Struct Client

pub struct Client { /* private fields */ }

Client for Amazon Bedrock

Client for invoking operations on Amazon Bedrock. Each operation on Amazon Bedrock is a method on this this struct. .send() MUST be invoked on the generated operations to dispatch the request to the service.

Constructing a Client

A Config is required to construct a client. For most use cases, the aws-config crate should be used to automatically resolve this config using aws_config::load_from_env(), since this will resolve an SdkConfig which can be shared across multiple different AWS SDK clients. This config resolution process can be customized by calling aws_config::from_env() instead, which returns a ConfigLoader that uses the builder pattern to customize the default config.

In the simplest case, creating a client looks as follows:

let config = aws_config::load_from_env().await;
let client = aws_sdk_bedrock::Client::new(&config);

Occasionally, SDKs may have additional service-specific values that can be set on the Config that is absent from SdkConfig, or slightly different settings for a specific client may be desired. The Builder struct implements From<&SdkConfig>, so setting these specific settings can be done as follows:

let sdk_config = ::aws_config::load_from_env().await;
let config = aws_sdk_bedrock::config::Builder::from(&sdk_config)
    .some_service_specific_setting("value")
    .build();

See the aws-config docs and Config for more information on customizing configuration.

Note: Client construction is expensive due to connection thread pool initialization, and should be done once at application start-up.

Using the Client

A client has a function for every operation that can be performed by the service. For example, the CreateEvaluationJob operation has a Client::create_evaluation_job, function which returns a builder for that operation. The fluent builder ultimately has a send() function that returns an async future that returns a result, as illustrated below:

let result = client.create_evaluation_job()
    .job_name("example")
    .send()
    .await;

The underlying HTTP requests that get made by this can be modified with the customize_operation function on the fluent builder. See the customize module for more information.

Implementations

impl Client

pub fn batch_delete_evaluation_job( &self, ) -> BatchDeleteEvaluationJobFluentBuilder

Constructs a fluent builder for the BatchDeleteEvaluationJob operation.

• The fluent builder is configurable:
  • job_identifiers(impl Into<String>) / set_job_identifiers(Option<Vec::<String>>):
    required: true
    

    A list of one or more evaluation job Amazon Resource Names (ARNs) you want to delete.

    
    
• On success, responds with BatchDeleteEvaluationJobOutput with field(s):
  • errors(Vec::<BatchDeleteEvaluationJobError>):

    A JSON object containing the HTTP status codes and the ARNs of evaluation jobs that failed to be deleted.

  • evaluation_jobs(Vec::<BatchDeleteEvaluationJobItem>):

    The list of evaluation jobs for deletion.

• On failure, responds with SdkError<BatchDeleteEvaluationJobError>

impl Client

pub fn create_evaluation_job(&self) -> CreateEvaluationJobFluentBuilder

Constructs a fluent builder for the CreateEvaluationJob operation.

• The fluent builder is configurable:
  • job_name(impl Into<String>) / set_job_name(Option<String>):
    required: true
    

    A name for the evaluation job. Names must unique with your Amazon Web Services account, and your account’s Amazon Web Services region.

    
    
  • job_description(impl Into<String>) / set_job_description(Option<String>):
    required: false
    

    A description of the evaluation job.

    
    
  • client_request_token(impl Into<String>) / set_client_request_token(Option<String>):
    required: false
    

    A unique, case-sensitive identifier to ensure that the API request completes no more than one time. If this token matches a previous request, Amazon Bedrock ignores the request, but does not return an error. For more information, see Ensuring idempotency.

    
    
  • role_arn(impl Into<String>) / set_role_arn(Option<String>):
    required: true
    

    The Amazon Resource Name (ARN) of an IAM service role that Amazon Bedrock can assume to perform tasks on your behalf. To learn more about the required permissions, see Required permissions for model evaluations.

    
    
  • customer_encryption_key_id(impl Into<String>) / set_customer_encryption_key_id(Option<String>):
    required: false
    

    Specify your customer managed encryption key Amazon Resource Name (ARN) that will be used to encrypt your evaluation job.

    
    
  • job_tags(Tag) / set_job_tags(Option<Vec::<Tag>>):
    required: false
    

    Tags to attach to the model evaluation job.

    
    
  • application_type(ApplicationType) / set_application_type(Option<ApplicationType>):
    required: false
    

    Specifies whether the evaluation job is for evaluating a model or evaluating a knowledge base (retrieval and response generation).

    
    
  • evaluation_config(EvaluationConfig) / set_evaluation_config(Option<EvaluationConfig>):
    required: true
    

    Contains the configuration details of either an automated or human-based evaluation job.

    
    
  • inference_config(EvaluationInferenceConfig) / set_inference_config(Option<EvaluationInferenceConfig>):
    required: true
    

    Contains the configuration details of the inference model for the evaluation job.

    For model evaluation jobs, automated jobs support a single model or inference profile, and jobs that use human workers support two models or inference profiles.

    
    
  • output_data_config(EvaluationOutputDataConfig) / set_output_data_config(Option<EvaluationOutputDataConfig>):
    required: true
    

    Contains the configuration details of the Amazon S3 bucket for storing the results of the evaluation job.

    
    
• On success, responds with CreateEvaluationJobOutput with field(s):
  • job_arn(String):

    The Amazon Resource Name (ARN) of the evaluation job.

• On failure, responds with SdkError<CreateEvaluationJobError>

impl Client

pub fn create_guardrail(&self) -> CreateGuardrailFluentBuilder

Constructs a fluent builder for the CreateGuardrail operation.

• The fluent builder is configurable:
  • name(impl Into<String>) / set_name(Option<String>):
    required: true
    

    The name to give the guardrail.

    
    
  • description(impl Into<String>) / set_description(Option<String>):
    required: false
    

    A description of the guardrail.

    
    
  • topic_policy_config(GuardrailTopicPolicyConfig) / set_topic_policy_config(Option<GuardrailTopicPolicyConfig>):
    required: false
    

    The topic policies to configure for the guardrail.

    
    
  • content_policy_config(GuardrailContentPolicyConfig) / set_content_policy_config(Option<GuardrailContentPolicyConfig>):
    required: false
    

    The content filter policies to configure for the guardrail.

    
    
  • word_policy_config(GuardrailWordPolicyConfig) / set_word_policy_config(Option<GuardrailWordPolicyConfig>):
    required: false
    

    The word policy you configure for the guardrail.

    
    
  • sensitive_information_policy_config(GuardrailSensitiveInformationPolicyConfig) / set_sensitive_information_policy_config(Option<GuardrailSensitiveInformationPolicyConfig>):
    required: false
    

    The sensitive information policy to configure for the guardrail.

    
    
  • contextual_grounding_policy_config(GuardrailContextualGroundingPolicyConfig) / set_contextual_grounding_policy_config(Option<GuardrailContextualGroundingPolicyConfig>):
    required: false
    

    The contextual grounding policy configuration used to create a guardrail.

    
    
  • cross_region_config(GuardrailCrossRegionConfig) / set_cross_region_config(Option<GuardrailCrossRegionConfig>):
    required: false
    

    The system-defined guardrail profile that you’re using with your guardrail. Guardrail profiles define the destination Amazon Web Services Regions where guardrail inference requests can be automatically routed.

    For more information, see the Amazon Bedrock User Guide.

    
    
  • blocked_input_messaging(impl Into<String>) / set_blocked_input_messaging(Option<String>):
    required: true
    

    The message to return when the guardrail blocks a prompt.

    
    
  • blocked_outputs_messaging(impl Into<String>) / set_blocked_outputs_messaging(Option<String>):
    required: true
    

    The message to return when the guardrail blocks a model response.

    
    
  • kms_key_id(impl Into<String>) / set_kms_key_id(Option<String>):
    required: false
    

    The ARN of the KMS key that you use to encrypt the guardrail.

    
    
  • tags(Tag) / set_tags(Option<Vec::<Tag>>):
    required: false
    

    The tags that you want to attach to the guardrail.

    
    
  • client_request_token(impl Into<String>) / set_client_request_token(Option<String>):
    required: false
    

    A unique, case-sensitive identifier to ensure that the API request completes no more than once. If this token matches a previous request, Amazon Bedrock ignores the request, but does not return an error. For more information, see Ensuring idempotency in the Amazon S3 User Guide.

    
    
• On success, responds with CreateGuardrailOutput with field(s):
  • guardrail_id(String):

    The unique identifier of the guardrail that was created.

  • guardrail_arn(String):

    The ARN of the guardrail.

  • version(String):

    The version of the guardrail that was created. This value will always be DRAFT.

  • created_at(DateTime):

    The time at which the guardrail was created.

• On failure, responds with SdkError<CreateGuardrailError>

impl Client

pub fn create_guardrail_version(&self) -> CreateGuardrailVersionFluentBuilder

Constructs a fluent builder for the CreateGuardrailVersion operation.

• The fluent builder is configurable:
  • guardrail_identifier(impl Into<String>) / set_guardrail_identifier(Option<String>):
    required: true
    

    The unique identifier of the guardrail. This can be an ID or the ARN.

    
    
  • description(impl Into<String>) / set_description(Option<String>):
    required: false
    

    A description of the guardrail version.

    
    
  • client_request_token(impl Into<String>) / set_client_request_token(Option<String>):
    required: false
    

    A unique, case-sensitive identifier to ensure that the API request completes no more than once. If this token matches a previous request, Amazon Bedrock ignores the request, but does not return an error. For more information, see Ensuring idempotency in the Amazon S3 User Guide.

    
    
• On success, responds with CreateGuardrailVersionOutput with field(s):
  • guardrail_id(String):

    The unique identifier of the guardrail.

  • version(String):

    The number of the version of the guardrail.

• On failure, responds with SdkError<CreateGuardrailVersionError>

impl Client

pub fn create_inference_profile(&self) -> CreateInferenceProfileFluentBuilder

Constructs a fluent builder for the CreateInferenceProfile operation.

• The fluent builder is configurable:
  • inference_profile_name(impl Into<String>) / set_inference_profile_name(Option<String>):
    required: true
    

    A name for the inference profile.

    
    
  • description(impl Into<String>) / set_description(Option<String>):
    required: false
    

    A description for the inference profile.

    
    
  • client_request_token(impl Into<String>) / set_client_request_token(Option<String>):
    required: false
    

    A unique, case-sensitive identifier to ensure that the API request completes no more than one time. If this token matches a previous request, Amazon Bedrock ignores the request, but does not return an error. For more information, see Ensuring idempotency.

    
    
  • model_source(InferenceProfileModelSource) / set_model_source(Option<InferenceProfileModelSource>):
    required: true
    

    The foundation model or system-defined inference profile that the inference profile will track metrics and costs for.

    
    
  • tags(Tag) / set_tags(Option<Vec::<Tag>>):
    required: false
    

    An array of objects, each of which contains a tag and its value. For more information, see Tagging resources in the Amazon Bedrock User Guide.

    
    
• On success, responds with CreateInferenceProfileOutput with field(s):
  • inference_profile_arn(String):

    The ARN of the inference profile that you created.

  • status(Option<InferenceProfileStatus>):

    The status of the inference profile. ACTIVE means that the inference profile is ready to be used.

