Class: Aws::Bedrock::Client
- Inherits:
-
Seahorse::Client::Base
- Object
- Seahorse::Client::Base
- Aws::Bedrock::Client
- Includes:
- ClientStubs
- Defined in:
- gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb
Overview
An API client for Bedrock. To construct a client, you need to configure a :region and :credentials.
client = Aws::Bedrock::Client.new(
region: region_name,
credentials: credentials,
# ...
)
For details on configuring region and credentials see the developer guide.
See #initialize for a full list of supported configuration options.
Instance Attribute Summary
Attributes inherited from Seahorse::Client::Base
API Operations collapse
-
#archive_project(params = {}) ⇒ Types::ArchiveProjectResponse
Archives a project.
-
#batch_delete_advanced_prompt_optimization_job(params = {}) ⇒ Types::BatchDeleteAdvancedPromptOptimizationJobResponse
Deletes one or more advanced prompt optimization jobs.
-
#batch_delete_evaluation_job(params = {}) ⇒ Types::BatchDeleteEvaluationJobResponse
Deletes a batch of evaluation jobs.
-
#cancel_automated_reasoning_policy_build_workflow(params = {}) ⇒ Struct
Cancels a running Automated Reasoning policy build workflow.
-
#create_advanced_prompt_optimization_job(params = {}) ⇒ Types::CreateAdvancedPromptOptimizationJobResponse
Creates an advanced prompt optimization job.
-
#create_automated_reasoning_policy(params = {}) ⇒ Types::CreateAutomatedReasoningPolicyResponse
Creates an Automated Reasoning policy for Amazon Bedrock Guardrails.
-
#create_automated_reasoning_policy_test_case(params = {}) ⇒ Types::CreateAutomatedReasoningPolicyTestCaseResponse
Creates a test for an Automated Reasoning policy.
-
#create_automated_reasoning_policy_version(params = {}) ⇒ Types::CreateAutomatedReasoningPolicyVersionResponse
Creates a new version of an existing Automated Reasoning policy.
-
#create_custom_model(params = {}) ⇒ Types::CreateCustomModelResponse
Creates a new custom model in Amazon Bedrock.
-
#create_custom_model_deployment(params = {}) ⇒ Types::CreateCustomModelDeploymentResponse
Deploys a custom model for on-demand inference in Amazon Bedrock.
-
#create_evaluation_job(params = {}) ⇒ Types::CreateEvaluationJobResponse
Creates an evaluation job.
-
#create_foundation_model_agreement(params = {}) ⇒ Types::CreateFoundationModelAgreementResponse
Request a model access agreement for the specified model.
-
#create_guardrail(params = {}) ⇒ Types::CreateGuardrailResponse
Creates a guardrail to block topics and to implement safeguards for your generative AI applications.
-
#create_guardrail_version(params = {}) ⇒ Types::CreateGuardrailVersionResponse
Creates a version of the guardrail.
-
#create_inference_profile(params = {}) ⇒ Types::CreateInferenceProfileResponse
Creates an application inference profile to track metrics and costs when invoking a model.
-
#create_marketplace_model_endpoint(params = {}) ⇒ Types::CreateMarketplaceModelEndpointResponse
Creates an endpoint for a model from Amazon Bedrock Marketplace.
-
#create_model_copy_job(params = {}) ⇒ Types::CreateModelCopyJobResponse
Copies a model to another region so that it can be used there.
-
#create_model_customization_job(params = {}) ⇒ Types::CreateModelCustomizationJobResponse
Creates a fine-tuning job to customize a base model.
-
#create_model_import_job(params = {}) ⇒ Types::CreateModelImportJobResponse
Creates a model import job to import model that you have customized in other environments, such as Amazon SageMaker.
-
#create_model_invocation_job(params = {}) ⇒ Types::CreateModelInvocationJobResponse
Creates a batch inference job to invoke a model on multiple prompts.
-
#create_project(params = {}) ⇒ Types::CreateProjectResponse
Creates a project: a workload boundary within the account that inference requests can be associated with.
-
#create_prompt_router(params = {}) ⇒ Types::CreatePromptRouterResponse
Creates a prompt router that manages the routing of requests between multiple foundation models based on the routing criteria.
-
#create_provisioned_model_throughput(params = {}) ⇒ Types::CreateProvisionedModelThroughputResponse
Creates dedicated throughput for a base or custom model with the model units and for the duration that you specify.
-
#delete_account_data_retention_storage(params = {}) ⇒ Struct
Deletes your account's retention storage configuration for a model provider.
-
#delete_automated_reasoning_policy(params = {}) ⇒ Struct
Deletes an Automated Reasoning policy or policy version.
-
#delete_automated_reasoning_policy_build_workflow(params = {}) ⇒ Struct
Deletes an Automated Reasoning policy build workflow and its associated artifacts.
-
#delete_automated_reasoning_policy_test_case(params = {}) ⇒ Struct
Deletes an Automated Reasoning policy test.
-
#delete_custom_model(params = {}) ⇒ Struct
Deletes a custom model that you created earlier.
-
#delete_custom_model_deployment(params = {}) ⇒ Struct
Deletes a custom model deployment.
-
#delete_enforced_guardrail_configuration(params = {}) ⇒ Struct
Deletes the account-level enforced guardrail configuration.
-
#delete_foundation_model_agreement(params = {}) ⇒ Struct
Delete the model access agreement for the specified model.
-
#delete_guardrail(params = {}) ⇒ Struct
Deletes a guardrail.
-
#delete_imported_model(params = {}) ⇒ Struct
Deletes a custom model that you imported earlier.
-
#delete_inference_profile(params = {}) ⇒ Struct
Deletes an application inference profile.
-
#delete_marketplace_model_endpoint(params = {}) ⇒ Struct
Deletes an endpoint for a model from Amazon Bedrock Marketplace.
-
#delete_model_invocation_logging_configuration(params = {}) ⇒ Struct
Delete the invocation logging.
-
#delete_organization_data_retention_storage(params = {}) ⇒ Struct
Deletes the organization's retention storage configuration for a model provider.
-
#delete_project_data_retention_storage(params = {}) ⇒ Struct
Deletes a project's retention storage configuration for a model provider.
-
#delete_prompt_router(params = {}) ⇒ Struct
Deletes a specified prompt router.
-
#delete_provisioned_model_throughput(params = {}) ⇒ Struct
Deletes a Provisioned Throughput.
-
#delete_resource_policy(params = {}) ⇒ Struct
Deletes a previously created Bedrock resource policy.
-
#deregister_marketplace_model_endpoint(params = {}) ⇒ Struct
Deregisters an endpoint for a model from Amazon Bedrock Marketplace.
-
#export_automated_reasoning_policy_version(params = {}) ⇒ Types::ExportAutomatedReasoningPolicyVersionResponse
Exports the policy definition for an Automated Reasoning policy version.
-
#get_account_data_retention(params = {}) ⇒ Types::GetAccountDataRetentionResponse
Returns the account-wide data retention mode for Amazon Bedrock.
-
#get_account_data_retention_storage(params = {}) ⇒ Types::GetAccountDataRetentionStorageResponse
Returns your account's stored retention storage configuration for a model provider.
-
#get_advanced_prompt_optimization_job(params = {}) ⇒ Types::GetAdvancedPromptOptimizationJobResponse
Gets information about an advanced prompt optimization job.
-
#get_automated_reasoning_policy(params = {}) ⇒ Types::GetAutomatedReasoningPolicyResponse
Retrieves details about an Automated Reasoning policy or policy version.
-
#get_automated_reasoning_policy_annotations(params = {}) ⇒ Types::GetAutomatedReasoningPolicyAnnotationsResponse
Retrieves the current annotations for an Automated Reasoning policy build workflow.
-
#get_automated_reasoning_policy_build_workflow(params = {}) ⇒ Types::GetAutomatedReasoningPolicyBuildWorkflowResponse
Retrieves detailed information about an Automated Reasoning policy build workflow, including its status, configuration, and metadata.
-
#get_automated_reasoning_policy_build_workflow_result_assets(params = {}) ⇒ Types::GetAutomatedReasoningPolicyBuildWorkflowResultAssetsResponse
Retrieves the resulting assets from a completed Automated Reasoning policy build workflow, including build logs, quality reports, and generated policy artifacts.
-
#get_automated_reasoning_policy_next_scenario(params = {}) ⇒ Types::GetAutomatedReasoningPolicyNextScenarioResponse
Retrieves the next test scenario for validating an Automated Reasoning policy.
-
#get_automated_reasoning_policy_test_case(params = {}) ⇒ Types::GetAutomatedReasoningPolicyTestCaseResponse
Retrieves details about a specific Automated Reasoning policy test.
-
#get_automated_reasoning_policy_test_result(params = {}) ⇒ Types::GetAutomatedReasoningPolicyTestResultResponse
Retrieves the test result for a specific Automated Reasoning policy test.
-
#get_custom_model(params = {}) ⇒ Types::GetCustomModelResponse
Get the properties associated with a Amazon Bedrock custom model that you have created.
-
#get_custom_model_deployment(params = {}) ⇒ Types::GetCustomModelDeploymentResponse
Retrieves information about a custom model deployment, including its status, configuration, and metadata.
-
#get_evaluation_job(params = {}) ⇒ Types::GetEvaluationJobResponse
Gets information about an evaluation job, such as the status of the job.
