Deletes a batch of evaluation jobs. An evaluation job can only be deleted if it has following status FAILED, COMPLETED, and STOPPED. You can request up to 25 model evaluation jobs be deleted in a single request.
Creates an evaluation job.
", "idempotent":true }, "CreateGuardrail":{ "name":"CreateGuardrail", "http":{ "method":"POST", "requestUri":"/guardrails", "responseCode":202 }, "input":{"shape":"CreateGuardrailRequest"}, "output":{"shape":"CreateGuardrailResponse"}, "errors":[ {"shape":"ResourceNotFoundException"}, {"shape":"AccessDeniedException"}, {"shape":"ValidationException"}, {"shape":"ConflictException"}, {"shape":"InternalServerException"}, {"shape":"TooManyTagsException"}, {"shape":"ServiceQuotaExceededException"}, {"shape":"ThrottlingException"} ], "documentation":"Creates a guardrail to block topics and to implement safeguards for your generative AI applications.
You can configure the following policies in a guardrail to avoid undesirable and harmful content, filter out denied topics and words, and remove sensitive information for privacy protection.
Content filters - Adjust filter strengths to block input prompts or model responses containing harmful content.
Denied topics - Define a set of topics that are undesirable in the context of your application. These topics will be blocked if detected in user queries or model responses.
Word filters - Configure filters to block undesirable words, phrases, and profanity. Such words can include offensive terms, competitor names etc.
Sensitive information filters - Block or mask sensitive information such as personally identifiable information (PII) or custom regex in user inputs and model responses.
In addition to the above policies, you can also configure the messages to be returned to the user if a user input or model response is in violation of the policies defined in the guardrail.
For more information, see Amazon Bedrock Guardrails in the Amazon Bedrock User Guide.
" }, "CreateGuardrailVersion":{ "name":"CreateGuardrailVersion", "http":{ "method":"POST", "requestUri":"/guardrails/{guardrailIdentifier}", "responseCode":202 }, "input":{"shape":"CreateGuardrailVersionRequest"}, "output":{"shape":"CreateGuardrailVersionResponse"}, "errors":[ {"shape":"ResourceNotFoundException"}, {"shape":"AccessDeniedException"}, {"shape":"ValidationException"}, {"shape":"ConflictException"}, {"shape":"InternalServerException"}, {"shape":"ServiceQuotaExceededException"}, {"shape":"ThrottlingException"} ], "documentation":"Creates a version of the guardrail. Use this API to create a snapshot of the guardrail when you are satisfied with a configuration, or to compare the configuration with another version.
" }, "CreateInferenceProfile":{ "name":"CreateInferenceProfile", "http":{ "method":"POST", "requestUri":"/inference-profiles", "responseCode":201 }, "input":{"shape":"CreateInferenceProfileRequest"}, "output":{"shape":"CreateInferenceProfileResponse"}, "errors":[ {"shape":"ResourceNotFoundException"}, {"shape":"AccessDeniedException"}, {"shape":"ValidationException"}, {"shape":"ConflictException"}, {"shape":"InternalServerException"}, {"shape":"TooManyTagsException"}, {"shape":"ServiceQuotaExceededException"}, {"shape":"ThrottlingException"} ], "documentation":"Creates an application inference profile to track metrics and costs when invoking a model. To create an application inference profile for a foundation model in one region, specify the ARN of the model in that region. To create an application inference profile for a foundation model across multiple regions, specify the ARN of the system-defined inference profile that contains the regions that you want to route requests to. For more information, see Increase throughput and resilience with cross-region inference in Amazon Bedrock. in the Amazon Bedrock User Guide.
", "idempotent":true }, "CreateMarketplaceModelEndpoint":{ "name":"CreateMarketplaceModelEndpoint", "http":{ "method":"POST", "requestUri":"/marketplace-model/endpoints", "responseCode":200 }, "input":{"shape":"CreateMarketplaceModelEndpointRequest"}, "output":{"shape":"CreateMarketplaceModelEndpointResponse"}, "errors":[ {"shape":"ResourceNotFoundException"}, {"shape":"AccessDeniedException"}, {"shape":"ValidationException"}, {"shape":"ConflictException"}, {"shape":"InternalServerException"}, {"shape":"ServiceQuotaExceededException"}, {"shape":"ThrottlingException"} ], "documentation":"Creates an endpoint for a model from Amazon Bedrock Marketplace. The endpoint is hosted by Amazon SageMaker.
" }, "CreateModelCopyJob":{ "name":"CreateModelCopyJob", "http":{ "method":"POST", "requestUri":"/model-copy-jobs", "responseCode":201 }, "input":{"shape":"CreateModelCopyJobRequest"}, "output":{"shape":"CreateModelCopyJobResponse"}, "errors":[ {"shape":"ResourceNotFoundException"}, {"shape":"AccessDeniedException"}, {"shape":"InternalServerException"}, {"shape":"TooManyTagsException"} ], "documentation":"Copies a model to another region so that it can be used there. For more information, see Copy models to be used in other regions in the Amazon Bedrock User Guide.
", "idempotent":true }, "CreateModelCustomizationJob":{ "name":"CreateModelCustomizationJob", "http":{ "method":"POST", "requestUri":"/model-customization-jobs", "responseCode":201 }, "input":{"shape":"CreateModelCustomizationJobRequest"}, "output":{"shape":"CreateModelCustomizationJobResponse"}, "errors":[ {"shape":"ResourceNotFoundException"}, {"shape":"AccessDeniedException"}, {"shape":"ValidationException"}, {"shape":"ConflictException"}, {"shape":"InternalServerException"}, {"shape":"TooManyTagsException"}, {"shape":"ServiceQuotaExceededException"}, {"shape":"ThrottlingException"} ], "documentation":"Creates a fine-tuning job to customize a base model.
You specify the base foundation model and the location of the training data. After the model-customization job completes successfully, your custom model resource will be ready to use. Amazon Bedrock returns validation loss metrics and output generations after the job completes.
For information on the format of training and validation data, see Prepare the datasets.
Model-customization jobs are asynchronous and the completion time depends on the base model and the training/validation data size. To monitor a job, use the GetModelCustomizationJob operation to retrieve the job status.
For more information, see Custom models in the Amazon Bedrock User Guide.
", "idempotent":true }, "CreateModelImportJob":{ "name":"CreateModelImportJob", "http":{ "method":"POST", "requestUri":"/model-import-jobs", "responseCode":201 }, "input":{"shape":"CreateModelImportJobRequest"}, "output":{"shape":"CreateModelImportJobResponse"}, "errors":[ {"shape":"ResourceNotFoundException"}, {"shape":"AccessDeniedException"}, {"shape":"ValidationException"}, {"shape":"ConflictException"}, {"shape":"InternalServerException"}, {"shape":"TooManyTagsException"}, {"shape":"ServiceQuotaExceededException"}, {"shape":"ThrottlingException"} ], "documentation":"Creates a model import job to import model that you have customized in other environments, such as Amazon SageMaker. For more information, see Import a customized model
", "idempotent":true }, "CreateModelInvocationJob":{ "name":"CreateModelInvocationJob", "http":{ "method":"POST", "requestUri":"/model-invocation-job", "responseCode":200 }, "input":{"shape":"CreateModelInvocationJobRequest"}, "output":{"shape":"CreateModelInvocationJobResponse"}, "errors":[ {"shape":"ResourceNotFoundException"}, {"shape":"AccessDeniedException"}, {"shape":"ValidationException"}, {"shape":"ConflictException"}, {"shape":"InternalServerException"}, {"shape":"ServiceQuotaExceededException"}, {"shape":"ThrottlingException"} ], "documentation":"Creates a batch inference job to invoke a model on multiple prompts. Format your data according to Format your inference data and upload it to an Amazon S3 bucket. For more information, see Process multiple prompts with batch inference.
The response returns a jobArn that you can use to stop or get details about the job.
Creates a prompt router that manages the routing of requests between multiple foundation models based on the routing criteria.
", "idempotent":true }, "CreateProvisionedModelThroughput":{ "name":"CreateProvisionedModelThroughput", "http":{ "method":"POST", "requestUri":"/provisioned-model-throughput", "responseCode":201 }, "input":{"shape":"CreateProvisionedModelThroughputRequest"}, "output":{"shape":"CreateProvisionedModelThroughputResponse"}, "errors":[ {"shape":"ResourceNotFoundException"}, {"shape":"AccessDeniedException"}, {"shape":"ValidationException"}, {"shape":"InternalServerException"}, {"shape":"TooManyTagsException"}, {"shape":"ServiceQuotaExceededException"}, {"shape":"ThrottlingException"} ], "documentation":"Creates dedicated throughput for a base or custom model with the model units and for the duration that you specify. For pricing details, see Amazon Bedrock Pricing. For more information, see Provisioned Throughput in the Amazon Bedrock User Guide.
", "idempotent":true }, "DeleteCustomModel":{ "name":"DeleteCustomModel", "http":{ "method":"DELETE", "requestUri":"/custom-models/{modelIdentifier}", "responseCode":200 }, "input":{"shape":"DeleteCustomModelRequest"}, "output":{"shape":"DeleteCustomModelResponse"}, "errors":[ {"shape":"ResourceNotFoundException"}, {"shape":"AccessDeniedException"}, {"shape":"ValidationException"}, {"shape":"ConflictException"}, {"shape":"InternalServerException"}, {"shape":"ThrottlingException"} ], "documentation":"Deletes a custom model that you created earlier. For more information, see Custom models in the Amazon Bedrock User Guide.
", "idempotent":true }, "DeleteGuardrail":{ "name":"DeleteGuardrail", "http":{ "method":"DELETE", "requestUri":"/guardrails/{guardrailIdentifier}", "responseCode":202 }, "input":{"shape":"DeleteGuardrailRequest"}, "output":{"shape":"DeleteGuardrailResponse"}, "errors":[ {"shape":"ResourceNotFoundException"}, {"shape":"AccessDeniedException"}, {"shape":"ValidationException"}, {"shape":"ConflictException"}, {"shape":"InternalServerException"}, {"shape":"ThrottlingException"} ], "documentation":"Deletes a guardrail.
To delete a guardrail, only specify the ARN of the guardrail in the guardrailIdentifier field. If you delete a guardrail, all of its versions will be deleted.
To delete a version of a guardrail, specify the ARN of the guardrail in the guardrailIdentifier field and the version in the guardrailVersion field.
Deletes a custom model that you imported earlier. For more information, see Import a customized model in the Amazon Bedrock User Guide.
", "idempotent":true }, "DeleteInferenceProfile":{ "name":"DeleteInferenceProfile", "http":{ "method":"DELETE", "requestUri":"/inference-profiles/{inferenceProfileIdentifier}", "responseCode":200 }, "input":{"shape":"DeleteInferenceProfileRequest"}, "output":{"shape":"DeleteInferenceProfileResponse"}, "errors":[ {"shape":"ResourceNotFoundException"}, {"shape":"AccessDeniedException"}, {"shape":"ValidationException"}, {"shape":"ConflictException"}, {"shape":"InternalServerException"}, {"shape":"ThrottlingException"} ], "documentation":"Deletes an application inference profile. For more information, see Increase throughput and resilience with cross-region inference in Amazon Bedrock. in the Amazon Bedrock User Guide.
", "idempotent":true }, "DeleteMarketplaceModelEndpoint":{ "name":"DeleteMarketplaceModelEndpoint", "http":{ "method":"DELETE", "requestUri":"/marketplace-model/endpoints/{endpointArn}", "responseCode":200 }, "input":{"shape":"DeleteMarketplaceModelEndpointRequest"}, "output":{"shape":"DeleteMarketplaceModelEndpointResponse"}, "errors":[ {"shape":"ResourceNotFoundException"}, {"shape":"AccessDeniedException"}, {"shape":"ValidationException"}, {"shape":"InternalServerException"}, {"shape":"ThrottlingException"} ], "documentation":"Deletes an endpoint for a model from Amazon Bedrock Marketplace.
", "idempotent":true }, "DeleteModelInvocationLoggingConfiguration":{ "name":"DeleteModelInvocationLoggingConfiguration", "http":{ "method":"DELETE", "requestUri":"/logging/modelinvocations", "responseCode":200 }, "input":{"shape":"DeleteModelInvocationLoggingConfigurationRequest"}, "output":{"shape":"DeleteModelInvocationLoggingConfigurationResponse"}, "errors":[ {"shape":"AccessDeniedException"}, {"shape":"InternalServerException"}, {"shape":"ThrottlingException"} ], "documentation":"Delete the invocation logging.
", "idempotent":true }, "DeletePromptRouter":{ "name":"DeletePromptRouter", "http":{ "method":"DELETE", "requestUri":"/prompt-routers/{promptRouterArn}", "responseCode":200 }, "input":{"shape":"DeletePromptRouterRequest"}, "output":{"shape":"DeletePromptRouterResponse"}, "errors":[ {"shape":"ResourceNotFoundException"}, {"shape":"AccessDeniedException"}, {"shape":"ValidationException"}, {"shape":"InternalServerException"}, {"shape":"ThrottlingException"} ], "documentation":"Deletes a specified prompt router. This action cannot be undone.
", "idempotent":true }, "DeleteProvisionedModelThroughput":{ "name":"DeleteProvisionedModelThroughput", "http":{ "method":"DELETE", "requestUri":"/provisioned-model-throughput/{provisionedModelId}", "responseCode":200 }, "input":{"shape":"DeleteProvisionedModelThroughputRequest"}, "output":{"shape":"DeleteProvisionedModelThroughputResponse"}, "errors":[ {"shape":"ResourceNotFoundException"}, {"shape":"AccessDeniedException"}, {"shape":"ValidationException"}, {"shape":"ConflictException"}, {"shape":"InternalServerException"}, {"shape":"ThrottlingException"} ], "documentation":"Deletes a Provisioned Throughput. You can't delete a Provisioned Throughput before the commitment term is over. For more information, see Provisioned Throughput in the Amazon Bedrock User Guide.
", "idempotent":true }, "DeregisterMarketplaceModelEndpoint":{ "name":"DeregisterMarketplaceModelEndpoint", "http":{ "method":"DELETE", "requestUri":"/marketplace-model/endpoints/{endpointArn}/registration", "responseCode":200 }, "input":{"shape":"DeregisterMarketplaceModelEndpointRequest"}, "output":{"shape":"DeregisterMarketplaceModelEndpointResponse"}, "errors":[ {"shape":"ResourceNotFoundException"}, {"shape":"ServiceUnavailableException"}, {"shape":"AccessDeniedException"}, {"shape":"ValidationException"}, {"shape":"InternalServerException"}, {"shape":"ThrottlingException"} ], "documentation":"Deregisters an endpoint for a model from Amazon Bedrock Marketplace. This operation removes the endpoint's association with Amazon Bedrock but does not delete the underlying Amazon SageMaker endpoint.
" }, "GetCustomModel":{ "name":"GetCustomModel", "http":{ "method":"GET", "requestUri":"/custom-models/{modelIdentifier}", "responseCode":200 }, "input":{"shape":"GetCustomModelRequest"}, "output":{"shape":"GetCustomModelResponse"}, "errors":[ {"shape":"ResourceNotFoundException"}, {"shape":"AccessDeniedException"}, {"shape":"ValidationException"}, {"shape":"InternalServerException"}, {"shape":"ThrottlingException"} ], "documentation":"Get the properties associated with a Amazon Bedrock custom model that you have created.For more information, see Custom models in the Amazon Bedrock User Guide.
" }, "GetEvaluationJob":{ "name":"GetEvaluationJob", "http":{ "method":"GET", "requestUri":"/evaluation-jobs/{jobIdentifier}", "responseCode":200 }, "input":{"shape":"GetEvaluationJobRequest"}, "output":{"shape":"GetEvaluationJobResponse"}, "errors":[ {"shape":"ResourceNotFoundException"}, {"shape":"AccessDeniedException"}, {"shape":"ValidationException"}, {"shape":"InternalServerException"}, {"shape":"ThrottlingException"} ], "documentation":"Gets information about an evaluation job, such as the status of the job.
" }, "GetFoundationModel":{ "name":"GetFoundationModel", "http":{ "method":"GET", "requestUri":"/foundation-models/{modelIdentifier}", "responseCode":200 }, "input":{"shape":"GetFoundationModelRequest"}, "output":{"shape":"GetFoundationModelResponse"}, "errors":[ {"shape":"ResourceNotFoundException"}, {"shape":"AccessDeniedException"}, {"shape":"ValidationException"}, {"shape":"InternalServerException"}, {"shape":"ThrottlingException"} ], "documentation":"Get details about a Amazon Bedrock foundation model.
" }, "GetGuardrail":{ "name":"GetGuardrail", "http":{ "method":"GET", "requestUri":"/guardrails/{guardrailIdentifier}", "responseCode":200 }, "input":{"shape":"GetGuardrailRequest"}, "output":{"shape":"GetGuardrailResponse"}, "errors":[ {"shape":"ResourceNotFoundException"}, {"shape":"AccessDeniedException"}, {"shape":"ValidationException"}, {"shape":"InternalServerException"}, {"shape":"ThrottlingException"} ], "documentation":"Gets details about a guardrail. If you don't specify a version, the response returns details for the DRAFT version.
Gets properties associated with a customized model you imported.
" }, "GetInferenceProfile":{ "name":"GetInferenceProfile", "http":{ "method":"GET", "requestUri":"/inference-profiles/{inferenceProfileIdentifier}", "responseCode":200 }, "input":{"shape":"GetInferenceProfileRequest"}, "output":{"shape":"GetInferenceProfileResponse"}, "errors":[ {"shape":"ResourceNotFoundException"}, {"shape":"AccessDeniedException"}, {"shape":"ValidationException"}, {"shape":"InternalServerException"}, {"shape":"ThrottlingException"} ], "documentation":"Gets information about an inference profile. For more information, see Increase throughput and resilience with cross-region inference in Amazon Bedrock. in the Amazon Bedrock User Guide.
" }, "GetMarketplaceModelEndpoint":{ "name":"GetMarketplaceModelEndpoint", "http":{ "method":"GET", "requestUri":"/marketplace-model/endpoints/{endpointArn}", "responseCode":200 }, "input":{"shape":"GetMarketplaceModelEndpointRequest"}, "output":{"shape":"GetMarketplaceModelEndpointResponse"}, "errors":[ {"shape":"ResourceNotFoundException"}, {"shape":"AccessDeniedException"}, {"shape":"ValidationException"}, {"shape":"InternalServerException"}, {"shape":"ThrottlingException"} ], "documentation":"Retrieves details about a specific endpoint for a model from Amazon Bedrock Marketplace.
" }, "GetModelCopyJob":{ "name":"GetModelCopyJob", "http":{ "method":"GET", "requestUri":"/model-copy-jobs/{jobArn}", "responseCode":200 }, "input":{"shape":"GetModelCopyJobRequest"}, "output":{"shape":"GetModelCopyJobResponse"}, "errors":[ {"shape":"ResourceNotFoundException"}, {"shape":"AccessDeniedException"}, {"shape":"ValidationException"}, {"shape":"InternalServerException"}, {"shape":"ThrottlingException"} ], "documentation":"Retrieves information about a model copy job. For more information, see Copy models to be used in other regions in the Amazon Bedrock User Guide.
" }, "GetModelCustomizationJob":{ "name":"GetModelCustomizationJob", "http":{ "method":"GET", "requestUri":"/model-customization-jobs/{jobIdentifier}", "responseCode":200 }, "input":{"shape":"GetModelCustomizationJobRequest"}, "output":{"shape":"GetModelCustomizationJobResponse"}, "errors":[ {"shape":"ResourceNotFoundException"}, {"shape":"AccessDeniedException"}, {"shape":"ValidationException"}, {"shape":"InternalServerException"}, {"shape":"ThrottlingException"} ], "documentation":"Retrieves the properties associated with a model-customization job, including the status of the job. For more information, see Custom models in the Amazon Bedrock User Guide.
" }, "GetModelImportJob":{ "name":"GetModelImportJob", "http":{ "method":"GET", "requestUri":"/model-import-jobs/{jobIdentifier}", "responseCode":200 }, "input":{"shape":"GetModelImportJobRequest"}, "output":{"shape":"GetModelImportJobResponse"}, "errors":[ {"shape":"ResourceNotFoundException"}, {"shape":"AccessDeniedException"}, {"shape":"ValidationException"}, {"shape":"InternalServerException"}, {"shape":"ThrottlingException"} ], "documentation":"Retrieves the properties associated with import model job, including the status of the job. For more information, see Import a customized model in the Amazon Bedrock User Guide.
" }, "GetModelInvocationJob":{ "name":"GetModelInvocationJob", "http":{ "method":"GET", "requestUri":"/model-invocation-job/{jobIdentifier}", "responseCode":200 }, "input":{"shape":"GetModelInvocationJobRequest"}, "output":{"shape":"GetModelInvocationJobResponse"}, "errors":[ {"shape":"ResourceNotFoundException"}, {"shape":"AccessDeniedException"}, {"shape":"ValidationException"}, {"shape":"InternalServerException"}, {"shape":"ThrottlingException"} ], "documentation":"Gets details about a batch inference job. For more information, see Monitor batch inference jobs
" }, "GetModelInvocationLoggingConfiguration":{ "name":"GetModelInvocationLoggingConfiguration", "http":{ "method":"GET", "requestUri":"/logging/modelinvocations", "responseCode":200 }, "input":{"shape":"GetModelInvocationLoggingConfigurationRequest"}, "output":{"shape":"GetModelInvocationLoggingConfigurationResponse"}, "errors":[ {"shape":"AccessDeniedException"}, {"shape":"InternalServerException"}, {"shape":"ThrottlingException"} ], "documentation":"Get the current configuration values for model invocation logging.
" }, "GetPromptRouter":{ "name":"GetPromptRouter", "http":{ "method":"GET", "requestUri":"/prompt-routers/{promptRouterArn}", "responseCode":200 }, "input":{"shape":"GetPromptRouterRequest"}, "output":{"shape":"GetPromptRouterResponse"}, "errors":[ {"shape":"ResourceNotFoundException"}, {"shape":"AccessDeniedException"}, {"shape":"ValidationException"}, {"shape":"InternalServerException"}, {"shape":"ThrottlingException"} ], "documentation":"Retrieves details about a prompt router.
" }, "GetProvisionedModelThroughput":{ "name":"GetProvisionedModelThroughput", "http":{ "method":"GET", "requestUri":"/provisioned-model-throughput/{provisionedModelId}", "responseCode":200 }, "input":{"shape":"GetProvisionedModelThroughputRequest"}, "output":{"shape":"GetProvisionedModelThroughputResponse"}, "errors":[ {"shape":"ResourceNotFoundException"}, {"shape":"AccessDeniedException"}, {"shape":"ValidationException"}, {"shape":"InternalServerException"}, {"shape":"ThrottlingException"} ], "documentation":"Returns details for a Provisioned Throughput. For more information, see Provisioned Throughput in the Amazon Bedrock User Guide.
" }, "ListCustomModels":{ "name":"ListCustomModels", "http":{ "method":"GET", "requestUri":"/custom-models", "responseCode":200 }, "input":{"shape":"ListCustomModelsRequest"}, "output":{"shape":"ListCustomModelsResponse"}, "errors":[ {"shape":"AccessDeniedException"}, {"shape":"ValidationException"}, {"shape":"InternalServerException"}, {"shape":"ThrottlingException"} ], "documentation":"Returns a list of the custom models that you have created with the CreateModelCustomizationJob operation.
For more information, see Custom models in the Amazon Bedrock User Guide.
" }, "ListEvaluationJobs":{ "name":"ListEvaluationJobs", "http":{ "method":"GET", "requestUri":"/evaluation-jobs", "responseCode":200 }, "input":{"shape":"ListEvaluationJobsRequest"}, "output":{"shape":"ListEvaluationJobsResponse"}, "errors":[ {"shape":"AccessDeniedException"}, {"shape":"ValidationException"}, {"shape":"InternalServerException"}, {"shape":"ThrottlingException"} ], "documentation":"Lists all existing evaluation jobs.
" }, "ListFoundationModels":{ "name":"ListFoundationModels", "http":{ "method":"GET", "requestUri":"/foundation-models", "responseCode":200 }, "input":{"shape":"ListFoundationModelsRequest"}, "output":{"shape":"ListFoundationModelsResponse"}, "errors":[ {"shape":"AccessDeniedException"}, {"shape":"ValidationException"}, {"shape":"InternalServerException"}, {"shape":"ThrottlingException"} ], "documentation":"Lists Amazon Bedrock foundation models that you can use. You can filter the results with the request parameters. For more information, see Foundation models in the Amazon Bedrock User Guide.
" }, "ListGuardrails":{ "name":"ListGuardrails", "http":{ "method":"GET", "requestUri":"/guardrails", "responseCode":200 }, "input":{"shape":"ListGuardrailsRequest"}, "output":{"shape":"ListGuardrailsResponse"}, "errors":[ {"shape":"ResourceNotFoundException"}, {"shape":"AccessDeniedException"}, {"shape":"ValidationException"}, {"shape":"InternalServerException"}, {"shape":"ThrottlingException"} ], "documentation":"Lists details about all the guardrails in an account. To list the DRAFT version of all your guardrails, don't specify the guardrailIdentifier field. To list all versions of a guardrail, specify the ARN of the guardrail in the guardrailIdentifier field.
You can set the maximum number of results to return in a response in the maxResults field. If there are more results than the number you set, the response returns a nextToken that you can send in another ListGuardrails request to see the next batch of results.
Returns a list of models you've imported. You can filter the results to return based on one or more criteria. For more information, see Import a customized model in the Amazon Bedrock User Guide.
" }, "ListInferenceProfiles":{ "name":"ListInferenceProfiles", "http":{ "method":"GET", "requestUri":"/inference-profiles", "responseCode":200 }, "input":{"shape":"ListInferenceProfilesRequest"}, "output":{"shape":"ListInferenceProfilesResponse"}, "errors":[ {"shape":"AccessDeniedException"}, {"shape":"ValidationException"}, {"shape":"InternalServerException"}, {"shape":"ThrottlingException"} ], "documentation":"Returns a list of inference profiles that you can use. For more information, see Increase throughput and resilience with cross-region inference in Amazon Bedrock. in the Amazon Bedrock User Guide.
" }, "ListMarketplaceModelEndpoints":{ "name":"ListMarketplaceModelEndpoints", "http":{ "method":"GET", "requestUri":"/marketplace-model/endpoints", "responseCode":200 }, "input":{"shape":"ListMarketplaceModelEndpointsRequest"}, "output":{"shape":"ListMarketplaceModelEndpointsResponse"}, "errors":[ {"shape":"ResourceNotFoundException"}, {"shape":"AccessDeniedException"}, {"shape":"ValidationException"}, {"shape":"InternalServerException"}, {"shape":"ThrottlingException"} ], "documentation":"Lists the endpoints for models from Amazon Bedrock Marketplace in your Amazon Web Services account.
