Class AmazonSageMakerServiceSettings.Builder
java.lang.Object
co.elastic.clients.util.ObjectBuilderBase
co.elastic.clients.util.WithJsonObjectBuilderBase<AmazonSageMakerServiceSettings.Builder>
co.elastic.clients.elasticsearch.inference.AmazonSageMakerServiceSettings.Builder
- All Implemented Interfaces:
WithJson<AmazonSageMakerServiceSettings.Builder>
,ObjectBuilder<AmazonSageMakerServiceSettings>
- Enclosing class:
- AmazonSageMakerServiceSettings
public static class AmazonSageMakerServiceSettings.Builder
extends WithJsonObjectBuilderBase<AmazonSageMakerServiceSettings.Builder>
implements ObjectBuilder<AmazonSageMakerServiceSettings>
Builder for
AmazonSageMakerServiceSettings
.-
Constructor Summary
Constructors -
Method Summary
Modifier and TypeMethodDescriptionRequired - A valid AWS access key that has permissions to use Amazon SageMaker and access to models for invoking requests.api
(AmazonSageMakerApi value) Required - The API format to use when calling SageMaker.The maximum number of inputs in each batch.build()
Builds aAmazonSageMakerServiceSettings
.dimensions
(Integer value) The number of dimensions returned by the text embedding models.endpointName
(String value) Required - The name of the SageMaker endpoint.inferenceComponentName
(String value) The inference component to directly invoke when calling a multi-component endpoint.Required - The region that your endpoint or Amazon Resource Name (ARN) is deployed in.Required - A valid AWS secret key that is paired with theaccess_key
.protected AmazonSageMakerServiceSettings.Builder
self()
targetContainerHostname
(String value) The container to directly invoke when calling a multi-container endpoint.targetModel
(String value) The model ID when calling a multi-model endpoint.Methods inherited from class co.elastic.clients.util.WithJsonObjectBuilderBase
withJson
Methods inherited from class co.elastic.clients.util.ObjectBuilderBase
_checkSingleUse, _listAdd, _listAddAll, _mapPut, _mapPutAll
-
Constructor Details
-
Builder
public Builder()
-
-
Method Details
-
accessKey
Required - A valid AWS access key that has permissions to use Amazon SageMaker and access to models for invoking requests.API name:
access_key
-
endpointName
Required - The name of the SageMaker endpoint.API name:
endpoint_name
-
api
Required - The API format to use when calling SageMaker. Elasticsearch will convert the POST _inference request to this data format when invoking the SageMaker endpoint.API name:
api
-
region
Required - The region that your endpoint or Amazon Resource Name (ARN) is deployed in. The list of available regions per model can be found in the Amazon SageMaker documentation.API name:
region
-
secretKey
Required - A valid AWS secret key that is paired with theaccess_key
. For information about creating and managing access and secret keys, refer to the AWS documentation.API name:
secret_key
-
targetModel
The model ID when calling a multi-model endpoint.API name:
target_model
-
targetContainerHostname
The container to directly invoke when calling a multi-container endpoint.API name:
target_container_hostname
-
inferenceComponentName
The inference component to directly invoke when calling a multi-component endpoint.API name:
inference_component_name
-
batchSize
The maximum number of inputs in each batch. This value is used by inference ingestion pipelines when processing semantic values. It correlates to the number of times the SageMaker endpoint is invoked (one per batch of input).API name:
batch_size
-
dimensions
The number of dimensions returned by the text embedding models. If this value is not provided, then it is guessed by making invoking the endpoint for thetext_embedding
task.API name:
dimensions
-
self
- Specified by:
self
in classWithJsonObjectBuilderBase<AmazonSageMakerServiceSettings.Builder>
-
build
Builds aAmazonSageMakerServiceSettings
.- Specified by:
build
in interfaceObjectBuilder<AmazonSageMakerServiceSettings>
- Throws:
NullPointerException
- if some of the required fields are null.
-