Class: Aws::Bedrock::Types::GuardrailManagedWordsConfig

Inherits:

Struct

• Object
• Struct
• Aws::Bedrock::Types::GuardrailManagedWordsConfig

Includes:

Structure

Defined in:

lib/aws-sdk-bedrock/types.rb

Overview

The managed word list to configure for the guardrail.

See Also:

• AWS API Documentation

Constant Summary

SENSITIVE =

[:input_action, :output_action]

Instance Attribute Summary

• #input_action ⇒ String

  Specifies the action to take when harmful content is detected in the input.

• #input_enabled ⇒ Boolean

  Specifies whether to enable guardrail evaluation on the input.

• #output_action ⇒ String

  Specifies the action to take when harmful content is detected in the output.

• #output_enabled ⇒ Boolean

  Specifies whether to enable guardrail evaluation on the output.

• #type ⇒ String

  The managed word type to configure for the guardrail.

Instance Attribute Details

#input_action ⇒ String

Specifies the action to take when harmful content is detected in the input. Supported values include:

• ‘BLOCK` – Block the content and replace it with blocked messaging.

• ‘NONE` – Take no action but return detection information in the trace response.

# File 'lib/aws-sdk-bedrock/types.rb', line 4003

class GuardrailManagedWordsConfig < Struct.new(
  :type,
  :input_action,
  :output_action,
  :input_enabled,
  :output_enabled)
  SENSITIVE = [:input_action, :output_action]
  include Aws::Structure
end

#input_enabled ⇒ Boolean

Specifies whether to enable guardrail evaluation on the input. When disabled, you aren’t charged for the evaluation. The evaluation doesn’t appear in the response.

# File 'lib/aws-sdk-bedrock/types.rb', line 4003

class GuardrailManagedWordsConfig < Struct.new(
  :type,
  :input_action,
  :output_action,
  :input_enabled,
  :output_enabled)
  SENSITIVE = [:input_action, :output_action]
  include Aws::Structure
end

#output_action ⇒ String

Specifies the action to take when harmful content is detected in the output. Supported values include:

• ‘BLOCK` – Block the content and replace it with blocked messaging.

• ‘NONE` – Take no action but return detection information in the trace response.

# File 'lib/aws-sdk-bedrock/types.rb', line 4003

class GuardrailManagedWordsConfig < Struct.new(
  :type,
  :input_action,
  :output_action,
  :input_enabled,
  :output_enabled)
  SENSITIVE = [:input_action, :output_action]
  include Aws::Structure
end

#output_enabled ⇒ Boolean

Specifies whether to enable guardrail evaluation on the output. When disabled, you aren’t charged for the evaluation. The evaluation doesn’t appear in the response.

# File 'lib/aws-sdk-bedrock/types.rb', line 4003

class GuardrailManagedWordsConfig < Struct.new(
  :type,
  :input_action,
  :output_action,
  :input_enabled,
  :output_enabled)
  SENSITIVE = [:input_action, :output_action]
  include Aws::Structure
end

#type ⇒ String

The managed word type to configure for the guardrail.

# File 'lib/aws-sdk-bedrock/types.rb', line 4003

class GuardrailManagedWordsConfig < Struct.new(
  :type,
  :input_action,
  :output_action,
  :input_enabled,
  :output_enabled)
  SENSITIVE = [:input_action, :output_action]
  include Aws::Structure
end