-
#get_foundation_model(params = {}) ⇒ Types::GetFoundationModelResponse
Get details about a Amazon Bedrock foundation model.
-
#get_foundation_model_availability(params = {}) ⇒ Types::GetFoundationModelAvailabilityResponse
Get information about the Foundation model availability.
-
#get_guardrail(params = {}) ⇒ Types::GetGuardrailResponse
Gets details about a guardrail.
-
#get_imported_model(params = {}) ⇒ Types::GetImportedModelResponse
Gets properties associated with a customized model you imported.
-
#get_inference_profile(params = {}) ⇒ Types::GetInferenceProfileResponse
Gets information about an inference profile.
-
#get_marketplace_model_endpoint(params = {}) ⇒ Types::GetMarketplaceModelEndpointResponse
Retrieves details about a specific endpoint for a model from Amazon Bedrock Marketplace.
-
#get_model_copy_job(params = {}) ⇒ Types::GetModelCopyJobResponse
Retrieves information about a model copy job.
-
#get_model_customization_job(params = {}) ⇒ Types::GetModelCustomizationJobResponse
Retrieves the properties associated with a model-customization job, including the status of the job.
-
#get_model_import_job(params = {}) ⇒ Types::GetModelImportJobResponse
Retrieves the properties associated with import model job, including the status of the job.
-
#get_model_invocation_job(params = {}) ⇒ Types::GetModelInvocationJobResponse
Gets details about a batch inference job.
-
#get_model_invocation_logging_configuration(params = {}) ⇒ Types::GetModelInvocationLoggingConfigurationResponse
Get the current configuration values for model invocation logging.
-
#get_organization_data_retention_storage(params = {}) ⇒ Types::GetOrganizationDataRetentionStorageResponse
Returns the organization's retention storage configuration for a model provider.
-
#get_project(params = {}) ⇒ Types::GetProjectResponse
Retrieves a project.
-
#get_project_data_retention_storage(params = {}) ⇒ Types::GetProjectDataRetentionStorageResponse
Returns a project's retention storage configuration for a model provider.
-
#get_prompt_router(params = {}) ⇒ Types::GetPromptRouterResponse
Retrieves details about a prompt router.
-
#get_provisioned_model_throughput(params = {}) ⇒ Types::GetProvisionedModelThroughputResponse
Returns details for a Provisioned Throughput.
-
#get_resource_policy(params = {}) ⇒ Types::GetResourcePolicyResponse
Gets the resource policy document for a Bedrock resource.
-
#get_trusted_access_program(params = {}) ⇒ Types::GetTrustedAccessProgramResponse
Gets trusted access program details and resolves participation for your account and its current organization.
-
#get_trusted_access_program_account_enrollment(params = {}) ⇒ Types::GetTrustedAccessProgramAccountEnrollmentResponse
Gets the calling account's stored enrollment setting for a trusted access program.
-
#get_trusted_access_program_organization_enrollment(params = {}) ⇒ Types::GetTrustedAccessProgramOrganizationEnrollmentResponse
Gets the current organization's stored enrollment setting for a trusted access program.
-
#get_trusted_access_program_project_enrollment(params = {}) ⇒ Types::GetTrustedAccessProgramProjectEnrollmentResponse
Gets a named project's stored enrollment setting for a trusted access program.
-
#get_use_case_for_model_access(params = {}) ⇒ Types::GetUseCaseForModelAccessResponse
Get usecase for model access.
-
#list_advanced_prompt_optimization_jobs(params = {}) ⇒ Types::ListAdvancedPromptOptimizationJobsResponse
Lists the advanced prompt optimization jobs in your account.
-
#list_automated_reasoning_policies(params = {}) ⇒ Types::ListAutomatedReasoningPoliciesResponse
Lists all Automated Reasoning policies in your account, with optional filtering by policy ARN.
-
#list_automated_reasoning_policy_build_workflows(params = {}) ⇒ Types::ListAutomatedReasoningPolicyBuildWorkflowsResponse
Lists all build workflows for an Automated Reasoning policy, showing the history of policy creation and modification attempts.
-
#list_automated_reasoning_policy_test_cases(params = {}) ⇒ Types::ListAutomatedReasoningPolicyTestCasesResponse
Lists tests for an Automated Reasoning policy.
-
#list_automated_reasoning_policy_test_results(params = {}) ⇒ Types::ListAutomatedReasoningPolicyTestResultsResponse
Lists test results for an Automated Reasoning policy, showing how the policy performed against various test scenarios and validation checks.
-
#list_custom_model_deployments(params = {}) ⇒ Types::ListCustomModelDeploymentsResponse
Lists custom model deployments in your account.
-
#list_custom_models(params = {}) ⇒ Types::ListCustomModelsResponse
Returns a list of the custom models that you have created with the
CreateModelCustomizationJoboperation. -
#list_enforced_guardrails_configuration(params = {}) ⇒ Types::ListEnforcedGuardrailsConfigurationResponse
Lists the account-level enforced guardrail configurations.
-
#list_evaluation_jobs(params = {}) ⇒ Types::ListEvaluationJobsResponse
Lists all existing evaluation jobs.
-
#list_foundation_model_agreement_offers(params = {}) ⇒ Types::ListFoundationModelAgreementOffersResponse
Get the offers associated with the specified model.
-
#list_foundation_models(params = {}) ⇒ Types::ListFoundationModelsResponse
Lists Amazon Bedrock foundation models that you can use.
-
#list_guardrails(params = {}) ⇒ Types::ListGuardrailsResponse
Lists details about all the guardrails in an account.
-
#list_imported_models(params = {}) ⇒ Types::ListImportedModelsResponse
Returns a list of models you've imported.
-
#list_inference_profiles(params = {}) ⇒ Types::ListInferenceProfilesResponse
Returns a list of inference profiles that you can use.
-
#list_marketplace_model_endpoints(params = {}) ⇒ Types::ListMarketplaceModelEndpointsResponse
Lists the endpoints for models from Amazon Bedrock Marketplace in your Amazon Web Services account.
-
#list_model_copy_jobs(params = {}) ⇒ Types::ListModelCopyJobsResponse
Returns a list of model copy jobs that you have submitted.
-
#list_model_customization_jobs(params = {}) ⇒ Types::ListModelCustomizationJobsResponse
Returns a list of model customization jobs that you have submitted.
-
#list_model_import_jobs(params = {}) ⇒ Types::ListModelImportJobsResponse
Returns a list of import jobs you've submitted.
-
#list_model_invocation_jobs(params = {}) ⇒ Types::ListModelInvocationJobsResponse
Lists all batch inference jobs in the account.
-
#list_projects(params = {}) ⇒ Types::ListProjectsResponse
Lists the account's projects.
-
#list_prompt_routers(params = {}) ⇒ Types::ListPromptRoutersResponse
Retrieves a list of prompt routers.
-
#list_provisioned_model_throughputs(params = {}) ⇒ Types::ListProvisionedModelThroughputsResponse
Lists the Provisioned Throughputs in the account.
-
#list_tags_for_resource(params = {}) ⇒ Types::ListTagsForResourceResponse
List the tags associated with the specified resource.
-
#list_trusted_access_programs(params = {}) ⇒ Types::ListTrustedAccessProgramsResponse
Lists all trusted access programs visible to your account, ordered by program ID.
-
#put_account_data_retention(params = {}) ⇒ Types::PutAccountDataRetentionResponse
Sets the account-wide data retention mode for Amazon Bedrock.
-
#put_account_data_retention_storage(params = {}) ⇒ Types::PutAccountDataRetentionStorageResponse
Creates or replaces the calling account's retention storage record for a model provider.
-
#put_enforced_guardrail_configuration(params = {}) ⇒ Types::PutEnforcedGuardrailConfigurationResponse
Sets the account-level enforced guardrail configuration.
-
#put_model_invocation_logging_configuration(params = {}) ⇒ Struct
Set the configuration values for model invocation logging.
-
#put_organization_data_retention_storage(params = {}) ⇒ Types::PutOrganizationDataRetentionStorageResponse
Creates or replaces the organization's retention storage record for a model provider.
-
#put_project_data_retention_storage(params = {}) ⇒ Types::PutProjectDataRetentionStorageResponse
Creates or replaces a project's retention storage record for a model provider.
-
#put_resource_policy(params = {}) ⇒ Types::PutResourcePolicyResponse
Adds a resource policy for a Bedrock resource.
-
#put_trusted_access_program_account_enrollment(params = {}) ⇒ Types::PutTrustedAccessProgramAccountEnrollmentResponse
Sets your account's enrollment preference for a trusted access program.
-
#put_trusted_access_program_organization_enrollment(params = {}) ⇒ Types::PutTrustedAccessProgramOrganizationEnrollmentResponse
Sets the current organization's enrollment preference for a trusted access program.
-
#put_trusted_access_program_project_enrollment(params = {}) ⇒ Types::PutTrustedAccessProgramProjectEnrollmentResponse
Sets a named project's enrollment preference for a trusted access program.
-
#put_use_case_for_model_access(params = {}) ⇒ Struct
Put usecase for model access.
-
#register_marketplace_model_endpoint(params = {}) ⇒ Types::RegisterMarketplaceModelEndpointResponse
Registers an existing Amazon SageMaker endpoint with Amazon Bedrock Marketplace, allowing it to be used with Amazon Bedrock APIs.