• On failure, responds with SdkError<CreateInferenceProfileError>

impl Client

pub fn create_marketplace_model_endpoint( &self, ) -> CreateMarketplaceModelEndpointFluentBuilder

Constructs a fluent builder for the CreateMarketplaceModelEndpoint operation.

• The fluent builder is configurable:
  • model_source_identifier(impl Into<String>) / set_model_source_identifier(Option<String>):
    required: true
    

    The ARN of the model from Amazon Bedrock Marketplace that you want to deploy to the endpoint.

    
    
  • endpoint_config(EndpointConfig) / set_endpoint_config(Option<EndpointConfig>):
    required: true
    

    The configuration for the endpoint, including the number and type of instances to use.

    
    
  • accept_eula(bool) / set_accept_eula(Option<bool>):
    required: false
    

    Indicates whether you accept the end-user license agreement (EULA) for the model. Set to true to accept the EULA.

    
    
  • endpoint_name(impl Into<String>) / set_endpoint_name(Option<String>):
    required: true
    

    The name of the endpoint. This name must be unique within your Amazon Web Services account and region.

    
    
  • client_request_token(impl Into<String>) / set_client_request_token(Option<String>):
    required: false
    

    A unique, case-sensitive identifier that you provide to ensure the idempotency of the request. This token is listed as not required because Amazon Web Services SDKs automatically generate it for you and set this parameter. If you’re not using the Amazon Web Services SDK or the CLI, you must provide this token or the action will fail.

    
    
  • tags(Tag) / set_tags(Option<Vec::<Tag>>):
    required: false
    

    An array of key-value pairs to apply to the underlying Amazon SageMaker endpoint. You can use these tags to organize and identify your Amazon Web Services resources.

    
    
• On success, responds with CreateMarketplaceModelEndpointOutput with field(s):
  • marketplace_model_endpoint(Option<MarketplaceModelEndpoint>):

    Details about the created endpoint.

• On failure, responds with SdkError<CreateMarketplaceModelEndpointError>

impl Client

pub fn create_model_copy_job(&self) -> CreateModelCopyJobFluentBuilder

Constructs a fluent builder for the CreateModelCopyJob operation.

• The fluent builder is configurable:
  • source_model_arn(impl Into<String>) / set_source_model_arn(Option<String>):
    required: true
    

    The Amazon Resource Name (ARN) of the model to be copied.

    
    
  • target_model_name(impl Into<String>) / set_target_model_name(Option<String>):
    required: true
    

    A name for the copied model.

    
    
  • model_kms_key_id(impl Into<String>) / set_model_kms_key_id(Option<String>):
    required: false
    

    The ARN of the KMS key that you use to encrypt the model copy.

    
    
  • target_model_tags(Tag) / set_target_model_tags(Option<Vec::<Tag>>):
    required: false
    

    Tags to associate with the target model. For more information, see Tag resources in the Amazon Bedrock User Guide.

    
    
  • client_request_token(impl Into<String>) / set_client_request_token(Option<String>):
    required: false
    

    A unique, case-sensitive identifier to ensure that the API request completes no more than one time. If this token matches a previous request, Amazon Bedrock ignores the request, but does not return an error. For more information, see Ensuring idempotency.

    
    
• On success, responds with CreateModelCopyJobOutput with field(s):
  • job_arn(String):

    The Amazon Resource Name (ARN) of the model copy job.

• On failure, responds with SdkError<CreateModelCopyJobError>

impl Client

pub fn create_model_customization_job( &self, ) -> CreateModelCustomizationJobFluentBuilder

Constructs a fluent builder for the CreateModelCustomizationJob operation.

• The fluent builder is configurable:
  • job_name(impl Into<String>) / set_job_name(Option<String>):
    required: true
    

    A name for the fine-tuning job.

    
    
  • custom_model_name(impl Into<String>) / set_custom_model_name(Option<String>):
    required: true
    

    A name for the resulting custom model.

    
    
  • role_arn(impl Into<String>) / set_role_arn(Option<String>):
    required: true
    

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

    
    
  • client_request_token(impl Into<String>) / set_client_request_token(Option<String>):
    required: false
    

    A unique, case-sensitive identifier to ensure that the API request completes no more than one time. If this token matches a previous request, Amazon Bedrock ignores the request, but does not return an error. For more information, see Ensuring idempotency.

    
    
  • base_model_identifier(impl Into<String>) / set_base_model_identifier(Option<String>):
    required: true
    

    Name of the base model.

    
    
  • customization_type(CustomizationType) / set_customization_type(Option<CustomizationType>):
    required: false
    

    The customization type.

    
    
  • custom_model_kms_key_id(impl Into<String>) / set_custom_model_kms_key_id(Option<String>):
    required: false
    

    The custom model is encrypted at rest using this key.

    
    
  • job_tags(Tag) / set_job_tags(Option<Vec::<Tag>>):
    required: false
    

    Tags to attach to the job.

    
    
  • custom_model_tags(Tag) / set_custom_model_tags(Option<Vec::<Tag>>):
    required: false
    

    Tags to attach to the resulting custom model.

    
    
  • training_data_config(TrainingDataConfig) / set_training_data_config(Option<TrainingDataConfig>):
    required: true
    

    Information about the training dataset.

    
    
  • validation_data_config(ValidationDataConfig) / set_validation_data_config(Option<ValidationDataConfig>):
    required: false
    

    Information about the validation dataset.

    
    
  • output_data_config(OutputDataConfig) / set_output_data_config(Option<OutputDataConfig>):
    required: true
    

    S3 location for the output data.

    
    
  • hyper_parameters(impl Into<String>, impl Into<String>) / set_hyper_parameters(Option<HashMap::<String, String>>):
    required: false
    

    Parameters related to tuning the model. For details on the format for different models, see Custom model hyperparameters.

    
    
  • vpc_config(VpcConfig) / set_vpc_config(Option<VpcConfig>):
    required: false
    

    The configuration of the Virtual Private Cloud (VPC) that contains the resources that you’re using for this job. For more information, see Protect your model customization jobs using a VPC.

    
    
  • customization_config(CustomizationConfig) / set_customization_config(Option<CustomizationConfig>):
    required: false
    

    The customization configuration for the model customization job.

    
    
• On success, responds with CreateModelCustomizationJobOutput with field(s):
  • job_arn(String):

    Amazon Resource Name (ARN) of the fine tuning job

• On failure, responds with SdkError<CreateModelCustomizationJobError>

impl Client

pub fn create_model_import_job(&self) -> CreateModelImportJobFluentBuilder

Constructs a fluent builder for the CreateModelImportJob operation.

• The fluent builder is configurable:
  • job_name(impl Into<String>) / set_job_name(Option<String>):
    required: true
    

    The name of the import job.

    
    
  • imported_model_name(impl Into<String>) / set_imported_model_name(Option<String>):
    required: true
    

    The name of the imported model.

    
    
  • role_arn(impl Into<String>) / set_role_arn(Option<String>):
    required: true
    

    The Amazon Resource Name (ARN) of the model import job.

    
    
  • model_data_source(ModelDataSource) / set_model_data_source(Option<ModelDataSource>):
    required: true
    

    The data source for the imported model.

    
    
  • job_tags(Tag) / set_job_tags(Option<Vec::<Tag>>):
    required: false
    

    Tags to attach to this import job.

    
    
  • imported_model_tags(Tag) / set_imported_model_tags(Option<Vec::<Tag>>):
    required: false
    

    Tags to attach to the imported model.

    
    
  • client_request_token(impl Into<String>) / set_client_request_token(Option<String>):
    required: false
    

    A unique, case-sensitive identifier to ensure that the API request completes no more than one time. If this token matches a previous request, Amazon Bedrock ignores the request, but does not return an error. For more information, see Ensuring idempotency.

    
    
  • vpc_config(VpcConfig) / set_vpc_config(Option<VpcConfig>):
    required: false
    

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

    
    
  • imported_model_kms_key_id(impl Into<String>) / set_imported_model_kms_key_id(Option<String>):
    required: false
    

    The imported model is encrypted at rest using this key.

    
    
• On success, responds with CreateModelImportJobOutput with field(s):
  • job_arn(String):

    The Amazon Resource Name (ARN) of the model import job.

• On failure, responds with SdkError<CreateModelImportJobError>

impl Client

pub fn create_model_invocation_job( &self, ) -> CreateModelInvocationJobFluentBuilder

Constructs a fluent builder for the CreateModelInvocationJob operation.

• The fluent builder is configurable:
  • job_name(impl Into<String>) / set_job_name(Option<String>):
    required: true
    

    A name to give the batch inference job.

    
    
  • role_arn(impl Into<String>) / set_role_arn(Option<String>):
    required: true
    

    The Amazon Resource Name (ARN) of the service role with permissions to carry out and manage batch inference. You can use the console to create a default service role or follow the steps at Create a service role for batch inference.

    
    
  • client_request_token(impl Into<String>) / set_client_request_token(Option<String>):
    required: false
    

    A unique, case-sensitive identifier to ensure that the API request completes no more than one time. If this token matches a previous request, Amazon Bedrock ignores the request, but does not return an error. For more information, see Ensuring idempotency.

    
    
  • model_id(impl Into<String>) / set_model_id(Option<String>):
    required: true
    

    The unique identifier of the foundation model to use for the batch inference job.

    
    
  • input_data_config(ModelInvocationJobInputDataConfig) / set_input_data_config(Option<ModelInvocationJobInputDataConfig>):
    required: true
    

    Details about the location of the input to the batch inference job.

    
    
  • output_data_config(ModelInvocationJobOutputDataConfig) / set_output_data_config(Option<ModelInvocationJobOutputDataConfig>):
    required: true
    

    Details about the location of the output of the batch inference job.

    
    
  • vpc_config(VpcConfig) / set_vpc_config(Option<VpcConfig>):
    required: false
    

    The configuration of the Virtual Private Cloud (VPC) for the data in the batch inference job. For more information, see Protect batch inference jobs using a VPC.

    
    
  • timeout_duration_in_hours(i32) / set_timeout_duration_in_hours(Option<i32>):
    required: false
    

    The number of hours after which to force the batch inference job to time out.

    
    
  • tags(Tag) / set_tags(Option<Vec::<Tag>>):
    required: false
    

    Any tags to associate with the batch inference job. For more information, see Tagging Amazon Bedrock resources.

    
    
• On success, responds with CreateModelInvocationJobOutput with field(s):
  • job_arn(String):

    The Amazon Resource Name (ARN) of the batch inference job.

• On failure, responds with SdkError<CreateModelInvocationJobError>

impl Client

pub fn create_prompt_router(&self) -> CreatePromptRouterFluentBuilder

Constructs a fluent builder for the CreatePromptRouter operation.

• The fluent builder is configurable:
  • client_request_token(impl Into<String>) / set_client_request_token(Option<String>):
    required: false
    

    A unique, case-sensitive identifier that you provide to ensure idempotency of your requests. If not specified, the Amazon Web Services SDK automatically generates one for you.

    
    
  • prompt_router_name(impl Into<String>) / set_prompt_router_name(Option<String>):
    required: true
    

    The name of the prompt router. The name must be unique within your Amazon Web Services account in the current region.

