View Source AWS.Bedrock (aws-elixir v1.0.4)
Describes the API operations for creating, managing, fine-turning, and evaluating Amazon Bedrock models.
Link to this section Summary
Functions
Deletes a batch of evaluation jobs.
Creates an evaluation job.
Creates a guardrail to block topics and to implement safeguards for your generative AI applications.
Creates a version of the guardrail.
Creates an application inference profile to track metrics and costs when invoking a model.
Creates an endpoint for a model from Amazon Bedrock Marketplace.
Copies a model to another region so that it can be used there.
Creates a fine-tuning job to customize a base model.
Creates a model import job to import model that you have customized in other environments, such as Amazon SageMaker.
Creates a batch inference job to invoke a model on multiple prompts.
Creates dedicated throughput for a base or custom model with the model units and for the duration that you specify.
Deletes a custom model that you created earlier.
Deletes a guardrail.
Deletes a custom model that you imported earlier.
Deletes an application inference profile.
Deletes an endpoint for a model from Amazon Bedrock Marketplace.
Delete the invocation logging.
Deletes a Provisioned Throughput.
Deregisters an endpoint for a model from Amazon Bedrock Marketplace.
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.
Gets information about an evaluation job, such as the status of the job.
Get details about a Amazon Bedrock foundation model.
Gets details about a guardrail.
Gets properties associated with a customized model you imported.
Gets information about an inference profile.
Retrieves details about a specific endpoint for a model from Amazon Bedrock Marketplace.
Retrieves information about a model copy job.
Retrieves the properties associated with a model-customization job, including the status of the job.
Retrieves the properties associated with import model job, including the status of the job.
Gets details about a batch inference job.
Get the current configuration values for model invocation logging.
Retrieves details about a prompt router.
Returns details for a Provisioned Throughput.
Returns a list of the custom models that you have created with the
CreateModelCustomizationJob operation.
Lists all existing evaluation jobs.
Lists Amazon Bedrock foundation models that you can use.
Lists details about all the guardrails in an account.
Returns a list of models you've imported.
Returns a list of inference profiles that you can use.
Lists the endpoints for models from Amazon Bedrock Marketplace in your Amazon Web Services account.
Returns a list of model copy jobs that you have submitted.
Returns a list of model customization jobs that you have submitted.
Returns a list of import jobs you've submitted.
Lists all batch inference jobs in the account.
Retrieves a list of prompt routers.
Lists the Provisioned Throughputs in the account.
List the tags associated with the specified resource.
Set the configuration values for model invocation logging.
Registers an existing Amazon SageMaker endpoint with Amazon Bedrock Marketplace, allowing it to be used with Amazon Bedrock APIs.
Stops an evaluation job that is current being created or running.
Stops an active model customization job.
Stops a batch inference job.
Associate tags with a resource.
Remove one or more tags from a resource.
Updates a guardrail with the values you specify.
Updates the configuration of an existing endpoint for a model from Amazon Bedrock Marketplace.
Updates the name or associated model for a Provisioned Throughput.
Link to this section Functions
Deletes a batch of evaluation jobs.
An evaluation job can only be deleted if it has
following status FAILED, COMPLETED, and STOPPED.
You can request up to 25 model evaluation jobs be deleted in a single request.
Creates an evaluation job.
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.
create_guardrail_version(client, guardrail_identifier, input, options \\ [])
View SourceCreates 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.
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.
Creates an endpoint for a model from Amazon Bedrock Marketplace.
The endpoint is hosted by Amazon SageMaker.
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.
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.
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
Creates a batch inference job to invoke a model on multiple prompts.
Format your data according to Format your inference data and upload it to an Amazon S3 bucket. For more information, see Process multiple prompts with batch inference.
The response returns a jobArn that you can use to stop or get details about
the job.
Creates 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.
delete_custom_model(client, model_identifier, input, options \\ [])
View SourceDeletes a custom model that you created earlier.
For more information, see Custom models in the Amazon Bedrock User Guide.
delete_guardrail(client, guardrail_identifier, input, options \\ [])
View SourceDeletes a guardrail.