-
#start_automated_reasoning_policy_build_workflow(params = {}) ⇒ Types::StartAutomatedReasoningPolicyBuildWorkflowResponse
Starts a new build workflow for an Automated Reasoning policy.
-
#start_automated_reasoning_policy_test_workflow(params = {}) ⇒ Types::StartAutomatedReasoningPolicyTestWorkflowResponse
Initiates a test workflow to validate Automated Reasoning policy tests.
-
#start_trusted_access_program_account_application(params = {}) ⇒ Types::StartTrustedAccessProgramAccountApplicationResponse
Prepare a provider application handoff for the calling account.
-
#start_trusted_access_program_organization_application(params = {}) ⇒ Types::StartTrustedAccessProgramOrganizationApplicationResponse
Prepare a provider application handoff for the calling account's current organization.
-
#start_trusted_access_program_project_application(params = {}) ⇒ Types::StartTrustedAccessProgramProjectApplicationResponse
Prepare a provider application handoff for a named project.
-
#stop_advanced_prompt_optimization_job(params = {}) ⇒ Struct
Stops an advanced prompt optimization job that is in progress.
-
#stop_evaluation_job(params = {}) ⇒ Struct
Stops an evaluation job that is current being created or running.
-
#stop_model_customization_job(params = {}) ⇒ Struct
Stops an active model customization job.
-
#stop_model_invocation_job(params = {}) ⇒ Struct
Stops a batch inference job.
-
#tag_resource(params = {}) ⇒ Struct
Associate tags with a resource.
-
#untag_resource(params = {}) ⇒ Struct
Remove one or more tags from a resource.
-
#update_automated_reasoning_policy(params = {}) ⇒ Types::UpdateAutomatedReasoningPolicyResponse
Updates an existing Automated Reasoning policy with new rules, variables, or configuration.
-
#update_automated_reasoning_policy_annotations(params = {}) ⇒ Types::UpdateAutomatedReasoningPolicyAnnotationsResponse
Updates the annotations for an Automated Reasoning policy build workflow.
-
#update_automated_reasoning_policy_test_case(params = {}) ⇒ Types::UpdateAutomatedReasoningPolicyTestCaseResponse
Updates an existing Automated Reasoning policy test.
-
#update_custom_model_deployment(params = {}) ⇒ Types::UpdateCustomModelDeploymentResponse
Updates a custom model deployment with a new custom model.
-
#update_guardrail(params = {}) ⇒ Types::UpdateGuardrailResponse
Updates a guardrail with the values you specify.
-
#update_marketplace_model_endpoint(params = {}) ⇒ Types::UpdateMarketplaceModelEndpointResponse
Updates the configuration of an existing endpoint for a model from Amazon Bedrock Marketplace.
-
#update_project(params = {}) ⇒ Types::UpdateProjectResponse
Updates one mutable project field per call: exactly one of
nameordataRetentionmust be set. -
#update_provisioned_model_throughput(params = {}) ⇒ Struct
Updates the name or associated model for a Provisioned Throughput.
Instance Method Summary collapse
-
#initialize(options) ⇒ Client
constructor
A new instance of Client.
Methods included from ClientStubs
#api_requests, #stub_data, #stub_responses
Methods inherited from Seahorse::Client::Base
add_plugin, api, clear_plugins, define, new, #operation_names, plugins, remove_plugin, set_api, set_plugins
Methods included from Seahorse::Client::HandlerBuilder
#handle, #handle_request, #handle_response
Constructor Details
#initialize(options) ⇒ Client
Returns a new instance of Client.
481 482 483 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 481 def initialize(*args) super end |
Instance Method Details
#archive_project(params = {}) ⇒ Types::ArchiveProjectResponse
Archives a project. Archiving is terminal; there is no delete. Archiving an already-archived project succeeds without effect. The default project cannot be archived.
524 525 526 527 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 524 def archive_project(params = {}, = {}) req = build_request(:archive_project, params) req.send_request() end |
#batch_delete_advanced_prompt_optimization_job(params = {}) ⇒ Types::BatchDeleteAdvancedPromptOptimizationJobResponse
Deletes one or more advanced prompt optimization jobs.
560 561 562 563 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 560 def batch_delete_advanced_prompt_optimization_job(params = {}, = {}) req = build_request(:batch_delete_advanced_prompt_optimization_job, params) req.send_request() end |
#batch_delete_evaluation_job(params = {}) ⇒ Types::BatchDeleteEvaluationJobResponse
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.
628 629 630 631 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 628 def batch_delete_evaluation_job(params = {}, = {}) req = build_request(:batch_delete_evaluation_job, params) req.send_request() end |
#cancel_automated_reasoning_policy_build_workflow(params = {}) ⇒ Struct
Cancels a running Automated Reasoning policy build workflow. This stops the policy generation process and prevents further processing of the source documents.
659 660 661 662 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 659 def cancel_automated_reasoning_policy_build_workflow(params = {}, = {}) req = build_request(:cancel_automated_reasoning_policy_build_workflow, params) req.send_request() end |
#create_advanced_prompt_optimization_job(params = {}) ⇒ Types::CreateAdvancedPromptOptimizationJobResponse
Creates an advanced prompt optimization job. The job optimizes your prompt templates for specific models using your evaluation dataset and criteria.
750 751 752 753 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 750 def create_advanced_prompt_optimization_job(params = {}, = {}) req = build_request(:create_advanced_prompt_optimization_job, params) req.send_request() end |
#create_automated_reasoning_policy(params = {}) ⇒ Types::CreateAutomatedReasoningPolicyResponse
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.
867 868 869 870 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 867 def create_automated_reasoning_policy(params = {}, = {}) req = build_request(:create_automated_reasoning_policy, params) req.send_request() end |
#create_automated_reasoning_policy_test_case(params = {}) ⇒ Types::CreateAutomatedReasoningPolicyTestCaseResponse
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.
970 971 972 973 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 970 def create_automated_reasoning_policy_test_case(params = {}, = {}) req = build_request(:create_automated_reasoning_policy_test_case, params) req.send_request() end |
#create_automated_reasoning_policy_version(params = {}) ⇒ Types::CreateAutomatedReasoningPolicyVersionResponse
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.
1036 1037 1038 1039 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 1036 def create_automated_reasoning_policy_version(params = {}, = {}) req = build_request(:create_automated_reasoning_policy_version, params) req.send_request() end |
#create_custom_model(params = {}) ⇒ Types::CreateCustomModelResponse
Creates a new custom model in Amazon Bedrock. After the model is active, you can use it for inference.
You can provide the model data source in one of the following ways:
customModelDataSource— Specify a SageMaker AI model package ARN. Amazon Bedrock resolves the model package to retrieve the model artifacts. This is the preferred method for new SageMaker AI training outputs.modelSourceConfig— Specify an Amazon S3 URI pointing to the Amazon-managed Amazon S3 bucket containing your model artifacts.
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 registrationActive- Model is ready for use in inferenceFailed- Creation process encountered an error
Related APIs
1225 1226 1227 1228 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 1225 def create_custom_model(params = {}, = {}) req = build_request(:create_custom_model, params) req.send_request() end |
#create_custom_model_deployment(params = {}) ⇒ Types::CreateCustomModelDeploymentResponse
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:
1311 1312 1313 1314 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 1311 def create_custom_model_deployment(params = {}, = {}) req = build_request(:create_custom_model_deployment, params) req.send_request() end |
#create_evaluation_job(params = {}) ⇒ Types::CreateEvaluationJobResponse
Creates an evaluation job.
1810 1811 1812 1813 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 1810 def create_evaluation_job(params = {}, = {}) req = build_request(:create_evaluation_job, params) req.send_request() end |
#create_foundation_model_agreement(params = {}) ⇒ Types::CreateFoundationModelAgreementResponse
Request a model access agreement for the specified model.
1842 1843 1844 1845 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 1842 def create_foundation_model_agreement(params = {}, = {}) req = build_request(:create_foundation_model_agreement, params) req.send_request() end |
#create_guardrail(params = {}) ⇒ Types::CreateGuardrailResponse
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.
2078 2079 2080 2081 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 2078 def create_guardrail(params = {}, = {}) req = build_request(:create_guardrail, params) req.send_request() end |
#create_guardrail_version(params = {}) ⇒ Types::CreateGuardrailVersionResponse
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.
2129 2130 2131 2132 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 2129 def create_guardrail_version(params = {}, = {}) req = build_request(:create_guardrail_version, params) req.send_request() end |
#create_inference_profile(params = {}) ⇒ Types::CreateInferenceProfileResponse
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.
2211 2212 2213 2214 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 2211 def create_inference_profile(params = {}, = {}) req = build_request(:create_inference_profile, params) req.send_request() end |
#create_marketplace_model_endpoint(params = {}) ⇒ Types::CreateMarketplaceModelEndpointResponse
Creates an endpoint for a model from Amazon Bedrock Marketplace. The endpoint is hosted by Amazon SageMaker.
2304 2305 2306 2307 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 2304 def create_marketplace_model_endpoint(params = {}, = {}) req = build_request(:create_marketplace_model_endpoint, params) req.send_request() end |
#create_model_copy_job(params = {}) ⇒ Types::CreateModelCopyJobResponse
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.