    
    
  • models(PromptRouterTargetModel) / set_models(Option<Vec::<PromptRouterTargetModel>>):
    required: true
    

    A list of foundation models that the prompt router can route requests to. At least one model must be specified.

    
    
  • description(impl Into<String>) / set_description(Option<String>):
    required: false
    

    An optional description of the prompt router to help identify its purpose.

    
    
  • routing_criteria(RoutingCriteria) / set_routing_criteria(Option<RoutingCriteria>):
    required: true
    

    The criteria, which is the response quality difference, used to determine how incoming requests are routed to different models.

    
    
  • fallback_model(PromptRouterTargetModel) / set_fallback_model(Option<PromptRouterTargetModel>):
    required: true
    

    The default model to use when the routing criteria is not met.

    
    
  • tags(Tag) / set_tags(Option<Vec::<Tag>>):
    required: false
    

    An array of key-value pairs to apply to this resource as tags. You can use tags to categorize and manage your Amazon Web Services resources.

    
    
• On success, responds with CreatePromptRouterOutput with field(s):
  • prompt_router_arn(Option<String>):

    The Amazon Resource Name (ARN) that uniquely identifies the prompt router.

• On failure, responds with SdkError<CreatePromptRouterError>

impl Client

pub fn create_provisioned_model_throughput( &self, ) -> CreateProvisionedModelThroughputFluentBuilder

Constructs a fluent builder for the CreateProvisionedModelThroughput operation.

• The fluent builder is configurable:
  • client_request_token(impl Into<String>) / set_client_request_token(Option<String>):
    required: false
    

    A unique, case-sensitive identifier to ensure that the API request completes no more than one time. If this token matches a previous request, Amazon Bedrock ignores the request, but does not return an error. For more information, see Ensuring idempotency in the Amazon S3 User Guide.

    
    
  • model_units(i32) / set_model_units(Option<i32>):
    required: true
    

    Number of model units to allocate. A model unit delivers a specific throughput level for the specified model. The throughput level of a model unit specifies the total number of input and output tokens that it can process and generate within a span of one minute. By default, your account has no model units for purchasing Provisioned Throughputs with commitment. You must first visit the Amazon Web Services support center to request MUs.

    For model unit quotas, see Provisioned Throughput quotas in the Amazon Bedrock User Guide.

    For more information about what an MU specifies, contact your Amazon Web Services account manager.

    
    
  • provisioned_model_name(impl Into<String>) / set_provisioned_model_name(Option<String>):
    required: true
    

    The name for this Provisioned Throughput.

    
    
  • model_id(impl Into<String>) / set_model_id(Option<String>):
    required: true
    

    The Amazon Resource Name (ARN) or name of the model to associate with this Provisioned Throughput. For a list of models for which you can purchase Provisioned Throughput, see Amazon Bedrock model IDs for purchasing Provisioned Throughput in the Amazon Bedrock User Guide.

    
    
  • commitment_duration(CommitmentDuration) / set_commitment_duration(Option<CommitmentDuration>):
    required: false
    

    The commitment duration requested for the Provisioned Throughput. Billing occurs hourly and is discounted for longer commitment terms. To request a no-commit Provisioned Throughput, omit this field.

    Custom models support all levels of commitment. To see which base models support no commitment, see Supported regions and models for Provisioned Throughput in the Amazon Bedrock User Guide

    
    
  • tags(Tag) / set_tags(Option<Vec::<Tag>>):
    required: false
    

    Tags to associate with this Provisioned Throughput.

    
    
• On success, responds with CreateProvisionedModelThroughputOutput with field(s):
  • provisioned_model_arn(String):

    The Amazon Resource Name (ARN) for this Provisioned Throughput.

• On failure, responds with SdkError<CreateProvisionedModelThroughputError>

impl Client

pub fn delete_custom_model(&self) -> DeleteCustomModelFluentBuilder

Constructs a fluent builder for the DeleteCustomModel operation.

• The fluent builder is configurable:
  • model_identifier(impl Into<String>) / set_model_identifier(Option<String>):
    required: true
    

    Name of the model to delete.

    
    
• On success, responds with DeleteCustomModelOutput
• On failure, responds with SdkError<DeleteCustomModelError>

impl Client

pub fn delete_guardrail(&self) -> DeleteGuardrailFluentBuilder

Constructs a fluent builder for the DeleteGuardrail operation.

• The fluent builder is configurable:
  • guardrail_identifier(impl Into<String>) / set_guardrail_identifier(Option<String>):
    required: true
    

    The unique identifier of the guardrail. This can be an ID or the ARN.

    
    
  • guardrail_version(impl Into<String>) / set_guardrail_version(Option<String>):
    required: false
    

    The version of the guardrail.

    
    
• On success, responds with DeleteGuardrailOutput
• On failure, responds with SdkError<DeleteGuardrailError>

impl Client

pub fn delete_imported_model(&self) -> DeleteImportedModelFluentBuilder

Constructs a fluent builder for the DeleteImportedModel operation.

• The fluent builder is configurable:
  • model_identifier(impl Into<String>) / set_model_identifier(Option<String>):
    required: true
    

    Name of the imported model to delete.

    
    
• On success, responds with DeleteImportedModelOutput
• On failure, responds with SdkError<DeleteImportedModelError>

impl Client

pub fn delete_inference_profile(&self) -> DeleteInferenceProfileFluentBuilder

Constructs a fluent builder for the DeleteInferenceProfile operation.

• The fluent builder is configurable:
  • inference_profile_identifier(impl Into<String>) / set_inference_profile_identifier(Option<String>):
    required: true
    

    The Amazon Resource Name (ARN) or ID of the application inference profile to delete.

    
    
• On success, responds with DeleteInferenceProfileOutput
• On failure, responds with SdkError<DeleteInferenceProfileError>

impl Client

pub fn delete_marketplace_model_endpoint( &self, ) -> DeleteMarketplaceModelEndpointFluentBuilder

Constructs a fluent builder for the DeleteMarketplaceModelEndpoint operation.

• The fluent builder is configurable:
  • endpoint_arn(impl Into<String>) / set_endpoint_arn(Option<String>):
    required: true
    

    The Amazon Resource Name (ARN) of the endpoint you want to delete.

    
    
• On success, responds with DeleteMarketplaceModelEndpointOutput
• On failure, responds with SdkError<DeleteMarketplaceModelEndpointError>

impl Client

pub fn delete_model_invocation_logging_configuration( &self, ) -> DeleteModelInvocationLoggingConfigurationFluentBuilder

Constructs a fluent builder for the DeleteModelInvocationLoggingConfiguration operation.

• The fluent builder takes no input, just send it.
• On success, responds with DeleteModelInvocationLoggingConfigurationOutput
• On failure, responds with SdkError<DeleteModelInvocationLoggingConfigurationError>

impl Client

pub fn delete_prompt_router(&self) -> DeletePromptRouterFluentBuilder

Constructs a fluent builder for the DeletePromptRouter operation.

• The fluent builder is configurable:
  • prompt_router_arn(impl Into<String>) / set_prompt_router_arn(Option<String>):
    required: true
    

    The Amazon Resource Name (ARN) of the prompt router to delete.

    
    
• On success, responds with DeletePromptRouterOutput
• On failure, responds with SdkError<DeletePromptRouterError>

impl Client

pub fn delete_provisioned_model_throughput( &self, ) -> DeleteProvisionedModelThroughputFluentBuilder

Constructs a fluent builder for the DeleteProvisionedModelThroughput operation.

• The fluent builder is configurable:
  • provisioned_model_id(impl Into<String>) / set_provisioned_model_id(Option<String>):
    required: true
    

    The Amazon Resource Name (ARN) or name of the Provisioned Throughput.

    
    
• On success, responds with DeleteProvisionedModelThroughputOutput
• On failure, responds with SdkError<DeleteProvisionedModelThroughputError>

impl Client

pub fn deregister_marketplace_model_endpoint( &self, ) -> DeregisterMarketplaceModelEndpointFluentBuilder

Constructs a fluent builder for the DeregisterMarketplaceModelEndpoint operation.

• The fluent builder is configurable:
  • endpoint_arn(impl Into<String>) / set_endpoint_arn(Option<String>):
    required: true
    

    The Amazon Resource Name (ARN) of the endpoint you want to deregister.

    
    
• On success, responds with DeregisterMarketplaceModelEndpointOutput
• On failure, responds with SdkError<DeregisterMarketplaceModelEndpointError>

impl Client

pub fn get_custom_model(&self) -> GetCustomModelFluentBuilder

Constructs a fluent builder for the GetCustomModel operation.

• The fluent builder is configurable:
  • model_identifier(impl Into<String>) / set_model_identifier(Option<String>):
    required: true
    

    Name or Amazon Resource Name (ARN) of the custom model.

    
    
• On success, responds with GetCustomModelOutput with field(s):
  • model_arn(String):

    Amazon Resource Name (ARN) associated with this model.

  • model_name(String):

    Model name associated with this model.

  • job_name(Option<String>):

    Job name associated with this model.

  • job_arn(String):

    Job Amazon Resource Name (ARN) associated with this model.

  • base_model_arn(String):

    Amazon Resource Name (ARN) of the base model.

  • customization_type(Option<CustomizationType>):

    The type of model customization.

  • model_kms_key_arn(Option<String>):

    The custom model is encrypted at rest using this key.

  • hyper_parameters(Option<HashMap::<String, String>>):

    Hyperparameter values associated with this model. For details on the format for different models, see Custom model hyperparameters.

  • training_data_config(Option<TrainingDataConfig>):

    Contains information about the training dataset.

  • validation_data_config(Option<ValidationDataConfig>):

    Contains information about the validation dataset.

  • output_data_config(Option<OutputDataConfig>):

    Output data configuration associated with this custom model.

  • training_metrics(Option<TrainingMetrics>):

    Contains training metrics from the job creation.

  • validation_metrics(Option<Vec::<ValidatorMetric>>):

    The validation metrics from the job creation.

  • creation_time(DateTime):

    Creation time of the model.

  • customization_config(Option<CustomizationConfig>):

    The customization configuration for the custom model.

• On failure, responds with SdkError<GetCustomModelError>

impl Client

pub fn get_evaluation_job(&self) -> GetEvaluationJobFluentBuilder

Constructs a fluent builder for the GetEvaluationJob operation.

• The fluent builder is configurable:
  • job_identifier(impl Into<String>) / set_job_identifier(Option<String>):
    required: true
    

    The Amazon Resource Name (ARN) of the evaluation job you want get information on.

    
    
• On success, responds with GetEvaluationJobOutput with field(s):
  • job_name(String):

    The name for the evaluation job.

  • status(EvaluationJobStatus):

    The current status of the evaluation job.

  • job_arn(String):

    The Amazon Resource Name (ARN) of the evaluation job.

  • job_description(Option<String>):

    The description of the evaluation job.

  • role_arn(String):

    The Amazon Resource Name (ARN) of the IAM service role used in the evaluation job.

  • customer_encryption_key_id(Option<String>):

    The Amazon Resource Name (ARN) of the customer managed encryption key specified when the evaluation job was created.

  • job_type(EvaluationJobType):

    Specifies whether the evaluation job is automated or human-based.

