Class: Aws::Bedrock::Types::CreateGuardrailRequest

Inherits:

Struct

• Object
• Struct
• Aws::Bedrock::Types::CreateGuardrailRequest

Includes:

Structure

Defined in:

lib/aws-sdk-bedrock/types.rb

Overview

See Also:

• AWS API Documentation

Constant Summary

SENSITIVE =

[:name, :description, :blocked_input_messaging, :blocked_outputs_messaging]

Instance Attribute Summary

• #automated_reasoning_policy_config ⇒ Types::GuardrailAutomatedReasoningPolicyConfig

  Optional configuration for integrating Automated Reasoning policies with the new guardrail.

• #blocked_input_messaging ⇒ String

  The message to return when the guardrail blocks a prompt.

• #blocked_outputs_messaging ⇒ String

  The message to return when the guardrail blocks a model response.

• #client_request_token ⇒ String

  A unique, case-sensitive identifier to ensure that the API request completes no more than once.

• #content_policy_config ⇒ Types::GuardrailContentPolicyConfig

  The content filter policies to configure for the guardrail.

• #contextual_grounding_policy_config ⇒ Types::GuardrailContextualGroundingPolicyConfig

  The contextual grounding policy configuration used to create a guardrail.

• #cross_region_config ⇒ Types::GuardrailCrossRegionConfig

  The system-defined guardrail profile that you’re using with your guardrail.

• #description ⇒ String

  A description of the guardrail.

• #kms_key_id ⇒ String

  The ARN of the KMS key that you use to encrypt the guardrail.

• #name ⇒ String

  The name to give the guardrail.

• #sensitive_information_policy_config ⇒ Types::GuardrailSensitiveInformationPolicyConfig

  The sensitive information policy to configure for the guardrail.

• #tags ⇒ Array<Types::Tag>

  The tags that you want to attach to the guardrail.

• #topic_policy_config ⇒ Types::GuardrailTopicPolicyConfig

  The topic policies to configure for the guardrail.

• #word_policy_config ⇒ Types::GuardrailWordPolicyConfig

  The word policy you configure for the guardrail.

Instance Attribute Details

#automated_reasoning_policy_config ⇒ Types::GuardrailAutomatedReasoningPolicyConfig

Optional configuration for integrating Automated Reasoning policies with the new guardrail.

Returns:

• (Types::GuardrailAutomatedReasoningPolicyConfig)

# File 'lib/aws-sdk-bedrock/types.rb', line 2975

class CreateGuardrailRequest < Struct.new(
  :name,
  :description,
  :topic_policy_config,
  :content_policy_config,
  :word_policy_config,
  :sensitive_information_policy_config,
  :contextual_grounding_policy_config,
  :automated_reasoning_policy_config,
  :cross_region_config,
  :blocked_input_messaging,
  :blocked_outputs_messaging,
  :kms_key_id,
  :tags,
  :client_request_token)
  SENSITIVE = [:name, :description, :blocked_input_messaging, :blocked_outputs_messaging]
  include Aws::Structure
end

#blocked_input_messaging ⇒ String

The message to return when the guardrail blocks a prompt.

Returns:

• (String)

# File 'lib/aws-sdk-bedrock/types.rb', line 2975

class CreateGuardrailRequest < Struct.new(
  :name,
  :description,
  :topic_policy_config,
  :content_policy_config,
  :word_policy_config,
  :sensitive_information_policy_config,
  :contextual_grounding_policy_config,
  :automated_reasoning_policy_config,
  :cross_region_config,
  :blocked_input_messaging,
  :blocked_outputs_messaging,
  :kms_key_id,
  :tags,
  :client_request_token)
  SENSITIVE = [:name, :description, :blocked_input_messaging, :blocked_outputs_messaging]
  include Aws::Structure
end

#blocked_outputs_messaging ⇒ String

The message to return when the guardrail blocks a model response.

Returns:

• (String)

# File 'lib/aws-sdk-bedrock/types.rb', line 2975

class CreateGuardrailRequest < Struct.new(
  :name,
  :description,
  :topic_policy_config,
  :content_policy_config,
  :word_policy_config,
  :sensitive_information_policy_config,
  :contextual_grounding_policy_config,
  :automated_reasoning_policy_config,
  :cross_region_config,
  :blocked_input_messaging,
  :blocked_outputs_messaging,
  :kms_key_id,
  :tags,
  :client_request_token)
  SENSITIVE = [:name, :description, :blocked_input_messaging, :blocked_outputs_messaging]
  include Aws::Structure
end

#client_request_token ⇒ String

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*.

