Describes the API operations for creating, managing, fine-turning, and evaluating Amazon Bedrock models.
", "operations": { "BatchDeleteEvaluationJob": "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.
Cancels a running Automated Reasoning policy build workflow. This stops the policy generation process and prevents further processing of the source documents.
", "CreateAutomatedReasoningPolicy": "Creates an Automated Reasoning policy for Amazon Bedrock Guardrails. Automated Reasoning policies use mathematical techniques to detect hallucinations, suggest corrections, and highlight unstated assumptions in the responses of your GenAI application.
To create a policy, you upload a source document that describes the rules that you're encoding. Automated Reasoning extracts important concepts from the source document that will become variables in the policy and infers policy rules.
", "CreateAutomatedReasoningPolicyTestCase": "Creates a test for an Automated Reasoning policy. Tests validate that your policy works as expected by providing sample inputs and expected outcomes. Use tests to verify policy behavior before deploying to production.
", "CreateAutomatedReasoningPolicyVersion": "Creates a new version of an existing Automated Reasoning policy. This allows you to iterate on your policy rules while maintaining previous versions for rollback or comparison purposes.
", "CreateCustomModel": "Creates a new custom model in Amazon Bedrock. After the model is active, you can use it for inference.
To use the model for inference, you must purchase Provisioned Throughput for it. You can't use On-demand inference with these custom models. For more information about Provisioned Throughput, see Provisioned Throughput.
The model appears in ListCustomModels with a customizationType of imported. To track the status of the new model, you use the GetCustomModel API operation. The model can be in the following states:
Creating - Initial state during validation and registration
Active - Model is ready for use in inference
Failed - Creation process encountered an error
Related APIs
", "CreateCustomModelDeployment": "Deploys a custom model for on-demand inference in Amazon Bedrock. After you deploy your custom model, you use the deployment's Amazon Resource Name (ARN) as the modelId parameter when you submit prompts and generate responses with model inference.
For more information about setting up on-demand inference for custom models, see Set up inference for a custom model.
The following actions are related to the CreateCustomModelDeployment operation:
Creates an evaluation job.
", "CreateFoundationModelAgreement": "Request a model access agreement for the specified model.
", "CreateGuardrail": "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": "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": "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.
", "CreateMarketplaceModelEndpoint": "Creates an endpoint for a model from Amazon Bedrock Marketplace. The endpoint is hosted by Amazon SageMaker.
", "CreateModelCopyJob": "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.
", "CreateModelCustomizationJob": "Creates a fine-tuning job to customize a base model.
You specify the base foundation model and the location of the training data. After the model-customization job completes successfully, your custom model resource will be ready to use. 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.
", "CreateModelImportJob": "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
", "CreateModelInvocationJob": "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.
", "CreateProvisionedModelThroughput": "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.
", "DeleteAutomatedReasoningPolicy": "Deletes an Automated Reasoning policy or policy version. This operation is idempotent. If you delete a policy more than once, each call succeeds. Deleting a policy removes it permanently and cannot be undone.
", "DeleteAutomatedReasoningPolicyBuildWorkflow": "Deletes an Automated Reasoning policy build workflow and its associated artifacts. This permanently removes the workflow history and any generated assets.
", "DeleteAutomatedReasoningPolicyTestCase": "Deletes an Automated Reasoning policy test. This operation is idempotent; if you delete a test more than once, each call succeeds.
", "DeleteCustomModel": "Deletes a custom model that you created earlier. For more information, see Custom models in the Amazon Bedrock User Guide.
", "DeleteCustomModelDeployment": "Deletes a custom model deployment. This operation stops the deployment and removes it from your account. After deletion, the deployment ARN can no longer be used for inference requests.
The following actions are related to the DeleteCustomModelDeployment operation:
Delete the model access agreement for the specified model.
", "DeleteGuardrail": "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.
", "DeleteInferenceProfile": "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.
", "DeleteMarketplaceModelEndpoint": "Deletes an endpoint for a model from Amazon Bedrock Marketplace.
", "DeleteModelInvocationLoggingConfiguration": "Delete the invocation logging.
", "DeletePromptRouter": "Deletes a specified prompt router. This action cannot be undone.
", "DeleteProvisionedModelThroughput": "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.
", "DeregisterMarketplaceModelEndpoint": "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.
", "ExportAutomatedReasoningPolicyVersion": "Exports the policy definition for an Automated Reasoning policy version. Returns the complete policy definition including rules, variables, and custom variable types in a structured format.
", "GetAutomatedReasoningPolicy": "Retrieves details about an Automated Reasoning policy or policy version. Returns information including the policy definition, metadata, and timestamps.
", "GetAutomatedReasoningPolicyAnnotations": "Retrieves the current annotations for an Automated Reasoning policy build workflow. Annotations contain corrections to the rules, variables and types to be applied to the policy.
", "GetAutomatedReasoningPolicyBuildWorkflow": "Retrieves detailed information about an Automated Reasoning policy build workflow, including its status, configuration, and metadata.
", "GetAutomatedReasoningPolicyBuildWorkflowResultAssets": "Retrieves the resulting assets from a completed Automated Reasoning policy build workflow, including build logs, quality reports, and generated policy artifacts.
", "GetAutomatedReasoningPolicyNextScenario": "Retrieves the next test scenario for validating an Automated Reasoning policy. This is used during the interactive policy refinement process to test policy behavior.
", "GetAutomatedReasoningPolicyTestCase": "Retrieves details about a specific Automated Reasoning policy test.
", "GetAutomatedReasoningPolicyTestResult": "Retrieves the test result for a specific Automated Reasoning policy test. Returns detailed validation findings and execution status.
", "GetCustomModel": "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.
", "GetCustomModelDeployment": "Retrieves information about a custom model deployment, including its status, configuration, and metadata. Use this operation to monitor the deployment status and retrieve details needed for inference requests.
The following actions are related to the GetCustomModelDeployment operation:
Gets information about an evaluation job, such as the status of the job.
", "GetFoundationModel": "Get details about a Amazon Bedrock foundation model.
", "GetFoundationModelAvailability": "Get information about the Foundation model availability.
", "GetGuardrail": "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": "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": "Retrieves details about a specific endpoint for a model from Amazon Bedrock Marketplace.
", "GetModelCopyJob": "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": "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": "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": "Gets details about a batch inference job. For more information, see Monitor batch inference jobs
", "GetModelInvocationLoggingConfiguration": "Get the current configuration values for model invocation logging.
", "GetPromptRouter": "Retrieves details about a prompt router.
", "GetProvisionedModelThroughput": "Returns details for a Provisioned Throughput. For more information, see Provisioned Throughput in the Amazon Bedrock User Guide.
", "GetUseCaseForModelAccess": "Get usecase for model access.
", "ListAutomatedReasoningPolicies": "Lists all Automated Reasoning policies in your account, with optional filtering by policy ARN. This helps you manage and discover existing policies.
", "ListAutomatedReasoningPolicyBuildWorkflows": "Lists all build workflows for an Automated Reasoning policy, showing the history of policy creation and modification attempts.
", "ListAutomatedReasoningPolicyTestCases": "Lists tests for an Automated Reasoning policy. We recommend using pagination to ensure that the operation returns quickly and successfully.
", "ListAutomatedReasoningPolicyTestResults": "Lists test results for an Automated Reasoning policy, showing how the policy performed against various test scenarios and validation checks.
", "ListCustomModelDeployments": "Lists custom model deployments in your account. You can filter the results by creation time, name, status, and associated model. Use this operation to manage and monitor your custom model deployments.
We recommend using pagination to ensure that the operation returns quickly and successfully.
The following actions are related to the ListCustomModelDeployments operation:
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": "Lists all existing evaluation jobs.
", "ListFoundationModelAgreementOffers": "Get the offers associated with the specified model.
", "ListFoundationModels": "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": "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": "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": "Lists the endpoints for models from Amazon Bedrock Marketplace in your Amazon Web Services account.
", "ListModelCopyJobs": "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": "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": "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": "Lists all batch inference jobs in the account. For more information, see View details about a batch inference job.
", "ListPromptRouters": "Retrieves a list of prompt routers.
", "ListProvisionedModelThroughputs": "Lists the Provisioned Throughputs in the account. For more information, see Provisioned Throughput in the Amazon Bedrock User Guide.
", "ListTagsForResource": "List the tags associated with the specified resource.
For more information, see Tagging resources in the Amazon Bedrock User Guide.
", "PutModelInvocationLoggingConfiguration": "Set the configuration values for model invocation logging.
", "PutUseCaseForModelAccess": "Put usecase for model access.
", "RegisterMarketplaceModelEndpoint": "Registers an existing Amazon SageMaker endpoint with Amazon Bedrock Marketplace, allowing it to be used with Amazon Bedrock APIs.
", "StartAutomatedReasoningPolicyBuildWorkflow": "Starts a new build workflow for an Automated Reasoning policy. This initiates the process of analyzing source documents and generating policy rules, variables, and types.
", "StartAutomatedReasoningPolicyTestWorkflow": "Initiates a test workflow to validate Automated Reasoning policy tests. The workflow executes the specified tests against the policy and generates validation results.
", "StopEvaluationJob": "Stops an evaluation job that is current being created or running.
", "StopModelCustomizationJob": "Stops an active model customization job. For more information, see Custom models in the Amazon Bedrock User Guide.
", "StopModelInvocationJob": "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": "Associate tags with a resource. For more information, see Tagging resources in the Amazon Bedrock User Guide.
", "UntagResource": "Remove one or more tags from a resource. For more information, see Tagging resources in the Amazon Bedrock User Guide.
", "UpdateAutomatedReasoningPolicy": "Updates an existing Automated Reasoning policy with new rules, variables, or configuration. This creates a new version of the policy while preserving the previous version.
", "UpdateAutomatedReasoningPolicyAnnotations": "Updates the annotations for an Automated Reasoning policy build workflow. This allows you to modify extracted rules, variables, and types before finalizing the policy.
", "UpdateAutomatedReasoningPolicyTestCase": "Updates an existing Automated Reasoning policy test. You can modify the content, query, expected result, and confidence threshold.
", "UpdateGuardrail": "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": "Updates the name or associated model for a Provisioned Throughput. For more information, see Provisioned Throughput in the Amazon Bedrock User Guide.
" }, "shapes": { "AcceptEula": { "base": null, "refs": { "CreateMarketplaceModelEndpointRequest$acceptEula": "Indicates whether you accept the end-user license agreement (EULA) for the model. Set to true to accept the EULA.
The request is denied because of missing access permissions.
", "refs": { } }, "AccountId": { "base": null, "refs": { "CustomModelSummary$ownerAccountId": "The unique identifier of the account that owns the model.
", "GetModelCopyJobResponse$sourceAccountId": "The unique identifier of the account that the model being copied originated from.
", "ListModelCopyJobsRequest$sourceAccountEquals": "Filters for model copy jobs in which the account that the source model belongs to is equal to the value that you specify.
", "ModelCopyJobSummary$sourceAccountId": "The unique identifier of the account that the model being copied originated from.
", "ModelInvocationJobS3InputDataConfig$s3BucketOwner": "The ID of the Amazon Web Services account that owns the S3 bucket containing the input data.
", "ModelInvocationJobS3OutputDataConfig$s3BucketOwner": "The ID of the Amazon Web Services account that owns the S3 bucket containing the output data.
" } }, "AcknowledgementFormDataBody": { "base": null, "refs": { "GetUseCaseForModelAccessResponse$formData": "Get customer profile Response.
", "PutUseCaseForModelAccessRequest$formData": "Put customer profile Request.
" } }, "AdditionalModelRequestFields": { "base": null, "refs": { "ExternalSourcesGenerationConfiguration$additionalModelRequestFields": "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.
", "GenerationConfiguration$additionalModelRequestFields": "Additional model parameters and corresponding values not included in the textInferenceConfig structure for a knowledge base. This allows you to provide custom model parameters specific to the language model being used.
A list of additional fields to include in the model request during reranking. These fields provide extra context or configuration options specific to the selected foundation model.
" } }, "AdditionalModelRequestFieldsKey": { "base": null, "refs": { "AdditionalModelRequestFields$key": null } }, "AdditionalModelRequestFieldsValue": { "base": null, "refs": { "AdditionalModelRequestFields$value": null } }, "AgreementAvailability": { "base": "Information about the agreement availability
", "refs": { "GetFoundationModelAvailabilityResponse$agreementAvailability": "Agreement availability.
" } }, "AgreementStatus": { "base": null, "refs": { "AgreementAvailability$status": "Status of the agreement.
" } }, "ApplicationType": { "base": null, "refs": { "CreateEvaluationJobRequest$applicationType": "Specifies whether the evaluation job is for evaluating a model or evaluating a knowledge base (retrieval and response generation).
", "EvaluationSummary$applicationType": "Specifies whether the evaluation job is for evaluating a model or evaluating a knowledge base (retrieval and response generation).
", "GetEvaluationJobResponse$applicationType": "Specifies whether the evaluation job is for evaluating a model or evaluating a knowledge base (retrieval and response generation).
", "ListEvaluationJobsRequest$applicationTypeEquals": "A filter to only list evaluation jobs that are either model evaluations or knowledge base evaluations.
" } }, "Arn": { "base": null, "refs": { "DeleteMarketplaceModelEndpointRequest$endpointArn": "The Amazon Resource Name (ARN) of the endpoint you want to delete.
", "DeregisterMarketplaceModelEndpointRequest$endpointArn": "The Amazon Resource Name (ARN) of the endpoint you want to deregister.
", "GetMarketplaceModelEndpointRequest$endpointArn": "The Amazon Resource Name (ARN) of the endpoint you want to get information about.
", "MarketplaceModelEndpoint$endpointArn": "The Amazon Resource Name (ARN) of the endpoint.
", "MarketplaceModelEndpointSummary$endpointArn": "The Amazon Resource Name (ARN) of the endpoint.
", "RegisterMarketplaceModelEndpointRequest$endpointIdentifier": "The ARN of the Amazon SageMaker endpoint you want to register with Amazon Bedrock Marketplace.
", "UpdateMarketplaceModelEndpointRequest$endpointArn": "The Amazon Resource Name (ARN) of the endpoint you want to update.
" } }, "AttributeType": { "base": null, "refs": { "MetadataAttributeSchema$type": "The data type of the metadata attribute. The type determines how the attribute can be used in filter expressions and reranking.
" } }, "AuthorizationStatus": { "base": null, "refs": { "GetFoundationModelAvailabilityResponse$authorizationStatus": "Authorization status.
" } }, "AutomatedEvaluationConfig": { "base": "The configuration details of an automated evaluation job. The EvaluationDatasetMetricConfig object is used to specify the prompt datasets, task type, and metric names.
Contains the configuration details of an automated evaluation job that computes metrics.
" } }, "AutomatedEvaluationCustomMetricConfig": { "base": "Defines the configuration of custom metrics to be used in an evaluation job. To learn more about using custom metrics in Amazon Bedrock evaluation jobs, see Create a prompt for a custom metrics (LLM-as-a-judge model evaluations) and Create a prompt for a custom metrics (RAG evaluations).
", "refs": { "AutomatedEvaluationConfig$customMetricConfig": "Defines the configuration of custom metrics to be used in an evaluation job.
" } }, "AutomatedEvaluationCustomMetricSource": { "base": "An array item definining a single custom metric for use in an Amazon Bedrock evaluation job.
", "refs": { "AutomatedEvaluationCustomMetrics$member": null } }, "AutomatedEvaluationCustomMetrics": { "base": null, "refs": { "AutomatedEvaluationCustomMetricConfig$customMetrics": "Defines a list of custom metrics to be used in an Amazon Bedrock evaluation job.
" } }, "AutomatedReasoningCheckDifferenceScenarioList": { "base": null, "refs": { "AutomatedReasoningCheckTranslationAmbiguousFinding$differenceScenarios": "Scenarios showing how the different translation options differ in meaning.
" } }, "AutomatedReasoningCheckFinding": { "base": "Represents the result of an Automated Reasoning validation check, indicating whether the content is logically valid, invalid, or falls into other categories based on the policy rules.
", "refs": { "AutomatedReasoningCheckFindingList$member": null } }, "AutomatedReasoningCheckFindingList": { "base": null, "refs": { "AutomatedReasoningPolicyTestResult$testFindings": "Detailed findings from the test run, including any issues, violations, or unexpected behaviors discovered.
" } }, "AutomatedReasoningCheckImpossibleFinding": { "base": "Indicates that no valid claims can be made due to logical contradictions in the premises or rules.
", "refs": { "AutomatedReasoningCheckFinding$impossible": "Indicates that Automated Reasoning cannot make a statement about the claims. This can happen if the premises are logically incorrect, or if there is a conflict within the Automated Reasoning policy itself.
" } }, "AutomatedReasoningCheckInputTextReference": { "base": "References a portion of the original input text that corresponds to logical elements.
", "refs": { "AutomatedReasoningCheckInputTextReferenceList$member": null } }, "AutomatedReasoningCheckInputTextReferenceList": { "base": null, "refs": { "AutomatedReasoningCheckTranslation$untranslatedPremises": "References to portions of the original input text that correspond to the premises but could not be fully translated.
", "AutomatedReasoningCheckTranslation$untranslatedClaims": "References to portions of the original input text that correspond to the claims but could not be fully translated.
" } }, "AutomatedReasoningCheckInvalidFinding": { "base": "Indicates that the claims are logically false and contradictory to the established rules or premises.
", "refs": { "AutomatedReasoningCheckFinding$invalid": "Indicates that the claims are false. The claims are not implied by the premises and Automated Reasoning policy. Furthermore, there exist different claims that are consistent with the premises and Automated Reasoning policy.
" } }, "AutomatedReasoningCheckLogicWarning": { "base": "Identifies logical issues in the translated statements that exist independent of any policy rules, such as statements that are always true or always false.
", "refs": { "AutomatedReasoningCheckImpossibleFinding$logicWarning": "Indication of a logic issue with the translation without needing to consider the automated reasoning policy rules.
", "AutomatedReasoningCheckInvalidFinding$logicWarning": "Indication of a logic issue with the translation without needing to consider the automated reasoning policy rules.
", "AutomatedReasoningCheckSatisfiableFinding$logicWarning": "Indication of a logic issue with the translation without needing to consider the automated reasoning policy rules.
", "AutomatedReasoningCheckValidFinding$logicWarning": "Indication of a logic issue with the translation without needing to consider the automated reasoning policy rules.
" } }, "AutomatedReasoningCheckLogicWarningType": { "base": null, "refs": { "AutomatedReasoningCheckLogicWarning$type": "The category of the detected logical issue, such as statements that are always true or always false.
" } }, "AutomatedReasoningCheckNoTranslationsFinding": { "base": "Indicates that no relevant logical information could be extracted from the input for validation.
", "refs": { "AutomatedReasoningCheckFinding$noTranslations": "Identifies that some or all of the input prompt wasn't translated into logic. This can happen if the input isn't relevant to the Automated Reasoning policy, or if the policy doesn't have variables to model relevant input.
" } }, "AutomatedReasoningCheckResult": { "base": null, "refs": { "AutomatedReasoningPolicyScenario$expectedResult": "The expected outcome when this scenario is evaluated against the policy (e.g., PASS, FAIL, VIOLATION).
", "AutomatedReasoningPolicyTestCase$expectedAggregatedFindingsResult": "The expected result of the Automated Reasoning check for this test.
", "AutomatedReasoningPolicyTestResult$aggregatedTestFindingsResult": "A summary of all test findings, aggregated to provide an overall assessment of policy quality and correctness.
", "CreateAutomatedReasoningPolicyTestCaseRequest$expectedAggregatedFindingsResult": "The expected result of the Automated Reasoning check. Valid values include: , TOO_COMPLEX, and NO_TRANSLATIONS.
VALID - The claims are true. The claims are implied by the premises and the Automated Reasoning policy. Given the Automated Reasoning policy and premises, it is not possible for these claims to be false. In other words, there are no alternative answers that are true that contradict the claims.
INVALID - The claims are false. The claims are not implied by the premises and Automated Reasoning policy. Furthermore, there exists different claims that are consistent with the premises and Automated Reasoning policy.
SATISFIABLE - The claims can be true or false. It depends on what assumptions are made for the claim to be implied from the premises and Automated Reasoning policy rules. In this situation, different assumptions can make input claims false and alternative claims true.
IMPOSSIBLE - Automated Reasoning can’t make a statement about the claims. This can happen if the premises are logically incorrect, or if there is a conflict within the Automated Reasoning policy itself.
TRANSLATION_AMBIGUOUS - Detected an ambiguity in the translation meant it would be unsound to continue with validity checking. Additional context or follow-up questions might be needed to get translation to succeed.
TOO_COMPLEX - The input contains too much information for Automated Reasoning to process within its latency limits.
NO_TRANSLATIONS - Identifies that some or all of the input prompt wasn't translated into logic. This can happen if the input isn't relevant to the Automated Reasoning policy, or if the policy doesn't have variables to model relevant input. If Automated Reasoning can't translate anything, you get a single NO_TRANSLATIONS finding. You might also see a NO_TRANSLATIONS (along with other findings) if some part of the validation isn't translated.
The updated expected result of the Automated Reasoning check.
" } }, "AutomatedReasoningCheckRule": { "base": "References a specific automated reasoning policy rule that was applied during evaluation.
", "refs": { "AutomatedReasoningCheckRuleList$member": null } }, "AutomatedReasoningCheckRuleList": { "base": null, "refs": { "AutomatedReasoningCheckImpossibleFinding$contradictingRules": "The automated reasoning policy rules that contradict the claims and/or premises in the input.
", "AutomatedReasoningCheckInvalidFinding$contradictingRules": "The automated reasoning policy rules that contradict the claims in the input.
", "AutomatedReasoningCheckValidFinding$supportingRules": "The automated reasoning policy rules that support why this result is considered valid.
" } }, "AutomatedReasoningCheckSatisfiableFinding": { "base": "Indicates that the claims could be either true or false depending on additional assumptions not provided in the input.
", "refs": { "AutomatedReasoningCheckFinding$satisfiable": "Indicates that the claims can be true or false. It depends on what assumptions are made for the claim to be implied from the premises and Automated Reasoning policy rules. In this situation, different assumptions can make input claims false and alternative claims true.
" } }, "AutomatedReasoningCheckScenario": { "base": "Represents a logical scenario where claims can be evaluated as true or false, containing specific logical assignments.
", "refs": { "AutomatedReasoningCheckDifferenceScenarioList$member": null, "AutomatedReasoningCheckSatisfiableFinding$claimsTrueScenario": "An example scenario demonstrating how the claims could be logically true.
", "AutomatedReasoningCheckSatisfiableFinding$claimsFalseScenario": "An example scenario demonstrating how the claims could be logically false.
", "AutomatedReasoningCheckValidFinding$claimsTrueScenario": "An example scenario demonstrating how the claims are logically true.
" } }, "AutomatedReasoningCheckTooComplexFinding": { "base": "Indicates that the input exceeds the processing capacity due to the volume or complexity of the logical information.
", "refs": { "AutomatedReasoningCheckFinding$tooComplex": "Indicates that the input contains too much information for Automated Reasoning to process within its latency limits.
" } }, "AutomatedReasoningCheckTranslation": { "base": "Contains the logical translation of natural language input into formal logical statements, including premises, claims, and confidence scores.
", "refs": { "AutomatedReasoningCheckImpossibleFinding$translation": "The logical translation of the input that this finding evaluates.
", "AutomatedReasoningCheckInvalidFinding$translation": "The logical translation of the input that this finding invalidates.
", "AutomatedReasoningCheckSatisfiableFinding$translation": "The logical translation of the input that this finding evaluates.
", "AutomatedReasoningCheckTranslationList$member": null, "AutomatedReasoningCheckValidFinding$translation": "The logical translation of the input that this finding validates.
" } }, "AutomatedReasoningCheckTranslationAmbiguousFinding": { "base": "Indicates that the input has multiple valid logical interpretations, requiring additional context or clarification.
", "refs": { "AutomatedReasoningCheckFinding$translationAmbiguous": "Indicates that an ambiguity was detected in the translation, making it unsound to continue with validity checking. Additional context or follow-up questions might be needed to get translation to succeed.
" } }, "AutomatedReasoningCheckTranslationConfidence": { "base": null, "refs": { "AutomatedReasoningCheckTranslation$confidence": "A confidence score between 0 and 1 indicating how certain the system is about the logical translation.
", "AutomatedReasoningPolicyTestCase$confidenceThreshold": "The minimum confidence level for logic validation. Content meeting this threshold is considered high-confidence and can be validated.
", "CreateAutomatedReasoningPolicyTestCaseRequest$confidenceThreshold": "The minimum confidence level for logic validation. Content that meets the threshold is considered a high-confidence finding that can be validated.
", "UpdateAutomatedReasoningPolicyTestCaseRequest$confidenceThreshold": "The updated minimum confidence level for logic validation. If null is provided, the threshold will be removed.
" } }, "AutomatedReasoningCheckTranslationList": { "base": null, "refs": { "AutomatedReasoningCheckTranslationOption$translations": "Different logical interpretations that were detected during translation of the input.
" } }, "AutomatedReasoningCheckTranslationOption": { "base": "Represents one possible logical interpretation of ambiguous input content.
", "refs": { "AutomatedReasoningCheckTranslationOptionList$member": null } }, "AutomatedReasoningCheckTranslationOptionList": { "base": null, "refs": { "AutomatedReasoningCheckTranslationAmbiguousFinding$options": "Different logical interpretations that were detected during translation of the input.
" } }, "AutomatedReasoningCheckValidFinding": { "base": "Indicates that the claims are definitively true and logically implied by the premises, with no possible alternative interpretations.
", "refs": { "AutomatedReasoningCheckFinding$valid": "Indicates that the claims are true. The claims are implied by the premises and the Automated Reasoning policy. Given the Automated Reasoning policy and premises, it is not possible for these claims to be false.
" } }, "AutomatedReasoningConfidenceFilterThreshold": { "base": null, "refs": { "GuardrailAutomatedReasoningPolicy$confidenceThreshold": "The minimum confidence level required for Automated Reasoning policy violations to trigger guardrail actions. Values range from 0.0 to 1.0.
", "GuardrailAutomatedReasoningPolicyConfig$confidenceThreshold": "The confidence threshold for triggering guardrail actions based on Automated Reasoning policy violations.
" } }, "AutomatedReasoningLogicStatement": { "base": "Represents a logical statement that can be expressed both in formal logic notation and natural language, providing dual representations for better understanding and validation.
", "refs": { "AutomatedReasoningLogicStatementList$member": null } }, "AutomatedReasoningLogicStatementContent": { "base": null, "refs": { "AutomatedReasoningLogicStatement$logic": "The formal logic representation of the statement using mathematical notation and logical operators.
" } }, "AutomatedReasoningLogicStatementList": { "base": null, "refs": { "AutomatedReasoningCheckLogicWarning$premises": "The logical statements that serve as premises under which the claims are validated.
", "AutomatedReasoningCheckLogicWarning$claims": "The logical statements that are validated while assuming the policy and premises.
", "AutomatedReasoningCheckScenario$statements": "List of logical assignments and statements that define this scenario.
", "AutomatedReasoningCheckTranslation$premises": "The logical statements that serve as the foundation or assumptions for the claims.
", "AutomatedReasoningCheckTranslation$claims": "The logical statements that are being validated against the premises and policy rules.
" } }, "AutomatedReasoningNaturalLanguageStatementContent": { "base": null, "refs": { "AutomatedReasoningCheckInputTextReference$text": "The specific text from the original input that this reference points to.
", "AutomatedReasoningLogicStatement$naturalLanguage": "The natural language representation of the logical statement, providing a human-readable interpretation of the formal logic.
" } }, "AutomatedReasoningPolicyAddRuleAnnotation": { "base": "An annotation for adding a new rule to an Automated Reasoning policy using a formal logical expression.
", "refs": { "AutomatedReasoningPolicyAnnotation$addRule": "An operation to add a new logical rule to the policy using formal mathematical expressions.
" } }, "AutomatedReasoningPolicyAddRuleFromNaturalLanguageAnnotation": { "base": "An annotation for adding a new rule to the policy by converting a natural language description into a formal logical expression.
", "refs": { "AutomatedReasoningPolicyAnnotation$addRuleFromNaturalLanguage": "An operation to add a new rule by converting natural language descriptions into formal logical expressions.
" } }, "AutomatedReasoningPolicyAddRuleMutation": { "base": "A mutation operation that adds a new rule to the policy definition during the build process.
", "refs": { "AutomatedReasoningPolicyMutation$addRule": "A mutation to add a new rule to the policy.
" } }, "AutomatedReasoningPolicyAddTypeAnnotation": { "base": "An annotation for adding a new custom type to an Automated Reasoning policy, defining a set of possible values for variables.
", "refs": { "AutomatedReasoningPolicyAnnotation$addType": "An operation to add a new custom type to the policy, defining a set of possible values for policy variables.
" } }, "AutomatedReasoningPolicyAddTypeMutation": { "base": "A mutation operation that adds a new custom type to the policy definition during the build process.
", "refs": { "AutomatedReasoningPolicyMutation$addType": "A mutation to add a new custom type to the policy.
" } }, "AutomatedReasoningPolicyAddTypeValue": { "base": "Represents a single value that can be added to an existing custom type in the policy.
", "refs": { "AutomatedReasoningPolicyTypeValueAnnotation$addTypeValue": "An operation to add a new value to an existing custom type.
" } }, "AutomatedReasoningPolicyAddVariableAnnotation": { "base": "An annotation for adding a new variable to an Automated Reasoning policy, which can be used in rule expressions.
", "refs": { "AutomatedReasoningPolicyAnnotation$addVariable": "An operation to add a new variable to the policy, which can be used in rule expressions to represent dynamic values.
" } }, "AutomatedReasoningPolicyAddVariableMutation": { "base": "A mutation operation that adds a new variable to the policy definition during the build process.
", "refs": { "AutomatedReasoningPolicyMutation$addVariable": "A mutation to add a new variable to the policy.
" } }, "AutomatedReasoningPolicyAnnotation": { "base": "Contains the various operations that can be performed on an Automated Reasoning policy, including adding, updating, and deleting rules, variables, and types.
", "refs": { "AutomatedReasoningPolicyAnnotationList$member": null, "AutomatedReasoningPolicyBuildLogEntry$annotation": "The annotation or operation that was being processed when this log entry was created.
" } }, "AutomatedReasoningPolicyAnnotationFeedbackNaturalLanguage": { "base": null, "refs": { "AutomatedReasoningPolicyUpdateFromRuleFeedbackAnnotation$feedback": "The feedback information about rule performance, including suggestions for improvements or corrections.
", "AutomatedReasoningPolicyUpdateFromScenarioFeedbackAnnotation$feedback": "The feedback information about scenario performance, including any issues or improvements identified.