  • application_type(Option<ApplicationType>):

    Specifies whether the evaluation job is for evaluating a model or evaluating a knowledge base (retrieval and response generation).

  • evaluation_config(Option<EvaluationConfig>):

    Contains the configuration details of either an automated or human-based evaluation job.

  • inference_config(Option<EvaluationInferenceConfig>):

    Contains the configuration details of the inference model used for the evaluation job.

  • output_data_config(Option<EvaluationOutputDataConfig>):

    Contains the configuration details of the Amazon S3 bucket for storing the results of the evaluation job.

  • creation_time(DateTime):

    The time the evaluation job was created.

  • last_modified_time(Option<DateTime>):

    The time the evaluation job was last modified.

  • failure_messages(Option<Vec::<String>>):

    A list of strings that specify why the evaluation job failed to create.

• On failure, responds with SdkError<GetEvaluationJobError>

impl Client

pub fn get_foundation_model(&self) -> GetFoundationModelFluentBuilder

Constructs a fluent builder for the GetFoundationModel operation.

• The fluent builder is configurable:
  • model_identifier(impl Into<String>) / set_model_identifier(Option<String>):
    required: true
    

    The model identifier.

    
    
• On success, responds with GetFoundationModelOutput with field(s):
  • model_details(Option<FoundationModelDetails>):

    Information about the foundation model.

• On failure, responds with SdkError<GetFoundationModelError>

impl Client

pub fn get_guardrail(&self) -> GetGuardrailFluentBuilder

Constructs a fluent builder for the GetGuardrail operation.

• The fluent builder is configurable:
  • guardrail_identifier(impl Into<String>) / set_guardrail_identifier(Option<String>):
    required: true
    

    The unique identifier of the guardrail for which to get details. This can be an ID or the ARN.

    
    
  • guardrail_version(impl Into<String>) / set_guardrail_version(Option<String>):
    required: false
    

    The version of the guardrail for which to get details. If you don’t specify a version, the response returns details for the DRAFT version.

    
    
• On success, responds with GetGuardrailOutput with field(s):
  • name(String):

    The name of the guardrail.

  • description(Option<String>):

    The description of the guardrail.

  • guardrail_id(String):

    The unique identifier of the guardrail.

  • guardrail_arn(String):

    The ARN of the guardrail.

  • version(String):

    The version of the guardrail.

  • status(GuardrailStatus):

    The status of the guardrail.

  • topic_policy(Option<GuardrailTopicPolicy>):

    The topic policy that was configured for the guardrail.

  • content_policy(Option<GuardrailContentPolicy>):

    The content policy that was configured for the guardrail.

  • word_policy(Option<GuardrailWordPolicy>):

    The word policy that was configured for the guardrail.

  • sensitive_information_policy(Option<GuardrailSensitiveInformationPolicy>):

    The sensitive information policy that was configured for the guardrail.

  • contextual_grounding_policy(Option<GuardrailContextualGroundingPolicy>):

    The contextual grounding policy used in the guardrail.

  • cross_region_details(Option<GuardrailCrossRegionDetails>):

    Details about the system-defined guardrail profile that you’re using with your guardrail, including the guardrail profile ID and Amazon Resource Name (ARN).

  • created_at(DateTime):

    The date and time at which the guardrail was created.

  • updated_at(DateTime):

    The date and time at which the guardrail was updated.

  • status_reasons(Option<Vec::<String>>):

    Appears if the status is FAILED. A list of reasons for why the guardrail failed to be created, updated, versioned, or deleted.

  • failure_recommendations(Option<Vec::<String>>):

    Appears if the status of the guardrail is FAILED. A list of recommendations to carry out before retrying the request.

  • blocked_input_messaging(String):

    The message that the guardrail returns when it blocks a prompt.

  • blocked_outputs_messaging(String):

    The message that the guardrail returns when it blocks a model response.

  • kms_key_arn(Option<String>):

    The ARN of the KMS key that encrypts the guardrail.

• On failure, responds with SdkError<GetGuardrailError>

impl Client

pub fn get_imported_model(&self) -> GetImportedModelFluentBuilder

Constructs a fluent builder for the GetImportedModel operation.

• The fluent builder is configurable:
  • model_identifier(impl Into<String>) / set_model_identifier(Option<String>):
    required: true
    

    Name or Amazon Resource Name (ARN) of the imported model.

    
    
• On success, responds with GetImportedModelOutput with field(s):
  • model_arn(Option<String>):

    The Amazon Resource Name (ARN) associated with this imported model.

  • model_name(Option<String>):

    The name of the imported model.

  • job_name(Option<String>):

    Job name associated with the imported model.

  • job_arn(Option<String>):

    Job Amazon Resource Name (ARN) associated with the imported model.

  • model_data_source(Option<ModelDataSource>):

    The data source for this imported model.

  • creation_time(Option<DateTime>):

    Creation time of the imported model.

  • model_architecture(Option<String>):

    The architecture of the imported model.

  • model_kms_key_arn(Option<String>):

    The imported model is encrypted at rest using this key.

  • instruct_supported(Option<bool>):

    Specifies if the imported model supports converse.

  • custom_model_units(Option<CustomModelUnits>):

    Information about the hardware utilization for a single copy of the model.

• On failure, responds with SdkError<GetImportedModelError>

impl Client

pub fn get_inference_profile(&self) -> GetInferenceProfileFluentBuilder

Constructs a fluent builder for the GetInferenceProfile operation.

• The fluent builder is configurable:
  • inference_profile_identifier(impl Into<String>) / set_inference_profile_identifier(Option<String>):
    required: true
    

    The ID or Amazon Resource Name (ARN) of the inference profile.

    
    
• On success, responds with GetInferenceProfileOutput with field(s):
  • inference_profile_name(String):

    The name of the inference profile.

  • description(Option<String>):

    The description of the inference profile.

  • created_at(Option<DateTime>):

    The time at which the inference profile was created.

  • updated_at(Option<DateTime>):

    The time at which the inference profile was last updated.

  • inference_profile_arn(String):

    The Amazon Resource Name (ARN) of the inference profile.

  • models(Vec::<InferenceProfileModel>):

    A list of information about each model in the inference profile.

  • inference_profile_id(String):

    The unique identifier of the inference profile.

  • status(InferenceProfileStatus):

    The status of the inference profile. ACTIVE means that the inference profile is ready to be used.

  • r#type(InferenceProfileType):

    The type of the inference profile. The following types are possible:

    • SYSTEM_DEFINED – The inference profile is defined by Amazon Bedrock. You can route inference requests across regions with these inference profiles.

    • APPLICATION – The inference profile was created by a user. This type of inference profile can track metrics and costs when invoking the model in it. The inference profile may route requests to one or multiple regions.

• On failure, responds with SdkError<GetInferenceProfileError>

impl Client

pub fn get_marketplace_model_endpoint( &self, ) -> GetMarketplaceModelEndpointFluentBuilder

Constructs a fluent builder for the GetMarketplaceModelEndpoint operation.

• The fluent builder is configurable:
  • endpoint_arn(impl Into<String>) / set_endpoint_arn(Option<String>):
    required: true
    

    The Amazon Resource Name (ARN) of the endpoint you want to get information about.

    
    
• On success, responds with GetMarketplaceModelEndpointOutput with field(s):
  • marketplace_model_endpoint(Option<MarketplaceModelEndpoint>):

    Details about the requested endpoint.

• On failure, responds with SdkError<GetMarketplaceModelEndpointError>

impl Client

pub fn get_model_copy_job(&self) -> GetModelCopyJobFluentBuilder

Constructs a fluent builder for the GetModelCopyJob operation.

• The fluent builder is configurable:
  • job_arn(impl Into<String>) / set_job_arn(Option<String>):
    required: true
    

    The Amazon Resource Name (ARN) of the model copy job.

    
    
• On success, responds with GetModelCopyJobOutput with field(s):
  • job_arn(String):

    The Amazon Resource Name (ARN) of the model copy job.

  • status(ModelCopyJobStatus):

    The status of the model copy job.

  • creation_time(DateTime):

    The time at which the model copy job was created.

  • target_model_arn(String):

    The Amazon Resource Name (ARN) of the copied model.

  • target_model_name(Option<String>):

    The name of the copied model.

  • source_account_id(String):

    The unique identifier of the account that the model being copied originated from.

  • source_model_arn(String):

    The Amazon Resource Name (ARN) of the original model being copied.

  • target_model_kms_key_arn(Option<String>):

    The Amazon Resource Name (ARN) of the KMS key encrypting the copied model.

  • target_model_tags(Option<Vec::<Tag>>):

    The tags associated with the copied model.

  • failure_message(Option<String>):

    An error message for why the model copy job failed.

  • source_model_name(Option<String>):

    The name of the original model being copied.

• On failure, responds with SdkError<GetModelCopyJobError>

impl Client

pub fn get_model_customization_job( &self, ) -> GetModelCustomizationJobFluentBuilder

Constructs a fluent builder for the GetModelCustomizationJob operation.

• The fluent builder is configurable:
  • job_identifier(impl Into<String>) / set_job_identifier(Option<String>):
    required: true
    

    Identifier for the customization job.

    
    
• On success, responds with GetModelCustomizationJobOutput with field(s):
  • job_arn(String):

    The Amazon Resource Name (ARN) of the customization job.

  • job_name(String):

    The name of the customization job.

  • output_model_name(String):

    The name of the output model.

  • output_model_arn(Option<String>):

    The Amazon Resource Name (ARN) of the output model.

  • client_request_token(Option<String>):

    The token that you specified in the CreateCustomizationJob request.

  • role_arn(String):

    The Amazon Resource Name (ARN) of the IAM role.

  • status(Option<ModelCustomizationJobStatus>):

    The status of the job. A successful job transitions from in-progress to completed when the output model is ready to use. If the job failed, the failure message contains information about why the job failed.

  • failure_message(Option<String>):

    Information about why the job failed.

  • status_details(Option<StatusDetails>):

    For a Distillation job, the details about the statuses of the sub-tasks of the customization job.

  • creation_time(DateTime):

    Time that the resource was created.

  • last_modified_time(Option<DateTime>):

    Time that the resource was last modified.

  • end_time(Option<DateTime>):

    Time that the resource transitioned to terminal state.

  • base_model_arn(String):

    Amazon Resource Name (ARN) of the base model.

  • hyper_parameters(Option<HashMap::<String, String>>):

    The hyperparameter values for the job. For details on the format for different models, see Custom model hyperparameters.

  • training_data_config(Option<TrainingDataConfig>):

    Contains information about the training dataset.

  • validation_data_config(Option<ValidationDataConfig>):

    Contains information about the validation dataset.

  • output_data_config(Option<OutputDataConfig>):

    Output data configuration

  • customization_type(Option<CustomizationType>):

    The type of model customization.

  • output_model_kms_key_arn(Option<String>):

    The custom model is encrypted at rest using this key.

  • training_metrics(Option<TrainingMetrics>):

    Contains training metrics from the job creation.

  • validation_metrics(Option<Vec::<ValidatorMetric>>):

    The loss metric for each validator that you provided in the createjob request.

  • vpc_config(Option<VpcConfig>):

    VPC configuration for the custom model job.

