Amazon Bedrock¶

Description¶

Describes the API operations for creating, managing, fine-turning, and evaluating Amazon Bedrock models.

Usage¶

bedrock(config = list(), credentials = list(), endpoint = NULL, region = NULL)

Arguments¶

config

Optional configuration of credentials, endpoint, and/or region.
- credentials:
  - creds:
    - access_key_id: AWS access key ID
    - secret_access_key: AWS secret access key
    - session_token: AWS temporary session token
  - profile: The name of a profile to use. If not given, then the default profile is used.
  - anonymous: Set anonymous credentials.
- endpoint: The complete URL to use for the constructed client.
- region: The AWS Region used in instantiating the client.
- close_connection: Immediately close all HTTP connections.
- timeout: The time in seconds till a timeout exception is thrown when attempting to make a connection. The default is 60 seconds.
- s3_force_path_style: Set this to true to force the request to use path-style addressing, i.e. http://s3.amazonaws.com/BUCKET/KEY.
- sts_regional_endpoint: Set sts regional endpoint resolver to regional or legacy https://docs.aws.amazon.com/sdkref/latest/guide/feature-sts-regionalized-endpoints.html
- use_dual_stack: Set this to true to use the dualstack (IPv4 and IPv6) endpoint for a service, where available, falling back to the regular endpoint when it isn't. Defaults to the AWS_USE_DUALSTACK_ENDPOINT environment variable when unset.
credentials

Optional credentials shorthand for the config parameter
- creds:
  - access_key_id: AWS access key ID
  - secret_access_key: AWS secret access key
  - session_token: AWS temporary session token
- profile: The name of a profile to use. If not given, then the default profile is used.
- anonymous: Set anonymous credentials.
endpoint

Optional shorthand for complete URL to use for the constructed client.
region

Optional shorthand for AWS Region used in instantiating the client.

Value¶

A client for the service. You can call the service's operations using syntax like svc$operation(...), where svc is the name you've assigned to the client. The available operations are listed in the Operations section.

Service syntax¶

svc <- bedrock(
  config = list(
    credentials = list(
      creds = list(
        access_key_id = "string",
        secret_access_key = "string",
        session_token = "string"
      ),
      profile = "string",
      anonymous = "logical"
    ),
    endpoint = "string",
    region = "string",
    close_connection = "logical",
    timeout = "numeric",
    s3_force_path_style = "logical",
    sts_regional_endpoint = "string",
    use_dual_stack = "logical"
  ),
  credentials = list(
    creds = list(
      access_key_id = "string",
      secret_access_key = "string",
      session_token = "string"
    ),
    profile = "string",
    anonymous = "logical"
  ),
  endpoint = "string",
  region = "string"
)