" }, "ListModelCopyJobs":{ "name":"ListModelCopyJobs", "http":{ "method":"GET", "requestUri":"/model-copy-jobs", "responseCode":200 }, "input":{"shape":"ListModelCopyJobsRequest"}, "output":{"shape":"ListModelCopyJobsResponse"}, "errors":[ {"shape":"ResourceNotFoundException"}, {"shape":"AccessDeniedException"}, {"shape":"ValidationException"}, {"shape":"InternalServerException"}, {"shape":"ThrottlingException"} ], "documentation":"Returns a list of model copy jobs that you have submitted. You can filter the jobs to return based on one or more criteria. For more information, see Copy models to be used in other regions in the Amazon Bedrock User Guide.
" }, "ListModelCustomizationJobs":{ "name":"ListModelCustomizationJobs", "http":{ "method":"GET", "requestUri":"/model-customization-jobs", "responseCode":200 }, "input":{"shape":"ListModelCustomizationJobsRequest"}, "output":{"shape":"ListModelCustomizationJobsResponse"}, "errors":[ {"shape":"AccessDeniedException"}, {"shape":"ValidationException"}, {"shape":"InternalServerException"}, {"shape":"ThrottlingException"} ], "documentation":"Returns a list of model customization jobs that you have submitted. You can filter the jobs to return based on one or more criteria.
For more information, see Custom models in the Amazon Bedrock User Guide.
" }, "ListModelImportJobs":{ "name":"ListModelImportJobs", "http":{ "method":"GET", "requestUri":"/model-import-jobs", "responseCode":200 }, "input":{"shape":"ListModelImportJobsRequest"}, "output":{"shape":"ListModelImportJobsResponse"}, "errors":[ {"shape":"AccessDeniedException"}, {"shape":"ValidationException"}, {"shape":"InternalServerException"}, {"shape":"ThrottlingException"} ], "documentation":"Returns a list of import jobs you've submitted. You can filter the results to return based on one or more criteria. For more information, see Import a customized model in the Amazon Bedrock User Guide.
" }, "ListModelInvocationJobs":{ "name":"ListModelInvocationJobs", "http":{ "method":"GET", "requestUri":"/model-invocation-jobs", "responseCode":200 }, "input":{"shape":"ListModelInvocationJobsRequest"}, "output":{"shape":"ListModelInvocationJobsResponse"}, "errors":[ {"shape":"AccessDeniedException"}, {"shape":"ValidationException"}, {"shape":"InternalServerException"}, {"shape":"ThrottlingException"} ], "documentation":"Lists all batch inference jobs in the account. For more information, see View details about a batch inference job.
" }, "ListPromptRouters":{ "name":"ListPromptRouters", "http":{ "method":"GET", "requestUri":"/prompt-routers", "responseCode":200 }, "input":{"shape":"ListPromptRoutersRequest"}, "output":{"shape":"ListPromptRoutersResponse"}, "errors":[ {"shape":"AccessDeniedException"}, {"shape":"ValidationException"}, {"shape":"InternalServerException"}, {"shape":"ThrottlingException"} ], "documentation":"Retrieves a list of prompt routers.
" }, "ListProvisionedModelThroughputs":{ "name":"ListProvisionedModelThroughputs", "http":{ "method":"GET", "requestUri":"/provisioned-model-throughputs", "responseCode":200 }, "input":{"shape":"ListProvisionedModelThroughputsRequest"}, "output":{"shape":"ListProvisionedModelThroughputsResponse"}, "errors":[ {"shape":"AccessDeniedException"}, {"shape":"ValidationException"}, {"shape":"InternalServerException"}, {"shape":"ThrottlingException"} ], "documentation":"Lists the Provisioned Throughputs in the account. For more information, see Provisioned Throughput in the Amazon Bedrock User Guide.
" }, "ListTagsForResource":{ "name":"ListTagsForResource", "http":{ "method":"POST", "requestUri":"/listTagsForResource", "responseCode":200 }, "input":{"shape":"ListTagsForResourceRequest"}, "output":{"shape":"ListTagsForResourceResponse"}, "errors":[ {"shape":"ResourceNotFoundException"}, {"shape":"AccessDeniedException"}, {"shape":"ValidationException"}, {"shape":"InternalServerException"}, {"shape":"ThrottlingException"} ], "documentation":"List the tags associated with the specified resource.
For more information, see Tagging resources in the Amazon Bedrock User Guide.
" }, "PutModelInvocationLoggingConfiguration":{ "name":"PutModelInvocationLoggingConfiguration", "http":{ "method":"PUT", "requestUri":"/logging/modelinvocations", "responseCode":200 }, "input":{"shape":"PutModelInvocationLoggingConfigurationRequest"}, "output":{"shape":"PutModelInvocationLoggingConfigurationResponse"}, "errors":[ {"shape":"AccessDeniedException"}, {"shape":"ValidationException"}, {"shape":"InternalServerException"}, {"shape":"ThrottlingException"} ], "documentation":"Set the configuration values for model invocation logging.
", "idempotent":true }, "RegisterMarketplaceModelEndpoint":{ "name":"RegisterMarketplaceModelEndpoint", "http":{ "method":"POST", "requestUri":"/marketplace-model/endpoints/{endpointIdentifier}/registration", "responseCode":200 }, "input":{"shape":"RegisterMarketplaceModelEndpointRequest"}, "output":{"shape":"RegisterMarketplaceModelEndpointResponse"}, "errors":[ {"shape":"ResourceNotFoundException"}, {"shape":"ServiceUnavailableException"}, {"shape":"AccessDeniedException"}, {"shape":"ValidationException"}, {"shape":"InternalServerException"}, {"shape":"ThrottlingException"} ], "documentation":"Registers an existing Amazon SageMaker endpoint with Amazon Bedrock Marketplace, allowing it to be used with Amazon Bedrock APIs.
" }, "StopEvaluationJob":{ "name":"StopEvaluationJob", "http":{ "method":"POST", "requestUri":"/evaluation-job/{jobIdentifier}/stop", "responseCode":200 }, "input":{"shape":"StopEvaluationJobRequest"}, "output":{"shape":"StopEvaluationJobResponse"}, "errors":[ {"shape":"ResourceNotFoundException"}, {"shape":"AccessDeniedException"}, {"shape":"ValidationException"}, {"shape":"ConflictException"}, {"shape":"InternalServerException"}, {"shape":"ThrottlingException"} ], "documentation":"Stops an evaluation job that is current being created or running.
" }, "StopModelCustomizationJob":{ "name":"StopModelCustomizationJob", "http":{ "method":"POST", "requestUri":"/model-customization-jobs/{jobIdentifier}/stop", "responseCode":200 }, "input":{"shape":"StopModelCustomizationJobRequest"}, "output":{"shape":"StopModelCustomizationJobResponse"}, "errors":[ {"shape":"ResourceNotFoundException"}, {"shape":"AccessDeniedException"}, {"shape":"ValidationException"}, {"shape":"ConflictException"}, {"shape":"InternalServerException"}, {"shape":"ThrottlingException"} ], "documentation":"Stops an active model customization job. For more information, see Custom models in the Amazon Bedrock User Guide.
", "idempotent":true }, "StopModelInvocationJob":{ "name":"StopModelInvocationJob", "http":{ "method":"POST", "requestUri":"/model-invocation-job/{jobIdentifier}/stop", "responseCode":200 }, "input":{"shape":"StopModelInvocationJobRequest"}, "output":{"shape":"StopModelInvocationJobResponse"}, "errors":[ {"shape":"ResourceNotFoundException"}, {"shape":"AccessDeniedException"}, {"shape":"ValidationException"}, {"shape":"ConflictException"}, {"shape":"InternalServerException"}, {"shape":"ThrottlingException"} ], "documentation":"Stops a batch inference job. You're only charged for tokens that were already processed. For more information, see Stop a batch inference job.
" }, "TagResource":{ "name":"TagResource", "http":{ "method":"POST", "requestUri":"/tagResource", "responseCode":200 }, "input":{"shape":"TagResourceRequest"}, "output":{"shape":"TagResourceResponse"}, "errors":[ {"shape":"ResourceNotFoundException"}, {"shape":"AccessDeniedException"}, {"shape":"ValidationException"}, {"shape":"InternalServerException"}, {"shape":"TooManyTagsException"}, {"shape":"ThrottlingException"} ], "documentation":"Associate tags with a resource. For more information, see Tagging resources in the Amazon Bedrock User Guide.
" }, "UntagResource":{ "name":"UntagResource", "http":{ "method":"POST", "requestUri":"/untagResource", "responseCode":200 }, "input":{"shape":"UntagResourceRequest"}, "output":{"shape":"UntagResourceResponse"}, "errors":[ {"shape":"ResourceNotFoundException"}, {"shape":"AccessDeniedException"}, {"shape":"ValidationException"}, {"shape":"InternalServerException"}, {"shape":"ThrottlingException"} ], "documentation":"Remove one or more tags from a resource. For more information, see Tagging resources in the Amazon Bedrock User Guide.
" }, "UpdateGuardrail":{ "name":"UpdateGuardrail", "http":{ "method":"PUT", "requestUri":"/guardrails/{guardrailIdentifier}", "responseCode":202 }, "input":{"shape":"UpdateGuardrailRequest"}, "output":{"shape":"UpdateGuardrailResponse"}, "errors":[ {"shape":"ResourceNotFoundException"}, {"shape":"AccessDeniedException"}, {"shape":"ValidationException"}, {"shape":"ConflictException"}, {"shape":"InternalServerException"}, {"shape":"ServiceQuotaExceededException"}, {"shape":"ThrottlingException"} ], "documentation":"Updates a guardrail with the values you specify.
Specify a name and optional description.
Specify messages for when the guardrail successfully blocks a prompt or a model response in the blockedInputMessaging and blockedOutputsMessaging fields.
Specify topics for the guardrail to deny in the topicPolicyConfig object. Each GuardrailTopicConfig object in the topicsConfig list pertains to one topic.
Give a name and description so that the guardrail can properly identify the topic.
Specify DENY in the type field.
(Optional) Provide up to five prompts that you would categorize as belonging to the topic in the examples list.
Specify filter strengths for the harmful categories defined in Amazon Bedrock in the contentPolicyConfig object. Each GuardrailContentFilterConfig object in the filtersConfig list pertains to a harmful category. For more information, see Content filters. For more information about the fields in a content filter, see GuardrailContentFilterConfig.
Specify the category in the type field.
Specify the strength of the filter for prompts in the inputStrength field and for model responses in the strength field of the GuardrailContentFilterConfig.
(Optional) For security, include the ARN of a KMS key in the kmsKeyId field.
Updates the configuration of an existing endpoint for a model from Amazon Bedrock Marketplace.
" }, "UpdateProvisionedModelThroughput":{ "name":"UpdateProvisionedModelThroughput", "http":{ "method":"PATCH", "requestUri":"/provisioned-model-throughput/{provisionedModelId}", "responseCode":200 }, "input":{"shape":"UpdateProvisionedModelThroughputRequest"}, "output":{"shape":"UpdateProvisionedModelThroughputResponse"}, "errors":[ {"shape":"ResourceNotFoundException"}, {"shape":"AccessDeniedException"}, {"shape":"ValidationException"}, {"shape":"InternalServerException"}, {"shape":"ThrottlingException"} ], "documentation":"Updates the name or associated model for a Provisioned Throughput. For more information, see Provisioned Throughput in the Amazon Bedrock User Guide.
", "idempotent":true } }, "shapes":{ "AcceptEula":{"type":"boolean"}, "AccessDeniedException":{ "type":"structure", "members":{ "message":{"shape":"NonBlankString"} }, "documentation":"The request is denied because of missing access permissions.
", "error":{ "httpStatusCode":403, "senderFault":true }, "exception":true }, "AccountId":{ "type":"string", "pattern":"[0-9]{12}" }, "AdditionalModelRequestFields":{ "type":"map", "key":{"shape":"AdditionalModelRequestFieldsKey"}, "value":{"shape":"AdditionalModelRequestFieldsValue"} }, "AdditionalModelRequestFieldsKey":{ "type":"string", "max":100, "min":1 }, "AdditionalModelRequestFieldsValue":{ "type":"structure", "members":{ }, "document":true }, "ApplicationType":{ "type":"string", "enum":[ "ModelEvaluation", "RagEvaluation" ] }, "Arn":{ "type":"string", "max":2048, "min":0 }, "AutomatedEvaluationConfig":{ "type":"structure", "required":["datasetMetricConfigs"], "members":{ "datasetMetricConfigs":{ "shape":"EvaluationDatasetMetricConfigs", "documentation":"Configuration details of the prompt datasets and metrics you want to use for your evaluation job.
" }, "evaluatorModelConfig":{ "shape":"EvaluatorModelConfig", "documentation":"Contains the evaluator model configuration details. EvaluatorModelConfig is required for evaluation jobs that use a knowledge base or in model evaluation job that use a model as judge. This model computes all evaluation related metrics.
The configuration details of an automated evaluation job. The EvaluationDatasetMetricConfig object is used to specify the prompt datasets, task type, and metric names.
The ARN of the evaluation job being deleted.
" }, "code":{ "shape":"String", "documentation":"A HTTP status code of the evaluation job being deleted.
" }, "message":{ "shape":"String", "documentation":"A status message about the evaluation job deletion.
" } }, "documentation":"A JSON array that provides the status of the evaluation jobs being deleted.
" }, "BatchDeleteEvaluationJobErrors":{ "type":"list", "member":{"shape":"BatchDeleteEvaluationJobError"}, "max":25, "min":0 }, "BatchDeleteEvaluationJobItem":{ "type":"structure", "required":[ "jobIdentifier", "jobStatus" ], "members":{ "jobIdentifier":{ "shape":"EvaluationJobIdentifier", "documentation":"The Amazon Resource Name (ARN) of the evaluation job for deletion.
" }, "jobStatus":{ "shape":"EvaluationJobStatus", "documentation":"The status of the evaluation job for deletion.
" } }, "documentation":"An evaluation job for deletion, and it’s current status.
" }, "BatchDeleteEvaluationJobItems":{ "type":"list", "member":{"shape":"BatchDeleteEvaluationJobItem"} }, "BatchDeleteEvaluationJobRequest":{ "type":"structure", "required":["jobIdentifiers"], "members":{ "jobIdentifiers":{ "shape":"EvaluationJobIdentifiers", "documentation":"A list of one or more evaluation job Amazon Resource Names (ARNs) you want to delete.
" } } }, "BatchDeleteEvaluationJobResponse":{ "type":"structure", "required":[ "errors", "evaluationJobs" ], "members":{ "errors":{ "shape":"BatchDeleteEvaluationJobErrors", "documentation":"A JSON object containing the HTTP status codes and the ARNs of evaluation jobs that failed to be deleted.
" }, "evaluationJobs":{ "shape":"BatchDeleteEvaluationJobItems", "documentation":"The list of evaluation jobs for deletion.
" } } }, "BedrockEvaluatorModel":{ "type":"structure", "required":["modelIdentifier"], "members":{ "modelIdentifier":{ "shape":"EvaluatorModelIdentifier", "documentation":"The Amazon Resource Name (ARN) of the evaluator model used used in knowledge base evaluation job or in model evaluation job that use a model as judge.
" } }, "documentation":"The evaluator model used in knowledge base evaluation job or in model evaluation job that use a model as judge. This model computes all evaluation related metrics.
" }, "BedrockEvaluatorModels":{ "type":"list", "member":{"shape":"BedrockEvaluatorModel"}, "max":1, "min":1 }, "BedrockModelArn":{ "type":"string", "max":2048, "min":1, "pattern":"(arn:aws(-[^:]+)?:bedrock:[a-z0-9-]{1,20}:(([0-9]{12}:custom-model/[a-z0-9-]{1,63}[.]{1}[a-z0-9-]{1,63}/[a-z0-9]{12})|(:foundation-model/[a-z0-9-]{1,63}[.]{1}[a-z0-9-]{1,63}([.:]?[a-z0-9-]{1,63}))))|(arn:aws(|-us-gov|-cn|-iso|-iso-b):bedrock:(|[0-9a-z-]{1,20}):(|[0-9]{12}):inference-profile/[a-zA-Z0-9-:.]+)|([a-z0-9-]{1,63}[.]{1}[a-z0-9-]{1,63}([.:]?[a-z0-9-]{1,63}))|(([0-9a-zA-Z][_-]?)+)" }, "BedrockModelId":{ "type":"string", "max":140, "min":0, "pattern":"[a-z0-9-]{1,63}[.]{1}[a-z0-9-]{1,63}([a-z0-9-]{1,63}[.]){0,2}[a-z0-9-]{1,63}([:][a-z0-9-]{1,63}){0,2}(/[a-z0-9]{12}|)" }, "Boolean":{ "type":"boolean", "box":true }, "BrandedName":{ "type":"string", "max":20, "min":1, "pattern":".*" }, "BucketName":{ "type":"string", "max":63, "min":3 }, "ByteContentBlob":{ "type":"blob", "max":10485760, "min":1, "sensitive":true }, "ByteContentDoc":{ "type":"structure", "required":[ "identifier", "contentType", "data" ], "members":{ "identifier":{ "shape":"Identifier", "documentation":"The file name of the document contained in the wrapper object.
" }, "contentType":{ "shape":"ContentType", "documentation":"The MIME type of the document contained in the wrapper object.
" }, "data":{ "shape":"ByteContentBlob", "documentation":"The byte value of the file to upload, encoded as a Base-64 string.
" } }, "documentation":"Contains the document contained in the wrapper object, along with its attributes/fields.
" }, "CloudWatchConfig":{ "type":"structure", "required":[ "logGroupName", "roleArn" ], "members":{ "logGroupName":{ "shape":"LogGroupName", "documentation":"The log group name.
" }, "roleArn":{ "shape":"RoleArn", "documentation":"The role Amazon Resource Name (ARN).
" }, "largeDataDeliveryS3Config":{ "shape":"S3Config", "documentation":"S3 configuration for delivering a large amount of data.
" } }, "documentation":"CloudWatch logging configuration.
" }, "CommitmentDuration":{ "type":"string", "enum":[ "OneMonth", "SixMonths" ] }, "ConflictException":{ "type":"structure", "members":{ "message":{"shape":"NonBlankString"} }, "documentation":"Error occurred because of a conflict while performing an operation.
", "error":{ "httpStatusCode":400, "senderFault":true }, "exception":true }, "ContentType":{ "type":"string", "pattern":".*[a-z]{1,20}/.{1,20}.*" }, "CreateEvaluationJobRequest":{ "type":"structure", "required":[ "jobName", "roleArn", "evaluationConfig", "inferenceConfig", "outputDataConfig" ], "members":{ "jobName":{ "shape":"EvaluationJobName", "documentation":"A name for the evaluation job. Names must unique with your Amazon Web Services account, and your account's Amazon Web Services region.
" }, "jobDescription":{ "shape":"EvaluationJobDescription", "documentation":"A description of the evaluation job.
" }, "clientRequestToken":{ "shape":"IdempotencyToken", "documentation":"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.
", "idempotencyToken":true }, "roleArn":{ "shape":"RoleArn", "documentation":"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.
" }, "customerEncryptionKeyId":{ "shape":"KmsKeyId", "documentation":"Specify your customer managed encryption key Amazon Resource Name (ARN) that will be used to encrypt your evaluation job.
" }, "jobTags":{ "shape":"TagList", "documentation":"Tags to attach to the model evaluation job.
" }, "applicationType":{ "shape":"ApplicationType", "documentation":"Specifies whether the evaluation job is for evaluating a model or evaluating a knowledge base (retrieval and response generation).
" }, "evaluationConfig":{ "shape":"EvaluationConfig", "documentation":"Contains the configuration details of either an automated or human-based evaluation job.
" }, "inferenceConfig":{ "shape":"EvaluationInferenceConfig", "documentation":"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.
" }, "outputDataConfig":{ "shape":"EvaluationOutputDataConfig", "documentation":"Contains the configuration details of the Amazon S3 bucket for storing the results of the evaluation job.
" } } }, "CreateEvaluationJobResponse":{ "type":"structure", "required":["jobArn"], "members":{ "jobArn":{ "shape":"EvaluationJobArn", "documentation":"The Amazon Resource Name (ARN) of the evaluation job.
" } } }, "CreateGuardrailRequest":{ "type":"structure", "required":[ "name", "blockedInputMessaging", "blockedOutputsMessaging" ], "members":{ "name":{ "shape":"GuardrailName", "documentation":"The name to give the guardrail.
" }, "description":{ "shape":"GuardrailDescription", "documentation":"A description of the guardrail.
" }, "topicPolicyConfig":{ "shape":"GuardrailTopicPolicyConfig", "documentation":"The topic policies to configure for the guardrail.
" }, "contentPolicyConfig":{ "shape":"GuardrailContentPolicyConfig", "documentation":"The content filter policies to configure for the guardrail.
" }, "wordPolicyConfig":{ "shape":"GuardrailWordPolicyConfig", "documentation":"The word policy you configure for the guardrail.
" }, "sensitiveInformationPolicyConfig":{ "shape":"GuardrailSensitiveInformationPolicyConfig", "documentation":"The sensitive information policy to configure for the guardrail.
" }, "contextualGroundingPolicyConfig":{ "shape":"GuardrailContextualGroundingPolicyConfig", "documentation":"The contextual grounding policy configuration used to create a guardrail.
" }, "blockedInputMessaging":{ "shape":"GuardrailBlockedMessaging", "documentation":"The message to return when the guardrail blocks a prompt.
" }, "blockedOutputsMessaging":{ "shape":"GuardrailBlockedMessaging", "documentation":"The message to return when the guardrail blocks a model response.
" }, "kmsKeyId":{ "shape":"KmsKeyId", "documentation":"The ARN of the KMS key that you use to encrypt the guardrail.
" }, "tags":{ "shape":"TagList", "documentation":"The tags that you want to attach to the guardrail.
" }, "clientRequestToken":{ "shape":"IdempotencyToken", "documentation":"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.
", "idempotencyToken":true } } }, "CreateGuardrailResponse":{ "type":"structure", "required":[ "guardrailId", "guardrailArn", "version", "createdAt" ], "members":{ "guardrailId":{ "shape":"GuardrailId", "documentation":"The unique identifier of the guardrail that was created.
" }, "guardrailArn":{ "shape":"GuardrailArn", "documentation":"The ARN of the guardrail.
" }, "version":{ "shape":"GuardrailDraftVersion", "documentation":"The version of the guardrail that was created. This value will always be DRAFT.
The time at which the guardrail was created.
" } } }, "CreateGuardrailVersionRequest":{ "type":"structure", "required":["guardrailIdentifier"], "members":{ "guardrailIdentifier":{ "shape":"GuardrailIdentifier", "documentation":"The unique identifier of the guardrail. This can be an ID or the ARN.
", "location":"uri", "locationName":"guardrailIdentifier" }, "description":{ "shape":"GuardrailDescription", "documentation":"A description of the guardrail version.
" }, "clientRequestToken":{ "shape":"IdempotencyToken", "documentation":"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.
", "idempotencyToken":true } } }, "CreateGuardrailVersionResponse":{ "type":"structure", "required":[ "guardrailId", "version" ], "members":{ "guardrailId":{ "shape":"GuardrailId", "documentation":"The unique identifier of the guardrail.
" }, "version":{ "shape":"GuardrailNumericalVersion", "documentation":"The number of the version of the guardrail.
" } } }, "CreateInferenceProfileRequest":{ "type":"structure", "required":[ "inferenceProfileName", "modelSource" ], "members":{ "inferenceProfileName":{ "shape":"InferenceProfileName", "documentation":"A name for the inference profile.
" }, "description":{ "shape":"InferenceProfileDescription", "documentation":"A description for the inference profile.
" }, "clientRequestToken":{ "shape":"IdempotencyToken", "documentation":"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.
", "idempotencyToken":true }, "modelSource":{ "shape":"InferenceProfileModelSource", "documentation":"The foundation model or system-defined inference profile that the inference profile will track metrics and costs for.
" }, "tags":{ "shape":"TagList", "documentation":"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.
" } } }, "CreateInferenceProfileResponse":{ "type":"structure", "required":["inferenceProfileArn"], "members":{ "inferenceProfileArn":{ "shape":"InferenceProfileArn", "documentation":"The ARN of the inference profile that you created.
" }, "status":{ "shape":"InferenceProfileStatus", "documentation":"The status of the inference profile. ACTIVE means that the inference profile is ready to be used.
The ARN of the model from Amazon Bedrock Marketplace that you want to deploy to the endpoint.
" }, "endpointConfig":{ "shape":"EndpointConfig", "documentation":"The configuration for the endpoint, including the number and type of instances to use.
" }, "acceptEula":{ "shape":"AcceptEula", "documentation":"Indicates whether you accept the end-user license agreement (EULA) for the model. Set to true to accept the EULA.
The name of the endpoint. This name must be unique within your Amazon Web Services account and region.
" }, "clientRequestToken":{ "shape":"IdempotencyToken", "documentation":"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.
", "idempotencyToken":true }, "tags":{ "shape":"TagList", "documentation":"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.
" } } }, "CreateMarketplaceModelEndpointResponse":{ "type":"structure", "required":["marketplaceModelEndpoint"], "members":{ "marketplaceModelEndpoint":{ "shape":"MarketplaceModelEndpoint", "documentation":"Details about the created endpoint.
" } } }, "CreateModelCopyJobRequest":{ "type":"structure", "required":[ "sourceModelArn", "targetModelName" ], "members":{ "sourceModelArn":{ "shape":"ModelArn", "documentation":"The Amazon Resource Name (ARN) of the model to be copied.
" }, "targetModelName":{ "shape":"CustomModelName", "documentation":"A name for the copied model.
" }, "modelKmsKeyId":{ "shape":"KmsKeyId", "documentation":"The ARN of the KMS key that you use to encrypt the model copy.
" }, "targetModelTags":{ "shape":"TagList", "documentation":"Tags to associate with the target model. For more information, see Tag resources in the Amazon Bedrock User Guide.
" }, "clientRequestToken":{ "shape":"IdempotencyToken", "documentation":"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.
", "idempotencyToken":true } } }, "CreateModelCopyJobResponse":{ "type":"structure", "required":["jobArn"], "members":{ "jobArn":{ "shape":"ModelCopyJobArn", "documentation":"The Amazon Resource Name (ARN) of the model copy job.
" } } }, "CreateModelCustomizationJobRequest":{ "type":"structure", "required":[ "jobName", "customModelName", "roleArn", "baseModelIdentifier", "trainingDataConfig", "outputDataConfig" ], "members":{ "jobName":{ "shape":"JobName", "documentation":"A name for the fine-tuning job.
" }, "customModelName":{ "shape":"CustomModelName", "documentation":"A name for the resulting custom model.
" }, "roleArn":{ "shape":"RoleArn", "documentation":"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.
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.
", "idempotencyToken":true }, "baseModelIdentifier":{ "shape":"BaseModelIdentifier", "documentation":"Name of the base model.
" }, "customizationType":{ "shape":"CustomizationType", "documentation":"The customization type.
" }, "customModelKmsKeyId":{ "shape":"KmsKeyId", "documentation":"The custom model is encrypted at rest using this key.