  • customization_config(Option<CustomizationConfig>):

    The customization configuration for the model customization job.

• On failure, responds with SdkError<GetModelCustomizationJobError>

impl Client

pub fn get_model_import_job(&self) -> GetModelImportJobFluentBuilder

Constructs a fluent builder for the GetModelImportJob operation.

• The fluent builder is configurable:
  • job_identifier(impl Into<String>) / set_job_identifier(Option<String>):
    required: true
    

    The identifier of the import job.

    
    
• On success, responds with GetModelImportJobOutput with field(s):
  • job_arn(Option<String>):

    The Amazon Resource Name (ARN) of the import job.

  • job_name(Option<String>):

    The name of the import job.

  • imported_model_name(Option<String>):

    The name of the imported model.

  • imported_model_arn(Option<String>):

    The Amazon Resource Name (ARN) of the imported model.

  • role_arn(Option<String>):

    The Amazon Resource Name (ARN) of the IAM role associated with this job.

  • model_data_source(Option<ModelDataSource>):

    The data source for the imported model.

  • status(Option<ModelImportJobStatus>):

    The status of the job. A successful job transitions from in-progress to completed when the imported model is ready to use. If the job failed, the failure message contains information about why the job failed.

  • failure_message(Option<String>):

    Information about why the import job failed.

  • creation_time(Option<DateTime>):

    The time the resource was created.

  • last_modified_time(Option<DateTime>):

    Time the resource was last modified.

  • end_time(Option<DateTime>):

    Time that the resource transitioned to terminal state.

  • vpc_config(Option<VpcConfig>):

    The Virtual Private Cloud (VPC) configuration of the import model job.

  • imported_model_kms_key_arn(Option<String>):

    The imported model is encrypted at rest using this key.

• On failure, responds with SdkError<GetModelImportJobError>

impl Client

pub fn get_model_invocation_job(&self) -> GetModelInvocationJobFluentBuilder

Constructs a fluent builder for the GetModelInvocationJob operation.

• The fluent builder is configurable:
  • job_identifier(impl Into<String>) / set_job_identifier(Option<String>):
    required: true
    

    The Amazon Resource Name (ARN) of the batch inference job.

    
    
• On success, responds with GetModelInvocationJobOutput with field(s):
  • job_arn(String):

    The Amazon Resource Name (ARN) of the batch inference job.

  • job_name(Option<String>):

    The name of the batch inference job.

  • model_id(String):

    The unique identifier of the foundation model used for model inference.

  • client_request_token(Option<String>):

    A unique, case-sensitive identifier to ensure that the API request completes no more than one time. If this token matches a previous request, Amazon Bedrock ignores the request, but does not return an error. For more information, see Ensuring idempotency.

  • role_arn(String):

    The Amazon Resource Name (ARN) of the service role with permissions to carry out and manage batch inference. You can use the console to create a default service role or follow the steps at Create a service role for batch inference.

  • status(Option<ModelInvocationJobStatus>):

    The status of the batch inference job.

    The following statuses are possible:

    • Submitted – This job has been submitted to a queue for validation.

    • Validating – This job is being validated for the requirements described in Format and upload your batch inference data. The criteria include the following:

      • Your IAM service role has access to the Amazon S3 buckets containing your files.

      • Your files are .jsonl files and each individual record is a JSON object in the correct format. Note that validation doesn’t check if the modelInput value matches the request body for the model.

      • Your files fulfill the requirements for file size and number of records. For more information, see Quotas for Amazon Bedrock.

    • Scheduled – This job has been validated and is now in a queue. The job will automatically start when it reaches its turn.

    • Expired – This job timed out because it was scheduled but didn’t begin before the set timeout duration. Submit a new job request.

    • InProgress – This job has begun. You can start viewing the results in the output S3 location.

    • Completed – This job has successfully completed. View the output files in the output S3 location.

    • PartiallyCompleted – This job has partially completed. Not all of your records could be processed in time. View the output files in the output S3 location.

    • Failed – This job has failed. Check the failure message for any further details. For further assistance, reach out to the Amazon Web ServicesSupport Center.

    • Stopped – This job was stopped by a user.

    • Stopping – This job is being stopped by a user.

  • message(Option<String>):

    If the batch inference job failed, this field contains a message describing why the job failed.

  • submit_time(DateTime):

    The time at which the batch inference job was submitted.

  • last_modified_time(Option<DateTime>):

    The time at which the batch inference job was last modified.

  • end_time(Option<DateTime>):

    The time at which the batch inference job ended.

  • input_data_config(Option<ModelInvocationJobInputDataConfig>):

    Details about the location of the input to the batch inference job.

  • output_data_config(Option<ModelInvocationJobOutputDataConfig>):

    Details about the location of the output of the batch inference job.

  • vpc_config(Option<VpcConfig>):

    The configuration of the Virtual Private Cloud (VPC) for the data in the batch inference job. For more information, see Protect batch inference jobs using a VPC.

  • timeout_duration_in_hours(Option<i32>):

    The number of hours after which batch inference job was set to time out.

  • job_expiration_time(Option<DateTime>):

    The time at which the batch inference job times or timed out.

• On failure, responds with SdkError<GetModelInvocationJobError>

impl Client

pub fn get_model_invocation_logging_configuration( &self, ) -> GetModelInvocationLoggingConfigurationFluentBuilder

Constructs a fluent builder for the GetModelInvocationLoggingConfiguration operation.

• The fluent builder takes no input, just send it.
• On success, responds with GetModelInvocationLoggingConfigurationOutput with field(s):
  • logging_config(Option<LoggingConfig>):

    The current configuration values.

• On failure, responds with SdkError<GetModelInvocationLoggingConfigurationError>

impl Client

pub fn get_prompt_router(&self) -> GetPromptRouterFluentBuilder

Constructs a fluent builder for the GetPromptRouter operation.

• The fluent builder is configurable:
  • prompt_router_arn(impl Into<String>) / set_prompt_router_arn(Option<String>):
    required: true
    

    The prompt router’s ARN

    
    
• On success, responds with GetPromptRouterOutput with field(s):
  • prompt_router_name(String):

    The router’s name.

  • routing_criteria(Option<RoutingCriteria>):

    The router’s routing criteria.

  • description(Option<String>):

    The router’s description.

  • created_at(Option<DateTime>):

    When the router was created.

  • updated_at(Option<DateTime>):

    When the router was updated.

  • prompt_router_arn(String):

    The prompt router’s ARN

  • models(Vec::<PromptRouterTargetModel>):

    The router’s models.

  • fallback_model(Option<PromptRouterTargetModel>):

    The router’s fallback model.

  • status(PromptRouterStatus):

    The router’s status.

  • r#type(PromptRouterType):

    The router’s type.

• On failure, responds with SdkError<GetPromptRouterError>

impl Client

pub fn get_provisioned_model_throughput( &self, ) -> GetProvisionedModelThroughputFluentBuilder

Constructs a fluent builder for the GetProvisionedModelThroughput operation.

• The fluent builder is configurable:
  • provisioned_model_id(impl Into<String>) / set_provisioned_model_id(Option<String>):
    required: true
    

    The Amazon Resource Name (ARN) or name of the Provisioned Throughput.

    
    
• On success, responds with GetProvisionedModelThroughputOutput with field(s):
  • model_units(i32):

    The number of model units allocated to this Provisioned Throughput.

  • desired_model_units(i32):

    The number of model units that was requested for this Provisioned Throughput.

  • provisioned_model_name(String):

    The name of the Provisioned Throughput.

  • provisioned_model_arn(String):

    The Amazon Resource Name (ARN) of the Provisioned Throughput.

  • model_arn(String):

    The Amazon Resource Name (ARN) of the model associated with this Provisioned Throughput.

  • desired_model_arn(String):

    The Amazon Resource Name (ARN) of the model requested to be associated to this Provisioned Throughput. This value differs from the modelArn if updating hasn’t completed.

  • foundation_model_arn(String):

    The Amazon Resource Name (ARN) of the base model for which the Provisioned Throughput was created, or of the base model that the custom model for which the Provisioned Throughput was created was customized.

  • status(ProvisionedModelStatus):

    The status of the Provisioned Throughput.

  • creation_time(DateTime):

    The timestamp of the creation time for this Provisioned Throughput.

  • last_modified_time(DateTime):

    The timestamp of the last time that this Provisioned Throughput was modified.

  • failure_message(Option<String>):

    A failure message for any issues that occurred during creation, updating, or deletion of the Provisioned Throughput.

  • commitment_duration(Option<CommitmentDuration>):

    Commitment duration of the Provisioned Throughput.

  • commitment_expiration_time(Option<DateTime>):

    The timestamp for when the commitment term for the Provisioned Throughput expires.

• On failure, responds with SdkError<GetProvisionedModelThroughputError>

impl Client

pub fn list_custom_models(&self) -> ListCustomModelsFluentBuilder

Constructs a fluent builder for the ListCustomModels operation. This operation supports pagination; See into_paginator().

• The fluent builder is configurable:
  • creation_time_before(DateTime) / set_creation_time_before(Option<DateTime>):
    required: false
    

    Return custom models created before the specified time.

    
    
  • creation_time_after(DateTime) / set_creation_time_after(Option<DateTime>):
    required: false
    

    Return custom models created after the specified time.

    
    
  • name_contains(impl Into<String>) / set_name_contains(Option<String>):
    required: false
    

    Return custom models only if the job name contains these characters.

    
    
  • base_model_arn_equals(impl Into<String>) / set_base_model_arn_equals(Option<String>):
    required: false
    

    Return custom models only if the base model Amazon Resource Name (ARN) matches this parameter.

    
    
  • foundation_model_arn_equals(impl Into<String>) / set_foundation_model_arn_equals(Option<String>):
    required: false
    

    Return custom models only if the foundation model Amazon Resource Name (ARN) matches this parameter.

    
    
  • max_results(i32) / set_max_results(Option<i32>):
    required: false
    

    The maximum number of results to return in the response. If the total number of results is greater than this value, use the token returned in the response in the nextToken field when making another request to return the next batch of results.

    
    
  • next_token(impl Into<String>) / set_next_token(Option<String>):
    required: false
    

    If the total number of results is greater than the maxResults value provided in the request, enter the token returned in the nextToken field in the response in this field to return the next batch of results.

    
    
  • sort_by(SortModelsBy) / set_sort_by(Option<SortModelsBy>):
    required: false
    

    The field to sort by in the returned list of models.

    
    
  • sort_order(SortOrder) / set_sort_order(Option<SortOrder>):
    required: false
    

    The sort order of the results.

    
    
  • is_owned(bool) / set_is_owned(Option<bool>):
    required: false
    

    Return custom models depending on if the current account owns them (true) or if they were shared with the current account (false).

    
    
• On success, responds with ListCustomModelsOutput with field(s):
  • next_token(Option<String>):

    If the total number of results is greater than the maxResults value provided in the request, use this token when making another request in the nextToken field to return the next batch of results.

  • model_summaries(Option<Vec::<CustomModelSummary>>):

    Model summaries.

• On failure, responds with SdkError<ListCustomModelsError>

impl Client

pub fn list_evaluation_jobs(&self) -> ListEvaluationJobsFluentBuilder

Constructs a fluent builder for the ListEvaluationJobs operation. This operation supports pagination; See into_paginator().