*
To delete a guardrail, only specify the ARN of the guardrail in the
guardrailIdentifier field. If you delete a guardrail, all of its versions will
be deleted.
*
To delete a version of a guardrail, specify the ARN of the guardrail in the
guardrailIdentifier field and the version in the guardrailVersion field.
delete_imported_model(client, model_identifier, input, options \\ [])
View SourceDeletes a custom model that you imported earlier.
For more information, see Import a customized model in the Amazon Bedrock User Guide.
delete_inference_profile(client, inference_profile_identifier, input, options \\ [])
View SourceDeletes 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.
delete_marketplace_model_endpoint(client, endpoint_arn, input, options \\ [])
View SourceDeletes an endpoint for a model from Amazon Bedrock Marketplace.
delete_model_invocation_logging_configuration(client, input, options \\ [])
View SourceDelete the invocation logging.
delete_provisioned_model_throughput(client, provisioned_model_id, input, options \\ [])
View SourceDeletes 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.
deregister_marketplace_model_endpoint(client, endpoint_arn, input, options \\ [])
View SourceDeregisters 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.
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.
Gets information about an evaluation job, such as the status of the job.
Get details about a Amazon Bedrock foundation model.
get_guardrail(client, guardrail_identifier, guardrail_version \\ nil, options \\ [])
View SourceGets details about a guardrail.
If you don't specify a version, the response returns details for the DRAFT
version.
Gets properties associated with a customized model you imported.
get_inference_profile(client, inference_profile_identifier, options \\ [])
View SourceGets 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.
get_marketplace_model_endpoint(client, endpoint_arn, options \\ [])
View SourceRetrieves details about a specific endpoint for a model from Amazon Bedrock Marketplace.
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.
get_model_customization_job(client, job_identifier, options \\ [])
View SourceRetrieves 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.
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.
Gets details about a batch inference job.
For more information, see Monitor batch inference jobs
Get the current configuration values for model invocation logging.
Retrieves details about a prompt router.
get_provisioned_model_throughput(client, provisioned_model_id, options \\ [])
View SourceReturns details for a Provisioned Throughput.
For more information, see Provisioned Throughput in the Amazon Bedrock User Guide.
list_custom_models(client, base_model_arn_equals \\ nil, creation_time_after \\ nil, creation_time_before \\ nil, foundation_model_arn_equals \\ nil, is_owned \\ nil, max_results \\ nil, name_contains \\ nil, next_token \\ nil, sort_by \\ nil, sort_order \\ nil, options \\ [])
View SourceReturns 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.
list_evaluation_jobs(client, application_type_equals \\ nil, creation_time_after \\ nil, creation_time_before \\ nil, max_results \\ nil, name_contains \\ nil, next_token \\ nil, sort_by \\ nil, sort_order \\ nil, status_equals \\ nil, options \\ [])
View SourceLists all existing evaluation jobs.
list_foundation_models(client, by_customization_type \\ nil, by_inference_type \\ nil, by_output_modality \\ nil, by_provider \\ nil, options \\ [])
View SourceLists 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.
list_guardrails(client, guardrail_identifier \\ nil, max_results \\ nil, next_token \\ nil, options \\ [])
View SourceLists 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.
list_imported_models(client, creation_time_after \\ nil, creation_time_before \\ nil, max_results \\ nil, name_contains \\ nil, next_token \\ nil, sort_by \\ nil, sort_order \\ nil, options \\ [])
View SourceReturns 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.
list_inference_profiles(client, max_results \\ nil, next_token \\ nil, type_equals \\ nil, options \\ [])
View SourceReturns 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.
list_marketplace_model_endpoints(client, max_results \\ nil, model_source_equals \\ nil, next_token \\ nil, options \\ [])
View SourceLists the endpoints for models from Amazon Bedrock Marketplace in your Amazon Web Services account.
list_model_copy_jobs(client, creation_time_after \\ nil, creation_time_before \\ nil, max_results \\ nil, next_token \\ nil, sort_by \\ nil, sort_order \\ nil, source_account_equals \\ nil, source_model_arn_equals \\ nil, status_equals \\ nil, target_model_name_contains \\ nil, options \\ [])
View SourceReturns 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.
