class CfnGuardrailPropsMixin

Language	Type name
.NET	Amazon.CDK.Mixins.Preview.AWS.Bedrock.Mixins.CfnGuardrailPropsMixin
Go	github.com/aws/aws-cdk-go/awscdkmixinspreview/v2/awsbedrock/mixins#CfnGuardrailPropsMixin
Java	software.amazon.awscdk.mixins.preview.services.bedrock.mixins.CfnGuardrailPropsMixin
Python	aws_cdk.mixins_preview.aws_bedrock.mixins.CfnGuardrailPropsMixin
TypeScript	@aws-cdk/mixins-preview » aws_bedrock » mixins » CfnGuardrailPropsMixin

Implements IMixin

Extends Mixin

Creates a guardrail to detect and filter harmful content in your generative AI application.

Amazon Bedrock Guardrails provides the following safeguards (also known as policies) to detect and filter harmful content:

• Content filters - Detect and filter harmful text or image content in input prompts or model responses. Filtering is done based on detection of certain predefined harmful content categories: Hate, Insults, Sexual, Violence, Misconduct and Prompt Attack. You also can adjust the filter strength for each of these categories.
• Denied topics - Define a set of topics that are undesirable in the context of your application. The filter will help block them if detected in user queries or model responses.
• Word filters - Configure filters to help block undesirable words, phrases, and profanity (exact match). Such words can include offensive terms, competitor names, etc.
• Sensitive information filters - Configure filters to help block or mask sensitive information, such as personally identifiable information (PII), or custom regex in user inputs and model responses. Blocking or masking is done based on probabilistic detection of sensitive information in standard formats in entities such as SSN number, Date of Birth, address, etc. This also allows configuring regular expression based detection of patterns for identifiers.
• Contextual grounding check - Help detect and filter hallucinations in model responses based on grounding in a source and relevance to the user query.

For more information, see How Amazon Bedrock Guardrails works .

See also: http://docs.aws.amazon.com/AWSCloudFormation/latest/UserGuide/aws-resource-bedrock-guardrail.html

Example

// The code below shows an example of how to instantiate this type.
// The values are placeholders you should change.
import { mixins } from '@aws-cdk/mixins-preview';
import { mixins as bedrock_mixins } from '@aws-cdk/mixins-preview/aws-bedrock';
const cfnGuardrailPropsMixin = new bedrock_mixins.CfnGuardrailPropsMixin({
  automatedReasoningPolicyConfig: {
    confidenceThreshold: 123,
    policies: ['policies'],
  },
  blockedInputMessaging: 'blockedInputMessaging',
  blockedOutputsMessaging: 'blockedOutputsMessaging',
  contentPolicyConfig: {
    contentFiltersTierConfig: {
      tierName: 'tierName',
    },
    filtersConfig: [{
      inputAction: 'inputAction',
      inputEnabled: false,
      inputModalities: ['inputModalities'],
      inputStrength: 'inputStrength',
      outputAction: 'outputAction',
      outputEnabled: false,
      outputModalities: ['outputModalities'],
      outputStrength: 'outputStrength',
      type: 'type',
    }],
  },
  contextualGroundingPolicyConfig: {
    filtersConfig: [{
      action: 'action',
      enabled: false,
      threshold: 123,
      type: 'type',
    }],
  },
  crossRegionConfig: {
    guardrailProfileArn: 'guardrailProfileArn',
  },
  description: 'description',
  kmsKeyArn: 'kmsKeyArn',
  name: 'name',
  sensitiveInformationPolicyConfig: {
    piiEntitiesConfig: [{
      action: 'action',
      inputAction: 'inputAction',
      inputEnabled: false,
      outputAction: 'outputAction',
      outputEnabled: false,
      type: 'type',
    }],
    regexesConfig: [{
      action: 'action',
      description: 'description',
      inputAction: 'inputAction',
      inputEnabled: false,
      name: 'name',
      outputAction: 'outputAction',
      outputEnabled: false,
      pattern: 'pattern',
    }],
  },
  tags: [{
    key: 'key',
    value: 'value',
  }],
  topicPolicyConfig: {
    topicsConfig: [{
      definition: 'definition',
      examples: ['examples'],
      inputAction: 'inputAction',
      inputEnabled: false,
      name: 'name',
      outputAction: 'outputAction',
      outputEnabled: false,
      type: 'type',
    }],
    topicsTierConfig: {
      tierName: 'tierName',
    },
  },
  wordPolicyConfig: {
    managedWordListsConfig: [{
      inputAction: 'inputAction',
      inputEnabled: false,
      outputAction: 'outputAction',
      outputEnabled: false,
      type: 'type',
    }],
    wordsConfig: [{
      inputAction: 'inputAction',
      inputEnabled: false,
      outputAction: 'outputAction',
      outputEnabled: false,
      text: 'text',
    }],
  },
}, /* all optional props */ {
  strategy: mixins.PropertyMergeStrategy.OVERRIDE,
});

Initializer

new CfnGuardrailPropsMixin(props: CfnGuardrailMixinProps, options?: CfnPropertyMixinOptions)

Parameters

• props CfnGuardrailMixinProps — L1 properties to apply.
• options CfnPropertyMixinOptions — Mixin options.

Create a mixin to apply properties to AWS::Bedrock::Guardrail.

Properties

Name	Type	Description
props	CfnGuardrailMixinProps
strategy	PropertyMergeStrategy
static CFN_PROPERTY_KEYS	string[]

---

props

Type: CfnGuardrailMixinProps

---

strategy

Type: PropertyMergeStrategy

---

static CFN_PROPERTY_KEYS

Type: string[]

Methods

Name	Description
applyTo(construct)	Apply the mixin properties to the construct.
supports(construct)	Check if this mixin supports the given construct.

---

applyTo(construct)

public applyTo(construct: IConstruct): IConstruct

Parameters

• construct IConstruct

Returns

• IConstruct

Apply the mixin properties to the construct.

---

supports(construct)

public supports(construct: IConstruct): boolean

Parameters

• construct IConstruct

Returns

• boolean

Check if this mixin supports the given construct.