2376 2377 2378 2379 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 2376 def create_model_copy_job(params = {}, = {}) req = build_request(:create_model_copy_job, params) req.send_request() end |
#create_model_customization_job(params = {}) ⇒ Types::CreateModelCustomizationJobResponse
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.
2592 2593 2594 2595 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 2592 def create_model_customization_job(params = {}, = {}) req = build_request(:create_model_customization_job, params) req.send_request() end |
#create_model_import_job(params = {}) ⇒ Types::CreateModelImportJobResponse
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
2683 2684 2685 2686 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 2683 def create_model_import_job(params = {}, = {}) req = build_request(:create_model_import_job, params) req.send_request() end |
#create_model_invocation_job(params = {}) ⇒ Types::CreateModelInvocationJobResponse
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.
2808 2809 2810 2811 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 2808 def create_model_invocation_job(params = {}, = {}) req = build_request(:create_model_invocation_job, params) req.send_request() end |
#create_project(params = {}) ⇒ Types::CreateProjectResponse
Creates a project: a workload boundary within the account that inference requests can be associated with.
2867 2868 2869 2870 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 2867 def create_project(params = {}, = {}) req = build_request(:create_project, params) req.send_request() end |
#create_prompt_router(params = {}) ⇒ Types::CreatePromptRouterResponse
Creates a prompt router that manages the routing of requests between multiple foundation models based on the routing criteria.
2943 2944 2945 2946 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 2943 def create_prompt_router(params = {}, = {}) req = build_request(:create_prompt_router, params) req.send_request() end |
#create_provisioned_model_throughput(params = {}) ⇒ Types::CreateProvisionedModelThroughputResponse
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.
3054 3055 3056 3057 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 3054 def create_provisioned_model_throughput(params = {}, = {}) req = build_request(:create_provisioned_model_throughput, params) req.send_request() end |
#delete_account_data_retention_storage(params = {}) ⇒ Struct
Deletes your account's retention storage configuration for a model provider. Deleting an absent configuration succeeds. You do not need to participate in the program to delete the configuration. You can delete it even if your account is ineligible or its eligibility is revoked.
3081 3082 3083 3084 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 3081 def delete_account_data_retention_storage(params = {}, = {}) req = build_request(:delete_account_data_retention_storage, params) req.send_request() end |
#delete_automated_reasoning_policy(params = {}) ⇒ Struct
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.
3116 3117 3118 3119 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 3116 def delete_automated_reasoning_policy(params = {}, = {}) req = build_request(:delete_automated_reasoning_policy, params) req.send_request() end |
#delete_automated_reasoning_policy_build_workflow(params = {}) ⇒ Struct
Deletes an Automated Reasoning policy build workflow and its associated artifacts. This permanently removes the workflow history and any generated assets.
3151 3152 3153 3154 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 3151 def delete_automated_reasoning_policy_build_workflow(params = {}, = {}) req = build_request(:delete_automated_reasoning_policy_build_workflow, params) req.send_request() end |
#delete_automated_reasoning_policy_test_case(params = {}) ⇒ Struct
Deletes an Automated Reasoning policy test. This operation is idempotent; if you delete a test more than once, each call succeeds.
3184 3185 3186 3187 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 3184 def delete_automated_reasoning_policy_test_case(params = {}, = {}) req = build_request(:delete_automated_reasoning_policy_test_case, params) req.send_request() end |
#delete_custom_model(params = {}) ⇒ Struct
Deletes a custom model that you created earlier. For more information, see Custom models in the Amazon Bedrock User Guide.
3212 3213 3214 3215 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 3212 def delete_custom_model(params = {}, = {}) req = build_request(:delete_custom_model, params) req.send_request() end |
#delete_custom_model_deployment(params = {}) ⇒ Struct
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:
3252 3253 3254 3255 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 3252 def delete_custom_model_deployment(params = {}, = {}) req = build_request(:delete_custom_model_deployment, params) req.send_request() end |
#delete_enforced_guardrail_configuration(params = {}) ⇒ Struct
Deletes the account-level enforced guardrail configuration.
3274 3275 3276 3277 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 3274 def delete_enforced_guardrail_configuration(params = {}, = {}) req = build_request(:delete_enforced_guardrail_configuration, params) req.send_request() end |
#delete_foundation_model_agreement(params = {}) ⇒ Struct
Delete the model access agreement for the specified model.
3296 3297 3298 3299 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 3296 def delete_foundation_model_agreement(params = {}, = {}) req = build_request(:delete_foundation_model_agreement, params) req.send_request() end |
#delete_guardrail(params = {}) ⇒ Struct
Deletes a guardrail.
To delete a guardrail, only specify the ARN of the guardrail in the
guardrailIdentifierfield. 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
guardrailIdentifierfield and the version in theguardrailVersionfield.
3330 3331 3332 3333 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 3330 def delete_guardrail(params = {}, = {}) req = build_request(:delete_guardrail, params) req.send_request() end |
#delete_imported_model(params = {}) ⇒ Struct
Deletes a custom model that you imported earlier. For more information, see Import a customized model in the Amazon Bedrock User Guide.
3359 3360 3361 3362 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 3359 def delete_imported_model(params = {}, = {}) req = build_request(:delete_imported_model, params) req.send_request() end |
#delete_inference_profile(params = {}) ⇒ Struct
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.
3388 3389 3390 3391 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 3388 def delete_inference_profile(params = {}, = {}) req = build_request(:delete_inference_profile, params) req.send_request() end |
#delete_marketplace_model_endpoint(params = {}) ⇒ Struct
Deletes an endpoint for a model from Amazon Bedrock Marketplace.
3410 3411 3412 3413 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 3410 def delete_marketplace_model_endpoint(params = {}, = {}) req = build_request(:delete_marketplace_model_endpoint, params) req.send_request() end |
#delete_model_invocation_logging_configuration(params = {}) ⇒ Struct
Delete the invocation logging.
3423 3424 3425 3426 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 3423 def delete_model_invocation_logging_configuration(params = {}, = {}) req = build_request(:delete_model_invocation_logging_configuration, params) req.send_request() end |
#delete_organization_data_retention_storage(params = {}) ⇒ Struct
Deletes the organization's retention storage configuration for a model provider. The caller must be the organization's management account or a delegated administrator. Deleting an absent configuration succeeds; no program participation is required to delete.
3449 3450 3451 3452 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 3449 def delete_organization_data_retention_storage(params = {}, = {}) req = build_request(:delete_organization_data_retention_storage, params) req.send_request() end |
#delete_project_data_retention_storage(params = {}) ⇒ Struct
Deletes a project's retention storage configuration for a model
provider. Deleting an absent configuration on an active project
succeeds. If the project does not exist or your account does not own
it, the operation returns ResourceNotFoundException. For an archived
project, the operation returns ValidationException. You can read the
archived project's stored configuration until Amazon Bedrock purges
the project. You do not need to participate in the program to delete
the configuration.
3485 3486 3487 3488 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 3485 def delete_project_data_retention_storage(params = {}, = {}) req = build_request(:delete_project_data_retention_storage, params) req.send_request() end |
#delete_prompt_router(params = {}) ⇒ Struct
Deletes a specified prompt router. This action cannot be undone.
3507 3508 3509 3510 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 3507 def delete_prompt_router(params = {}, = {}) req = build_request(:delete_prompt_router, params) req.send_request() end |
#delete_provisioned_model_throughput(params = {}) ⇒ Struct
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.
3536 3537 3538 3539 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 3536 def delete_provisioned_model_throughput(params = {}, = {}) req = build_request(:delete_provisioned_model_throughput, params) req.send_request() end |
#delete_resource_policy(params = {}) ⇒ Struct
Deletes a previously created Bedrock resource policy.
3558 3559 3560 3561 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 3558 def delete_resource_policy(params = {}, = {}) req = build_request(:delete_resource_policy, params) req.send_request() end |
#deregister_marketplace_model_endpoint(params = {}) ⇒ Struct
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.
3582 3583 3584 3585 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 3582 def deregister_marketplace_model_endpoint(params = {}, = {}) req = build_request(:deregister_marketplace_model_endpoint, params) req.send_request() end |
#export_automated_reasoning_policy_version(params = {}) ⇒ Types::ExportAutomatedReasoningPolicyVersionResponse
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.
3628 3629 3630 3631 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 3628 def export_automated_reasoning_policy_version(params = {}, = {}) req = build_request(:export_automated_reasoning_policy_version, params) req.send_request() end |
#get_account_data_retention(params = {}) ⇒ Types::GetAccountDataRetentionResponse
Returns the account-wide data retention mode for Amazon Bedrock.
3649 3650 3651 3652 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 3649 def get_account_data_retention(params = {}, = {}) req = build_request(:get_account_data_retention, params) req.send_request() end |
#get_account_data_retention_storage(params = {}) ⇒ Types::GetAccountDataRetentionStorageResponse
Returns your account's stored retention storage configuration for a
model provider. Amazon Bedrock determines whether the configuration
applies when processing an inference request. Returns
ResourceNotFoundException when no configuration exists.
3695 3696 3697 3698 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 3695 def get_account_data_retention_storage(params = {}, = {}) req = build_request(:get_account_data_retention_storage, params) req.send_request() end |
#get_advanced_prompt_optimization_job(params = {}) ⇒ Types::GetAdvancedPromptOptimizationJobResponse
Gets information about an advanced prompt optimization job.