" } }, "AutomatedReasoningPolicyAnnotationIngestContent": { "base": null, "refs": { "AutomatedReasoningPolicyIngestContentAnnotation$content": "The new content to be analyzed and incorporated into the policy, such as additional documents or rule descriptions.
" } }, "AutomatedReasoningPolicyAnnotationList": { "base": null, "refs": { "AutomatedReasoningPolicyBuildWorkflowRepairContent$annotations": "Specific annotations or modifications to apply during the policy repair process, such as rule corrections or variable updates.
", "GetAutomatedReasoningPolicyAnnotationsResponse$annotations": "The current set of annotations containing rules, variables, and types extracted from the source documents. These can be modified before finalizing the policy.
", "UpdateAutomatedReasoningPolicyAnnotationsRequest$annotations": "The updated annotations containing modified rules, variables, and types for the policy.
" } }, "AutomatedReasoningPolicyAnnotationRuleNaturalLanguage": { "base": null, "refs": { "AutomatedReasoningPolicyAddRuleFromNaturalLanguageAnnotation$naturalLanguage": "The natural language description of the rule that should be converted into a formal logical expression.
" } }, "AutomatedReasoningPolicyAnnotationStatus": { "base": null, "refs": { "AutomatedReasoningPolicyBuildLogEntry$status": "The status of the build step (e.g., SUCCESS, FAILED, IN_PROGRESS).
" } }, "AutomatedReasoningPolicyArn": { "base": null, "refs": { "AutomatedReasoningCheckRule$policyVersionArn": "The ARN of the automated reasoning policy version that contains this rule.
", "AutomatedReasoningPolicyBuildWorkflowSummary$policyArn": "The Amazon Resource Name (ARN) of the Automated Reasoning policy associated with this build workflow.
", "AutomatedReasoningPolicySummary$policyArn": "The Amazon Resource Name (ARN) of the policy.
", "AutomatedReasoningPolicyTestResult$policyArn": "The Amazon Resource Name (ARN) of the Automated Reasoning policy that was tested.
", "CancelAutomatedReasoningPolicyBuildWorkflowRequest$policyArn": "The Amazon Resource Name (ARN) of the Automated Reasoning policy whose build workflow you want to cancel.
", "CreateAutomatedReasoningPolicyResponse$policyArn": "The Amazon Resource Name (ARN) of the Automated Reasoning policy that you created.
", "CreateAutomatedReasoningPolicyTestCaseRequest$policyArn": "The Amazon Resource Name (ARN) of the Automated Reasoning policy for which to create the test.
", "CreateAutomatedReasoningPolicyTestCaseResponse$policyArn": "The Amazon Resource Name (ARN) of the policy for which the test was created.
", "CreateAutomatedReasoningPolicyVersionRequest$policyArn": "The Amazon Resource Name (ARN) of the Automated Reasoning policy for which to create a version.
", "CreateAutomatedReasoningPolicyVersionResponse$policyArn": "The versioned Amazon Resource Name (ARN) of the policy version.
", "DeleteAutomatedReasoningPolicyBuildWorkflowRequest$policyArn": "The Amazon Resource Name (ARN) of the Automated Reasoning policy whose build workflow you want to delete.
", "DeleteAutomatedReasoningPolicyRequest$policyArn": "The Amazon Resource Name (ARN) of the Automated Reasoning policy to delete.
", "DeleteAutomatedReasoningPolicyTestCaseRequest$policyArn": "The Amazon Resource Name (ARN) of the Automated Reasoning policy that contains the test.
", "ExportAutomatedReasoningPolicyVersionRequest$policyArn": "The Amazon Resource Name (ARN) of the Automated Reasoning policy to export. Can be either the unversioned ARN for the draft policy or a versioned ARN for a specific policy version.
", "GetAutomatedReasoningPolicyAnnotationsRequest$policyArn": "The Amazon Resource Name (ARN) of the Automated Reasoning policy whose annotations you want to retrieve.
", "GetAutomatedReasoningPolicyAnnotationsResponse$policyArn": "The Amazon Resource Name (ARN) of the Automated Reasoning policy.
", "GetAutomatedReasoningPolicyBuildWorkflowRequest$policyArn": "The Amazon Resource Name (ARN) of the Automated Reasoning policy whose build workflow you want to retrieve.
", "GetAutomatedReasoningPolicyBuildWorkflowResponse$policyArn": "The Amazon Resource Name (ARN) of the Automated Reasoning policy.
", "GetAutomatedReasoningPolicyBuildWorkflowResultAssetsRequest$policyArn": "The Amazon Resource Name (ARN) of the Automated Reasoning policy whose build workflow assets you want to retrieve.
", "GetAutomatedReasoningPolicyBuildWorkflowResultAssetsResponse$policyArn": "The Amazon Resource Name (ARN) of the Automated Reasoning policy.
", "GetAutomatedReasoningPolicyNextScenarioRequest$policyArn": "The Amazon Resource Name (ARN) of the Automated Reasoning policy for which you want to get the next test scenario.
", "GetAutomatedReasoningPolicyNextScenarioResponse$policyArn": "The Amazon Resource Name (ARN) of the Automated Reasoning policy.
", "GetAutomatedReasoningPolicyRequest$policyArn": "The Amazon Resource Name (ARN) of the Automated Reasoning policy to retrieve. Can be either the unversioned ARN for the draft policy or an ARN for a specific policy version.
", "GetAutomatedReasoningPolicyResponse$policyArn": "The Amazon Resource Name (ARN) of the policy.
", "GetAutomatedReasoningPolicyTestCaseRequest$policyArn": "The Amazon Resource Name (ARN) of the Automated Reasoning policy that contains the test.
", "GetAutomatedReasoningPolicyTestCaseResponse$policyArn": "The Amazon Resource Name (ARN) of the policy that contains the test.
", "GetAutomatedReasoningPolicyTestResultRequest$policyArn": "The Amazon Resource Name (ARN) of the Automated Reasoning policy.
", "GuardrailAutomatedReasoningPolicyConfigPoliciesList$member": null, "GuardrailAutomatedReasoningPolicyPoliciesList$member": null, "ListAutomatedReasoningPoliciesRequest$policyArn": "Optional filter to list only the policy versions with the specified Amazon Resource Name (ARN). If not provided, the DRAFT versions for all policies are listed.
", "ListAutomatedReasoningPolicyBuildWorkflowsRequest$policyArn": "The Amazon Resource Name (ARN) of the Automated Reasoning policy whose build workflows you want to list.
", "ListAutomatedReasoningPolicyTestCasesRequest$policyArn": "The Amazon Resource Name (ARN) of the Automated Reasoning policy for which to list tests.
", "ListAutomatedReasoningPolicyTestResultsRequest$policyArn": "The Amazon Resource Name (ARN) of the Automated Reasoning policy whose test results you want to list.
", "StartAutomatedReasoningPolicyBuildWorkflowRequest$policyArn": "The Amazon Resource Name (ARN) of the Automated Reasoning policy for which to start the build workflow.
", "StartAutomatedReasoningPolicyBuildWorkflowResponse$policyArn": "The Amazon Resource Name (ARN) of the Automated Reasoning policy.
", "StartAutomatedReasoningPolicyTestWorkflowRequest$policyArn": "The Amazon Resource Name (ARN) of the Automated Reasoning policy to test.
", "StartAutomatedReasoningPolicyTestWorkflowResponse$policyArn": "The Amazon Resource Name (ARN) of the policy for which the test workflow was started.
", "UpdateAutomatedReasoningPolicyAnnotationsRequest$policyArn": "The Amazon Resource Name (ARN) of the Automated Reasoning policy whose annotations you want to update.
", "UpdateAutomatedReasoningPolicyAnnotationsResponse$policyArn": "The Amazon Resource Name (ARN) of the Automated Reasoning policy.
", "UpdateAutomatedReasoningPolicyRequest$policyArn": "The Amazon Resource Name (ARN) of the Automated Reasoning policy to update. This must be the ARN of a draft policy.
", "UpdateAutomatedReasoningPolicyResponse$policyArn": "The Amazon Resource Name (ARN) of the updated policy.
", "UpdateAutomatedReasoningPolicyTestCaseRequest$policyArn": "The Amazon Resource Name (ARN) of the Automated Reasoning policy that contains the test.
", "UpdateAutomatedReasoningPolicyTestCaseResponse$policyArn": "The Amazon Resource Name (ARN) of the policy that contains the updated test.
" } }, "AutomatedReasoningPolicyBuildDocumentContentType": { "base": null, "refs": { "AutomatedReasoningPolicyBuildWorkflowDocument$documentContentType": "The MIME type of the document content (e.g., text/plain, application/pdf, text/markdown).
", "GetAutomatedReasoningPolicyBuildWorkflowResponse$documentContentType": "The content type of the source document (e.g., text/plain, application/pdf).
" } }, "AutomatedReasoningPolicyBuildDocumentDescription": { "base": null, "refs": { "AutomatedReasoningPolicyBuildWorkflowDocument$documentDescription": "A detailed description of the document's content and how it should be used in the policy generation process.
", "GetAutomatedReasoningPolicyBuildWorkflowResponse$documentDescription": "A detailed description of the document's content and how it should be used in the policy generation process.
" } }, "AutomatedReasoningPolicyBuildDocumentName": { "base": null, "refs": { "AutomatedReasoningPolicyBuildWorkflowDocument$documentName": "A descriptive name for the document that helps identify its purpose and content.
", "GetAutomatedReasoningPolicyBuildWorkflowResponse$documentName": "The name of the source document used in the build workflow.
" } }, "AutomatedReasoningPolicyBuildLog": { "base": "Contains detailed logging information about the policy build process, including steps taken, decisions made, and any issues encountered.
", "refs": { "AutomatedReasoningPolicyBuildResultAssets$buildLog": "The complete build log containing detailed information about each step in the policy generation process.
" } }, "AutomatedReasoningPolicyBuildLogEntry": { "base": "Represents a single entry in the policy build log, containing information about a specific step or event in the build process.
", "refs": { "AutomatedReasoningPolicyBuildLogEntryList$member": null } }, "AutomatedReasoningPolicyBuildLogEntryList": { "base": null, "refs": { "AutomatedReasoningPolicyBuildLog$entries": "A list of log entries documenting each step in the policy build process, including timestamps, status, and detailed messages.
" } }, "AutomatedReasoningPolicyBuildMessageType": { "base": null, "refs": { "AutomatedReasoningPolicyBuildStepMessage$messageType": "The type of message (e.g., INFO, WARNING, ERROR) indicating its severity and purpose.
" } }, "AutomatedReasoningPolicyBuildResultAssetType": { "base": null, "refs": { "GetAutomatedReasoningPolicyBuildWorkflowResultAssetsRequest$assetType": "The type of asset to retrieve (e.g., BUILD_LOG, QUALITY_REPORT, POLICY_DEFINITION).
" } }, "AutomatedReasoningPolicyBuildResultAssets": { "base": "Contains the various assets generated during a policy build workflow, including logs, quality reports, and the final policy definition.
", "refs": { "GetAutomatedReasoningPolicyBuildWorkflowResultAssetsResponse$buildWorkflowAssets": "The requested build workflow asset. This is a union type that returns only one of the available asset types (logs, reports, or generated artifacts) based on the specific asset type requested in the API call.
" } }, "AutomatedReasoningPolicyBuildStep": { "base": "Represents a single step in the policy build process, containing context about what was being processed and any messages or results.
", "refs": { "AutomatedReasoningPolicyBuildStepList$member": null } }, "AutomatedReasoningPolicyBuildStepContext": { "base": "Provides context about what type of operation was being performed during a build step.
", "refs": { "AutomatedReasoningPolicyBuildStep$context": "Contextual information about what was being processed during this build step, such as the type of operation or the source material being analyzed.
" } }, "AutomatedReasoningPolicyBuildStepList": { "base": null, "refs": { "AutomatedReasoningPolicyBuildLogEntry$buildSteps": "Detailed information about the specific build steps that were executed, including any sub-operations or transformations.
" } }, "AutomatedReasoningPolicyBuildStepMessage": { "base": "Represents a message generated during a build step, providing information about what happened or any issues encountered.
", "refs": { "AutomatedReasoningPolicyBuildStepMessageList$member": null } }, "AutomatedReasoningPolicyBuildStepMessageList": { "base": null, "refs": { "AutomatedReasoningPolicyBuildStep$messages": "A list of messages generated during this build step, including informational messages, warnings, and error details.
" } }, "AutomatedReasoningPolicyBuildWorkflowDocument": { "base": "Represents a source document used in the policy build workflow, containing the content and metadata needed for policy generation.
", "refs": { "AutomatedReasoningPolicyBuildWorkflowDocumentList$member": null } }, "AutomatedReasoningPolicyBuildWorkflowDocumentDocumentBlob": { "base": null, "refs": { "AutomatedReasoningPolicyBuildWorkflowDocument$document": "The actual content of the source document that will be analyzed to extract policy rules and concepts.
" } }, "AutomatedReasoningPolicyBuildWorkflowDocumentList": { "base": null, "refs": { "AutomatedReasoningPolicyWorkflowTypeContent$documents": "The list of documents to be processed in a document ingestion workflow.
" } }, "AutomatedReasoningPolicyBuildWorkflowId": { "base": null, "refs": { "AutomatedReasoningPolicyBuildWorkflowSummary$buildWorkflowId": "The unique identifier of the build workflow.
", "CancelAutomatedReasoningPolicyBuildWorkflowRequest$buildWorkflowId": "The unique identifier of the build workflow to cancel. You can get this ID from the StartAutomatedReasoningPolicyBuildWorkflow response or by listing build workflows.
", "DeleteAutomatedReasoningPolicyBuildWorkflowRequest$buildWorkflowId": "The unique identifier of the build workflow to delete.
", "GetAutomatedReasoningPolicyAnnotationsRequest$buildWorkflowId": "The unique identifier of the build workflow whose annotations you want to retrieve.
", "GetAutomatedReasoningPolicyAnnotationsResponse$buildWorkflowId": "The unique identifier of the build workflow.
", "GetAutomatedReasoningPolicyBuildWorkflowRequest$buildWorkflowId": "The unique identifier of the build workflow to retrieve.
", "GetAutomatedReasoningPolicyBuildWorkflowResponse$buildWorkflowId": "The unique identifier of the build workflow.
", "GetAutomatedReasoningPolicyBuildWorkflowResultAssetsRequest$buildWorkflowId": "The unique identifier of the build workflow whose result assets you want to retrieve.
", "GetAutomatedReasoningPolicyBuildWorkflowResultAssetsResponse$buildWorkflowId": "The unique identifier of the build workflow.
", "GetAutomatedReasoningPolicyNextScenarioRequest$buildWorkflowId": "The unique identifier of the build workflow associated with the test scenarios.
", "GetAutomatedReasoningPolicyTestResultRequest$buildWorkflowId": "The build workflow identifier. The build workflow must display a COMPLETED status to get results.
The unique identifier of the build workflow whose test results you want to list.
", "StartAutomatedReasoningPolicyBuildWorkflowResponse$buildWorkflowId": "The unique identifier of the newly started build workflow. Use this ID to track the workflow's progress and retrieve its results.
", "StartAutomatedReasoningPolicyTestWorkflowRequest$buildWorkflowId": "The build workflow identifier. The build workflow must show a COMPLETED status before running tests.
The unique identifier of the build workflow whose annotations you want to update.
", "UpdateAutomatedReasoningPolicyAnnotationsResponse$buildWorkflowId": "The unique identifier of the build workflow.
" } }, "AutomatedReasoningPolicyBuildWorkflowRepairContent": { "base": "Contains content and instructions for repairing or improving an existing Automated Reasoning policy.
", "refs": { "AutomatedReasoningPolicyWorkflowTypeContent$policyRepairAssets": "The assets and instructions needed for a policy repair workflow, including repair annotations and guidance.
" } }, "AutomatedReasoningPolicyBuildWorkflowSource": { "base": "Defines the source content for a policy build workflow, which can include documents, repair instructions, or other input materials.
", "refs": { "StartAutomatedReasoningPolicyBuildWorkflowRequest$sourceContent": "The source content for the build workflow, such as documents to analyze or repair instructions for existing policies.
" } }, "AutomatedReasoningPolicyBuildWorkflowStatus": { "base": null, "refs": { "AutomatedReasoningPolicyBuildWorkflowSummary$status": "The current status of the build workflow (e.g., RUNNING, COMPLETED, FAILED, CANCELLED).
", "GetAutomatedReasoningPolicyBuildWorkflowResponse$status": "The current status of the build workflow (e.g., RUNNING, COMPLETED, FAILED, CANCELLED).
" } }, "AutomatedReasoningPolicyBuildWorkflowSummaries": { "base": null, "refs": { "ListAutomatedReasoningPolicyBuildWorkflowsResponse$automatedReasoningPolicyBuildWorkflowSummaries": "A list of build workflow summaries, each containing key information about a build workflow including its status and timestamps.
" } }, "AutomatedReasoningPolicyBuildWorkflowSummary": { "base": "Provides a summary of a policy build workflow, including its current status, timing information, and key identifiers.
", "refs": { "AutomatedReasoningPolicyBuildWorkflowSummaries$member": null } }, "AutomatedReasoningPolicyBuildWorkflowType": { "base": null, "refs": { "AutomatedReasoningPolicyBuildWorkflowSummary$buildWorkflowType": "The type of build workflow (e.g., DOCUMENT_INGESTION, POLICY_REPAIR).
", "GetAutomatedReasoningPolicyBuildWorkflowResponse$buildWorkflowType": "The type of build workflow being executed (e.g., DOCUMENT_INGESTION, POLICY_REPAIR).
", "StartAutomatedReasoningPolicyBuildWorkflowRequest$buildWorkflowType": "The type of build workflow to start (e.g., DOCUMENT_INGESTION for processing new documents, POLICY_REPAIR for fixing existing policies).
" } }, "AutomatedReasoningPolicyConflictedRuleIdList": { "base": null, "refs": { "AutomatedReasoningPolicyDefinitionQualityReport$conflictingRules": "A list of rules that may conflict with each other, potentially leading to inconsistent policy behavior.
" } }, "AutomatedReasoningPolicyDefinition": { "base": "Contains the formal logic rules, variables, and custom variable types that define an Automated Reasoning policy. The policy definition specifies the constraints used to validate foundation model responses for accuracy and logical consistency.
", "refs": { "AutomatedReasoningPolicyBuildResultAssets$policyDefinition": "The complete policy definition generated by the build workflow, containing all rules, variables, and custom types extracted from the source documents.
", "AutomatedReasoningPolicyBuildWorkflowSource$policyDefinition": "An existing policy definition that serves as the starting point for the build workflow, typically used in policy repair or update scenarios.
", "CreateAutomatedReasoningPolicyRequest$policyDefinition": "The policy definition that contains the formal logic rules, variables, and custom variable types used to validate foundation model responses in your application.
", "ExportAutomatedReasoningPolicyVersionResponse$policyDefinition": "The exported policy definition containing the formal logic rules, variables, and custom variable types.
", "UpdateAutomatedReasoningPolicyRequest$policyDefinition": "The updated policy definition containing the formal logic rules, variables, and types.
" } }, "AutomatedReasoningPolicyDefinitionElement": { "base": "Represents a single element in an Automated Reasoning policy definition, such as a rule, variable, or type definition.
", "refs": { "AutomatedReasoningPolicyBuildStep$priorElement": "Reference to the previous element or step in the build process, helping to trace the sequence of operations.
" } }, "AutomatedReasoningPolicyDefinitionQualityReport": { "base": "Provides a comprehensive analysis of the quality and completeness of an Automated Reasoning policy definition, highlighting potential issues and optimization opportunities.
", "refs": { "AutomatedReasoningPolicyBuildResultAssets$qualityReport": "A comprehensive report analyzing the quality of the generated policy, including metrics about rule coverage, potential conflicts, and unused elements.
" } }, "AutomatedReasoningPolicyDefinitionRule": { "base": "Represents a formal logic rule in an Automated Reasoning policy. For example, rules can be expressed as if-then statements that define logical constraints.
", "refs": { "AutomatedReasoningPolicyAddRuleMutation$rule": "The rule definition that specifies the formal logical expression and metadata for the new rule being added to the policy.
", "AutomatedReasoningPolicyDefinitionElement$policyDefinitionRule": "A rule element within the policy definition that contains a formal logical expression used for validation.
", "AutomatedReasoningPolicyDefinitionRuleList$member": null, "AutomatedReasoningPolicyUpdateRuleMutation$rule": "The updated rule definition containing the modified formal logical expression and any changed metadata for the existing rule.
" } }, "AutomatedReasoningPolicyDefinitionRuleAlternateExpression": { "base": null, "refs": { "AutomatedReasoningPolicyDefinitionRule$alternateExpression": "The human-readable form of the rule expression, often in natural language or simplified notation.
" } }, "AutomatedReasoningPolicyDefinitionRuleExpression": { "base": null, "refs": { "AutomatedReasoningPolicyAddRuleAnnotation$expression": "The formal logical expression that defines the rule, using mathematical notation and referencing policy variables and types.
", "AutomatedReasoningPolicyDefinitionRule$expression": "The formal logic expression of the rule.
", "AutomatedReasoningPolicyUpdateRuleAnnotation$expression": "The new formal logical expression for the rule, replacing the previous expression.
" } }, "AutomatedReasoningPolicyDefinitionRuleId": { "base": null, "refs": { "AutomatedReasoningCheckRule$id": "The unique identifier of the automated reasoning rule.
", "AutomatedReasoningPolicyConflictedRuleIdList$member": null, "AutomatedReasoningPolicyDefinitionRule$id": "The unique identifier of the rule within the policy.
", "AutomatedReasoningPolicyDefinitionRuleIdList$member": null, "AutomatedReasoningPolicyDeleteRuleAnnotation$ruleId": "The unique identifier of the rule to delete from the policy.
", "AutomatedReasoningPolicyDeleteRuleMutation$id": "The unique identifier of the rule to delete.
", "AutomatedReasoningPolicyDisjointedRuleIdList$member": null, "AutomatedReasoningPolicyUpdateRuleAnnotation$ruleId": "The unique identifier of the rule to update.
" } }, "AutomatedReasoningPolicyDefinitionRuleIdList": { "base": null, "refs": { "AutomatedReasoningPolicyScenario$ruleIds": "The list of rule identifiers that are expected to be triggered or evaluated by this test scenario.
", "AutomatedReasoningPolicyUpdateFromRuleFeedbackAnnotation$ruleIds": "The list of rule identifiers that the feedback applies to.
", "AutomatedReasoningPolicyUpdateFromScenarioFeedbackAnnotation$ruleIds": "The list of rule identifiers that were involved in the scenario being evaluated.
" } }, "AutomatedReasoningPolicyDefinitionRuleList": { "base": null, "refs": { "AutomatedReasoningPolicyDefinition$rules": "The formal logic rules extracted from the source document. Rules define the logical constraints that determine whether model responses are valid, invalid, or satisfiable.
" } }, "AutomatedReasoningPolicyDefinitionType": { "base": "Represents a custom user-defined viarble type in an Automated Reasoning policy. Types are enum-based and provide additional context beyond predefined variable types.
", "refs": { "AutomatedReasoningPolicyAddTypeMutation$type": "The type definition that specifies the name, description, and possible values for the new custom type being added to the policy.
", "AutomatedReasoningPolicyDefinitionElement$policyDefinitionType": "A custom type element within the policy definition that defines a set of possible values for variables.
", "AutomatedReasoningPolicyDefinitionTypeList$member": null, "AutomatedReasoningPolicyUpdateTypeMutation$type": "The updated type definition containing the modified name, description, or values for the existing custom type.
" } }, "AutomatedReasoningPolicyDefinitionTypeDescription": { "base": null, "refs": { "AutomatedReasoningPolicyAddTypeAnnotation$description": "A description of what the custom type represents and how it should be used in the policy.
", "AutomatedReasoningPolicyDefinitionType$description": "The description of what the custom type represents.
", "AutomatedReasoningPolicyUpdateTypeAnnotation$description": "The new description for the custom type, replacing the previous description.
" } }, "AutomatedReasoningPolicyDefinitionTypeList": { "base": null, "refs": { "AutomatedReasoningPolicyDefinition$types": "The custom user-defined vairable types used in the policy. Types are enum-based variable types that provide additional context beyond the predefined variable types.
" } }, "AutomatedReasoningPolicyDefinitionTypeName": { "base": null, "refs": { "AutomatedReasoningPolicyAddTypeAnnotation$name": "The name of the new custom type. This name will be used to reference the type in variable definitions and rules.
", "AutomatedReasoningPolicyAddVariableAnnotation$type": "The type of the variable, which can be a built-in type (like string or number) or a custom type defined in the policy.
", "AutomatedReasoningPolicyDefinitionType$name": "The name of the custom type.
", "AutomatedReasoningPolicyDefinitionTypeNameList$member": null, "AutomatedReasoningPolicyDefinitionTypeValuePair$typeName": "The name of the custom type that contains the referenced value.
", "AutomatedReasoningPolicyDefinitionVariable$type": "The data type of the variable. Valid types include bool, int, real, enum, and custom types that you can provide.
", "AutomatedReasoningPolicyDeleteTypeAnnotation$name": "The name of the custom type to delete from the policy. The type must not be referenced by any variables or rules.
", "AutomatedReasoningPolicyDeleteTypeMutation$name": "The name of the custom type to delete.
", "AutomatedReasoningPolicyUpdateTypeAnnotation$name": "The current name of the custom type to update.
", "AutomatedReasoningPolicyUpdateTypeAnnotation$newName": "The new name for the custom type, if you want to rename it. If not provided, the name remains unchanged.
" } }, "AutomatedReasoningPolicyDefinitionTypeNameList": { "base": null, "refs": { "AutomatedReasoningPolicyDefinitionQualityReport$unusedTypes": "A list of custom types that are defined but not referenced by any variables or rules, suggesting they may be unnecessary.
" } }, "AutomatedReasoningPolicyDefinitionTypeValue": { "base": "Represents a single value within a custom type definition, including its identifier and description.
", "refs": { "AutomatedReasoningPolicyDefinitionTypeValueList$member": null } }, "AutomatedReasoningPolicyDefinitionTypeValueDescription": { "base": null, "refs": { "AutomatedReasoningPolicyAddTypeValue$description": "A description of what this new type value represents and when it should be used.
", "AutomatedReasoningPolicyDefinitionTypeValue$description": "A human-readable description explaining what this type value represents and when it should be used.
", "AutomatedReasoningPolicyUpdateTypeValue$description": "The new description for the type value, replacing the previous description.
" } }, "AutomatedReasoningPolicyDefinitionTypeValueList": { "base": null, "refs": { "AutomatedReasoningPolicyAddTypeAnnotation$values": "The list of possible values that variables of this type can take, each with its own description and identifier.
", "AutomatedReasoningPolicyDefinitionType$values": "The possible values for this enum-based type, each with its own description.
" } }, "AutomatedReasoningPolicyDefinitionTypeValueName": { "base": null, "refs": { "AutomatedReasoningPolicyAddTypeValue$value": "The identifier or name of the new value to add to the type.
", "AutomatedReasoningPolicyDefinitionTypeValue$value": "The actual value or identifier for this type value.
", "AutomatedReasoningPolicyDefinitionTypeValuePair$valueName": "The name of the specific value within the type.
", "AutomatedReasoningPolicyDeleteTypeValue$value": "The identifier or name of the value to remove from the type.
", "AutomatedReasoningPolicyUpdateTypeValue$value": "The current identifier or name of the type value to update.
", "AutomatedReasoningPolicyUpdateTypeValue$newValue": "The new identifier or name for the type value, if you want to rename it.
" } }, "AutomatedReasoningPolicyDefinitionTypeValuePair": { "base": "Associates a type name with a specific value name, used for referencing type values in rules and other policy elements.
", "refs": { "AutomatedReasoningPolicyDefinitionTypeValuePairList$member": null } }, "AutomatedReasoningPolicyDefinitionTypeValuePairList": { "base": null, "refs": { "AutomatedReasoningPolicyDefinitionQualityReport$unusedTypeValues": "A list of type values that are defined but never used in any rules, indicating potential cleanup opportunities.
" } }, "AutomatedReasoningPolicyDefinitionVariable": { "base": "Represents a variable in an Automated Reasoning policy. Variables represent concepts that can have values assigned during natural language translation.
", "refs": { "AutomatedReasoningPolicyAddVariableMutation$variable": "The variable definition that specifies the name, type, and description for the new variable being added to the policy.
", "AutomatedReasoningPolicyDefinitionElement$policyDefinitionVariable": "A variable element within the policy definition that represents a concept used in logical expressions and rules.
", "AutomatedReasoningPolicyDefinitionVariableList$member": null, "AutomatedReasoningPolicyUpdateVariableMutation$variable": "The updated variable definition containing the modified name, type, or description for the existing variable.
" } }, "AutomatedReasoningPolicyDefinitionVariableDescription": { "base": null, "refs": { "AutomatedReasoningPolicyAddVariableAnnotation$description": "A description of what the variable represents and how it should be used in rules.
", "AutomatedReasoningPolicyDefinitionVariable$description": "The description of the variable that explains what it represents and how users might refer to it. Clear and comprehensive descriptions are essential for accurate natural language translation.
", "AutomatedReasoningPolicyUpdateVariableAnnotation$description": "The new description for the variable, replacing the previous description.
" } }, "AutomatedReasoningPolicyDefinitionVariableList": { "base": null, "refs": { "AutomatedReasoningPolicyDefinition$variables": "The variables that represent concepts in the policy. Variables can have values assigned when translating natural language into formal logic. Their descriptions are crucial for accurate translation.
" } }, "AutomatedReasoningPolicyDefinitionVariableName": { "base": null, "refs": { "AutomatedReasoningPolicyAddVariableAnnotation$name": "The name of the new variable. This name will be used to reference the variable in rule expressions.
", "AutomatedReasoningPolicyDefinitionVariable$name": "The name of the variable. Use descriptive names that clearly indicate the concept being represented.
", "AutomatedReasoningPolicyDefinitionVariableNameList$member": null, "AutomatedReasoningPolicyDeleteVariableAnnotation$name": "The name of the variable to delete from the policy. The variable must not be referenced by any rules.
", "AutomatedReasoningPolicyDeleteVariableMutation$name": "The name of the variable to delete.
", "AutomatedReasoningPolicyUpdateVariableAnnotation$name": "The current name of the variable to update.
", "AutomatedReasoningPolicyUpdateVariableAnnotation$newName": "The new name for the variable, if you want to rename it. If not provided, the name remains unchanged.
" } }, "AutomatedReasoningPolicyDefinitionVariableNameList": { "base": null, "refs": { "AutomatedReasoningPolicyDefinitionQualityReport$unusedVariables": "A list of variables that are defined but not referenced by any rules, suggesting they may be unnecessary.
", "AutomatedReasoningPolicyDisjointRuleSet$variables": "The set of variables that are used by the rules in this disjoint set.