list_model_customization_jobs(client, creation_time_after \\ nil, creation_time_before \\ nil, max_results \\ nil, name_contains \\ nil, next_token \\ nil, sort_by \\ nil, sort_order \\ nil, status_equals \\ nil, options \\ [])
View SourceReturns 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.
list_model_import_jobs(client, creation_time_after \\ nil, creation_time_before \\ nil, max_results \\ nil, name_contains \\ nil, next_token \\ nil, sort_by \\ nil, sort_order \\ nil, status_equals \\ nil, options \\ [])
View SourceReturns 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.
list_model_invocation_jobs(client, max_results \\ nil, name_contains \\ nil, next_token \\ nil, sort_by \\ nil, sort_order \\ nil, status_equals \\ nil, submit_time_after \\ nil, submit_time_before \\ nil, options \\ [])
View SourceLists all batch inference jobs in the account.
For more information, see View details about a batch inference job.
list_prompt_routers(client, max_results \\ nil, next_token \\ nil, options \\ [])
View SourceRetrieves a list of prompt routers.
list_provisioned_model_throughputs(client, creation_time_after \\ nil, creation_time_before \\ nil, max_results \\ nil, model_arn_equals \\ nil, name_contains \\ nil, next_token \\ nil, sort_by \\ nil, sort_order \\ nil, status_equals \\ nil, options \\ [])
View SourceLists the Provisioned Throughputs in the account.
For more information, see Provisioned Throughput in the Amazon Bedrock User Guide.
List the tags associated with the specified resource.
For more information, see Tagging resources in the Amazon Bedrock User Guide.
put_model_invocation_logging_configuration(client, input, options \\ [])
View SourceSet the configuration values for model invocation logging.
register_marketplace_model_endpoint(client, endpoint_identifier, input, options \\ [])
View SourceRegisters an existing Amazon SageMaker endpoint with Amazon Bedrock Marketplace, allowing it to be used with Amazon Bedrock APIs.
Stops an evaluation job that is current being created or running.
stop_model_customization_job(client, job_identifier, input, options \\ [])
View SourceStops an active model customization job.
For more information, see Custom models in the Amazon Bedrock User Guide.
stop_model_invocation_job(client, job_identifier, input, options \\ [])
View SourceStops a batch inference job.
You're only charged for tokens that were already processed. For more information, see Stop a batch inference job.
Associate tags with a resource.
For more information, see Tagging resources in the Amazon Bedrock User Guide.
Remove one or more tags from a resource.
For more information, see Tagging resources in the Amazon Bedrock User Guide.
update_guardrail(client, guardrail_identifier, input, options \\ [])
View SourceUpdates a guardrail with the values you specify.
*
Specify a name and optional description.
*
Specify messages for when the guardrail successfully blocks a prompt or a model
response in the blockedInputMessaging and blockedOutputsMessaging fields.
*
Specify topics for the guardrail to deny in the topicPolicyConfig object. Each
GuardrailTopicConfig object in the topicsConfig list pertains to one topic.
*Give a name and description so that the guardrail can properly identify the
topic.
*Specify DENY in the type field.
*(Optional) Provide up to five prompts that you would categorize as belonging to
the topic in the examples list.
*
Specify filter strengths for the harmful categories defined in Amazon Bedrock in
the contentPolicyConfig object. Each
GuardrailContentFilterConfig
object in the filtersConfig list pertains to a harmful category. For more
information, see Content filters.
For more information about the fields in a content filter, see
GuardrailContentFilterConfig.
*Specify the category in the type field.
*Specify the strength of the filter for prompts in the inputStrength field and
for model responses in the strength field of the
GuardrailContentFilterConfig.
*
(Optional) For security, include the ARN of a KMS key in the kmsKeyId field.
update_marketplace_model_endpoint(client, endpoint_arn, input, options \\ [])
View SourceUpdates the configuration of an existing endpoint for a model from Amazon Bedrock Marketplace.
update_provisioned_model_throughput(client, provisioned_model_id, input, options \\ [])
View SourceUpdates the name or associated model for a Provisioned Throughput.
For more information, see Provisioned Throughput in the Amazon Bedrock User Guide.