" }, "jobTags":{ "shape":"TagList", "documentation":"Tags to attach to the job.
" }, "customModelTags":{ "shape":"TagList", "documentation":"Tags to attach to the resulting custom model.
" }, "trainingDataConfig":{ "shape":"TrainingDataConfig", "documentation":"Information about the training dataset.
" }, "validationDataConfig":{ "shape":"ValidationDataConfig", "documentation":"Information about the validation dataset.
" }, "outputDataConfig":{ "shape":"OutputDataConfig", "documentation":"S3 location for the output data.
" }, "hyperParameters":{ "shape":"ModelCustomizationHyperParameters", "documentation":"Parameters related to tuning the model. For details on the format for different models, see Custom model hyperparameters.
" }, "vpcConfig":{ "shape":"VpcConfig", "documentation":"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.
" }, "customizationConfig":{ "shape":"CustomizationConfig", "documentation":"The customization configuration for the model customization job.
" } } }, "CreateModelCustomizationJobResponse":{ "type":"structure", "required":["jobArn"], "members":{ "jobArn":{ "shape":"ModelCustomizationJobArn", "documentation":"Amazon Resource Name (ARN) of the fine tuning job
" } } }, "CreateModelImportJobRequest":{ "type":"structure", "required":[ "jobName", "importedModelName", "roleArn", "modelDataSource" ], "members":{ "jobName":{ "shape":"JobName", "documentation":"The name of the import job.
" }, "importedModelName":{ "shape":"ImportedModelName", "documentation":"The name of the imported model.
" }, "roleArn":{ "shape":"RoleArn", "documentation":"The Amazon Resource Name (ARN) of the model import job.
" }, "modelDataSource":{ "shape":"ModelDataSource", "documentation":"The data source for the imported model.
" }, "jobTags":{ "shape":"TagList", "documentation":"Tags to attach to this import job.
" }, "importedModelTags":{ "shape":"TagList", "documentation":"Tags to attach to the imported model.
" }, "clientRequestToken":{ "shape":"IdempotencyToken", "documentation":"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.
" }, "vpcConfig":{ "shape":"VpcConfig", "documentation":"VPC configuration parameters for the private Virtual Private Cloud (VPC) that contains the resources you are using for the import job.
" }, "importedModelKmsKeyId":{ "shape":"KmsKeyId", "documentation":"The imported model is encrypted at rest using this key.
" } } }, "CreateModelImportJobResponse":{ "type":"structure", "required":["jobArn"], "members":{ "jobArn":{ "shape":"ModelImportJobArn", "documentation":"The Amazon Resource Name (ARN) of the model import job.
" } } }, "CreateModelInvocationJobRequest":{ "type":"structure", "required":[ "jobName", "roleArn", "modelId", "inputDataConfig", "outputDataConfig" ], "members":{ "jobName":{ "shape":"ModelInvocationJobName", "documentation":"A name to give the batch inference job.
" }, "roleArn":{ "shape":"RoleArn", "documentation":"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.
" }, "clientRequestToken":{ "shape":"ModelInvocationIdempotencyToken", "documentation":"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.
", "idempotencyToken":true }, "modelId":{ "shape":"ModelId", "documentation":"The unique identifier of the foundation model to use for the batch inference job.
" }, "inputDataConfig":{ "shape":"ModelInvocationJobInputDataConfig", "documentation":"Details about the location of the input to the batch inference job.
" }, "outputDataConfig":{ "shape":"ModelInvocationJobOutputDataConfig", "documentation":"Details about the location of the output of the batch inference job.
" }, "vpcConfig":{ "shape":"VpcConfig", "documentation":"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.
" }, "timeoutDurationInHours":{ "shape":"ModelInvocationJobTimeoutDurationInHours", "documentation":"The number of hours after which to force the batch inference job to time out.
" }, "tags":{ "shape":"TagList", "documentation":"Any tags to associate with the batch inference job. For more information, see Tagging Amazon Bedrock resources.
" } } }, "CreateModelInvocationJobResponse":{ "type":"structure", "required":["jobArn"], "members":{ "jobArn":{ "shape":"ModelInvocationJobArn", "documentation":"The Amazon Resource Name (ARN) of the batch inference job.
" } } }, "CreatePromptRouterRequest":{ "type":"structure", "required":[ "promptRouterName", "models", "routingCriteria", "fallbackModel" ], "members":{ "clientRequestToken":{ "shape":"IdempotencyToken", "documentation":"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.
", "idempotencyToken":true }, "promptRouterName":{ "shape":"PromptRouterName", "documentation":"The name of the prompt router. The name must be unique within your Amazon Web Services account in the current region.
" }, "models":{ "shape":"PromptRouterTargetModels", "documentation":"A list of foundation models that the prompt router can route requests to. At least one model must be specified.
" }, "description":{ "shape":"PromptRouterDescription", "documentation":"An optional description of the prompt router to help identify its purpose.
" }, "routingCriteria":{ "shape":"RoutingCriteria", "documentation":"The criteria, which is the response quality difference, used to determine how incoming requests are routed to different models.
" }, "fallbackModel":{ "shape":"PromptRouterTargetModel", "documentation":"The default model to use when the routing criteria is not met.
" }, "tags":{ "shape":"TagList", "documentation":"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.
" } } }, "CreatePromptRouterResponse":{ "type":"structure", "members":{ "promptRouterArn":{ "shape":"PromptRouterArn", "documentation":"The Amazon Resource Name (ARN) that uniquely identifies the prompt router.
" } } }, "CreateProvisionedModelThroughputRequest":{ "type":"structure", "required":[ "modelUnits", "provisionedModelName", "modelId" ], "members":{ "clientRequestToken":{ "shape":"IdempotencyToken", "documentation":"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.
", "idempotencyToken":true }, "modelUnits":{ "shape":"PositiveInteger", "documentation":"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.
" }, "provisionedModelName":{ "shape":"ProvisionedModelName", "documentation":"The name for this Provisioned Throughput.
" }, "modelId":{ "shape":"ModelIdentifier", "documentation":"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.
" }, "commitmentDuration":{ "shape":"CommitmentDuration", "documentation":"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":{ "shape":"TagList", "documentation":"Tags to associate with this Provisioned Throughput.
" } } }, "CreateProvisionedModelThroughputResponse":{ "type":"structure", "required":["provisionedModelArn"], "members":{ "provisionedModelArn":{ "shape":"ProvisionedModelArn", "documentation":"The Amazon Resource Name (ARN) for this Provisioned Throughput.
" } } }, "CustomModelArn":{ "type":"string", "max":1011, "min":20, "pattern":"arn:aws(-[^:]+)?:bedrock:[a-z0-9-]{1,20}:[0-9]{12}:custom-model/[a-z0-9-]{1,63}[.]{1}[a-z0-9-]{1,63}([a-z0-9-]{1,63}[.]){0,2}[a-z0-9-]{1,63}([:][a-z0-9-]{1,63}){0,2}/[a-z0-9]{12}" }, "CustomModelName":{ "type":"string", "max":63, "min":1, "pattern":"([0-9a-zA-Z][_-]?){1,63}" }, "CustomModelSummary":{ "type":"structure", "required":[ "modelArn", "modelName", "creationTime", "baseModelArn", "baseModelName" ], "members":{ "modelArn":{ "shape":"CustomModelArn", "documentation":"The Amazon Resource Name (ARN) of the custom model.
" }, "modelName":{ "shape":"CustomModelName", "documentation":"The name of the custom model.
" }, "creationTime":{ "shape":"Timestamp", "documentation":"Creation time of the model.
" }, "baseModelArn":{ "shape":"ModelArn", "documentation":"The base model Amazon Resource Name (ARN).
" }, "baseModelName":{ "shape":"ModelName", "documentation":"The base model name.
" }, "customizationType":{ "shape":"CustomizationType", "documentation":"Specifies whether to carry out continued pre-training of a model or whether to fine-tune it. For more information, see Custom models.
" }, "ownerAccountId":{ "shape":"AccountId", "documentation":"The unique identifier of the account that owns the model.
" } }, "documentation":"Summary information for a custom model.
" }, "CustomModelSummaryList":{ "type":"list", "member":{"shape":"CustomModelSummary"} }, "CustomizationConfig":{ "type":"structure", "members":{ "distillationConfig":{ "shape":"DistillationConfig", "documentation":"The distillation configuration for the custom model.
" } }, "documentation":"A model customization configuration
", "union":true }, "CustomizationType":{ "type":"string", "enum":[ "FINE_TUNING", "CONTINUED_PRE_TRAINING", "DISTILLATION" ] }, "DeleteCustomModelRequest":{ "type":"structure", "required":["modelIdentifier"], "members":{ "modelIdentifier":{ "shape":"ModelIdentifier", "documentation":"Name of the model to delete.
", "location":"uri", "locationName":"modelIdentifier" } } }, "DeleteCustomModelResponse":{ "type":"structure", "members":{ } }, "DeleteGuardrailRequest":{ "type":"structure", "required":["guardrailIdentifier"], "members":{ "guardrailIdentifier":{ "shape":"GuardrailIdentifier", "documentation":"The unique identifier of the guardrail. This can be an ID or the ARN.
", "location":"uri", "locationName":"guardrailIdentifier" }, "guardrailVersion":{ "shape":"GuardrailNumericalVersion", "documentation":"The version of the guardrail.
", "location":"querystring", "locationName":"guardrailVersion" } } }, "DeleteGuardrailResponse":{ "type":"structure", "members":{ } }, "DeleteImportedModelRequest":{ "type":"structure", "required":["modelIdentifier"], "members":{ "modelIdentifier":{ "shape":"ImportedModelIdentifier", "documentation":"Name of the imported model to delete.
", "location":"uri", "locationName":"modelIdentifier" } } }, "DeleteImportedModelResponse":{ "type":"structure", "members":{ } }, "DeleteInferenceProfileRequest":{ "type":"structure", "required":["inferenceProfileIdentifier"], "members":{ "inferenceProfileIdentifier":{ "shape":"InferenceProfileIdentifier", "documentation":"The Amazon Resource Name (ARN) or ID of the application inference profile to delete.
", "location":"uri", "locationName":"inferenceProfileIdentifier" } } }, "DeleteInferenceProfileResponse":{ "type":"structure", "members":{ } }, "DeleteMarketplaceModelEndpointRequest":{ "type":"structure", "required":["endpointArn"], "members":{ "endpointArn":{ "shape":"Arn", "documentation":"The Amazon Resource Name (ARN) of the endpoint you want to delete.
", "location":"uri", "locationName":"endpointArn" } } }, "DeleteMarketplaceModelEndpointResponse":{ "type":"structure", "members":{ } }, "DeleteModelInvocationLoggingConfigurationRequest":{ "type":"structure", "members":{ } }, "DeleteModelInvocationLoggingConfigurationResponse":{ "type":"structure", "members":{ } }, "DeletePromptRouterRequest":{ "type":"structure", "required":["promptRouterArn"], "members":{ "promptRouterArn":{ "shape":"PromptRouterArn", "documentation":"The Amazon Resource Name (ARN) of the prompt router to delete.
", "location":"uri", "locationName":"promptRouterArn" } } }, "DeletePromptRouterResponse":{ "type":"structure", "members":{ } }, "DeleteProvisionedModelThroughputRequest":{ "type":"structure", "required":["provisionedModelId"], "members":{ "provisionedModelId":{ "shape":"ProvisionedModelId", "documentation":"The Amazon Resource Name (ARN) or name of the Provisioned Throughput.
", "location":"uri", "locationName":"provisionedModelId" } } }, "DeleteProvisionedModelThroughputResponse":{ "type":"structure", "members":{ } }, "DeregisterMarketplaceModelEndpointRequest":{ "type":"structure", "required":["endpointArn"], "members":{ "endpointArn":{ "shape":"Arn", "documentation":"The Amazon Resource Name (ARN) of the endpoint you want to deregister.
", "location":"uri", "locationName":"endpointArn" } } }, "DeregisterMarketplaceModelEndpointResponse":{ "type":"structure", "members":{ } }, "DistillationConfig":{ "type":"structure", "required":["teacherModelConfig"], "members":{ "teacherModelConfig":{ "shape":"TeacherModelConfig", "documentation":"The teacher model configuration.
" } }, "documentation":"Settings for distilling a foundation model into a smaller and more efficient model.
" }, "EndpointConfig":{ "type":"structure", "members":{ "sageMaker":{ "shape":"SageMakerEndpoint", "documentation":"The configuration specific to Amazon SageMaker for the endpoint.
" } }, "documentation":"Specifies the configuration for the endpoint.
", "union":true }, "EndpointName":{ "type":"string", "max":30, "min":1 }, "ErrorMessage":{ "type":"string", "max":2048, "min":0 }, "ErrorMessages":{ "type":"list", "member":{"shape":"ErrorMessage"}, "max":20, "min":0 }, "EvaluationBedrockModel":{ "type":"structure", "required":["modelIdentifier"], "members":{ "modelIdentifier":{ "shape":"EvaluationModelIdentifier", "documentation":"The ARN of the Amazon Bedrock model or inference profile specified.
" }, "inferenceParams":{ "shape":"EvaluationModelInferenceParams", "documentation":"Each Amazon Bedrock support different inference parameters that change how the model behaves during inference.
" }, "performanceConfig":{ "shape":"PerformanceConfiguration", "documentation":"Specifies performance settings for the model or inference profile.
" } }, "documentation":"Contains the ARN of the Amazon Bedrock model or inference profile specified in your evaluation job. Each Amazon Bedrock model supports different inferenceParams. To learn more about supported inference parameters for Amazon Bedrock models, see Inference parameters for foundation models.
The inferenceParams are specified using JSON. To successfully insert JSON as string make sure that all quotations are properly escaped. For example, \"temperature\":\"0.25\" key value pair would need to be formatted as \\\"temperature\\\":\\\"0.25\\\" to successfully accepted in the request.
Contains the configuration details of an automated evaluation job that computes metrics.
" }, "human":{ "shape":"HumanEvaluationConfig", "documentation":"Contains the configuration details of an evaluation job that uses human workers.
" } }, "documentation":"The configuration details of either an automated or human-based evaluation job.
", "union":true }, "EvaluationDataset":{ "type":"structure", "required":["name"], "members":{ "name":{ "shape":"EvaluationDatasetName", "documentation":"Used to specify supported built-in prompt datasets. Valid values are Builtin.Bold, Builtin.BoolQ, Builtin.NaturalQuestions, Builtin.Gigaword, Builtin.RealToxicityPrompts, Builtin.TriviaQA, Builtin.T-Rex, Builtin.WomensEcommerceClothingReviews and Builtin.Wikitext2.
For custom prompt datasets, you must specify the location in Amazon S3 where the prompt dataset is saved.
" } }, "documentation":"Used to specify the name of a built-in prompt dataset and optionally, the Amazon S3 bucket where a custom prompt dataset is saved.
" }, "EvaluationDatasetLocation":{ "type":"structure", "members":{ "s3Uri":{ "shape":"S3Uri", "documentation":"The S3 URI of the S3 bucket specified in the job.
" } }, "documentation":"The location in Amazon S3 where your prompt dataset is stored.
", "union":true }, "EvaluationDatasetMetricConfig":{ "type":"structure", "required":[ "taskType", "dataset", "metricNames" ], "members":{ "taskType":{ "shape":"EvaluationTaskType", "documentation":"The the type of task you want to evaluate for your evaluation job. This applies only to model evaluation jobs and is ignored for knowledge base evaluation jobs.
" }, "dataset":{ "shape":"EvaluationDataset", "documentation":"Specifies the prompt dataset.
" }, "metricNames":{ "shape":"EvaluationMetricNames", "documentation":"The names of the metrics you want to use for your evaluation job.
For knowledge base evaluation jobs that evaluate retrieval only, valid values are \"Builtin.ContextRelevance\", \"Builtin.ContextConverage\".
For knowledge base evaluation jobs that evaluate retrieval with response generation, valid values are \"Builtin.Correctness\", \"Builtin.Completeness\", \"Builtin.Helpfulness\", \"Builtin.LogicalCoherence\", \"Builtin.Faithfulness\", \"Builtin.Harmfulness\", \"Builtin.Stereotyping\", \"Builtin.Refusal\".
For automated model evaluation jobs, valid values are \"Builtin.Accuracy\", \"Builtin.Robustness\", and \"Builtin.Toxicity\". In model evaluation jobs that use a LLM as judge you can specify \"Builtin.Correctness\", \"Builtin.Completeness\", \"Builtin.Faithfulness\", \"Builtin.Helpfulness\", \"Builtin.Coherence\", \"Builtin.Relevance\", \"Builtin.FollowingInstructions\", \"Builtin.ProfessionalStyleAndTone\", You can also specify the following responsible AI related metrics only for model evaluation job that use a LLM as judge \"Builtin.Harmfulness\", \"Builtin.Stereotyping\", and \"Builtin.Refusal\".
For human-based model evaluation jobs, the list of strings must match the name parameter specified in HumanEvaluationCustomMetric.
Defines the prompt datasets, built-in metric names and custom metric names, and the task type.
" }, "EvaluationDatasetMetricConfigs":{ "type":"list", "member":{"shape":"EvaluationDatasetMetricConfig"}, "max":5, "min":1 }, "EvaluationDatasetName":{ "type":"string", "max":63, "min":1, "pattern":"[0-9a-zA-Z-_.]+", "sensitive":true }, "EvaluationInferenceConfig":{ "type":"structure", "members":{ "models":{ "shape":"EvaluationModelConfigs", "documentation":"Specifies the inference models.
" }, "ragConfigs":{ "shape":"RagConfigs", "documentation":"Contains the configuration details of the inference for a knowledge base evaluation job, including either the retrieval only configuration or the retrieval with response generation configuration.
" } }, "documentation":"The configuration details of the inference model for an evaluation job.
For automated model evaluation jobs, only a single model is supported.
For human-based model evaluation jobs, your annotator can compare the responses for up to two different models.
", "union":true }, "EvaluationJobArn":{ "type":"string", "max":1011, "min":0, "pattern":"arn:aws(-[^:]+)?:bedrock:[a-z0-9-]{1,20}:[0-9]{12}:evaluation-job/[a-z0-9]{12}" }, "EvaluationJobDescription":{ "type":"string", "max":200, "min":1, "pattern":".+", "sensitive":true }, "EvaluationJobIdentifier":{ "type":"string", "max":1011, "min":0, "pattern":"(arn:aws(-[^:]+)?:bedrock:[a-z0-9-]{1,20}:[0-9]{12}:evaluation-job/[a-z0-9]{12})", "sensitive":true }, "EvaluationJobIdentifiers":{ "type":"list", "member":{"shape":"EvaluationJobIdentifier"}, "max":25, "min":1 }, "EvaluationJobName":{ "type":"string", "max":63, "min":1, "pattern":"[a-z0-9](-*[a-z0-9]){0,62}" }, "EvaluationJobStatus":{ "type":"string", "enum":[ "InProgress", "Completed", "Failed", "Stopping", "Stopped", "Deleting" ] }, "EvaluationJobType":{ "type":"string", "enum":[ "Human", "Automated" ] }, "EvaluationMetricDescription":{ "type":"string", "max":63, "min":1, "pattern":".+", "sensitive":true }, "EvaluationMetricName":{ "type":"string", "max":63, "min":1, "pattern":"[0-9a-zA-Z-_.]+", "sensitive":true }, "EvaluationMetricNames":{ "type":"list", "member":{"shape":"EvaluationMetricName"}, "max":15, "min":1 }, "EvaluationModelConfig":{ "type":"structure", "members":{ "bedrockModel":{ "shape":"EvaluationBedrockModel", "documentation":"Defines the Amazon Bedrock model or inference profile and inference parameters you want used.
" } }, "documentation":"Defines the models used in the model evaluation job.
", "union":true }, "EvaluationModelConfigs":{ "type":"list", "member":{"shape":"EvaluationModelConfig"}, "max":2, "min":1 }, "EvaluationModelIdentifier":{ "type":"string", "max":2048, "min":1, "pattern":"(arn:aws(-[^:]+)?:bedrock:[a-z0-9-]{1,20}:((:foundation-model/[a-z0-9-]{1,63}[.]{1}[a-z0-9-]{1,63}([.:]?[a-z0-9-]{1,63}))|([0-9]{12}:provisioned-model/[a-z0-9]{12})|([0-9]{12}:imported-model/[a-z0-9]{12})|([0-9]{12}:application-inference-profile/[a-z0-9]{12})|([0-9]{12}:inference-profile/(([a-z-]{2,8}.)[a-z0-9-]{1,63}[.]{1}[a-z0-9-]{1,63}([.:]?[a-z0-9-]{1,63})))|([0-9]{12}:default-prompt-router/[a-zA-Z0-9-:.]+)))|(([a-z]{2}[.]{1})([a-z0-9-]{1,63}[.]{1}[a-z0-9-]{1,63}([.:]?[a-z0-9-]{1,63})))|([a-z0-9-]{1,63}[.]{1}[a-z0-9-]{1,63}([.:]?[a-z0-9-]{1,63}))|arn:aws(-[^:]+)?:sagemaker:[a-z0-9-]{1,20}:[0-9]{12}:endpoint/[a-z0-9-]{1,63}" }, "EvaluationModelIdentifiers":{ "type":"list", "member":{"shape":"EvaluationModelIdentifier"}, "max":2, "min":0 }, "EvaluationModelInferenceParams":{ "type":"string", "max":1023, "min":1, "sensitive":true }, "EvaluationOutputDataConfig":{ "type":"structure", "required":["s3Uri"], "members":{ "s3Uri":{ "shape":"S3Uri", "documentation":"The Amazon S3 URI where the results of the evaluation job are saved.
" } }, "documentation":"The Amazon S3 location where the results of your evaluation job are saved.
" }, "EvaluationRatingMethod":{ "type":"string", "max":100, "min":1, "pattern":"[0-9a-zA-Z-_]+" }, "EvaluationSummaries":{ "type":"list", "member":{"shape":"EvaluationSummary"}, "max":5, "min":1 }, "EvaluationSummary":{ "type":"structure", "required":[ "jobArn", "jobName", "status", "creationTime", "jobType", "evaluationTaskTypes" ], "members":{ "jobArn":{ "shape":"EvaluationJobArn", "documentation":"The Amazon Resource Name (ARN) of the evaluation job.
" }, "jobName":{ "shape":"EvaluationJobName", "documentation":"The name for the evaluation job.
" }, "status":{ "shape":"EvaluationJobStatus", "documentation":"The current status of the evaluation job.
" }, "creationTime":{ "shape":"Timestamp", "documentation":"The time the evaluation job was created.
" }, "jobType":{ "shape":"EvaluationJobType", "documentation":"Specifies whether the evaluation job is automated or human-based.
" }, "evaluationTaskTypes":{ "shape":"EvaluationTaskTypes", "documentation":"The type of task for model evaluation.
" }, "modelIdentifiers":{ "shape":"EvaluationModelIdentifiers", "documentation":"The Amazon Resource Names (ARNs) of the model(s) used for the evaluation job.
" }, "ragIdentifiers":{ "shape":"RAGIdentifiers", "documentation":"The Amazon Resource Names (ARNs) of the knowledge base resources used for a knowledge base evaluation job.
" }, "evaluatorModelIdentifiers":{ "shape":"EvaluatorModelIdentifiers", "documentation":"The Amazon Resource Names (ARNs) of the models used to compute the metrics for a knowledge base evaluation job.
" }, "applicationType":{ "shape":"ApplicationType", "documentation":"Specifies whether the evaluation job is for evaluating a model or evaluating a knowledge base (retrieval and response generation).
" } }, "documentation":"Summary information of an evaluation job.
" }, "EvaluationTaskType":{ "type":"string", "enum":[ "Summarization", "Classification", "QuestionAndAnswer", "Generation", "Custom" ], "max":63, "min":1, "pattern":"[A-Za-z0-9]+" }, "EvaluationTaskTypes":{ "type":"list", "member":{"shape":"EvaluationTaskType"}, "max":5, "min":1 }, "EvaluatorModelConfig":{ "type":"structure", "members":{ "bedrockEvaluatorModels":{ "shape":"BedrockEvaluatorModels", "documentation":"The evaluator model used in knowledge base evaluation job or in model evaluation job that use a model as judge. This model computes all evaluation related metrics.
" } }, "documentation":"Specifies the model configuration for the evaluator model. EvaluatorModelConfig is required for evaluation jobs that use a knowledge base or in model evaluation job that use a model as judge. This model computes all evaluation related metrics.
The source type of the external source wrapper object.
" }, "s3Location":{ "shape":"S3ObjectDoc", "documentation":"The S3 location of the external source wrapper object.
" }, "byteContent":{ "shape":"ByteContentDoc", "documentation":"The identifier, content type, and data of the external source wrapper object.
" } }, "documentation":"The unique external source of the content contained in the wrapper object.
" }, "ExternalSourceType":{ "type":"string", "enum":[ "S3", "BYTE_CONTENT" ] }, "ExternalSources":{ "type":"list", "member":{"shape":"ExternalSource"}, "max":1, "min":1 }, "ExternalSourcesGenerationConfiguration":{ "type":"structure", "members":{ "promptTemplate":{ "shape":"PromptTemplate", "documentation":"Contains the template for the prompt for the external source wrapper object.
" }, "guardrailConfiguration":{ "shape":"GuardrailConfiguration", "documentation":"Configuration details for the guardrail.
" }, "kbInferenceConfig":{ "shape":"KbInferenceConfig", "documentation":"Configuration details for inference when using RetrieveAndGenerate to generate responses while using an external source.
Additional model parameters and their corresponding values not included in the text inference configuration for an external source. Takes in custom model parameters specific to the language model being used.
" } }, "documentation":"The response generation configuration of the external source wrapper object.
" }, "ExternalSourcesRetrieveAndGenerateConfiguration":{ "type":"structure", "required":[ "modelArn", "sources" ], "members":{ "modelArn":{ "shape":"BedrockModelArn", "documentation":"The Amazon Resource Name (ARN) of the foundation model or inference profile used to generate responses.
" }, "sources":{ "shape":"ExternalSources", "documentation":"The document for the external source wrapper object in the retrieveAndGenerate function.
Contains configurations details for response generation based on retrieved text chunks.
" } }, "documentation":"The configuration of the external source wrapper object in the retrieveAndGenerate function.
The name of metadata attribute/field, which must match the name in your data source/document metadata.
" }, "value":{ "shape":"FilterValue", "documentation":"The value of the metadata attribute/field.
" } }, "documentation":"Specifies the name of the metadata attribute/field to apply filters. You must match the name of the attribute/field in your data source/document metadata.
