interface ContentFilter 🔹

Language	Type name
.NET	`Amazon.CDK.AWS.Bedrock.Alpha.ContentFilter`
Go	`github.com/aws/aws-cdk-go/awsbedrockalpha/v2#ContentFilter`
Java	`software.amazon.awscdk.services.bedrock.alpha.ContentFilter`
Python	`aws_cdk.aws_bedrock_alpha.ContentFilter`
TypeScript (source)	`@aws-cdk/aws-bedrock-alpha` » `ContentFilter`

Interface to declare a content filter.

Example

// Create a guardrail to filter inappropriate content
const guardrail = new bedrock.Guardrail(this, 'bedrockGuardrails', {
  guardrailName: 'my-BedrockGuardrails',
  description: 'Legal ethical guardrails.',
});

guardrail.addContentFilter({
  type: bedrock.ContentFilterType.SEXUAL,
  inputStrength: bedrock.ContentFilterStrength.HIGH,
  outputStrength: bedrock.ContentFilterStrength.MEDIUM,
});

// Create an agent with the guardrail
const agentWithGuardrail = new bedrock.Agent(this, 'AgentWithGuardrail', {
  foundationModel: bedrock.BedrockFoundationModel.ANTHROPIC_CLAUDE_HAIKU_V1_0,
  instruction: 'You are a helpful and friendly agent that answers questions about literature.',
  guardrail: guardrail,
});

Properties

Name	Type	Description
inputStrength🔹	`ContentFilterStrength`	The strength of the content filter to apply to prompts / user input.
outputStrength🔹	`ContentFilterStrength`	The strength of the content filter to apply to model responses.
type🔹	`ContentFilterType`	The type of harmful category that the content filter is applied to.
inputAction?🔹	`GuardrailAction`	The action to take when content is detected in the input.
inputEnabled?🔹	`boolean`	Whether the content filter is enabled for input.
inputModalities?🔹	`ModalityType[]`	The input modalities to apply the content filter to.
outputAction?🔹	`GuardrailAction`	The action to take when content is detected in the output.
outputEnabled?🔹	`boolean`	Whether the content filter is enabled for output.
outputModalities?🔹	`ModalityType[]`	The output modalities to apply the content filter to.

inputStrength🔹

Type: ContentFilterStrength

The strength of the content filter to apply to prompts / user input.

outputStrength🔹

Type: ContentFilterStrength

The strength of the content filter to apply to model responses.

type🔹

Type: ContentFilterType

The type of harmful category that the content filter is applied to.

inputAction?🔹

Type: GuardrailAction (optional, default: GuardrailAction.BLOCK)

The action to take when content is detected in the input.

inputEnabled?🔹

Type: boolean (optional, default: true)

Whether the content filter is enabled for input.

inputModalities?🔹

Type: ModalityType[] (optional, default: undefined - Applies to text modality)

The input modalities to apply the content filter to.

outputAction?🔹

Type: GuardrailAction (optional, default: GuardrailAction.BLOCK)

The action to take when content is detected in the output.

outputEnabled?🔹