3750 3751 3752 3753 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 3750 def get_advanced_prompt_optimization_job(params = {}, = {}) req = build_request(:get_advanced_prompt_optimization_job, params) req.send_request() end |
#get_automated_reasoning_policy(params = {}) ⇒ Types::GetAutomatedReasoningPolicyResponse
Retrieves details about an Automated Reasoning policy or policy version. Returns information including the policy definition, metadata, and timestamps.
3798 3799 3800 3801 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 3798 def get_automated_reasoning_policy(params = {}, = {}) req = build_request(:get_automated_reasoning_policy, params) req.send_request() end |
#get_automated_reasoning_policy_annotations(params = {}) ⇒ Types::GetAutomatedReasoningPolicyAnnotationsResponse
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.
3880 3881 3882 3883 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 3880 def get_automated_reasoning_policy_annotations(params = {}, = {}) req = build_request(:get_automated_reasoning_policy_annotations, params) req.send_request() end |
#get_automated_reasoning_policy_build_workflow(params = {}) ⇒ Types::GetAutomatedReasoningPolicyBuildWorkflowResponse
Retrieves detailed information about an Automated Reasoning policy build workflow, including its status, configuration, and metadata.
3930 3931 3932 3933 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 3930 def get_automated_reasoning_policy_build_workflow(params = {}, = {}) req = build_request(:get_automated_reasoning_policy_build_workflow, params) req.send_request() end |
#get_automated_reasoning_policy_build_workflow_result_assets(params = {}) ⇒ Types::GetAutomatedReasoningPolicyBuildWorkflowResultAssetsResponse
Retrieves the resulting assets from a completed Automated Reasoning policy build workflow, including build logs, quality reports, and generated policy artifacts.
4146 4147 4148 4149 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 4146 def get_automated_reasoning_policy_build_workflow_result_assets(params = {}, = {}) req = build_request(:get_automated_reasoning_policy_build_workflow_result_assets, params) req.send_request() end |
#get_automated_reasoning_policy_next_scenario(params = {}) ⇒ Types::GetAutomatedReasoningPolicyNextScenarioResponse
Retrieves the next test scenario for validating an Automated Reasoning policy. This is used during the interactive policy refinement process to test policy behavior.
4188 4189 4190 4191 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 4188 def get_automated_reasoning_policy_next_scenario(params = {}, = {}) req = build_request(:get_automated_reasoning_policy_next_scenario, params) req.send_request() end |
#get_automated_reasoning_policy_test_case(params = {}) ⇒ Types::GetAutomatedReasoningPolicyTestCaseResponse
Retrieves details about a specific Automated Reasoning policy test.
4229 4230 4231 4232 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 4229 def get_automated_reasoning_policy_test_case(params = {}, = {}) req = build_request(:get_automated_reasoning_policy_test_case, params) req.send_request() end |
#get_automated_reasoning_policy_test_result(params = {}) ⇒ Types::GetAutomatedReasoningPolicyTestResultResponse
Retrieves the test result for a specific Automated Reasoning policy test. Returns detailed validation findings and execution status.
4386 4387 4388 4389 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 4386 def get_automated_reasoning_policy_test_result(params = {}, = {}) req = build_request(:get_automated_reasoning_policy_test_result, params) req.send_request() end |
#get_custom_model(params = {}) ⇒ Types::GetCustomModelResponse
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.
4482 4483 4484 4485 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 4482 def get_custom_model(params = {}, = {}) req = build_request(:get_custom_model, params) req.send_request() end |
#get_custom_model_deployment(params = {}) ⇒ Types::GetCustomModelDeploymentResponse
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:
4545 4546 4547 4548 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 4545 def get_custom_model_deployment(params = {}, = {}) req = build_request(:get_custom_model_deployment, params) req.send_request() end |
#get_evaluation_job(params = {}) ⇒ Types::GetEvaluationJobResponse
Gets information about an evaluation job, such as the status of the job.
4729 4730 4731 4732 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 4729 def get_evaluation_job(params = {}, = {}) req = build_request(:get_evaluation_job, params) req.send_request() end |
#get_foundation_model(params = {}) ⇒ Types::GetFoundationModelResponse
Get details about a Amazon Bedrock foundation model.
4788 4789 4790 4791 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 4788 def get_foundation_model(params = {}, = {}) req = build_request(:get_foundation_model, params) req.send_request() end |
#get_foundation_model_availability(params = {}) ⇒ Types::GetFoundationModelAvailabilityResponse
Get information about the Foundation model availability.
4825 4826 4827 4828 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 4825 def get_foundation_model_availability(params = {}, = {}) req = build_request(:get_foundation_model_availability, params) req.send_request() end |
#get_guardrail(params = {}) ⇒ Types::GetGuardrailResponse
Gets details about a guardrail. If you don't specify a version, the
response returns details for the DRAFT version.
4957 4958 4959 4960 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 4957 def get_guardrail(params = {}, = {}) req = build_request(:get_guardrail, params) req.send_request() end |
#get_imported_model(params = {}) ⇒ Types::GetImportedModelResponse
Gets properties associated with a customized model you imported.
5004 5005 5006 5007 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 5004 def get_imported_model(params = {}, = {}) req = build_request(:get_imported_model, params) req.send_request() end |
#get_inference_profile(params = {}) ⇒ Types::GetInferenceProfileResponse
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.
5070 5071 5072 5073 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 5070 def get_inference_profile(params = {}, = {}) req = build_request(:get_inference_profile, params) req.send_request() end |
#get_marketplace_model_endpoint(params = {}) ⇒ Types::GetMarketplaceModelEndpointResponse
Retrieves details about a specific endpoint for a model from Amazon Bedrock Marketplace.
5115 5116 5117 5118 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 5115 def get_marketplace_model_endpoint(params = {}, = {}) req = build_request(:get_marketplace_model_endpoint, params) req.send_request() end |
#get_model_copy_job(params = {}) ⇒ Types::GetModelCopyJobResponse
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.
5172 5173 5174 5175 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 5172 def get_model_copy_job(params = {}, = {}) req = build_request(:get_model_copy_job, params) req.send_request() end |
#get_model_customization_job(params = {}) ⇒ Types::GetModelCustomizationJobResponse
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.
5291 5292 5293 5294 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 5291 def get_model_customization_job(params = {}, = {}) req = build_request(:get_model_customization_job, params) req.send_request() end |
#get_model_import_job(params = {}) ⇒ Types::GetModelImportJobResponse
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.
5353 5354 5355 5356 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 5353 def get_model_import_job(params = {}, = {}) req = build_request(:get_model_import_job, params) req.send_request() end |
#get_model_invocation_job(params = {}) ⇒ Types::GetModelInvocationJobResponse
Gets details about a batch inference job. For more information, see Monitor batch inference jobs
5431 5432 5433 5434 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 5431 def get_model_invocation_job(params = {}, = {}) req = build_request(:get_model_invocation_job, params) req.send_request() end |
#get_model_invocation_logging_configuration(params = {}) ⇒ Types::GetModelInvocationLoggingConfigurationResponse
Get the current configuration values for model invocation logging.
5460 5461 5462 5463 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 5460 def get_model_invocation_logging_configuration(params = {}, = {}) req = build_request(:get_model_invocation_logging_configuration, params) req.send_request() end |
#get_organization_data_retention_storage(params = {}) ⇒ Types::GetOrganizationDataRetentionStorageResponse
Returns the organization's retention storage configuration for a model provider. The caller must be the organization's management account or a delegated administrator. Returns ResourceNotFoundException when no configuration exists.
5506 5507 5508 5509 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 5506 def get_organization_data_retention_storage(params = {}, = {}) req = build_request(:get_organization_data_retention_storage, params) req.send_request() end |
#get_project(params = {}) ⇒ Types::GetProjectResponse
Retrieves a project.
5546 5547 5548 5549 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 5546 def get_project(params = {}, = {}) req = build_request(:get_project, params) req.send_request() end |
#get_project_data_retention_storage(params = {}) ⇒ Types::GetProjectDataRetentionStorageResponse
Returns a project's retention storage configuration for a model provider. Returns ResourceNotFoundException when the project does not exist, is not owned by the calling account, or has no configuration.
5599 5600 5601 5602 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 5599 def get_project_data_retention_storage(params = {}, = {}) req = build_request(:get_project_data_retention_storage, params) req.send_request() end |
#get_prompt_router(params = {}) ⇒ Types::GetPromptRouterResponse
Retrieves details about a prompt router.
5646 5647 5648 5649 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 5646 def get_prompt_router(params = {}, = {}) req = build_request(:get_prompt_router, params) req.send_request() end |
#get_provisioned_model_throughput(params = {}) ⇒ Types::GetProvisionedModelThroughputResponse
Returns details for a Provisioned Throughput. For more information, see Provisioned Throughput in the Amazon Bedrock User Guide.
