Copyright | (c) 2013-2023 Brendan Hay |
---|---|
License | Mozilla Public License, v. 2.0. |
Maintainer | Brendan Hay |
Stability | auto-generated |
Portability | non-portable (GHC extensions) |
Safe Haskell | Safe-Inferred |
Language | Haskell2010 |
Creates an inference experiment using the configurations specified in the request.
Use this API to setup and schedule an experiment to compare model variants on a Amazon SageMaker inference endpoint. For more information about inference experiments, see Shadow tests.
Amazon SageMaker begins your experiment at the scheduled time and routes traffic to your endpoint's model variants based on your specified configuration.
While the experiment is in progress or after it has concluded, you can view metrics that compare your model variants. For more information, see View, monitor, and edit shadow tests.
Synopsis
- data CreateInferenceExperiment = CreateInferenceExperiment' {
- dataStorageConfig :: Maybe InferenceExperimentDataStorageConfig
- description :: Maybe Text
- kmsKey :: Maybe Text
- schedule :: Maybe InferenceExperimentSchedule
- tags :: Maybe [Tag]
- name :: Text
- type' :: InferenceExperimentType
- roleArn :: Text
- endpointName :: Text
- modelVariants :: NonEmpty ModelVariantConfig
- shadowModeConfig :: ShadowModeConfig
- newCreateInferenceExperiment :: Text -> InferenceExperimentType -> Text -> Text -> NonEmpty ModelVariantConfig -> ShadowModeConfig -> CreateInferenceExperiment
- createInferenceExperiment_dataStorageConfig :: Lens' CreateInferenceExperiment (Maybe InferenceExperimentDataStorageConfig)
- createInferenceExperiment_description :: Lens' CreateInferenceExperiment (Maybe Text)
- createInferenceExperiment_kmsKey :: Lens' CreateInferenceExperiment (Maybe Text)
- createInferenceExperiment_schedule :: Lens' CreateInferenceExperiment (Maybe InferenceExperimentSchedule)
- createInferenceExperiment_tags :: Lens' CreateInferenceExperiment (Maybe [Tag])
- createInferenceExperiment_name :: Lens' CreateInferenceExperiment Text
- createInferenceExperiment_type :: Lens' CreateInferenceExperiment InferenceExperimentType
- createInferenceExperiment_roleArn :: Lens' CreateInferenceExperiment Text
- createInferenceExperiment_endpointName :: Lens' CreateInferenceExperiment Text
- createInferenceExperiment_modelVariants :: Lens' CreateInferenceExperiment (NonEmpty ModelVariantConfig)
- createInferenceExperiment_shadowModeConfig :: Lens' CreateInferenceExperiment ShadowModeConfig
- data CreateInferenceExperimentResponse = CreateInferenceExperimentResponse' {}
- newCreateInferenceExperimentResponse :: Int -> Text -> CreateInferenceExperimentResponse
- createInferenceExperimentResponse_httpStatus :: Lens' CreateInferenceExperimentResponse Int
- createInferenceExperimentResponse_inferenceExperimentArn :: Lens' CreateInferenceExperimentResponse Text
Creating a Request
data CreateInferenceExperiment Source #
See: newCreateInferenceExperiment
smart constructor.
CreateInferenceExperiment' | |
|
Instances
newCreateInferenceExperiment Source #
:: Text | |
-> InferenceExperimentType | |
-> Text | |
-> Text | |
-> NonEmpty ModelVariantConfig | |
-> ShadowModeConfig | |
-> CreateInferenceExperiment |
Create a value of CreateInferenceExperiment
with all optional fields omitted.
Use generic-lens or optics to modify other optional fields.
The following record fields are available, with the corresponding lenses provided for backwards compatibility:
$sel:dataStorageConfig:CreateInferenceExperiment'
, createInferenceExperiment_dataStorageConfig
- The Amazon S3 location and configuration for storing inference request
and response data.
This is an optional parameter that you can use for data capture. For more information, see Capture data.
CreateInferenceExperiment
, createInferenceExperiment_description
- A description for the inference experiment.
CreateInferenceExperiment
, createInferenceExperiment_kmsKey
- The Amazon Web Services Key Management Service (Amazon Web Services KMS)
key that Amazon SageMaker uses to encrypt data on the storage volume
attached to the ML compute instance that hosts the endpoint. The
KmsKey
can be any of the following formats:
KMS key ID
"1234abcd-12ab-34cd-56ef-1234567890ab"
Amazon Resource Name (ARN) of a KMS key
"arn:aws:kms:us-west-2:111122223333:key/1234abcd-12ab-34cd-56ef-1234567890ab"
KMS key Alias
"alias/ExampleAlias"
Amazon Resource Name (ARN) of a KMS key Alias
"arn:aws:kms:us-west-2:111122223333:alias/ExampleAlias"
If you use a KMS key ID or an alias of your KMS key, the Amazon
SageMaker execution role must include permissions to call kms:Encrypt
.
