GuardrailRegex
The regular expression configured for the guardrail.
Contents
- action
-
The action taken when a match to the regular expression is detected.
Type: String
Valid Values:
BLOCK | ANONYMIZE | NONERequired: Yes
- name
-
The name of the regular expression for the guardrail.
Type: String
Length Constraints: Minimum length of 1. Maximum length of 100.
Required: Yes
- pattern
-
The pattern of the regular expression configured for the guardrail.
Type: String
Length Constraints: Minimum length of 1. Maximum length of 500.
Required: Yes
- description
-
The description of the regular expression for the guardrail.
Type: String
Length Constraints: Minimum length of 1. Maximum length of 1000.
Required: No
- inputAction
-
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.
Type: String
Valid Values:
BLOCK | ANONYMIZE | NONERequired: No
-
- inputEnabled
-
Indicates whether guardrail evaluation is enabled on the input. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
Type: Boolean
Required: No
- outputAction
-
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.
Type: String
Valid Values:
BLOCK | ANONYMIZE | NONERequired: No
-
- outputEnabled
-
Indicates whether guardrail evaluation is enabled on the output. When disabled, you aren't charged for the evaluation. The evaluation doesn't appear in the response.
Type: Boolean
Required: No
See Also
For more information about using this API in one of the language-specific AWS SDKs, see the following: