AWS::Bedrock::Guardrail TopicConfig - AWS CloudFormation

This is the new AWS CloudFormation Template Reference Guide. Please update your bookmarks and links. For help getting started with CloudFormation, see the AWS CloudFormation User Guide.

AWS::Bedrock::Guardrail TopicConfig

Details about topics for the guardrail to identify and deny.

Syntax

To declare this entity in your AWS CloudFormation template, use the following syntax:

JSON

{ "Definition" : String, "Examples" : [ String, ... ], "InputAction" : String, "InputEnabled" : Boolean, "Name" : String, "OutputAction" : String, "OutputEnabled" : Boolean, "Type" : String }

YAML

Definition: String Examples: - String InputAction: String InputEnabled: Boolean Name: String OutputAction: String OutputEnabled: Boolean Type: String

Properties

Definition

A definition of the topic to deny.

Required: Yes

Type: String

Minimum: 1

Maximum: 200

Update requires: No interruption

Examples

A list of prompts, each of which is an example of a prompt that can be categorized as belonging to the topic.

Required: No

Type: Array of String

Maximum: 100

Minimum: 1 | 0

Update requires: No interruption

InputAction

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.

Required: No

Type: String

Allowed values: BLOCK | NONE

Update requires: No interruption

InputEnabled

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.

Required: No

Type: Boolean

Update requires: No interruption

Name

The name of the topic to deny.

Required: Yes

Type: String

Pattern: ^[0-9a-zA-Z-_ !?.]+$

Minimum: 1

Maximum: 100

Update requires: No interruption

OutputAction

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.

Required: No

Type: String

Allowed values: BLOCK | NONE

Update requires: No interruption

OutputEnabled

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.

Required: No

Type: Boolean

Update requires: No interruption

Type

Specifies to deny the topic.

Required: Yes

Type: String

Allowed values: DENY

Update requires: No interruption