If you don't provide a KMS key ID, Amazon SageMaker uses the default
KMS key for Amazon S3 for your role's account. Amazon SageMaker uses
server-side encryption with KMS managed keys for OutputDataConfig
. If
you use a bucket policy with an s3:PutObject
permission that only
allows objects with server-side encryption, set the condition key of
s3:x-amz-server-side-encryption
to "aws:kms"
. For more
information, see
KMS managed Encryption Keys
in the Amazon Simple Storage Service Developer Guide.
The KMS key policy must grant permission to the IAM role that you
specify in your CreateEndpoint
and UpdateEndpoint
requests. For more
information, see
Using Key Policies in Amazon Web Services KMS
in the Amazon Web Services Key Management Service Developer Guide.
CreateInferenceExperiment
, createInferenceExperiment_schedule
- The duration for which you want the inference experiment to run. If you
don't specify this field, the experiment automatically starts
immediately upon creation and concludes after 7 days.
CreateInferenceExperiment
, createInferenceExperiment_tags
- Array of key-value pairs. You can use tags to categorize your Amazon Web
Services resources in different ways, for example, by purpose, owner, or
environment. For more information, see
Tagging your Amazon Web Services Resources.
CreateInferenceExperiment
, createInferenceExperiment_name
- The name for the inference experiment.
CreateInferenceExperiment
, createInferenceExperiment_type
- The type of the inference experiment that you want to run. The following
types of experiments are possible:
ShadowMode
: You can use this type to validate a shadow variant. For more information, see Shadow tests.
CreateInferenceExperiment
, createInferenceExperiment_roleArn
- The ARN of the IAM role that Amazon SageMaker can assume to access model
artifacts and container images, and manage Amazon SageMaker Inference
endpoints for model deployment.
CreateInferenceExperiment
, createInferenceExperiment_endpointName
- The name of the Amazon SageMaker endpoint on which you want to run the
inference experiment.
$sel:modelVariants:CreateInferenceExperiment'
, createInferenceExperiment_modelVariants
- An array of ModelVariantConfig
objects. There is one for each variant
in the inference experiment. Each ModelVariantConfig
object in the
array describes the infrastructure configuration for the corresponding
variant.
$sel:shadowModeConfig:CreateInferenceExperiment'
, createInferenceExperiment_shadowModeConfig
- The configuration of ShadowMode
inference experiment type. Use this
field to specify a production variant which takes all the inference
requests, and a shadow variant to which Amazon SageMaker replicates a
percentage of the inference requests. For the shadow variant also
specify the percentage of requests that Amazon SageMaker replicates.
Request Lenses
createInferenceExperiment_dataStorageConfig :: Lens' CreateInferenceExperiment (Maybe InferenceExperimentDataStorageConfig) Source #
The Amazon S3 location and configuration for storing inference request and response data.
This is an optional parameter that you can use for data capture. For more information, see Capture data.
createInferenceExperiment_description :: Lens' CreateInferenceExperiment (Maybe Text) Source #
A description for the inference experiment.
createInferenceExperiment_kmsKey :: Lens' CreateInferenceExperiment (Maybe Text) Source #
The Amazon Web Services Key Management Service (Amazon Web Services KMS)
key that Amazon SageMaker uses to encrypt data on the storage volume
attached to the ML compute instance that hosts the endpoint. The
KmsKey
can be any of the following formats:
KMS key ID
"1234abcd-12ab-34cd-56ef-1234567890ab"
Amazon Resource Name (ARN) of a KMS key
"arn:aws:kms:us-west-2:111122223333:key/1234abcd-12ab-34cd-56ef-1234567890ab"
KMS key Alias
"alias/ExampleAlias"
Amazon Resource Name (ARN) of a KMS key Alias
"arn:aws:kms:us-west-2:111122223333:alias/ExampleAlias"
If you use a KMS key ID or an alias of your KMS key, the Amazon
SageMaker execution role must include permissions to call kms:Encrypt
.
If you don't provide a KMS key ID, Amazon SageMaker uses the default
KMS key for Amazon S3 for your role's account. Amazon SageMaker uses
server-side encryption with KMS managed keys for OutputDataConfig
. If
you use a bucket policy with an s3:PutObject
permission that only
allows objects with server-side encryption, set the condition key of
s3:x-amz-server-side-encryption
to "aws:kms"
. For more
information, see
KMS managed Encryption Keys
in the Amazon Simple Storage Service Developer Guide.