5704 5705 5706 5707 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 5704 def get_provisioned_model_throughput(params = {}, = {}) req = build_request(:get_provisioned_model_throughput, params) req.send_request() end |
#get_resource_policy(params = {}) ⇒ Types::GetResourcePolicyResponse
Gets the resource policy document for a Bedrock resource
5732 5733 5734 5735 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 5732 def get_resource_policy(params = {}, = {}) req = build_request(:get_resource_policy, params) req.send_request() end |
#get_trusted_access_program(params = {}) ⇒ Types::GetTrustedAccessProgramResponse
Gets trusted access program details and resolves participation for your account and its current organization. If you specify a project, Amazon Bedrock resolves participation for the project, including inheritance from the account and organization. Archived projects remain readable until they expire. Returns the same flat summary as a ListTrustedAccessPrograms item. An absent or invisible program returns ResourceNotFoundException.
5803 5804 5805 5806 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 5803 def get_trusted_access_program(params = {}, = {}) req = build_request(:get_trusted_access_program, params) req.send_request() end |
#get_trusted_access_program_account_enrollment(params = {}) ⇒ Types::GetTrustedAccessProgramAccountEnrollmentResponse
Gets the calling account's stored enrollment setting for a trusted access program. The account is derived from the authenticated caller. Use GetTrustedAccessProgram to retrieve the resolved participation status, including organization inheritance. If no enrollment is stored, returns inherit without timestamps.
5837 5838 5839 5840 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 5837 def get_trusted_access_program_account_enrollment(params = {}, = {}) req = build_request(:get_trusted_access_program_account_enrollment, params) req.send_request() end |
#get_trusted_access_program_organization_enrollment(params = {}) ⇒ Types::GetTrustedAccessProgramOrganizationEnrollmentResponse
Gets the current organization's stored enrollment setting for a trusted access program. The organization and payer account are derived from the authenticated context. Requires operation permission and management-account or Bedrock-specific delegated-administrator authority. The setting can differ from the caller's resolved status returned by GetTrustedAccessProgram. If no enrollment is stored, returns inherit without timestamps.
5873 5874 5875 5876 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 5873 def get_trusted_access_program_organization_enrollment(params = {}, = {}) req = build_request(:get_trusted_access_program_organization_enrollment, params) req.send_request() end |
#get_trusted_access_program_project_enrollment(params = {}) ⇒ Types::GetTrustedAccessProgramProjectEnrollmentResponse
Gets a named project's stored enrollment setting for a trusted access program. The project must exist in this Region and be owned by the calling account. Archived projects remain readable until they expire. Use GetTrustedAccessProgram with projectIdentifier to retrieve resolved participation, including account and organization inheritance. If no enrollment is stored, returns inherit without timestamps.
5917 5918 5919 5920 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 5917 def get_trusted_access_program_project_enrollment(params = {}, = {}) req = build_request(:get_trusted_access_program_project_enrollment, params) req.send_request() end |
#get_use_case_for_model_access(params = {}) ⇒ Types::GetUseCaseForModelAccessResponse
Get usecase for model access.
5936 5937 5938 5939 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 5936 def get_use_case_for_model_access(params = {}, = {}) req = build_request(:get_use_case_for_model_access, params) req.send_request() end |
#list_advanced_prompt_optimization_jobs(params = {}) ⇒ Types::ListAdvancedPromptOptimizationJobsResponse
Lists the advanced prompt optimization jobs in your account.
The returned response is a pageable response and is Enumerable. For details on usage see PageableResponse.
5987 5988 5989 5990 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 5987 def list_advanced_prompt_optimization_jobs(params = {}, = {}) req = build_request(:list_advanced_prompt_optimization_jobs, params) req.send_request() end |
#list_automated_reasoning_policies(params = {}) ⇒ Types::ListAutomatedReasoningPoliciesResponse
Lists all Automated Reasoning policies in your account, with optional filtering by policy ARN. This helps you manage and discover existing policies.
The returned response is a pageable response and is Enumerable. For details on usage see PageableResponse.
6039 6040 6041 6042 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 6039 def list_automated_reasoning_policies(params = {}, = {}) req = build_request(:list_automated_reasoning_policies, params) req.send_request() end |
#list_automated_reasoning_policy_build_workflows(params = {}) ⇒ Types::ListAutomatedReasoningPolicyBuildWorkflowsResponse
Lists all build workflows for an Automated Reasoning policy, showing the history of policy creation and modification attempts.
The returned response is a pageable response and is Enumerable. For details on usage see PageableResponse.
6089 6090 6091 6092 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 6089 def list_automated_reasoning_policy_build_workflows(params = {}, = {}) req = build_request(:list_automated_reasoning_policy_build_workflows, params) req.send_request() end |
#list_automated_reasoning_policy_test_cases(params = {}) ⇒ Types::ListAutomatedReasoningPolicyTestCasesResponse
Lists tests for an Automated Reasoning policy. We recommend using pagination to ensure that the operation returns quickly and successfully.
The returned response is a pageable response and is Enumerable. For details on usage see PageableResponse.
6140 6141 6142 6143 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 6140 def list_automated_reasoning_policy_test_cases(params = {}, = {}) req = build_request(:list_automated_reasoning_policy_test_cases, params) req.send_request() end |
#list_automated_reasoning_policy_test_results(params = {}) ⇒ Types::ListAutomatedReasoningPolicyTestResultsResponse
Lists test results for an Automated Reasoning policy, showing how the policy performed against various test scenarios and validation checks.
The returned response is a pageable response and is Enumerable. For details on usage see PageableResponse.
6309 6310 6311 6312 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 6309 def list_automated_reasoning_policy_test_results(params = {}, = {}) req = build_request(:list_automated_reasoning_policy_test_results, params) req.send_request() end |
#list_custom_model_deployments(params = {}) ⇒ Types::ListCustomModelDeploymentsResponse
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:
The returned response is a pageable response and is Enumerable. For details on usage see PageableResponse.
6405 6406 6407 6408 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 6405 def list_custom_model_deployments(params = {}, = {}) req = build_request(:list_custom_model_deployments, params) req.send_request() end |
#list_custom_models(params = {}) ⇒ Types::ListCustomModelsResponse
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.
The returned response is a pageable response and is Enumerable. For details on usage see PageableResponse.
6514 6515 6516 6517 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 6514 def list_custom_models(params = {}, = {}) req = build_request(:list_custom_models, params) req.send_request() end |
#list_enforced_guardrails_configuration(params = {}) ⇒ Types::ListEnforcedGuardrailsConfigurationResponse
Lists the account-level enforced guardrail configurations.
The returned response is a pageable response and is Enumerable. For details on usage see PageableResponse.
6562 6563 6564 6565 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 6562 def list_enforced_guardrails_configuration(params = {}, = {}) req = build_request(:list_enforced_guardrails_configuration, params) req.send_request() end |
#list_evaluation_jobs(params = {}) ⇒ Types::ListEvaluationJobsResponse
Lists all existing evaluation jobs.
The returned response is a pageable response and is Enumerable. For details on usage see PageableResponse.
6655 6656 6657 6658 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 6655 def list_evaluation_jobs(params = {}, = {}) req = build_request(:list_evaluation_jobs, params) req.send_request() end |
#list_foundation_model_agreement_offers(params = {}) ⇒ Types::ListFoundationModelAgreementOffersResponse
Get the offers associated with the specified model.
6699 6700 6701 6702 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 6699 def list_foundation_model_agreement_offers(params = {}, = {}) req = build_request(:list_foundation_model_agreement_offers, params) req.send_request() end |
#list_foundation_models(params = {}) ⇒ Types::ListFoundationModelsResponse
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.
6790 6791 6792 6793 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 6790 def list_foundation_models(params = {}, = {}) req = build_request(:list_foundation_models, params) req.send_request() end |
#list_guardrails(params = {}) ⇒ Types::ListGuardrailsResponse
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.
The returned response is a pageable response and is Enumerable. For details on usage see PageableResponse.
6850 6851 6852 6853 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 6850 def list_guardrails(params = {}, = {}) req = build_request(:list_guardrails, params) req.send_request() end |
#list_imported_models(params = {}) ⇒ Types::ListImportedModelsResponse
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.
The returned response is a pageable response and is Enumerable. For details on usage see PageableResponse.
6926 6927 6928 6929 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 6926 def list_imported_models(params = {}, = {}) req = build_request(:list_imported_models, params) req.send_request() end |
#list_inference_profiles(params = {}) ⇒ Types::ListInferenceProfilesResponse
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.
The returned response is a pageable response and is Enumerable. For details on usage see PageableResponse.
7014 7015 7016 7017 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 7014 def list_inference_profiles(params = {}, = {}) req = build_request(:list_inference_profiles, params) req.send_request() end |
#list_marketplace_model_endpoints(params = {}) ⇒ Types::ListMarketplaceModelEndpointsResponse
Lists the endpoints for models from Amazon Bedrock Marketplace in your Amazon Web Services account.
The returned response is a pageable response and is Enumerable. For details on usage see PageableResponse.
7064 7065 7066 7067 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 7064 def list_marketplace_model_endpoints(params = {}, = {}) req = build_request(:list_marketplace_model_endpoints, params) req.send_request() end |
#list_model_copy_jobs(params = {}) ⇒ Types::ListModelCopyJobsResponse
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.
The returned response is a pageable response and is Enumerable. For details on usage see PageableResponse.
7164 7165 7166 7167 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 7164 def list_model_copy_jobs(params = {}, = {}) req = build_request(:list_model_copy_jobs, params) req.send_request() end |
#list_model_customization_jobs(params = {}) ⇒ Types::ListModelCustomizationJobsResponse
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.
