interface WordConfigProperty

Language	Type name
.NET	`Amazon.CDK.AWS.Bedrock.CfnGuardrail.WordConfigProperty`
Go	`github.com/aws/aws-cdk-go/awscdk/v2/awsbedrock#CfnGuardrail_WordConfigProperty`
Java	`software.amazon.awscdk.services.bedrock.CfnGuardrail.WordConfigProperty`
Python	`aws_cdk.aws_bedrock.CfnGuardrail.WordConfigProperty`
TypeScript	`aws-cdk-lib` » `aws_bedrock` » `CfnGuardrail` » `WordConfigProperty`

A word to configure for the guardrail.

Example

// The code below shows an example of how to instantiate this type.
// The values are placeholders you should change.
import { aws_bedrock as bedrock } from 'aws-cdk-lib';
const wordConfigProperty: bedrock.CfnGuardrail.WordConfigProperty = {
  text: 'text',

  // the properties below are optional
  inputAction: 'inputAction',
  inputEnabled: false,
  outputAction: 'outputAction',
  outputEnabled: false,
};

Properties

Name	Type	Description
text	`string`	Text of the word configured for the guardrail to block.
inputAction?	`string`	Specifies the action to take when harmful content is detected in the input. Supported values include:.
inputEnabled?	`boolean \|` `IResolvable`	Specifies whether to enable guardrail evaluation on the intput.
outputAction?	`string`	Specifies the action to take when harmful content is detected in the output. Supported values include:.
outputEnabled?	`boolean \|` `IResolvable`	Specifies whether to enable guardrail evaluation on the output.

text

Type: string

Text of the word configured for the guardrail to block.

inputAction?

Type: string (optional)

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.

inputEnabled?

Type: boolean | IResolvable (optional)

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.

outputAction?

Type: string (optional)

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.

outputEnabled?