Bedrock

create_evaluation_job(evaluation_config, inference_config, job_name, output_data_config, role_arn)
create_evaluation_job(evaluation_config, inference_config, job_name, output_data_config, role_arn, params::Dict{String,<:Any})

API operation for creating and managing Amazon Bedrock automatic model evaluation jobs and model evaluation jobs that use human workers. To learn more about the requirements for creating a model evaluation job see, Model evaluations.

Arguments

• evaluation_config: Specifies whether the model evaluation job is automatic or uses human worker.
• inference_config: Specify the models you want to use in your model evaluation job. Automatic model evaluation jobs support a single model, and model evaluation job that use human workers support two models.
• job_name: The name of the model evaluation job. Model evaluation job names must unique with your AWS account, and your account's AWS region.
• output_data_config: An object that defines where the results of model evaluation job will be saved in Amazon S3.
• role_arn: The Amazon Resource Name (ARN) of an IAM service role that Amazon Bedrock can assume to perform tasks on your behalf. The service role must have Amazon Bedrock as the service principal, and provide access to any Amazon S3 buckets specified in the EvaluationConfig object. To pass this role to Amazon Bedrock, the caller of this API must have the iam:PassRole permission. To learn more about the required permissions, see Required permissions.

Optional Parameters

Optional parameters can be passed as a params::Dict{String,<:Any}. Valid keys are:

• "clientRequestToken": A unique, case-sensitive identifier to ensure that the API request completes no more than one time. If this token matches a previous request, Amazon Bedrock ignores the request, but does not return an error. For more information, see Ensuring idempotency.
• "customerEncryptionKeyId": Specify your customer managed key ARN that will be used to encrypt your model evaluation job.
• "jobDescription": A description of the model evaluation job.
• "jobTags": Tags to attach to the model evaluation job.

create_guardrail(blocked_input_messaging, blocked_outputs_messaging, name)
create_guardrail(blocked_input_messaging, blocked_outputs_messaging, name, params::Dict{String,<:Any})

Creates a guardrail to block topics and to filter out harmful content. 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. (Optional) Attach any tags to the guardrail in the tags object. For more information, see Tag resources.

Arguments

• blocked_input_messaging: The message to return when the guardrail blocks a prompt.
• blocked_outputs_messaging: The message to return when the guardrail blocks a model response.
• name: The name to give the guardrail.

Optional Parameters

Optional parameters can be passed as a params::Dict{String,<:Any}. Valid keys are:

• "clientRequestToken": A unique, case-sensitive identifier to ensure that the API request completes no more than once. If this token matches a previous request, Amazon Bedrock ignores the request, but does not return an error. For more information, see Ensuring idempotency in the Amazon S3 User Guide.
• "contentPolicyConfig": The content filter policies to configure for the guardrail.
• "description": A description of the guardrail.
• "kmsKeyId": The ARN of the KMS key that you use to encrypt the guardrail.
• "sensitiveInformationPolicyConfig": The sensitive information policy to configure for the guardrail.
• "tags": The tags that you want to attach to the guardrail.
• "topicPolicyConfig": The topic policies to configure for the guardrail.
• "wordPolicyConfig": The word policy you configure for the guardrail.

create_guardrail_version(guardrail_identifier)
create_guardrail_version(guardrail_identifier, params::Dict{String,<:Any})

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.

Arguments

• guardrail_identifier: The unique identifier of the guardrail.

Optional Parameters

Optional parameters can be passed as a params::Dict{String,<:Any}. Valid keys are:

• "clientRequestToken": A unique, case-sensitive identifier to ensure that the API request completes no more than once. If this token matches a previous request, Amazon Bedrock ignores the request, but does not return an error. For more information, see Ensuring idempotency in the Amazon S3 User Guide.
• "description": A description of the guardrail version.

create_model_customization_job(base_model_identifier, custom_model_name, hyper_parameters, job_name, output_data_config, role_arn, training_data_config)
create_model_customization_job(base_model_identifier, custom_model_name, hyper_parameters, job_name, output_data_config, role_arn, training_data_config, params::Dict{String,<:Any})

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.

