endpoint's DeployedModels' Model's PredictSchemata's parameters_schema_uri.

.google.protobuf.Value parameters = 4;

Returns
TypeDescription
ValueOrBuilder

hasExplanationSpecOverride()

public abstract boolean hasExplanationSpecOverride()

If specified, overrides the explanation_spec of the DeployedModel. Can be used for explaining prediction results with different configurations, such as:

  • Explaining top-5 predictions results as opposed to top-1;
  • Increasing path count or step count of the attribution methods to reduce approximate errors;
  • Using different baselines for explaining the prediction results.

.google.cloud.vertexai.v1.ExplanationSpecOverride explanation_spec_override = 5;

Returns
TypeDescription
boolean

Whether the explanationSpecOverride field is set.

hasParameters()

public abstract boolean hasParameters()

The parameters that govern the prediction. The schema of the parameters may be specified via Endpoint's DeployedModels' Model's PredictSchemata's parameters_schema_uri.

.google.protobuf.Value parameters = 4;

Returns
TypeDescription
boolean

Whether the parameters field is set.