" }, "FilterKey":{ "type":"string", "max":100, "min":1 }, "FilterValue":{ "type":"structure", "members":{ }, "document":true }, "FineTuningJobStatus":{ "type":"string", "enum":[ "InProgress", "Completed", "Failed", "Stopping", "Stopped" ] }, "FoundationModelArn":{ "type":"string", "pattern":"arn:aws(-[^:]+)?:bedrock:[a-z0-9-]{1,20}::foundation-model/[a-z0-9-]{1,63}[.]{1}([a-z0-9-]{1,63}[.]){0,2}[a-z0-9-]{1,63}([:][a-z0-9-]{1,63}){0,2}" }, "FoundationModelDetails":{ "type":"structure", "required":[ "modelArn", "modelId" ], "members":{ "modelArn":{ "shape":"FoundationModelArn", "documentation":"The model Amazon Resource Name (ARN).
" }, "modelId":{ "shape":"BedrockModelId", "documentation":"The model identifier.
" }, "modelName":{ "shape":"BrandedName", "documentation":"The model name.
" }, "providerName":{ "shape":"BrandedName", "documentation":"The model's provider name.
" }, "inputModalities":{ "shape":"ModelModalityList", "documentation":"The input modalities that the model supports.
" }, "outputModalities":{ "shape":"ModelModalityList", "documentation":"The output modalities that the model supports.
" }, "responseStreamingSupported":{ "shape":"Boolean", "documentation":"Indicates whether the model supports streaming.
" }, "customizationsSupported":{ "shape":"ModelCustomizationList", "documentation":"The customization that the model supports.
" }, "inferenceTypesSupported":{ "shape":"InferenceTypeList", "documentation":"The inference types that the model supports.
" }, "modelLifecycle":{ "shape":"FoundationModelLifecycle", "documentation":"Contains details about whether a model version is available or deprecated
" } }, "documentation":"Information about a foundation model.
" }, "FoundationModelLifecycle":{ "type":"structure", "required":["status"], "members":{ "status":{ "shape":"FoundationModelLifecycleStatus", "documentation":"Specifies whether a model version is available (ACTIVE) or deprecated (LEGACY.
Details about whether a model version is available or deprecated.
" }, "FoundationModelLifecycleStatus":{ "type":"string", "enum":[ "ACTIVE", "LEGACY" ] }, "FoundationModelSummary":{ "type":"structure", "required":[ "modelArn", "modelId" ], "members":{ "modelArn":{ "shape":"FoundationModelArn", "documentation":"The Amazon Resource Name (ARN) of the foundation model.
" }, "modelId":{ "shape":"BedrockModelId", "documentation":"The model ID of the foundation model.
" }, "modelName":{ "shape":"BrandedName", "documentation":"The name of the model.
" }, "providerName":{ "shape":"BrandedName", "documentation":"The model's provider name.
" }, "inputModalities":{ "shape":"ModelModalityList", "documentation":"The input modalities that the model supports.
" }, "outputModalities":{ "shape":"ModelModalityList", "documentation":"The output modalities that the model supports.
" }, "responseStreamingSupported":{ "shape":"Boolean", "documentation":"Indicates whether the model supports streaming.
" }, "customizationsSupported":{ "shape":"ModelCustomizationList", "documentation":"Whether the model supports fine-tuning or continual pre-training.
" }, "inferenceTypesSupported":{ "shape":"InferenceTypeList", "documentation":"The inference types that the model supports.
" }, "modelLifecycle":{ "shape":"FoundationModelLifecycle", "documentation":"Contains details about whether a model version is available or deprecated.
" } }, "documentation":"Summary information for a foundation model.
" }, "FoundationModelSummaryList":{ "type":"list", "member":{"shape":"FoundationModelSummary"} }, "GenerationConfiguration":{ "type":"structure", "members":{ "promptTemplate":{ "shape":"PromptTemplate", "documentation":"Contains the template for the prompt that's sent to the model for response generation.
" }, "guardrailConfiguration":{ "shape":"GuardrailConfiguration", "documentation":"Contains configuration details for the guardrail.
" }, "kbInferenceConfig":{ "shape":"KbInferenceConfig", "documentation":"Contains configuration details for inference for knowledge base retrieval and response generation.
" }, "additionalModelRequestFields":{ "shape":"AdditionalModelRequestFields", "documentation":"Additional model parameters and corresponding values not included in the textInferenceConfig structure for a knowledge base. This allows you to provide custom model parameters specific to the language model being used.
The configuration details for response generation based on retrieved text chunks.
" }, "GetCustomModelRequest":{ "type":"structure", "required":["modelIdentifier"], "members":{ "modelIdentifier":{ "shape":"ModelIdentifier", "documentation":"Name or Amazon Resource Name (ARN) of the custom model.
", "location":"uri", "locationName":"modelIdentifier" } } }, "GetCustomModelResponse":{ "type":"structure", "required":[ "modelArn", "modelName", "jobArn", "baseModelArn", "trainingDataConfig", "outputDataConfig", "creationTime" ], "members":{ "modelArn":{ "shape":"ModelArn", "documentation":"Amazon Resource Name (ARN) associated with this model.
" }, "modelName":{ "shape":"CustomModelName", "documentation":"Model name associated with this model.
" }, "jobName":{ "shape":"JobName", "documentation":"Job name associated with this model.
" }, "jobArn":{ "shape":"ModelCustomizationJobArn", "documentation":"Job Amazon Resource Name (ARN) associated with this model.
" }, "baseModelArn":{ "shape":"ModelArn", "documentation":"Amazon Resource Name (ARN) of the base model.
" }, "customizationType":{ "shape":"CustomizationType", "documentation":"The type of model customization.
" }, "modelKmsKeyArn":{ "shape":"KmsKeyArn", "documentation":"The custom model is encrypted at rest using this key.
" }, "hyperParameters":{ "shape":"ModelCustomizationHyperParameters", "documentation":"Hyperparameter values associated with this model. For details on the format for different models, see Custom model hyperparameters.
" }, "trainingDataConfig":{ "shape":"TrainingDataConfig", "documentation":"Contains information about the training dataset.
" }, "validationDataConfig":{ "shape":"ValidationDataConfig", "documentation":"Contains information about the validation dataset.
" }, "outputDataConfig":{ "shape":"OutputDataConfig", "documentation":"Output data configuration associated with this custom model.
" }, "trainingMetrics":{ "shape":"TrainingMetrics", "documentation":"Contains training metrics from the job creation.
" }, "validationMetrics":{ "shape":"ValidationMetrics", "documentation":"The validation metrics from the job creation.
" }, "creationTime":{ "shape":"Timestamp", "documentation":"Creation time of the model.
" }, "customizationConfig":{ "shape":"CustomizationConfig", "documentation":"The customization configuration for the custom model.
" } } }, "GetEvaluationJobRequest":{ "type":"structure", "required":["jobIdentifier"], "members":{ "jobIdentifier":{ "shape":"EvaluationJobIdentifier", "documentation":"The Amazon Resource Name (ARN) of the evaluation job you want get information on.
", "location":"uri", "locationName":"jobIdentifier" } } }, "GetEvaluationJobResponse":{ "type":"structure", "required":[ "jobName", "status", "jobArn", "roleArn", "jobType", "evaluationConfig", "inferenceConfig", "outputDataConfig", "creationTime" ], "members":{ "jobName":{ "shape":"EvaluationJobName", "documentation":"The name for the evaluation job.
" }, "status":{ "shape":"EvaluationJobStatus", "documentation":"The current status of the evaluation job.
" }, "jobArn":{ "shape":"EvaluationJobArn", "documentation":"The Amazon Resource Name (ARN) of the evaluation job.
" }, "jobDescription":{ "shape":"EvaluationJobDescription", "documentation":"The description of the evaluation job.
" }, "roleArn":{ "shape":"RoleArn", "documentation":"The Amazon Resource Name (ARN) of the IAM service role used in the evaluation job.
" }, "customerEncryptionKeyId":{ "shape":"KmsKeyId", "documentation":"The Amazon Resource Name (ARN) of the customer managed encryption key specified when the evaluation job was created.
" }, "jobType":{ "shape":"EvaluationJobType", "documentation":"Specifies whether the evaluation job is automated or human-based.
" }, "applicationType":{ "shape":"ApplicationType", "documentation":"Specifies whether the evaluation job is for evaluating a model or evaluating a knowledge base (retrieval and response generation).
" }, "evaluationConfig":{ "shape":"EvaluationConfig", "documentation":"Contains the configuration details of either an automated or human-based evaluation job.
" }, "inferenceConfig":{ "shape":"EvaluationInferenceConfig", "documentation":"Contains the configuration details of the inference model used for the evaluation job.
" }, "outputDataConfig":{ "shape":"EvaluationOutputDataConfig", "documentation":"Contains the configuration details of the Amazon S3 bucket for storing the results of the evaluation job.
" }, "creationTime":{ "shape":"Timestamp", "documentation":"The time the evaluation job was created.
" }, "lastModifiedTime":{ "shape":"Timestamp", "documentation":"The time the evaluation job was last modified.
" }, "failureMessages":{ "shape":"ErrorMessages", "documentation":"A list of strings that specify why the evaluation job failed to create.
" } } }, "GetFoundationModelRequest":{ "type":"structure", "required":["modelIdentifier"], "members":{ "modelIdentifier":{ "shape":"ModelIdentifier", "documentation":"The model identifier.
", "location":"uri", "locationName":"modelIdentifier" } } }, "GetFoundationModelResponse":{ "type":"structure", "members":{ "modelDetails":{ "shape":"FoundationModelDetails", "documentation":"Information about the foundation model.
" } } }, "GetGuardrailRequest":{ "type":"structure", "required":["guardrailIdentifier"], "members":{ "guardrailIdentifier":{ "shape":"GuardrailIdentifier", "documentation":"The unique identifier of the guardrail for which to get details. This can be an ID or the ARN.
", "location":"uri", "locationName":"guardrailIdentifier" }, "guardrailVersion":{ "shape":"GuardrailVersion", "documentation":"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.
The name of the guardrail.
" }, "description":{ "shape":"GuardrailDescription", "documentation":"The description of the guardrail.
" }, "guardrailId":{ "shape":"GuardrailId", "documentation":"The unique identifier of the guardrail.
" }, "guardrailArn":{ "shape":"GuardrailArn", "documentation":"The ARN of the guardrail.
" }, "version":{ "shape":"GuardrailVersion", "documentation":"The version of the guardrail.
" }, "status":{ "shape":"GuardrailStatus", "documentation":"The status of the guardrail.
" }, "topicPolicy":{ "shape":"GuardrailTopicPolicy", "documentation":"The topic policy that was configured for the guardrail.
" }, "contentPolicy":{ "shape":"GuardrailContentPolicy", "documentation":"The content policy that was configured for the guardrail.
" }, "wordPolicy":{ "shape":"GuardrailWordPolicy", "documentation":"The word policy that was configured for the guardrail.
" }, "sensitiveInformationPolicy":{ "shape":"GuardrailSensitiveInformationPolicy", "documentation":"The sensitive information policy that was configured for the guardrail.
" }, "contextualGroundingPolicy":{ "shape":"GuardrailContextualGroundingPolicy", "documentation":"The contextual grounding policy used in the guardrail.
" }, "createdAt":{ "shape":"Timestamp", "documentation":"The date and time at which the guardrail was created.
" }, "updatedAt":{ "shape":"Timestamp", "documentation":"The date and time at which the guardrail was updated.
" }, "statusReasons":{ "shape":"GuardrailStatusReasons", "documentation":"Appears if the status is FAILED. A list of reasons for why the guardrail failed to be created, updated, versioned, or deleted.
Appears if the status of the guardrail is FAILED. A list of recommendations to carry out before retrying the request.
The message that the guardrail returns when it blocks a prompt.
" }, "blockedOutputsMessaging":{ "shape":"GuardrailBlockedMessaging", "documentation":"The message that the guardrail returns when it blocks a model response.
" }, "kmsKeyArn":{ "shape":"KmsKeyArn", "documentation":"The ARN of the KMS key that encrypts the guardrail.
" } } }, "GetImportedModelRequest":{ "type":"structure", "required":["modelIdentifier"], "members":{ "modelIdentifier":{ "shape":"ImportedModelIdentifier", "documentation":"Name or Amazon Resource Name (ARN) of the imported model.
", "location":"uri", "locationName":"modelIdentifier" } } }, "GetImportedModelResponse":{ "type":"structure", "members":{ "modelArn":{ "shape":"ImportedModelArn", "documentation":"The Amazon Resource Name (ARN) associated with this imported model.
" }, "modelName":{ "shape":"ImportedModelName", "documentation":"The name of the imported model.
" }, "jobName":{ "shape":"JobName", "documentation":"Job name associated with the imported model.
" }, "jobArn":{ "shape":"ModelImportJobArn", "documentation":"Job Amazon Resource Name (ARN) associated with the imported model.
" }, "modelDataSource":{ "shape":"ModelDataSource", "documentation":"The data source for this imported model.
" }, "creationTime":{ "shape":"Timestamp", "documentation":"Creation time of the imported model.
" }, "modelArchitecture":{ "shape":"String", "documentation":"The architecture of the imported model.
" }, "modelKmsKeyArn":{ "shape":"KmsKeyArn", "documentation":"The imported model is encrypted at rest using this key.
" }, "instructSupported":{ "shape":"InstructSupported", "documentation":"Specifies if the imported model supports converse.
" } } }, "GetInferenceProfileRequest":{ "type":"structure", "required":["inferenceProfileIdentifier"], "members":{ "inferenceProfileIdentifier":{ "shape":"InferenceProfileIdentifier", "documentation":"The ID or Amazon Resource Name (ARN) of the inference profile.
", "location":"uri", "locationName":"inferenceProfileIdentifier" } } }, "GetInferenceProfileResponse":{ "type":"structure", "required":[ "inferenceProfileName", "inferenceProfileArn", "models", "inferenceProfileId", "status", "type" ], "members":{ "inferenceProfileName":{ "shape":"InferenceProfileName", "documentation":"The name of the inference profile.
" }, "description":{ "shape":"InferenceProfileDescription", "documentation":"The description of the inference profile.
" }, "createdAt":{ "shape":"Timestamp", "documentation":"The time at which the inference profile was created.
" }, "updatedAt":{ "shape":"Timestamp", "documentation":"The time at which the inference profile was last updated.
" }, "inferenceProfileArn":{ "shape":"InferenceProfileArn", "documentation":"The Amazon Resource Name (ARN) of the inference profile.
" }, "models":{ "shape":"InferenceProfileModels", "documentation":"A list of information about each model in the inference profile.
" }, "inferenceProfileId":{ "shape":"InferenceProfileId", "documentation":"The unique identifier of the inference profile.
" }, "status":{ "shape":"InferenceProfileStatus", "documentation":"The status of the inference profile. ACTIVE means that the inference profile is ready to be used.
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.
The Amazon Resource Name (ARN) of the endpoint you want to get information about.
", "location":"uri", "locationName":"endpointArn" } } }, "GetMarketplaceModelEndpointResponse":{ "type":"structure", "members":{ "marketplaceModelEndpoint":{ "shape":"MarketplaceModelEndpoint", "documentation":"Details about the requested endpoint.
" } } }, "GetModelCopyJobRequest":{ "type":"structure", "required":["jobArn"], "members":{ "jobArn":{ "shape":"ModelCopyJobArn", "documentation":"The Amazon Resource Name (ARN) of the model copy job.
", "location":"uri", "locationName":"jobArn" } } }, "GetModelCopyJobResponse":{ "type":"structure", "required":[ "jobArn", "status", "creationTime", "targetModelArn", "sourceAccountId", "sourceModelArn" ], "members":{ "jobArn":{ "shape":"ModelCopyJobArn", "documentation":"The Amazon Resource Name (ARN) of the model copy job.
" }, "status":{ "shape":"ModelCopyJobStatus", "documentation":"The status of the model copy job.
" }, "creationTime":{ "shape":"Timestamp", "documentation":"The time at which the model copy job was created.
" }, "targetModelArn":{ "shape":"CustomModelArn", "documentation":"The Amazon Resource Name (ARN) of the copied model.
" }, "targetModelName":{ "shape":"CustomModelName", "documentation":"The name of the copied model.
" }, "sourceAccountId":{ "shape":"AccountId", "documentation":"The unique identifier of the account that the model being copied originated from.
" }, "sourceModelArn":{ "shape":"ModelArn", "documentation":"The Amazon Resource Name (ARN) of the original model being copied.
" }, "targetModelKmsKeyArn":{ "shape":"KmsKeyArn", "documentation":"The Amazon Resource Name (ARN) of the KMS key encrypting the copied model.
" }, "targetModelTags":{ "shape":"TagList", "documentation":"The tags associated with the copied model.
" }, "failureMessage":{ "shape":"ErrorMessage", "documentation":"An error message for why the model copy job failed.
" }, "sourceModelName":{ "shape":"CustomModelName", "documentation":"The name of the original model being copied.
" } } }, "GetModelCustomizationJobRequest":{ "type":"structure", "required":["jobIdentifier"], "members":{ "jobIdentifier":{ "shape":"ModelCustomizationJobIdentifier", "documentation":"Identifier for the customization job.
", "location":"uri", "locationName":"jobIdentifier" } } }, "GetModelCustomizationJobResponse":{ "type":"structure", "required":[ "jobArn", "jobName", "outputModelName", "roleArn", "creationTime", "baseModelArn", "trainingDataConfig", "validationDataConfig", "outputDataConfig" ], "members":{ "jobArn":{ "shape":"ModelCustomizationJobArn", "documentation":"The Amazon Resource Name (ARN) of the customization job.
" }, "jobName":{ "shape":"JobName", "documentation":"The name of the customization job.
" }, "outputModelName":{ "shape":"CustomModelName", "documentation":"The name of the output model.
" }, "outputModelArn":{ "shape":"CustomModelArn", "documentation":"The Amazon Resource Name (ARN) of the output model.
" }, "clientRequestToken":{ "shape":"IdempotencyToken", "documentation":"The token that you specified in the CreateCustomizationJob request.
The Amazon Resource Name (ARN) of the IAM role.
" }, "status":{ "shape":"ModelCustomizationJobStatus", "documentation":"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.
" }, "failureMessage":{ "shape":"ErrorMessage", "documentation":"Information about why the job failed.
" }, "creationTime":{ "shape":"Timestamp", "documentation":"Time that the resource was created.
" }, "lastModifiedTime":{ "shape":"Timestamp", "documentation":"Time that the resource was last modified.
" }, "endTime":{ "shape":"Timestamp", "documentation":"Time that the resource transitioned to terminal state.
" }, "baseModelArn":{ "shape":"FoundationModelArn", "documentation":"Amazon Resource Name (ARN) of the base model.
" }, "hyperParameters":{ "shape":"ModelCustomizationHyperParameters", "documentation":"The hyperparameter values for the job. For details on the format for different models, see Custom model hyperparameters.
" }, "trainingDataConfig":{ "shape":"TrainingDataConfig", "documentation":"Contains information about the training dataset.
" }, "validationDataConfig":{ "shape":"ValidationDataConfig", "documentation":"Contains information about the validation dataset.
" }, "outputDataConfig":{ "shape":"OutputDataConfig", "documentation":"Output data configuration
" }, "customizationType":{ "shape":"CustomizationType", "documentation":"The type of model customization.
" }, "outputModelKmsKeyArn":{ "shape":"KmsKeyArn", "documentation":"The custom model is encrypted at rest using this key.
" }, "trainingMetrics":{ "shape":"TrainingMetrics", "documentation":"Contains training metrics from the job creation.
" }, "validationMetrics":{ "shape":"ValidationMetrics", "documentation":"The loss metric for each validator that you provided in the createjob request.
" }, "vpcConfig":{ "shape":"VpcConfig", "documentation":"VPC configuration for the custom model job.
" }, "customizationConfig":{ "shape":"CustomizationConfig", "documentation":"The customization configuration for the model customization job.
" } } }, "GetModelImportJobRequest":{ "type":"structure", "required":["jobIdentifier"], "members":{ "jobIdentifier":{ "shape":"ModelImportJobIdentifier", "documentation":"The identifier of the import job.
", "location":"uri", "locationName":"jobIdentifier" } } }, "GetModelImportJobResponse":{ "type":"structure", "members":{ "jobArn":{ "shape":"ModelImportJobArn", "documentation":"The Amazon Resource Name (ARN) of the import job.
" }, "jobName":{ "shape":"JobName", "documentation":"The name of the import job.
" }, "importedModelName":{ "shape":"ImportedModelName", "documentation":"The name of the imported model.
" }, "importedModelArn":{ "shape":"ImportedModelArn", "documentation":"The Amazon Resource Name (ARN) of the imported model.
" }, "roleArn":{ "shape":"RoleArn", "documentation":"The Amazon Resource Name (ARN) of the IAM role associated with this job.
" }, "modelDataSource":{ "shape":"ModelDataSource", "documentation":"The data source for the imported model.
" }, "status":{ "shape":"ModelImportJobStatus", "documentation":"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.
" }, "failureMessage":{ "shape":"ErrorMessage", "documentation":"Information about why the import job failed.
" }, "creationTime":{ "shape":"Timestamp", "documentation":"The time the resource was created.
" }, "lastModifiedTime":{ "shape":"Timestamp", "documentation":"Time the resource was last modified.
" }, "endTime":{ "shape":"Timestamp", "documentation":"Time that the resource transitioned to terminal state.
" }, "vpcConfig":{ "shape":"VpcConfig", "documentation":"The Virtual Private Cloud (VPC) configuration of the import model job.
" }, "importedModelKmsKeyArn":{ "shape":"KmsKeyArn", "documentation":"The imported model is encrypted at rest using this key.
" } } }, "GetModelInvocationJobRequest":{ "type":"structure", "required":["jobIdentifier"], "members":{ "jobIdentifier":{ "shape":"ModelInvocationJobIdentifier", "documentation":"The Amazon Resource Name (ARN) of the batch inference job.
", "location":"uri", "locationName":"jobIdentifier" } } }, "GetModelInvocationJobResponse":{ "type":"structure", "required":[ "jobArn", "modelId", "roleArn", "submitTime", "inputDataConfig", "outputDataConfig" ], "members":{ "jobArn":{ "shape":"ModelInvocationJobArn", "documentation":"The Amazon Resource Name (ARN) of the batch inference job.
" }, "jobName":{ "shape":"ModelInvocationJobName", "documentation":"The name of the batch inference job.
" }, "modelId":{ "shape":"ModelId", "documentation":"The unique identifier of the foundation model used for model inference.
" }, "clientRequestToken":{ "shape":"ModelInvocationIdempotencyToken", "documentation":"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.
" }, "roleArn":{ "shape":"RoleArn", "documentation":"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":{ "shape":"ModelInvocationJobStatus", "documentation":"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 Services Support Center.
Stopped – This job was stopped by a user.
Stopping – This job is being stopped by a user.
If the batch inference job failed, this field contains a message describing why the job failed.
" }, "submitTime":{ "shape":"Timestamp", "documentation":"The time at which the batch inference job was submitted.
" }, "lastModifiedTime":{ "shape":"Timestamp", "documentation":"The time at which the batch inference job was last modified.
" }, "endTime":{ "shape":"Timestamp", "documentation":"The time at which the batch inference job ended.
" }, "inputDataConfig":{ "shape":"ModelInvocationJobInputDataConfig", "documentation":"Details about the location of the input to the batch inference job.
" }, "outputDataConfig":{ "shape":"ModelInvocationJobOutputDataConfig", "documentation":"Details about the location of the output of the batch inference job.
" }, "vpcConfig":{ "shape":"VpcConfig", "documentation":"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.
" }, "timeoutDurationInHours":{ "shape":"ModelInvocationJobTimeoutDurationInHours", "documentation":"The number of hours after which batch inference job was set to time out.
" }, "jobExpirationTime":{ "shape":"Timestamp", "documentation":"The time at which the batch inference job times or timed out.
" } } }, "GetModelInvocationLoggingConfigurationRequest":{ "type":"structure", "members":{ } }, "GetModelInvocationLoggingConfigurationResponse":{ "type":"structure", "members":{ "loggingConfig":{ "shape":"LoggingConfig", "documentation":"The current configuration values.
" } } }, "GetPromptRouterRequest":{ "type":"structure", "required":["promptRouterArn"], "members":{ "promptRouterArn":{ "shape":"PromptRouterArn", "documentation":"The prompt router's ARN
", "location":"uri", "locationName":"promptRouterArn" } } }, "GetPromptRouterResponse":{ "type":"structure", "required":[ "promptRouterName", "routingCriteria", "promptRouterArn", "models", "fallbackModel", "status", "type" ], "members":{ "promptRouterName":{ "shape":"PromptRouterName", "documentation":"The router's name.
" }, "routingCriteria":{ "shape":"RoutingCriteria", "documentation":"The router's routing criteria.
" }, "description":{ "shape":"PromptRouterDescription", "documentation":"The router's description.
" }, "createdAt":{ "shape":"Timestamp", "documentation":"When the router was created.
" }, "updatedAt":{ "shape":"Timestamp", "documentation":"When the router was updated.
" }, "promptRouterArn":{ "shape":"PromptRouterArn", "documentation":"The prompt router's ARN
" }, "models":{ "shape":"PromptRouterTargetModels", "documentation":"The router's models.
" }, "fallbackModel":{ "shape":"PromptRouterTargetModel", "documentation":"The router's fallback model.
" }, "status":{ "shape":"PromptRouterStatus", "documentation":"The router's status.
" }, "type":{ "shape":"PromptRouterType", "documentation":"The router's type.
" } } }, "GetProvisionedModelThroughputRequest":{ "type":"structure", "required":["provisionedModelId"], "members":{ "provisionedModelId":{ "shape":"ProvisionedModelId", "documentation":"The Amazon Resource Name (ARN) or name of the Provisioned Throughput.
", "location":"uri", "locationName":"provisionedModelId" } } }, "GetProvisionedModelThroughputResponse":{ "type":"structure", "required":[ "modelUnits", "desiredModelUnits", "provisionedModelName", "provisionedModelArn", "modelArn", "desiredModelArn", "foundationModelArn", "status", "creationTime", "lastModifiedTime" ], "members":{ "modelUnits":{ "shape":"PositiveInteger", "documentation":"The number of model units allocated to this Provisioned Throughput.
" }, "desiredModelUnits":{ "shape":"PositiveInteger", "documentation":"The number of model units that was requested for this Provisioned Throughput.
" }, "provisionedModelName":{ "shape":"ProvisionedModelName", "documentation":"The name of the Provisioned Throughput.
" }, "provisionedModelArn":{ "shape":"ProvisionedModelArn", "documentation":"The Amazon Resource Name (ARN) of the Provisioned Throughput.
" }, "modelArn":{ "shape":"ModelArn", "documentation":"The Amazon Resource Name (ARN) of the model associated with this Provisioned Throughput.
" }, "desiredModelArn":{ "shape":"ModelArn", "documentation":"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.
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":{ "shape":"ProvisionedModelStatus", "documentation":"The status of the Provisioned Throughput.
" }, "creationTime":{ "shape":"Timestamp", "documentation":"The timestamp of the creation time for this Provisioned Throughput.
" }, "lastModifiedTime":{ "shape":"Timestamp", "documentation":"The timestamp of the last time that this Provisioned Throughput was modified.
" }, "failureMessage":{ "shape":"ErrorMessage", "documentation":"A failure message for any issues that occurred during creation, updating, or deletion of the Provisioned Throughput.
" }, "commitmentDuration":{ "shape":"CommitmentDuration", "documentation":"Commitment duration of the Provisioned Throughput.
" }, "commitmentExpirationTime":{ "shape":"Timestamp", "documentation":"The timestamp for when the commitment term for the Provisioned Throughput expires.
" } } }, "GuardrailArn":{ "type":"string", "max":2048, "min":0, "pattern":"arn:aws(-[^:]+)?:bedrock:[a-z0-9-]{1,20}:[0-9]{12}:guardrail/[a-z0-9]+" }, "GuardrailBlockedMessaging":{ "type":"string", "max":500, "min":1, "sensitive":true }, "GuardrailConfiguration":{ "type":"structure", "required":[ "guardrailId", "guardrailVersion" ], "members":{ "guardrailId":{ "shape":"GuardrailConfigurationGuardrailIdString", "documentation":"The unique identifier for the guardrail.
" }, "guardrailVersion":{ "shape":"GuardrailConfigurationGuardrailVersionString", "documentation":"The version of the guardrail.
" } }, "documentation":"The configuration details for the guardrail.
" }, "GuardrailConfigurationGuardrailIdString":{ "type":"string", "max":64, "min":0, "pattern":"[a-z0-9]+" }, "GuardrailConfigurationGuardrailVersionString":{ "type":"string", "max":5, "min":1, "pattern":"(([1-9][0-9]{0,7})|(DRAFT))" }, "GuardrailContentFilter":{ "type":"structure", "required":[ "type", "inputStrength", "outputStrength" ], "members":{ "type":{ "shape":"GuardrailContentFilterType", "documentation":"The harmful category that the content filter is applied to.
" }, "inputStrength":{ "shape":"GuardrailFilterStrength", "documentation":"The strength of the content filter to apply to prompts. As you increase the filter strength, the likelihood of filtering harmful content increases and the probability of seeing harmful content in your application reduces.
" }, "outputStrength":{ "shape":"GuardrailFilterStrength", "documentation":"The strength of the content filter to apply to model responses. As you increase the filter strength, the likelihood of filtering harmful content increases and the probability of seeing harmful content in your application reduces.
" }, "inputModalities":{ "shape":"GuardrailModalities", "documentation":"The input modalities selected for the guardrail content filter.
" }, "outputModalities":{ "shape":"GuardrailModalities", "documentation":"The output modalities selected for the guardrail content filter.
" } }, "documentation":"Contains filter strengths for harmful content. Guardrails support the following content filters to detect and filter harmful user inputs and FM-generated outputs.
Hate – Describes language or a statement that discriminates, criticizes, insults, denounces, or dehumanizes a person or group on the basis of an identity (such as race, ethnicity, gender, religion, sexual orientation, ability, and national origin).
Insults – Describes language or a statement that includes demeaning, humiliating, mocking, insulting, or belittling language. This type of language is also labeled as bullying.
Sexual – Describes language or a statement that indicates sexual interest, activity, or arousal using direct or indirect references to body parts, physical traits, or sex.
Violence – Describes language or a statement that includes glorification of or threats to inflict physical pain, hurt, or injury toward a person, group or thing.
Content filtering depends on the confidence classification of user inputs and FM responses across each of the four harmful categories. All input and output statements are classified into one of four confidence levels (NONE, LOW, MEDIUM, HIGH) for each harmful category. For example, if a statement is classified as Hate with HIGH confidence, the likelihood of the statement representing hateful content is high. A single statement can be classified across multiple categories with varying confidence levels. For example, a single statement can be classified as Hate with HIGH confidence, Insults with LOW confidence, Sexual with NONE confidence, and Violence with MEDIUM confidence.
For more information, see Guardrails content filters.
This data type is used in the following API operations:
" }, "GuardrailContentFilterConfig":{ "type":"structure", "required":[ "type", "inputStrength", "outputStrength" ], "members":{ "type":{ "shape":"GuardrailContentFilterType", "documentation":"The harmful category that the content filter is applied to.
" }, "inputStrength":{ "shape":"GuardrailFilterStrength", "documentation":"The strength of the content filter to apply to prompts. As you increase the filter strength, the likelihood of filtering harmful content increases and the probability of seeing harmful content in your application reduces.
" }, "outputStrength":{ "shape":"GuardrailFilterStrength", "documentation":"The strength of the content filter to apply to model responses. As you increase the filter strength, the likelihood of filtering harmful content increases and the probability of seeing harmful content in your application reduces.
" }, "inputModalities":{ "shape":"GuardrailModalities", "documentation":"The input modalities selected for the guardrail content filter configuration.
" }, "outputModalities":{ "shape":"GuardrailModalities", "documentation":"The output modalities selected for the guardrail content filter configuration.
" } }, "documentation":"Contains filter strengths for harmful content. Guardrails support the following content filters to detect and filter harmful user inputs and FM-generated outputs.
Hate – Describes language or a statement that discriminates, criticizes, insults, denounces, or dehumanizes a person or group on the basis of an identity (such as race, ethnicity, gender, religion, sexual orientation, ability, and national origin).
Insults – Describes language or a statement that includes demeaning, humiliating, mocking, insulting, or belittling language. This type of language is also labeled as bullying.
Sexual – Describes language or a statement that indicates sexual interest, activity, or arousal using direct or indirect references to body parts, physical traits, or sex.
Violence – Describes language or a statement that includes glorification of or threats to inflict physical pain, hurt, or injury toward a person, group or thing.
Content filtering depends on the confidence classification of user inputs and FM responses across each of the four harmful categories. All input and output statements are classified into one of four confidence levels (NONE, LOW, MEDIUM, HIGH) for each harmful category. For example, if a statement is classified as Hate with HIGH confidence, the likelihood of the statement representing hateful content is high. A single statement can be classified across multiple categories with varying confidence levels. For example, a single statement can be classified as Hate with HIGH confidence, Insults with LOW confidence, Sexual with NONE confidence, and Violence with MEDIUM confidence.
For more information, see Guardrails content filters.
" }, "GuardrailContentFilterType":{ "type":"string", "enum":[ "SEXUAL", "VIOLENCE", "HATE", "INSULTS", "MISCONDUCT", "PROMPT_ATTACK" ] }, "GuardrailContentFilters":{ "type":"list", "member":{"shape":"GuardrailContentFilter"}, "max":6, "min":1 }, "GuardrailContentFiltersConfig":{ "type":"list", "member":{"shape":"GuardrailContentFilterConfig"}, "max":6, "min":1 }, "GuardrailContentPolicy":{ "type":"structure", "members":{ "filters":{ "shape":"GuardrailContentFilters", "documentation":"Contains the type of the content filter and how strongly it should apply to prompts and model responses.
" } }, "documentation":"Contains details about how to handle harmful content.
This data type is used in the following API operations:
" }, "GuardrailContentPolicyConfig":{ "type":"structure", "required":["filtersConfig"], "members":{ "filtersConfig":{ "shape":"GuardrailContentFiltersConfig", "documentation":"Contains the type of the content filter and how strongly it should apply to prompts and model responses.
" } }, "documentation":"Contains details about how to handle harmful content.
" }, "GuardrailContextualGroundingFilter":{ "type":"structure", "required":[ "type", "threshold" ], "members":{ "type":{ "shape":"GuardrailContextualGroundingFilterType", "documentation":"The filter type details for the guardrails contextual grounding filter.
" }, "threshold":{ "shape":"GuardrailContextualGroundingFilterThresholdDouble", "documentation":"The threshold details for the guardrails contextual grounding filter.
" } }, "documentation":"The details for the guardrails contextual grounding filter.
" }, "GuardrailContextualGroundingFilterConfig":{ "type":"structure", "required":[ "type", "threshold" ], "members":{ "type":{ "shape":"GuardrailContextualGroundingFilterType", "documentation":"The filter details for the guardrails contextual grounding filter.
" }, "threshold":{ "shape":"GuardrailContextualGroundingFilterConfigThresholdDouble", "documentation":"The threshold details for the guardrails contextual grounding filter.
" } }, "documentation":"The filter configuration details for the guardrails contextual grounding filter.
" }, "GuardrailContextualGroundingFilterConfigThresholdDouble":{ "type":"double", "box":true, "min":0 }, "GuardrailContextualGroundingFilterThresholdDouble":{ "type":"double", "box":true, "min":0 }, "GuardrailContextualGroundingFilterType":{ "type":"string", "enum":[ "GROUNDING", "RELEVANCE" ] }, "GuardrailContextualGroundingFilters":{ "type":"list", "member":{"shape":"GuardrailContextualGroundingFilter"}, "min":1 }, "GuardrailContextualGroundingFiltersConfig":{ "type":"list", "member":{"shape":"GuardrailContextualGroundingFilterConfig"}, "min":1 }, "GuardrailContextualGroundingPolicy":{ "type":"structure", "required":["filters"], "members":{ "filters":{ "shape":"GuardrailContextualGroundingFilters", "documentation":"The filter details for the guardrails contextual grounding policy.
" } }, "documentation":"The details for the guardrails contextual grounding policy.
" }, "GuardrailContextualGroundingPolicyConfig":{ "type":"structure", "required":["filtersConfig"], "members":{ "filtersConfig":{ "shape":"GuardrailContextualGroundingFiltersConfig", "documentation":"The filter configuration details for the guardrails contextual grounding policy.
" } }, "documentation":"The policy configuration details for the guardrails contextual grounding policy.
" }, "GuardrailDescription":{ "type":"string", "max":200, "min":1, "sensitive":true }, "GuardrailDraftVersion":{ "type":"string", "max":5, "min":5, "pattern":"DRAFT" }, "GuardrailFailureRecommendation":{ "type":"string", "max":200, "min":1, "sensitive":true }, "GuardrailFailureRecommendations":{ "type":"list", "member":{"shape":"GuardrailFailureRecommendation"}, "max":100, "min":0 }, "GuardrailFilterStrength":{ "type":"string", "enum":[ "NONE", "LOW", "MEDIUM", "HIGH" ] }, "GuardrailId":{ "type":"string", "max":64, "min":0, "pattern":"[a-z0-9]+" }, "GuardrailIdentifier":{ "type":"string", "max":2048, "min":0, "pattern":"(([a-z0-9]+)|(arn:aws(-[^:]+)?:bedrock:[a-z0-9-]{1,20}:[0-9]{12}:guardrail/[a-z0-9]+))" }, "GuardrailManagedWordLists":{ "type":"list", "member":{"shape":"GuardrailManagedWords"} }, "GuardrailManagedWordListsConfig":{ "type":"list", "member":{"shape":"GuardrailManagedWordsConfig"} }, "GuardrailManagedWords":{ "type":"structure", "required":["type"], "members":{ "type":{ "shape":"GuardrailManagedWordsType", "documentation":"ManagedWords$type The managed word type that was configured for the guardrail. (For now, we only offer profanity word list)
" } }, "documentation":"The managed word list that was configured for the guardrail. (This is a list of words that are pre-defined and managed by guardrails only.)
" }, "GuardrailManagedWordsConfig":{ "type":"structure", "required":["type"], "members":{ "type":{ "shape":"GuardrailManagedWordsType", "documentation":"The managed word type to configure for the guardrail.
" } }, "documentation":"The managed word list to configure for the guardrail.
" }, "GuardrailManagedWordsType":{ "type":"string", "enum":["PROFANITY"] }, "GuardrailModalities":{ "type":"list", "member":{"shape":"GuardrailModality"}, "max":2, "min":1 }, "GuardrailModality":{ "type":"string", "enum":[ "TEXT", "IMAGE" ], "sensitive":true }, "GuardrailName":{ "type":"string", "max":50, "min":1, "pattern":"[0-9a-zA-Z-_]+", "sensitive":true }, "GuardrailNumericalVersion":{ "type":"string", "pattern":"[1-9][0-9]{0,7}" }, "GuardrailPiiEntities":{ "type":"list", "member":{"shape":"GuardrailPiiEntity"}, "min":1 }, "GuardrailPiiEntitiesConfig":{ "type":"list", "member":{"shape":"GuardrailPiiEntityConfig"}, "min":1 }, "GuardrailPiiEntity":{ "type":"structure", "required":[ "type", "action" ], "members":{ "type":{ "shape":"GuardrailPiiEntityType", "documentation":"The type of PII entity. For example, Social Security Number.
" }, "action":{ "shape":"GuardrailSensitiveInformationAction", "documentation":"The configured guardrail action when PII entity is detected.
" } }, "documentation":"The PII entity configured for the guardrail.
" }, "GuardrailPiiEntityConfig":{ "type":"structure", "required":[ "type", "action" ], "members":{ "type":{ "shape":"GuardrailPiiEntityType", "documentation":"Configure guardrail type when the PII entity is detected.
The following PIIs are used to block or mask sensitive information:
General
ADDRESS
A physical address, such as \"100 Main Street, Anytown, USA\" or \"Suite #12, Building 123\". An address can include information such as the street, building, location, city, state, country, county, zip code, precinct, and neighborhood.
AGE
An individual's age, including the quantity and unit of time. For example, in the phrase \"I am 40 years old,\" Guardrails recognizes \"40 years\" as an age.
NAME
An individual's name. This entity type does not include titles, such as Dr., Mr., Mrs., or Miss. guardrails doesn't apply this entity type to names that are part of organizations or addresses. For example, guardrails recognizes the \"John Doe Organization\" as an organization, and it recognizes \"Jane Doe Street\" as an address.
An email address, such as marymajor@email.com.
PHONE
A phone number. This entity type also includes fax and pager numbers.
USERNAME
A user name that identifies an account, such as a login name, screen name, nick name, or handle.
PASSWORD
An alphanumeric string that is used as a password, such as \"*very20special#pass*\".
DRIVER_ID
The number assigned to a driver's license, which is an official document permitting an individual to operate one or more motorized vehicles on a public road. A driver's license number consists of alphanumeric characters.
LICENSE_PLATE
A license plate for a vehicle is issued by the state or country where the vehicle is registered. The format for passenger vehicles is typically five to eight digits, consisting of upper-case letters and numbers. The format varies depending on the location of the issuing state or country.
VEHICLE_IDENTIFICATION_NUMBER
A Vehicle Identification Number (VIN) uniquely identifies a vehicle. VIN content and format are defined in the ISO 3779 specification. Each country has specific codes and formats for VINs.
Finance
CREDIT_DEBIT_CARD_CVV
A three-digit card verification code (CVV) that is present on VISA, MasterCard, and Discover credit and debit cards. For American Express credit or debit cards, the CVV is a four-digit numeric code.
CREDIT_DEBIT_CARD_EXPIRY
The expiration date for a credit or debit card. This number is usually four digits long and is often formatted as month/year or MM/YY. Guardrails recognizes expiration dates such as 01/21, 01/2021, and Jan 2021.
CREDIT_DEBIT_CARD_NUMBER
The number for a credit or debit card. These numbers can vary from 13 to 16 digits in length. However, Amazon Comprehend also recognizes credit or debit card numbers when only the last four digits are present.
PIN
A four-digit personal identification number (PIN) with which you can access your bank account.
INTERNATIONAL_BANK_ACCOUNT_NUMBER
An International Bank Account Number has specific formats in each country. For more information, see www.iban.com/structure.
SWIFT_CODE
A SWIFT code is a standard format of Bank Identifier Code (BIC) used to specify a particular bank or branch. Banks use these codes for money transfers such as international wire transfers.
SWIFT codes consist of eight or 11 characters. The 11-digit codes refer to specific branches, while eight-digit codes (or 11-digit codes ending in 'XXX') refer to the head or primary office.
IT
IP_ADDRESS
An IPv4 address, such as 198.51.100.0.
MAC_ADDRESS
A media access control (MAC) address is a unique identifier assigned to a network interface controller (NIC).
URL
A web address, such as www.example.com.
AWS_ACCESS_KEY
A unique identifier that's associated with a secret access key; you use the access key ID and secret access key to sign programmatic Amazon Web Services requests cryptographically.
AWS_SECRET_KEY
A unique identifier that's associated with an access key. You use the access key ID and secret access key to sign programmatic Amazon Web Services requests cryptographically.
USA specific
US_BANK_ACCOUNT_NUMBER
A US bank account number, which is typically 10 to 12 digits long.
US_BANK_ROUTING_NUMBER
A US bank account routing number. These are typically nine digits long,
US_INDIVIDUAL_TAX_IDENTIFICATION_NUMBER
A US Individual Taxpayer Identification Number (ITIN) is a nine-digit number that starts with a \"9\" and contain a \"7\" or \"8\" as the fourth digit. An ITIN can be formatted with a space or a dash after the third and forth digits.
US_PASSPORT_NUMBER
A US passport number. Passport numbers range from six to nine alphanumeric characters.
US_SOCIAL_SECURITY_NUMBER
A US Social Security Number (SSN) is a nine-digit number that is issued to US citizens, permanent residents, and temporary working residents.
Canada specific
CA_HEALTH_NUMBER
A Canadian Health Service Number is a 10-digit unique identifier, required for individuals to access healthcare benefits.
CA_SOCIAL_INSURANCE_NUMBER
A Canadian Social Insurance Number (SIN) is a nine-digit unique identifier, required for individuals to access government programs and benefits.
The SIN is formatted as three groups of three digits, such as 123-456-789. A SIN can be validated through a simple check-digit process called the Luhn algorithm.
UK Specific
UK_NATIONAL_HEALTH_SERVICE_NUMBER
A UK National Health Service Number is a 10-17 digit number, such as 485 777 3456. The current system formats the 10-digit number with spaces after the third and sixth digits. The final digit is an error-detecting checksum.
UK_NATIONAL_INSURANCE_NUMBER
A UK National Insurance Number (NINO) provides individuals with access to National Insurance (social security) benefits. It is also used for some purposes in the UK tax system.
The number is nine digits long and starts with two letters, followed by six numbers and one letter. A NINO can be formatted with a space or a dash after the two letters and after the second, forth, and sixth digits.
UK_UNIQUE_TAXPAYER_REFERENCE_NUMBER
A UK Unique Taxpayer Reference (UTR) is a 10-digit number that identifies a taxpayer or a business.
Custom
Regex filter - You can use a regular expressions to define patterns for a guardrail to recognize and act upon such as serial number, booking ID etc..
Configure guardrail action when the PII entity is detected.
" } }, "documentation":"The PII entity to configure for the guardrail.
" }, "GuardrailPiiEntityType":{ "type":"string", "enum":[ "ADDRESS", "AGE", "AWS_ACCESS_KEY", "AWS_SECRET_KEY", "CA_HEALTH_NUMBER", "CA_SOCIAL_INSURANCE_NUMBER", "CREDIT_DEBIT_CARD_CVV", "CREDIT_DEBIT_CARD_EXPIRY", "CREDIT_DEBIT_CARD_NUMBER", "DRIVER_ID", "EMAIL", "INTERNATIONAL_BANK_ACCOUNT_NUMBER", "IP_ADDRESS", "LICENSE_PLATE", "MAC_ADDRESS", "NAME", "PASSWORD", "PHONE", "PIN", "SWIFT_CODE", "UK_NATIONAL_HEALTH_SERVICE_NUMBER", "UK_NATIONAL_INSURANCE_NUMBER", "UK_UNIQUE_TAXPAYER_REFERENCE_NUMBER", "URL", "USERNAME", "US_BANK_ACCOUNT_NUMBER", "US_BANK_ROUTING_NUMBER", "US_INDIVIDUAL_TAX_IDENTIFICATION_NUMBER", "US_PASSPORT_NUMBER", "US_SOCIAL_SECURITY_NUMBER", "VEHICLE_IDENTIFICATION_NUMBER" ] }, "GuardrailRegex":{ "type":"structure", "required":[ "name", "pattern", "action" ], "members":{ "name":{ "shape":"GuardrailRegexNameString", "documentation":"The name of the regular expression for the guardrail.
" }, "description":{ "shape":"GuardrailRegexDescriptionString", "documentation":"The description of the regular expression for the guardrail.
" }, "pattern":{ "shape":"GuardrailRegexPatternString", "documentation":"The pattern of the regular expression configured for the guardrail.
" }, "action":{ "shape":"GuardrailSensitiveInformationAction", "documentation":"The action taken when a match to the regular expression is detected.
" } }, "documentation":"The regular expression configured for the guardrail.
" }, "GuardrailRegexConfig":{ "type":"structure", "required":[ "name", "pattern", "action" ], "members":{ "name":{ "shape":"GuardrailRegexConfigNameString", "documentation":"The name of the regular expression to configure for the guardrail.
" }, "description":{ "shape":"GuardrailRegexConfigDescriptionString", "documentation":"The description of the regular expression to configure for the guardrail.
" }, "pattern":{ "shape":"GuardrailRegexConfigPatternString", "documentation":"The regular expression pattern to configure for the guardrail.
" }, "action":{ "shape":"GuardrailSensitiveInformationAction", "documentation":"The guardrail action to configure when matching regular expression is detected.
" } }, "documentation":"The regular expression to configure for the guardrail.
" }, "GuardrailRegexConfigDescriptionString":{ "type":"string", "max":1000, "min":1 }, "GuardrailRegexConfigNameString":{ "type":"string", "max":100, "min":1 }, "GuardrailRegexConfigPatternString":{ "type":"string", "max":500, "min":1 }, "GuardrailRegexDescriptionString":{ "type":"string", "max":1000, "min":1 }, "GuardrailRegexNameString":{ "type":"string", "max":100, "min":1 }, "GuardrailRegexPatternString":{ "type":"string", "max":500, "min":1 }, "GuardrailRegexes":{ "type":"list", "member":{"shape":"GuardrailRegex"} }, "GuardrailRegexesConfig":{ "type":"list", "member":{"shape":"GuardrailRegexConfig"}, "max":10, "min":1 }, "GuardrailSensitiveInformationAction":{ "type":"string", "enum":[ "BLOCK", "ANONYMIZE" ] }, "GuardrailSensitiveInformationPolicy":{ "type":"structure", "members":{ "piiEntities":{ "shape":"GuardrailPiiEntities", "documentation":"The list of PII entities configured for the guardrail.
" }, "regexes":{ "shape":"GuardrailRegexes", "documentation":"The list of regular expressions configured for the guardrail.
" } }, "documentation":"Contains details about PII entities and regular expressions configured for the guardrail.
" }, "GuardrailSensitiveInformationPolicyConfig":{ "type":"structure", "members":{ "piiEntitiesConfig":{ "shape":"GuardrailPiiEntitiesConfig", "documentation":"A list of PII entities to configure to the guardrail.
" }, "regexesConfig":{ "shape":"GuardrailRegexesConfig", "documentation":"A list of regular expressions to configure to the guardrail.
" } }, "documentation":"Contains details about PII entities and regular expressions to configure for the guardrail.
" }, "GuardrailStatus":{ "type":"string", "enum":[ "CREATING", "UPDATING", "VERSIONING", "READY", "FAILED", "DELETING" ] }, "GuardrailStatusReason":{ "type":"string", "max":200, "min":1, "sensitive":true }, "GuardrailStatusReasons":{ "type":"list", "member":{"shape":"GuardrailStatusReason"}, "max":100, "min":0 }, "GuardrailSummaries":{ "type":"list", "member":{"shape":"GuardrailSummary"}, "max":1000, "min":0 }, "GuardrailSummary":{ "type":"structure", "required":[ "id", "arn", "status", "name", "version", "createdAt", "updatedAt" ], "members":{ "id":{ "shape":"GuardrailId", "documentation":"The unique identifier of the guardrail.
" }, "arn":{ "shape":"GuardrailArn", "documentation":"The ARN of the guardrail.
" }, "status":{ "shape":"GuardrailStatus", "documentation":"The status of the guardrail.
" }, "name":{ "shape":"GuardrailName", "documentation":"The name of the guardrail.
" }, "description":{ "shape":"GuardrailDescription", "documentation":"A description of the guardrail.
" }, "version":{ "shape":"GuardrailVersion", "documentation":"The version of the guardrail.
" }, "createdAt":{ "shape":"Timestamp", "documentation":"The date and time at which the guardrail was created.
" }, "updatedAt":{ "shape":"Timestamp", "documentation":"The date and time at which the guardrail was last updated.
" } }, "documentation":"Contains details about a guardrail.
This data type is used in the following API operations:
" }, "GuardrailTopic":{ "type":"structure", "required":[ "name", "definition" ], "members":{ "name":{ "shape":"GuardrailTopicName", "documentation":"The name of the topic to deny.
" }, "definition":{ "shape":"GuardrailTopicDefinition", "documentation":"A definition of the topic to deny.
" }, "examples":{ "shape":"GuardrailTopicExamples", "documentation":"A list of prompts, each of which is an example of a prompt that can be categorized as belonging to the topic.
" }, "type":{ "shape":"GuardrailTopicType", "documentation":"Specifies to deny the topic.
" } }, "documentation":"Details about topics for the guardrail to identify and deny.
This data type is used in the following API operations:
" }, "GuardrailTopicConfig":{ "type":"structure", "required":[ "name", "definition", "type" ], "members":{ "name":{ "shape":"GuardrailTopicName", "documentation":"The name of the topic to deny.
" }, "definition":{ "shape":"GuardrailTopicDefinition", "documentation":"A definition of the topic to deny.
" }, "examples":{ "shape":"GuardrailTopicExamples", "documentation":"A list of prompts, each of which is an example of a prompt that can be categorized as belonging to the topic.
" }, "type":{ "shape":"GuardrailTopicType", "documentation":"Specifies to deny the topic.
" } }, "documentation":"Details about topics for the guardrail to identify and deny.
" }, "GuardrailTopicDefinition":{ "type":"string", "max":200, "min":1, "sensitive":true }, "GuardrailTopicExample":{ "type":"string", "max":100, "min":1, "sensitive":true }, "GuardrailTopicExamples":{ "type":"list", "member":{"shape":"GuardrailTopicExample"}, "max":5, "min":0 }, "GuardrailTopicName":{ "type":"string", "max":100, "min":1, "pattern":"[0-9a-zA-Z-_ !?.]+", "sensitive":true }, "GuardrailTopicPolicy":{ "type":"structure", "required":["topics"], "members":{ "topics":{ "shape":"GuardrailTopics", "documentation":"A list of policies related to topics that the guardrail should deny.
" } }, "documentation":"Contains details about topics that the guardrail should identify and deny.
This data type is used in the following API operations:
" }, "GuardrailTopicPolicyConfig":{ "type":"structure", "required":["topicsConfig"], "members":{ "topicsConfig":{ "shape":"GuardrailTopicsConfig", "documentation":"A list of policies related to topics that the guardrail should deny.
" } }, "documentation":"Contains details about topics that the guardrail should identify and deny.
" }, "GuardrailTopicType":{ "type":"string", "enum":["DENY"] }, "GuardrailTopics":{ "type":"list", "member":{"shape":"GuardrailTopic"}, "max":30, "min":1 }, "GuardrailTopicsConfig":{ "type":"list", "member":{"shape":"GuardrailTopicConfig"}, "max":30, "min":1 }, "GuardrailVersion":{ "type":"string", "pattern":"(([1-9][0-9]{0,7})|(DRAFT))" }, "GuardrailWord":{ "type":"structure", "required":["text"], "members":{ "text":{ "shape":"GuardrailWordTextString", "documentation":"Text of the word configured for the guardrail to block.
" } }, "documentation":"A word configured for the guardrail.
" }, "GuardrailWordConfig":{ "type":"structure", "required":["text"], "members":{ "text":{ "shape":"GuardrailWordConfigTextString", "documentation":"Text of the word configured for the guardrail to block.
" } }, "documentation":"A word to configure for the guardrail.
" }, "GuardrailWordConfigTextString":{ "type":"string", "max":100, "min":1 }, "GuardrailWordPolicy":{ "type":"structure", "members":{ "words":{ "shape":"GuardrailWords", "documentation":"A list of words configured for the guardrail.
" }, "managedWordLists":{ "shape":"GuardrailManagedWordLists", "documentation":"A list of managed words configured for the guardrail.
" } }, "documentation":"Contains details about the word policy configured for the guardrail.
" }, "GuardrailWordPolicyConfig":{ "type":"structure", "members":{ "wordsConfig":{ "shape":"GuardrailWordsConfig", "documentation":"A list of words to configure for the guardrail.
" }, "managedWordListsConfig":{ "shape":"GuardrailManagedWordListsConfig", "documentation":"A list of managed words to configure for the guardrail.
" } }, "documentation":"Contains details about the word policy to configured for the guardrail.
" }, "GuardrailWordTextString":{ "type":"string", "max":100, "min":1 }, "GuardrailWords":{ "type":"list", "member":{"shape":"GuardrailWord"}, "max":10000, "min":1 }, "GuardrailWordsConfig":{ "type":"list", "member":{"shape":"GuardrailWordConfig"}, "max":10000, "min":1 }, "HumanEvaluationConfig":{ "type":"structure", "required":["datasetMetricConfigs"], "members":{ "humanWorkflowConfig":{ "shape":"HumanWorkflowConfig", "documentation":"The parameters of the human workflow.
" }, "customMetrics":{ "shape":"HumanEvaluationCustomMetrics", "documentation":"A HumanEvaluationCustomMetric object. It contains the names the metrics, how the metrics are to be evaluated, an optional description.
Use to specify the metrics, task, and prompt dataset to be used in your model evaluation job.
" } }, "documentation":"Specifies the custom metrics, how tasks will be rated, the flow definition ARN, and your custom prompt datasets. Model evaluation jobs use human workers only support the use of custom prompt datasets. To learn more about custom prompt datasets and the required format, see Custom prompt datasets.
When you create custom metrics in HumanEvaluationCustomMetric you must specify the metric's name. The list of names specified in the HumanEvaluationCustomMetric array, must match the metricNames array of strings specified in EvaluationDatasetMetricConfig. For example, if in the HumanEvaluationCustomMetric array your specified the names \"accuracy\", \"toxicity\", \"readability\" as custom metrics then the metricNames array would need to look like the following [\"accuracy\", \"toxicity\", \"readability\"] in EvaluationDatasetMetricConfig.
The name of the metric. Your human evaluators will see this name in the evaluation UI.
" }, "description":{ "shape":"EvaluationMetricDescription", "documentation":"An optional description of the metric. Use this parameter to provide more details about the metric.
" }, "ratingMethod":{ "shape":"EvaluationRatingMethod", "documentation":"Choose how you want your human workers to evaluation your model. Valid values for rating methods are ThumbsUpDown, IndividualLikertScale,ComparisonLikertScale, ComparisonChoice, and ComparisonRank
In a model evaluation job that uses human workers you must define the name of the metric, and how you want that metric rated ratingMethod, and an optional description of the metric.
The Amazon Resource Number (ARN) for the flow definition
" }, "instructions":{ "shape":"HumanTaskInstructions", "documentation":"Instructions for the flow definition
" } }, "documentation":"Contains SageMakerFlowDefinition object. The object is used to specify the prompt dataset, task type, rating method and metric names.
The Amazon Resource Name (ARN) of the imported model.
" }, "modelName":{ "shape":"ImportedModelName", "documentation":"Name of the imported model.
" }, "creationTime":{ "shape":"Timestamp", "documentation":"Creation time of the imported model.
" }, "instructSupported":{ "shape":"InstructSupported", "documentation":"Specifies if the imported model supports converse.
" }, "modelArchitecture":{ "shape":"ModelArchitecture", "documentation":"The architecture of the imported model.
" } }, "documentation":"Information about the imported model.
" }, "ImportedModelSummaryList":{ "type":"list", "member":{"shape":"ImportedModelSummary"} }, "InferenceProfileArn":{ "type":"string", "max":2048, "min":1, "pattern":"arn:aws(|-us-gov|-cn|-iso|-iso-b):bedrock:(|[0-9a-z-]{0,20}):(|[0-9]{12}):(inference-profile|application-inference-profile)/[a-zA-Z0-9-:.]+" }, "InferenceProfileDescription":{ "type":"string", "max":200, "min":1, "pattern":"([0-9a-zA-Z:.][ _-]?)+", "sensitive":true }, "InferenceProfileId":{ "type":"string", "max":64, "min":1, "pattern":"[a-zA-Z0-9-:.]+" }, "InferenceProfileIdentifier":{ "type":"string", "max":2048, "min":1, "pattern":"(arn:aws(|-us-gov|-cn|-iso|-iso-b):bedrock:(|[0-9a-z-]{0,20}):(|[0-9]{12}):(inference-profile|application-inference-profile)/)?[a-zA-Z0-9-:.]+" }, "InferenceProfileModel":{ "type":"structure", "members":{ "modelArn":{ "shape":"FoundationModelArn", "documentation":"The Amazon Resource Name (ARN) of the model.
" } }, "documentation":"Contains information about a model.
" }, "InferenceProfileModelSource":{ "type":"structure", "members":{ "copyFrom":{ "shape":"InferenceProfileModelSourceArn", "documentation":"The ARN of the model or system-defined inference profile that is the source for the inference profile.
" } }, "documentation":"Contains information about the model or system-defined inference profile that is the source for an inference profile..
", "union":true }, "InferenceProfileModelSourceArn":{ "type":"string", "max":2048, "min":1, "pattern":"arn:aws(|-us-gov|-cn|-iso|-iso-b):bedrock:(|[0-9a-z-]{0,20}):(|[0-9]{12}):(inference-profile|foundation-model)/[a-zA-Z0-9-:.]+" }, "InferenceProfileModels":{ "type":"list", "member":{"shape":"InferenceProfileModel"}, "max":5, "min":1 }, "InferenceProfileName":{ "type":"string", "max":64, "min":1, "pattern":"([0-9a-zA-Z][ _-]?)+" }, "InferenceProfileStatus":{ "type":"string", "enum":["ACTIVE"] }, "InferenceProfileSummaries":{ "type":"list", "member":{"shape":"InferenceProfileSummary"} }, "InferenceProfileSummary":{ "type":"structure", "required":[ "inferenceProfileName", "inferenceProfileArn", "models", "inferenceProfileId", "status", "type" ], "members":{ "inferenceProfileName":{ "shape":"InferenceProfileName", "documentation":"The name of the inference profile.
" }, "description":{ "shape":"InferenceProfileDescription", "documentation":"The description of the inference profile.
" }, "createdAt":{ "shape":"Timestamp", "documentation":"The time at which the inference profile was created.
" }, "updatedAt":{ "shape":"Timestamp", "documentation":"The time at which the inference profile was last updated.
" }, "inferenceProfileArn":{ "shape":"InferenceProfileArn", "documentation":"The Amazon Resource Name (ARN) of the inference profile.
" }, "models":{ "shape":"InferenceProfileModels", "documentation":"A list of information about each model in the inference profile.
" }, "inferenceProfileId":{ "shape":"InferenceProfileId", "documentation":"The unique identifier of the inference profile.
" }, "status":{ "shape":"InferenceProfileStatus", "documentation":"The status of the inference profile. ACTIVE means that the inference profile is ready to be used.
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.
Contains information about an inference profile.
" }, "InferenceProfileType":{ "type":"string", "enum":[ "SYSTEM_DEFINED", "APPLICATION" ] }, "InferenceType":{ "type":"string", "enum":[ "ON_DEMAND", "PROVISIONED" ] }, "InferenceTypeList":{ "type":"list", "member":{"shape":"InferenceType"} }, "InstanceCount":{ "type":"integer", "box":true, "min":1 }, "InstanceType":{ "type":"string", "max":50, "min":1 }, "InstructSupported":{ "type":"boolean", "box":true }, "Integer":{ "type":"integer", "box":true }, "InternalServerException":{ "type":"structure", "members":{ "message":{"shape":"NonBlankString"} }, "documentation":"An internal server error occurred. Retry your request.
", "error":{"httpStatusCode":500}, "exception":true, "fault":true }, "InvocationLogSource":{ "type":"structure", "members":{ "s3Uri":{ "shape":"S3Uri", "documentation":"The URI of an invocation log in a bucket.
" } }, "documentation":"A storage location for invocation logs.
", "union":true }, "InvocationLogsConfig":{ "type":"structure", "required":["invocationLogSource"], "members":{ "usePromptResponse":{ "shape":"UsePromptResponse", "documentation":"Whether to use the model's response for training, or just the prompt. The default value is False.
The source of the invocation logs.
" }, "requestMetadataFilters":{ "shape":"RequestMetadataFilters", "documentation":"Rules for filtering invocation logs based on request metadata.
" } }, "documentation":"Settings for using invocation logs to customize a model.
" }, "JobName":{ "type":"string", "max":63, "min":1, "pattern":"[a-zA-Z0-9](-*[a-zA-Z0-9\\+\\-\\.])*" }, "KbInferenceConfig":{ "type":"structure", "members":{ "textInferenceConfig":{ "shape":"TextInferenceConfig", "documentation":"Contains configuration details for text generation using a language model via the RetrieveAndGenerate function.
Contains configuration details of the inference for knowledge base retrieval and response generation.
" }, "KeyPrefix":{ "type":"string", "max":1024, "min":0 }, "KmsKeyArn":{ "type":"string", "max":2048, "min":1, "pattern":"arn:aws(-[^:]+)?:kms:[a-zA-Z0-9-]*:[0-9]{12}:key/[a-zA-Z0-9-]{36}" }, "KmsKeyId":{ "type":"string", "max":2048, "min":1, "pattern":"(arn:aws(-[^:]+)?:kms:[a-zA-Z0-9-]*:[0-9]{12}:((key/[a-zA-Z0-9-]{36})|(alias/[a-zA-Z0-9-_/]+)))|([a-zA-Z0-9-]{36})|(alias/[a-zA-Z0-9-_/]+)" }, "KnowledgeBaseConfig":{ "type":"structure", "members":{ "retrieveConfig":{ "shape":"RetrieveConfig", "documentation":"Contains configuration details for retrieving information from a knowledge base.
" }, "retrieveAndGenerateConfig":{ "shape":"RetrieveAndGenerateConfiguration", "documentation":"Contains configuration details for retrieving information from a knowledge base and generating responses.
" } }, "documentation":"The configuration details for retrieving information from a knowledge base and generating responses.
", "union":true }, "KnowledgeBaseId":{ "type":"string", "max":10, "min":0, "pattern":"[0-9a-zA-Z]+" }, "KnowledgeBaseRetrievalConfiguration":{ "type":"structure", "required":["vectorSearchConfiguration"], "members":{ "vectorSearchConfiguration":{ "shape":"KnowledgeBaseVectorSearchConfiguration", "documentation":"Contains configuration details for returning the results from the vector search.
" } }, "documentation":"Contains configuration details for retrieving information from a knowledge base.
" }, "KnowledgeBaseRetrieveAndGenerateConfiguration":{ "type":"structure", "required":[ "knowledgeBaseId", "modelArn" ], "members":{ "knowledgeBaseId":{ "shape":"KnowledgeBaseId", "documentation":"The unique identifier of the knowledge base.
" }, "modelArn":{ "shape":"BedrockModelArn", "documentation":"The Amazon Resource Name (ARN) of the foundation model or inference profile used to generate responses.
" }, "retrievalConfiguration":{ "shape":"KnowledgeBaseRetrievalConfiguration", "documentation":"Contains configuration details for retrieving text chunks.
" }, "generationConfiguration":{ "shape":"GenerationConfiguration", "documentation":"Contains configurations details for response generation based on retrieved text chunks.
" }, "orchestrationConfiguration":{ "shape":"OrchestrationConfiguration", "documentation":"Contains configuration details for the model to process the prompt prior to retrieval and response generation.
" } }, "documentation":"Contains configuration details for retrieving information from a knowledge base and generating responses.
" }, "KnowledgeBaseVectorSearchConfiguration":{ "type":"structure", "members":{ "numberOfResults":{ "shape":"KnowledgeBaseVectorSearchConfigurationNumberOfResultsInteger", "documentation":"The number of text chunks to retrieve; the number of results to return.
" }, "overrideSearchType":{ "shape":"SearchType", "documentation":"By default, Amazon Bedrock decides a search strategy for you. If you're using an Amazon OpenSearch Serverless vector store that contains a filterable text field, you can specify whether to query the knowledge base with a HYBRID search using both vector embeddings and raw text, or SEMANTIC search using only vector embeddings. For other vector store configurations, only SEMANTIC search is available.
Specifies the filters to use on the metadata fields in the knowledge base data sources before returning results.
" } }, "documentation":"The configuration details for returning the results from the knowledge base vector search.
" }, "KnowledgeBaseVectorSearchConfigurationNumberOfResultsInteger":{ "type":"integer", "box":true, "max":100, "min":1 }, "ListCustomModelsRequest":{ "type":"structure", "members":{ "creationTimeBefore":{ "shape":"Timestamp", "documentation":"Return custom models created before the specified time.
", "location":"querystring", "locationName":"creationTimeBefore" }, "creationTimeAfter":{ "shape":"Timestamp", "documentation":"Return custom models created after the specified time.
", "location":"querystring", "locationName":"creationTimeAfter" }, "nameContains":{ "shape":"CustomModelName", "documentation":"Return custom models only if the job name contains these characters.
", "location":"querystring", "locationName":"nameContains" }, "baseModelArnEquals":{ "shape":"ModelArn", "documentation":"Return custom models only if the base model Amazon Resource Name (ARN) matches this parameter.
", "location":"querystring", "locationName":"baseModelArnEquals" }, "foundationModelArnEquals":{ "shape":"FoundationModelArn", "documentation":"Return custom models only if the foundation model Amazon Resource Name (ARN) matches this parameter.
", "location":"querystring", "locationName":"foundationModelArnEquals" }, "maxResults":{ "shape":"MaxResults", "documentation":"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.
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.
The field to sort by in the returned list of models.
", "location":"querystring", "locationName":"sortBy" }, "sortOrder":{ "shape":"SortOrder", "documentation":"The sort order of the results.
", "location":"querystring", "locationName":"sortOrder" }, "isOwned":{ "shape":"Boolean", "documentation":"Return custom models depending on if the current account owns them (true) or if they were shared with the current account (false).
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.
" } } }, "ListEvaluationJobsRequest":{ "type":"structure", "members":{ "creationTimeAfter":{ "shape":"Timestamp", "documentation":"A filter to only list evaluation jobs created after a specified time.
", "location":"querystring", "locationName":"creationTimeAfter" }, "creationTimeBefore":{ "shape":"Timestamp", "documentation":"A filter to only list evaluation jobs created before a specified time.
", "location":"querystring", "locationName":"creationTimeBefore" }, "statusEquals":{ "shape":"EvaluationJobStatus", "documentation":"A filter to only list evaluation jobs that are of a certain status.
", "location":"querystring", "locationName":"statusEquals" }, "applicationTypeEquals":{ "shape":"ApplicationType", "documentation":"A filter to only list evaluation jobs that are either model evaluations or knowledge base evaluations.
", "location":"querystring", "locationName":"applicationTypeEquals" }, "nameContains":{ "shape":"EvaluationJobName", "documentation":"A filter to only list evaluation jobs that contain a specified string in the job name.
", "location":"querystring", "locationName":"nameContains" }, "maxResults":{ "shape":"MaxResults", "documentation":"The maximum number of results to return.
", "location":"querystring", "locationName":"maxResults" }, "nextToken":{ "shape":"PaginationToken", "documentation":"Continuation token from the previous response, for Amazon Bedrock to list the next set of results.
", "location":"querystring", "locationName":"nextToken" }, "sortBy":{ "shape":"SortJobsBy", "documentation":"Specifies a creation time to sort the list of evaluation jobs by when they were created.
", "location":"querystring", "locationName":"sortBy" }, "sortOrder":{ "shape":"SortOrder", "documentation":"Specifies whether to sort the list of evaluation jobs by either ascending or descending order.
", "location":"querystring", "locationName":"sortOrder" } } }, "ListEvaluationJobsResponse":{ "type":"structure", "members":{ "nextToken":{ "shape":"PaginationToken", "documentation":"Continuation token from the previous response, for Amazon Bedrock to list the next set of results.
" }, "jobSummaries":{ "shape":"EvaluationSummaries", "documentation":"A list of summaries of the evaluation jobs.
" } } }, "ListFoundationModelsRequest":{ "type":"structure", "members":{ "byProvider":{ "shape":"Provider", "documentation":"Return models belonging to the model provider that you specify.
", "location":"querystring", "locationName":"byProvider" }, "byCustomizationType":{ "shape":"ModelCustomization", "documentation":"Return models that support the customization type that you specify. For more information, see Custom models in the Amazon Bedrock User Guide.
", "location":"querystring", "locationName":"byCustomizationType" }, "byOutputModality":{ "shape":"ModelModality", "documentation":"Return models that support the output modality that you specify.
", "location":"querystring", "locationName":"byOutputModality" }, "byInferenceType":{ "shape":"InferenceType", "documentation":"Return models that support the inference type that you specify. For more information, see Provisioned Throughput in the Amazon Bedrock User Guide.
", "location":"querystring", "locationName":"byInferenceType" } } }, "ListFoundationModelsResponse":{ "type":"structure", "members":{ "modelSummaries":{ "shape":"FoundationModelSummaryList", "documentation":"A list of Amazon Bedrock foundation models.
" } } }, "ListGuardrailsRequest":{ "type":"structure", "members":{ "guardrailIdentifier":{ "shape":"GuardrailIdentifier", "documentation":"The unique identifier of the guardrail. This can be an ID or the ARN.
", "location":"querystring", "locationName":"guardrailIdentifier" }, "maxResults":{ "shape":"MaxResults", "documentation":"The maximum number of results to return in the response.
", "location":"querystring", "locationName":"maxResults" }, "nextToken":{ "shape":"PaginationToken", "documentation":"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.
A list of objects, each of which contains details about a guardrail.
" }, "nextToken":{ "shape":"PaginationToken", "documentation":"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.
Return imported models that created before the specified time.
", "location":"querystring", "locationName":"creationTimeBefore" }, "creationTimeAfter":{ "shape":"Timestamp", "documentation":"Return imported models that were created after the specified time.
", "location":"querystring", "locationName":"creationTimeAfter" }, "nameContains":{ "shape":"ImportedModelName", "documentation":"Return imported models only if the model name contains these characters.
", "location":"querystring", "locationName":"nameContains" }, "maxResults":{ "shape":"MaxResults", "documentation":"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.
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.
The field to sort by in the returned list of imported models.
", "location":"querystring", "locationName":"sortBy" }, "sortOrder":{ "shape":"SortOrder", "documentation":"Specifies whetehr to sort the results in ascending or descending order.
", "location":"querystring", "locationName":"sortOrder" } } }, "ListImportedModelsResponse":{ "type":"structure", "members":{ "nextToken":{ "shape":"PaginationToken", "documentation":"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.
" } } }, "ListInferenceProfilesRequest":{ "type":"structure", "members":{ "maxResults":{ "shape":"MaxResults", "documentation":"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.
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.
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.
A list of information about each inference profile that you can use.
" }, "nextToken":{ "shape":"PaginationToken", "documentation":"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.
The maximum number of results to return in a single call. If more results are available, the operation returns a NextToken value.
The token for the next set of results. You receive this token from a previous ListMarketplaceModelEndpoints call.
If specified, only endpoints for the given model source identifier are returned.
", "location":"querystring", "locationName":"modelSourceIdentifier" } } }, "ListMarketplaceModelEndpointsResponse":{ "type":"structure", "members":{ "marketplaceModelEndpoints":{ "shape":"MarketplaceModelEndpointSummaries", "documentation":"An array of endpoint summaries.
" }, "nextToken":{ "shape":"PaginationToken", "documentation":"The token for the next set of results. Use this token to get the next set of results.
" } } }, "ListModelCopyJobsRequest":{ "type":"structure", "members":{ "creationTimeAfter":{ "shape":"Timestamp", "documentation":"Filters for model copy jobs created after the specified time.
", "location":"querystring", "locationName":"creationTimeAfter" }, "creationTimeBefore":{ "shape":"Timestamp", "documentation":"Filters for model copy jobs created before the specified time.
", "location":"querystring", "locationName":"creationTimeBefore" }, "statusEquals":{ "shape":"ModelCopyJobStatus", "documentation":"Filters for model copy jobs whose status matches the value that you specify.
", "location":"querystring", "locationName":"statusEquals" }, "sourceAccountEquals":{ "shape":"AccountId", "documentation":"Filters for model copy jobs in which the account that the source model belongs to is equal to the value that you specify.
", "location":"querystring", "locationName":"sourceAccountEquals" }, "sourceModelArnEquals":{ "shape":"ModelArn", "documentation":"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.
", "location":"querystring", "locationName":"sourceModelArnEquals" }, "targetModelNameContains":{ "shape":"CustomModelName", "documentation":"Filters for model copy jobs in which the name of the copied model contains the string that you specify.
", "location":"querystring", "locationName":"outputModelNameContains" }, "maxResults":{ "shape":"MaxResults", "documentation":"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.
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.
The field to sort by in the returned list of model copy jobs.
", "location":"querystring", "locationName":"sortBy" }, "sortOrder":{ "shape":"SortOrder", "documentation":"Specifies whether to sort the results in ascending or descending order.
", "location":"querystring", "locationName":"sortOrder" } } }, "ListModelCopyJobsResponse":{ "type":"structure", "members":{ "nextToken":{ "shape":"PaginationToken", "documentation":"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.
A list of information about each model copy job.
" } } }, "ListModelCustomizationJobsRequest":{ "type":"structure", "members":{ "creationTimeAfter":{ "shape":"Timestamp", "documentation":"Return customization jobs created after the specified time.
", "location":"querystring", "locationName":"creationTimeAfter" }, "creationTimeBefore":{ "shape":"Timestamp", "documentation":"Return customization jobs created before the specified time.
", "location":"querystring", "locationName":"creationTimeBefore" }, "statusEquals":{ "shape":"FineTuningJobStatus", "documentation":"Return customization jobs with the specified status.
", "location":"querystring", "locationName":"statusEquals" }, "nameContains":{ "shape":"JobName", "documentation":"Return customization jobs only if the job name contains these characters.
", "location":"querystring", "locationName":"nameContains" }, "maxResults":{ "shape":"MaxResults", "documentation":"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.
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.
The field to sort by in the returned list of jobs.
", "location":"querystring", "locationName":"sortBy" }, "sortOrder":{ "shape":"SortOrder", "documentation":"The sort order of the results.
", "location":"querystring", "locationName":"sortOrder" } } }, "ListModelCustomizationJobsResponse":{ "type":"structure", "members":{ "nextToken":{ "shape":"PaginationToken", "documentation":"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.
Job summaries.
" } } }, "ListModelImportJobsRequest":{ "type":"structure", "members":{ "creationTimeAfter":{ "shape":"Timestamp", "documentation":"Return import jobs that were created after the specified time.
", "location":"querystring", "locationName":"creationTimeAfter" }, "creationTimeBefore":{ "shape":"Timestamp", "documentation":"Return import jobs that were created before the specified time.
", "location":"querystring", "locationName":"creationTimeBefore" }, "statusEquals":{ "shape":"ModelImportJobStatus", "documentation":"Return imported jobs with the specified status.
", "location":"querystring", "locationName":"statusEquals" }, "nameContains":{ "shape":"JobName", "documentation":"Return imported jobs only if the job name contains these characters.
", "location":"querystring", "locationName":"nameContains" }, "maxResults":{ "shape":"MaxResults", "documentation":"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.
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.
The field to sort by in the returned list of imported jobs.
", "location":"querystring", "locationName":"sortBy" }, "sortOrder":{ "shape":"SortOrder", "documentation":"Specifies whether to sort the results in ascending or descending order.
", "location":"querystring", "locationName":"sortOrder" } } }, "ListModelImportJobsResponse":{ "type":"structure", "members":{ "nextToken":{ "shape":"PaginationToken", "documentation":"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.
Import job summaries.
" } } }, "ListModelInvocationJobsRequest":{ "type":"structure", "members":{ "submitTimeAfter":{ "shape":"Timestamp", "documentation":"Specify a time to filter for batch inference jobs that were submitted after the time you specify.
", "location":"querystring", "locationName":"submitTimeAfter" }, "submitTimeBefore":{ "shape":"Timestamp", "documentation":"Specify a time to filter for batch inference jobs that were submitted before the time you specify.
", "location":"querystring", "locationName":"submitTimeBefore" }, "statusEquals":{ "shape":"ModelInvocationJobStatus", "documentation":"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 Services Support Center.
Stopped – This job was stopped by a user.
Stopping – This job is being stopped by a user.
Specify a string to filter for batch inference jobs whose names contain the string.
", "location":"querystring", "locationName":"nameContains" }, "maxResults":{ "shape":"MaxResults", "documentation":"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.
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.
An attribute by which to sort the results.
", "location":"querystring", "locationName":"sortBy" }, "sortOrder":{ "shape":"SortOrder", "documentation":"Specifies whether to sort the results by ascending or descending order.
", "location":"querystring", "locationName":"sortOrder" } } }, "ListModelInvocationJobsResponse":{ "type":"structure", "members":{ "nextToken":{ "shape":"PaginationToken", "documentation":"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.
A list of items, each of which contains a summary about a batch inference job.
" } } }, "ListPromptRoutersRequest":{ "type":"structure", "members":{ "maxResults":{ "shape":"MaxResults", "documentation":"The maximum number of prompt routers to return in one page of results.
", "location":"querystring", "locationName":"maxResults" }, "nextToken":{ "shape":"PaginationToken", "documentation":"Specify the pagination token from a previous request to retrieve the next page of results.
", "location":"querystring", "locationName":"nextToken" }, "type":{ "shape":"PromptRouterType", "documentation":"The type of the prompt routers, such as whether it's default or custom.
", "location":"querystring", "locationName":"type" } } }, "ListPromptRoutersResponse":{ "type":"structure", "members":{ "promptRouterSummaries":{ "shape":"PromptRouterSummaries", "documentation":"A list of prompt router summaries.