The returned response is a pageable response and is Enumerable. For details on usage see PageableResponse.
7259 7260 7261 7262 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 7259 def list_model_customization_jobs(params = {}, = {}) req = build_request(:list_model_customization_jobs, params) req.send_request() end |
#list_model_import_jobs(params = {}) ⇒ Types::ListModelImportJobsResponse
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.
The returned response is a pageable response and is Enumerable. For details on usage see PageableResponse.
7342 7343 7344 7345 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 7342 def list_model_import_jobs(params = {}, = {}) req = build_request(:list_model_import_jobs, params) req.send_request() end |
#list_model_invocation_jobs(params = {}) ⇒ Types::ListModelInvocationJobsResponse
Lists all batch inference jobs in the account. For more information, see View details about a batch inference job.
The returned response is a pageable response and is Enumerable. For details on usage see PageableResponse.
7491 7492 7493 7494 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 7491 def list_model_invocation_jobs(params = {}, = {}) req = build_request(:list_model_invocation_jobs, params) req.send_request() end |
#list_projects(params = {}) ⇒ Types::ListProjectsResponse
Lists the account's projects. Results are paginated: when the
response includes nextToken, pass it in the next request to fetch
the following page. Page size is 1-100, default 20. By default every
project is returned regardless of status; set statusFilter to list
only active or only archived projects.
The returned response is a pageable response and is Enumerable. For details on usage see PageableResponse.
7546 7547 7548 7549 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 7546 def list_projects(params = {}, = {}) req = build_request(:list_projects, params) req.send_request() end |
#list_prompt_routers(params = {}) ⇒ Types::ListPromptRoutersResponse
Retrieves a list of prompt routers.
The returned response is a pageable response and is Enumerable. For details on usage see PageableResponse.
7599 7600 7601 7602 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 7599 def list_prompt_routers(params = {}, = {}) req = build_request(:list_prompt_routers, params) req.send_request() end |
#list_provisioned_model_throughputs(params = {}) ⇒ Types::ListProvisionedModelThroughputsResponse
Lists the Provisioned Throughputs in the account. For more information, see Provisioned Throughput in the Amazon Bedrock User Guide.
The returned response is a pageable response and is Enumerable. For details on usage see PageableResponse.
7694 7695 7696 7697 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 7694 def list_provisioned_model_throughputs(params = {}, = {}) req = build_request(:list_provisioned_model_throughputs, params) req.send_request() end |
#list_tags_for_resource(params = {}) ⇒ Types::ListTagsForResourceResponse
List the tags associated with the specified resource.
For more information, see Tagging resources in the Amazon Bedrock User Guide.
7731 7732 7733 7734 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 7731 def (params = {}, = {}) req = build_request(:list_tags_for_resource, params) req.send_request() end |
#list_trusted_access_programs(params = {}) ⇒ Types::ListTrustedAccessProgramsResponse
Lists all trusted access programs visible to your account, ordered by program ID. Amazon Bedrock resolves participation for your account and its current organization. If you specify a project, Amazon Bedrock resolves participation for the project, including inheritance from the account and organization. Archived projects remain readable until they expire. Amazon Bedrock returns all visible programs in one response.
The returned response is a pageable response and is Enumerable. For details on usage see PageableResponse.
7799 7800 7801 7802 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 7799 def list_trusted_access_programs(params = {}, = {}) req = build_request(:list_trusted_access_programs, params) req.send_request() end |
#put_account_data_retention(params = {}) ⇒ Types::PutAccountDataRetentionResponse
Sets the account-wide data retention mode for Amazon Bedrock.
7829 7830 7831 7832 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 7829 def put_account_data_retention(params = {}, = {}) req = build_request(:put_account_data_retention, params) req.send_request() end |
#put_account_data_retention_storage(params = {}) ⇒ Types::PutAccountDataRetentionStorageResponse
Creates or replaces the calling account's retention storage record for a model provider. Amazon Bedrock identifies the account from your authenticated request. Requires resolved trusted access eligibility for a storage-capable program of the provider at a covering scope; otherwise returns ConflictException. Writes replace the whole record; the last write wins.
For customer_managed destinations, Amazon Bedrock validates the
caller's and service's access to the bucket and key before saving
the configuration. The bucket and key must be in the AWS Region where
you register the configuration. Validation failures reject the write.
7897 7898 7899 7900 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 7897 def put_account_data_retention_storage(params = {}, = {}) req = build_request(:put_account_data_retention_storage, params) req.send_request() end |
#put_enforced_guardrail_configuration(params = {}) ⇒ Types::PutEnforcedGuardrailConfigurationResponse
Sets the account-level enforced guardrail configuration.
7944 7945 7946 7947 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 7944 def put_enforced_guardrail_configuration(params = {}, = {}) req = build_request(:put_enforced_guardrail_configuration, params) req.send_request() end |
#put_model_invocation_logging_configuration(params = {}) ⇒ Struct
Set the configuration values for model invocation logging.
7984 7985 7986 7987 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 7984 def put_model_invocation_logging_configuration(params = {}, = {}) req = build_request(:put_model_invocation_logging_configuration, params) req.send_request() end |
#put_organization_data_retention_storage(params = {}) ⇒ Types::PutOrganizationDataRetentionStorageResponse
Creates or replaces the organization's retention storage record for a model provider. The organization is resolved from the authenticated caller's management context; the caller must be the organization's management account or a delegated administrator. Requires resolved organization-scope trusted access eligibility for a storage-capable program of the provider; otherwise returns ConflictException. Writes replace the whole record; the last write wins.
For customer_managed destinations, Amazon Bedrock validates the
caller's and service's access to the bucket and key before saving
the configuration. The bucket and key must be in the AWS Region where
you register the configuration. Validation failures reject the write.
8053 8054 8055 8056 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 8053 def put_organization_data_retention_storage(params = {}, = {}) req = build_request(:put_organization_data_retention_storage, params) req.send_request() end |
#put_project_data_retention_storage(params = {}) ⇒ Types::PutProjectDataRetentionStorageResponse
Creates or replaces a project's retention storage record for a model
provider. The project must be active in this AWS Region and owned by
the calling account. A missing or unowned project returns
ResourceNotFoundException; an archived project returns
ValidationException.
Requires applicable project, account, or organization approval for a
storage-capable trusted access program of the provider, with no
applicable revocation. Otherwise, the operation returns
ConflictException. Enrollment is not required to save the
configuration.
The request replaces the complete stored configuration. The last successful write wins.
For customer_managed destinations, Amazon Bedrock validates the
caller's and service's access to the bucket and key before saving
the configuration. The bucket and key must be in the AWS Region where
you register the configuration. Validation failures reject the write.
8137 8138 8139 8140 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 8137 def put_project_data_retention_storage(params = {}, = {}) req = build_request(:put_project_data_retention_storage, params) req.send_request() end |
#put_resource_policy(params = {}) ⇒ Types::PutResourcePolicyResponse
Adds a resource policy for a Bedrock resource.
8169 8170 8171 8172 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 8169 def put_resource_policy(params = {}, = {}) req = build_request(:put_resource_policy, params) req.send_request() end |
#put_trusted_access_program_account_enrollment(params = {}) ⇒ Types::PutTrustedAccessProgramAccountEnrollmentResponse
Sets your account's enrollment preference for a trusted access
program. Amazon Bedrock identifies the account from your authenticated
request. To enable enrollment, your account needs applicable approval
and no applicable revocation, including when you repeat an enabled
setting. Otherwise, Amazon Bedrock returns ConflictException and
preserves the stored setting. With the required permissions, you can
set disabled or inherit even if your account is ineligible or its
eligibility is revoked.
8212 8213 8214 8215 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 8212 def put_trusted_access_program_account_enrollment(params = {}, = {}) req = build_request(:put_trusted_access_program_account_enrollment, params) req.send_request() end |
#put_trusted_access_program_organization_enrollment(params = {}) ⇒ Types::PutTrustedAccessProgramOrganizationEnrollmentResponse
Sets the current organization's enrollment preference for a trusted
access program. The organization and payer account are derived from
the authenticated context. Every write requires operation permission
and management-account or Bedrock-specific delegated-administrator
authority. Enabling requires approval and no revocation for the
organization, including when repeating an enabled setting; otherwise
returns ConflictException and preserves the stored setting. Account
approval alone is insufficient. If you have the required permissions,
you can set the enrollment preference to disabled or inherit even
if your organization is ineligible or its eligibility is revoked.
8258 8259 8260 8261 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 8258 def put_trusted_access_program_organization_enrollment(params = {}, = {}) req = build_request(:put_trusted_access_program_organization_enrollment, params) req.send_request() end |
#put_trusted_access_program_project_enrollment(params = {}) ⇒ Types::PutTrustedAccessProgramProjectEnrollmentResponse
Sets a named project's enrollment preference for a trusted access program. The project must be active in this Region and owned by the calling account. Enabling requires applicable project, account, or organization approval and no applicable revocation, including when repeating an enabled setting; otherwise returns ConflictException and preserves the stored setting. Authorized disable and inherit writes are allowed while ineligible or revoked. Archived projects reject all writes with ValidationException.