" } }, "AutomatedReasoningPolicyDeleteRuleAnnotation": { "base": "An annotation for removing a rule from an Automated Reasoning policy.
", "refs": { "AutomatedReasoningPolicyAnnotation$deleteRule": "An operation to remove a rule from the policy.
" } }, "AutomatedReasoningPolicyDeleteRuleMutation": { "base": "A mutation operation that removes a rule from the policy definition during the build process.
", "refs": { "AutomatedReasoningPolicyMutation$deleteRule": "A mutation to remove a rule from the policy.
" } }, "AutomatedReasoningPolicyDeleteTypeAnnotation": { "base": "An annotation for removing a custom type from an Automated Reasoning policy.
", "refs": { "AutomatedReasoningPolicyAnnotation$deleteType": "An operation to remove a custom type from the policy. The type must not be referenced by any variables or rules.
" } }, "AutomatedReasoningPolicyDeleteTypeMutation": { "base": "A mutation operation that removes a custom type from the policy definition during the build process.
", "refs": { "AutomatedReasoningPolicyMutation$deleteType": "A mutation to remove a custom type from the policy.
" } }, "AutomatedReasoningPolicyDeleteTypeValue": { "base": "Represents a value to be removed from an existing custom type in the policy.
", "refs": { "AutomatedReasoningPolicyTypeValueAnnotation$deleteTypeValue": "An operation to remove a value from an existing custom type.
" } }, "AutomatedReasoningPolicyDeleteVariableAnnotation": { "base": "An annotation for removing a variable from an Automated Reasoning policy.
", "refs": { "AutomatedReasoningPolicyAnnotation$deleteVariable": "An operation to remove a variable from the policy. The variable must not be referenced by any rules.
" } }, "AutomatedReasoningPolicyDeleteVariableMutation": { "base": "A mutation operation that removes a variable from the policy definition during the build process.
", "refs": { "AutomatedReasoningPolicyMutation$deleteVariable": "A mutation to remove a variable from the policy.
" } }, "AutomatedReasoningPolicyDescription": { "base": null, "refs": { "AutomatedReasoningPolicySummary$description": "The description of the policy.
", "CreateAutomatedReasoningPolicyRequest$description": "A description of the Automated Reasoning policy. Use this to provide context about the policy's purpose and the types of validations it performs.
", "CreateAutomatedReasoningPolicyResponse$description": "The description of the Automated Reasoning policy.
", "CreateAutomatedReasoningPolicyVersionResponse$description": "The description of the policy version.
", "GetAutomatedReasoningPolicyResponse$description": "The description of the policy.
", "UpdateAutomatedReasoningPolicyRequest$description": "The updated description for the Automated Reasoning policy.
" } }, "AutomatedReasoningPolicyDisjointRuleSet": { "base": "Represents a set of rules that operate on completely separate variables, indicating they address different concerns or domains within the policy.
", "refs": { "AutomatedReasoningPolicyDisjointRuleSetList$member": null } }, "AutomatedReasoningPolicyDisjointRuleSetList": { "base": null, "refs": { "AutomatedReasoningPolicyDefinitionQualityReport$disjointRuleSets": "Groups of rules that operate on completely separate sets of variables, indicating the policy may be addressing multiple unrelated concerns.
" } }, "AutomatedReasoningPolicyDisjointedRuleIdList": { "base": null, "refs": { "AutomatedReasoningPolicyDisjointRuleSet$rules": "The list of rules that form this disjoint set, all operating on the same set of variables.
" } }, "AutomatedReasoningPolicyFormatVersion": { "base": null, "refs": { "AutomatedReasoningPolicyDefinition$version": "The version of the policy definition format.
" } }, "AutomatedReasoningPolicyHash": { "base": null, "refs": { "CreateAutomatedReasoningPolicyResponse$definitionHash": "The hash of the policy definition. This is used as a concurrency token for creating policy versions that you can use in your application.
", "CreateAutomatedReasoningPolicyVersionRequest$lastUpdatedDefinitionHash": "The hash of the current policy definition used as a concurrency token to ensure the policy hasn't been modified since you last retrieved it.
", "CreateAutomatedReasoningPolicyVersionResponse$definitionHash": "The hash of the policy definition for this version.
", "GetAutomatedReasoningPolicyAnnotationsResponse$annotationSetHash": "A hash value representing the current state of the annotations. This is used for optimistic concurrency control when updating annotations.
", "GetAutomatedReasoningPolicyResponse$definitionHash": "The hash of the policy definition used as a concurrency token.
", "UpdateAutomatedReasoningPolicyAnnotationsRequest$lastUpdatedAnnotationSetHash": "The hash value of the annotation set that you're updating. This is used for optimistic concurrency control to prevent conflicting updates.
", "UpdateAutomatedReasoningPolicyAnnotationsResponse$annotationSetHash": "The new hash value representing the updated state of the annotations.
", "UpdateAutomatedReasoningPolicyResponse$definitionHash": "The hash of the updated policy definition.
" } }, "AutomatedReasoningPolicyId": { "base": null, "refs": { "AutomatedReasoningPolicySummary$policyId": "The unique identifier of the policy.
", "GetAutomatedReasoningPolicyResponse$policyId": "The unique identifier of the policy.
" } }, "AutomatedReasoningPolicyIngestContentAnnotation": { "base": "An annotation for processing and incorporating new content into an Automated Reasoning policy.
", "refs": { "AutomatedReasoningPolicyAnnotation$ingestContent": "An operation to process and incorporate new content into the policy, extracting additional rules and concepts.
" } }, "AutomatedReasoningPolicyMutation": { "base": "A container for various mutation operations that can be applied to an Automated Reasoning policy, including adding, updating, and deleting policy elements.
", "refs": { "AutomatedReasoningPolicyBuildStepContext$mutation": "Indicates that this build step involved modifying the policy structure, such as adding or updating rules, variables, or types.
" } }, "AutomatedReasoningPolicyName": { "base": null, "refs": { "AutomatedReasoningPolicySummary$name": "The name of the policy.
", "CreateAutomatedReasoningPolicyRequest$name": "A unique name for the Automated Reasoning policy. The name must be between 1 and 63 characters and can contain letters, numbers, hyphens, and underscores.
", "CreateAutomatedReasoningPolicyResponse$name": "The name of the Automated Reasoning policy.
", "CreateAutomatedReasoningPolicyVersionResponse$name": "The name of the policy version.
", "GetAutomatedReasoningPolicyAnnotationsResponse$name": "The name of the Automated Reasoning policy.
", "GetAutomatedReasoningPolicyResponse$name": "The name of the policy.
", "UpdateAutomatedReasoningPolicyRequest$name": "The updated name for the Automated Reasoning policy.
", "UpdateAutomatedReasoningPolicyResponse$name": "The updated name of the policy.
" } }, "AutomatedReasoningPolicyPlanning": { "base": "Represents the planning phase of policy build workflow, where the system analyzes source content and determines what operations to perform.
", "refs": { "AutomatedReasoningPolicyBuildStepContext$planning": "Indicates that this build step was part of the planning phase, where the system determines what operations to perform.
" } }, "AutomatedReasoningPolicyScenario": { "base": "Represents a test scenario used to validate an Automated Reasoning policy, including the test conditions and expected outcomes.
", "refs": { "GetAutomatedReasoningPolicyNextScenarioResponse$scenario": "The next test scenario to validate, including the test expression and expected results.
" } }, "AutomatedReasoningPolicyScenarioAlternateExpression": { "base": null, "refs": { "AutomatedReasoningPolicyScenario$alternateExpression": "An alternative way to express the same test scenario, used for validation and comparison purposes.
" } }, "AutomatedReasoningPolicyScenarioExpression": { "base": null, "refs": { "AutomatedReasoningPolicyScenario$expression": "The logical expression or condition that defines this test scenario.
", "AutomatedReasoningPolicyUpdateFromScenarioFeedbackAnnotation$scenarioExpression": "The logical expression that defines the test scenario that generated this feedback.
" } }, "AutomatedReasoningPolicySummaries": { "base": null, "refs": { "ListAutomatedReasoningPoliciesResponse$automatedReasoningPolicySummaries": "A list of Automated Reasoning policy summaries.
" } }, "AutomatedReasoningPolicySummary": { "base": "Contains summary information about an Automated Reasoning policy, including metadata and timestamps.
", "refs": { "AutomatedReasoningPolicySummaries$member": null } }, "AutomatedReasoningPolicyTestCase": { "base": "Represents a test for validating an Automated Reasoning policy. tests contain sample inputs and expected outcomes to verify policy behavior.
", "refs": { "AutomatedReasoningPolicyTestCaseList$member": null, "AutomatedReasoningPolicyTestResult$testCase": "The test case that was executed, including the input content, expected results, and configuration parameters used during validation.
", "GetAutomatedReasoningPolicyTestCaseResponse$testCase": "The test details including the content, query, expected result, and metadata.
" } }, "AutomatedReasoningPolicyTestCaseId": { "base": null, "refs": { "AutomatedReasoningPolicyTestCase$testCaseId": "The unique identifier of the test.
", "AutomatedReasoningPolicyTestCaseIdList$member": null, "CreateAutomatedReasoningPolicyTestCaseResponse$testCaseId": "The unique identifier of the created test.
", "DeleteAutomatedReasoningPolicyTestCaseRequest$testCaseId": "The unique identifier of the test to delete.
", "GetAutomatedReasoningPolicyTestCaseRequest$testCaseId": "The unique identifier of the test to retrieve.
", "GetAutomatedReasoningPolicyTestResultRequest$testCaseId": "The unique identifier of the test for which to retrieve results.
", "UpdateAutomatedReasoningPolicyTestCaseRequest$testCaseId": "The unique identifier of the test to update.
", "UpdateAutomatedReasoningPolicyTestCaseResponse$testCaseId": "The unique identifier of the updated test.
" } }, "AutomatedReasoningPolicyTestCaseIdList": { "base": null, "refs": { "StartAutomatedReasoningPolicyTestWorkflowRequest$testCaseIds": "The list of test identifiers to run. If not provided, all tests for the policy are run.
" } }, "AutomatedReasoningPolicyTestCaseList": { "base": null, "refs": { "ListAutomatedReasoningPolicyTestCasesResponse$testCases": "A list of tests for the specified policy.
" } }, "AutomatedReasoningPolicyTestGuardContent": { "base": null, "refs": { "AutomatedReasoningPolicyTestCase$guardContent": "The output content to be validated by the policy, typically representing a foundation model response.
", "CreateAutomatedReasoningPolicyTestCaseRequest$guardContent": "The output content that's validated by the Automated Reasoning policy. This represents the foundation model response that will be checked for accuracy.
", "UpdateAutomatedReasoningPolicyTestCaseRequest$guardContent": "The updated content to be validated by the Automated Reasoning policy.
" } }, "AutomatedReasoningPolicyTestList": { "base": null, "refs": { "ListAutomatedReasoningPolicyTestResultsResponse$testResults": "A list of test results, each containing information about how the policy performed on specific test scenarios.
" } }, "AutomatedReasoningPolicyTestQueryContent": { "base": null, "refs": { "AutomatedReasoningPolicyTestCase$queryContent": "The input query or prompt that generated the content. This provides context for the validation.
", "CreateAutomatedReasoningPolicyTestCaseRequest$queryContent": "The input query or prompt that generated the content. This provides context for the validation.
", "UpdateAutomatedReasoningPolicyTestCaseRequest$queryContent": "The updated input query or prompt that generated the content.
" } }, "AutomatedReasoningPolicyTestResult": { "base": "Contains the results of testing an Automated Reasoning policy against various scenarios and validation checks.
", "refs": { "AutomatedReasoningPolicyTestList$member": null, "GetAutomatedReasoningPolicyTestResultResponse$testResult": "The test result containing validation findings, execution status, and detailed analysis.
" } }, "AutomatedReasoningPolicyTestRunResult": { "base": null, "refs": { "AutomatedReasoningPolicyTestResult$testRunResult": "The overall result of the test run, indicating whether the policy passed or failed validation.
" } }, "AutomatedReasoningPolicyTestRunStatus": { "base": null, "refs": { "AutomatedReasoningPolicyTestResult$testRunStatus": "The overall status of the test run (e.g., COMPLETED, FAILED, IN_PROGRESS).
" } }, "AutomatedReasoningPolicyTypeValueAnnotation": { "base": "An annotation for managing values within custom types, including adding, updating, or removing specific type values.
", "refs": { "AutomatedReasoningPolicyTypeValueAnnotationList$member": null } }, "AutomatedReasoningPolicyTypeValueAnnotationList": { "base": null, "refs": { "AutomatedReasoningPolicyUpdateTypeAnnotation$values": "The updated list of values for the custom type, which can include additions, modifications, or removals.
" } }, "AutomatedReasoningPolicyUpdateFromRuleFeedbackAnnotation": { "base": "An annotation for updating the policy based on feedback about how specific rules performed during testing or real-world usage.
", "refs": { "AutomatedReasoningPolicyAnnotation$updateFromRulesFeedback": "An operation to update the policy based on feedback about how specific rules performed during testing or validation.
" } }, "AutomatedReasoningPolicyUpdateFromScenarioFeedbackAnnotation": { "base": "An annotation for updating the policy based on feedback about how it performed on specific test scenarios.
", "refs": { "AutomatedReasoningPolicyAnnotation$updateFromScenarioFeedback": "An operation to update the policy based on feedback about how it performed on specific test scenarios.
" } }, "AutomatedReasoningPolicyUpdateRuleAnnotation": { "base": "An annotation for modifying an existing rule in an Automated Reasoning policy.
", "refs": { "AutomatedReasoningPolicyAnnotation$updateRule": "An operation to modify an existing rule in the policy, such as changing its logical expression or conditions.
" } }, "AutomatedReasoningPolicyUpdateRuleMutation": { "base": "A mutation operation that modifies an existing rule in the policy definition during the build process.
", "refs": { "AutomatedReasoningPolicyMutation$updateRule": "A mutation to modify an existing rule in the policy.
" } }, "AutomatedReasoningPolicyUpdateTypeAnnotation": { "base": "An annotation for modifying an existing custom type in an Automated Reasoning policy.
", "refs": { "AutomatedReasoningPolicyAnnotation$updateType": "An operation to modify an existing custom type in the policy, such as changing its name, description, or allowed values.
" } }, "AutomatedReasoningPolicyUpdateTypeMutation": { "base": "A mutation operation that modifies an existing custom type in the policy definition during the build process.
", "refs": { "AutomatedReasoningPolicyMutation$updateType": "A mutation to modify an existing custom type in the policy.
" } }, "AutomatedReasoningPolicyUpdateTypeValue": { "base": "Represents a modification to a value within an existing custom type.
", "refs": { "AutomatedReasoningPolicyTypeValueAnnotation$updateTypeValue": "An operation to modify an existing value within a custom type.
" } }, "AutomatedReasoningPolicyUpdateVariableAnnotation": { "base": "An annotation for modifying an existing variable in an Automated Reasoning policy.
", "refs": { "AutomatedReasoningPolicyAnnotation$updateVariable": "An operation to modify an existing variable in the policy, such as changing its name, type, or description.
" } }, "AutomatedReasoningPolicyUpdateVariableMutation": { "base": "A mutation operation that modifies an existing variable in the policy definition during the build process.
", "refs": { "AutomatedReasoningPolicyMutation$updateVariable": "A mutation to modify an existing variable in the policy.
" } }, "AutomatedReasoningPolicyVersion": { "base": null, "refs": { "AutomatedReasoningPolicySummary$version": "The version of the policy.
", "CreateAutomatedReasoningPolicyResponse$version": "The version number of the newly created Automated Reasoning policy. The initial version is always DRAFT.
", "CreateAutomatedReasoningPolicyVersionResponse$version": "The version number of the policy version.
", "GetAutomatedReasoningPolicyResponse$version": "The version of the policy.
" } }, "AutomatedReasoningPolicyWorkflowTypeContent": { "base": "Defines the content and configuration for different types of policy build workflows.
", "refs": { "AutomatedReasoningPolicyBuildWorkflowSource$workflowContent": "The actual content to be processed in the build workflow, such as documents to analyze or repair instructions to apply.
" } }, "BaseModelIdentifier": { "base": null, "refs": { "CreateModelCustomizationJobRequest$baseModelIdentifier": "Name of the base model.
" } }, "BatchDeleteEvaluationJobError": { "base": "A JSON array that provides the status of the evaluation jobs being deleted.
", "refs": { "BatchDeleteEvaluationJobErrors$member": null } }, "BatchDeleteEvaluationJobErrors": { "base": null, "refs": { "BatchDeleteEvaluationJobResponse$errors": "A JSON object containing the HTTP status codes and the ARNs of evaluation jobs that failed to be deleted.
" } }, "BatchDeleteEvaluationJobItem": { "base": "An evaluation job for deletion, and it’s current status.
", "refs": { "BatchDeleteEvaluationJobItems$member": null } }, "BatchDeleteEvaluationJobItems": { "base": null, "refs": { "BatchDeleteEvaluationJobResponse$evaluationJobs": "The list of evaluation jobs for deletion.
" } }, "BatchDeleteEvaluationJobRequest": { "base": null, "refs": { } }, "BatchDeleteEvaluationJobResponse": { "base": null, "refs": { } }, "BedrockEvaluatorModel": { "base": "The evaluator model used in knowledge base evaluation job or in model evaluation job that use a model as judge. This model computes all evaluation related metrics.
", "refs": { "BedrockEvaluatorModels$member": null } }, "BedrockEvaluatorModels": { "base": null, "refs": { "EvaluatorModelConfig$bedrockEvaluatorModels": "The evaluator model used in knowledge base evaluation job or in model evaluation job that use a model as judge. This model computes all evaluation related metrics.
" } }, "BedrockModelArn": { "base": null, "refs": { "ExternalSourcesRetrieveAndGenerateConfiguration$modelArn": "The Amazon Resource Name (ARN) of the foundation model or inference profile used to generate responses.
", "ImplicitFilterConfiguration$modelArn": "The Amazon Resource Name (ARN) of the foundation model used for implicit filtering. This model processes the query to extract relevant filtering criteria.
", "KnowledgeBaseRetrieveAndGenerateConfiguration$modelArn": "The Amazon Resource Name (ARN) of the foundation model or inference profile used to generate responses.
" } }, "BedrockModelId": { "base": null, "refs": { "CreateFoundationModelAgreementRequest$modelId": "Model Id of the model for the access request.
", "CreateFoundationModelAgreementResponse$modelId": "Model Id of the model for the access request.
", "DeleteFoundationModelAgreementRequest$modelId": "Model Id of the model access to delete.
", "FoundationModelDetails$modelId": "The model identifier.
", "FoundationModelSummary$modelId": "The model ID of the foundation model.
", "GetFoundationModelAvailabilityRequest$modelId": "The model Id of the foundation model.
", "GetFoundationModelAvailabilityResponse$modelId": "The model Id of the foundation model.
", "ListFoundationModelAgreementOffersRequest$modelId": "Model Id of the foundation model.
", "ListFoundationModelAgreementOffersResponse$modelId": "Model Id of the foundation model.
" } }, "BedrockRerankingModelArn": { "base": null, "refs": { "VectorSearchBedrockRerankingModelConfiguration$modelArn": "The Amazon Resource Name (ARN) of the foundation model to use for reranking. This model processes the query and search results to determine a more relevant ordering.
" } }, "Boolean": { "base": null, "refs": { "FoundationModelDetails$responseStreamingSupported": "Indicates whether the model supports streaming.
", "FoundationModelSummary$responseStreamingSupported": "Indicates whether the model supports streaming.
", "GuardrailContentFilter$inputEnabled": "Indicates whether guardrail evaluation is enabled on the input. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
", "GuardrailContentFilter$outputEnabled": "Indicates whether guardrail evaluation is enabled on the output. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
", "GuardrailContentFilterConfig$inputEnabled": "Specifies whether to enable guardrail evaluation on the input. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
", "GuardrailContentFilterConfig$outputEnabled": "Specifies whether to enable guardrail evaluation on the output. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
", "GuardrailContextualGroundingFilter$enabled": "Indicates whether contextual grounding is enabled for evaluation. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
", "GuardrailContextualGroundingFilterConfig$enabled": "Specifies whether to enable contextual grounding evaluation. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
", "GuardrailManagedWords$inputEnabled": "Indicates whether guardrail evaluation is enabled on the input. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
", "GuardrailManagedWords$outputEnabled": "Indicates whether guardrail evaluation is enabled on the output. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
", "GuardrailManagedWordsConfig$inputEnabled": "Specifies whether to enable guardrail evaluation on the input. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
", "GuardrailManagedWordsConfig$outputEnabled": "Specifies whether to enable guardrail evaluation on the output. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
", "GuardrailPiiEntity$inputEnabled": "Indicates whether guardrail evaluation is enabled on the input. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
", "GuardrailPiiEntity$outputEnabled": "Indicates whether guardrail evaluation is enabled on the output. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
", "GuardrailPiiEntityConfig$inputEnabled": "Specifies whether to enable guardrail evaluation on the input. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
", "GuardrailPiiEntityConfig$outputEnabled": "Specifies whether to enable guardrail evaluation on the output. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
", "GuardrailRegex$inputEnabled": "Indicates whether guardrail evaluation is enabled on the input. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
", "GuardrailRegex$outputEnabled": "Indicates whether guardrail evaluation is enabled on the output. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
", "GuardrailRegexConfig$inputEnabled": "Specifies whether to enable guardrail evaluation on the input. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
", "GuardrailRegexConfig$outputEnabled": "Specifies whether to enable guardrail evaluation on the output. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
", "GuardrailTopic$inputEnabled": "Indicates whether guardrail evaluation is enabled on the input. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
", "GuardrailTopic$outputEnabled": "Indicates whether guardrail evaluation is enabled on the output. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
", "GuardrailTopicConfig$inputEnabled": "Specifies whether to enable guardrail evaluation on the input. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
", "GuardrailTopicConfig$outputEnabled": "Specifies whether to enable guardrail evaluation on the output. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
", "GuardrailWord$inputEnabled": "Indicates whether guardrail evaluation is enabled on the input. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
", "GuardrailWord$outputEnabled": "Indicates whether guardrail evaluation is enabled on the output. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
", "GuardrailWordConfig$inputEnabled": "Specifies whether to enable guardrail evaluation on the intput. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
", "GuardrailWordConfig$outputEnabled": "Specifies whether to enable guardrail evaluation on the output. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
", "ListCustomModelsRequest$isOwned": "Return custom models depending on if the current account owns them (true) or if they were shared with the current account (false).
Set to include text data in the log delivery.
", "LoggingConfig$imageDataDeliveryEnabled": "Set to include image data in the log delivery.
", "LoggingConfig$embeddingDataDeliveryEnabled": "Set to include embeddings data in the log delivery.
", "LoggingConfig$videoDataDeliveryEnabled": "Set to include video data in the log delivery.
" } }, "BrandedName": { "base": null, "refs": { "FoundationModelDetails$modelName": "The model name.
", "FoundationModelDetails$providerName": "The model's provider name.
", "FoundationModelSummary$modelName": "The name of the model.
", "FoundationModelSummary$providerName": "The model's provider name.
" } }, "BucketName": { "base": null, "refs": { "S3Config$bucketName": "S3 bucket name.
" } }, "ByteContentBlob": { "base": null, "refs": { "ByteContentDoc$data": "The byte value of the file to upload, encoded as a Base-64 string.
" } }, "ByteContentDoc": { "base": "Contains the document contained in the wrapper object, along with its attributes/fields.
", "refs": { "ExternalSource$byteContent": "The identifier, content type, and data of the external source wrapper object.
" } }, "CancelAutomatedReasoningPolicyBuildWorkflowRequest": { "base": null, "refs": { } }, "CancelAutomatedReasoningPolicyBuildWorkflowResponse": { "base": null, "refs": { } }, "CloudWatchConfig": { "base": "CloudWatch logging configuration.
", "refs": { "LoggingConfig$cloudWatchConfig": "CloudWatch logging configuration.
" } }, "CommitmentDuration": { "base": null, "refs": { "CreateProvisionedModelThroughputRequest$commitmentDuration": "The commitment duration requested for the Provisioned Throughput. Billing occurs hourly and is discounted for longer commitment terms. To request a no-commit Provisioned Throughput, omit this field.
Custom models support all levels of commitment. To see which base models support no commitment, see Supported regions and models for Provisioned Throughput in the Amazon Bedrock User Guide
", "GetProvisionedModelThroughputResponse$commitmentDuration": "Commitment duration of the Provisioned Throughput.
", "ProvisionedModelSummary$commitmentDuration": "The duration for which the Provisioned Throughput was committed.
" } }, "ConflictException": { "base": "Error occurred because of a conflict while performing an operation.
", "refs": { } }, "ContentType": { "base": null, "refs": { "ByteContentDoc$contentType": "The MIME type of the document contained in the wrapper object.
" } }, "CreateAutomatedReasoningPolicyRequest": { "base": null, "refs": { } }, "CreateAutomatedReasoningPolicyResponse": { "base": null, "refs": { } }, "CreateAutomatedReasoningPolicyTestCaseRequest": { "base": null, "refs": { } }, "CreateAutomatedReasoningPolicyTestCaseResponse": { "base": null, "refs": { } }, "CreateAutomatedReasoningPolicyVersionRequest": { "base": null, "refs": { } }, "CreateAutomatedReasoningPolicyVersionResponse": { "base": null, "refs": { } }, "CreateCustomModelDeploymentRequest": { "base": null, "refs": { } }, "CreateCustomModelDeploymentResponse": { "base": null, "refs": { } }, "CreateCustomModelRequest": { "base": null, "refs": { } }, "CreateCustomModelResponse": { "base": null, "refs": { } }, "CreateEvaluationJobRequest": { "base": null, "refs": { } }, "CreateEvaluationJobResponse": { "base": null, "refs": { } }, "CreateFoundationModelAgreementRequest": { "base": null, "refs": { } }, "CreateFoundationModelAgreementResponse": { "base": null, "refs": { } }, "CreateGuardrailRequest": { "base": null, "refs": { } }, "CreateGuardrailResponse": { "base": null, "refs": { } }, "CreateGuardrailVersionRequest": { "base": null, "refs": { } }, "CreateGuardrailVersionResponse": { "base": null, "refs": { } }, "CreateInferenceProfileRequest": { "base": null, "refs": { } }, "CreateInferenceProfileResponse": { "base": null, "refs": { } }, "CreateMarketplaceModelEndpointRequest": { "base": null, "refs": { } }, "CreateMarketplaceModelEndpointResponse": { "base": null, "refs": { } }, "CreateModelCopyJobRequest": { "base": null, "refs": { } }, "CreateModelCopyJobResponse": { "base": null, "refs": { } }, "CreateModelCustomizationJobRequest": { "base": null, "refs": { } }, "CreateModelCustomizationJobResponse": { "base": null, "refs": { } }, "CreateModelImportJobRequest": { "base": null, "refs": { } }, "CreateModelImportJobResponse": { "base": null, "refs": { } }, "CreateModelInvocationJobRequest": { "base": null, "refs": { } }, "CreateModelInvocationJobResponse": { "base": null, "refs": { } }, "CreatePromptRouterRequest": { "base": null, "refs": { } }, "CreatePromptRouterResponse": { "base": null, "refs": { } }, "CreateProvisionedModelThroughputRequest": { "base": null, "refs": { } }, "CreateProvisionedModelThroughputResponse": { "base": null, "refs": { } }, "CustomMetricBedrockEvaluatorModel": { "base": "Defines the model you want to evaluate custom metrics in an Amazon Bedrock evaluation job.
", "refs": { "CustomMetricBedrockEvaluatorModels$member": null } }, "CustomMetricBedrockEvaluatorModels": { "base": null, "refs": { "CustomMetricEvaluatorModelConfig$bedrockEvaluatorModels": "Defines the model you want to evaluate custom metrics in an Amazon Bedrock evaluation job.
" } }, "CustomMetricDefinition": { "base": "The definition of a custom metric for use in an Amazon Bedrock evaluation job. A custom metric definition includes a metric name, prompt (instructions) and optionally, a rating scale. Your prompt must include a task description and input variables. The required input variables are different for model-as-a-judge and RAG evaluations.
For more information about how to define a custom metric in Amazon Bedrock, see Create a prompt for a custom metrics (LLM-as-a-judge model evaluations) and Create a prompt for a custom metrics (RAG evaluations).
", "refs": { "AutomatedEvaluationCustomMetricSource$customMetricDefinition": "The definition of a custom metric for use in an Amazon Bedrock evaluation job.
" } }, "CustomMetricEvaluatorModelConfig": { "base": "Configuration of the evaluator model you want to use to evaluate custom metrics in an Amazon Bedrock evaluation job.
", "refs": { "AutomatedEvaluationCustomMetricConfig$evaluatorModelConfig": "Configuration of the evaluator model you want to use to evaluate custom metrics in an Amazon Bedrock evaluation job.
" } }, "CustomMetricInstructions": { "base": null, "refs": { "CustomMetricDefinition$instructions": "The prompt for a custom metric that instructs the evaluator model how to rate the model or RAG source under evaluation.
" } }, "CustomModelArn": { "base": null, "refs": { "CreateCustomModelDeploymentRequest$modelArn": "The Amazon Resource Name (ARN) of the custom model to deploy for on-demand inference. The custom model must be in the Active state.
The Amazon Resource Name (ARN) of the custom model.
", "GetCustomModelDeploymentResponse$modelArn": "The Amazon Resource Name (ARN) of the custom model associated with this deployment.
", "GetModelCopyJobResponse$targetModelArn": "The Amazon Resource Name (ARN) of the copied model.
", "GetModelCustomizationJobResponse$outputModelArn": "The Amazon Resource Name (ARN) of the output model.
", "ListCustomModelDeploymentsRequest$modelArnEquals": "Filters deployments by the Amazon Resource Name (ARN) of the associated custom model.
", "ModelCopyJobSummary$targetModelArn": "The Amazon Resource Name (ARN) of the copied model.
", "ModelCustomizationJobSummary$customModelArn": "Amazon Resource Name (ARN) of the custom model.
" } }, "CustomModelDeploymentArn": { "base": null, "refs": { "CreateCustomModelDeploymentResponse$customModelDeploymentArn": "The Amazon Resource Name (ARN) of the custom model deployment. Use this ARN as the modelId parameter when invoking the model with the InvokeModel or Converse operations.
The Amazon Resource Name (ARN) of the custom model deployment.
", "GetCustomModelDeploymentResponse$customModelDeploymentArn": "The Amazon Resource Name (ARN) of the custom model deployment.
" } }, "CustomModelDeploymentDescription": { "base": null, "refs": { "CreateCustomModelDeploymentRequest$description": "A description for the custom model deployment to help you identify its purpose.
", "GetCustomModelDeploymentResponse$description": "The description of the custom model deployment.
" } }, "CustomModelDeploymentIdentifier": { "base": null, "refs": { "DeleteCustomModelDeploymentRequest$customModelDeploymentIdentifier": "The Amazon Resource Name (ARN) or name of the custom model deployment to delete.