Operations¶

`batch_delete_advanced_prompt_optimization_job`	Deletes one or more advanced prompt optimization jobs
`batch_delete_evaluation_job`	Deletes a batch of evaluation jobs
`cancel_automated_reasoning_policy_build_workflow`	Cancels a running Automated Reasoning policy build workflow
`create_advanced_prompt_optimization_job`	Creates an advanced prompt optimization job
`create_automated_reasoning_policy`	Creates an Automated Reasoning policy for Amazon Bedrock Guardrails
`create_automated_reasoning_policy_test_case`	Creates a test for an Automated Reasoning policy
`create_automated_reasoning_policy_version`	Creates a new version of an existing Automated Reasoning policy
`create_custom_model`	Creates a new custom model in Amazon Bedrock
`create_custom_model_deployment`	Deploys a custom model for on-demand inference in Amazon Bedrock
`create_evaluation_job`	Creates an evaluation job
`create_foundation_model_agreement`	Request a model access agreement for the specified model
`create_guardrail`	Creates a guardrail to block topics and to implement safeguards for your generative AI applications
`create_guardrail_version`	Creates a version of the guardrail
`create_inference_profile`	Creates an application inference profile to track metrics and costs when invoking a model
`create_marketplace_model_endpoint`	Creates an endpoint for a model from Amazon Bedrock Marketplace
`create_model_copy_job`	Copies a model to another region so that it can be used there
`create_model_customization_job`	Creates a fine-tuning job to customize a base model
`create_model_import_job`	Creates a model import job to import model that you have customized in other environments, such as Amazon SageMaker
`create_model_invocation_job`	Creates a batch inference job to invoke a model on multiple prompts
`create_prompt_router`	Creates a prompt router that manages the routing of requests between multiple foundation models based on the routing criteria
`create_provisioned_model_throughput`	Creates dedicated throughput for a base or custom model with the model units and for the duration that you specify
`delete_automated_reasoning_policy`	Deletes an Automated Reasoning policy or policy version
`delete_automated_reasoning_policy_build_workflow`	Deletes an Automated Reasoning policy build workflow and its associated artifacts
`delete_automated_reasoning_policy_test_case`	Deletes an Automated Reasoning policy test
`delete_custom_model`	Deletes a custom model that you created earlier
`delete_custom_model_deployment`	Deletes a custom model deployment
`delete_enforced_guardrail_configuration`	Deletes the account-level enforced guardrail configuration
`delete_foundation_model_agreement`	Delete the model access agreement for the specified model
`delete_guardrail`	Deletes a guardrail
`delete_imported_model`	Deletes a custom model that you imported earlier
`delete_inference_profile`	Deletes an application inference profile
`delete_marketplace_model_endpoint`	Deletes an endpoint for a model from Amazon Bedrock Marketplace
`delete_model_invocation_logging_configuration`	Delete the invocation logging
`delete_prompt_router`	Deletes a specified prompt router
`delete_provisioned_model_throughput`	Deletes a Provisioned Throughput
`delete_resource_policy`	Deletes a previously created Bedrock resource policy
`deregister_marketplace_model_endpoint`	Deregisters an endpoint for a model from Amazon Bedrock Marketplace
`export_automated_reasoning_policy_version`	Exports the policy definition for an Automated Reasoning policy version
`get_account_data_retention`	Returns the account-wide data retention mode for Amazon Bedrock
`get_advanced_prompt_optimization_job`	Gets information about an advanced prompt optimization job
`get_automated_reasoning_policy`	Retrieves details about an Automated Reasoning policy or policy version
`get_automated_reasoning_policy_annotations`	Retrieves the current annotations for an Automated Reasoning policy build workflow
`get_automated_reasoning_policy_build_workflow`	Retrieves detailed information about an Automated Reasoning policy build workflow, including its status, configuration, and metadata
`get_automated_reasoning_policy_build_workflow_result_assets`	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`	Retrieves the next test scenario for validating an Automated Reasoning policy
`get_automated_reasoning_policy_test_case`	Retrieves details about a specific Automated Reasoning policy test
`get_automated_reasoning_policy_test_result`	Retrieves the test result for a specific Automated Reasoning policy test
`get_custom_model`	Get the properties associated with a Amazon Bedrock custom model that you have created
`get_custom_model_deployment`	Retrieves information about a custom model deployment, including its status, configuration, and metadata
`get_evaluation_job`	Gets information about an evaluation job, such as the status of the job
`get_foundation_model`	Get details about a Amazon Bedrock foundation model
`get_foundation_model_availability`	Get information about the Foundation model availability
`get_guardrail`	Gets details about a guardrail