Arguments

• base_model_identifier: Name of the base model.
• custom_model_name: A name for the resulting custom model.
• hyper_parameters: Parameters related to tuning the model. For details on the format for different models, see Custom model hyperparameters.
• job_name: A name for the fine-tuning job.
• output_data_config: S3 location for the output data.
• role_arn: The Amazon Resource Name (ARN) of an IAM service role that Amazon Bedrock can assume to perform tasks on your behalf. For example, during model training, Amazon Bedrock needs your permission to read input data from an S3 bucket, write model artifacts to an S3 bucket. To pass this role to Amazon Bedrock, the caller of this API must have the iam:PassRole permission.
• training_data_config: Information about the training dataset.

Optional Parameters

Optional parameters can be passed as a params::Dict{String,<:Any}. Valid keys are:

• "clientRequestToken": A unique, case-sensitive identifier to ensure that the API request completes no more than one time. If this token matches a previous request, Amazon Bedrock ignores the request, but does not return an error. For more information, see Ensuring idempotency.
• "customModelKmsKeyId": The custom model is encrypted at rest using this key.
• "customModelTags": Tags to attach to the resulting custom model.
• "customizationType": The customization type.
• "jobTags": Tags to attach to the job.
• "validationDataConfig": Information about the validation dataset.
• "vpcConfig": VPC configuration (optional). Configuration parameters for the private Virtual Private Cloud (VPC) that contains the resources you are using for this job.

create_provisioned_model_throughput(model_id, model_units, provisioned_model_name)
create_provisioned_model_throughput(model_id, model_units, provisioned_model_name, params::Dict{String,<:Any})

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.

Arguments

• model_id: The Amazon Resource Name (ARN) or name of the model to associate with this Provisioned Throughput. For a list of models for which you can purchase Provisioned Throughput, see Amazon Bedrock model IDs for purchasing Provisioned Throughput in the Amazon Bedrock User Guide.
• model_units: Number of model units to allocate. A model unit delivers a specific throughput level for the specified model. The throughput level of a model unit specifies the total number of input and output tokens that it can process and generate within a span of one minute. By default, your account has no model units for purchasing Provisioned Throughputs with commitment. You must first visit the Amazon Web Services support center to request MUs. For model unit quotas, see Provisioned Throughput quotas in the Amazon Bedrock User Guide. For more information about what an MU specifies, contact your Amazon Web Services account manager.
• provisioned_model_name: The name for this Provisioned Throughput.

Optional Parameters

Optional parameters can be passed as a params::Dict{String,<:Any}. Valid keys are:

• "clientRequestToken": A unique, case-sensitive identifier to ensure that the API request completes no more than one time. If this token matches a previous request, Amazon Bedrock ignores the request, but does not return an error. For more information, see Ensuring idempotency in the Amazon S3 User Guide.
• "commitmentDuration": The commitment duration requested for the Provisioned Throughput. Billing occurs hourly and is discounted for longer commitment terms. To request a no-commit Provisioned Throughput, omit this field. Custom models support all levels of commitment. To see which base models support no commitment, see Supported regions and models for Provisioned Throughput in the Amazon Bedrock User Guide
• "tags": Tags to associate with this Provisioned Throughput.

delete_custom_model(model_identifier)
delete_custom_model(model_identifier, params::Dict{String,<:Any})

Deletes a custom model that you created earlier. For more information, see Custom models in the Amazon Bedrock User Guide.

Arguments

• model_identifier: Name of the model to delete.

delete_guardrail(guardrail_identifier)
delete_guardrail(guardrail_identifier, params::Dict{String,<:Any})

Deletes a guardrail. To delete a guardrail, only specify the ARN of the guardrail in the guardrailIdentifier field. If you delete a guardrail, all of its versions will be deleted. To delete a version of a guardrail, specify the ARN of the guardrail in the guardrailIdentifier field and the version in the guardrailVersion field.