", "GetCustomModelDeploymentRequest$customModelDeploymentIdentifier": "The Amazon Resource Name (ARN) or name of the custom model deployment to retrieve information about.
" } }, "CustomModelDeploymentStatus": { "base": null, "refs": { "CustomModelDeploymentSummary$status": "The status of the custom model deployment. Possible values are CREATING, ACTIVE, and FAILED.
The status of the custom model deployment. Possible values are:
CREATING - The deployment is being set up and prepared for inference.
ACTIVE - The deployment is ready and available for inference requests.
FAILED - The deployment failed to be created or became unavailable.
Filters deployments by status. Valid values are CREATING, ACTIVE, and FAILED.
Contains summary information about a custom model deployment, including its ARN, name, status, and associated custom model.
", "refs": { "CustomModelDeploymentSummaryList$member": null } }, "CustomModelDeploymentSummaryList": { "base": null, "refs": { "ListCustomModelDeploymentsResponse$modelDeploymentSummaries": "A list of custom model deployment summaries.
" } }, "CustomModelName": { "base": null, "refs": { "CreateCustomModelRequest$modelName": "A unique name for the custom model.
", "CreateModelCopyJobRequest$targetModelName": "A name for the copied model.
", "CreateModelCustomizationJobRequest$customModelName": "A name for the resulting custom model.
", "CustomModelSummary$modelName": "The name of the custom model.
", "GetCustomModelResponse$modelName": "Model name associated with this model.
", "GetModelCopyJobResponse$targetModelName": "The name of the copied model.
", "GetModelCopyJobResponse$sourceModelName": "The name of the original model being copied.
", "GetModelCustomizationJobResponse$outputModelName": "The name of the output model.
", "ListCustomModelsRequest$nameContains": "Return custom models only if the job name contains these characters.
", "ListModelCopyJobsRequest$targetModelNameContains": "Filters for model copy jobs in which the name of the copied model contains the string that you specify.
", "ModelCopyJobSummary$targetModelName": "The name of the copied model.
", "ModelCopyJobSummary$sourceModelName": "The name of the original model being copied.
", "ModelCustomizationJobSummary$customModelName": "Name of the custom model.
" } }, "CustomModelSummary": { "base": "Summary information for a custom model.
", "refs": { "CustomModelSummaryList$member": null } }, "CustomModelSummaryList": { "base": null, "refs": { "ListCustomModelsResponse$modelSummaries": "Model summaries.
" } }, "CustomModelUnits": { "base": "A CustomModelUnit (CMU) is an abstract view of the hardware utilization that Amazon Bedrock needs to host a single copy of your custom model. A model copy represents a single instance of your imported model that is ready to serve inference requests. Amazon Bedrock determines the number of custom model units that a model copy needs when you import the custom model.
You can use CustomModelUnits to estimate the cost of running your custom model. For more information, see Calculate the cost of running a custom model in the Amazon Bedrock user guide.
Information about the hardware utilization for a single copy of the model.
" } }, "CustomModelUnitsVersion": { "base": null, "refs": { "CustomModelUnits$customModelUnitsVersion": "The version of the custom model unit. Use to determine the billing rate for the custom model unit.
" } }, "CustomizationConfig": { "base": "A model customization configuration
", "refs": { "CreateModelCustomizationJobRequest$customizationConfig": "The customization configuration for the model customization job.
", "GetCustomModelResponse$customizationConfig": "The customization configuration for the custom model.
", "GetModelCustomizationJobResponse$customizationConfig": "The customization configuration for the model customization job.
" } }, "CustomizationType": { "base": null, "refs": { "CreateModelCustomizationJobRequest$customizationType": "The customization type.
", "CustomModelSummary$customizationType": "Specifies whether to carry out continued pre-training of a model or whether to fine-tune it. For more information, see Custom models.
", "GetCustomModelResponse$customizationType": "The type of model customization.
", "GetModelCustomizationJobResponse$customizationType": "The type of model customization.
", "ModelCustomizationJobSummary$customizationType": "Specifies whether to carry out continued pre-training of a model or whether to fine-tune it. For more information, see Custom models.
" } }, "DataProcessingDetails": { "base": "For a Distillation job, the status details for the data processing sub-task of the job.
", "refs": { "StatusDetails$dataProcessingDetails": "The status details for the data processing sub-task of the job.
" } }, "DeleteAutomatedReasoningPolicyBuildWorkflowRequest": { "base": null, "refs": { } }, "DeleteAutomatedReasoningPolicyBuildWorkflowResponse": { "base": null, "refs": { } }, "DeleteAutomatedReasoningPolicyRequest": { "base": null, "refs": { } }, "DeleteAutomatedReasoningPolicyResponse": { "base": null, "refs": { } }, "DeleteAutomatedReasoningPolicyTestCaseRequest": { "base": null, "refs": { } }, "DeleteAutomatedReasoningPolicyTestCaseResponse": { "base": null, "refs": { } }, "DeleteCustomModelDeploymentRequest": { "base": null, "refs": { } }, "DeleteCustomModelDeploymentResponse": { "base": null, "refs": { } }, "DeleteCustomModelRequest": { "base": null, "refs": { } }, "DeleteCustomModelResponse": { "base": null, "refs": { } }, "DeleteFoundationModelAgreementRequest": { "base": null, "refs": { } }, "DeleteFoundationModelAgreementResponse": { "base": null, "refs": { } }, "DeleteGuardrailRequest": { "base": null, "refs": { } }, "DeleteGuardrailResponse": { "base": null, "refs": { } }, "DeleteImportedModelRequest": { "base": null, "refs": { } }, "DeleteImportedModelResponse": { "base": null, "refs": { } }, "DeleteInferenceProfileRequest": { "base": null, "refs": { } }, "DeleteInferenceProfileResponse": { "base": null, "refs": { } }, "DeleteMarketplaceModelEndpointRequest": { "base": null, "refs": { } }, "DeleteMarketplaceModelEndpointResponse": { "base": null, "refs": { } }, "DeleteModelInvocationLoggingConfigurationRequest": { "base": null, "refs": { } }, "DeleteModelInvocationLoggingConfigurationResponse": { "base": null, "refs": { } }, "DeletePromptRouterRequest": { "base": null, "refs": { } }, "DeletePromptRouterResponse": { "base": null, "refs": { } }, "DeleteProvisionedModelThroughputRequest": { "base": null, "refs": { } }, "DeleteProvisionedModelThroughputResponse": { "base": null, "refs": { } }, "DeregisterMarketplaceModelEndpointRequest": { "base": null, "refs": { } }, "DeregisterMarketplaceModelEndpointResponse": { "base": null, "refs": { } }, "DimensionalPriceRate": { "base": "Dimensional price rate.
", "refs": { "RateCard$member": null } }, "DistillationConfig": { "base": "Settings for distilling a foundation model into a smaller and more efficient model.
", "refs": { "CustomizationConfig$distillationConfig": "The Distillation configuration for the custom model.
" } }, "EndpointConfig": { "base": "Specifies the configuration for the endpoint.
", "refs": { "CreateMarketplaceModelEndpointRequest$endpointConfig": "The configuration for the endpoint, including the number and type of instances to use.
", "MarketplaceModelEndpoint$endpointConfig": "The configuration of the endpoint, including the number and type of instances used.
", "UpdateMarketplaceModelEndpointRequest$endpointConfig": "The new configuration for the endpoint, including the number and type of instances to use.
" } }, "EndpointName": { "base": null, "refs": { "CreateMarketplaceModelEndpointRequest$endpointName": "The name of the endpoint. This name must be unique within your Amazon Web Services account and region.
" } }, "EntitlementAvailability": { "base": null, "refs": { "GetFoundationModelAvailabilityResponse$entitlementAvailability": "Entitlement availability.
" } }, "ErrorMessage": { "base": null, "refs": { "CustomModelDeploymentSummary$failureMessage": "If the deployment status is FAILED, this field contains a message describing the failure reason.
If the deployment status is FAILED, this field contains a message describing the failure reason.
A failure message for any issues that occurred when creating the custom model. This is included for only a failed CreateCustomModel operation.
", "GetModelCopyJobResponse$failureMessage": "An error message for why the model copy job failed.
", "GetModelCustomizationJobResponse$failureMessage": "Information about why the job failed.
", "GetModelImportJobResponse$failureMessage": "Information about why the import job failed.
", "GetProvisionedModelThroughputResponse$failureMessage": "A failure message for any issues that occurred during creation, updating, or deletion of the Provisioned Throughput.
", "ModelCopyJobSummary$failureMessage": "If a model fails to be copied, a message describing why the job failed is included here.
" } }, "ErrorMessages": { "base": null, "refs": { "GetEvaluationJobResponse$failureMessages": "A list of strings that specify why the evaluation job failed to create.
" } }, "EvaluationBedrockKnowledgeBaseIdentifiers": { "base": null, "refs": { "EvaluationRagConfigSummary$bedrockKnowledgeBaseIdentifiers": "The Amazon Resource Names (ARNs) of the Knowledge Base resources used for a Knowledge Base evaluation job where Amazon Bedrock invokes the Knowledge Base for you.
", "EvaluationSummary$ragIdentifiers": "The Amazon Resource Names (ARNs) of the knowledge base resources used for a knowledge base evaluation job.
" } }, "EvaluationBedrockModel": { "base": "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.
Defines the Amazon Bedrock model or inference profile and inference parameters you want used.
" } }, "EvaluationBedrockModelIdentifier": { "base": null, "refs": { "EvaluationBedrockModel$modelIdentifier": "The ARN of the Amazon Bedrock model or inference profile specified.
", "EvaluationBedrockModelIdentifiers$member": null } }, "EvaluationBedrockModelIdentifiers": { "base": null, "refs": { "EvaluationModelConfigSummary$bedrockModelIdentifiers": "The Amazon Resource Names (ARNs) of the models used for the evaluation job.
", "EvaluationSummary$modelIdentifiers": "The Amazon Resource Names (ARNs) of the model(s) used for the evaluation job.
" } }, "EvaluationConfig": { "base": "The configuration details of either an automated or human-based evaluation job.
", "refs": { "CreateEvaluationJobRequest$evaluationConfig": "Contains the configuration details of either an automated or human-based evaluation job.
", "GetEvaluationJobResponse$evaluationConfig": "Contains the configuration details of either an automated or human-based evaluation job.
" } }, "EvaluationDataset": { "base": "Used to specify the name of a built-in prompt dataset and optionally, the Amazon S3 bucket where a custom prompt dataset is saved.
", "refs": { "EvaluationDatasetMetricConfig$dataset": "Specifies the prompt dataset.
" } }, "EvaluationDatasetLocation": { "base": "The location in Amazon S3 where your prompt dataset is stored.
", "refs": { "EvaluationDataset$datasetLocation": "For custom prompt datasets, you must specify the location in Amazon S3 where the prompt dataset is saved.
" } }, "EvaluationDatasetMetricConfig": { "base": "Defines the prompt datasets, built-in metric names and custom metric names, and the task type.
", "refs": { "EvaluationDatasetMetricConfigs$member": null } }, "EvaluationDatasetMetricConfigs": { "base": null, "refs": { "AutomatedEvaluationConfig$datasetMetricConfigs": "Configuration details of the prompt datasets and metrics you want to use for your evaluation job.
", "HumanEvaluationConfig$datasetMetricConfigs": "Use to specify the metrics, task, and prompt dataset to be used in your model evaluation job.
" } }, "EvaluationDatasetName": { "base": null, "refs": { "EvaluationDataset$name": "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.
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.
", "refs": { "CreateEvaluationJobRequest$inferenceConfig": "Contains the configuration details of the inference model for the evaluation job.
For model evaluation jobs, automated jobs support a single model or inference profile, and jobs that use human workers support two models or inference profiles.
", "GetEvaluationJobResponse$inferenceConfig": "Contains the configuration details of the inference model used for the evaluation job.
" } }, "EvaluationInferenceConfigSummary": { "base": "Identifies the models, Knowledge Bases, or other RAG sources evaluated in a model or Knowledge Base evaluation job.
", "refs": { "EvaluationSummary$inferenceConfigSummary": "Identifies the models, Knowledge Bases, or other RAG sources evaluated in a model or Knowledge Base evaluation job.
" } }, "EvaluationJobArn": { "base": null, "refs": { "CreateEvaluationJobResponse$jobArn": "The Amazon Resource Name (ARN) of the evaluation job.
", "EvaluationSummary$jobArn": "The Amazon Resource Name (ARN) of the evaluation job.
", "GetEvaluationJobResponse$jobArn": "The Amazon Resource Name (ARN) of the evaluation job.
" } }, "EvaluationJobDescription": { "base": null, "refs": { "CreateEvaluationJobRequest$jobDescription": "A description of the evaluation job.
", "GetEvaluationJobResponse$jobDescription": "The description of the evaluation job.
" } }, "EvaluationJobIdentifier": { "base": null, "refs": { "BatchDeleteEvaluationJobError$jobIdentifier": "The ARN of the evaluation job being deleted.
", "BatchDeleteEvaluationJobItem$jobIdentifier": "The Amazon Resource Name (ARN) of the evaluation job for deletion.
", "EvaluationJobIdentifiers$member": null, "GetEvaluationJobRequest$jobIdentifier": "The Amazon Resource Name (ARN) of the evaluation job you want get information on.
", "StopEvaluationJobRequest$jobIdentifier": "The Amazon Resource Name (ARN) of the evaluation job you want to stop.
" } }, "EvaluationJobIdentifiers": { "base": null, "refs": { "BatchDeleteEvaluationJobRequest$jobIdentifiers": "A list of one or more evaluation job Amazon Resource Names (ARNs) you want to delete.
" } }, "EvaluationJobName": { "base": null, "refs": { "CreateEvaluationJobRequest$jobName": "A name for the evaluation job. Names must unique with your Amazon Web Services account, and your account's Amazon Web Services region.
", "EvaluationSummary$jobName": "The name for the evaluation job.
", "GetEvaluationJobResponse$jobName": "The name for the evaluation job.
", "ListEvaluationJobsRequest$nameContains": "A filter to only list evaluation jobs that contain a specified string in the job name.
" } }, "EvaluationJobStatus": { "base": null, "refs": { "BatchDeleteEvaluationJobItem$jobStatus": "The status of the evaluation job for deletion.
", "EvaluationSummary$status": "The current status of the evaluation job.
", "GetEvaluationJobResponse$status": "The current status of the evaluation job.
", "ListEvaluationJobsRequest$statusEquals": "A filter to only list evaluation jobs that are of a certain status.
" } }, "EvaluationJobType": { "base": null, "refs": { "EvaluationSummary$jobType": "Specifies whether the evaluation job is automated or human-based.
", "GetEvaluationJobResponse$jobType": "Specifies whether the evaluation job is automated or human-based.
" } }, "EvaluationMetricDescription": { "base": null, "refs": { "HumanEvaluationCustomMetric$description": "An optional description of the metric. Use this parameter to provide more details about the metric.
" } }, "EvaluationMetricName": { "base": null, "refs": { "EvaluationMetricNames$member": null, "HumanEvaluationCustomMetric$name": "The name of the metric. Your human evaluators will see this name in the evaluation UI.
" } }, "EvaluationMetricNames": { "base": null, "refs": { "EvaluationDatasetMetricConfig$metricNames": "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.ContextCoverage\".
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 models used in the model evaluation job.
", "refs": { "EvaluationModelConfigs$member": null } }, "EvaluationModelConfigSummary": { "base": "A summary of the models used in an Amazon Bedrock model evaluation job. These resources can be models in Amazon Bedrock or models outside of Amazon Bedrock that you use to generate your own inference response data.
", "refs": { "EvaluationInferenceConfigSummary$modelConfigSummary": "A summary of the models used in an Amazon Bedrock model evaluation job. These resources can be models in Amazon Bedrock or models outside of Amazon Bedrock that you use to generate your own inference response data.
" } }, "EvaluationModelConfigs": { "base": null, "refs": { "EvaluationInferenceConfig$models": "Specifies the inference models.
" } }, "EvaluationModelInferenceParams": { "base": null, "refs": { "EvaluationBedrockModel$inferenceParams": "Each Amazon Bedrock support different inference parameters that change how the model behaves during inference.
" } }, "EvaluationOutputDataConfig": { "base": "The Amazon S3 location where the results of your evaluation job are saved.
", "refs": { "CreateEvaluationJobRequest$outputDataConfig": "Contains the configuration details of the Amazon S3 bucket for storing the results of the evaluation job.
", "GetEvaluationJobResponse$outputDataConfig": "Contains the configuration details of the Amazon S3 bucket for storing the results of the evaluation job.
" } }, "EvaluationPrecomputedInferenceSource": { "base": "A summary of a model used for a model evaluation job where you provide your own inference response data.
", "refs": { "EvaluationModelConfig$precomputedInferenceSource": "Defines the model used to generate inference response data for a model evaluation job where you provide your own inference response data.
" } }, "EvaluationPrecomputedInferenceSourceIdentifier": { "base": null, "refs": { "EvaluationPrecomputedInferenceSource$inferenceSourceIdentifier": "A label that identifies a model used in a model evaluation job where you provide your own inference response data.
", "EvaluationPrecomputedInferenceSourceIdentifiers$member": null } }, "EvaluationPrecomputedInferenceSourceIdentifiers": { "base": null, "refs": { "EvaluationModelConfigSummary$precomputedInferenceSourceIdentifiers": "A label that identifies the models used for a model evaluation job where you provide your own inference response data.
" } }, "EvaluationPrecomputedRagSourceConfig": { "base": "A summary of a RAG source used for a Knowledge Base evaluation job where you provide your own inference response data.
", "refs": { "RAGConfig$precomputedRagSourceConfig": "Contains configuration details about the RAG source used to generate inference response data for a Knowledge Base evaluation job.
" } }, "EvaluationPrecomputedRagSourceIdentifier": { "base": null, "refs": { "EvaluationPrecomputedRagSourceIdentifiers$member": null, "EvaluationPrecomputedRetrieveAndGenerateSourceConfig$ragSourceIdentifier": "A label that identifies the RAG source used for a retrieve-and-generate Knowledge Base evaluation job where you provide your own inference response data.
", "EvaluationPrecomputedRetrieveSourceConfig$ragSourceIdentifier": "A label that identifies the RAG source used for a retrieve-only Knowledge Base evaluation job where you provide your own inference response data.
" } }, "EvaluationPrecomputedRagSourceIdentifiers": { "base": null, "refs": { "EvaluationRagConfigSummary$precomputedRagSourceIdentifiers": "A label that identifies the RAG sources used for a Knowledge Base evaluation job where you provide your own inference response data.
" } }, "EvaluationPrecomputedRetrieveAndGenerateSourceConfig": { "base": "A summary of a RAG source used for a retrieve-and-generate Knowledge Base evaluation job where you provide your own inference response data.
", "refs": { "EvaluationPrecomputedRagSourceConfig$retrieveAndGenerateSourceConfig": "A summary of a RAG source used for a retrieve-and-generate Knowledge Base evaluation job where you provide your own inference response data.
" } }, "EvaluationPrecomputedRetrieveSourceConfig": { "base": "A summary of a RAG source used for a retrieve-only Knowledge Base evaluation job where you provide your own inference response data.
", "refs": { "EvaluationPrecomputedRagSourceConfig$retrieveSourceConfig": "A summary of a RAG source used for a retrieve-only Knowledge Base evaluation job where you provide your own inference response data.
" } }, "EvaluationRagConfigSummary": { "base": "A summary of the RAG resources used in an Amazon Bedrock Knowledge Base evaluation job. These resources can be Knowledge Bases in Amazon Bedrock or RAG sources outside of Amazon Bedrock that you use to generate your own inference response data.
", "refs": { "EvaluationInferenceConfigSummary$ragConfigSummary": "A summary of the RAG resources used in an Amazon Bedrock Knowledge Base evaluation job. These resources can be Knowledge Bases in Amazon Bedrock or RAG sources outside of Amazon Bedrock that you use to generate your own inference response data.
" } }, "EvaluationRatingMethod": { "base": null, "refs": { "HumanEvaluationCustomMetric$ratingMethod": "Choose how you want your human workers to evaluation your model. Valid values for rating methods are ThumbsUpDown, IndividualLikertScale,ComparisonLikertScale, ComparisonChoice, and ComparisonRank
A list of summaries of the evaluation jobs.
" } }, "EvaluationSummary": { "base": "Summary information of an evaluation job.
", "refs": { "EvaluationSummaries$member": null } }, "EvaluationTaskType": { "base": null, "refs": { "EvaluationDatasetMetricConfig$taskType": "The the type of task you want to evaluate for your evaluation job. This applies only to model evaluation jobs and is ignored for knowledge base evaluation jobs.
", "EvaluationTaskTypes$member": null } }, "EvaluationTaskTypes": { "base": null, "refs": { "EvaluationSummary$evaluationTaskTypes": "The type of task for model evaluation.
" } }, "EvaluatorModelConfig": { "base": "Specifies the model configuration for the evaluator model. EvaluatorModelConfig is required for evaluation jobs that use a knowledge base or in model evaluation job that use a model as judge. This model computes all evaluation related metrics.
Contains the evaluator model configuration details. EvaluatorModelConfig is required for evaluation jobs that use a knowledge base or in model evaluation job that use a model as judge. This model computes all evaluation related metrics.
The Amazon Resource Name (ARN) of the evaluator model used used in knowledge base evaluation job or in model evaluation job that use a model as judge.
", "CustomMetricBedrockEvaluatorModel$modelIdentifier": "The Amazon Resource Name (ARN) of the evaluator model for custom metrics. For a list of supported evaluator models, see Evaluate model performance using another LLM as a judge and Evaluate the performance of RAG sources using Amazon Bedrock evaluations.
", "EvaluatorModelIdentifiers$member": null } }, "EvaluatorModelIdentifiers": { "base": null, "refs": { "EvaluationSummary$evaluatorModelIdentifiers": "The Amazon Resource Names (ARNs) of the models used to compute the metrics for a knowledge base evaluation job.
", "EvaluationSummary$customMetricsEvaluatorModelIdentifiers": "The Amazon Resource Names (ARNs) of the models used to compute custom metrics in an Amazon Bedrock evaluation job.
" } }, "ExportAutomatedReasoningPolicyVersionRequest": { "base": null, "refs": { } }, "ExportAutomatedReasoningPolicyVersionResponse": { "base": null, "refs": { } }, "ExternalSource": { "base": "The unique external source of the content contained in the wrapper object.
", "refs": { "ExternalSources$member": null } }, "ExternalSourceType": { "base": null, "refs": { "ExternalSource$sourceType": "The source type of the external source wrapper object.
" } }, "ExternalSources": { "base": null, "refs": { "ExternalSourcesRetrieveAndGenerateConfiguration$sources": "The document for the external source wrapper object in the retrieveAndGenerate function.
The response generation configuration of the external source wrapper object.
", "refs": { "ExternalSourcesRetrieveAndGenerateConfiguration$generationConfiguration": "Contains configurations details for response generation based on retrieved text chunks.
" } }, "ExternalSourcesRetrieveAndGenerateConfiguration": { "base": "The configuration of the external source wrapper object in the retrieveAndGenerate function.
The configuration for the external source wrapper object in the retrieveAndGenerate function.
Specifies a field to be used during the reranking process in a Knowledge Base vector search. This structure identifies metadata fields that should be considered when reordering search results to improve relevance.
", "refs": { "FieldsForReranking$member": null } }, "FieldForRerankingFieldNameString": { "base": null, "refs": { "FieldForReranking$fieldName": "The name of the metadata field to be used during the reranking process.
" } }, "FieldsForReranking": { "base": null, "refs": { "RerankingMetadataSelectiveModeConfiguration$fieldsToInclude": "A list of metadata field names to explicitly include in the reranking process. Only these fields will be considered when reordering search results. This parameter cannot be used together with fieldsToExclude.
", "RerankingMetadataSelectiveModeConfiguration$fieldsToExclude": "A list of metadata field names to explicitly exclude from the reranking process. All metadata fields except these will be considered when reordering search results. This parameter cannot be used together with fieldsToInclude.
" } }, "FilterAttribute": { "base": "Specifies the name of the metadata attribute/field to apply filters. You must match the name of the attribute/field in your data source/document metadata.
", "refs": { "RetrievalFilter$equals": "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\" }
The name of metadata attribute/field, which must match the name in your data source/document metadata.
" } }, "FilterValue": { "base": null, "refs": { "FilterAttribute$value": "The value of the metadata attribute/field.
" } }, "FineTuningJobStatus": { "base": null, "refs": { "ListModelCustomizationJobsRequest$statusEquals": "Return customization jobs with the specified status.
" } }, "Float": { "base": null, "refs": { "RatingScaleItemValue$floatValue": "A floating point number representing the value for a rating in a custom metric rating scale.
" } }, "FoundationModelArn": { "base": null, "refs": { "FoundationModelDetails$modelArn": "The model Amazon Resource Name (ARN).
", "FoundationModelSummary$modelArn": "The Amazon Resource Name (ARN) of the foundation model.
", "GetModelCustomizationJobResponse$baseModelArn": "Amazon Resource Name (ARN) of the base model.
", "GetProvisionedModelThroughputResponse$foundationModelArn": "The Amazon Resource Name (ARN) of the base model for which the Provisioned Throughput was created, or of the base model that the custom model for which the Provisioned Throughput was created was customized.
", "InferenceProfileModel$modelArn": "The Amazon Resource Name (ARN) of the model.
", "ListCustomModelsRequest$foundationModelArnEquals": "Return custom models only if the foundation model Amazon Resource Name (ARN) matches this parameter.
", "ProvisionedModelSummary$foundationModelArn": "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.
" } }, "FoundationModelDetails": { "base": "Information about a foundation model.
", "refs": { "GetFoundationModelResponse$modelDetails": "Information about the foundation model.
" } }, "FoundationModelLifecycle": { "base": "Details about whether a model version is available or deprecated.
", "refs": { "FoundationModelDetails$modelLifecycle": "Contains details about whether a model version is available or deprecated
", "FoundationModelSummary$modelLifecycle": "Contains details about whether a model version is available or deprecated.
" } }, "FoundationModelLifecycleStatus": { "base": null, "refs": { "FoundationModelLifecycle$status": "Specifies whether a model version is available (ACTIVE) or deprecated (LEGACY.
Summary information for a foundation model.
", "refs": { "FoundationModelSummaryList$member": null } }, "FoundationModelSummaryList": { "base": null, "refs": { "ListFoundationModelsResponse$modelSummaries": "A list of Amazon Bedrock foundation models.
" } }, "GenerationConfiguration": { "base": "The configuration details for response generation based on retrieved text chunks.
", "refs": { "KnowledgeBaseRetrieveAndGenerateConfiguration$generationConfiguration": "Contains configurations details for response generation based on retrieved text chunks.
" } }, "GetAutomatedReasoningPolicyAnnotationsRequest": { "base": null, "refs": { } }, "GetAutomatedReasoningPolicyAnnotationsResponse": { "base": null, "refs": { } }, "GetAutomatedReasoningPolicyBuildWorkflowRequest": { "base": null, "refs": { } }, "GetAutomatedReasoningPolicyBuildWorkflowResponse": { "base": null, "refs": { } }, "GetAutomatedReasoningPolicyBuildWorkflowResultAssetsRequest": { "base": null, "refs": { } }, "GetAutomatedReasoningPolicyBuildWorkflowResultAssetsResponse": { "base": null, "refs": { } }, "GetAutomatedReasoningPolicyNextScenarioRequest": { "base": null, "refs": { } }, "GetAutomatedReasoningPolicyNextScenarioResponse": { "base": null, "refs": { } }, "GetAutomatedReasoningPolicyRequest": { "base": null, "refs": { } }, "GetAutomatedReasoningPolicyResponse": { "base": null, "refs": { } }, "GetAutomatedReasoningPolicyTestCaseRequest": { "base": null, "refs": { } }, "GetAutomatedReasoningPolicyTestCaseResponse": { "base": null, "refs": { } }, "GetAutomatedReasoningPolicyTestResultRequest": { "base": null, "refs": { } }, "GetAutomatedReasoningPolicyTestResultResponse": { "base": null, "refs": { } }, "GetCustomModelDeploymentRequest": { "base": null, "refs": { } }, "GetCustomModelDeploymentResponse": { "base": null, "refs": { } }, "GetCustomModelRequest": { "base": null, "refs": { } }, "GetCustomModelResponse": { "base": null, "refs": { } }, "GetEvaluationJobRequest": { "base": null, "refs": { } }, "GetEvaluationJobResponse": { "base": null, "refs": { } }, "GetFoundationModelAvailabilityRequest": { "base": null, "refs": { } }, "GetFoundationModelAvailabilityResponse": { "base": null, "refs": { } }, "GetFoundationModelRequest": { "base": null, "refs": { } }, "GetFoundationModelResponse": { "base": null, "refs": { } }, "GetGuardrailRequest": { "base": null, "refs": { } }, "GetGuardrailResponse": { "base": null, "refs": { } }, "GetImportedModelRequest": { "base": null, "refs": { } }, "GetImportedModelResponse": { "base": null, "refs": { } }, "GetInferenceProfileRequest": { "base": null, "refs": { } }, "GetInferenceProfileResponse": { "base": null, "refs": { } }, "GetMarketplaceModelEndpointRequest": { "base": null, "refs": { } }, "GetMarketplaceModelEndpointResponse": { "base": null, "refs": { } }, "GetModelCopyJobRequest": { "base": null, "refs": { } }, "GetModelCopyJobResponse": { "base": null, "refs": { } }, "GetModelCustomizationJobRequest": { "base": null, "refs": { } }, "GetModelCustomizationJobResponse": { "base": null, "refs": { } }, "GetModelImportJobRequest": { "base": null, "refs": { } }, "GetModelImportJobResponse": { "base": null, "refs": { } }, "GetModelInvocationJobRequest": { "base": null, "refs": { } }, "GetModelInvocationJobResponse": { "base": null, "refs": { } }, "GetModelInvocationLoggingConfigurationRequest": { "base": null, "refs": { } }, "GetModelInvocationLoggingConfigurationResponse": { "base": null, "refs": { } }, "GetPromptRouterRequest": { "base": null, "refs": { } }, "GetPromptRouterResponse": { "base": null, "refs": { } }, "GetProvisionedModelThroughputRequest": { "base": null, "refs": { } }, "GetProvisionedModelThroughputResponse": { "base": null, "refs": { } }, "GetUseCaseForModelAccessRequest": { "base": null, "refs": { } }, "GetUseCaseForModelAccessResponse": { "base": null, "refs": { } }, "GuardrailArn": { "base": null, "refs": { "CreateGuardrailResponse$guardrailArn": "The ARN of the guardrail.
", "GetGuardrailResponse$guardrailArn": "The ARN of the guardrail.