8309 8310 8311 8312 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 8309 def put_trusted_access_program_project_enrollment(params = {}, = {}) req = build_request(:put_trusted_access_program_project_enrollment, params) req.send_request() end |
#put_use_case_for_model_access(params = {}) ⇒ Struct
Put usecase for model access.
8331 8332 8333 8334 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 8331 def put_use_case_for_model_access(params = {}, = {}) req = build_request(:put_use_case_for_model_access, params) req.send_request() end |
#register_marketplace_model_endpoint(params = {}) ⇒ Types::RegisterMarketplaceModelEndpointResponse
Registers an existing Amazon SageMaker endpoint with Amazon Bedrock Marketplace, allowing it to be used with Amazon Bedrock APIs.
8381 8382 8383 8384 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 8381 def register_marketplace_model_endpoint(params = {}, = {}) req = build_request(:register_marketplace_model_endpoint, params) req.send_request() end |
#start_automated_reasoning_policy_build_workflow(params = {}) ⇒ Types::StartAutomatedReasoningPolicyBuildWorkflowResponse
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.
8573 8574 8575 8576 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 8573 def start_automated_reasoning_policy_build_workflow(params = {}, = {}) req = build_request(:start_automated_reasoning_policy_build_workflow, params) req.send_request() end |
#start_automated_reasoning_policy_test_workflow(params = {}) ⇒ Types::StartAutomatedReasoningPolicyTestWorkflowResponse
Initiates a test workflow to validate Automated Reasoning policy tests. The workflow executes the specified tests against the policy and generates validation results.
8624 8625 8626 8627 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 8624 def start_automated_reasoning_policy_test_workflow(params = {}, = {}) req = build_request(:start_automated_reasoning_policy_test_workflow, params) req.send_request() end |
#start_trusted_access_program_account_application(params = {}) ⇒ Types::StartTrustedAccessProgramAccountApplicationResponse
Prepare a provider application handoff for the calling account. This does not submit an application, grant eligibility, or change enrollment. Programs without self-service applications return ValidationException with guidance to contact the AWS account team. Repeated calls can issue fresh tokens. Successful responses use Cache-Control: no-store.
8659 8660 8661 8662 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 8659 def start_trusted_access_program_account_application(params = {}, = {}) req = build_request(:start_trusted_access_program_account_application, params) req.send_request() end |
#start_trusted_access_program_organization_application(params = {}) ⇒ Types::StartTrustedAccessProgramOrganizationApplicationResponse
Prepare a provider application handoff for the calling account's current organization. Requires operation permission and management-account or Bedrock-specific delegated-administrator authority. This does not submit an application, grant eligibility, or change enrollment. Programs without self-service applications return ValidationException with guidance to contact the AWS account team. Repeated calls can issue fresh tokens. Successful responses use Cache-Control: no-store.
8696 8697 8698 8699 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 8696 def start_trusted_access_program_organization_application(params = {}, = {}) req = build_request(:start_trusted_access_program_organization_application, params) req.send_request() end |
#start_trusted_access_program_project_application(params = {}) ⇒ Types::StartTrustedAccessProgramProjectApplicationResponse
Prepare a provider application handoff for a named project. The project must be active in this Region and owned by the calling account. Archived projects return ValidationException. This does not submit an application, grant eligibility, or change enrollment. Programs without self-service applications return ValidationException with guidance to contact the AWS account team. Repeated calls can issue fresh tokens. Successful responses use Cache-Control: no-store.
8740 8741 8742 8743 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 8740 def start_trusted_access_program_project_application(params = {}, = {}) req = build_request(:start_trusted_access_program_project_application, params) req.send_request() end |
#stop_advanced_prompt_optimization_job(params = {}) ⇒ Struct
Stops an advanced prompt optimization job that is in progress.
8762 8763 8764 8765 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 8762 def stop_advanced_prompt_optimization_job(params = {}, = {}) req = build_request(:stop_advanced_prompt_optimization_job, params) req.send_request() end |
#stop_evaluation_job(params = {}) ⇒ Struct
Stops an evaluation job that is current being created or running.
8784 8785 8786 8787 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 8784 def stop_evaluation_job(params = {}, = {}) req = build_request(:stop_evaluation_job, params) req.send_request() end |
#stop_model_customization_job(params = {}) ⇒ Struct
Stops an active model customization job. For more information, see Custom models in the Amazon Bedrock User Guide.
8812 8813 8814 8815 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 8812 def stop_model_customization_job(params = {}, = {}) req = build_request(:stop_model_customization_job, params) req.send_request() end |
#stop_model_invocation_job(params = {}) ⇒ Struct
Stops a batch inference job. You're only charged for tokens that were already processed. For more information, see Stop a batch inference job.
8840 8841 8842 8843 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 8840 def stop_model_invocation_job(params = {}, = {}) req = build_request(:stop_model_invocation_job, params) req.send_request() end |
#tag_resource(params = {}) ⇒ Struct
Associate tags with a resource. For more information, see Tagging resources in the Amazon Bedrock User Guide.
8876 8877 8878 8879 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 8876 def tag_resource(params = {}, = {}) req = build_request(:tag_resource, params) req.send_request() end |
#untag_resource(params = {}) ⇒ Struct
Remove one or more tags from a resource. For more information, see Tagging resources in the Amazon Bedrock User Guide.
8907 8908 8909 8910 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 8907 def untag_resource(params = {}, = {}) req = build_request(:untag_resource, params) req.send_request() end |
#update_automated_reasoning_policy(params = {}) ⇒ Types::UpdateAutomatedReasoningPolicyResponse
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.
8985 8986 8987 8988 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 8985 def update_automated_reasoning_policy(params = {}, = {}) req = build_request(:update_automated_reasoning_policy, params) req.send_request() end |
#update_automated_reasoning_policy_annotations(params = {}) ⇒ Types::UpdateAutomatedReasoningPolicyAnnotationsResponse
Updates the annotations for an Automated Reasoning policy build workflow. This allows you to modify extracted rules, variables, and types before finalizing the policy.
9113 9114 9115 9116 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 9113 def update_automated_reasoning_policy_annotations(params = {}, = {}) req = build_request(:update_automated_reasoning_policy_annotations, params) req.send_request() end |
#update_automated_reasoning_policy_test_case(params = {}) ⇒ Types::UpdateAutomatedReasoningPolicyTestCaseResponse
Updates an existing Automated Reasoning policy test. You can modify the content, query, expected result, and confidence threshold.
9181 9182 9183 9184 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 9181 def update_automated_reasoning_policy_test_case(params = {}, = {}) req = build_request(:update_automated_reasoning_policy_test_case, params) req.send_request() end |
#update_custom_model_deployment(params = {}) ⇒ Types::UpdateCustomModelDeploymentResponse
Updates a custom model deployment with a new custom model. This allows you to deploy updated models without creating new deployment endpoints.
9217 9218 9219 9220 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 9217 def update_custom_model_deployment(params = {}, = {}) req = build_request(:update_custom_model_deployment, params) req.send_request() end |
#update_guardrail(params = {}) ⇒ Types::UpdateGuardrailResponse
Updates a guardrail with the values you specify.
Specify a
nameand optionaldescription.Specify messages for when the guardrail successfully blocks a prompt or a model response in the
blockedInputMessagingandblockedOutputsMessagingfields.Specify topics for the guardrail to deny in the
topicPolicyConfigobject. Each GuardrailTopicConfig object in thetopicsConfiglist pertains to one topic.Give a
nameanddescriptionso that the guardrail can properly identify the topic.Specify
DENYin thetypefield.(Optional) Provide up to five prompts that you would categorize as belonging to the topic in the
exampleslist.
Specify filter strengths for the harmful categories defined in Amazon Bedrock in the
contentPolicyConfigobject. Each GuardrailContentFilterConfig object in thefiltersConfiglist 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
typefield.Specify the strength of the filter for prompts in the
inputStrengthfield and for model responses in thestrengthfield of the GuardrailContentFilterConfig.
- (Optional) For security, include the ARN of a KMS key in the
kmsKeyIdfield.
9440 9441 9442 9443 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 9440 def update_guardrail(params = {}, = {}) req = build_request(:update_guardrail, params) req.send_request() end |
#update_marketplace_model_endpoint(params = {}) ⇒ Types::UpdateMarketplaceModelEndpointResponse
Updates the configuration of an existing endpoint for a model from Amazon Bedrock Marketplace.
9511 9512 9513 9514 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 9511 def update_marketplace_model_endpoint(params = {}, = {}) req = build_request(:update_marketplace_model_endpoint, params) req.send_request() end |
#update_project(params = {}) ⇒ Types::UpdateProjectResponse
Updates one mutable project field per call: exactly one of name or
dataRetention must be set. The default project and archived projects
cannot be updated.
9564 9565 9566 9567 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 9564 def update_project(params = {}, = {}) req = build_request(:update_project, params) req.send_request() end |
#update_provisioned_model_throughput(params = {}) ⇒ Struct
Updates the name or associated model for a Provisioned Throughput. For more information, see Provisioned Throughput in the Amazon Bedrock User Guide.
9612 9613 9614 9615 |
# File 'gems/aws-sdk-bedrock/lib/aws-sdk-bedrock/client.rb', line 9612 def update_provisioned_model_throughput(params = {}, = {}) req = build_request(:update_provisioned_model_throughput, params) req.send_request() end |