" }, "nextToken":{ "shape":"PaginationToken", "documentation":"Specify the pagination token from a previous request to retrieve the next page of results.
" } } }, "ListProvisionedModelThroughputsRequest":{ "type":"structure", "members":{ "creationTimeAfter":{ "shape":"Timestamp", "documentation":"A filter that returns Provisioned Throughputs created after the specified time.
", "location":"querystring", "locationName":"creationTimeAfter" }, "creationTimeBefore":{ "shape":"Timestamp", "documentation":"A filter that returns Provisioned Throughputs created before the specified time.
", "location":"querystring", "locationName":"creationTimeBefore" }, "statusEquals":{ "shape":"ProvisionedModelStatus", "documentation":"A filter that returns Provisioned Throughputs if their statuses matches the value that you specify.
", "location":"querystring", "locationName":"statusEquals" }, "modelArnEquals":{ "shape":"ModelArn", "documentation":"A filter that returns Provisioned Throughputs whose model Amazon Resource Name (ARN) is equal to the value that you specify.
", "location":"querystring", "locationName":"modelArnEquals" }, "nameContains":{ "shape":"ProvisionedModelName", "documentation":"A filter that returns Provisioned Throughputs if their name contains the expression that you specify.
", "location":"querystring", "locationName":"nameContains" }, "maxResults":{ "shape":"MaxResults", "documentation":"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.
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.
The field by which to sort the returned list of Provisioned Throughputs.
", "location":"querystring", "locationName":"sortBy" }, "sortOrder":{ "shape":"SortOrder", "documentation":"The sort order of the results.
", "location":"querystring", "locationName":"sortOrder" } } }, "ListProvisionedModelThroughputsResponse":{ "type":"structure", "members":{ "nextToken":{ "shape":"PaginationToken", "documentation":"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.
A list of summaries, one for each Provisioned Throughput in the response.
" } } }, "ListTagsForResourceRequest":{ "type":"structure", "required":["resourceARN"], "members":{ "resourceARN":{ "shape":"TaggableResourcesArn", "documentation":"The Amazon Resource Name (ARN) of the resource.
" } } }, "ListTagsForResourceResponse":{ "type":"structure", "members":{ "tags":{ "shape":"TagList", "documentation":"An array of the tags associated with this resource.
" } } }, "LogGroupName":{ "type":"string", "max":512, "min":1 }, "LoggingConfig":{ "type":"structure", "members":{ "cloudWatchConfig":{ "shape":"CloudWatchConfig", "documentation":"CloudWatch logging configuration.
" }, "s3Config":{ "shape":"S3Config", "documentation":"S3 configuration for storing log data.
" }, "textDataDeliveryEnabled":{ "shape":"Boolean", "documentation":"Set to include text data in the log delivery.
" }, "imageDataDeliveryEnabled":{ "shape":"Boolean", "documentation":"Set to include image data in the log delivery.
" }, "embeddingDataDeliveryEnabled":{ "shape":"Boolean", "documentation":"Set to include embeddings data in the log delivery.
" }, "videoDataDeliveryEnabled":{ "shape":"Boolean", "documentation":"Set to include video data in the log delivery.
" } }, "documentation":"Configuration fields for invocation logging.
" }, "MarketplaceModelEndpoint":{ "type":"structure", "required":[ "endpointArn", "modelSourceIdentifier", "createdAt", "updatedAt", "endpointConfig", "endpointStatus" ], "members":{ "endpointArn":{ "shape":"Arn", "documentation":"The Amazon Resource Name (ARN) of the endpoint.
" }, "modelSourceIdentifier":{ "shape":"ModelSourceIdentifier", "documentation":"The ARN of the model from Amazon Bedrock Marketplace that is deployed on this endpoint.
" }, "status":{ "shape":"Status", "documentation":"The overall status of the endpoint in Amazon Bedrock Marketplace (e.g., ACTIVE, INACTIVE).
" }, "statusMessage":{ "shape":"String", "documentation":"Additional information about the overall status, if available.
" }, "createdAt":{ "shape":"Timestamp", "documentation":"The timestamp when the endpoint was registered.
" }, "updatedAt":{ "shape":"Timestamp", "documentation":"The timestamp when the endpoint was last updated.
" }, "endpointConfig":{ "shape":"EndpointConfig", "documentation":"The configuration of the endpoint, including the number and type of instances used.
" }, "endpointStatus":{ "shape":"String", "documentation":"The current status of the endpoint (e.g., Creating, InService, Updating, Failed).
" }, "endpointStatusMessage":{ "shape":"String", "documentation":"Additional information about the endpoint status, if available.
" } }, "documentation":"Contains details about an endpoint for a model from Amazon Bedrock Marketplace.
" }, "MarketplaceModelEndpointSummaries":{ "type":"list", "member":{"shape":"MarketplaceModelEndpointSummary"}, "max":1000, "min":0 }, "MarketplaceModelEndpointSummary":{ "type":"structure", "required":[ "endpointArn", "modelSourceIdentifier", "createdAt", "updatedAt" ], "members":{ "endpointArn":{ "shape":"Arn", "documentation":"The Amazon Resource Name (ARN) of the endpoint.
" }, "modelSourceIdentifier":{ "shape":"ModelSourceIdentifier", "documentation":"The ARN of the model from Amazon Bedrock Marketplace that is deployed on this endpoint.
" }, "status":{ "shape":"Status", "documentation":"The overall status of the endpoint in Amazon Bedrock Marketplace.
" }, "statusMessage":{ "shape":"String", "documentation":"Additional information about the overall status, if available.
" }, "createdAt":{ "shape":"Timestamp", "documentation":"The timestamp when the endpoint was created.
" }, "updatedAt":{ "shape":"Timestamp", "documentation":"The timestamp when the endpoint was last updated.
" } }, "documentation":"Provides a summary of an endpoint for a model from Amazon Bedrock Marketplace.
" }, "MaxResults":{ "type":"integer", "box":true, "max":1000, "min":1 }, "MaxTokens":{ "type":"integer", "box":true, "max":65536, "min":0 }, "Message":{ "type":"string", "max":2048, "min":0, "sensitive":true }, "MetricFloat":{ "type":"float", "box":true }, "ModelArchitecture":{"type":"string"}, "ModelArn":{ "type":"string", "max":1011, "min":20, "pattern":"arn:aws(-[^:]+)?:bedrock:[a-z0-9-]{1,20}:(([0-9]{12}:custom-model/[a-z0-9-]{1,63}[.]{1}[a-z0-9-]{1,63}/[a-z0-9]{12})|(:foundation-model/[a-z0-9-]{1,63}[.]{1}([a-z0-9-]{1,63}[.]){0,2}[a-z0-9-]{1,63}([:][a-z0-9-]{1,63}){0,2}))" }, "ModelCopyJobArn":{ "type":"string", "max":1011, "min":0, "pattern":"arn:aws(-[^:]+)?:bedrock:[a-z0-9-]{1,20}:[0-9]{12}:model-copy-job/[a-z0-9]{12}" }, "ModelCopyJobStatus":{ "type":"string", "enum":[ "InProgress", "Completed", "Failed" ] }, "ModelCopyJobSummaries":{ "type":"list", "member":{"shape":"ModelCopyJobSummary"} }, "ModelCopyJobSummary":{ "type":"structure", "required":[ "jobArn", "status", "creationTime", "targetModelArn", "sourceAccountId", "sourceModelArn" ], "members":{ "jobArn":{ "shape":"ModelCopyJobArn", "documentation":"The Amazon Resoource Name (ARN) of the model copy job.
" }, "status":{ "shape":"ModelCopyJobStatus", "documentation":"The status of the model copy job.
" }, "creationTime":{ "shape":"Timestamp", "documentation":"The time that the model copy job was created.
" }, "targetModelArn":{ "shape":"CustomModelArn", "documentation":"The Amazon Resource Name (ARN) of the copied model.
" }, "targetModelName":{ "shape":"CustomModelName", "documentation":"The name of the copied model.
" }, "sourceAccountId":{ "shape":"AccountId", "documentation":"The unique identifier of the account that the model being copied originated from.
" }, "sourceModelArn":{ "shape":"ModelArn", "documentation":"The Amazon Resource Name (ARN) of the original model being copied.
" }, "targetModelKmsKeyArn":{ "shape":"KmsKeyArn", "documentation":"The Amazon Resource Name (ARN) of the KMS key used to encrypt the copied model.
" }, "targetModelTags":{ "shape":"TagList", "documentation":"Tags associated with the copied model.
" }, "failureMessage":{ "shape":"ErrorMessage", "documentation":"If a model fails to be copied, a message describing why the job failed is included here.
" }, "sourceModelName":{ "shape":"CustomModelName", "documentation":"The name of the original model being copied.
" } }, "documentation":"Contains details about each model copy job.
This data type is used in the following API operations:
" }, "ModelCustomization":{ "type":"string", "enum":[ "FINE_TUNING", "CONTINUED_PRE_TRAINING", "DISTILLATION" ] }, "ModelCustomizationHyperParameters":{ "type":"map", "key":{"shape":"String"}, "value":{"shape":"String"} }, "ModelCustomizationJobArn":{ "type":"string", "max":1011, "min":0, "pattern":"arn:aws(-[^:]+)?:bedrock:[a-z0-9-]{1,20}:[0-9]{12}:model-customization-job/[a-z0-9-]{1,63}[.]{1}[a-z0-9-]{1,63}([a-z0-9-]{1,63}[.]){0,2}[a-z0-9-]{1,63}([:][a-z0-9-]{1,63}){0,2}/[a-z0-9]{12}" }, "ModelCustomizationJobIdentifier":{ "type":"string", "max":1011, "min":0, "pattern":"(arn:aws(-[^:]+)?:bedrock:[a-z0-9-]{1,20}:[0-9]{12}:model-customization-job/[a-z0-9-]{1,63}[.]{1}[a-z0-9-]{1,63}([a-z0-9-]{1,63}[.]){0,2}[a-z0-9-]{1,63}([:][a-z0-9-]{1,63}){0,2}/[a-z0-9]{12})|([a-zA-Z0-9](-*[a-zA-Z0-9\\+\\-\\.])*)" }, "ModelCustomizationJobStatus":{ "type":"string", "enum":[ "InProgress", "Completed", "Failed", "Stopping", "Stopped" ] }, "ModelCustomizationJobSummaries":{ "type":"list", "member":{"shape":"ModelCustomizationJobSummary"} }, "ModelCustomizationJobSummary":{ "type":"structure", "required":[ "jobArn", "baseModelArn", "jobName", "status", "creationTime" ], "members":{ "jobArn":{ "shape":"ModelCustomizationJobArn", "documentation":"Amazon Resource Name (ARN) of the customization job.
" }, "baseModelArn":{ "shape":"ModelArn", "documentation":"Amazon Resource Name (ARN) of the base model.
" }, "jobName":{ "shape":"JobName", "documentation":"Name of the customization job.
" }, "status":{ "shape":"ModelCustomizationJobStatus", "documentation":"Status of the customization job.
" }, "lastModifiedTime":{ "shape":"Timestamp", "documentation":"Time that the customization job was last modified.
" }, "creationTime":{ "shape":"Timestamp", "documentation":"Creation time of the custom model.
" }, "endTime":{ "shape":"Timestamp", "documentation":"Time that the customization job ended.
" }, "customModelArn":{ "shape":"CustomModelArn", "documentation":"Amazon Resource Name (ARN) of the custom model.
" }, "customModelName":{ "shape":"CustomModelName", "documentation":"Name of the custom model.
" }, "customizationType":{ "shape":"CustomizationType", "documentation":"Specifies whether to carry out continued pre-training of a model or whether to fine-tune it. For more information, see Custom models.
" } }, "documentation":"Information about one customization job
" }, "ModelCustomizationList":{ "type":"list", "member":{"shape":"ModelCustomization"} }, "ModelDataSource":{ "type":"structure", "members":{ "s3DataSource":{ "shape":"S3DataSource", "documentation":"The Amazon S3 data source of the imported model.
" } }, "documentation":"Data source for the imported model.
", "union":true }, "ModelId":{ "type":"string", "max":2048, "min":1, "pattern":"(arn:aws(-[^:]+)?:bedrock:[a-z0-9-]{1,20}:(([0-9]{12}:custom-model/[a-z0-9-]{1,63}[.]{1}[a-z0-9-:]{1,63}/[a-z0-9]{12}$)|(:foundation-model/[a-z0-9-]{1,63}[.]{1}[a-z0-9-]{1,63}$)))|([a-z0-9-]{1,63}[.]{1}[a-z0-9-]{1,63}([.]?[a-z0-9-]{1,63})([:][a-z0-9-]{1,63}){0,2})|(([0-9a-zA-Z][_-]?)+)" }, "ModelIdentifier":{ "type":"string", "max":2048, "min":1, "pattern":"arn:aws(-[^:]+)?:bedrock:[a-z0-9-]{1,20}:(([0-9]{12}:custom-model/[a-z0-9-]{1,63}[.]{1}[a-z0-9-]{1,63}(([:][a-z0-9-]{1,63}){0,2})?/[a-z0-9]{12})|(:foundation-model/([a-z0-9-]{1,63}[.]{1}[a-z0-9-]{1,63}([.]?[a-z0-9-]{1,63})([:][a-z0-9-]{1,63}){0,2})))|(([a-z0-9-]{1,63}[.]{1}[a-z0-9-]{1,63}([.]?[a-z0-9-]{1,63})([:][a-z0-9-]{1,63}){0,2}))|(([0-9a-zA-Z][_-]?)+)" }, "ModelImportJobArn":{ "type":"string", "max":1011, "min":0, "pattern":"arn:aws(-[^:]+)?:bedrock:[a-z0-9-]{1,20}:[0-9]{12}:model-import-job/[a-z0-9]{12}" }, "ModelImportJobIdentifier":{ "type":"string", "max":1011, "min":0, "pattern":"(arn:aws(-[^:]+)?:bedrock:[a-z0-9-]{1,20}:[0-9]{12}:model-import-job/[a-z0-9]{12})|([a-zA-Z0-9](-*[a-zA-Z0-9\\+\\-\\.])*)" }, "ModelImportJobStatus":{ "type":"string", "enum":[ "InProgress", "Completed", "Failed" ] }, "ModelImportJobSummaries":{ "type":"list", "member":{"shape":"ModelImportJobSummary"} }, "ModelImportJobSummary":{ "type":"structure", "required":[ "jobArn", "jobName", "status", "creationTime" ], "members":{ "jobArn":{ "shape":"ModelImportJobArn", "documentation":"The Amazon Resource Name (ARN) of the import job.
" }, "jobName":{ "shape":"JobName", "documentation":"The name of the import job.
" }, "status":{ "shape":"ModelImportJobStatus", "documentation":"The status of the imported job.
" }, "lastModifiedTime":{ "shape":"Timestamp", "documentation":"The time when the import job was last modified.
" }, "creationTime":{ "shape":"Timestamp", "documentation":"The time import job was created.
" }, "endTime":{ "shape":"Timestamp", "documentation":"The time when import job ended.
" }, "importedModelArn":{ "shape":"ImportedModelArn", "documentation":"The Amazon resource Name (ARN) of the imported model.
" }, "importedModelName":{ "shape":"ImportedModelName", "documentation":"The name of the imported model.
" } }, "documentation":"Information about the import job.
" }, "ModelInvocationIdempotencyToken":{ "type":"string", "max":256, "min":1, "pattern":"[a-zA-Z0-9]{1,256}(-*[a-zA-Z0-9]){0,256}" }, "ModelInvocationJobArn":{ "type":"string", "max":1011, "min":0, "pattern":"(arn:aws(-[^:]+)?:bedrock:[a-z0-9-]{1,20}:[0-9]{12}:model-invocation-job/[a-z0-9]{12})" }, "ModelInvocationJobIdentifier":{ "type":"string", "max":1011, "min":0, "pattern":"((arn:aws(-[^:]+)?:bedrock:[a-z0-9-]{1,20}:[0-9]{12}:model-invocation-job/)?[a-z0-9]{12})" }, "ModelInvocationJobInputDataConfig":{ "type":"structure", "members":{ "s3InputDataConfig":{ "shape":"ModelInvocationJobS3InputDataConfig", "documentation":"Contains the configuration of the S3 location of the input data.
" } }, "documentation":"Details about the location of the input to the batch inference job.
", "union":true }, "ModelInvocationJobName":{ "type":"string", "max":63, "min":1, "pattern":"[a-zA-Z0-9]{1,63}(-*[a-zA-Z0-9\\+\\-\\.]){0,63}" }, "ModelInvocationJobOutputDataConfig":{ "type":"structure", "members":{ "s3OutputDataConfig":{ "shape":"ModelInvocationJobS3OutputDataConfig", "documentation":"Contains the configuration of the S3 location of the output data.
" } }, "documentation":"Contains the configuration of the S3 location of the output data.
", "union":true }, "ModelInvocationJobS3InputDataConfig":{ "type":"structure", "required":["s3Uri"], "members":{ "s3InputFormat":{ "shape":"S3InputFormat", "documentation":"The format of the input data.
" }, "s3Uri":{ "shape":"S3Uri", "documentation":"The S3 location of the input data.
" }, "s3BucketOwner":{ "shape":"AccountId", "documentation":"The ID of the Amazon Web Services account that owns the S3 bucket containing the input data.
" } }, "documentation":"Contains the configuration of the S3 location of the input data.
" }, "ModelInvocationJobS3OutputDataConfig":{ "type":"structure", "required":["s3Uri"], "members":{ "s3Uri":{ "shape":"S3Uri", "documentation":"The S3 location of the output data.
" }, "s3EncryptionKeyId":{ "shape":"KmsKeyId", "documentation":"The unique identifier of the key that encrypts the S3 location of the output data.
" }, "s3BucketOwner":{ "shape":"AccountId", "documentation":"The ID of the Amazon Web Services account that owns the S3 bucket containing the output data.
" } }, "documentation":"Contains the configuration of the S3 location of the output data.
" }, "ModelInvocationJobStatus":{ "type":"string", "enum":[ "Submitted", "InProgress", "Completed", "Failed", "Stopping", "Stopped", "PartiallyCompleted", "Expired", "Validating", "Scheduled" ] }, "ModelInvocationJobSummaries":{ "type":"list", "member":{"shape":"ModelInvocationJobSummary"} }, "ModelInvocationJobSummary":{ "type":"structure", "required":[ "jobArn", "jobName", "modelId", "roleArn", "submitTime", "inputDataConfig", "outputDataConfig" ], "members":{ "jobArn":{ "shape":"ModelInvocationJobArn", "documentation":"The Amazon Resource Name (ARN) of the batch inference job.
" }, "jobName":{ "shape":"ModelInvocationJobName", "documentation":"The name of the batch inference job.
" }, "modelId":{ "shape":"ModelId", "documentation":"The unique identifier of the foundation model used for model inference.
" }, "clientRequestToken":{ "shape":"ModelInvocationIdempotencyToken", "documentation":"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.
" }, "roleArn":{ "shape":"RoleArn", "documentation":"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":{ "shape":"ModelInvocationJobStatus", "documentation":"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 Services Support Center.
Stopped – This job was stopped by a user.
Stopping – This job is being stopped by a user.
If the batch inference job failed, this field contains a message describing why the job failed.
" }, "submitTime":{ "shape":"Timestamp", "documentation":"The time at which the batch inference job was submitted.
" }, "lastModifiedTime":{ "shape":"Timestamp", "documentation":"The time at which the batch inference job was last modified.
" }, "endTime":{ "shape":"Timestamp", "documentation":"The time at which the batch inference job ended.
" }, "inputDataConfig":{ "shape":"ModelInvocationJobInputDataConfig", "documentation":"Details about the location of the input to the batch inference job.
" }, "outputDataConfig":{ "shape":"ModelInvocationJobOutputDataConfig", "documentation":"Details about the location of the output of the batch inference job.
" }, "vpcConfig":{ "shape":"VpcConfig", "documentation":"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.
" }, "timeoutDurationInHours":{ "shape":"ModelInvocationJobTimeoutDurationInHours", "documentation":"The number of hours after which the batch inference job was set to time out.
" }, "jobExpirationTime":{ "shape":"Timestamp", "documentation":"The time at which the batch inference job times or timed out.
" } }, "documentation":"A summary of a batch inference job.
" }, "ModelInvocationJobTimeoutDurationInHours":{ "type":"integer", "box":true, "max":168, "min":24 }, "ModelModality":{ "type":"string", "enum":[ "TEXT", "IMAGE", "EMBEDDING" ] }, "ModelModalityList":{ "type":"list", "member":{"shape":"ModelModality"} }, "ModelName":{ "type":"string", "max":63, "min":1, "pattern":"([a-z0-9-]{1,63}[.]{1}[a-z0-9-]{1,63})" }, "ModelSourceIdentifier":{ "type":"string", "max":2048, "min":0, "pattern":".*arn:aws:sagemaker:.*:hub-content/SageMakerPublicHub/Model/.*" }, "NonBlankString":{ "type":"string", "pattern":"[\\s\\S]*" }, "OrchestrationConfiguration":{ "type":"structure", "required":["queryTransformationConfiguration"], "members":{ "queryTransformationConfiguration":{ "shape":"QueryTransformationConfiguration", "documentation":"Contains configuration details for transforming the prompt.
" } }, "documentation":"The configuration details for the model to process the prompt prior to retrieval and response generation.
" }, "OutputDataConfig":{ "type":"structure", "required":["s3Uri"], "members":{ "s3Uri":{ "shape":"S3Uri", "documentation":"The S3 URI where the output data is stored.
" } }, "documentation":"S3 Location of the output data.
" }, "PaginationToken":{ "type":"string", "max":2048, "min":1, "pattern":"\\S*" }, "PerformanceConfigLatency":{ "type":"string", "enum":[ "standard", "optimized" ] }, "PerformanceConfiguration":{ "type":"structure", "members":{ "latency":{ "shape":"PerformanceConfigLatency", "documentation":"Specifies whether to use the latency-optimized or standard version of a model or inference profile.
" } }, "documentation":"Contains performance settings for a model.
" }, "PositiveInteger":{ "type":"integer", "box":true, "min":1 }, "PromptRouterArn":{ "type":"string", "max":2048, "min":1, "pattern":"arn:aws(-[^:]+)?:bedrock:[a-z0-9-]{1,20}:[0-9]{12}:default-prompt-router/[a-zA-Z0-9-:.]+" }, "PromptRouterDescription":{ "type":"string", "max":200, "min":1, "pattern":"([0-9a-zA-Z:.][ _-]?)+", "sensitive":true }, "PromptRouterName":{ "type":"string", "max":64, "min":1, "pattern":"([0-9a-zA-Z][ _-]?)+" }, "PromptRouterStatus":{ "type":"string", "enum":["AVAILABLE"] }, "PromptRouterSummaries":{ "type":"list", "member":{"shape":"PromptRouterSummary"} }, "PromptRouterSummary":{ "type":"structure", "required":[ "promptRouterName", "routingCriteria", "promptRouterArn", "models", "fallbackModel", "status", "type" ], "members":{ "promptRouterName":{ "shape":"PromptRouterName", "documentation":"The router's name.
" }, "routingCriteria":{ "shape":"RoutingCriteria", "documentation":"The router's routing criteria.
" }, "description":{ "shape":"PromptRouterDescription", "documentation":"The router's description.
" }, "createdAt":{ "shape":"Timestamp", "documentation":"When the router was created.
" }, "updatedAt":{ "shape":"Timestamp", "documentation":"When the router was updated.
" }, "promptRouterArn":{ "shape":"PromptRouterArn", "documentation":"The router's ARN.
" }, "models":{ "shape":"PromptRouterTargetModels", "documentation":"The router's models.
" }, "fallbackModel":{ "shape":"PromptRouterTargetModel", "documentation":"The router's fallback model.
" }, "status":{ "shape":"PromptRouterStatus", "documentation":"The router's status.
" }, "type":{ "shape":"PromptRouterType", "documentation":"The summary's type.
" } }, "documentation":"Details about a prompt router.
" }, "PromptRouterTargetModel":{ "type":"structure", "required":["modelArn"], "members":{ "modelArn":{ "shape":"PromptRouterTargetModelArn", "documentation":"The target model's ARN.
" } }, "documentation":"The target model for a prompt router.
" }, "PromptRouterTargetModelArn":{ "type":"string", "max":2048, "min":1, "pattern":".*(^arn:aws(-[^:]+)?:bedrock:[a-z0-9-]{1,20}::foundation-model/[a-z0-9-]{1,63}[.]{1}([a-z0-9-]{1,63}[.]){0,2}[a-z0-9-]{1,63}([:][a-z0-9-]{1,63}){0,2})|(^arn:aws(|-us-gov|-cn|-iso|-iso-b):bedrock:(|[0-9a-z-]{0,20}):(|[0-9]{12}):(inference-profile|application-inference-profile)/[a-zA-Z0-9-:.]+)" }, "PromptRouterTargetModels":{ "type":"list", "member":{"shape":"PromptRouterTargetModel"} }, "PromptRouterType":{ "type":"string", "enum":[ "custom", "default" ] }, "PromptTemplate":{ "type":"structure", "members":{ "textPromptTemplate":{ "shape":"TextPromptTemplate", "documentation":"The template for the prompt that's sent to the model for response generation. You can include prompt placeholders, which become replaced before the prompt is sent to the model to provide instructions and context to the model. In addition, you can include XML tags to delineate meaningful sections of the prompt template.
For more information, see Knowledge base prompt template and Use XML tags with Anthropic Claude models.
" } }, "documentation":"The template for the prompt that's sent to the model for response generation.
" }, "Provider":{ "type":"string", "pattern":"[A-Za-z0-9- ]{1,63}" }, "ProvisionedModelArn":{ "type":"string", "pattern":"arn:aws(-[^:]+)?:bedrock:[a-z0-9-]{1,20}:[0-9]{12}:provisioned-model/[a-z0-9]{12}" }, "ProvisionedModelId":{ "type":"string", "pattern":"((([0-9a-zA-Z][_-]?)+)|(arn:aws(-[^:]+)?:bedrock:[a-z0-9-]{1,20}:[0-9]{12}:provisioned-model/[a-z0-9]{12}))" }, "ProvisionedModelName":{ "type":"string", "max":63, "min":1, "pattern":"([0-9a-zA-Z][_-]?)+" }, "ProvisionedModelStatus":{ "type":"string", "enum":[ "Creating", "InService", "Updating", "Failed" ] }, "ProvisionedModelSummaries":{ "type":"list", "member":{"shape":"ProvisionedModelSummary"} }, "ProvisionedModelSummary":{ "type":"structure", "required":[ "provisionedModelName", "provisionedModelArn", "modelArn", "desiredModelArn", "foundationModelArn", "modelUnits", "desiredModelUnits", "status", "creationTime", "lastModifiedTime" ], "members":{ "provisionedModelName":{ "shape":"ProvisionedModelName", "documentation":"The name of the Provisioned Throughput.
" }, "provisionedModelArn":{ "shape":"ProvisionedModelArn", "documentation":"The Amazon Resource Name (ARN) of the Provisioned Throughput.