", "GuardrailSummary$arn": "The ARN of the guardrail.
", "UpdateGuardrailResponse$guardrailArn": "The ARN of the guardrail.
" } }, "GuardrailAutomatedReasoningPolicy": { "base": "Represents the configuration of Automated Reasoning policies within a Amazon Bedrock Guardrail, including the policies to apply and confidence thresholds.
", "refs": { "GetGuardrailResponse$automatedReasoningPolicy": "The current Automated Reasoning policy configuration for the guardrail, if any is configured.
" } }, "GuardrailAutomatedReasoningPolicyConfig": { "base": "Configuration settings for integrating Automated Reasoning policies with Amazon Bedrock Guardrails.
", "refs": { "CreateGuardrailRequest$automatedReasoningPolicyConfig": "Optional configuration for integrating Automated Reasoning policies with the new guardrail.
", "UpdateGuardrailRequest$automatedReasoningPolicyConfig": "Updated configuration for Automated Reasoning policies associated with the guardrail.
" } }, "GuardrailAutomatedReasoningPolicyConfigPoliciesList": { "base": null, "refs": { "GuardrailAutomatedReasoningPolicyConfig$policies": "The list of Automated Reasoning policy ARNs to include in the guardrail configuration.
" } }, "GuardrailAutomatedReasoningPolicyPoliciesList": { "base": null, "refs": { "GuardrailAutomatedReasoningPolicy$policies": "The list of Automated Reasoning policy ARNs that should be applied as part of this guardrail configuration.
" } }, "GuardrailBlockedMessaging": { "base": null, "refs": { "CreateGuardrailRequest$blockedInputMessaging": "The message to return when the guardrail blocks a prompt.
", "CreateGuardrailRequest$blockedOutputsMessaging": "The message to return when the guardrail blocks a model response.
", "GetGuardrailResponse$blockedInputMessaging": "The message that the guardrail returns when it blocks a prompt.
", "GetGuardrailResponse$blockedOutputsMessaging": "The message that the guardrail returns when it blocks a model response.
", "UpdateGuardrailRequest$blockedInputMessaging": "The message to return when the guardrail blocks a prompt.
", "UpdateGuardrailRequest$blockedOutputsMessaging": "The message to return when the guardrail blocks a model response.
" } }, "GuardrailConfiguration": { "base": "The configuration details for the guardrail.
", "refs": { "ExternalSourcesGenerationConfiguration$guardrailConfiguration": "Configuration details for the guardrail.
", "GenerationConfiguration$guardrailConfiguration": "Contains configuration details for the guardrail.
" } }, "GuardrailConfigurationGuardrailIdString": { "base": null, "refs": { "GuardrailConfiguration$guardrailId": "The unique identifier for the guardrail.
" } }, "GuardrailConfigurationGuardrailVersionString": { "base": null, "refs": { "GuardrailConfiguration$guardrailVersion": "The version of the guardrail.
" } }, "GuardrailContentFilter": { "base": "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:
", "refs": { "GuardrailContentFilters$member": null } }, "GuardrailContentFilterAction": { "base": null, "refs": { "GuardrailContentFilter$inputAction": "The action to take when harmful content is detected in the input. Supported values include:
BLOCK – Block the content and replace it with blocked messaging.
NONE – Take no action but return detection information in the trace response.
The action to take when harmful content is detected in the output. Supported values include:
BLOCK – Block the content and replace it with blocked messaging.
NONE – Take no action but return detection information in the trace response.
Specifies the action to take when harmful content is detected. Supported values include:
BLOCK – Block the content and replace it with blocked messaging.
NONE – Take no action but return detection information in the trace response.
Specifies the action to take when harmful content is detected in the output. Supported values include:
BLOCK – Block the content and replace it with blocked messaging.
NONE – Take no action but return detection information in the trace response.
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.
", "refs": { "GuardrailContentFiltersConfig$member": null } }, "GuardrailContentFilterType": { "base": null, "refs": { "GuardrailContentFilter$type": "The harmful category that the content filter is applied to.
", "GuardrailContentFilterConfig$type": "The harmful category that the content filter is applied to.
" } }, "GuardrailContentFilters": { "base": null, "refs": { "GuardrailContentPolicy$filters": "Contains the type of the content filter and how strongly it should apply to prompts and model responses.
" } }, "GuardrailContentFiltersConfig": { "base": null, "refs": { "GuardrailContentPolicyConfig$filtersConfig": "Contains the type of the content filter and how strongly it should apply to prompts and model responses.
" } }, "GuardrailContentFiltersTier": { "base": "The tier that your guardrail uses for content filters.
", "refs": { "GuardrailContentPolicy$tier": "The tier that your guardrail uses for content filters.
" } }, "GuardrailContentFiltersTierConfig": { "base": "The tier that your guardrail uses for content filters. Consider using a tier that balances performance, accuracy, and compatibility with your existing generative AI workflows.
", "refs": { "GuardrailContentPolicyConfig$tierConfig": "The tier that your guardrail uses for content filters.
" } }, "GuardrailContentFiltersTierName": { "base": null, "refs": { "GuardrailContentFiltersTier$tierName": "The tier that your guardrail uses for content filters. Valid values include:
CLASSIC tier – Provides established guardrails functionality supporting English, French, and Spanish languages.
STANDARD tier – Provides a more robust solution than the CLASSIC tier and has more comprehensive language support. This tier requires that your guardrail use cross-Region inference.
The tier that your guardrail uses for content filters. Valid values include:
CLASSIC tier – Provides established guardrails functionality supporting English, French, and Spanish languages.
STANDARD tier – Provides a more robust solution than the CLASSIC tier and has more comprehensive language support. This tier requires that your guardrail use cross-Region inference.
Contains details about how to handle harmful content.
This data type is used in the following API operations:
", "refs": { "GetGuardrailResponse$contentPolicy": "The content policy that was configured for the guardrail.
" } }, "GuardrailContentPolicyConfig": { "base": "Contains details about how to handle harmful content.
", "refs": { "CreateGuardrailRequest$contentPolicyConfig": "The content filter policies to configure for the guardrail.
", "UpdateGuardrailRequest$contentPolicyConfig": "The content policy to configure for the guardrail.
" } }, "GuardrailContextualGroundingAction": { "base": null, "refs": { "GuardrailContextualGroundingFilter$action": "The action to take when content fails the contextual grounding evaluation. Supported values include:
BLOCK – Block the content and replace it with blocked messaging.
NONE – Take no action but return detection information in the trace response.
Specifies the action to take when content fails the contextual grounding evaluation. Supported values include:
BLOCK – Block the content and replace it with blocked messaging.
NONE – Take no action but return detection information in the trace response.
The details for the guardrails contextual grounding filter.
", "refs": { "GuardrailContextualGroundingFilters$member": null } }, "GuardrailContextualGroundingFilterConfig": { "base": "The filter configuration details for the guardrails contextual grounding filter.
", "refs": { "GuardrailContextualGroundingFiltersConfig$member": null } }, "GuardrailContextualGroundingFilterConfigThresholdDouble": { "base": null, "refs": { "GuardrailContextualGroundingFilterConfig$threshold": "The threshold details for the guardrails contextual grounding filter.
" } }, "GuardrailContextualGroundingFilterThresholdDouble": { "base": null, "refs": { "GuardrailContextualGroundingFilter$threshold": "The threshold details for the guardrails contextual grounding filter.
" } }, "GuardrailContextualGroundingFilterType": { "base": null, "refs": { "GuardrailContextualGroundingFilter$type": "The filter type details for the guardrails contextual grounding filter.
", "GuardrailContextualGroundingFilterConfig$type": "The filter details for the guardrails contextual grounding filter.
" } }, "GuardrailContextualGroundingFilters": { "base": null, "refs": { "GuardrailContextualGroundingPolicy$filters": "The filter details for the guardrails contextual grounding policy.
" } }, "GuardrailContextualGroundingFiltersConfig": { "base": null, "refs": { "GuardrailContextualGroundingPolicyConfig$filtersConfig": "The filter configuration details for the guardrails contextual grounding policy.
" } }, "GuardrailContextualGroundingPolicy": { "base": "The details for the guardrails contextual grounding policy.
", "refs": { "GetGuardrailResponse$contextualGroundingPolicy": "The contextual grounding policy used in the guardrail.
" } }, "GuardrailContextualGroundingPolicyConfig": { "base": "The policy configuration details for the guardrails contextual grounding policy.
", "refs": { "CreateGuardrailRequest$contextualGroundingPolicyConfig": "The contextual grounding policy configuration used to create a guardrail.
", "UpdateGuardrailRequest$contextualGroundingPolicyConfig": "The contextual grounding policy configuration used to update a guardrail.
" } }, "GuardrailCrossRegionConfig": { "base": "The system-defined guardrail profile that you're using with your guardrail. Guardrail profiles define the destination Amazon Web Services Regions where guardrail inference requests can be automatically routed. Using guardrail profiles helps maintain guardrail performance and reliability when demand increases.
For more information, see the Amazon Bedrock User Guide.
", "refs": { "CreateGuardrailRequest$crossRegionConfig": "The system-defined guardrail profile that you're using with your guardrail. Guardrail profiles define the destination Amazon Web Services Regions where guardrail inference requests can be automatically routed.
For more information, see the Amazon Bedrock User Guide.
", "UpdateGuardrailRequest$crossRegionConfig": "The system-defined guardrail profile that you're using with your guardrail. Guardrail profiles define the destination Amazon Web Services Regions where guardrail inference requests can be automatically routed.
For more information, see the Amazon Bedrock User Guide.
" } }, "GuardrailCrossRegionDetails": { "base": "Contains details about the system-defined guardrail profile that you're using with your guardrail for cross-Region inference.
For more information, see the Amazon Bedrock User Guide.
", "refs": { "GetGuardrailResponse$crossRegionDetails": "Details about the system-defined guardrail profile that you're using with your guardrail, including the guardrail profile ID and Amazon Resource Name (ARN).
", "GuardrailSummary$crossRegionDetails": "Details about the system-defined guardrail profile that you're using with your guardrail, including the guardrail profile ID and Amazon Resource Name (ARN).
" } }, "GuardrailCrossRegionGuardrailProfileArn": { "base": null, "refs": { "GuardrailCrossRegionDetails$guardrailProfileArn": "The Amazon Resource Name (ARN) of the guardrail profile that you're using with your guardrail.
" } }, "GuardrailCrossRegionGuardrailProfileId": { "base": null, "refs": { "GuardrailCrossRegionDetails$guardrailProfileId": "The ID of the guardrail profile that your guardrail is using. Profile availability depends on your current Amazon Web Services Region. For more information, see the Amazon Bedrock User Guide.
" } }, "GuardrailCrossRegionGuardrailProfileIdentifier": { "base": null, "refs": { "GuardrailCrossRegionConfig$guardrailProfileIdentifier": "The ID or Amazon Resource Name (ARN) of the guardrail profile that your guardrail is using. Guardrail profile availability depends on your current Amazon Web Services Region. For more information, see the Amazon Bedrock User Guide.
" } }, "GuardrailDescription": { "base": null, "refs": { "CreateGuardrailRequest$description": "A description of the guardrail.
", "CreateGuardrailVersionRequest$description": "A description of the guardrail version.
", "GetGuardrailResponse$description": "The description of the guardrail.
", "GuardrailSummary$description": "A description of the guardrail.
", "UpdateGuardrailRequest$description": "A description of the guardrail.
" } }, "GuardrailDraftVersion": { "base": null, "refs": { "CreateGuardrailResponse$version": "The version of the guardrail that was created. This value will always be DRAFT.
The version of the guardrail.
" } }, "GuardrailFailureRecommendation": { "base": null, "refs": { "GuardrailFailureRecommendations$member": null } }, "GuardrailFailureRecommendations": { "base": null, "refs": { "GetGuardrailResponse$failureRecommendations": "Appears if the status of the guardrail is FAILED. A list of recommendations to carry out before retrying the request.
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.
", "GuardrailContentFilter$outputStrength": "The strength of the content filter to apply to model responses. As you increase the filter strength, the likelihood of filtering harmful content increases and the probability of seeing harmful content in your application reduces.
", "GuardrailContentFilterConfig$inputStrength": "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.
", "GuardrailContentFilterConfig$outputStrength": "The strength of the content filter to apply to model responses. As you increase the filter strength, the likelihood of filtering harmful content increases and the probability of seeing harmful content in your application reduces.
" } }, "GuardrailId": { "base": null, "refs": { "CreateGuardrailResponse$guardrailId": "The unique identifier of the guardrail that was created.
", "CreateGuardrailVersionResponse$guardrailId": "The unique identifier of the guardrail.
", "GetGuardrailResponse$guardrailId": "The unique identifier of the guardrail.
", "GuardrailSummary$id": "The unique identifier of the guardrail.
", "UpdateGuardrailResponse$guardrailId": "The unique identifier of the guardrail
" } }, "GuardrailIdentifier": { "base": null, "refs": { "CreateGuardrailVersionRequest$guardrailIdentifier": "The unique identifier of the guardrail. This can be an ID or the ARN.
", "DeleteGuardrailRequest$guardrailIdentifier": "The unique identifier of the guardrail. This can be an ID or the ARN.
", "GetGuardrailRequest$guardrailIdentifier": "The unique identifier of the guardrail for which to get details. This can be an ID or the ARN.
", "ListGuardrailsRequest$guardrailIdentifier": "The unique identifier of the guardrail. This can be an ID or the ARN.
", "UpdateGuardrailRequest$guardrailIdentifier": "The unique identifier of the guardrail. This can be an ID or the ARN.
" } }, "GuardrailManagedWordLists": { "base": null, "refs": { "GuardrailWordPolicy$managedWordLists": "A list of managed words configured for the guardrail.
" } }, "GuardrailManagedWordListsConfig": { "base": null, "refs": { "GuardrailWordPolicyConfig$managedWordListsConfig": "A list of managed words to configure for the guardrail.
" } }, "GuardrailManagedWords": { "base": "The managed word list that was configured for the guardrail. (This is a list of words that are pre-defined and managed by guardrails only.)
", "refs": { "GuardrailManagedWordLists$member": null } }, "GuardrailManagedWordsConfig": { "base": "The managed word list to configure for the guardrail.
", "refs": { "GuardrailManagedWordListsConfig$member": null } }, "GuardrailManagedWordsType": { "base": null, "refs": { "GuardrailManagedWords$type": "ManagedWords$type The managed word type that was configured for the guardrail. (For now, we only offer profanity word list)
", "GuardrailManagedWordsConfig$type": "The managed word type to configure for the guardrail.
" } }, "GuardrailModalities": { "base": null, "refs": { "GuardrailContentFilter$inputModalities": "The input modalities selected for the guardrail content filter.
", "GuardrailContentFilter$outputModalities": "The output modalities selected for the guardrail content filter.
", "GuardrailContentFilterConfig$inputModalities": "The input modalities selected for the guardrail content filter configuration.
", "GuardrailContentFilterConfig$outputModalities": "The output modalities selected for the guardrail content filter configuration.
" } }, "GuardrailModality": { "base": null, "refs": { "GuardrailModalities$member": null } }, "GuardrailName": { "base": null, "refs": { "CreateGuardrailRequest$name": "The name to give the guardrail.
", "GetGuardrailResponse$name": "The name of the guardrail.
", "GuardrailSummary$name": "The name of the guardrail.
", "UpdateGuardrailRequest$name": "A name for the guardrail.
" } }, "GuardrailNumericalVersion": { "base": null, "refs": { "CreateGuardrailVersionResponse$version": "The number of the version of the guardrail.
", "DeleteGuardrailRequest$guardrailVersion": "The version of the guardrail.
" } }, "GuardrailPiiEntities": { "base": null, "refs": { "GuardrailSensitiveInformationPolicy$piiEntities": "The list of PII entities configured for the guardrail.
" } }, "GuardrailPiiEntitiesConfig": { "base": null, "refs": { "GuardrailSensitiveInformationPolicyConfig$piiEntitiesConfig": "A list of PII entities to configure to the guardrail.
" } }, "GuardrailPiiEntity": { "base": "The PII entity configured for the guardrail.
", "refs": { "GuardrailPiiEntities$member": null } }, "GuardrailPiiEntityConfig": { "base": "The PII entity to configure for the guardrail.
", "refs": { "GuardrailPiiEntitiesConfig$member": null } }, "GuardrailPiiEntityType": { "base": null, "refs": { "GuardrailPiiEntity$type": "The type of PII entity. For example, Social Security Number.
", "GuardrailPiiEntityConfig$type": "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..
The regular expression configured for the guardrail.
", "refs": { "GuardrailRegexes$member": null } }, "GuardrailRegexConfig": { "base": "The regular expression to configure for the guardrail.
", "refs": { "GuardrailRegexesConfig$member": null } }, "GuardrailRegexConfigDescriptionString": { "base": null, "refs": { "GuardrailRegexConfig$description": "The description of the regular expression to configure for the guardrail.
" } }, "GuardrailRegexConfigNameString": { "base": null, "refs": { "GuardrailRegexConfig$name": "The name of the regular expression to configure for the guardrail.
" } }, "GuardrailRegexConfigPatternString": { "base": null, "refs": { "GuardrailRegexConfig$pattern": "The regular expression pattern to configure for the guardrail.
" } }, "GuardrailRegexDescriptionString": { "base": null, "refs": { "GuardrailRegex$description": "The description of the regular expression for the guardrail.
" } }, "GuardrailRegexNameString": { "base": null, "refs": { "GuardrailRegex$name": "The name of the regular expression for the guardrail.
" } }, "GuardrailRegexPatternString": { "base": null, "refs": { "GuardrailRegex$pattern": "The pattern of the regular expression configured for the guardrail.
" } }, "GuardrailRegexes": { "base": null, "refs": { "GuardrailSensitiveInformationPolicy$regexes": "The list of regular expressions configured for the guardrail.
" } }, "GuardrailRegexesConfig": { "base": null, "refs": { "GuardrailSensitiveInformationPolicyConfig$regexesConfig": "A list of regular expressions to configure to the guardrail.
" } }, "GuardrailSensitiveInformationAction": { "base": null, "refs": { "GuardrailPiiEntity$action": "The configured guardrail action when PII entity is detected.
", "GuardrailPiiEntity$inputAction": "The action to take when harmful content is detected in the input. Supported values include:
BLOCK – Block the content and replace it with blocked messaging.
ANONYMIZE – Mask the content and replace it with identifier tags.
NONE – Take no action but return detection information in the trace response.
The action to take when harmful content is detected in the output. Supported values include:
BLOCK – Block the content and replace it with blocked messaging.
ANONYMIZE – Mask the content and replace it with identifier tags.
NONE – Take no action but return detection information in the trace response.
Configure guardrail action when the PII entity is detected.
", "GuardrailPiiEntityConfig$inputAction": "Specifies the action to take when harmful content is detected in the input. Supported values include:
BLOCK – Block the content and replace it with blocked messaging.
ANONYMIZE – Mask the content and replace it with identifier tags.
NONE – Take no action but return detection information in the trace response.
Specifies the action to take when harmful content is detected in the output. Supported values include:
BLOCK – Block the content and replace it with blocked messaging.
ANONYMIZE – Mask the content and replace it with identifier tags.
NONE – Take no action but return detection information in the trace response.
The action taken when a match to the regular expression is detected.
", "GuardrailRegex$inputAction": "The action to take when harmful content is detected in the input. Supported values include:
BLOCK – Block the content and replace it with blocked messaging.
NONE – Take no action but return detection information in the trace response.
The action to take when harmful content is detected in the output. Supported values include:
BLOCK – Block the content and replace it with blocked messaging.
NONE – Take no action but return detection information in the trace response.
The guardrail action to configure when matching regular expression is detected.
", "GuardrailRegexConfig$inputAction": "Specifies the action to take when harmful content is detected in the input. Supported values include:
BLOCK – Block the content and replace it with blocked messaging.
NONE – Take no action but return detection information in the trace response.
Specifies the action to take when harmful content is detected in the output. Supported values include:
BLOCK – Block the content and replace it with blocked messaging.
NONE – Take no action but return detection information in the trace response.
Contains details about PII entities and regular expressions configured for the guardrail.
", "refs": { "GetGuardrailResponse$sensitiveInformationPolicy": "The sensitive information policy that was configured for the guardrail.
" } }, "GuardrailSensitiveInformationPolicyConfig": { "base": "Contains details about PII entities and regular expressions to configure for the guardrail.
", "refs": { "CreateGuardrailRequest$sensitiveInformationPolicyConfig": "The sensitive information policy to configure for the guardrail.
", "UpdateGuardrailRequest$sensitiveInformationPolicyConfig": "The sensitive information policy to configure for the guardrail.
" } }, "GuardrailStatus": { "base": null, "refs": { "GetGuardrailResponse$status": "The status of the guardrail.
", "GuardrailSummary$status": "The status of the guardrail.
" } }, "GuardrailStatusReason": { "base": null, "refs": { "GuardrailStatusReasons$member": null } }, "GuardrailStatusReasons": { "base": null, "refs": { "GetGuardrailResponse$statusReasons": "Appears if the status is FAILED. A list of reasons for why the guardrail failed to be created, updated, versioned, or deleted.
A list of objects, each of which contains details about a guardrail.
" } }, "GuardrailSummary": { "base": "Contains details about a guardrail.
This data type is used in the following API operations:
", "refs": { "GuardrailSummaries$member": null } }, "GuardrailTopic": { "base": "Details about topics for the guardrail to identify and deny.
This data type is used in the following API operations:
", "refs": { "GuardrailTopics$member": null } }, "GuardrailTopicAction": { "base": null, "refs": { "GuardrailTopic$inputAction": "The action to take when harmful content is detected in the input. Supported values include:
BLOCK – Block the content and replace it with blocked messaging.
NONE – Take no action but return detection information in the trace response.
The action to take when harmful content is detected in the output. Supported values include:
BLOCK – Block the content and replace it with blocked messaging.
NONE – Take no action but return detection information in the trace response.
Specifies the action to take when harmful content is detected in the input. Supported values include:
BLOCK – Block the content and replace it with blocked messaging.
NONE – Take no action but return detection information in the trace response.
Specifies the action to take when harmful content is detected in the output. Supported values include:
BLOCK – Block the content and replace it with blocked messaging.
NONE – Take no action but return detection information in the trace response.
Details about topics for the guardrail to identify and deny.
", "refs": { "GuardrailTopicsConfig$member": null } }, "GuardrailTopicDefinition": { "base": null, "refs": { "GuardrailTopic$definition": "A definition of the topic to deny.
", "GuardrailTopicConfig$definition": "A definition of the topic to deny.
" } }, "GuardrailTopicExample": { "base": null, "refs": { "GuardrailTopicExamples$member": null } }, "GuardrailTopicExamples": { "base": null, "refs": { "GuardrailTopic$examples": "A list of prompts, each of which is an example of a prompt that can be categorized as belonging to the topic.
", "GuardrailTopicConfig$examples": "A list of prompts, each of which is an example of a prompt that can be categorized as belonging to the topic.
" } }, "GuardrailTopicName": { "base": null, "refs": { "GuardrailTopic$name": "The name of the topic to deny.
", "GuardrailTopicConfig$name": "The name of the topic to deny.
" } }, "GuardrailTopicPolicy": { "base": "Contains details about topics that the guardrail should identify and deny.
This data type is used in the following API operations:
", "refs": { "GetGuardrailResponse$topicPolicy": "The topic policy that was configured for the guardrail.
" } }, "GuardrailTopicPolicyConfig": { "base": "Contains details about topics that the guardrail should identify and deny.
", "refs": { "CreateGuardrailRequest$topicPolicyConfig": "The topic policies to configure for the guardrail.
", "UpdateGuardrailRequest$topicPolicyConfig": "The topic policy to configure for the guardrail.
" } }, "GuardrailTopicType": { "base": null, "refs": { "GuardrailTopic$type": "Specifies to deny the topic.
", "GuardrailTopicConfig$type": "Specifies to deny the topic.
" } }, "GuardrailTopics": { "base": null, "refs": { "GuardrailTopicPolicy$topics": "A list of policies related to topics that the guardrail should deny.
" } }, "GuardrailTopicsConfig": { "base": null, "refs": { "GuardrailTopicPolicyConfig$topicsConfig": "A list of policies related to topics that the guardrail should deny.
" } }, "GuardrailTopicsTier": { "base": "The tier that your guardrail uses for denied topic filters.
", "refs": { "GuardrailTopicPolicy$tier": "The tier that your guardrail uses for denied topic filters.
" } }, "GuardrailTopicsTierConfig": { "base": "The tier that your guardrail uses for denied topic filters. Consider using a tier that balances performance, accuracy, and compatibility with your existing generative AI workflows.
", "refs": { "GuardrailTopicPolicyConfig$tierConfig": "The tier that your guardrail uses for denied topic filters.
" } }, "GuardrailTopicsTierName": { "base": null, "refs": { "GuardrailTopicsTier$tierName": "The tier that your guardrail uses for denied topic filters. Valid values include:
CLASSIC tier – Provides established guardrails functionality supporting English, French, and Spanish languages.
STANDARD tier – Provides a more robust solution than the CLASSIC tier and has more comprehensive language support. This tier requires that your guardrail use cross-Region inference.
The tier that your guardrail uses for denied topic filters. Valid values include:
CLASSIC tier – Provides established guardrails functionality supporting English, French, and Spanish languages.
STANDARD tier – Provides a more robust solution than the CLASSIC tier and has more comprehensive language support. This tier requires that your guardrail use cross-Region inference.
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 version of the guardrail.
", "GuardrailSummary$version": "The version of the guardrail.
" } }, "GuardrailWord": { "base": "A word configured for the guardrail.
", "refs": { "GuardrailWords$member": null } }, "GuardrailWordAction": { "base": null, "refs": { "GuardrailManagedWords$inputAction": "The action to take when harmful content is detected in the input. Supported values include:
BLOCK – Block the content and replace it with blocked messaging.
NONE – Take no action but return detection information in the trace response.
The action to take when harmful content is detected in the output. Supported values include:
BLOCK – Block the content and replace it with blocked messaging.
NONE – Take no action but return detection information in the trace response.
Specifies the action to take when harmful content is detected in the input. Supported values include:
BLOCK – Block the content and replace it with blocked messaging.
NONE – Take no action but return detection information in the trace response.
Specifies the action to take when harmful content is detected in the output. Supported values include:
BLOCK – Block the content and replace it with blocked messaging.
NONE – Take no action but return detection information in the trace response.
The action to take when harmful content is detected in the input. Supported values include:
BLOCK – Block the content and replace it with blocked messaging.
NONE – Take no action but return detection information in the trace response.
The action to take when harmful content is detected in the output. Supported values include:
BLOCK – Block the content and replace it with blocked messaging.
NONE – Take no action but return detection information in the trace response.
Specifies the action to take when harmful content is detected in the input. Supported values include:
BLOCK – Block the content and replace it with blocked messaging.
NONE – Take no action but return detection information in the trace response.
Specifies the action to take when harmful content is detected in the output. Supported values include:
BLOCK – Block the content and replace it with blocked messaging.
NONE – Take no action but return detection information in the trace response.
A word to configure for the guardrail.
", "refs": { "GuardrailWordsConfig$member": null } }, "GuardrailWordConfigTextString": { "base": null, "refs": { "GuardrailWordConfig$text": "Text of the word configured for the guardrail to block.
" } }, "GuardrailWordPolicy": { "base": "Contains details about the word policy configured for the guardrail.
", "refs": { "GetGuardrailResponse$wordPolicy": "The word policy that was configured for the guardrail.
" } }, "GuardrailWordPolicyConfig": { "base": "Contains details about the word policy to configured for the guardrail.
", "refs": { "CreateGuardrailRequest$wordPolicyConfig": "The word policy you configure for the guardrail.
", "UpdateGuardrailRequest$wordPolicyConfig": "The word policy to configure for the guardrail.
" } }, "GuardrailWordTextString": { "base": null, "refs": { "GuardrailWord$text": "Text of the word configured for the guardrail to block.
" } }, "GuardrailWords": { "base": null, "refs": { "GuardrailWordPolicy$words": "A list of words configured for the guardrail.
" } }, "GuardrailWordsConfig": { "base": null, "refs": { "GuardrailWordPolicyConfig$wordsConfig": "A list of words to configure for the guardrail.
" } }, "HumanEvaluationConfig": { "base": "Specifies the custom metrics, how tasks will be rated, the flow definition ARN, and your custom prompt datasets. Model evaluation jobs use human workers only support the use of custom prompt datasets. To learn more about custom prompt datasets and the required format, see Custom prompt datasets.
When you create custom metrics in HumanEvaluationCustomMetric you must specify the metric's name. The list of names specified in the HumanEvaluationCustomMetric array, must match the metricNames array of strings specified in EvaluationDatasetMetricConfig. For example, if in the HumanEvaluationCustomMetric array your specified the names \"accuracy\", \"toxicity\", \"readability\" as custom metrics then the metricNames array would need to look like the following [\"accuracy\", \"toxicity\", \"readability\"] in EvaluationDatasetMetricConfig.
Contains the configuration details of an evaluation job that uses human workers.
" } }, "HumanEvaluationCustomMetric": { "base": "In a model evaluation job that uses human workers you must define the name of the metric, and how you want that metric rated ratingMethod, and an optional description of the metric.
A HumanEvaluationCustomMetric object. It contains the names the metrics, how the metrics are to be evaluated, an optional description.
Instructions for the flow definition
" } }, "HumanWorkflowConfig": { "base": "Contains SageMakerFlowDefinition object. The object is used to specify the prompt dataset, task type, rating method and metric names.
The parameters of the human workflow.
" } }, "IdempotencyToken": { "base": null, "refs": { "CreateAutomatedReasoningPolicyRequest$clientRequestToken": "A unique, case-sensitive identifier to ensure that the operation completes no more than once. If this token matches a previous request, Amazon Bedrock ignores the request but doesn't return an error.
", "CreateAutomatedReasoningPolicyTestCaseRequest$clientRequestToken": "A unique, case-sensitive identifier to ensure that the operation completes no more than one time. If this token matches a previous request, Amazon Bedrock ignores the request, but does not return an error.
", "CreateAutomatedReasoningPolicyVersionRequest$clientRequestToken": "A unique, case-sensitive identifier to ensure that the operation completes no more than one time. If this token matches a previous request, Amazon Bedrock ignores the request, but does not return an error.
", "CreateCustomModelDeploymentRequest$clientRequestToken": "A unique, case-sensitive identifier to ensure that the operation completes no more than one time. If this token matches a previous request, Amazon Bedrock ignores the request, but does not return an error. For more information, see Ensuring idempotency.
", "CreateCustomModelRequest$clientRequestToken": "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.
", "CreateEvaluationJobRequest$clientRequestToken": "A unique, case-sensitive identifier to ensure that the API request completes no more than one time. If this token matches a previous request, Amazon Bedrock ignores the request, but does not return an error. For more information, see Ensuring idempotency.