• The fluent builder is configurable:
  • creation_time_after(DateTime) / set_creation_time_after(Option<DateTime>):
    required: false
    

    A filter to only list evaluation jobs created after a specified time.

    
    
  • creation_time_before(DateTime) / set_creation_time_before(Option<DateTime>):
    required: false
    

    A filter to only list evaluation jobs created before a specified time.

    
    
  • status_equals(EvaluationJobStatus) / set_status_equals(Option<EvaluationJobStatus>):
    required: false
    

    A filter to only list evaluation jobs that are of a certain status.

    
    
  • application_type_equals(ApplicationType) / set_application_type_equals(Option<ApplicationType>):
    required: false
    

    A filter to only list evaluation jobs that are either model evaluations or knowledge base evaluations.

    
    
  • name_contains(impl Into<String>) / set_name_contains(Option<String>):
    required: false
    

    A filter to only list evaluation jobs that contain a specified string in the job name.

    
    
  • max_results(i32) / set_max_results(Option<i32>):
    required: false
    

    The maximum number of results to return.

    
    
  • next_token(impl Into<String>) / set_next_token(Option<String>):
    required: false
    

    Continuation token from the previous response, for Amazon Bedrock to list the next set of results.

    
    
  • sort_by(SortJobsBy) / set_sort_by(Option<SortJobsBy>):
    required: false
    

    Specifies a creation time to sort the list of evaluation jobs by when they were created.

    
    
  • sort_order(SortOrder) / set_sort_order(Option<SortOrder>):
    required: false
    

    Specifies whether to sort the list of evaluation jobs by either ascending or descending order.

    
    
• On success, responds with ListEvaluationJobsOutput with field(s):
  • next_token(Option<String>):

    Continuation token from the previous response, for Amazon Bedrock to list the next set of results.

  • job_summaries(Option<Vec::<EvaluationSummary>>):

    A list of summaries of the evaluation jobs.

• On failure, responds with SdkError<ListEvaluationJobsError>

impl Client

pub fn list_foundation_models(&self) -> ListFoundationModelsFluentBuilder

Constructs a fluent builder for the ListFoundationModels operation.

• The fluent builder is configurable:
  • by_provider(impl Into<String>) / set_by_provider(Option<String>):
    required: false
    

    Return models belonging to the model provider that you specify.

    
    
  • by_customization_type(ModelCustomization) / set_by_customization_type(Option<ModelCustomization>):
    required: false
    

    Return models that support the customization type that you specify. For more information, see Custom models in the Amazon Bedrock User Guide.

    
    
  • by_output_modality(ModelModality) / set_by_output_modality(Option<ModelModality>):
    required: false
    

    Return models that support the output modality that you specify.

    
    
  • by_inference_type(InferenceType) / set_by_inference_type(Option<InferenceType>):
    required: false
    

    Return models that support the inference type that you specify. For more information, see Provisioned Throughput in the Amazon Bedrock User Guide.

    
    
• On success, responds with ListFoundationModelsOutput with field(s):
  • model_summaries(Option<Vec::<FoundationModelSummary>>):

    A list of Amazon Bedrock foundation models.

• On failure, responds with SdkError<ListFoundationModelsError>

impl Client

pub fn list_guardrails(&self) -> ListGuardrailsFluentBuilder

Constructs a fluent builder for the ListGuardrails operation. This operation supports pagination; See into_paginator().

• The fluent builder is configurable:
  • guardrail_identifier(impl Into<String>) / set_guardrail_identifier(Option<String>):
    required: false
    

    The unique identifier of the guardrail. This can be an ID or the ARN.

    
    
  • max_results(i32) / set_max_results(Option<i32>):
    required: false
    

    The maximum number of results to return in the response.

    
    
  • next_token(impl Into<String>) / set_next_token(Option<String>):
    required: false
    

    If there are more results than were returned in the response, the response returns a nextToken that you can send in another ListGuardrails request to see the next batch of results.

    
    
• On success, responds with ListGuardrailsOutput with field(s):
  • guardrails(Vec::<GuardrailSummary>):

    A list of objects, each of which contains details about a guardrail.

  • next_token(Option<String>):

    If there are more results than were returned in the response, the response returns a nextToken that you can send in another ListGuardrails request to see the next batch of results.

• On failure, responds with SdkError<ListGuardrailsError>

impl Client

pub fn list_imported_models(&self) -> ListImportedModelsFluentBuilder

Constructs a fluent builder for the ListImportedModels operation. This operation supports pagination; See into_paginator().

• The fluent builder is configurable:
  • creation_time_before(DateTime) / set_creation_time_before(Option<DateTime>):
    required: false
    

    Return imported models that created before the specified time.

    
    
  • creation_time_after(DateTime) / set_creation_time_after(Option<DateTime>):
    required: false
    

    Return imported models that were created after the specified time.

    
    
  • name_contains(impl Into<String>) / set_name_contains(Option<String>):
    required: false
    

    Return imported models only if the model name contains these characters.

    
    
  • max_results(i32) / set_max_results(Option<i32>):
    required: false
    

    The maximum number of results to return in the response. If the total number of results is greater than this value, use the token returned in the response in the nextToken field when making another request to return the next batch of results.

    
    
  • next_token(impl Into<String>) / set_next_token(Option<String>):
    required: false
    

    If the total number of results is greater than the maxResults value provided in the request, enter the token returned in the nextToken field in the response in this field to return the next batch of results.

    
    
  • sort_by(SortModelsBy) / set_sort_by(Option<SortModelsBy>):
    required: false
    

    The field to sort by in the returned list of imported models.

    
    
  • sort_order(SortOrder) / set_sort_order(Option<SortOrder>):
    required: false
    

    Specifies whetehr to sort the results in ascending or descending order.

    
    
• On success, responds with ListImportedModelsOutput with field(s):
  • next_token(Option<String>):

    If the total number of results is greater than the maxResults value provided in the request, use this token when making another request in the nextToken field to return the next batch of results.

  • model_summaries(Option<Vec::<ImportedModelSummary>>):

    Model summaries.

• On failure, responds with SdkError<ListImportedModelsError>

impl Client

pub fn list_inference_profiles(&self) -> ListInferenceProfilesFluentBuilder

Constructs a fluent builder for the ListInferenceProfiles operation. This operation supports pagination; See into_paginator().

• The fluent builder is configurable:
  • max_results(i32) / set_max_results(Option<i32>):
    required: false
    

    The maximum number of results to return in the response. If the total number of results is greater than this value, use the token returned in the response in the nextToken field when making another request to return the next batch of results.

    
    
  • next_token(impl Into<String>) / set_next_token(Option<String>):
    required: false
    

    If the total number of results is greater than the maxResults value provided in the request, enter the token returned in the nextToken field in the response in this field to return the next batch of results.

    
    
  • type_equals(InferenceProfileType) / set_type_equals(Option<InferenceProfileType>):
    required: false
    

    Filters for inference profiles that match the type you specify.

    • SYSTEM_DEFINED – The inference profile is defined by Amazon Bedrock. You can route inference requests across regions with these inference profiles.

    • APPLICATION – The inference profile was created by a user. This type of inference profile can track metrics and costs when invoking the model in it. The inference profile may route requests to one or multiple regions.

    
    
• On success, responds with ListInferenceProfilesOutput with field(s):
  • inference_profile_summaries(Option<Vec::<InferenceProfileSummary>>):

    A list of information about each inference profile that you can use.

  • next_token(Option<String>):

    If the total number of results is greater than the maxResults value provided in the request, use this token when making another request in the nextToken field to return the next batch of results.

• On failure, responds with SdkError<ListInferenceProfilesError>

impl Client

pub fn list_marketplace_model_endpoints( &self, ) -> ListMarketplaceModelEndpointsFluentBuilder

Constructs a fluent builder for the ListMarketplaceModelEndpoints operation. This operation supports pagination; See into_paginator().

• The fluent builder is configurable:
  • max_results(i32) / set_max_results(Option<i32>):
    required: false
    

    The maximum number of results to return in a single call. If more results are available, the operation returns a NextToken value.

    
    
  • next_token(impl Into<String>) / set_next_token(Option<String>):
    required: false
    

    The token for the next set of results. You receive this token from a previous ListMarketplaceModelEndpoints call.

    
    
  • model_source_equals(impl Into<String>) / set_model_source_equals(Option<String>):
    required: false
    

    If specified, only endpoints for the given model source identifier are returned.

    
    
• On success, responds with ListMarketplaceModelEndpointsOutput with field(s):
  • marketplace_model_endpoints(Option<Vec::<MarketplaceModelEndpointSummary>>):

    An array of endpoint summaries.

  • next_token(Option<String>):

    The token for the next set of results. Use this token to get the next set of results.

• On failure, responds with SdkError<ListMarketplaceModelEndpointsError>

impl Client

pub fn list_model_copy_jobs(&self) -> ListModelCopyJobsFluentBuilder

Constructs a fluent builder for the ListModelCopyJobs operation. This operation supports pagination; See into_paginator().

• The fluent builder is configurable:
  • creation_time_after(DateTime) / set_creation_time_after(Option<DateTime>):
    required: false
    

    Filters for model copy jobs created after the specified time.

    
    
  • creation_time_before(DateTime) / set_creation_time_before(Option<DateTime>):
    required: false
    

    Filters for model copy jobs created before the specified time.

    
    
  • status_equals(ModelCopyJobStatus) / set_status_equals(Option<ModelCopyJobStatus>):
    required: false
    

    Filters for model copy jobs whose status matches the value that you specify.

    
    
  • source_account_equals(impl Into<String>) / set_source_account_equals(Option<String>):
    required: false
    

    Filters for model copy jobs in which the account that the source model belongs to is equal to the value that you specify.

    
    
  • source_model_arn_equals(impl Into<String>) / set_source_model_arn_equals(Option<String>):
    required: false
    

    Filters for model copy jobs in which the Amazon Resource Name (ARN) of the source model to is equal to the value that you specify.

    
    
  • target_model_name_contains(impl Into<String>) / set_target_model_name_contains(Option<String>):
    required: false
    

    Filters for model copy jobs in which the name of the copied model contains the string that you specify.

    
    
  • max_results(i32) / set_max_results(Option<i32>):
    required: false
    

    The maximum number of results to return in the response. If the total number of results is greater than this value, use the token returned in the response in the nextToken field when making another request to return the next batch of results.

    
    
  • next_token(impl Into<String>) / set_next_token(Option<String>):
    required: false
    

    If the total number of results is greater than the maxResults value provided in the request, enter the token returned in the nextToken field in the response in this field to return the next batch of results.

    
    
  • sort_by(SortJobsBy) / set_sort_by(Option<SortJobsBy>):
    required: false
    

    The field to sort by in the returned list of model copy jobs.

    
    
  • sort_order(SortOrder) / set_sort_order(Option<SortOrder>):
    required: false
    

    Specifies whether to sort the results in ascending or descending order.

    
    
• On success, responds with ListModelCopyJobsOutput with field(s):
  • next_token(Option<String>):

    If the total number of results is greater than the maxResults value provided in the request, use this token when making another request in the nextToken field to return the next batch of results.

