Class: Aws::Bedrock::Types::GuardrailWordConfig

Inherits:
Struct
  • Object
show all
Includes:
Structure
Defined in:
lib/aws-sdk-bedrock/types.rb

Overview

A word to configure for the guardrail.

Constant Summary collapse

SENSITIVE =
[:input_action, :output_action]

Instance Attribute Summary collapse

Instance Attribute Details

#input_actionString

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.

Returns:

  • (String)


4857
4858
4859
4860
4861
4862
4863
4864
4865
# File 'lib/aws-sdk-bedrock/types.rb', line 4857

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

#input_enabledBoolean

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

Returns:

  • (Boolean)


4857
4858
4859
4860
4861
4862
4863
4864
4865
# File 'lib/aws-sdk-bedrock/types.rb', line 4857

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

#output_actionString

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.

Returns:

  • (String)


4857
4858
4859
4860
4861
4862
4863
4864
4865
# File 'lib/aws-sdk-bedrock/types.rb', line 4857

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

#output_enabledBoolean

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.

Returns:

  • (Boolean)


4857
4858
4859
4860
4861
4862
4863
4864
4865
# File 'lib/aws-sdk-bedrock/types.rb', line 4857

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

#textString

Text of the word configured for the guardrail to block.

Returns:

  • (String)


4857
4858
4859
4860
4861
4862
4863
4864
4865
# File 'lib/aws-sdk-bedrock/types.rb', line 4857

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