", "CreateGuardrailRequest$clientRequestToken": "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.
", "CreateGuardrailVersionRequest$clientRequestToken": "A unique, case-sensitive identifier to ensure that the API request completes no more than once. If this token matches a previous request, Amazon Bedrock ignores the request, but does not return an error. For more information, see Ensuring idempotency in the Amazon S3 User Guide.
", "CreateInferenceProfileRequest$clientRequestToken": "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.
", "CreateMarketplaceModelEndpointRequest$clientRequestToken": "A unique, case-sensitive identifier that you provide to ensure the idempotency of the request. This token is listed as not required because Amazon Web Services SDKs automatically generate it for you and set this parameter. If you're not using the Amazon Web Services SDK or the CLI, you must provide this token or the action will fail.
", "CreateModelCopyJobRequest$clientRequestToken": "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.
", "CreateModelCustomizationJobRequest$clientRequestToken": "A unique, case-sensitive identifier to ensure that the API request completes no more than one time. If this token matches a previous request, Amazon Bedrock ignores the request, but does not return an error. For more information, see Ensuring idempotency.
", "CreateModelImportJobRequest$clientRequestToken": "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.
", "CreatePromptRouterRequest$clientRequestToken": "A unique, case-sensitive identifier that you provide to ensure idempotency of your requests. If not specified, the Amazon Web Services SDK automatically generates one for you.
", "CreateProvisionedModelThroughputRequest$clientRequestToken": "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.
", "GetModelCustomizationJobResponse$clientRequestToken": "The token that you specified in the CreateCustomizationJob request.
A unique, case-sensitive identifier to ensure that the operation completes no more than once. If this token matches a previous request, Amazon Bedrock ignores the request but doesn't return an error.
", "StartAutomatedReasoningPolicyTestWorkflowRequest$clientRequestToken": "A unique, case-sensitive identifier to ensure that the operation completes no more than one time. If this token matches a previous request, Amazon Bedrock ignores the request but doesn't return an error.
", "UpdateAutomatedReasoningPolicyTestCaseRequest$clientRequestToken": "A unique, case-sensitive identifier to ensure that the operation completes no more than one time. If this token matches a previous request, Amazon Bedrock ignores the request, but does not return an error.
", "UpdateMarketplaceModelEndpointRequest$clientRequestToken": "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.
" } }, "Identifier": { "base": null, "refs": { "ByteContentDoc$identifier": "The file name of the document contained in the wrapper object.
" } }, "ImplicitFilterConfiguration": { "base": "Configuration for implicit filtering in Knowledge Base vector searches. Implicit filtering allows you to automatically filter search results based on metadata attributes without requiring explicit filter expressions in each query.
", "refs": { "KnowledgeBaseVectorSearchConfiguration$implicitFilterConfiguration": "Configuration for implicit filtering in Knowledge Base vector searches. This allows the system to automatically apply filters based on the query context without requiring explicit filter expressions.
" } }, "ImportedModelArn": { "base": null, "refs": { "GetImportedModelResponse$modelArn": "The Amazon Resource Name (ARN) associated with this imported model.
", "GetModelImportJobResponse$importedModelArn": "The Amazon Resource Name (ARN) of the imported model.
", "ImportedModelSummary$modelArn": "The Amazon Resource Name (ARN) of the imported model.
", "ModelImportJobSummary$importedModelArn": "The Amazon resource Name (ARN) of the imported model.
" } }, "ImportedModelIdentifier": { "base": null, "refs": { "DeleteImportedModelRequest$modelIdentifier": "Name of the imported model to delete.
", "GetImportedModelRequest$modelIdentifier": "Name or Amazon Resource Name (ARN) of the imported model.
" } }, "ImportedModelName": { "base": null, "refs": { "CreateModelImportJobRequest$importedModelName": "The name of the imported model.
", "GetImportedModelResponse$modelName": "The name of the imported model.
", "GetModelImportJobResponse$importedModelName": "The name of the imported model.
", "ImportedModelSummary$modelName": "Name of the imported model.
", "ListImportedModelsRequest$nameContains": "Return imported models only if the model name contains these characters.
", "ModelImportJobSummary$importedModelName": "The name of the imported model.
" } }, "ImportedModelSummary": { "base": "Information about the imported model.
", "refs": { "ImportedModelSummaryList$member": null } }, "ImportedModelSummaryList": { "base": null, "refs": { "ListImportedModelsResponse$modelSummaries": "Model summaries.
" } }, "InferenceProfileArn": { "base": null, "refs": { "CreateInferenceProfileResponse$inferenceProfileArn": "The ARN of the inference profile that you created.
", "GetInferenceProfileResponse$inferenceProfileArn": "The Amazon Resource Name (ARN) of the inference profile.
", "InferenceProfileSummary$inferenceProfileArn": "The Amazon Resource Name (ARN) of the inference profile.
" } }, "InferenceProfileDescription": { "base": null, "refs": { "CreateInferenceProfileRequest$description": "A description for the inference profile.
", "GetInferenceProfileResponse$description": "The description of the inference profile.
", "InferenceProfileSummary$description": "The description of the inference profile.
" } }, "InferenceProfileId": { "base": null, "refs": { "GetInferenceProfileResponse$inferenceProfileId": "The unique identifier of the inference profile.
", "InferenceProfileSummary$inferenceProfileId": "The unique identifier of the inference profile.
" } }, "InferenceProfileIdentifier": { "base": null, "refs": { "DeleteInferenceProfileRequest$inferenceProfileIdentifier": "The Amazon Resource Name (ARN) or ID of the application inference profile to delete.
", "GetInferenceProfileRequest$inferenceProfileIdentifier": "The ID or Amazon Resource Name (ARN) of the inference profile.
" } }, "InferenceProfileModel": { "base": "Contains information about a model.
", "refs": { "InferenceProfileModels$member": null } }, "InferenceProfileModelSource": { "base": "Contains information about the model or system-defined inference profile that is the source for an inference profile..
", "refs": { "CreateInferenceProfileRequest$modelSource": "The foundation model or system-defined inference profile that the inference profile will track metrics and costs for.
" } }, "InferenceProfileModelSourceArn": { "base": null, "refs": { "InferenceProfileModelSource$copyFrom": "The ARN of the model or system-defined inference profile that is the source for the inference profile.
" } }, "InferenceProfileModels": { "base": null, "refs": { "GetInferenceProfileResponse$models": "A list of information about each model in the inference profile.
", "InferenceProfileSummary$models": "A list of information about each model in the inference profile.
" } }, "InferenceProfileName": { "base": null, "refs": { "CreateInferenceProfileRequest$inferenceProfileName": "A name for the inference profile.
", "GetInferenceProfileResponse$inferenceProfileName": "The name of the inference profile.
", "InferenceProfileSummary$inferenceProfileName": "The name of the inference profile.
" } }, "InferenceProfileStatus": { "base": null, "refs": { "CreateInferenceProfileResponse$status": "The status of the inference profile. ACTIVE means that the inference profile is ready to be used.
The status of the inference profile. ACTIVE means that the inference profile is ready to be used.
The status of the inference profile. ACTIVE means that the inference profile is ready to be used.
A list of information about each inference profile that you can use.
" } }, "InferenceProfileSummary": { "base": "Contains information about an inference profile.
", "refs": { "InferenceProfileSummaries$member": null } }, "InferenceProfileType": { "base": null, "refs": { "GetInferenceProfileResponse$type": "The type of the inference profile. The following types are possible:
SYSTEM_DEFINED – The inference profile is defined by Amazon Bedrock. You can route inference requests across regions with these inference profiles.
APPLICATION – The inference profile was created by a user. This type of inference profile can track metrics and costs when invoking the model in it. The inference profile may route requests to one or multiple regions.
The type of the inference profile. The following types are possible:
SYSTEM_DEFINED – The inference profile is defined by Amazon Bedrock. You can route inference requests across regions with these inference profiles.
APPLICATION – The inference profile was created by a user. This type of inference profile can track metrics and costs when invoking the model in it. The inference profile may route requests to one or multiple regions.
Filters for inference profiles that match the type you specify.
SYSTEM_DEFINED – The inference profile is defined by Amazon Bedrock. You can route inference requests across regions with these inference profiles.
APPLICATION – The inference profile was created by a user. This type of inference profile can track metrics and costs when invoking the model in it. The inference profile may route requests to one or multiple regions.
Return models that support the inference type that you specify. For more information, see Provisioned Throughput in the Amazon Bedrock User Guide.
" } }, "InferenceTypeList": { "base": null, "refs": { "FoundationModelDetails$inferenceTypesSupported": "The inference types that the model supports.
", "FoundationModelSummary$inferenceTypesSupported": "The inference types that the model supports.
" } }, "InstanceCount": { "base": null, "refs": { "SageMakerEndpoint$initialInstanceCount": "The number of Amazon EC2 compute instances to deploy for initial endpoint creation.
" } }, "InstanceType": { "base": null, "refs": { "SageMakerEndpoint$instanceType": "The Amazon EC2 compute instance type to deploy for hosting the model.
" } }, "InstructSupported": { "base": null, "refs": { "GetImportedModelResponse$instructSupported": "Specifies if the imported model supports converse.
", "ImportedModelSummary$instructSupported": "Specifies if the imported model supports converse.
" } }, "Integer": { "base": null, "refs": { "AutomatedReasoningPolicyDefinitionQualityReport$typeCount": "The total number of custom types defined in the policy.
", "AutomatedReasoningPolicyDefinitionQualityReport$variableCount": "The total number of variables defined in the policy.
", "AutomatedReasoningPolicyDefinitionQualityReport$ruleCount": "The total number of rules defined in the policy.
", "CustomModelUnits$customModelUnitsPerModelCopy": "The number of custom model units used to host a model copy.
", "TeacherModelConfig$maxResponseLengthForInference": "The maximum number of tokens requested when the customization job invokes the teacher model.
" } }, "InternalServerException": { "base": "An internal server error occurred. Retry your request.
", "refs": { } }, "InvocationLogSource": { "base": "A storage location for invocation logs.
", "refs": { "InvocationLogsConfig$invocationLogSource": "The source of the invocation logs.
" } }, "InvocationLogsConfig": { "base": "Settings for using invocation logs to customize a model.
", "refs": { "TrainingDataConfig$invocationLogsConfig": "Settings for using invocation logs to customize a model.
" } }, "JobName": { "base": null, "refs": { "CreateModelCustomizationJobRequest$jobName": "A name for the fine-tuning job.
", "CreateModelImportJobRequest$jobName": "The name of the import job.
", "GetCustomModelResponse$jobName": "Job name associated with this model.
", "GetImportedModelResponse$jobName": "Job name associated with the imported model.
", "GetModelCustomizationJobResponse$jobName": "The name of the customization job.
", "GetModelImportJobResponse$jobName": "The name of the import job.
", "ListModelCustomizationJobsRequest$nameContains": "Return customization jobs only if the job name contains these characters.
", "ListModelImportJobsRequest$nameContains": "Return imported jobs only if the job name contains these characters.
", "ModelCustomizationJobSummary$jobName": "Name of the customization job.
", "ModelImportJobSummary$jobName": "The name of the import job.
" } }, "JobStatusDetails": { "base": null, "refs": { "DataProcessingDetails$status": "The status of the data processing sub-task of the job.
", "TrainingDetails$status": "The status of the training sub-task of the job.
", "ValidationDetails$status": "The status of the validation sub-task of the job.
" } }, "KbInferenceConfig": { "base": "Contains configuration details of the inference for knowledge base retrieval and response generation.
", "refs": { "ExternalSourcesGenerationConfiguration$kbInferenceConfig": "Configuration details for inference when using RetrieveAndGenerate to generate responses while using an external source.
Contains configuration details for inference for knowledge base retrieval and response generation.
" } }, "KeyPrefix": { "base": null, "refs": { "S3Config$keyPrefix": "S3 prefix.
" } }, "KmsKeyArn": { "base": null, "refs": { "CreateCustomModelRequest$modelKmsKeyArn": "The Amazon Resource Name (ARN) of the customer managed KMS key to encrypt the custom model. If you don't provide a KMS key, Amazon Bedrock uses an Amazon Web Services-managed KMS key to encrypt the model.
If you provide a customer managed KMS key, your Amazon Bedrock service role must have permissions to use it. For more information see Encryption of imported models.
", "GetCustomModelResponse$modelKmsKeyArn": "The custom model is encrypted at rest using this key.
", "GetGuardrailResponse$kmsKeyArn": "The ARN of the KMS key that encrypts the guardrail.
", "GetImportedModelResponse$modelKmsKeyArn": "The imported model is encrypted at rest using this key.
", "GetModelCopyJobResponse$targetModelKmsKeyArn": "The Amazon Resource Name (ARN) of the KMS key encrypting the copied model.
", "GetModelCustomizationJobResponse$outputModelKmsKeyArn": "The custom model is encrypted at rest using this key.
", "GetModelImportJobResponse$importedModelKmsKeyArn": "The imported model is encrypted at rest using this key.
", "ModelCopyJobSummary$targetModelKmsKeyArn": "The Amazon Resource Name (ARN) of the KMS key used to encrypt the copied model.
", "UpdateAutomatedReasoningPolicyTestCaseRequest$kmsKeyArn": "The KMS key ARN for encrypting the test at rest. If not provided, the key will not be updated. Use DISCARD to remove the key.
Specify your customer managed encryption key Amazon Resource Name (ARN) that will be used to encrypt your evaluation job.
", "CreateGuardrailRequest$kmsKeyId": "The ARN of the KMS key that you use to encrypt the guardrail.
", "CreateModelCopyJobRequest$modelKmsKeyId": "The ARN of the KMS key that you use to encrypt the model copy.
", "CreateModelCustomizationJobRequest$customModelKmsKeyId": "The custom model is encrypted at rest using this key.
", "CreateModelImportJobRequest$importedModelKmsKeyId": "The imported model is encrypted at rest using this key.
", "GetEvaluationJobResponse$customerEncryptionKeyId": "The Amazon Resource Name (ARN) of the customer managed encryption key specified when the evaluation job was created.
", "ModelInvocationJobS3OutputDataConfig$s3EncryptionKeyId": "The unique identifier of the key that encrypts the S3 location of the output data.
", "SageMakerEndpoint$kmsEncryptionKey": "The Amazon Web Services KMS key that Amazon SageMaker uses to encrypt data on the storage volume attached to the Amazon EC2 compute instance that hosts the endpoint.
", "UpdateGuardrailRequest$kmsKeyId": "The ARN of the KMS key with which to encrypt the guardrail.
" } }, "KnowledgeBaseConfig": { "base": "The configuration details for retrieving information from a knowledge base and generating responses.
", "refs": { "RAGConfig$knowledgeBaseConfig": "Contains configuration details for knowledge base retrieval and response generation.
" } }, "KnowledgeBaseId": { "base": null, "refs": { "EvaluationBedrockKnowledgeBaseIdentifiers$member": null, "KnowledgeBaseRetrieveAndGenerateConfiguration$knowledgeBaseId": "The unique identifier of the knowledge base.
", "RetrieveConfig$knowledgeBaseId": "The unique identifier of the knowledge base.
" } }, "KnowledgeBaseRetrievalConfiguration": { "base": "Contains configuration details for retrieving information from a knowledge base.
", "refs": { "KnowledgeBaseRetrieveAndGenerateConfiguration$retrievalConfiguration": "Contains configuration details for retrieving text chunks.
", "RetrieveConfig$knowledgeBaseRetrievalConfiguration": "Contains configuration details for knowledge base retrieval.
" } }, "KnowledgeBaseRetrieveAndGenerateConfiguration": { "base": "Contains configuration details for retrieving information from a knowledge base and generating responses.
", "refs": { "RetrieveAndGenerateConfiguration$knowledgeBaseConfiguration": "Contains configuration details for the knowledge base retrieval and response generation.
" } }, "KnowledgeBaseVectorSearchConfiguration": { "base": "The configuration details for returning the results from the knowledge base vector search.
", "refs": { "KnowledgeBaseRetrievalConfiguration$vectorSearchConfiguration": "Contains configuration details for returning the results from the vector search.
" } }, "KnowledgeBaseVectorSearchConfigurationNumberOfResultsInteger": { "base": null, "refs": { "KnowledgeBaseVectorSearchConfiguration$numberOfResults": "The number of text chunks to retrieve; the number of results to return.
" } }, "LegalTerm": { "base": "The legal term of the agreement.
", "refs": { "TermDetails$legalTerm": "Describes the legal terms.
" } }, "ListAutomatedReasoningPoliciesRequest": { "base": null, "refs": { } }, "ListAutomatedReasoningPoliciesResponse": { "base": null, "refs": { } }, "ListAutomatedReasoningPolicyBuildWorkflowsRequest": { "base": null, "refs": { } }, "ListAutomatedReasoningPolicyBuildWorkflowsResponse": { "base": null, "refs": { } }, "ListAutomatedReasoningPolicyTestCasesRequest": { "base": null, "refs": { } }, "ListAutomatedReasoningPolicyTestCasesResponse": { "base": null, "refs": { } }, "ListAutomatedReasoningPolicyTestResultsRequest": { "base": null, "refs": { } }, "ListAutomatedReasoningPolicyTestResultsResponse": { "base": null, "refs": { } }, "ListCustomModelDeploymentsRequest": { "base": null, "refs": { } }, "ListCustomModelDeploymentsResponse": { "base": null, "refs": { } }, "ListCustomModelsRequest": { "base": null, "refs": { } }, "ListCustomModelsResponse": { "base": null, "refs": { } }, "ListEvaluationJobsRequest": { "base": null, "refs": { } }, "ListEvaluationJobsResponse": { "base": null, "refs": { } }, "ListFoundationModelAgreementOffersRequest": { "base": null, "refs": { } }, "ListFoundationModelAgreementOffersResponse": { "base": null, "refs": { } }, "ListFoundationModelsRequest": { "base": null, "refs": { } }, "ListFoundationModelsResponse": { "base": null, "refs": { } }, "ListGuardrailsRequest": { "base": null, "refs": { } }, "ListGuardrailsResponse": { "base": null, "refs": { } }, "ListImportedModelsRequest": { "base": null, "refs": { } }, "ListImportedModelsResponse": { "base": null, "refs": { } }, "ListInferenceProfilesRequest": { "base": null, "refs": { } }, "ListInferenceProfilesResponse": { "base": null, "refs": { } }, "ListMarketplaceModelEndpointsRequest": { "base": null, "refs": { } }, "ListMarketplaceModelEndpointsResponse": { "base": null, "refs": { } }, "ListModelCopyJobsRequest": { "base": null, "refs": { } }, "ListModelCopyJobsResponse": { "base": null, "refs": { } }, "ListModelCustomizationJobsRequest": { "base": null, "refs": { } }, "ListModelCustomizationJobsResponse": { "base": null, "refs": { } }, "ListModelImportJobsRequest": { "base": null, "refs": { } }, "ListModelImportJobsResponse": { "base": null, "refs": { } }, "ListModelInvocationJobsRequest": { "base": null, "refs": { } }, "ListModelInvocationJobsResponse": { "base": null, "refs": { } }, "ListPromptRoutersRequest": { "base": null, "refs": { } }, "ListPromptRoutersResponse": { "base": null, "refs": { } }, "ListProvisionedModelThroughputsRequest": { "base": null, "refs": { } }, "ListProvisionedModelThroughputsResponse": { "base": null, "refs": { } }, "ListTagsForResourceRequest": { "base": null, "refs": { } }, "ListTagsForResourceResponse": { "base": null, "refs": { } }, "LogGroupName": { "base": null, "refs": { "CloudWatchConfig$logGroupName": "The log group name.
" } }, "LoggingConfig": { "base": "Configuration fields for invocation logging.
", "refs": { "GetModelInvocationLoggingConfigurationResponse$loggingConfig": "The current configuration values.
", "PutModelInvocationLoggingConfigurationRequest$loggingConfig": "The logging configuration values to set.
" } }, "MarketplaceModelEndpoint": { "base": "Contains details about an endpoint for a model from Amazon Bedrock Marketplace.
", "refs": { "CreateMarketplaceModelEndpointResponse$marketplaceModelEndpoint": "Details about the created endpoint.
", "GetMarketplaceModelEndpointResponse$marketplaceModelEndpoint": "Details about the requested endpoint.
", "RegisterMarketplaceModelEndpointResponse$marketplaceModelEndpoint": "Details about the registered endpoint.
", "UpdateMarketplaceModelEndpointResponse$marketplaceModelEndpoint": "Details about the updated endpoint.
" } }, "MarketplaceModelEndpointSummaries": { "base": null, "refs": { "ListMarketplaceModelEndpointsResponse$marketplaceModelEndpoints": "An array of endpoint summaries.
" } }, "MarketplaceModelEndpointSummary": { "base": "Provides a summary of an endpoint for a model from Amazon Bedrock Marketplace.
", "refs": { "MarketplaceModelEndpointSummaries$member": null } }, "MaxResults": { "base": null, "refs": { "ListAutomatedReasoningPoliciesRequest$maxResults": "The maximum number of policies to return in a single call.
", "ListAutomatedReasoningPolicyBuildWorkflowsRequest$maxResults": "The maximum number of build workflows to return in a single response. Valid range is 1-100.
", "ListAutomatedReasoningPolicyTestCasesRequest$maxResults": "The maximum number of tests to return in a single call.
", "ListAutomatedReasoningPolicyTestResultsRequest$maxResults": "The maximum number of test results to return in a single response. Valid range is 1-100.
", "ListCustomModelDeploymentsRequest$maxResults": "The maximum number of results to return in a single call.
", "ListCustomModelsRequest$maxResults": "The maximum number of results to return in the response. If the total number of results is greater than this value, use the token returned in the response in the nextToken field when making another request to return the next batch of results.
The maximum number of results to return.
", "ListGuardrailsRequest$maxResults": "The maximum number of results to return in the response.
", "ListImportedModelsRequest$maxResults": "The maximum number of results to return in the response. If the total number of results is greater than this value, use the token returned in the response in the nextToken field when making another request to return the next batch of results.
The maximum number of results to return in the response. If the total number of results is greater than this value, use the token returned in the response in the nextToken field when making another request to return the next batch of results.
The maximum number of results to return in a single call. If more results are available, the operation returns a NextToken value.
The maximum number of results to return in the response. If the total number of results is greater than this value, use the token returned in the response in the nextToken field when making another request to return the next batch of results.
The maximum number of results to return in the response. If the total number of results is greater than this value, use the token returned in the response in the nextToken field when making another request to return the next batch of results.
The maximum number of results to return in the response. If the total number of results is greater than this value, use the token returned in the response in the nextToken field when making another request to return the next batch of results.
The maximum number of results to return. If there are more results than the number that you specify, a nextToken value is returned. Use the nextToken in a request to return the next batch of results.
The maximum number of prompt routers to return in one page of results.
", "ListProvisionedModelThroughputsRequest$maxResults": "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.
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.
" } }, "Message": { "base": null, "refs": { "GetModelInvocationJobResponse$message": "If the batch inference job failed, this field contains a message describing why the job failed.
", "ModelInvocationJobSummary$message": "If the batch inference job failed, this field contains a message describing why the job failed.
" } }, "MetadataAttributeSchema": { "base": "Defines the schema for a metadata attribute used in Knowledge Base vector searches. Metadata attributes provide additional context for documents and can be used for filtering and reranking search results.
", "refs": { "MetadataAttributeSchemaList$member": null } }, "MetadataAttributeSchemaDescriptionString": { "base": null, "refs": { "MetadataAttributeSchema$description": "An optional description of the metadata attribute that provides additional context about its purpose and usage.
" } }, "MetadataAttributeSchemaKeyString": { "base": null, "refs": { "MetadataAttributeSchema$key": "The unique identifier for the metadata attribute. This key is used to reference the attribute in filter expressions and reranking configurations.
" } }, "MetadataAttributeSchemaList": { "base": null, "refs": { "ImplicitFilterConfiguration$metadataAttributes": "A list of metadata attribute schemas that define the structure and properties of metadata fields used for implicit filtering. Each attribute defines a key, type, and optional description.
" } }, "MetadataConfigurationForReranking": { "base": "Configuration for how metadata should be used during the reranking process in Knowledge Base vector searches. This determines which metadata fields are included or excluded when reordering search results.
", "refs": { "VectorSearchBedrockRerankingConfiguration$metadataConfiguration": "Configuration for how document metadata should be used during the reranking process. This determines which metadata fields are included when reordering search results.
" } }, "MetricFloat": { "base": null, "refs": { "TrainingMetrics$trainingLoss": "Loss metric associated with the custom job.
", "ValidatorMetric$validationLoss": "The validation loss associated with this validator.
" } }, "MetricName": { "base": null, "refs": { "CustomMetricDefinition$name": "The name for a custom metric. Names must be unique in your Amazon Web Services region.
" } }, "ModelArchitecture": { "base": null, "refs": { "ImportedModelSummary$modelArchitecture": "The architecture of the imported model.
" } }, "ModelArn": { "base": null, "refs": { "CreateCustomModelResponse$modelArn": "The Amazon Resource Name (ARN) of the new custom model.
", "CreateModelCopyJobRequest$sourceModelArn": "The Amazon Resource Name (ARN) of the model to be copied.
", "CustomModelDeploymentSummary$modelArn": "The Amazon Resource Name (ARN) of the custom model associated with this deployment.
", "CustomModelSummary$baseModelArn": "The base model Amazon Resource Name (ARN).
", "GetCustomModelResponse$modelArn": "Amazon Resource Name (ARN) associated with this model.
", "GetCustomModelResponse$baseModelArn": "Amazon Resource Name (ARN) of the base model.
", "GetModelCopyJobResponse$sourceModelArn": "The Amazon Resource Name (ARN) of the original model being copied.
", "GetProvisionedModelThroughputResponse$modelArn": "The Amazon Resource Name (ARN) of the model associated with this Provisioned Throughput.
", "GetProvisionedModelThroughputResponse$desiredModelArn": "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.
Return custom models only if the base model Amazon Resource Name (ARN) matches this parameter.
", "ListModelCopyJobsRequest$sourceModelArnEquals": "Filters for model copy jobs in which the Amazon Resource Name (ARN) of the source model to is equal to the value that you specify.
", "ListProvisionedModelThroughputsRequest$modelArnEquals": "A filter that returns Provisioned Throughputs whose model Amazon Resource Name (ARN) is equal to the value that you specify.
", "ModelCopyJobSummary$sourceModelArn": "The Amazon Resource Name (ARN) of the original model being copied.
", "ModelCustomizationJobSummary$baseModelArn": "Amazon Resource Name (ARN) of the base model.
", "ProvisionedModelSummary$modelArn": "The Amazon Resource Name (ARN) of the model associated with the Provisioned Throughput.
", "ProvisionedModelSummary$desiredModelArn": "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 model copy job.
", "GetModelCopyJobRequest$jobArn": "The Amazon Resource Name (ARN) of the model copy job.
", "GetModelCopyJobResponse$jobArn": "The Amazon Resource Name (ARN) of the model copy job.
", "ModelCopyJobSummary$jobArn": "The Amazon Resoource Name (ARN) of the model copy job.
" } }, "ModelCopyJobStatus": { "base": null, "refs": { "GetModelCopyJobResponse$status": "The status of the model copy job.
", "ListModelCopyJobsRequest$statusEquals": "Filters for model copy jobs whose status matches the value that you specify.
", "ModelCopyJobSummary$status": "The status of the model copy job.
" } }, "ModelCopyJobSummaries": { "base": null, "refs": { "ListModelCopyJobsResponse$modelCopyJobSummaries": "A list of information about each model copy job.
" } }, "ModelCopyJobSummary": { "base": "Contains details about each model copy job.
This data type is used in the following API operations:
", "refs": { "ModelCopyJobSummaries$member": null } }, "ModelCustomization": { "base": null, "refs": { "ListFoundationModelsRequest$byCustomizationType": "Return models that support the customization type that you specify. For more information, see Custom models in the Amazon Bedrock User Guide.
", "ModelCustomizationList$member": null } }, "ModelCustomizationHyperParameters": { "base": null, "refs": { "CreateModelCustomizationJobRequest$hyperParameters": "Parameters related to tuning the model. For details on the format for different models, see Custom model hyperparameters.
", "GetCustomModelResponse$hyperParameters": "Hyperparameter values associated with this model. For details on the format for different models, see Custom model hyperparameters.
", "GetModelCustomizationJobResponse$hyperParameters": "The hyperparameter values for the job. For details on the format for different models, see Custom model hyperparameters.
" } }, "ModelCustomizationJobArn": { "base": null, "refs": { "CreateModelCustomizationJobResponse$jobArn": "Amazon Resource Name (ARN) of the fine tuning job
", "GetCustomModelResponse$jobArn": "Job Amazon Resource Name (ARN) associated with this model. For models that you create with the CreateCustomModel API operation, this is NULL.
The Amazon Resource Name (ARN) of the customization job.
", "ModelCustomizationJobSummary$jobArn": "Amazon Resource Name (ARN) of the customization job.
" } }, "ModelCustomizationJobIdentifier": { "base": null, "refs": { "GetModelCustomizationJobRequest$jobIdentifier": "Identifier for the customization job.
", "StopModelCustomizationJobRequest$jobIdentifier": "Job identifier of the job to stop.
" } }, "ModelCustomizationJobStatus": { "base": null, "refs": { "GetModelCustomizationJobResponse$status": "The status of the job. A successful job transitions from in-progress to completed when the output model is ready to use. If the job failed, the failure message contains information about why the job failed.
", "ModelCustomizationJobSummary$status": "Status of the customization job.
" } }, "ModelCustomizationJobSummaries": { "base": null, "refs": { "ListModelCustomizationJobsResponse$modelCustomizationJobSummaries": "Job summaries.
" } }, "ModelCustomizationJobSummary": { "base": "Information about one customization job
", "refs": { "ModelCustomizationJobSummaries$member": null } }, "ModelCustomizationList": { "base": null, "refs": { "FoundationModelDetails$customizationsSupported": "The customization that the model supports.
", "FoundationModelSummary$customizationsSupported": "Whether the model supports fine-tuning or continual pre-training.
" } }, "ModelDataSource": { "base": "The data source of the model to import.
", "refs": { "CreateCustomModelRequest$modelSourceConfig": "The data source for the model. The Amazon S3 URI in the model source must be for the Amazon-managed Amazon S3 bucket containing your model artifacts.
", "CreateModelImportJobRequest$modelDataSource": "The data source for the imported model.
", "GetImportedModelResponse$modelDataSource": "The data source for this imported model.
", "GetModelImportJobResponse$modelDataSource": "The data source for the imported model.
" } }, "ModelDeploymentName": { "base": null, "refs": { "CreateCustomModelDeploymentRequest$modelDeploymentName": "The name for the custom model deployment. The name must be unique within your Amazon Web Services account and Region.
", "CustomModelDeploymentSummary$customModelDeploymentName": "The name of the custom model deployment.
