Class: Aws::SageMaker::Types::CreateAIRecommendationJobRequest

Inherits:

Struct

• Object
• Struct
• Aws::SageMaker::Types::CreateAIRecommendationJobRequest

Includes:

Aws::Structure

Defined in:

lib/aws-sdk-sagemaker/types.rb

Overview

See Also:

• AWS API Documentation

Constant Summary

SENSITIVE =

[]

Instance Attribute Summary

• #adapter_source ⇒ Types::AIAdapterSource

  The LoRA adapter source for the recommendation job.

• #ai_recommendation_job_name ⇒ String

  The name of the AI recommendation job.

• #ai_workload_config_identifier ⇒ String

  The name or Amazon Resource Name (ARN) of the AI workload configuration to use for this recommendation job.

• #compute_spec ⇒ Types::AIRecommendationComputeSpec

  The compute resource specification for the recommendation job.

• #inference_specification ⇒ Types::AIRecommendationInferenceSpecification

  The inference framework configuration.

• #model_source ⇒ Types::AIModelSource

  The source of the model to optimize.

• #optimize_model ⇒ Boolean

  Whether to allow model optimization techniques such as quantization, speculative decoding, and kernel tuning.

• #output_config ⇒ Types::AIRecommendationOutputConfig

  The output configuration for the recommendation job, including the Amazon S3 location for results and an optional model package group where the optimized model is registered.

• #performance_target ⇒ Types::AIRecommendationPerformanceTarget

  The performance targets for the recommendation job.

• #role_arn ⇒ String

  The Amazon Resource Name (ARN) of an IAM role that enables Amazon SageMaker AI to perform tasks on your behalf.

• #tags ⇒ Array<Types::Tag>

  The metadata that you apply to Amazon Web Services resources to help you categorize and organize them.

Instance Attribute Details

#adapter_source ⇒ Types::AIAdapterSource

The LoRA adapter source for the recommendation job. Specify either a list of model package ARNs or Amazon S3 URIs for your LoRA adapters. When this parameter is absent, the recommendation job runs without LoRA adapter support.

Returns:

• (Types::AIAdapterSource)

# File 'lib/aws-sdk-sagemaker/types.rb', line 9118

class CreateAIRecommendationJobRequest < Struct.new(
  :ai_recommendation_job_name,
  :model_source,
  :output_config,
  :ai_workload_config_identifier,
  :performance_target,
  :role_arn,
  :inference_specification,
  :optimize_model,
  :compute_spec,
  :adapter_source,
  :tags)
  SENSITIVE = []
  include Aws::Structure
end

#ai_recommendation_job_name ⇒ String

The name of the AI recommendation job. The name must be unique within your Amazon Web Services account in the current Amazon Web Services Region.

Returns:

• (String)

# File 'lib/aws-sdk-sagemaker/types.rb', line 9118

class CreateAIRecommendationJobRequest < Struct.new(
  :ai_recommendation_job_name,
  :model_source,
  :output_config,
  :ai_workload_config_identifier,
  :performance_target,
  :role_arn,
  :inference_specification,
  :optimize_model,
  :compute_spec,
  :adapter_source,
  :tags)
  SENSITIVE = []
  include Aws::Structure
end

#ai_workload_config_identifier ⇒ String

The name or Amazon Resource Name (ARN) of the AI workload configuration to use for this recommendation job.

Returns:

• (String)

# File 'lib/aws-sdk-sagemaker/types.rb', line 9118

class CreateAIRecommendationJobRequest < Struct.new(
  :ai_recommendation_job_name,
  :model_source,
  :output_config,
  :ai_workload_config_identifier,
  :performance_target,
  :role_arn,
  :inference_specification,
  :optimize_model,
  :compute_spec,
  :adapter_source,
  :tags)
  SENSITIVE = []
  include Aws::Structure
end

#compute_spec ⇒ Types::AIRecommendationComputeSpec

The compute resource specification for the recommendation job. You can specify up to 3 instance types to consider, and optionally provide capacity reservation configuration.

Returns:

• (Types::AIRecommendationComputeSpec)

# File 'lib/aws-sdk-sagemaker/types.rb', line 9118

class CreateAIRecommendationJobRequest < Struct.new(
  :ai_recommendation_job_name,
  :model_source,
  :output_config,
  :ai_workload_config_identifier,
  :performance_target,
  :role_arn,
  :inference_specification,
  :optimize_model,
  :compute_spec,
  :adapter_source,
  :tags)
  SENSITIVE = []
  include Aws::Structure
end

#inference_specification ⇒ Types::AIRecommendationInferenceSpecification

The inference framework configuration. Specify the framework (such as LMI or vLLM) for the recommendation job.

