Struct aws_sdk_bedrock::operation::create_model_customization_job::builders::CreateModelCustomizationJobFluentBuilder

pub struct CreateModelCustomizationJobFluentBuilder { /* private fields */ }

Fluent builder constructing a request to CreateModelCustomizationJob.

Creates a fine-tuning job to customize a base model.

You specify the base foundation model and the location of the training data. After the model-customization job completes successfully, your custom model resource will be ready to use. Training data contains input and output text for each record in a JSONL format. Optionally, you can specify validation data in the same format as the training data. Bedrock returns validation loss metrics and output generations after the job completes.

Model-customization jobs are asynchronous and the completion time depends on the base model and the training/validation data size. To monitor a job, use the GetModelCustomizationJob operation to retrieve the job status.

For more information, see Custom models in the Bedrock User Guide.

Implementations

impl CreateModelCustomizationJobFluentBuilder

pub fn as_input(&self) -> &CreateModelCustomizationJobInputBuilder

Access the CreateModelCustomizationJob as a reference.

pub async fn send( self ) -> Result<CreateModelCustomizationJobOutput, SdkError<CreateModelCustomizationJobError, HttpResponse>>

Sends the request and returns the response.

If an error occurs, an SdkError will be returned with additional details that can be matched against.

By default, any retryable failures will be retried twice. Retry behavior is configurable with the RetryConfig, which can be set when configuring the client.

pub fn customize( self ) -> CustomizableOperation<CreateModelCustomizationJobOutput, CreateModelCustomizationJobError, Self>

Consumes this builder, creating a customizable operation that can be modified before being sent.

pub fn job_name(self, input: impl Into<String>) -> Self

Enter a unique name for the fine-tuning job.

pub fn set_job_name(self, input: Option<String>) -> Self

Enter a unique name for the fine-tuning job.

pub fn get_job_name(&self) -> &Option<String>

Enter a unique name for the fine-tuning job.

pub fn custom_model_name(self, input: impl Into<String>) -> Self

Enter a name for the custom model.

pub fn set_custom_model_name(self, input: Option<String>) -> Self

Enter a name for the custom model.

pub fn get_custom_model_name(&self) -> &Option<String>

Enter a name for the custom model.

pub fn role_arn(self, input: impl Into<String>) -> Self

The Amazon Resource Name (ARN) of an IAM role that Bedrock can assume to perform tasks on your behalf. For example, during model training, Bedrock needs your permission to read input data from an S3 bucket, write model artifacts to an S3 bucket. To pass this role to Bedrock, the caller of this API must have the iam:PassRole permission.

pub fn set_role_arn(self, input: Option<String>) -> Self

The Amazon Resource Name (ARN) of an IAM role that Bedrock can assume to perform tasks on your behalf. For example, during model training, Bedrock needs your permission to read input data from an S3 bucket, write model artifacts to an S3 bucket. To pass this role to Bedrock, the caller of this API must have the iam:PassRole permission.

pub fn get_role_arn(&self) -> &Option<String>

The Amazon Resource Name (ARN) of an IAM role that Bedrock can assume to perform tasks on your behalf. For example, during model training, Bedrock needs your permission to read input data from an S3 bucket, write model artifacts to an S3 bucket. To pass this role to Bedrock, the caller of this API must have the iam:PassRole permission.

pub fn client_request_token(self, input: impl Into<String>) -> Self

Unique token value that you can provide. The GetModelCustomizationJob response includes the same token value.

pub fn set_client_request_token(self, input: Option<String>) -> Self

Unique token value that you can provide. The GetModelCustomizationJob response includes the same token value.

pub fn get_client_request_token(&self) -> &Option<String>

Unique token value that you can provide. The GetModelCustomizationJob response includes the same token value.

pub fn base_model_identifier(self, input: impl Into<String>) -> Self

Name of the base model.

pub fn set_base_model_identifier(self, input: Option<String>) -> Self

Name of the base model.

pub fn get_base_model_identifier(&self) -> &Option<String>

Name of the base model.

pub fn custom_model_kms_key_id(self, input: impl Into<String>) -> Self

The custom model is encrypted at rest using this key.

pub fn set_custom_model_kms_key_id(self, input: Option<String>) -> Self

The custom model is encrypted at rest using this key.

pub fn get_custom_model_kms_key_id(&self) -> &Option<String>

The custom model is encrypted at rest using this key.

pub fn job_tags(self, input: Tag) -> Self

Appends an item to jobTags.

To override the contents of this collection use set_job_tags.

Assign tags to the job.

pub fn set_job_tags(self, input: Option<Vec<Tag>>) -> Self

Assign tags to the job.

pub fn get_job_tags(&self) -> &Option<Vec<Tag>>

Assign tags to the job.

pub fn custom_model_tags(self, input: Tag) -> Self

Appends an item to customModelTags.

To override the contents of this collection use set_custom_model_tags.

Assign tags to the custom model.

pub fn set_custom_model_tags(self, input: Option<Vec<Tag>>) -> Self

Assign tags to the custom model.

pub fn get_custom_model_tags(&self) -> &Option<Vec<Tag>>

Assign tags to the custom model.

pub fn training_data_config(self, input: TrainingDataConfig) -> Self

Information about the training dataset.

pub fn set_training_data_config(self, input: Option<TrainingDataConfig>) -> Self

Information about the training dataset.

pub fn get_training_data_config(&self) -> &Option<TrainingDataConfig>

Information about the training dataset.

pub fn validation_data_config(self, input: ValidationDataConfig) -> Self

Information about the validation dataset.

pub fn set_validation_data_config( self, input: Option<ValidationDataConfig> ) -> Self

Information about the validation dataset.

pub fn get_validation_data_config(&self) -> &Option<ValidationDataConfig>

Information about the validation dataset.

pub fn output_data_config(self, input: OutputDataConfig) -> Self

S3 location for the output data.

pub fn set_output_data_config(self, input: Option<OutputDataConfig>) -> Self

S3 location for the output data.

pub fn get_output_data_config(&self) -> &Option<OutputDataConfig>

S3 location for the output data.

pub fn hyper_parameters( self, k: impl Into<String>, v: impl Into<String> ) -> Self

Adds a key-value pair to hyperParameters.

To override the contents of this collection use set_hyper_parameters.

Parameters related to tuning the model.

pub fn set_hyper_parameters( self, input: Option<HashMap<String, String>> ) -> Self

Parameters related to tuning the model.

pub fn get_hyper_parameters(&self) -> &Option<HashMap<String, String>>

Parameters related to tuning the model.

pub fn vpc_config(self, input: VpcConfig) -> Self

VPC configuration (optional). Configuration parameters for the private Virtual Private Cloud (VPC) that contains the resources you are using for this job.

pub fn set_vpc_config(self, input: Option<VpcConfig>) -> Self

VPC configuration (optional). Configuration parameters for the private Virtual Private Cloud (VPC) that contains the resources you are using for this job.

pub fn get_vpc_config(&self) -> &Option<VpcConfig>

VPC configuration (optional). Configuration parameters for the private Virtual Private Cloud (VPC) that contains the resources you are using for this job.

Trait Implementations

impl Clone for CreateModelCustomizationJobFluentBuilder

fn clone(&self) -> CreateModelCustomizationJobFluentBuilder

Returns a copy of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for CreateModelCustomizationJobFluentBuilder

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.