**A suitable default value is auto-generated.** You should normally not need to pass this option.

[1]: docs.aws.amazon.com/AWSEC2/latest/APIReference/Run_Instance_Idempotency.html

Returns:

• (String)

# File 'lib/aws-sdk-bedrock/types.rb', line 2975

class CreateGuardrailRequest < Struct.new(
  :name,
  :description,
  :topic_policy_config,
  :content_policy_config,
  :word_policy_config,
  :sensitive_information_policy_config,
  :contextual_grounding_policy_config,
  :automated_reasoning_policy_config,
  :cross_region_config,
  :blocked_input_messaging,
  :blocked_outputs_messaging,
  :kms_key_id,
  :tags,
  :client_request_token)
  SENSITIVE = [:name, :description, :blocked_input_messaging, :blocked_outputs_messaging]
  include Aws::Structure
end

#content_policy_config ⇒ Types::GuardrailContentPolicyConfig

The content filter policies to configure for the guardrail.

Returns:

• (Types::GuardrailContentPolicyConfig)

# File 'lib/aws-sdk-bedrock/types.rb', line 2975

class CreateGuardrailRequest < Struct.new(
  :name,
  :description,
  :topic_policy_config,
  :content_policy_config,
  :word_policy_config,
  :sensitive_information_policy_config,
  :contextual_grounding_policy_config,
  :automated_reasoning_policy_config,
  :cross_region_config,
  :blocked_input_messaging,
  :blocked_outputs_messaging,
  :kms_key_id,
  :tags,
  :client_request_token)
  SENSITIVE = [:name, :description, :blocked_input_messaging, :blocked_outputs_messaging]
  include Aws::Structure
end

#contextual_grounding_policy_config ⇒ Types::GuardrailContextualGroundingPolicyConfig

The contextual grounding policy configuration used to create a guardrail.

Returns:

• (Types::GuardrailContextualGroundingPolicyConfig)

# File 'lib/aws-sdk-bedrock/types.rb', line 2975

class CreateGuardrailRequest < Struct.new(
  :name,
  :description,
  :topic_policy_config,
  :content_policy_config,
  :word_policy_config,
  :sensitive_information_policy_config,
  :contextual_grounding_policy_config,
  :automated_reasoning_policy_config,
  :cross_region_config,
  :blocked_input_messaging,
  :blocked_outputs_messaging,
  :kms_key_id,
  :tags,
  :client_request_token)
  SENSITIVE = [:name, :description, :blocked_input_messaging, :blocked_outputs_messaging]
  include Aws::Structure
end

#cross_region_config ⇒ Types::GuardrailCrossRegionConfig

The system-defined guardrail profile that you’re using with your guardrail. Guardrail profiles define the destination Amazon Web Services Regions where guardrail inference requests can be automatically routed.

For more information, see the [Amazon Bedrock User Guide].

[1]: docs.aws.amazon.com/bedrock/latest/userguide/guardrails-cross-region.html

Returns:

• (Types::GuardrailCrossRegionConfig)

# File 'lib/aws-sdk-bedrock/types.rb', line 2975

class CreateGuardrailRequest < Struct.new(
  :name,
  :description,
  :topic_policy_config,
  :content_policy_config,
  :word_policy_config,
  :sensitive_information_policy_config,
  :contextual_grounding_policy_config,
  :automated_reasoning_policy_config,
  :cross_region_config,
  :blocked_input_messaging,
  :blocked_outputs_messaging,
  :kms_key_id,
  :tags,
  :client_request_token)
  SENSITIVE = [:name, :description, :blocked_input_messaging, :blocked_outputs_messaging]
  include Aws::Structure
end

#description ⇒ String

A description of the guardrail.

Returns:

• (String)

# File 'lib/aws-sdk-bedrock/types.rb', line 2975

class CreateGuardrailRequest < Struct.new(
  :name,
  :description,
  :topic_policy_config,
  :content_policy_config,
  :word_policy_config,
  :sensitive_information_policy_config,
  :contextual_grounding_policy_config,
  :automated_reasoning_policy_config,
  :cross_region_config,
  :blocked_input_messaging,
  :blocked_outputs_messaging,
  :kms_key_id,
  :tags,
  :client_request_token)
  SENSITIVE = [:name, :description, :blocked_input_messaging, :blocked_outputs_messaging]
  include Aws::Structure
end

#kms_key_id ⇒ String

The ARN of the KMS key that you use to encrypt the guardrail.