", "GetCustomModelDeploymentResponse$modelDeploymentName": "The name of the custom model deployment.
", "ListCustomModelDeploymentsRequest$nameContains": "Filters deployments whose names contain the specified string.
" } }, "ModelId": { "base": null, "refs": { "CreateModelInvocationJobRequest$modelId": "The unique identifier of the foundation model to use for the batch inference job.
", "GetModelInvocationJobResponse$modelId": "The unique identifier of the foundation model used for model inference.
", "ModelInvocationJobSummary$modelId": "The unique identifier of the foundation model used for model inference.
" } }, "ModelIdentifier": { "base": null, "refs": { "CreateProvisionedModelThroughputRequest$modelId": "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.
", "DeleteCustomModelRequest$modelIdentifier": "Name of the model to delete.
", "GetCustomModelRequest$modelIdentifier": "Name or Amazon Resource Name (ARN) of the custom model.
", "GetFoundationModelRequest$modelIdentifier": "The model identifier.
", "UpdateProvisionedModelThroughputRequest$desiredModelId": "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.
The Amazon Resource Name (ARN) of the model import job.
", "GetImportedModelResponse$jobArn": "Job Amazon Resource Name (ARN) associated with the imported model.
", "GetModelImportJobResponse$jobArn": "The Amazon Resource Name (ARN) of the import job.
", "ModelImportJobSummary$jobArn": "The Amazon Resource Name (ARN) of the import job.
" } }, "ModelImportJobIdentifier": { "base": null, "refs": { "GetModelImportJobRequest$jobIdentifier": "The identifier of the import job.
" } }, "ModelImportJobStatus": { "base": null, "refs": { "GetModelImportJobResponse$status": "The status of the job. A successful job transitions from in-progress to completed when the imported model is ready to use. If the job failed, the failure message contains information about why the job failed.
", "ListModelImportJobsRequest$statusEquals": "Return imported jobs with the specified status.
", "ModelImportJobSummary$status": "The status of the imported job.
" } }, "ModelImportJobSummaries": { "base": null, "refs": { "ListModelImportJobsResponse$modelImportJobSummaries": "Import job summaries.
" } }, "ModelImportJobSummary": { "base": "Information about the import job.
", "refs": { "ModelImportJobSummaries$member": null } }, "ModelInvocationIdempotencyToken": { "base": null, "refs": { "CreateModelInvocationJobRequest$clientRequestToken": "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.
", "GetModelInvocationJobResponse$clientRequestToken": "A unique, case-sensitive identifier to ensure that the API request completes no more than one time. If this token matches a previous request, Amazon Bedrock ignores the request, but does not return an error. For more information, see Ensuring idempotency.
", "ModelInvocationJobSummary$clientRequestToken": "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.
" } }, "ModelInvocationJobArn": { "base": null, "refs": { "CreateModelInvocationJobResponse$jobArn": "The Amazon Resource Name (ARN) of the batch inference job.
", "GetModelInvocationJobResponse$jobArn": "The Amazon Resource Name (ARN) of the batch inference job.
", "ModelInvocationJobSummary$jobArn": "The Amazon Resource Name (ARN) of the batch inference job.
" } }, "ModelInvocationJobIdentifier": { "base": null, "refs": { "GetModelInvocationJobRequest$jobIdentifier": "The Amazon Resource Name (ARN) of the batch inference job.
", "StopModelInvocationJobRequest$jobIdentifier": "The Amazon Resource Name (ARN) of the batch inference job to stop.
" } }, "ModelInvocationJobInputDataConfig": { "base": "Details about the location of the input to the batch inference job.
", "refs": { "CreateModelInvocationJobRequest$inputDataConfig": "Details about the location of the input to the batch inference job.
", "GetModelInvocationJobResponse$inputDataConfig": "Details about the location of the input to the batch inference job.
", "ModelInvocationJobSummary$inputDataConfig": "Details about the location of the input to the batch inference job.
" } }, "ModelInvocationJobName": { "base": null, "refs": { "CreateModelInvocationJobRequest$jobName": "A name to give the batch inference job.
", "GetModelInvocationJobResponse$jobName": "The name of the batch inference job.
", "ListModelInvocationJobsRequest$nameContains": "Specify a string to filter for batch inference jobs whose names contain the string.
", "ModelInvocationJobSummary$jobName": "The name of the batch inference job.
" } }, "ModelInvocationJobOutputDataConfig": { "base": "Contains the configuration of the S3 location of the output data.
", "refs": { "CreateModelInvocationJobRequest$outputDataConfig": "Details about the location of the output of the batch inference job.
", "GetModelInvocationJobResponse$outputDataConfig": "Details about the location of the output of the batch inference job.
", "ModelInvocationJobSummary$outputDataConfig": "Details about the location of the output of the batch inference job.
" } }, "ModelInvocationJobS3InputDataConfig": { "base": "Contains the configuration of the S3 location of the input data.
", "refs": { "ModelInvocationJobInputDataConfig$s3InputDataConfig": "Contains the configuration of the S3 location of the input data.
" } }, "ModelInvocationJobS3OutputDataConfig": { "base": "Contains the configuration of the S3 location of the output data.
", "refs": { "ModelInvocationJobOutputDataConfig$s3OutputDataConfig": "Contains the configuration of the S3 location of the output data.
" } }, "ModelInvocationJobStatus": { "base": null, "refs": { "GetModelInvocationJobResponse$status": "The status of the batch inference job.
The following statuses are possible:
Submitted – This job has been submitted to a queue for validation.
Validating – This job is being validated for the requirements described in Format and upload your batch inference data. The criteria include the following:
Your IAM service role has access to the Amazon S3 buckets containing your files.
Your files are .jsonl files and each individual record is a JSON object in the correct format. Note that validation doesn't check if the modelInput value matches the request body for the model.
Your files fulfill the requirements for file size and number of records. For more information, see Quotas for Amazon Bedrock.
Scheduled – This job has been validated and is now in a queue. The job will automatically start when it reaches its turn.
Expired – This job timed out because it was scheduled but didn't begin before the set timeout duration. Submit a new job request.
InProgress – This job has begun. You can start viewing the results in the output S3 location.
Completed – This job has successfully completed. View the output files in the output S3 location.
PartiallyCompleted – This job has partially completed. Not all of your records could be processed in time. View the output files in the output S3 location.
Failed – This job has failed. Check the failure message for any further details. For further assistance, reach out to the Amazon Web ServicesSupport Center.
Stopped – This job was stopped by a user.
Stopping – This job is being stopped by a user.
Specify a status to filter for batch inference jobs whose statuses match the string you specify.
The following statuses are possible:
Submitted – This job has been submitted to a queue for validation.
Validating – This job is being validated for the requirements described in Format and upload your batch inference data. The criteria include the following:
Your IAM service role has access to the Amazon S3 buckets containing your files.
Your files are .jsonl files and each individual record is a JSON object in the correct format. Note that validation doesn't check if the modelInput value matches the request body for the model.
Your files fulfill the requirements for file size and number of records. For more information, see Quotas for Amazon Bedrock.
Scheduled – This job has been validated and is now in a queue. The job will automatically start when it reaches its turn.
Expired – This job timed out because it was scheduled but didn't begin before the set timeout duration. Submit a new job request.
InProgress – This job has begun. You can start viewing the results in the output S3 location.
Completed – This job has successfully completed. View the output files in the output S3 location.
PartiallyCompleted – This job has partially completed. Not all of your records could be processed in time. View the output files in the output S3 location.
Failed – This job has failed. Check the failure message for any further details. For further assistance, reach out to the Amazon Web ServicesSupport Center.
Stopped – This job was stopped by a user.
Stopping – This job is being stopped by a user.
The status of the batch inference job.
The following statuses are possible:
Submitted – This job has been submitted to a queue for validation.
Validating – This job is being validated for the requirements described in Format and upload your batch inference data. The criteria include the following:
Your IAM service role has access to the Amazon S3 buckets containing your files.
Your files are .jsonl files and each individual record is a JSON object in the correct format. Note that validation doesn't check if the modelInput value matches the request body for the model.
Your files fulfill the requirements for file size and number of records. For more information, see Quotas for Amazon Bedrock.
Scheduled – This job has been validated and is now in a queue. The job will automatically start when it reaches its turn.
Expired – This job timed out because it was scheduled but didn't begin before the set timeout duration. Submit a new job request.
InProgress – This job has begun. You can start viewing the results in the output S3 location.
Completed – This job has successfully completed. View the output files in the output S3 location.
PartiallyCompleted – This job has partially completed. Not all of your records could be processed in time. View the output files in the output S3 location.
Failed – This job has failed. Check the failure message for any further details. For further assistance, reach out to the Amazon Web ServicesSupport Center.
Stopped – This job was stopped by a user.
Stopping – This job is being stopped by a user.
A list of items, each of which contains a summary about a batch inference job.
" } }, "ModelInvocationJobSummary": { "base": "A summary of a batch inference job.
", "refs": { "ModelInvocationJobSummaries$member": null } }, "ModelInvocationJobTimeoutDurationInHours": { "base": null, "refs": { "CreateModelInvocationJobRequest$timeoutDurationInHours": "The number of hours after which to force the batch inference job to time out.
", "GetModelInvocationJobResponse$timeoutDurationInHours": "The number of hours after which batch inference job was set to time out.
", "ModelInvocationJobSummary$timeoutDurationInHours": "The number of hours after which the batch inference job was set to time out.
" } }, "ModelModality": { "base": null, "refs": { "ListFoundationModelsRequest$byOutputModality": "Return models that support the output modality that you specify.
", "ModelModalityList$member": null } }, "ModelModalityList": { "base": null, "refs": { "FoundationModelDetails$inputModalities": "The input modalities that the model supports.
", "FoundationModelDetails$outputModalities": "The output modalities that the model supports.
", "FoundationModelSummary$inputModalities": "The input modalities that the model supports.
", "FoundationModelSummary$outputModalities": "The output modalities that the model supports.
" } }, "ModelName": { "base": null, "refs": { "CustomModelSummary$baseModelName": "The base model name.
" } }, "ModelSourceIdentifier": { "base": null, "refs": { "CreateMarketplaceModelEndpointRequest$modelSourceIdentifier": "The ARN of the model from Amazon Bedrock Marketplace that you want to deploy to the endpoint.
", "ListMarketplaceModelEndpointsRequest$modelSourceEquals": "If specified, only endpoints for the given model source identifier are returned.
", "MarketplaceModelEndpoint$modelSourceIdentifier": "The ARN of the model from Amazon Bedrock Marketplace that is deployed on this endpoint.
", "MarketplaceModelEndpointSummary$modelSourceIdentifier": "The ARN of the model from Amazon Bedrock Marketplace that is deployed on this endpoint.
", "RegisterMarketplaceModelEndpointRequest$modelSourceIdentifier": "The ARN of the model from Amazon Bedrock Marketplace that is deployed on the endpoint.
" } }, "ModelStatus": { "base": null, "refs": { "CustomModelSummary$modelStatus": "The current status of the custom model. Possible values include:
Creating - The model is being created and validated.
Active - The model has been successfully created and is ready for use.
Failed - The model creation process failed.
The current status of the custom model. Possible values include:
Creating - The model is being created and validated.
Active - The model has been successfully created and is ready for use.
Failed - The model creation process failed. Check the failureMessage field for details.
The status of them model to filter results by. Possible values include:
Creating - Include only models that are currently being created and validated.
Active - Include only models that have been successfully created and are ready for use.
Failed - Include only models where the creation process failed.
If you don't specify a status, the API returns models in all states.
" } }, "NonBlankString": { "base": null, "refs": { "AccessDeniedException$message": null, "ConflictException$message": null, "InternalServerException$message": null, "ResourceInUseException$message": null, "ResourceNotFoundException$message": null, "ServiceQuotaExceededException$message": null, "ServiceUnavailableException$message": null, "ThrottlingException$message": null, "TooManyTagsException$message": null, "ValidationException$message": null } }, "Offer": { "base": "An offer dictates usage terms for the model.
", "refs": { "Offers$member": null } }, "OfferId": { "base": null, "refs": { "Offer$offerId": "Offer Id for a model offer.
" } }, "OfferToken": { "base": null, "refs": { "CreateFoundationModelAgreementRequest$offerToken": "An offer token encapsulates the information for an offer.
", "Offer$offerToken": "Offer token.
" } }, "OfferType": { "base": null, "refs": { "ListFoundationModelAgreementOffersRequest$offerType": "Type of offer associated with the model.
" } }, "Offers": { "base": null, "refs": { "ListFoundationModelAgreementOffersResponse$offers": "List of the offers associated with the specified model.
" } }, "OrchestrationConfiguration": { "base": "The configuration details for the model to process the prompt prior to retrieval and response generation.
", "refs": { "KnowledgeBaseRetrieveAndGenerateConfiguration$orchestrationConfiguration": "Contains configuration details for the model to process the prompt prior to retrieval and response generation.
" } }, "OutputDataConfig": { "base": "S3 Location of the output data.
", "refs": { "CreateModelCustomizationJobRequest$outputDataConfig": "S3 location for the output data.
", "GetCustomModelResponse$outputDataConfig": "Output data configuration associated with this custom model.
", "GetModelCustomizationJobResponse$outputDataConfig": "Output data configuration
" } }, "PaginationToken": { "base": null, "refs": { "ListAutomatedReasoningPoliciesRequest$nextToken": "The pagination token from a previous request to retrieve the next page of results.
", "ListAutomatedReasoningPoliciesResponse$nextToken": "The pagination token to use in a subsequent request to retrieve the next page of results.
", "ListAutomatedReasoningPolicyBuildWorkflowsRequest$nextToken": "A pagination token from a previous request to continue listing build workflows from where the previous request left off.
", "ListAutomatedReasoningPolicyBuildWorkflowsResponse$nextToken": "A pagination token to use in subsequent requests to retrieve additional build workflows.
", "ListAutomatedReasoningPolicyTestCasesRequest$nextToken": "The pagination token from a previous request to retrieve the next page of results.
", "ListAutomatedReasoningPolicyTestCasesResponse$nextToken": "The pagination token to use in a subsequent request to retrieve the next page of results.
", "ListAutomatedReasoningPolicyTestResultsRequest$nextToken": "A pagination token from a previous request to continue listing test results from where the previous request left off.
", "ListAutomatedReasoningPolicyTestResultsResponse$nextToken": "A pagination token to use in subsequent requests to retrieve additional test results.
", "ListCustomModelDeploymentsRequest$nextToken": "The token for the next set of results. Use this token to retrieve additional results when the response is truncated.
", "ListCustomModelDeploymentsResponse$nextToken": "The token for the next set of results. This value is null when there are no more results to return.
", "ListCustomModelsRequest$nextToken": "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.
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.
Continuation token from the previous response, for Amazon Bedrock to list the next set of results.
", "ListEvaluationJobsResponse$nextToken": "Continuation token from the previous response, for Amazon Bedrock to list the next set of results.
", "ListGuardrailsRequest$nextToken": "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.
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.
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.
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.
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.
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 token for the next set of results. You receive this token from a previous ListMarketplaceModelEndpoints call.
The token for the next set of results. Use this token to get the next set of results.
", "ListModelCopyJobsRequest$nextToken": "If the total number of results is greater than the maxResults value provided in the request, enter the token returned in the nextToken field in the response in this field to return the next batch of results.
If the total number of results is greater than the maxResults value provided in the request, use this token when making another request in the nextToken field to return the next batch of results.
If the total number of results is greater than the maxResults value provided in the request, enter the token returned in the nextToken field in the response in this field to return the next batch of results.
If the total number of results is greater than the maxResults value provided in the request, use this token when making another request in the nextToken field to return the next batch of results.
If the total number of results is greater than the maxResults value provided in the request, enter the token returned in the nextToken field in the response in this field to return the next batch of results.
If the total number of results is greater than the maxResults value provided in the request, enter the token returned in the nextToken field in the response in this field to return the next batch of results.
If there were more results than the value you specified in the maxResults field in a previous ListModelInvocationJobs request, the response would have returned a nextToken value. To see the next batch of results, send the nextToken value in another request.
If there are more results than can fit in the response, a nextToken is returned. Use the nextToken in a request to return the next batch of results.
Specify the pagination token from a previous request to retrieve the next page of results.
", "ListPromptRoutersResponse$nextToken": "Specify the pagination token from a previous request to retrieve the next page of results.
", "ListProvisionedModelThroughputsRequest$nextToken": "If there are more results than the number you specified in the maxResults field, the response returns a nextToken value. To see the next batch of results, specify the nextToken value in this field.
If there are more results than the number you specified in the maxResults field, this value is returned. To see the next batch of results, include this value in the nextToken field in another list request.
Specifies whether to use the latency-optimized or standard version of a model or inference profile.
" } }, "PerformanceConfiguration": { "base": "Contains performance settings for a model.
", "refs": { "EvaluationBedrockModel$performanceConfig": "Specifies performance settings for the model or inference profile.
" } }, "PositiveInteger": { "base": null, "refs": { "CreateProvisionedModelThroughputRequest$modelUnits": "Number of model units to allocate. A model unit delivers a specific throughput level for the specified model. The throughput level of a model unit specifies the total number of input and output tokens that it can process and generate within a span of one minute. By default, your account has no model units for purchasing Provisioned Throughputs with commitment. You must first visit the Amazon Web Services support center to request MUs.
For model unit quotas, see Provisioned Throughput quotas in the Amazon Bedrock User Guide.
For more information about what an MU specifies, contact your Amazon Web Services account manager.
", "GetProvisionedModelThroughputResponse$modelUnits": "The number of model units allocated to this Provisioned Throughput.
", "GetProvisionedModelThroughputResponse$desiredModelUnits": "The number of model units that was requested for this Provisioned Throughput.
", "ProvisionedModelSummary$modelUnits": "The number of model units allocated to the Provisioned Throughput.
", "ProvisionedModelSummary$desiredModelUnits": "The number of model units that was requested to be allocated to the Provisioned Throughput.
" } }, "PricingTerm": { "base": "Describes the usage-based pricing term.
", "refs": { "TermDetails$usageBasedPricingTerm": null } }, "PromptRouterArn": { "base": null, "refs": { "CreatePromptRouterResponse$promptRouterArn": "The Amazon Resource Name (ARN) that uniquely identifies the prompt router.
", "DeletePromptRouterRequest$promptRouterArn": "The Amazon Resource Name (ARN) of the prompt router to delete.
", "GetPromptRouterRequest$promptRouterArn": "The prompt router's ARN
", "GetPromptRouterResponse$promptRouterArn": "The prompt router's ARN
", "PromptRouterSummary$promptRouterArn": "The router's ARN.
" } }, "PromptRouterDescription": { "base": null, "refs": { "CreatePromptRouterRequest$description": "An optional description of the prompt router to help identify its purpose.
", "GetPromptRouterResponse$description": "The router's description.
", "PromptRouterSummary$description": "The router's description.
" } }, "PromptRouterName": { "base": null, "refs": { "CreatePromptRouterRequest$promptRouterName": "The name of the prompt router. The name must be unique within your Amazon Web Services account in the current region.
", "GetPromptRouterResponse$promptRouterName": "The router's name.
", "PromptRouterSummary$promptRouterName": "The router's name.
" } }, "PromptRouterStatus": { "base": null, "refs": { "GetPromptRouterResponse$status": "The router's status.
", "PromptRouterSummary$status": "The router's status.
" } }, "PromptRouterSummaries": { "base": null, "refs": { "ListPromptRoutersResponse$promptRouterSummaries": "A list of prompt router summaries.
" } }, "PromptRouterSummary": { "base": "Details about a prompt router.
", "refs": { "PromptRouterSummaries$member": null } }, "PromptRouterTargetModel": { "base": "The target model for a prompt router.
", "refs": { "CreatePromptRouterRequest$fallbackModel": "The default model to use when the routing criteria is not met.
", "GetPromptRouterResponse$fallbackModel": "The router's fallback model.
", "PromptRouterSummary$fallbackModel": "The router's fallback model.
", "PromptRouterTargetModels$member": null } }, "PromptRouterTargetModelArn": { "base": null, "refs": { "PromptRouterTargetModel$modelArn": "The target model's ARN.
" } }, "PromptRouterTargetModels": { "base": null, "refs": { "CreatePromptRouterRequest$models": "A list of foundation models that the prompt router can route requests to. At least one model must be specified.
", "GetPromptRouterResponse$models": "The router's models.
", "PromptRouterSummary$models": "The router's models.
" } }, "PromptRouterType": { "base": null, "refs": { "GetPromptRouterResponse$type": "The router's type.
", "ListPromptRoutersRequest$type": "The type of the prompt routers, such as whether it's default or custom.
", "PromptRouterSummary$type": "The summary's type.
" } }, "PromptTemplate": { "base": "The template for the prompt that's sent to the model for response generation.
", "refs": { "ExternalSourcesGenerationConfiguration$promptTemplate": "Contains the template for the prompt for the external source wrapper object.
", "GenerationConfiguration$promptTemplate": "Contains the template for the prompt that's sent to the model for response generation.
" } }, "Provider": { "base": null, "refs": { "ListFoundationModelsRequest$byProvider": "Return models belonging to the model provider that you specify.
" } }, "ProvisionedModelArn": { "base": null, "refs": { "CreateProvisionedModelThroughputResponse$provisionedModelArn": "The Amazon Resource Name (ARN) for this Provisioned Throughput.
", "GetProvisionedModelThroughputResponse$provisionedModelArn": "The Amazon Resource Name (ARN) of the Provisioned Throughput.
", "ProvisionedModelSummary$provisionedModelArn": "The Amazon Resource Name (ARN) of the Provisioned Throughput.
" } }, "ProvisionedModelId": { "base": null, "refs": { "DeleteProvisionedModelThroughputRequest$provisionedModelId": "The Amazon Resource Name (ARN) or name of the Provisioned Throughput.
", "GetProvisionedModelThroughputRequest$provisionedModelId": "The Amazon Resource Name (ARN) or name of the Provisioned Throughput.
", "UpdateProvisionedModelThroughputRequest$provisionedModelId": "The Amazon Resource Name (ARN) or name of the Provisioned Throughput to update.
" } }, "ProvisionedModelName": { "base": null, "refs": { "CreateProvisionedModelThroughputRequest$provisionedModelName": "The name for this Provisioned Throughput.
", "GetProvisionedModelThroughputResponse$provisionedModelName": "The name of the Provisioned Throughput.
", "ListProvisionedModelThroughputsRequest$nameContains": "A filter that returns Provisioned Throughputs if their name contains the expression that you specify.
", "ProvisionedModelSummary$provisionedModelName": "The name of the Provisioned Throughput.
", "UpdateProvisionedModelThroughputRequest$desiredProvisionedModelName": "The new name for this Provisioned Throughput.
" } }, "ProvisionedModelStatus": { "base": null, "refs": { "GetProvisionedModelThroughputResponse$status": "The status of the Provisioned Throughput.
", "ListProvisionedModelThroughputsRequest$statusEquals": "A filter that returns Provisioned Throughputs if their statuses matches the value that you specify.
", "ProvisionedModelSummary$status": "The status of the Provisioned Throughput.
" } }, "ProvisionedModelSummaries": { "base": null, "refs": { "ListProvisionedModelThroughputsResponse$provisionedModelSummaries": "A list of summaries, one for each Provisioned Throughput in the response.
" } }, "ProvisionedModelSummary": { "base": "A summary of information about a Provisioned Throughput.
This data type is used in the following API operations:
", "refs": { "ProvisionedModelSummaries$member": null } }, "PutModelInvocationLoggingConfigurationRequest": { "base": null, "refs": { } }, "PutModelInvocationLoggingConfigurationResponse": { "base": null, "refs": { } }, "PutUseCaseForModelAccessRequest": { "base": null, "refs": { } }, "PutUseCaseForModelAccessResponse": { "base": null, "refs": { } }, "QueryTransformationConfiguration": { "base": "The configuration details for transforming the prompt.
", "refs": { "OrchestrationConfiguration$queryTransformationConfiguration": "Contains configuration details for transforming the prompt.
" } }, "QueryTransformationType": { "base": null, "refs": { "QueryTransformationConfiguration$type": "The type of transformation to apply to the prompt.
" } }, "RAGConfig": { "base": "Contains configuration details for retrieval of information and response generation.
", "refs": { "RagConfigs$member": null } }, "RAGStopSequences": { "base": null, "refs": { "TextInferenceConfig$stopSequences": "A list of sequences of characters that, if generated, will cause the model to stop generating further tokens. Do not use a minimum length of 1 or a maximum length of 1000. The limit values described here are arbitrary values, for actual values consult the limits defined by your specific model.
" } }, "RAGStopSequencesMemberString": { "base": null, "refs": { "RAGStopSequences$member": null } }, "RagConfigs": { "base": null, "refs": { "EvaluationInferenceConfig$ragConfigs": "Contains the configuration details of the inference for a knowledge base evaluation job, including either the retrieval only configuration or the retrieval with response generation configuration.
" } }, "RateCard": { "base": null, "refs": { "PricingTerm$rateCard": "Describes a usage price for each dimension.
" } }, "RatingScale": { "base": null, "refs": { "CustomMetricDefinition$ratingScale": "Defines the rating scale to be used for a custom metric. We recommend that you always define a ratings scale when creating a custom metric. If you don't define a scale, Amazon Bedrock won't be able to visually display the results of the evaluation in the console or calculate average values of numerical scores. For more information on specifying a rating scale, see Specifying an output schema (rating scale).
" } }, "RatingScaleItem": { "base": "Defines the value and corresponding definition for one rating in a custom metric rating scale.
", "refs": { "RatingScale$member": null } }, "RatingScaleItemDefinition": { "base": null, "refs": { "RatingScaleItem$definition": "Defines the definition for one rating in a custom metric rating scale.
" } }, "RatingScaleItemValue": { "base": "Defines the value for one rating in a custom metric rating scale.
", "refs": { "RatingScaleItem$value": "Defines the value for one rating in a custom metric rating scale.
" } }, "RatingScaleItemValueStringValueString": { "base": null, "refs": { "RatingScaleItemValue$stringValue": "A string representing the value for a rating in a custom metric rating scale.
" } }, "RegionAvailability": { "base": null, "refs": { "GetFoundationModelAvailabilityResponse$regionAvailability": "Region availability.
" } }, "RegisterMarketplaceModelEndpointRequest": { "base": null, "refs": { } }, "RegisterMarketplaceModelEndpointResponse": { "base": null, "refs": { } }, "RequestMetadataBaseFilters": { "base": "A mapping of a metadata key to a value that it should or should not equal.
", "refs": { "RequestMetadataFiltersList$member": null } }, "RequestMetadataFilters": { "base": "Rules for filtering invocation logs. A filter can be a mapping of a metadata key to a value that it should or should not equal (a base filter), or a list of base filters that are all applied with AND or OR logical operators
Rules for filtering invocation logs based on request metadata.
" } }, "RequestMetadataFiltersList": { "base": null, "refs": { "RequestMetadataFilters$andAll": "Include results where all of the based filters match.
", "RequestMetadataFilters$orAll": "Include results where any of the base filters match.
" } }, "RequestMetadataMap": { "base": null, "refs": { "RequestMetadataBaseFilters$equals": "Include results where the key equals the value.
", "RequestMetadataBaseFilters$notEquals": "Include results where the key does not equal the value.
", "RequestMetadataFilters$equals": "Include results where the key equals the value.
", "RequestMetadataFilters$notEquals": "Include results where the key does not equal the value.
" } }, "RequestMetadataMapKeyString": { "base": null, "refs": { "RequestMetadataMap$key": null } }, "RequestMetadataMapValueString": { "base": null, "refs": { "RequestMetadataMap$value": null } }, "RerankingMetadataSelectionMode": { "base": null, "refs": { "MetadataConfigurationForReranking$selectionMode": "The mode for selecting which metadata fields to include in the reranking process. Valid values are ALL (use all available metadata fields) or SELECTIVE (use only specified fields).
" } }, "RerankingMetadataSelectiveModeConfiguration": { "base": "Configuration for selectively including or excluding metadata fields during the reranking process. This allows you to control which metadata attributes are considered when reordering search results.
", "refs": { "MetadataConfigurationForReranking$selectiveModeConfiguration": "Configuration for selective mode, which allows you to explicitly include or exclude specific metadata fields during reranking. This is only used when selectionMode is set to SELECTIVE.
" } }, "ResourceInUseException": { "base": "Thrown when attempting to delete or modify a resource that is currently being used by other resources or operations. For example, trying to delete an Automated Reasoning policy that is referenced by an active guardrail.
", "refs": { } }, "ResourceNotFoundException": { "base": "The specified resource Amazon Resource Name (ARN) was not found. Check the Amazon Resource Name (ARN) and try your request again.
", "refs": { } }, "RetrievalFilter": { "base": "Specifies the filters to use on the metadata attributes/fields in the knowledge base data sources before returning results.
", "refs": { "KnowledgeBaseVectorSearchConfiguration$filter": "Specifies the filters to use on the metadata fields in the knowledge base data sources before returning results.
", "RetrievalFilterList$member": null } }, "RetrievalFilterList": { "base": null, "refs": { "RetrievalFilter$andAll": "Knowledge base data sources are returned if their metadata attributes fulfill all the filter conditions inside this list.
", "RetrievalFilter$orAll": "Knowledge base data sources are returned if their metadata attributes fulfill at least one of the filter conditions inside this list.
" } }, "RetrieveAndGenerateConfiguration": { "base": "Contains configuration details for a knowledge base retrieval and response generation.
", "refs": { "KnowledgeBaseConfig$retrieveAndGenerateConfig": "Contains configuration details for retrieving information from a knowledge base and generating responses.
" } }, "RetrieveAndGenerateType": { "base": null, "refs": { "RetrieveAndGenerateConfiguration$type": "The type of resource that contains your data for retrieving information and generating responses.
If you choose to use EXTERNAL_SOURCES, then currently only Claude 3 Sonnet models for knowledge bases are supported.
The configuration details for retrieving information from a knowledge base.
", "refs": { "KnowledgeBaseConfig$retrieveConfig": "Contains configuration details for retrieving information from a knowledge base.
" } }, "RoleArn": { "base": "ARN of a IAM role
", "refs": { "CloudWatchConfig$roleArn": "The role Amazon Resource Name (ARN).
", "CreateCustomModelRequest$roleArn": "The Amazon Resource Name (ARN) of an IAM service role that Amazon Bedrock assumes to perform tasks on your behalf. This role must have permissions to access the Amazon S3 bucket containing your model artifacts and the KMS key (if specified). For more information, see Setting up an IAM service role for importing models in the Amazon Bedrock User Guide.
", "CreateEvaluationJobRequest$roleArn": "The Amazon Resource Name (ARN) of an IAM service role that Amazon Bedrock can assume to perform tasks on your behalf. To learn more about the required permissions, see Required permissions for model evaluations.
", "CreateModelCustomizationJobRequest$roleArn": "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.