The KMS key policy must grant permission to the IAM role that you
specify in your CreateEndpoint
and UpdateEndpoint
requests. For more
information, see
Using Key Policies in Amazon Web Services KMS
in the Amazon Web Services Key Management Service Developer Guide.
createInferenceExperiment_schedule :: Lens' CreateInferenceExperiment (Maybe InferenceExperimentSchedule) Source #
The duration for which you want the inference experiment to run. If you don't specify this field, the experiment automatically starts immediately upon creation and concludes after 7 days.
createInferenceExperiment_tags :: Lens' CreateInferenceExperiment (Maybe [Tag]) Source #
Array of key-value pairs. You can use tags to categorize your Amazon Web Services resources in different ways, for example, by purpose, owner, or environment. For more information, see Tagging your Amazon Web Services Resources.
createInferenceExperiment_name :: Lens' CreateInferenceExperiment Text Source #
The name for the inference experiment.
createInferenceExperiment_type :: Lens' CreateInferenceExperiment InferenceExperimentType Source #
The type of the inference experiment that you want to run. The following types of experiments are possible:
ShadowMode
: You can use this type to validate a shadow variant. For more information, see Shadow tests.
createInferenceExperiment_roleArn :: Lens' CreateInferenceExperiment Text Source #
The ARN of the IAM role that Amazon SageMaker can assume to access model artifacts and container images, and manage Amazon SageMaker Inference endpoints for model deployment.
createInferenceExperiment_endpointName :: Lens' CreateInferenceExperiment Text Source #
The name of the Amazon SageMaker endpoint on which you want to run the inference experiment.
createInferenceExperiment_modelVariants :: Lens' CreateInferenceExperiment (NonEmpty ModelVariantConfig) Source #
An array of ModelVariantConfig
objects. There is one for each variant
in the inference experiment. Each ModelVariantConfig
object in the
array describes the infrastructure configuration for the corresponding
variant.
createInferenceExperiment_shadowModeConfig :: Lens' CreateInferenceExperiment ShadowModeConfig Source #
The configuration of ShadowMode
inference experiment type. Use this
field to specify a production variant which takes all the inference
requests, and a shadow variant to which Amazon SageMaker replicates a
percentage of the inference requests. For the shadow variant also
specify the percentage of requests that Amazon SageMaker replicates.
Destructuring the Response
data CreateInferenceExperimentResponse Source #
See: newCreateInferenceExperimentResponse
smart constructor.
CreateInferenceExperimentResponse' | |
|
Instances
Generic CreateInferenceExperimentResponse Source # | |
Read CreateInferenceExperimentResponse Source # | |
Show CreateInferenceExperimentResponse Source # | |
NFData CreateInferenceExperimentResponse Source # | |
Defined in Amazonka.SageMaker.CreateInferenceExperiment rnf :: CreateInferenceExperimentResponse -> () # | |
Eq CreateInferenceExperimentResponse Source # | |
type Rep CreateInferenceExperimentResponse Source # | |
Defined in Amazonka.SageMaker.CreateInferenceExperiment type Rep CreateInferenceExperimentResponse = D1 ('MetaData "CreateInferenceExperimentResponse" "Amazonka.SageMaker.CreateInferenceExperiment" "amazonka-sagemaker-2.0-9SyrKZ4KqhsL1qX9u3ILA3" 'False) (C1 ('MetaCons "CreateInferenceExperimentResponse'" 'PrefixI 'True) (S1 ('MetaSel ('Just "httpStatus") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 Int) :*: S1 ('MetaSel ('Just "inferenceExperimentArn") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 Text))) |
newCreateInferenceExperimentResponse Source #
:: Int | |
-> Text |
|
-> CreateInferenceExperimentResponse |
Create a value of CreateInferenceExperimentResponse
with all optional fields omitted.
Use generic-lens or optics to modify other optional fields.
The following record fields are available, with the corresponding lenses provided for backwards compatibility:
$sel:httpStatus:CreateInferenceExperimentResponse'
, createInferenceExperimentResponse_httpStatus
- The response's http status code.
$sel:inferenceExperimentArn:CreateInferenceExperimentResponse'
, createInferenceExperimentResponse_inferenceExperimentArn
- The ARN for your inference experiment.
Response Lenses
createInferenceExperimentResponse_httpStatus :: Lens' CreateInferenceExperimentResponse Int Source #
The response's http status code.
createInferenceExperimentResponse_inferenceExperimentArn :: Lens' CreateInferenceExperimentResponse Text Source #
The ARN for your inference experiment.