Arguments

• guardrail_identifier: The unique identifier of the guardrail.

Optional Parameters

Optional parameters can be passed as a params::Dict{String,<:Any}. Valid keys are:

• "guardrailVersion": The version of the guardrail.

delete_model_invocation_logging_configuration()
delete_model_invocation_logging_configuration(params::Dict{String,<:Any})

Delete the invocation logging.

delete_provisioned_model_throughput(provisioned_model_id)
delete_provisioned_model_throughput(provisioned_model_id, params::Dict{String,<:Any})

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.

Arguments

• provisioned_model_id: The Amazon Resource Name (ARN) or name of the Provisioned Throughput.

get_custom_model(model_identifier)
get_custom_model(model_identifier, params::Dict{String,<:Any})

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.

Arguments

• model_identifier: Name or Amazon Resource Name (ARN) of the custom model.

get_evaluation_job(job_identifier)
get_evaluation_job(job_identifier, params::Dict{String,<:Any})

Retrieves the properties associated with a model evaluation job, including the status of the job. For more information, see Model evaluations.

Arguments

• job_identifier: The Amazon Resource Name (ARN) of the model evaluation job.

get_foundation_model(model_identifier)
get_foundation_model(model_identifier, params::Dict{String,<:Any})

Get details about a Amazon Bedrock foundation model.

Arguments

• model_identifier: The model identifier.

get_guardrail(guardrail_identifier)
get_guardrail(guardrail_identifier, params::Dict{String,<:Any})

Gets details about a guardrail. If you don't specify a version, the response returns details for the DRAFT version.

Arguments

• guardrail_identifier: The unique identifier of the guardrail for which to get details.

Optional Parameters

Optional parameters can be passed as a params::Dict{String,<:Any}. Valid keys are:

• "guardrailVersion": The version of the guardrail for which to get details. If you don't specify a version, the response returns details for the DRAFT version.

get_model_customization_job(job_identifier)
get_model_customization_job(job_identifier, params::Dict{String,<:Any})

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.

Arguments

• job_identifier: Identifier for the customization job.

get_model_invocation_logging_configuration()
get_model_invocation_logging_configuration(params::Dict{String,<:Any})

Get the current configuration values for model invocation logging.

get_provisioned_model_throughput(provisioned_model_id)
get_provisioned_model_throughput(provisioned_model_id, params::Dict{String,<:Any})

Returns details for a Provisioned Throughput. For more information, see Provisioned Throughput in the Amazon Bedrock User Guide.

Arguments

• provisioned_model_id: The Amazon Resource Name (ARN) or name of the Provisioned Throughput.

list_custom_models()
list_custom_models(params::Dict{String,<:Any})

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.

Optional Parameters

Optional parameters can be passed as a params::Dict{String,<:Any}. Valid keys are:

• "baseModelArnEquals": Return custom models only if the base model Amazon Resource Name (ARN) matches this parameter.
• "creationTimeAfter": Return custom models created after the specified time.
• "creationTimeBefore": Return custom models created before the specified time.
• "foundationModelArnEquals": Return custom models only if the foundation model Amazon Resource Name (ARN) matches this parameter.
• "maxResults": Maximum number of results to return in the response.
• "nameContains": Return custom models only if the job name contains these characters.
• "nextToken": Continuation token from the previous response, for Amazon Bedrock to list the next set of results.
• "sortBy": The field to sort by in the returned list of models.
• "sortOrder": The sort order of the results.

list_evaluation_jobs()
list_evaluation_jobs(params::Dict{String,<:Any})

Lists model evaluation jobs.

Optional Parameters

Optional parameters can be passed as a params::Dict{String,<:Any}. Valid keys are:

• "creationTimeAfter": A filter that includes model evaluation jobs created after the time specified.
• "creationTimeBefore": A filter that includes model evaluation jobs created prior to the time specified.
• "maxResults": The maximum number of results to return.
• "nameContains": Query parameter string for model evaluation job names.
• "nextToken": Continuation token from the previous response, for Amazon Bedrock to list the next set of results.
• "sortBy": Allows you to sort model evaluation jobs by when they were created.
• "sortOrder": How you want the order of jobs sorted.
• "statusEquals": Only return jobs where the status condition is met.

list_foundation_models()
list_foundation_models(params::Dict{String,<:Any})

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.

