Interface ModelConfiguration.Builder

  • Method Details

    • modelId

      The model to use for optimization. The value depends on the resource that you use:

      • If you use a base model, specify the model ID or its ARN. For a list of model IDs, see Models at a glance in the Amazon Bedrock User Guide.

      • If you use a cross-Region (system-defined) inference profile, specify the inference profile ID or its ARN. For a list of inference profile IDs, see Supported Regions and models for inference profiles in the Amazon Bedrock User Guide.

      • If you use an application inference profile, specify its full ARN, including the account ID and Region.

      Parameters:
      modelId - The model to use for optimization. The value depends on the resource that you use:

      • If you use a base model, specify the model ID or its ARN. For a list of model IDs, see Models at a glance in the Amazon Bedrock User Guide.

      • If you use a cross-Region (system-defined) inference profile, specify the inference profile ID or its ARN. For a list of inference profile IDs, see Supported Regions and models for inference profiles in the Amazon Bedrock User Guide.

      • If you use an application inference profile, specify its full ARN, including the account ID and Region.

      Returns:
      Returns a reference to this object so that method calls can be chained together.
    • inferenceConfig

      ModelConfiguration.Builder inferenceConfig(InferenceConfiguration inferenceConfig)

      The inference configuration for the model, including parameters such as maximum tokens, temperature, and top-p.

      Parameters:
      inferenceConfig - The inference configuration for the model, including parameters such as maximum tokens, temperature, and top-p.
      Returns:
      Returns a reference to this object so that method calls can be chained together.
    • inferenceConfig

      default ModelConfiguration.Builder inferenceConfig(Consumer<InferenceConfiguration.Builder> inferenceConfig)

      The inference configuration for the model, including parameters such as maximum tokens, temperature, and top-p.

      This is a convenience method that creates an instance of the InferenceConfiguration.Builder avoiding the need to create one manually via InferenceConfiguration.builder().

      When the Consumer completes, SdkBuilder.build() is called immediately and its result is passed to inferenceConfig(InferenceConfiguration).

      Parameters:
      inferenceConfig - a consumer that will call methods on InferenceConfiguration.Builder
      Returns:
      Returns a reference to this object so that method calls can be chained together.
      See Also:
    • additionalModelRequestFields

      ModelConfiguration.Builder additionalModelRequestFields(Map<String,Document> additionalModelRequestFields)

      Additional model request fields. Use this to pass model-specific parameters that are not included in the standard inference configuration.

      Parameters:
      additionalModelRequestFields - Additional model request fields. Use this to pass model-specific parameters that are not included in the standard inference configuration.
      Returns:
      Returns a reference to this object so that method calls can be chained together.