  • model_copy_job_summaries(Option<Vec::<ModelCopyJobSummary>>):

    A list of information about each model copy job.

• On failure, responds with SdkError<ListModelCopyJobsError>

impl Client

pub fn list_model_customization_jobs( &self, ) -> ListModelCustomizationJobsFluentBuilder

Constructs a fluent builder for the ListModelCustomizationJobs operation. This operation supports pagination; See into_paginator().

• The fluent builder is configurable:
  • creation_time_after(DateTime) / set_creation_time_after(Option<DateTime>):
    required: false
    

    Return customization jobs created after the specified time.

    
    
  • creation_time_before(DateTime) / set_creation_time_before(Option<DateTime>):
    required: false
    

    Return customization jobs created before the specified time.

    
    
  • status_equals(FineTuningJobStatus) / set_status_equals(Option<FineTuningJobStatus>):
    required: false
    

    Return customization jobs with the specified status.

    
    
  • name_contains(impl Into<String>) / set_name_contains(Option<String>):
    required: false
    

    Return customization jobs only if the job name contains these characters.

    
    
  • max_results(i32) / set_max_results(Option<i32>):
    required: false
    

    The maximum number of results to return in the response. If the total number of results is greater than this value, use the token returned in the response in the nextToken field when making another request to return the next batch of results.

    
    
  • next_token(impl Into<String>) / set_next_token(Option<String>):
    required: false
    

    If the total number of results is greater than the maxResults value provided in the request, enter the token returned in the nextToken field in the response in this field to return the next batch of results.

    
    
  • sort_by(SortJobsBy) / set_sort_by(Option<SortJobsBy>):
    required: false
    

    The field to sort by in the returned list of jobs.

    
    
  • sort_order(SortOrder) / set_sort_order(Option<SortOrder>):
    required: false
    

    The sort order of the results.

    
    
• On success, responds with ListModelCustomizationJobsOutput with field(s):
  • next_token(Option<String>):

    If the total number of results is greater than the maxResults value provided in the request, use this token when making another request in the nextToken field to return the next batch of results.

  • model_customization_job_summaries(Option<Vec::<ModelCustomizationJobSummary>>):

    Job summaries.

• On failure, responds with SdkError<ListModelCustomizationJobsError>

impl Client

pub fn list_model_import_jobs(&self) -> ListModelImportJobsFluentBuilder

Constructs a fluent builder for the ListModelImportJobs operation. This operation supports pagination; See into_paginator().

• The fluent builder is configurable:
  • creation_time_after(DateTime) / set_creation_time_after(Option<DateTime>):
    required: false
    

    Return import jobs that were created after the specified time.

    
    
  • creation_time_before(DateTime) / set_creation_time_before(Option<DateTime>):
    required: false
    

    Return import jobs that were created before the specified time.

    
    
  • status_equals(ModelImportJobStatus) / set_status_equals(Option<ModelImportJobStatus>):
    required: false
    

    Return imported jobs with the specified status.

    
    
  • name_contains(impl Into<String>) / set_name_contains(Option<String>):
    required: false
    

    Return imported jobs only if the job name contains these characters.

    
    
  • max_results(i32) / set_max_results(Option<i32>):
    required: false
    

    The maximum number of results to return in the response. If the total number of results is greater than this value, use the token returned in the response in the nextToken field when making another request to return the next batch of results.

    
    
  • next_token(impl Into<String>) / set_next_token(Option<String>):
    required: false
    

    If the total number of results is greater than the maxResults value provided in the request, enter the token returned in the nextToken field in the response in this field to return the next batch of results.

    
    
  • sort_by(SortJobsBy) / set_sort_by(Option<SortJobsBy>):
    required: false
    

    The field to sort by in the returned list of imported jobs.

    
    
  • sort_order(SortOrder) / set_sort_order(Option<SortOrder>):
    required: false
    

    Specifies whether to sort the results in ascending or descending order.

    
    
• On success, responds with ListModelImportJobsOutput with field(s):
  • next_token(Option<String>):

    If the total number of results is greater than the maxResults value provided in the request, enter the token returned in the nextToken field in the response in this field to return the next batch of results.

  • model_import_job_summaries(Option<Vec::<ModelImportJobSummary>>):

    Import job summaries.

• On failure, responds with SdkError<ListModelImportJobsError>

impl Client

pub fn list_model_invocation_jobs(&self) -> ListModelInvocationJobsFluentBuilder

Constructs a fluent builder for the ListModelInvocationJobs operation. This operation supports pagination; See into_paginator().

• The fluent builder is configurable:
  • submit_time_after(DateTime) / set_submit_time_after(Option<DateTime>):
    required: false
    

    Specify a time to filter for batch inference jobs that were submitted after the time you specify.

    
    
  • submit_time_before(DateTime) / set_submit_time_before(Option<DateTime>):
    required: false
    

    Specify a time to filter for batch inference jobs that were submitted before the time you specify.

    
    
  • status_equals(ModelInvocationJobStatus) / set_status_equals(Option<ModelInvocationJobStatus>):
    required: false
    

    Specify a status to filter for batch inference jobs whose statuses match the string you specify.

    The following statuses are possible:

    • Submitted – This job has been submitted to a queue for validation.

    • Validating – This job is being validated for the requirements described in Format and upload your batch inference data. The criteria include the following:

      • Your IAM service role has access to the Amazon S3 buckets containing your files.

      • Your files are .jsonl files and each individual record is a JSON object in the correct format. Note that validation doesn’t check if the modelInput value matches the request body for the model.

      • Your files fulfill the requirements for file size and number of records. For more information, see Quotas for Amazon Bedrock.

    • Scheduled – This job has been validated and is now in a queue. The job will automatically start when it reaches its turn.

    • Expired – This job timed out because it was scheduled but didn’t begin before the set timeout duration. Submit a new job request.

    • InProgress – This job has begun. You can start viewing the results in the output S3 location.

    • Completed – This job has successfully completed. View the output files in the output S3 location.

    • PartiallyCompleted – This job has partially completed. Not all of your records could be processed in time. View the output files in the output S3 location.

    • Failed – This job has failed. Check the failure message for any further details. For further assistance, reach out to the Amazon Web ServicesSupport Center.

    • Stopped – This job was stopped by a user.

    • Stopping – This job is being stopped by a user.

    
    
  • name_contains(impl Into<String>) / set_name_contains(Option<String>):
    required: false
    

    Specify a string to filter for batch inference jobs whose names contain the string.

    
    
  • max_results(i32) / set_max_results(Option<i32>):
    required: false
    

    The maximum number of results to return. If there are more results than the number that you specify, a nextToken value is returned. Use the nextToken in a request to return the next batch of results.

    
    
  • next_token(impl Into<String>) / set_next_token(Option<String>):
    required: false
    

    If there were more results than the value you specified in the maxResults field in a previous ListModelInvocationJobs request, the response would have returned a nextToken value. To see the next batch of results, send the nextToken value in another request.

    
    
  • sort_by(SortJobsBy) / set_sort_by(Option<SortJobsBy>):
    required: false
    

    An attribute by which to sort the results.

    
    
  • sort_order(SortOrder) / set_sort_order(Option<SortOrder>):
    required: false
    

    Specifies whether to sort the results by ascending or descending order.

    
    
• On success, responds with ListModelInvocationJobsOutput with field(s):
  • next_token(Option<String>):

    If there are more results than can fit in the response, a nextToken is returned. Use the nextToken in a request to return the next batch of results.

  • invocation_job_summaries(Option<Vec::<ModelInvocationJobSummary>>):

    A list of items, each of which contains a summary about a batch inference job.

• On failure, responds with SdkError<ListModelInvocationJobsError>

impl Client

pub fn list_prompt_routers(&self) -> ListPromptRoutersFluentBuilder

Constructs a fluent builder for the ListPromptRouters operation. This operation supports pagination; See into_paginator().

• The fluent builder is configurable:
  • max_results(i32) / set_max_results(Option<i32>):
    required: false
    

    The maximum number of prompt routers to return in one page of results.

    
    
  • next_token(impl Into<String>) / set_next_token(Option<String>):
    required: false
    

    Specify the pagination token from a previous request to retrieve the next page of results.

    
    
  • r#type(PromptRouterType) / set_type(Option<PromptRouterType>):
    required: false
    

    The type of the prompt routers, such as whether it’s default or custom.

    
    
• On success, responds with ListPromptRoutersOutput with field(s):
  • prompt_router_summaries(Option<Vec::<PromptRouterSummary>>):

    A list of prompt router summaries.

  • next_token(Option<String>):

    Specify the pagination token from a previous request to retrieve the next page of results.

• On failure, responds with SdkError<ListPromptRoutersError>

impl Client

pub fn list_provisioned_model_throughputs( &self, ) -> ListProvisionedModelThroughputsFluentBuilder

Constructs a fluent builder for the ListProvisionedModelThroughputs operation. This operation supports pagination; See into_paginator().

• The fluent builder is configurable:
  • creation_time_after(DateTime) / set_creation_time_after(Option<DateTime>):
    required: false
    

    A filter that returns Provisioned Throughputs created after the specified time.

    
    
  • creation_time_before(DateTime) / set_creation_time_before(Option<DateTime>):
    required: false
    

    A filter that returns Provisioned Throughputs created before the specified time.

    
    
  • status_equals(ProvisionedModelStatus) / set_status_equals(Option<ProvisionedModelStatus>):
    required: false
    

    A filter that returns Provisioned Throughputs if their statuses matches the value that you specify.

    
    
  • model_arn_equals(impl Into<String>) / set_model_arn_equals(Option<String>):
    required: false
    

    A filter that returns Provisioned Throughputs whose model Amazon Resource Name (ARN) is equal to the value that you specify.

    
    
  • name_contains(impl Into<String>) / set_name_contains(Option<String>):
    required: false
    

    A filter that returns Provisioned Throughputs if their name contains the expression that you specify.

    
    
  • max_results(i32) / set_max_results(Option<i32>):
    required: false
    

    THe maximum number of results to return in the response. If there are more results than the number you specified, the response returns a nextToken value. To see the next batch of results, send the nextToken value in another list request.

    
    
  • next_token(impl Into<String>) / set_next_token(Option<String>):
    required: false
    

    If there are more results than the number you specified in the maxResults field, the response returns a nextToken value. To see the next batch of results, specify the nextToken value in this field.

    
    
  • sort_by(SortByProvisionedModels) / set_sort_by(Option<SortByProvisionedModels>):
    required: false
    

    The field by which to sort the returned list of Provisioned Throughputs.

    
    
  • sort_order(SortOrder) / set_sort_order(Option<SortOrder>):
    required: false
    

    The sort order of the results.

    
    
• On success, responds with ListProvisionedModelThroughputsOutput with field(s):
  • next_token(Option<String>):

    If there are more results than the number you specified in the maxResults field, this value is returned. To see the next batch of results, include this value in the nextToken field in another list request.

  • provisioned_model_summaries(Option<Vec::<ProvisionedModelSummary>>):

    A list of summaries, one for each Provisioned Throughput in the response.

• On failure, responds with SdkError<ListProvisionedModelThroughputsError>

impl Client

pub fn list_tags_for_resource(&self) -> ListTagsForResourceFluentBuilder

Constructs a fluent builder for the ListTagsForResource operation.