" }, "modelArn":{ "shape":"ModelArn", "documentation":"The Amazon Resource Name (ARN) of the model associated with the Provisioned Throughput.
" }, "desiredModelArn":{ "shape":"ModelArn", "documentation":"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.
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.
" }, "modelUnits":{ "shape":"PositiveInteger", "documentation":"The number of model units allocated to the Provisioned Throughput.
" }, "desiredModelUnits":{ "shape":"PositiveInteger", "documentation":"The number of model units that was requested to be allocated to the Provisioned Throughput.
" }, "status":{ "shape":"ProvisionedModelStatus", "documentation":"The status of the Provisioned Throughput.
" }, "commitmentDuration":{ "shape":"CommitmentDuration", "documentation":"The duration for which the Provisioned Throughput was committed.
" }, "commitmentExpirationTime":{ "shape":"Timestamp", "documentation":"The timestamp for when the commitment term of the Provisioned Throughput expires.
" }, "creationTime":{ "shape":"Timestamp", "documentation":"The time that the Provisioned Throughput was created.
" }, "lastModifiedTime":{ "shape":"Timestamp", "documentation":"The time that the Provisioned Throughput was last modified.
" } }, "documentation":"A summary of information about a Provisioned Throughput.
This data type is used in the following API operations:
" }, "PutModelInvocationLoggingConfigurationRequest":{ "type":"structure", "required":["loggingConfig"], "members":{ "loggingConfig":{ "shape":"LoggingConfig", "documentation":"The logging configuration values to set.
" } } }, "PutModelInvocationLoggingConfigurationResponse":{ "type":"structure", "members":{ } }, "QueryTransformationConfiguration":{ "type":"structure", "required":["type"], "members":{ "type":{ "shape":"QueryTransformationType", "documentation":"The type of transformation to apply to the prompt.
" } }, "documentation":"The configuration details for transforming the prompt.
" }, "QueryTransformationType":{ "type":"string", "enum":["QUERY_DECOMPOSITION"] }, "RAGConfig":{ "type":"structure", "members":{ "knowledgeBaseConfig":{ "shape":"KnowledgeBaseConfig", "documentation":"Contains configuration details for knowledge base retrieval and response generation.
" } }, "documentation":"Contains configuration details for retrieval of information and response generation.
", "union":true }, "RAGIdentifiers":{ "type":"list", "member":{"shape":"KnowledgeBaseId"}, "max":1, "min":0 }, "RAGStopSequences":{ "type":"list", "member":{"shape":"RAGStopSequencesMemberString"}, "max":4, "min":0 }, "RAGStopSequencesMemberString":{ "type":"string", "max":1000, "min":1 }, "RagConfigs":{ "type":"list", "member":{"shape":"RAGConfig"}, "max":1, "min":1 }, "RegisterMarketplaceModelEndpointRequest":{ "type":"structure", "required":[ "endpointIdentifier", "modelSourceIdentifier" ], "members":{ "endpointIdentifier":{ "shape":"Arn", "documentation":"The ARN of the Amazon SageMaker endpoint you want to register with Amazon Bedrock Marketplace.
", "location":"uri", "locationName":"endpointIdentifier" }, "modelSourceIdentifier":{ "shape":"ModelSourceIdentifier", "documentation":"The ARN of the model from Amazon Bedrock Marketplace that is deployed on the endpoint.
" } } }, "RegisterMarketplaceModelEndpointResponse":{ "type":"structure", "required":["marketplaceModelEndpoint"], "members":{ "marketplaceModelEndpoint":{ "shape":"MarketplaceModelEndpoint", "documentation":"Details about the registered endpoint.
" } } }, "RequestMetadataBaseFilters":{ "type":"structure", "members":{ "equals":{ "shape":"RequestMetadataMap", "documentation":"Include results where the key equals the value.
" }, "notEquals":{ "shape":"RequestMetadataMap", "documentation":"Include results where the key does not equal the value.
" } }, "documentation":"A mapping of a metadata key to a value that it should or should not equal.
" }, "RequestMetadataFilters":{ "type":"structure", "members":{ "equals":{ "shape":"RequestMetadataMap", "documentation":"Include results where the key equals the value.
" }, "notEquals":{ "shape":"RequestMetadataMap", "documentation":"Include results where the key does not equal the value.
" }, "andAll":{ "shape":"RequestMetadataFiltersList", "documentation":"Include results where all of the based filters match.
" }, "orAll":{ "shape":"RequestMetadataFiltersList", "documentation":"Include results where any of the base filters match.
" } }, "documentation":"Rules for filtering invocation logs. A filter can be a mapping of a metadata key to a value that it should or should not equal (a base filter), or a list of base filters that are all applied with AND or OR logical operators
The specified resource Amazon Resource Name (ARN) was not found. Check the Amazon Resource Name (ARN) and try your request again.
", "error":{ "httpStatusCode":404, "senderFault":true }, "exception":true }, "RetrievalFilter":{ "type":"structure", "members":{ "equals":{ "shape":"FilterAttribute", "documentation":"Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value matches the value in this object.
The following example would return data sources with an animal attribute whose value is 'cat': \"equals\": { \"key\": \"animal\", \"value\": \"cat\" }
Knowledge base data sources that contain a metadata attribute whose name matches the key and whose value doesn't match the value in this object are returned.
The following example would return data sources that don't contain an animal attribute whose value is 'cat': \"notEquals\": { \"key\": \"animal\", \"value\": \"cat\" }
Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value is greater than the value in this object.
The following example would return data sources with an year attribute whose value is greater than '1989': \"greaterThan\": { \"key\": \"year\", \"value\": 1989 }
Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value is greater than or equal to the value in this object.
The following example would return data sources with an year attribute whose value is greater than or equal to '1989': \"greaterThanOrEquals\": { \"key\": \"year\", \"value\": 1989 }
Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value is less than the value in this object.
The following example would return data sources with an year attribute whose value is less than to '1989': \"lessThan\": { \"key\": \"year\", \"value\": 1989 }
Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value is less than or equal to the value in this object.
The following example would return data sources with an year attribute whose value is less than or equal to '1989': \"lessThanOrEquals\": { \"key\": \"year\", \"value\": 1989 }
Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value is in the list specified in the value in this object.
The following example would return data sources with an animal attribute that is either 'cat' or 'dog': \"in\": { \"key\": \"animal\", \"value\": [\"cat\", \"dog\"] }
Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value isn't in the list specified in the value in this object.
The following example would return data sources whose animal attribute is neither 'cat' nor 'dog': \"notIn\": { \"key\": \"animal\", \"value\": [\"cat\", \"dog\"] }
Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value starts with the value in this object. This filter is currently only supported for Amazon OpenSearch Serverless vector stores.
The following example would return data sources with an animal attribute starts with 'ca' (for example, 'cat' or 'camel'). \"startsWith\": { \"key\": \"animal\", \"value\": \"ca\" }
Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value is a list that contains the value as one of its members.
The following example would return data sources with an animals attribute that is a list containing a cat member (for example, [\"dog\", \"cat\"]): \"listContains\": { \"key\": \"animals\", \"value\": \"cat\" }
Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value is one of the following:
A string that contains the value as a substring. The following example would return data sources with an animal attribute that contains the substring at (for example, 'cat'): \"stringContains\": { \"key\": \"animal\", \"value\": \"at\" }
A list with a member that contains the value as a substring. The following example would return data sources with an animals attribute that is a list containing a member that contains the substring at (for example, [\"dog\", \"cat\"]): \"stringContains\": { \"key\": \"animals\", \"value\": \"at\" }
Knowledge base data sources are returned if their metadata attributes fulfill all the filter conditions inside this list.
" }, "orAll":{ "shape":"RetrievalFilterList", "documentation":"Knowledge base data sources are returned if their metadata attributes fulfill at least one of the filter conditions inside this list.
" } }, "documentation":"Specifies the filters to use on the metadata attributes/fields in the knowledge base data sources before returning results.
", "sensitive":true, "union":true }, "RetrievalFilterList":{ "type":"list", "member":{"shape":"RetrievalFilter"}, "min":2 }, "RetrieveAndGenerateConfiguration":{ "type":"structure", "required":["type"], "members":{ "type":{ "shape":"RetrieveAndGenerateType", "documentation":"The type of resource that contains your data for retrieving information and generating responses.
If you choose to use EXTERNAL_SOURCES, then currently only Claude 3 Sonnet models for knowledge bases are supported.
Contains configuration details for the knowledge base retrieval and response generation.
" }, "externalSourcesConfiguration":{ "shape":"ExternalSourcesRetrieveAndGenerateConfiguration", "documentation":"The configuration for the external source wrapper object in the retrieveAndGenerate function.
Contains configuration details for a knowledge base retrieval and response generation.
" }, "RetrieveAndGenerateType":{ "type":"string", "enum":[ "KNOWLEDGE_BASE", "EXTERNAL_SOURCES" ] }, "RetrieveConfig":{ "type":"structure", "required":[ "knowledgeBaseId", "knowledgeBaseRetrievalConfiguration" ], "members":{ "knowledgeBaseId":{ "shape":"KnowledgeBaseId", "documentation":"The unique identifier of the knowledge base.
" }, "knowledgeBaseRetrievalConfiguration":{ "shape":"KnowledgeBaseRetrievalConfiguration", "documentation":"Contains configuration details for knowledge base retrieval.
" } }, "documentation":"The configuration details for retrieving information from a knowledge base.
" }, "RoleArn":{ "type":"string", "documentation":"ARN of a IAM role
", "max":2048, "min":0, "pattern":"arn:aws(-[^:]+)?:iam::([0-9]{12})?:role/.+" }, "RoutingCriteria":{ "type":"structure", "required":["responseQualityDifference"], "members":{ "responseQualityDifference":{ "shape":"RoutingCriteriaResponseQualityDifferenceDouble", "documentation":"The criteria's response quality difference.
" } }, "documentation":"Routing criteria for a prompt router.
" }, "RoutingCriteriaResponseQualityDifferenceDouble":{ "type":"double", "box":true, "max":100, "min":0 }, "S3Config":{ "type":"structure", "required":["bucketName"], "members":{ "bucketName":{ "shape":"BucketName", "documentation":"S3 bucket name.
" }, "keyPrefix":{ "shape":"KeyPrefix", "documentation":"S3 prefix.
" } }, "documentation":"S3 configuration for storing log data.
" }, "S3DataSource":{ "type":"structure", "required":["s3Uri"], "members":{ "s3Uri":{ "shape":"S3Uri", "documentation":"The URI of the Amazon S3 data source.
" } }, "documentation":"The Amazon S3 data source of the imported job.
" }, "S3InputFormat":{ "type":"string", "enum":["JSONL"] }, "S3ObjectDoc":{ "type":"structure", "required":["uri"], "members":{ "uri":{ "shape":"kBS3Uri", "documentation":"The S3 URI location for the wrapper object of the document.
" } }, "documentation":"The unique wrapper object of the document from the S3 location.
" }, "S3Uri":{ "type":"string", "max":1024, "min":1, "pattern":"s3://[a-z0-9][-.a-z0-9]{1,61}(?:/[-!_*'().a-z0-9A-Z]+(?:/[-!_*'().a-z0-9A-Z]+)*)?/?" }, "SageMakerEndpoint":{ "type":"structure", "required":[ "initialInstanceCount", "instanceType", "executionRole" ], "members":{ "initialInstanceCount":{ "shape":"InstanceCount", "documentation":"The number of Amazon EC2 compute instances to deploy for initial endpoint creation.
" }, "instanceType":{ "shape":"InstanceType", "documentation":"The Amazon EC2 compute instance type to deploy for hosting the model.
" }, "executionRole":{ "shape":"RoleArn", "documentation":"The ARN of the IAM role that Amazon SageMaker can assume to access model artifacts and docker image for deployment on Amazon EC2 compute instances or for batch transform jobs.
" }, "kmsEncryptionKey":{ "shape":"KmsKeyId", "documentation":"The Amazon Web Services KMS key that Amazon SageMaker uses to encrypt data on the storage volume attached to the Amazon EC2 compute instance that hosts the endpoint.
" }, "vpc":{ "shape":"VpcConfig", "documentation":"The VPC configuration for the endpoint.
" } }, "documentation":"Specifies the configuration for a Amazon SageMaker endpoint.
" }, "SageMakerFlowDefinitionArn":{ "type":"string", "max":1024, "min":0, "pattern":"arn:aws(-[^:]+)?:sagemaker:[a-z0-9-]{1,20}:[0-9]{12}:flow-definition/.*" }, "SearchType":{ "type":"string", "enum":[ "HYBRID", "SEMANTIC" ] }, "SecurityGroupId":{ "type":"string", "max":32, "min":0, "pattern":"[-0-9a-zA-Z]+" }, "SecurityGroupIds":{ "type":"list", "member":{"shape":"SecurityGroupId"}, "max":5, "min":1 }, "ServiceQuotaExceededException":{ "type":"structure", "members":{ "message":{"shape":"NonBlankString"} }, "documentation":"The number of requests exceeds the service quota. Resubmit your request later.
", "error":{ "httpStatusCode":400, "senderFault":true }, "exception":true }, "ServiceUnavailableException":{ "type":"structure", "members":{ "message":{"shape":"NonBlankString"} }, "documentation":"Returned if the service cannot complete the request.
", "error":{"httpStatusCode":503}, "exception":true, "fault":true }, "SortByProvisionedModels":{ "type":"string", "enum":["CreationTime"] }, "SortJobsBy":{ "type":"string", "enum":["CreationTime"] }, "SortModelsBy":{ "type":"string", "enum":["CreationTime"] }, "SortOrder":{ "type":"string", "enum":[ "Ascending", "Descending" ] }, "Status":{ "type":"string", "enum":[ "REGISTERED", "INCOMPATIBLE_ENDPOINT" ] }, "StopEvaluationJobRequest":{ "type":"structure", "required":["jobIdentifier"], "members":{ "jobIdentifier":{ "shape":"EvaluationJobIdentifier", "documentation":"The Amazon Resource Name (ARN) of the evaluation job you want to stop.
", "location":"uri", "locationName":"jobIdentifier" } } }, "StopEvaluationJobResponse":{ "type":"structure", "members":{ } }, "StopModelCustomizationJobRequest":{ "type":"structure", "required":["jobIdentifier"], "members":{ "jobIdentifier":{ "shape":"ModelCustomizationJobIdentifier", "documentation":"Job identifier of the job to stop.
", "location":"uri", "locationName":"jobIdentifier" } } }, "StopModelCustomizationJobResponse":{ "type":"structure", "members":{ } }, "StopModelInvocationJobRequest":{ "type":"structure", "required":["jobIdentifier"], "members":{ "jobIdentifier":{ "shape":"ModelInvocationJobIdentifier", "documentation":"The Amazon Resource Name (ARN) of the batch inference job to stop.
", "location":"uri", "locationName":"jobIdentifier" } } }, "StopModelInvocationJobResponse":{ "type":"structure", "members":{ } }, "String":{"type":"string"}, "SubnetId":{ "type":"string", "max":32, "min":0, "pattern":"[-0-9a-zA-Z]+" }, "SubnetIds":{ "type":"list", "member":{"shape":"SubnetId"}, "max":16, "min":1 }, "Tag":{ "type":"structure", "required":[ "key", "value" ], "members":{ "key":{ "shape":"TagKey", "documentation":"Key for the tag.
" }, "value":{ "shape":"TagValue", "documentation":"Value for the tag.
" } }, "documentation":"Definition of the key/value pair for a tag.
" }, "TagKey":{ "type":"string", "max":128, "min":1, "pattern":"[a-zA-Z0-9\\s._:/=+@-]*" }, "TagKeyList":{ "type":"list", "member":{"shape":"TagKey"}, "max":200, "min":0 }, "TagList":{ "type":"list", "member":{"shape":"Tag"}, "max":200, "min":0 }, "TagResourceRequest":{ "type":"structure", "required":[ "resourceARN", "tags" ], "members":{ "resourceARN":{ "shape":"TaggableResourcesArn", "documentation":"The Amazon Resource Name (ARN) of the resource to tag.
" }, "tags":{ "shape":"TagList", "documentation":"Tags to associate with the resource.
" } } }, "TagResourceResponse":{ "type":"structure", "members":{ } }, "TagValue":{ "type":"string", "max":256, "min":0, "pattern":"[a-zA-Z0-9\\s._:/=+@-]*" }, "TaggableResourcesArn":{ "type":"string", "max":1011, "min":20, "pattern":".*(^[a-zA-Z0-9][a-zA-Z0-9\\-]*$)|(^arn:aws(-[^:]+)?:bedrock:[a-z0-9-]{1,20}:([0-9]{12}|)((:(fine-tuning-job|model-customization-job|custom-model)/[a-z0-9-]{1,63}[.]{1}[a-z0-9-]{1,63}([a-z0-9-]{1,63}[.]){0,2}[a-z0-9-]{1,63}([:][a-z0-9-]{1,63}){0,2}(/[a-z0-9]{12})$)|(:guardrail/[a-z0-9]+$)|(:automated-reasoning-policy/[a-zA-Z0-9]+(:[a-zA-Z0-9]+)?$)|(:(inference-profile|application-inference-profile)/[a-zA-Z0-9-:.]+$)|(:(provisioned-model|model-invocation-job|model-evaluation-job|evaluation-job|model-import-job|imported-model|async-invoke|provisioned-model-v2|provisioned-model-reservation|prompt-router)/[a-z0-9]{12}$))).*" }, "TeacherModelConfig":{ "type":"structure", "required":["teacherModelIdentifier"], "members":{ "teacherModelIdentifier":{ "shape":"TeacherModelIdentifier", "documentation":"The identifier of the teacher model.
" }, "maxResponseLengthForInference":{ "shape":"Integer", "documentation":"The maximum number of tokens requested when the customization job invokes the teacher model.
" } }, "documentation":"Details about a teacher model used for model customization.
" }, "TeacherModelIdentifier":{ "type":"string", "pattern":"arn:aws(-[^:]+)?:bedrock:[a-z0-9-]{1,20}::foundation-model/[a-z0-9-]{1,63}[.]{1}([a-z0-9-]{1,63}[.]){0,2}[a-z0-9-]{1,63}([:][a-z0-9-]{1,63}){0,2}|([a-z0-9-]{1,63}[.]{1}[a-z0-9-]{1,63}([.]?[a-z0-9-]{1,63})([:][a-z0-9-]{1,63}){0,2})|(([0-9a-zA-Z][_-]?)+)" }, "Temperature":{ "type":"float", "box":true, "max":1, "min":0 }, "TextInferenceConfig":{ "type":"structure", "members":{ "temperature":{ "shape":"Temperature", "documentation":"Controls the random-ness of text generated by the language model, influencing how much the model sticks to the most predictable next words versus exploring more surprising options. A lower temperature value (e.g. 0.2 or 0.3) makes model outputs more deterministic or predictable, while a higher temperature (e.g. 0.8 or 0.9) makes the outputs more creative or unpredictable.
" }, "topP":{ "shape":"TopP", "documentation":"A probability distribution threshold which controls what the model considers for the set of possible next tokens. The model will only consider the top p% of the probability distribution when generating the next token.
" }, "maxTokens":{ "shape":"MaxTokens", "documentation":"The maximum number of tokens to generate in the output text. Do not use the minimum of 0 or the maximum of 65536. The limit values described here are arbitrary values, for actual values consult the limits defined by your specific model.
" }, "stopSequences":{ "shape":"RAGStopSequences", "documentation":"A list of sequences of characters that, if generated, will cause the model to stop generating further tokens. Do not use a minimum length of 1 or a maximum length of 1000. The limit values described here are arbitrary values, for actual values consult the limits defined by your specific model.
" } }, "documentation":"The configuration details for text generation using a language model via the RetrieveAndGenerate function.
The number of requests exceeds the limit. Resubmit your request later.
", "error":{ "httpStatusCode":429, "senderFault":true }, "exception":true }, "Timestamp":{ "type":"timestamp", "timestampFormat":"iso8601" }, "TooManyTagsException":{ "type":"structure", "members":{ "message":{"shape":"NonBlankString"}, "resourceName":{ "shape":"TaggableResourcesArn", "documentation":"The name of the resource with too many tags.
" } }, "documentation":"The request contains more tags than can be associated with a resource (50 tags per resource). The maximum number of tags includes both existing tags and those included in your current request.
", "error":{ "httpStatusCode":400, "senderFault":true }, "exception":true }, "TopP":{ "type":"float", "box":true, "max":1, "min":0 }, "TrainingDataConfig":{ "type":"structure", "members":{ "s3Uri":{ "shape":"S3Uri", "documentation":"The S3 URI where the training data is stored.
" }, "invocationLogsConfig":{ "shape":"InvocationLogsConfig", "documentation":"Settings for using invocation logs to customize a model.
" } }, "documentation":"S3 Location of the training data.
" }, "TrainingMetrics":{ "type":"structure", "members":{ "trainingLoss":{ "shape":"MetricFloat", "documentation":"Loss metric associated with the custom job.
" } }, "documentation":"Metrics associated with the custom job.
" }, "UntagResourceRequest":{ "type":"structure", "required":[ "resourceARN", "tagKeys" ], "members":{ "resourceARN":{ "shape":"TaggableResourcesArn", "documentation":"The Amazon Resource Name (ARN) of the resource to untag.
" }, "tagKeys":{ "shape":"TagKeyList", "documentation":"Tag keys of the tags to remove from the resource.
" } } }, "UntagResourceResponse":{ "type":"structure", "members":{ } }, "UpdateGuardrailRequest":{ "type":"structure", "required":[ "guardrailIdentifier", "name", "blockedInputMessaging", "blockedOutputsMessaging" ], "members":{ "guardrailIdentifier":{ "shape":"GuardrailIdentifier", "documentation":"The unique identifier of the guardrail. This can be an ID or the ARN.
", "location":"uri", "locationName":"guardrailIdentifier" }, "name":{ "shape":"GuardrailName", "documentation":"A name for the guardrail.
" }, "description":{ "shape":"GuardrailDescription", "documentation":"A description of the guardrail.
" }, "topicPolicyConfig":{ "shape":"GuardrailTopicPolicyConfig", "documentation":"The topic policy to configure for the guardrail.
" }, "contentPolicyConfig":{ "shape":"GuardrailContentPolicyConfig", "documentation":"The content policy to configure for the guardrail.
" }, "wordPolicyConfig":{ "shape":"GuardrailWordPolicyConfig", "documentation":"The word policy to configure for the guardrail.
" }, "sensitiveInformationPolicyConfig":{ "shape":"GuardrailSensitiveInformationPolicyConfig", "documentation":"The sensitive information policy to configure for the guardrail.
" }, "contextualGroundingPolicyConfig":{ "shape":"GuardrailContextualGroundingPolicyConfig", "documentation":"The contextual grounding policy configuration used to update a guardrail.
" }, "blockedInputMessaging":{ "shape":"GuardrailBlockedMessaging", "documentation":"The message to return when the guardrail blocks a prompt.
" }, "blockedOutputsMessaging":{ "shape":"GuardrailBlockedMessaging", "documentation":"The message to return when the guardrail blocks a model response.
" }, "kmsKeyId":{ "shape":"KmsKeyId", "documentation":"The ARN of the KMS key with which to encrypt the guardrail.
" } } }, "UpdateGuardrailResponse":{ "type":"structure", "required":[ "guardrailId", "guardrailArn", "version", "updatedAt" ], "members":{ "guardrailId":{ "shape":"GuardrailId", "documentation":"The unique identifier of the guardrail
" }, "guardrailArn":{ "shape":"GuardrailArn", "documentation":"The ARN of the guardrail.
" }, "version":{ "shape":"GuardrailDraftVersion", "documentation":"The version of the guardrail.
" }, "updatedAt":{ "shape":"Timestamp", "documentation":"The date and time at which the guardrail was updated.
" } } }, "UpdateMarketplaceModelEndpointRequest":{ "type":"structure", "required":[ "endpointArn", "endpointConfig" ], "members":{ "endpointArn":{ "shape":"Arn", "documentation":"The Amazon Resource Name (ARN) of the endpoint you want to update.
", "location":"uri", "locationName":"endpointArn" }, "endpointConfig":{ "shape":"EndpointConfig", "documentation":"The new configuration for the endpoint, including the number and type of instances to use.
" }, "clientRequestToken":{ "shape":"IdempotencyToken", "documentation":"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.
", "idempotencyToken":true } } }, "UpdateMarketplaceModelEndpointResponse":{ "type":"structure", "required":["marketplaceModelEndpoint"], "members":{ "marketplaceModelEndpoint":{ "shape":"MarketplaceModelEndpoint", "documentation":"Details about the updated endpoint.
" } } }, "UpdateProvisionedModelThroughputRequest":{ "type":"structure", "required":["provisionedModelId"], "members":{ "provisionedModelId":{ "shape":"ProvisionedModelId", "documentation":"The Amazon Resource Name (ARN) or name of the Provisioned Throughput to update.
", "location":"uri", "locationName":"provisionedModelId" }, "desiredProvisionedModelName":{ "shape":"ProvisionedModelName", "documentation":"The new name for this Provisioned Throughput.
" }, "desiredModelId":{ "shape":"ModelIdentifier", "documentation":"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.
Information about the validators.
" } }, "documentation":"Array of up to 10 validators.
" }, "ValidationException":{ "type":"structure", "members":{ "message":{"shape":"NonBlankString"} }, "documentation":"Input validation failed. Check your request parameters and retry the request.
", "error":{ "httpStatusCode":400, "senderFault":true }, "exception":true }, "ValidationMetrics":{ "type":"list", "member":{"shape":"ValidatorMetric"} }, "Validator":{ "type":"structure", "required":["s3Uri"], "members":{ "s3Uri":{ "shape":"S3Uri", "documentation":"The S3 URI where the validation data is stored.
" } }, "documentation":"Information about a validator.
" }, "ValidatorMetric":{ "type":"structure", "members":{ "validationLoss":{ "shape":"MetricFloat", "documentation":"The validation loss associated with this validator.
" } }, "documentation":"The metric for the validator.
" }, "Validators":{ "type":"list", "member":{"shape":"Validator"}, "max":10, "min":0 }, "VpcConfig":{ "type":"structure", "required":[ "subnetIds", "securityGroupIds" ], "members":{ "subnetIds":{ "shape":"SubnetIds", "documentation":"An array of IDs for each subnet in the VPC to use.
" }, "securityGroupIds":{ "shape":"SecurityGroupIds", "documentation":"An array of IDs for each security group in the VPC to use.
" } }, "documentation":"The configuration of a virtual private cloud (VPC). For more information, see Protect your data using Amazon Virtual Private Cloud and Amazon Web Services PrivateLink.
" }, "kBS3Uri":{ "type":"string", "max":1024, "min":1, "pattern":"s3://[a-z0-9][a-z0-9.-]{1,61}[a-z0-9]/.{1,1024}" } }, "documentation":"Describes the API operations for creating, managing, fine-turning, and evaluating Amazon Bedrock models.
" }