CreateAIRecommendationJobRequest ¶

class CreateAIRecommendationJobRequest(TypedDict, closed=True):
    ai_recommendation_job_name: NotRequired[
        "capo_sagemaker.types.ai_entity_name.AIEntityName"
    ]
    """<p>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.</p>"""
    model_source: NotRequired["capo_sagemaker.types.ai_model_source.AIModelSource"]
    """<p>The source of the model to optimize. Specify the Amazon S3 location of the model artifacts.</p>"""
    output_config: NotRequired[
        "capo_sagemaker.types.ai_recommendation_output_config.AIRecommendationOutputConfig"
    ]
    """<p>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.</p>"""
    ai_workload_config_identifier: NotRequired[
        "capo_sagemaker.types.ai_resource_identifier.AIResourceIdentifier"
    ]
    """<p>The name or Amazon Resource Name (ARN) of the AI workload configuration to use for this recommendation job.</p>"""
    performance_target: NotRequired[
        "capo_sagemaker.types.ai_recommendation_performance_target.AIRecommendationPerformanceTarget"
    ]
    """<p>The performance targets for the recommendation job. Specify constraints on metrics such as time to first token (<code>ttft-ms</code>), <code>throughput</code>, or <code>cost</code>.</p>"""
    role_arn: NotRequired["capo_sagemaker.types.role_arn.RoleArn"]
    """<p>The Amazon Resource Name (ARN) of an IAM role that enables Amazon SageMaker AI to perform tasks on your behalf.</p>"""
    inference_specification: NotRequired[
        "capo_sagemaker.types.ai_recommendation_inference_specification.AIRecommendationInferenceSpecification"
    ]
    """<p>The inference framework configuration. Specify the framework (such as LMI or vLLM) for the recommendation job.</p>"""
    optimize_model: NotRequired[
        "capo_sagemaker.types.ai_recommendation_allow_optimization.AIRecommendationAllowOptimization"
    ]
    """<p>Whether to allow model optimization techniques such as quantization, speculative decoding, and kernel tuning. The default is <code>true</code>.</p>"""
    compute_spec: NotRequired[
        "capo_sagemaker.types.ai_recommendation_compute_spec.AIRecommendationComputeSpec"
    ]
    """<p>The compute resource specification for the recommendation job. You can specify up to 3 instance types to consider, and optionally provide capacity reservation configuration.</p>"""
    adapter_source: NotRequired[
        "capo_sagemaker.types.ai_adapter_source.AIAdapterSource"
    ]
    """<p>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.</p>"""
    tags: NotRequired["capo_sagemaker.types.tag_list.TagList"]
    """<p>The metadata that you apply to Amazon Web Services resources to help you categorize and organize them.</p>"""