• The fluent builder is configurable:
  • resource_arn(impl Into<String>) / set_resource_arn(Option<String>):
    required: true
    

    The Amazon Resource Name (ARN) of the resource.

    
    
• On success, responds with ListTagsForResourceOutput with field(s):
  • tags(Option<Vec::<Tag>>):

    An array of the tags associated with this resource.

• On failure, responds with SdkError<ListTagsForResourceError>

impl Client

pub fn put_model_invocation_logging_configuration( &self, ) -> PutModelInvocationLoggingConfigurationFluentBuilder

Constructs a fluent builder for the PutModelInvocationLoggingConfiguration operation.

• The fluent builder is configurable:
  • logging_config(LoggingConfig) / set_logging_config(Option<LoggingConfig>):
    required: true
    

    The logging configuration values to set.

    
    
• On success, responds with PutModelInvocationLoggingConfigurationOutput
• On failure, responds with SdkError<PutModelInvocationLoggingConfigurationError>

impl Client

pub fn register_marketplace_model_endpoint( &self, ) -> RegisterMarketplaceModelEndpointFluentBuilder

Constructs a fluent builder for the RegisterMarketplaceModelEndpoint operation.

• The fluent builder is configurable:
  • endpoint_identifier(impl Into<String>) / set_endpoint_identifier(Option<String>):
    required: true
    

    The ARN of the Amazon SageMaker endpoint you want to register with Amazon Bedrock Marketplace.

    
    
  • model_source_identifier(impl Into<String>) / set_model_source_identifier(Option<String>):
    required: true
    

    The ARN of the model from Amazon Bedrock Marketplace that is deployed on the endpoint.

    
    
• On success, responds with RegisterMarketplaceModelEndpointOutput with field(s):
  • marketplace_model_endpoint(Option<MarketplaceModelEndpoint>):

    Details about the registered endpoint.

• On failure, responds with SdkError<RegisterMarketplaceModelEndpointError>

impl Client

pub fn stop_evaluation_job(&self) -> StopEvaluationJobFluentBuilder

Constructs a fluent builder for the StopEvaluationJob operation.

• The fluent builder is configurable:
  • job_identifier(impl Into<String>) / set_job_identifier(Option<String>):
    required: true
    

    The Amazon Resource Name (ARN) of the evaluation job you want to stop.

    
    
• On success, responds with StopEvaluationJobOutput
• On failure, responds with SdkError<StopEvaluationJobError>

impl Client

pub fn stop_model_customization_job( &self, ) -> StopModelCustomizationJobFluentBuilder

Constructs a fluent builder for the StopModelCustomizationJob operation.

• The fluent builder is configurable:
  • job_identifier(impl Into<String>) / set_job_identifier(Option<String>):
    required: true
    

    Job identifier of the job to stop.

    
    
• On success, responds with StopModelCustomizationJobOutput
• On failure, responds with SdkError<StopModelCustomizationJobError>

impl Client

pub fn stop_model_invocation_job(&self) -> StopModelInvocationJobFluentBuilder

Constructs a fluent builder for the StopModelInvocationJob operation.

• The fluent builder is configurable:
  • job_identifier(impl Into<String>) / set_job_identifier(Option<String>):
    required: true
    

    The Amazon Resource Name (ARN) of the batch inference job to stop.

    
    
• On success, responds with StopModelInvocationJobOutput
• On failure, responds with SdkError<StopModelInvocationJobError>

impl Client

pub fn tag_resource(&self) -> TagResourceFluentBuilder

Constructs a fluent builder for the TagResource operation.

• The fluent builder is configurable:
  • resource_arn(impl Into<String>) / set_resource_arn(Option<String>):
    required: true
    

    The Amazon Resource Name (ARN) of the resource to tag.

    
    
  • tags(Tag) / set_tags(Option<Vec::<Tag>>):
    required: true
    

    Tags to associate with the resource.

    
    
• On success, responds with TagResourceOutput
• On failure, responds with SdkError<TagResourceError>

impl Client

pub fn untag_resource(&self) -> UntagResourceFluentBuilder

Constructs a fluent builder for the UntagResource operation.

• The fluent builder is configurable:
  • resource_arn(impl Into<String>) / set_resource_arn(Option<String>):
    required: true
    

    The Amazon Resource Name (ARN) of the resource to untag.

    
    
  • tag_keys(impl Into<String>) / set_tag_keys(Option<Vec::<String>>):
    required: true
    

    Tag keys of the tags to remove from the resource.

    
    
• On success, responds with UntagResourceOutput
• On failure, responds with SdkError<UntagResourceError>

impl Client

pub fn update_guardrail(&self) -> UpdateGuardrailFluentBuilder

Constructs a fluent builder for the UpdateGuardrail operation.

• The fluent builder is configurable:
  • guardrail_identifier(impl Into<String>) / set_guardrail_identifier(Option<String>):
    required: true
    

    The unique identifier of the guardrail. This can be an ID or the ARN.

    
    
  • name(impl Into<String>) / set_name(Option<String>):
    required: true
    

    A name for the guardrail.

    
    
  • description(impl Into<String>) / set_description(Option<String>):
    required: false
    

    A description of the guardrail.

    
    
  • topic_policy_config(GuardrailTopicPolicyConfig) / set_topic_policy_config(Option<GuardrailTopicPolicyConfig>):
    required: false
    

    The topic policy to configure for the guardrail.

    
    
  • content_policy_config(GuardrailContentPolicyConfig) / set_content_policy_config(Option<GuardrailContentPolicyConfig>):
    required: false
    

    The content policy to configure for the guardrail.

    
    
  • word_policy_config(GuardrailWordPolicyConfig) / set_word_policy_config(Option<GuardrailWordPolicyConfig>):
    required: false
    

    The word policy to configure for the guardrail.

    
    
  • sensitive_information_policy_config(GuardrailSensitiveInformationPolicyConfig) / set_sensitive_information_policy_config(Option<GuardrailSensitiveInformationPolicyConfig>):
    required: false
    

    The sensitive information policy to configure for the guardrail.

    
    
  • contextual_grounding_policy_config(GuardrailContextualGroundingPolicyConfig) / set_contextual_grounding_policy_config(Option<GuardrailContextualGroundingPolicyConfig>):
    required: false
    

    The contextual grounding policy configuration used to update a guardrail.

    
    
  • cross_region_config(GuardrailCrossRegionConfig) / set_cross_region_config(Option<GuardrailCrossRegionConfig>):
    required: false
    

    The system-defined guardrail profile that you’re using with your guardrail. Guardrail profiles define the destination Amazon Web Services Regions where guardrail inference requests can be automatically routed.

    For more information, see the Amazon Bedrock User Guide.

    
    
  • blocked_input_messaging(impl Into<String>) / set_blocked_input_messaging(Option<String>):
    required: true
    

    The message to return when the guardrail blocks a prompt.

    
    
  • blocked_outputs_messaging(impl Into<String>) / set_blocked_outputs_messaging(Option<String>):
    required: true
    

    The message to return when the guardrail blocks a model response.

    
    
  • kms_key_id(impl Into<String>) / set_kms_key_id(Option<String>):
    required: false
    

    The ARN of the KMS key with which to encrypt the guardrail.

    
    
• On success, responds with UpdateGuardrailOutput with field(s):
  • guardrail_id(String):

    The unique identifier of the guardrail

  • guardrail_arn(String):

    The ARN of the guardrail.

  • version(String):

    The version of the guardrail.

  • updated_at(DateTime):

    The date and time at which the guardrail was updated.

• On failure, responds with SdkError<UpdateGuardrailError>

impl Client

pub fn update_marketplace_model_endpoint( &self, ) -> UpdateMarketplaceModelEndpointFluentBuilder

Constructs a fluent builder for the UpdateMarketplaceModelEndpoint operation.

• The fluent builder is configurable:
  • endpoint_arn(impl Into<String>) / set_endpoint_arn(Option<String>):
    required: true
    

    The Amazon Resource Name (ARN) of the endpoint you want to update.

    
    
  • endpoint_config(EndpointConfig) / set_endpoint_config(Option<EndpointConfig>):
    required: true
    

    The new configuration for the endpoint, including the number and type of instances to use.

    
    
  • client_request_token(impl Into<String>) / set_client_request_token(Option<String>):
    required: false
    

    A unique, case-sensitive identifier that you provide to ensure the idempotency of the request. This token is listed as not required because Amazon Web Services SDKs automatically generate it for you and set this parameter. If you’re not using the Amazon Web Services SDK or the CLI, you must provide this token or the action will fail.

    
    
• On success, responds with UpdateMarketplaceModelEndpointOutput with field(s):
  • marketplace_model_endpoint(Option<MarketplaceModelEndpoint>):

    Details about the updated endpoint.

• On failure, responds with SdkError<UpdateMarketplaceModelEndpointError>

impl Client

pub fn update_provisioned_model_throughput( &self, ) -> UpdateProvisionedModelThroughputFluentBuilder

Constructs a fluent builder for the UpdateProvisionedModelThroughput operation.

• The fluent builder is configurable:
  • provisioned_model_id(impl Into<String>) / set_provisioned_model_id(Option<String>):
    required: true
    

    The Amazon Resource Name (ARN) or name of the Provisioned Throughput to update.

    
    
  • desired_provisioned_model_name(impl Into<String>) / set_desired_provisioned_model_name(Option<String>):
    required: false
    

    The new name for this Provisioned Throughput.

    
    
  • desired_model_id(impl Into<String>) / set_desired_model_id(Option<String>):
    required: false
    

    The Amazon Resource Name (ARN) of the new model to associate with this Provisioned Throughput. You can’t specify this field if this Provisioned Throughput is associated with a base model.

    If this Provisioned Throughput is associated with a custom model, you can specify one of the following options:

    • The base model from which the custom model was customized.

    • Another custom model that was customized from the same base model as the custom model.

    
    
• On success, responds with UpdateProvisionedModelThroughputOutput
• On failure, responds with SdkError<UpdateProvisionedModelThroughputError>

impl Client

pub fn from_conf(conf: Config) -> Self

Creates a new client from the service Config.

Panics

This method will panic in the following cases:

• Retries or timeouts are enabled without a sleep_impl configured.
• Identity caching is enabled without a sleep_impl and time_source configured.
• No behavior_version is provided.

The panic message for each of these will have instructions on how to resolve them.

pub fn config(&self) -> &Config

Returns the client’s configuration.

impl Client

pub fn new(sdk_config: &SdkConfig) -> Self

Creates a new client from an SDK Config.

Panics

• This method will panic if the sdk_config is missing an async sleep implementation. If you experience this panic, set the sleep_impl on the Config passed into this function to fix it.
• This method will panic if the sdk_config is missing an HTTP connector. If you experience this panic, set the http_connector on the Config passed into this function to fix it.
• This method will panic if no BehaviorVersion is provided. If you experience this panic, set behavior_version on the Config or enable the behavior-version-latest Cargo feature.

Trait Implementations

impl Clone for Client

fn clone(&self) -> Client

Returns a copy of the value.

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

Performs copy-assignment from source.

impl Debug for Client

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

Formats the value using the given formatter.