Returns:

• (String)

# File 'lib/aws-sdk-bedrock/types.rb', line 2975

class CreateGuardrailRequest < Struct.new(
  :name,
  :description,
  :topic_policy_config,
  :content_policy_config,
  :word_policy_config,
  :sensitive_information_policy_config,
  :contextual_grounding_policy_config,
  :automated_reasoning_policy_config,
  :cross_region_config,
  :blocked_input_messaging,
  :blocked_outputs_messaging,
  :kms_key_id,
  :tags,
  :client_request_token)
  SENSITIVE = [:name, :description, :blocked_input_messaging, :blocked_outputs_messaging]
  include Aws::Structure
end

#name ⇒ String

The name to give the guardrail.

Returns:

• (String)

# File 'lib/aws-sdk-bedrock/types.rb', line 2975

class CreateGuardrailRequest < Struct.new(
  :name,
  :description,
  :topic_policy_config,
  :content_policy_config,
  :word_policy_config,
  :sensitive_information_policy_config,
  :contextual_grounding_policy_config,
  :automated_reasoning_policy_config,
  :cross_region_config,
  :blocked_input_messaging,
  :blocked_outputs_messaging,
  :kms_key_id,
  :tags,
  :client_request_token)
  SENSITIVE = [:name, :description, :blocked_input_messaging, :blocked_outputs_messaging]
  include Aws::Structure
end

#sensitive_information_policy_config ⇒ Types::GuardrailSensitiveInformationPolicyConfig

The sensitive information policy to configure for the guardrail.

Returns:

• (Types::GuardrailSensitiveInformationPolicyConfig)

# File 'lib/aws-sdk-bedrock/types.rb', line 2975

class CreateGuardrailRequest < Struct.new(
  :name,
  :description,
  :topic_policy_config,
  :content_policy_config,
  :word_policy_config,
  :sensitive_information_policy_config,
  :contextual_grounding_policy_config,
  :automated_reasoning_policy_config,
  :cross_region_config,
  :blocked_input_messaging,
  :blocked_outputs_messaging,
  :kms_key_id,
  :tags,
  :client_request_token)
  SENSITIVE = [:name, :description, :blocked_input_messaging, :blocked_outputs_messaging]
  include Aws::Structure
end

#tags ⇒ Array<Types::Tag>

The tags that you want to attach to the guardrail.

Returns:

• (Array<Types::Tag>)

# File 'lib/aws-sdk-bedrock/types.rb', line 2975

class CreateGuardrailRequest < Struct.new(
  :name,
  :description,
  :topic_policy_config,
  :content_policy_config,
  :word_policy_config,
  :sensitive_information_policy_config,
  :contextual_grounding_policy_config,
  :automated_reasoning_policy_config,
  :cross_region_config,
  :blocked_input_messaging,
  :blocked_outputs_messaging,
  :kms_key_id,
  :tags,
  :client_request_token)
  SENSITIVE = [:name, :description, :blocked_input_messaging, :blocked_outputs_messaging]
  include Aws::Structure
end

#topic_policy_config ⇒ Types::GuardrailTopicPolicyConfig

The topic policies to configure for the guardrail.

Returns:

• (Types::GuardrailTopicPolicyConfig)

# File 'lib/aws-sdk-bedrock/types.rb', line 2975

class CreateGuardrailRequest < Struct.new(
  :name,
  :description,
  :topic_policy_config,
  :content_policy_config,
  :word_policy_config,
  :sensitive_information_policy_config,
  :contextual_grounding_policy_config,
  :automated_reasoning_policy_config,
  :cross_region_config,
  :blocked_input_messaging,
  :blocked_outputs_messaging,
  :kms_key_id,
  :tags,
  :client_request_token)
  SENSITIVE = [:name, :description, :blocked_input_messaging, :blocked_outputs_messaging]
  include Aws::Structure
end

#word_policy_config ⇒ Types::GuardrailWordPolicyConfig

The word policy you configure for the guardrail.

Returns:

• (Types::GuardrailWordPolicyConfig)

# File 'lib/aws-sdk-bedrock/types.rb', line 2975

class CreateGuardrailRequest < Struct.new(
  :name,
  :description,
  :topic_policy_config,
  :content_policy_config,
  :word_policy_config,
  :sensitive_information_policy_config,
  :contextual_grounding_policy_config,
  :automated_reasoning_policy_config,
  :cross_region_config,
  :blocked_input_messaging,
  :blocked_outputs_messaging,
  :kms_key_id,
  :tags,
  :client_request_token)
  SENSITIVE = [:name, :description, :blocked_input_messaging, :blocked_outputs_messaging]
  include Aws::Structure
end