`get_imported_model`	Gets properties associated with a customized model you imported
`get_inference_profile`	Gets information about an inference profile
`get_marketplace_model_endpoint`	Retrieves details about a specific endpoint for a model from Amazon Bedrock Marketplace
`get_model_copy_job`	Retrieves information about a model copy job
`get_model_customization_job`	Retrieves the properties associated with a model-customization job, including the status of the job
`get_model_import_job`	Retrieves the properties associated with import model job, including the status of the job
`get_model_invocation_job`	Gets details about a batch inference job
`get_model_invocation_logging_configuration`	Get the current configuration values for model invocation logging
`get_prompt_router`	Retrieves details about a prompt router
`get_provisioned_model_throughput`	Returns details for a Provisioned Throughput
`get_resource_policy`	Gets the resource policy document for a Bedrock resource
`get_use_case_for_model_access`	Get usecase for model access
`list_advanced_prompt_optimization_jobs`	Lists the advanced prompt optimization jobs in your account
`list_automated_reasoning_policies`	Lists all Automated Reasoning policies in your account, with optional filtering by policy ARN
`list_automated_reasoning_policy_build_workflows`	Lists all build workflows for an Automated Reasoning policy, showing the history of policy creation and modification attempts
`list_automated_reasoning_policy_test_cases`	Lists tests for an Automated Reasoning policy
`list_automated_reasoning_policy_test_results`	Lists test results for an Automated Reasoning policy, showing how the policy performed against various test scenarios and validation checks
`list_custom_model_deployments`	Lists custom model deployments in your account
`list_custom_models`	Returns a list of the custom models that you have created with the CreateModelCustomizationJob operation
`list_enforced_guardrails_configuration`	Lists the account-level enforced guardrail configurations
`list_evaluation_jobs`	Lists all existing evaluation jobs
`list_foundation_model_agreement_offers`	Get the offers associated with the specified model
`list_foundation_models`	Lists Amazon Bedrock foundation models that you can use
`list_guardrails`	Lists details about all the guardrails in an account
`list_imported_models`	Returns a list of models you've imported
`list_inference_profiles`	Returns a list of inference profiles that you can use
`list_marketplace_model_endpoints`	Lists the endpoints for models from Amazon Bedrock Marketplace in your Amazon Web Services account
`list_model_copy_jobs`	Returns a list of model copy jobs that you have submitted
`list_model_customization_jobs`	Returns a list of model customization jobs that you have submitted
`list_model_import_jobs`	Returns a list of import jobs you've submitted
`list_model_invocation_jobs`	Lists all batch inference jobs in the account
`list_prompt_routers`	Retrieves a list of prompt routers
`list_provisioned_model_throughputs`	Lists the Provisioned Throughputs in the account
`list_tags_for_resource`	List the tags associated with the specified resource
`put_account_data_retention`	Sets the account-wide data retention mode for Amazon Bedrock
`put_enforced_guardrail_configuration`	Sets the account-level enforced guardrail configuration
`put_model_invocation_logging_configuration`	Set the configuration values for model invocation logging
`put_resource_policy`	Adds a resource policy for a Bedrock resource
`put_use_case_for_model_access`	Put usecase for model access
`register_marketplace_model_endpoint`	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`	Starts a new build workflow for an Automated Reasoning policy
`start_automated_reasoning_policy_test_workflow`	Initiates a test workflow to validate Automated Reasoning policy tests
`stop_advanced_prompt_optimization_job`	Stops an advanced prompt optimization job that is in progress
`stop_evaluation_job`	Stops an evaluation job that is current being created or running
`stop_model_customization_job`	Stops an active model customization job
`stop_model_invocation_job`	Stops a batch inference job
`tag_resource`	Associate tags with a resource
`untag_resource`	Remove one or more tags from a resource
`update_automated_reasoning_policy`	Updates an existing Automated Reasoning policy with new rules, variables, or configuration
`update_automated_reasoning_policy_annotations`	Updates the annotations for an Automated Reasoning policy build workflow
`update_automated_reasoning_policy_test_case`	Updates an existing Automated Reasoning policy test
`update_custom_model_deployment`	Updates a custom model deployment with a new custom model
`update_guardrail`	Updates a guardrail with the values you specify
`update_marketplace_model_endpoint`	Updates the configuration of an existing endpoint for a model from Amazon Bedrock Marketplace
`update_provisioned_model_throughput`	Updates the name or associated model for a Provisioned Throughput

Examples¶

svc <- bedrock()
svc$batch_delete_advanced_prompt_optimization_job(
  Foo = 123
)