Returns:

• (Types::AIRecommendationInferenceSpecification)

# File 'lib/aws-sdk-sagemaker/types.rb', line 9118

class CreateAIRecommendationJobRequest < Struct.new(
  :ai_recommendation_job_name,
  :model_source,
  :output_config,
  :ai_workload_config_identifier,
  :performance_target,
  :role_arn,
  :inference_specification,
  :optimize_model,
  :compute_spec,
  :adapter_source,
  :tags)
  SENSITIVE = []
  include Aws::Structure
end

#model_source ⇒ Types::AIModelSource

The source of the model to optimize. Specify the Amazon S3 location of the model artifacts.

Returns:

• (Types::AIModelSource)

# File 'lib/aws-sdk-sagemaker/types.rb', line 9118

class CreateAIRecommendationJobRequest < Struct.new(
  :ai_recommendation_job_name,
  :model_source,
  :output_config,
  :ai_workload_config_identifier,
  :performance_target,
  :role_arn,
  :inference_specification,
  :optimize_model,
  :compute_spec,
  :adapter_source,
  :tags)
  SENSITIVE = []
  include Aws::Structure
end

#optimize_model ⇒ Boolean

Whether to allow model optimization techniques such as quantization, speculative decoding, and kernel tuning. The default is true.

Returns:

• (Boolean)

# File 'lib/aws-sdk-sagemaker/types.rb', line 9118

class CreateAIRecommendationJobRequest < Struct.new(
  :ai_recommendation_job_name,
  :model_source,
  :output_config,
  :ai_workload_config_identifier,
  :performance_target,
  :role_arn,
  :inference_specification,
  :optimize_model,
  :compute_spec,
  :adapter_source,
  :tags)
  SENSITIVE = []
  include Aws::Structure
end

#output_config ⇒ Types::AIRecommendationOutputConfig

The output configuration for the recommendation job, including the Amazon S3 location for results and an optional model package group where the optimized model is registered.

Returns:

• (Types::AIRecommendationOutputConfig)

# File 'lib/aws-sdk-sagemaker/types.rb', line 9118

class CreateAIRecommendationJobRequest < Struct.new(
  :ai_recommendation_job_name,
  :model_source,
  :output_config,
  :ai_workload_config_identifier,
  :performance_target,
  :role_arn,
  :inference_specification,
  :optimize_model,
  :compute_spec,
  :adapter_source,
  :tags)
  SENSITIVE = []
  include Aws::Structure
end

#performance_target ⇒ Types::AIRecommendationPerformanceTarget

The performance targets for the recommendation job. Specify constraints on metrics such as time to first token (ttft-ms), throughput, or cost.

Returns:

• (Types::AIRecommendationPerformanceTarget)

# File 'lib/aws-sdk-sagemaker/types.rb', line 9118

class CreateAIRecommendationJobRequest < Struct.new(
  :ai_recommendation_job_name,
  :model_source,
  :output_config,
  :ai_workload_config_identifier,
  :performance_target,
  :role_arn,
  :inference_specification,
  :optimize_model,
  :compute_spec,
  :adapter_source,
  :tags)
  SENSITIVE = []
  include Aws::Structure
end

#role_arn ⇒ String

The Amazon Resource Name (ARN) of an IAM role that enables Amazon SageMaker AI to perform tasks on your behalf.

Returns:

• (String)

# File 'lib/aws-sdk-sagemaker/types.rb', line 9118

class CreateAIRecommendationJobRequest < Struct.new(
  :ai_recommendation_job_name,
  :model_source,
  :output_config,
  :ai_workload_config_identifier,
  :performance_target,
  :role_arn,
  :inference_specification,
  :optimize_model,
  :compute_spec,
  :adapter_source,
  :tags)
  SENSITIVE = []
  include Aws::Structure
end

#tags ⇒ Array<Types::Tag>

The metadata that you apply to Amazon Web Services resources to help you categorize and organize them.

Returns:

• (Array<Types::Tag>)

# File 'lib/aws-sdk-sagemaker/types.rb', line 9118

class CreateAIRecommendationJobRequest < Struct.new(
  :ai_recommendation_job_name,
  :model_source,
  :output_config,
  :ai_workload_config_identifier,
  :performance_target,
  :role_arn,
  :inference_specification,
  :optimize_model,
  :compute_spec,
  :adapter_source,
  :tags)
  SENSITIVE = []
  include Aws::Structure
end