Optional Parameters

Optional parameters can be passed as a params::Dict{String,<:Any}. Valid keys are:

• "byCustomizationType": Return models that support the customization type that you specify. For more information, see Custom models in the Amazon Bedrock User Guide.
• "byInferenceType": Return models that support the inference type that you specify. For more information, see Provisioned Throughput in the Amazon Bedrock User Guide.
• "byOutputModality": Return models that support the output modality that you specify.
• "byProvider": Return models belonging to the model provider that you specify.

list_guardrails()
list_guardrails(params::Dict{String,<:Any})

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.

Optional Parameters

Optional parameters can be passed as a params::Dict{String,<:Any}. Valid keys are:

• "guardrailIdentifier": The unique identifier of the guardrail.
• "maxResults": The maximum number of results to return in the response.
• "nextToken": If there are more results than were returned in the response, the response returns a nextToken that you can send in another ListGuardrails request to see the next batch of results.

list_model_customization_jobs()
list_model_customization_jobs(params::Dict{String,<:Any})

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.

Optional Parameters

Optional parameters can be passed as a params::Dict{String,<:Any}. Valid keys are:

• "creationTimeAfter": Return customization jobs created after the specified time.
• "creationTimeBefore": Return customization jobs created before the specified time.
• "maxResults": Maximum number of results to return in the response.
• "nameContains": Return customization jobs only if the job name contains these characters.
• "nextToken": Continuation token from the previous response, for Amazon Bedrock to list the next set of results.
• "sortBy": The field to sort by in the returned list of jobs.
• "sortOrder": The sort order of the results.
• "statusEquals": Return customization jobs with the specified status.

list_provisioned_model_throughputs()
list_provisioned_model_throughputs(params::Dict{String,<:Any})

Lists the Provisioned Throughputs in the account. For more information, see Provisioned Throughput in the Amazon Bedrock User Guide.

Optional Parameters

Optional parameters can be passed as a params::Dict{String,<:Any}. Valid keys are:

• "creationTimeAfter": A filter that returns Provisioned Throughputs created after the specified time.
• "creationTimeBefore": A filter that returns Provisioned Throughputs created before the specified time.
• "maxResults": THe maximum number of results to return in the response. If there are more results than the number you specified, the response returns a nextToken value. To see the next batch of results, send the nextToken value in another list request.
• "modelArnEquals": A filter that returns Provisioned Throughputs whose model Amazon Resource Name (ARN) is equal to the value that you specify.
• "nameContains": A filter that returns Provisioned Throughputs if their name contains the expression that you specify.
• "nextToken": If there are more results than the number you specified in the maxResults field, the response returns a nextToken value. To see the next batch of results, specify the nextToken value in this field.
• "sortBy": The field by which to sort the returned list of Provisioned Throughputs.
• "sortOrder": The sort order of the results.
• "statusEquals": A filter that returns Provisioned Throughputs if their statuses matches the value that you specify.

list_tags_for_resource(resource_arn)
list_tags_for_resource(resource_arn, params::Dict{String,<:Any})

List the tags associated with the specified resource. For more information, see Tagging resources in the Amazon Bedrock User Guide.

Arguments

• resource_arn: The Amazon Resource Name (ARN) of the resource.

put_model_invocation_logging_configuration(logging_config)
put_model_invocation_logging_configuration(logging_config, params::Dict{String,<:Any})

Set the configuration values for model invocation logging.

Arguments

• logging_config: The logging configuration values to set.

stop_evaluation_job(job_identifier)
stop_evaluation_job(job_identifier, params::Dict{String,<:Any})

Stops an in progress model evaluation job.