The Amazon Resource Name (ARN) of the model import job.
", "CreateModelInvocationJobRequest$roleArn": "The Amazon Resource Name (ARN) of the service role with permissions to carry out and manage batch inference. You can use the console to create a default service role or follow the steps at Create a service role for batch inference.
", "GetEvaluationJobResponse$roleArn": "The Amazon Resource Name (ARN) of the IAM service role used in the evaluation job.
", "GetModelCustomizationJobResponse$roleArn": "The Amazon Resource Name (ARN) of the IAM role.
", "GetModelImportJobResponse$roleArn": "The Amazon Resource Name (ARN) of the IAM role associated with this job.
", "GetModelInvocationJobResponse$roleArn": "The Amazon Resource Name (ARN) of the service role with permissions to carry out and manage batch inference. You can use the console to create a default service role or follow the steps at Create a service role for batch inference.
", "ModelInvocationJobSummary$roleArn": "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.
", "SageMakerEndpoint$executionRole": "The ARN of the IAM role that Amazon SageMaker can assume to access model artifacts and docker image for deployment on Amazon EC2 compute instances or for batch transform jobs.
" } }, "RoutingCriteria": { "base": "Routing criteria for a prompt router.
", "refs": { "CreatePromptRouterRequest$routingCriteria": "The criteria, which is the response quality difference, used to determine how incoming requests are routed to different models.
", "GetPromptRouterResponse$routingCriteria": "The router's routing criteria.
", "PromptRouterSummary$routingCriteria": "The router's routing criteria.
" } }, "RoutingCriteriaResponseQualityDifferenceDouble": { "base": null, "refs": { "RoutingCriteria$responseQualityDifference": "The criteria's response quality difference.
" } }, "S3Config": { "base": "S3 configuration for storing log data.
", "refs": { "CloudWatchConfig$largeDataDeliveryS3Config": "S3 configuration for delivering a large amount of data.
", "LoggingConfig$s3Config": "S3 configuration for storing log data.
" } }, "S3DataSource": { "base": "The Amazon S3 data source of the model to import.
", "refs": { "ModelDataSource$s3DataSource": "The Amazon S3 data source of the model to import.
" } }, "S3InputFormat": { "base": null, "refs": { "ModelInvocationJobS3InputDataConfig$s3InputFormat": "The format of the input data.
" } }, "S3ObjectDoc": { "base": "The unique wrapper object of the document from the S3 location.
", "refs": { "ExternalSource$s3Location": "The S3 location of the external source wrapper object.
" } }, "S3Uri": { "base": null, "refs": { "EvaluationDatasetLocation$s3Uri": "The S3 URI of the S3 bucket specified in the job.
", "EvaluationOutputDataConfig$s3Uri": "The Amazon S3 URI where the results of the evaluation job are saved.
", "InvocationLogSource$s3Uri": "The URI of an invocation log in a bucket.
", "ModelInvocationJobS3InputDataConfig$s3Uri": "The S3 location of the input data.
", "ModelInvocationJobS3OutputDataConfig$s3Uri": "The S3 location of the output data.
", "OutputDataConfig$s3Uri": "The S3 URI where the output data is stored.
", "S3DataSource$s3Uri": "The URI of the Amazon S3 data source.
", "TrainingDataConfig$s3Uri": "The S3 URI where the training data is stored.
", "Validator$s3Uri": "The S3 URI where the validation data is stored.
" } }, "SageMakerEndpoint": { "base": "Specifies the configuration for a Amazon SageMaker endpoint.
", "refs": { "EndpointConfig$sageMaker": "The configuration specific to Amazon SageMaker for the endpoint.
" } }, "SageMakerFlowDefinitionArn": { "base": null, "refs": { "HumanWorkflowConfig$flowDefinitionArn": "The Amazon Resource Number (ARN) for the flow definition
" } }, "SearchType": { "base": null, "refs": { "KnowledgeBaseVectorSearchConfiguration$overrideSearchType": "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.
An array of IDs for each security group in the VPC to use.
" } }, "ServiceQuotaExceededException": { "base": "The number of requests exceeds the service quota. Resubmit your request later.
", "refs": { } }, "ServiceUnavailableException": { "base": "Returned if the service cannot complete the request.
", "refs": { } }, "SortByProvisionedModels": { "base": null, "refs": { "ListProvisionedModelThroughputsRequest$sortBy": "The field by which to sort the returned list of Provisioned Throughputs.
" } }, "SortJobsBy": { "base": null, "refs": { "ListEvaluationJobsRequest$sortBy": "Specifies a creation time to sort the list of evaluation jobs by when they were created.
", "ListModelCopyJobsRequest$sortBy": "The field to sort by in the returned list of model copy jobs.
", "ListModelCustomizationJobsRequest$sortBy": "The field to sort by in the returned list of jobs.
", "ListModelImportJobsRequest$sortBy": "The field to sort by in the returned list of imported jobs.
", "ListModelInvocationJobsRequest$sortBy": "An attribute by which to sort the results.
" } }, "SortModelsBy": { "base": null, "refs": { "ListCustomModelDeploymentsRequest$sortBy": "The field to sort the results by. The only supported value is CreationTime.
The field to sort by in the returned list of models.
", "ListImportedModelsRequest$sortBy": "The field to sort by in the returned list of imported models.
" } }, "SortOrder": { "base": null, "refs": { "ListCustomModelDeploymentsRequest$sortOrder": "The sort order for the results. Valid values are Ascending and Descending. Default is Descending.
The sort order of the results.
", "ListEvaluationJobsRequest$sortOrder": "Specifies whether to sort the list of evaluation jobs by either ascending or descending order.
", "ListImportedModelsRequest$sortOrder": "Specifies whetehr to sort the results in ascending or descending order.
", "ListModelCopyJobsRequest$sortOrder": "Specifies whether to sort the results in ascending or descending order.
", "ListModelCustomizationJobsRequest$sortOrder": "The sort order of the results.
", "ListModelImportJobsRequest$sortOrder": "Specifies whether to sort the results in ascending or descending order.
", "ListModelInvocationJobsRequest$sortOrder": "Specifies whether to sort the results by ascending or descending order.
", "ListProvisionedModelThroughputsRequest$sortOrder": "The sort order of the results.
" } }, "StartAutomatedReasoningPolicyBuildWorkflowRequest": { "base": null, "refs": { } }, "StartAutomatedReasoningPolicyBuildWorkflowResponse": { "base": null, "refs": { } }, "StartAutomatedReasoningPolicyTestWorkflowRequest": { "base": null, "refs": { } }, "StartAutomatedReasoningPolicyTestWorkflowResponse": { "base": null, "refs": { } }, "Status": { "base": null, "refs": { "MarketplaceModelEndpoint$status": "The overall status of the endpoint in Amazon Bedrock Marketplace (e.g., ACTIVE, INACTIVE).
", "MarketplaceModelEndpointSummary$status": "The overall status of the endpoint in Amazon Bedrock Marketplace.
" } }, "StatusDetails": { "base": "For a Distillation job, the status details for sub-tasks of the job. Possible statuses for each sub-task include the following:
NotStarted
InProgress
Completed
Stopping
Stopped
Failed
For a Distillation job, the details about the statuses of the sub-tasks of the customization job.
", "ModelCustomizationJobSummary$statusDetails": "Details about the status of the data processing sub-task of the job.
" } }, "StopEvaluationJobRequest": { "base": null, "refs": { } }, "StopEvaluationJobResponse": { "base": null, "refs": { } }, "StopModelCustomizationJobRequest": { "base": null, "refs": { } }, "StopModelCustomizationJobResponse": { "base": null, "refs": { } }, "StopModelInvocationJobRequest": { "base": null, "refs": { } }, "StopModelInvocationJobResponse": { "base": null, "refs": { } }, "String": { "base": null, "refs": { "AgreementAvailability$errorMessage": "Error message.
", "AutomatedReasoningPolicyBuildStepMessage$message": "The content of the message, describing what occurred during the build step.
", "BatchDeleteEvaluationJobError$code": "A HTTP status code of the evaluation job being deleted.
", "BatchDeleteEvaluationJobError$message": "A status message about the evaluation job deletion.
", "DimensionalPriceRate$dimension": "Dimension for the price rate.
", "DimensionalPriceRate$price": "Single-dimensional rate information.
", "DimensionalPriceRate$description": "Description of the price rate.
", "DimensionalPriceRate$unit": "Unit associated with the price.
", "GetImportedModelResponse$modelArchitecture": "The architecture of the imported model.
", "LegalTerm$url": "URL to the legal term document.
", "MarketplaceModelEndpoint$statusMessage": "Additional information about the overall status, if available.
", "MarketplaceModelEndpoint$endpointStatus": "The current status of the endpoint (e.g., Creating, InService, Updating, Failed).
", "MarketplaceModelEndpoint$endpointStatusMessage": "Additional information about the endpoint status, if available.
", "MarketplaceModelEndpointSummary$statusMessage": "Additional information about the overall status, if available.
", "ModelCustomizationHyperParameters$key": null, "ModelCustomizationHyperParameters$value": null, "SupportTerm$refundPolicyDescription": "Describes the refund policy.
", "ValidityTerm$agreementDuration": "Describes the agreement duration.
" } }, "SubnetId": { "base": null, "refs": { "SubnetIds$member": null } }, "SubnetIds": { "base": null, "refs": { "VpcConfig$subnetIds": "An array of IDs for each subnet in the VPC to use.
" } }, "SupportTerm": { "base": "Describes a support term.
", "refs": { "TermDetails$supportTerm": "Describes the support terms.
" } }, "Tag": { "base": "Definition of the key/value pair for a tag.
", "refs": { "TagList$member": null } }, "TagKey": { "base": null, "refs": { "Tag$key": "Key for the tag.
", "TagKeyList$member": null } }, "TagKeyList": { "base": null, "refs": { "UntagResourceRequest$tagKeys": "Tag keys of the tags to remove from the resource.
" } }, "TagList": { "base": null, "refs": { "CreateAutomatedReasoningPolicyRequest$tags": "A list of tags to associate with the Automated Reasoning policy. Tags help you organize and manage your policies.
", "CreateAutomatedReasoningPolicyVersionRequest$tags": "A list of tags to associate with the policy version.
", "CreateCustomModelDeploymentRequest$tags": "Tags to assign to the custom model deployment. You can use tags to organize and track your Amazon Web Services resources for cost allocation and management purposes.
", "CreateCustomModelRequest$modelTags": "A list of key-value pairs to associate with the custom model resource. You can use these tags to organize and identify your resources.
For more information, see Tagging resources in the Amazon Bedrock User Guide.
", "CreateEvaluationJobRequest$jobTags": "Tags to attach to the model evaluation job.
", "CreateGuardrailRequest$tags": "The tags that you want to attach to the guardrail.
", "CreateInferenceProfileRequest$tags": "An array of objects, each of which contains a tag and its value. For more information, see Tagging resources in the Amazon Bedrock User Guide.
", "CreateMarketplaceModelEndpointRequest$tags": "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.
", "CreateModelCopyJobRequest$targetModelTags": "Tags to associate with the target model. For more information, see Tag resources in the Amazon Bedrock User Guide.
", "CreateModelCustomizationJobRequest$jobTags": "Tags to attach to the job.
", "CreateModelCustomizationJobRequest$customModelTags": "Tags to attach to the resulting custom model.
", "CreateModelImportJobRequest$jobTags": "Tags to attach to this import job.
", "CreateModelImportJobRequest$importedModelTags": "Tags to attach to the imported model.
", "CreateModelInvocationJobRequest$tags": "Any tags to associate with the batch inference job. For more information, see Tagging Amazon Bedrock resources.
", "CreatePromptRouterRequest$tags": "An array of key-value pairs to apply to this resource as tags. You can use tags to categorize and manage your Amazon Web Services resources.
", "CreateProvisionedModelThroughputRequest$tags": "Tags to associate with this Provisioned Throughput.
", "GetModelCopyJobResponse$targetModelTags": "The tags associated with the copied model.
", "ListTagsForResourceResponse$tags": "An array of the tags associated with this resource.
", "ModelCopyJobSummary$targetModelTags": "Tags associated with the copied model.
", "TagResourceRequest$tags": "Tags to associate with the resource.
" } }, "TagResourceRequest": { "base": null, "refs": { } }, "TagResourceResponse": { "base": null, "refs": { } }, "TagValue": { "base": null, "refs": { "Tag$value": "Value for the tag.
" } }, "TaggableResourcesArn": { "base": null, "refs": { "ListTagsForResourceRequest$resourceARN": "The Amazon Resource Name (ARN) of the resource.
", "TagResourceRequest$resourceARN": "The Amazon Resource Name (ARN) of the resource to tag.
", "TooManyTagsException$resourceName": "The name of the resource with too many tags.
", "UntagResourceRequest$resourceARN": "The Amazon Resource Name (ARN) of the resource to untag.
" } }, "TeacherModelConfig": { "base": "Details about a teacher model used for model customization.
", "refs": { "DistillationConfig$teacherModelConfig": "The teacher model configuration.
" } }, "TeacherModelIdentifier": { "base": null, "refs": { "TeacherModelConfig$teacherModelIdentifier": "The identifier of the teacher model.
" } }, "Temperature": { "base": null, "refs": { "TextInferenceConfig$temperature": "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.
" } }, "TermDetails": { "base": "Describes the usage terms of an offer.
", "refs": { "Offer$termDetails": "Details about the terms of the offer.
" } }, "TextInferenceConfig": { "base": "The configuration details for text generation using a language model via the RetrieveAndGenerate function.
Contains configuration details for text generation using a language model via the RetrieveAndGenerate function.
The template for the prompt that's sent to the model for response generation. You can include prompt placeholders, which become replaced before the prompt is sent to the model to provide instructions and context to the model. In addition, you can include XML tags to delineate meaningful sections of the prompt template.
For more information, see Knowledge base prompt template and Use XML tags with Anthropic Claude models.
" } }, "ThrottlingException": { "base": "The number of requests exceeds the limit. Resubmit your request later.
", "refs": { } }, "Timestamp": { "base": null, "refs": { "AutomatedReasoningPolicyBuildWorkflowSummary$createdAt": "The timestamp when the build workflow was created.
", "AutomatedReasoningPolicyBuildWorkflowSummary$updatedAt": "The timestamp when the build workflow was last updated.
", "AutomatedReasoningPolicySummary$createdAt": "The timestamp when the policy was created.
", "AutomatedReasoningPolicySummary$updatedAt": "The timestamp when the policy was last updated.
", "AutomatedReasoningPolicyTestCase$createdAt": "The timestamp when the test was created.
", "AutomatedReasoningPolicyTestCase$updatedAt": "The timestamp when the test was last updated.
", "AutomatedReasoningPolicyTestResult$updatedAt": "The timestamp when the test results were last updated.
", "CreateAutomatedReasoningPolicyResponse$createdAt": "The timestamp when the policy was created.
", "CreateAutomatedReasoningPolicyResponse$updatedAt": "The timestamp when the policy was last updated.
", "CreateAutomatedReasoningPolicyVersionResponse$createdAt": "The timestamp when the policy version was created.
", "CreateGuardrailResponse$createdAt": "The time at which the guardrail was created.
", "CustomModelDeploymentSummary$createdAt": "The date and time when the custom model deployment was created.
", "CustomModelDeploymentSummary$lastUpdatedAt": "The date and time when the custom model deployment was last modified.
", "CustomModelSummary$creationTime": "Creation time of the model.
", "DataProcessingDetails$creationTime": "The start time of the data processing sub-task of the job.
", "DataProcessingDetails$lastModifiedTime": "The latest update to the data processing sub-task of the job.
", "DeleteAutomatedReasoningPolicyBuildWorkflowRequest$lastUpdatedAt": "The timestamp when the build workflow was last updated. This is used for optimistic concurrency control to prevent accidental deletion of workflows that have been modified.
", "DeleteAutomatedReasoningPolicyTestCaseRequest$lastUpdatedAt": "The timestamp when the test was last updated. This is used as a concurrency token to prevent conflicting modifications.
", "EvaluationSummary$creationTime": "The time the evaluation job was created.
", "GetAutomatedReasoningPolicyAnnotationsResponse$updatedAt": "The timestamp when the annotations were last updated.
", "GetAutomatedReasoningPolicyBuildWorkflowResponse$createdAt": "The timestamp when the build workflow was created.
", "GetAutomatedReasoningPolicyBuildWorkflowResponse$updatedAt": "The timestamp when the build workflow was last updated.
", "GetAutomatedReasoningPolicyResponse$createdAt": "The timestamp when the policy was created.
", "GetAutomatedReasoningPolicyResponse$updatedAt": "The timestamp when the policy was last updated.
", "GetCustomModelDeploymentResponse$createdAt": "The date and time when the custom model deployment was created.
", "GetCustomModelDeploymentResponse$lastUpdatedAt": "The date and time when the custom model deployment was last updated.
", "GetCustomModelResponse$creationTime": "Creation time of the model.
", "GetEvaluationJobResponse$creationTime": "The time the evaluation job was created.
", "GetEvaluationJobResponse$lastModifiedTime": "The time the evaluation job was last modified.
", "GetGuardrailResponse$createdAt": "The date and time at which the guardrail was created.
", "GetGuardrailResponse$updatedAt": "The date and time at which the guardrail was updated.
", "GetImportedModelResponse$creationTime": "Creation time of the imported model.
", "GetInferenceProfileResponse$createdAt": "The time at which the inference profile was created.
", "GetInferenceProfileResponse$updatedAt": "The time at which the inference profile was last updated.
", "GetModelCopyJobResponse$creationTime": "The time at which the model copy job was created.
", "GetModelCustomizationJobResponse$creationTime": "Time that the resource was created.
", "GetModelCustomizationJobResponse$lastModifiedTime": "Time that the resource was last modified.
", "GetModelCustomizationJobResponse$endTime": "Time that the resource transitioned to terminal state.
", "GetModelImportJobResponse$creationTime": "The time the resource was created.
", "GetModelImportJobResponse$lastModifiedTime": "Time the resource was last modified.
", "GetModelImportJobResponse$endTime": "Time that the resource transitioned to terminal state.
", "GetModelInvocationJobResponse$submitTime": "The time at which the batch inference job was submitted.
", "GetModelInvocationJobResponse$lastModifiedTime": "The time at which the batch inference job was last modified.
", "GetModelInvocationJobResponse$endTime": "The time at which the batch inference job ended.
", "GetModelInvocationJobResponse$jobExpirationTime": "The time at which the batch inference job times or timed out.
", "GetPromptRouterResponse$createdAt": "When the router was created.
", "GetPromptRouterResponse$updatedAt": "When the router was updated.
", "GetProvisionedModelThroughputResponse$creationTime": "The timestamp of the creation time for this Provisioned Throughput.
", "GetProvisionedModelThroughputResponse$lastModifiedTime": "The timestamp of the last time that this Provisioned Throughput was modified.
", "GetProvisionedModelThroughputResponse$commitmentExpirationTime": "The timestamp for when the commitment term for the Provisioned Throughput expires.
", "GuardrailSummary$createdAt": "The date and time at which the guardrail was created.
", "GuardrailSummary$updatedAt": "The date and time at which the guardrail was last updated.
", "ImportedModelSummary$creationTime": "Creation time of the imported model.
", "InferenceProfileSummary$createdAt": "The time at which the inference profile was created.
", "InferenceProfileSummary$updatedAt": "The time at which the inference profile was last updated.
", "ListCustomModelDeploymentsRequest$createdBefore": "Filters deployments created before the specified date and time.
", "ListCustomModelDeploymentsRequest$createdAfter": "Filters deployments created after the specified date and time.
", "ListCustomModelsRequest$creationTimeBefore": "Return custom models created before the specified time.
", "ListCustomModelsRequest$creationTimeAfter": "Return custom models created after the specified time.
", "ListEvaluationJobsRequest$creationTimeAfter": "A filter to only list evaluation jobs created after a specified time.
", "ListEvaluationJobsRequest$creationTimeBefore": "A filter to only list evaluation jobs created before a specified time.
", "ListImportedModelsRequest$creationTimeBefore": "Return imported models that created before the specified time.
", "ListImportedModelsRequest$creationTimeAfter": "Return imported models that were created after the specified time.
", "ListModelCopyJobsRequest$creationTimeAfter": "Filters for model copy jobs created after the specified time.
", "ListModelCopyJobsRequest$creationTimeBefore": "Filters for model copy jobs created before the specified time.
", "ListModelCustomizationJobsRequest$creationTimeAfter": "Return customization jobs created after the specified time.
", "ListModelCustomizationJobsRequest$creationTimeBefore": "Return customization jobs created before the specified time.
", "ListModelImportJobsRequest$creationTimeAfter": "Return import jobs that were created after the specified time.
", "ListModelImportJobsRequest$creationTimeBefore": "Return import jobs that were created before the specified time.
", "ListModelInvocationJobsRequest$submitTimeAfter": "Specify a time to filter for batch inference jobs that were submitted after the time you specify.
", "ListModelInvocationJobsRequest$submitTimeBefore": "Specify a time to filter for batch inference jobs that were submitted before the time you specify.
", "ListProvisionedModelThroughputsRequest$creationTimeAfter": "A filter that returns Provisioned Throughputs created after the specified time.
", "ListProvisionedModelThroughputsRequest$creationTimeBefore": "A filter that returns Provisioned Throughputs created before the specified time.
", "MarketplaceModelEndpoint$createdAt": "The timestamp when the endpoint was registered.
", "MarketplaceModelEndpoint$updatedAt": "The timestamp when the endpoint was last updated.
", "MarketplaceModelEndpointSummary$createdAt": "The timestamp when the endpoint was created.
", "MarketplaceModelEndpointSummary$updatedAt": "The timestamp when the endpoint was last updated.
", "ModelCopyJobSummary$creationTime": "The time that the model copy job was created.
", "ModelCustomizationJobSummary$lastModifiedTime": "Time that the customization job was last modified.
", "ModelCustomizationJobSummary$creationTime": "Creation time of the custom model.
", "ModelCustomizationJobSummary$endTime": "Time that the customization job ended.
", "ModelImportJobSummary$lastModifiedTime": "The time when the import job was last modified.
", "ModelImportJobSummary$creationTime": "The time import job was created.
", "ModelImportJobSummary$endTime": "The time when import job ended.
", "ModelInvocationJobSummary$submitTime": "The time at which the batch inference job was submitted.
", "ModelInvocationJobSummary$lastModifiedTime": "The time at which the batch inference job was last modified.
", "ModelInvocationJobSummary$endTime": "The time at which the batch inference job ended.
", "ModelInvocationJobSummary$jobExpirationTime": "The time at which the batch inference job times or timed out.
", "PromptRouterSummary$createdAt": "When the router was created.
", "PromptRouterSummary$updatedAt": "When the router was updated.
", "ProvisionedModelSummary$commitmentExpirationTime": "The timestamp for when the commitment term of the Provisioned Throughput expires.
", "ProvisionedModelSummary$creationTime": "The time that the Provisioned Throughput was created.
", "ProvisionedModelSummary$lastModifiedTime": "The time that the Provisioned Throughput was last modified.
", "TrainingDetails$creationTime": "The start time of the training sub-task of the job.
", "TrainingDetails$lastModifiedTime": "The latest update to the training sub-task of the job.
", "UpdateAutomatedReasoningPolicyAnnotationsResponse$updatedAt": "The timestamp when the annotations were updated.
", "UpdateAutomatedReasoningPolicyResponse$updatedAt": "The timestamp when the policy was last updated.
", "UpdateAutomatedReasoningPolicyTestCaseRequest$lastUpdatedAt": "The timestamp when the test was last updated. This is used as a concurrency token to prevent conflicting modifications.
", "UpdateGuardrailResponse$updatedAt": "The date and time at which the guardrail was updated.
", "ValidationDetails$creationTime": "The start time of the validation sub-task of the job.
", "ValidationDetails$lastModifiedTime": "The latest update to the validation sub-task of the job.
" } }, "TooManyTagsException": { "base": "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.
", "refs": { } }, "TopP": { "base": null, "refs": { "TextInferenceConfig$topP": "A probability distribution threshold which controls what the model considers for the set of possible next tokens. The model will only consider the top p% of the probability distribution when generating the next token.
" } }, "TrainingDataConfig": { "base": "S3 Location of the training data.
", "refs": { "CreateModelCustomizationJobRequest$trainingDataConfig": "Information about the training dataset.
", "GetCustomModelResponse$trainingDataConfig": "Contains information about the training dataset.
", "GetModelCustomizationJobResponse$trainingDataConfig": "Contains information about the training dataset.
" } }, "TrainingDetails": { "base": "For a Distillation job, the status details for the training sub-task of the job.
", "refs": { "StatusDetails$trainingDetails": "The status details for the training sub-task of the job.
" } }, "TrainingMetrics": { "base": "Metrics associated with the custom job.
", "refs": { "GetCustomModelResponse$trainingMetrics": "Contains training metrics from the job creation.
", "GetModelCustomizationJobResponse$trainingMetrics": "Contains training metrics from the job creation.
" } }, "UntagResourceRequest": { "base": null, "refs": { } }, "UntagResourceResponse": { "base": null, "refs": { } }, "UpdateAutomatedReasoningPolicyAnnotationsRequest": { "base": null, "refs": { } }, "UpdateAutomatedReasoningPolicyAnnotationsResponse": { "base": null, "refs": { } }, "UpdateAutomatedReasoningPolicyRequest": { "base": null, "refs": { } }, "UpdateAutomatedReasoningPolicyResponse": { "base": null, "refs": { } }, "UpdateAutomatedReasoningPolicyTestCaseRequest": { "base": null, "refs": { } }, "UpdateAutomatedReasoningPolicyTestCaseResponse": { "base": null, "refs": { } }, "UpdateGuardrailRequest": { "base": null, "refs": { } }, "UpdateGuardrailResponse": { "base": null, "refs": { } }, "UpdateMarketplaceModelEndpointRequest": { "base": null, "refs": { } }, "UpdateMarketplaceModelEndpointResponse": { "base": null, "refs": { } }, "UpdateProvisionedModelThroughputRequest": { "base": null, "refs": { } }, "UpdateProvisionedModelThroughputResponse": { "base": null, "refs": { } }, "UsePromptResponse": { "base": null, "refs": { "InvocationLogsConfig$usePromptResponse": "Whether to use the model's response for training, or just the prompt. The default value is False.
Array of up to 10 validators.
", "refs": { "CreateModelCustomizationJobRequest$validationDataConfig": "Information about the validation dataset.
", "GetCustomModelResponse$validationDataConfig": "Contains information about the validation dataset.
", "GetModelCustomizationJobResponse$validationDataConfig": "Contains information about the validation dataset.
" } }, "ValidationDetails": { "base": "For a Distillation job, the status details for the validation sub-task of the job.
", "refs": { "StatusDetails$validationDetails": "The status details for the validation sub-task of the job.
" } }, "ValidationException": { "base": "Input validation failed. Check your request parameters and retry the request.
", "refs": { } }, "ValidationMetrics": { "base": null, "refs": { "GetCustomModelResponse$validationMetrics": "The validation metrics from the job creation.
", "GetModelCustomizationJobResponse$validationMetrics": "The loss metric for each validator that you provided in the createjob request.
" } }, "Validator": { "base": "Information about a validator.
", "refs": { "Validators$member": null } }, "ValidatorMetric": { "base": "The metric for the validator.
", "refs": { "ValidationMetrics$member": null } }, "Validators": { "base": null, "refs": { "ValidationDataConfig$validators": "Information about the validators.
" } }, "ValidityTerm": { "base": "Describes the validity terms.
", "refs": { "TermDetails$validityTerm": "Describes the validity terms.
" } }, "VectorSearchBedrockRerankingConfiguration": { "base": "Configuration for using Amazon Bedrock foundation models to rerank Knowledge Base vector search results. This enables more sophisticated relevance ranking using large language models.
", "refs": { "VectorSearchRerankingConfiguration$bedrockRerankingConfiguration": "Configuration for using Amazon Bedrock foundation models to rerank search results. This is required when the reranking type is set to BEDROCK.
" } }, "VectorSearchBedrockRerankingConfigurationNumberOfRerankedResultsInteger": { "base": null, "refs": { "VectorSearchBedrockRerankingConfiguration$numberOfRerankedResults": "The maximum number of results to rerank. This limits how many of the initial vector search results will be processed by the reranking model. A smaller number improves performance but may exclude potentially relevant results.
" } }, "VectorSearchBedrockRerankingModelConfiguration": { "base": "Configuration for the Amazon Bedrock foundation model used for reranking vector search results. This specifies which model to use and any additional parameters required by the model.
", "refs": { "VectorSearchBedrockRerankingConfiguration$modelConfiguration": "Configuration for the Amazon Bedrock foundation model used for reranking. This includes the model ARN and any additional request fields required by the model.
" } }, "VectorSearchRerankingConfiguration": { "base": "Configuration for reranking vector search results to improve relevance. Reranking applies additional relevance models to reorder the initial vector search results based on more sophisticated criteria.
", "refs": { "KnowledgeBaseVectorSearchConfiguration$rerankingConfiguration": "Configuration for reranking search results in Knowledge Base vector searches. Reranking improves search relevance by reordering initial vector search results using more sophisticated relevance models.
" } }, "VectorSearchRerankingConfigurationType": { "base": null, "refs": { "VectorSearchRerankingConfiguration$type": "The type of reranking to apply to vector search results. Currently, the only supported value is BEDROCK, which uses Amazon Bedrock foundation models for reranking.
" } }, "VpcConfig": { "base": "The configuration of a virtual private cloud (VPC). For more information, see Protect your data using Amazon Virtual Private Cloud and Amazon Web Services PrivateLink.
", "refs": { "CreateModelCustomizationJobRequest$vpcConfig": "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.
", "CreateModelImportJobRequest$vpcConfig": "VPC configuration parameters for the private Virtual Private Cloud (VPC) that contains the resources you are using for the import job.
", "CreateModelInvocationJobRequest$vpcConfig": "The configuration of the Virtual Private Cloud (VPC) for the data in the batch inference job. For more information, see Protect batch inference jobs using a VPC.
", "GetModelCustomizationJobResponse$vpcConfig": "VPC configuration for the custom model job.
", "GetModelImportJobResponse$vpcConfig": "The Virtual Private Cloud (VPC) configuration of the import model job.
", "GetModelInvocationJobResponse$vpcConfig": "The configuration of the Virtual Private Cloud (VPC) for the data in the batch inference job. For more information, see Protect batch inference jobs using a VPC.
", "ModelInvocationJobSummary$vpcConfig": "The configuration of the Virtual Private Cloud (VPC) for the data in the batch inference job. For more information, see Protect batch inference jobs using a VPC.
", "SageMakerEndpoint$vpc": "The VPC configuration for the endpoint.
" } }, "kBS3Uri": { "base": null, "refs": { "S3ObjectDoc$uri": "The S3 URI location for the wrapper object of the document.
" } } } }