Arguments

• job_identifier: The ARN of the model evaluation job you want to stop.

stop_model_customization_job(job_identifier)
stop_model_customization_job(job_identifier, params::Dict{String,<:Any})

Stops an active model customization job. For more information, see Custom models in the Amazon Bedrock User Guide.

Arguments

• job_identifier: Job identifier of the job to stop.

tag_resource(resource_arn, tags)
tag_resource(resource_arn, tags, params::Dict{String,<:Any})

Associate tags with a resource. For more information, see Tagging resources in the Amazon Bedrock User Guide.

Arguments

• resource_arn: The Amazon Resource Name (ARN) of the resource to tag.
• tags: Tags to associate with the resource.

untag_resource(resource_arn, tag_keys)
untag_resource(resource_arn, tag_keys, params::Dict{String,<:Any})

Remove one or more tags from a resource. For more information, see Tagging resources in the Amazon Bedrock User Guide.

Arguments

• resource_arn: The Amazon Resource Name (ARN) of the resource to untag.
• tag_keys: Tag keys of the tags to remove from the resource.

update_guardrail(blocked_input_messaging, blocked_outputs_messaging, guardrail_identifier, name)
update_guardrail(blocked_input_messaging, blocked_outputs_messaging, guardrail_identifier, name, params::Dict{String,<:Any})

Updates a guardrail with the values you specify. Specify a name and optional description. Specify messages for when the guardrail successfully blocks a prompt or a model response in the blockedInputMessaging and blockedOutputsMessaging fields. Specify topics for the guardrail to deny in the topicPolicyConfig object. Each GuardrailTopicConfig object in the topicsConfig list pertains to one topic. Give a name and description so that the guardrail can properly identify the topic. Specify DENY in the type field. (Optional) Provide up to five prompts that you would categorize as belonging to the topic in the examples list. Specify filter strengths for the harmful categories defined in Amazon Bedrock in the contentPolicyConfig object. Each GuardrailContentFilterConfig object in the filtersConfig list pertains to a harmful category. For more information, see Content filters. For more information about the fields in a content filter, see GuardrailContentFilterConfig. Specify the category in the type field. Specify the strength of the filter for prompts in the inputStrength field and for model responses in the strength field of the GuardrailContentFilterConfig. (Optional) For security, include the ARN of a KMS key in the kmsKeyId field. (Optional) Attach any tags to the guardrail in the tags object. For more information, see Tag resources.

Arguments

• blocked_input_messaging: The message to return when the guardrail blocks a prompt.
• blocked_outputs_messaging: The message to return when the guardrail blocks a model response.
• guardrail_identifier: The unique identifier of the guardrail
• name: A name for the guardrail.

Optional Parameters

Optional parameters can be passed as a params::Dict{String,<:Any}. Valid keys are:

• "contentPolicyConfig": The content policy to configure for the guardrail.
• "description": A description of the guardrail.
• "kmsKeyId": The ARN of the KMS key with which to encrypt the guardrail.
• "sensitiveInformationPolicyConfig": The sensitive information policy to configure for the guardrail.
• "topicPolicyConfig": The topic policy to configure for the guardrail.
• "wordPolicyConfig": The word policy to configure for the guardrail.

update_provisioned_model_throughput(provisioned_model_id)
update_provisioned_model_throughput(provisioned_model_id, params::Dict{String,<:Any})

Updates the name or associated model for a Provisioned Throughput. For more information, see Provisioned Throughput in the Amazon Bedrock User Guide.

Arguments

• provisioned_model_id: The Amazon Resource Name (ARN) or name of the Provisioned Throughput to update.

Optional Parameters

Optional parameters can be passed as a params::Dict{String,<:Any}. Valid keys are:

• "desiredModelId": The Amazon Resource Name (ARN) of the new model to associate with this Provisioned Throughput. You can't specify this field if this Provisioned Throughput is associated with a base model. If this Provisioned Throughput is associated with a custom model, you can specify one of the following options: The base model from which the custom model was customized. Another custom model that was customized from the same base model as the custom model.
• "desiredProvisionedModelName": The new name for this Provisioned Throughput.