GuardrailContentFilter - Amazon Bedrock
ContentsSee Also
Services or capabilities described in AWS documentation might vary by Region. To see the differences applicable to the AWS European Sovereign Cloud Region, see the AWS European Sovereign Cloud User Guide.

GuardrailContentFilter

The content filter for a guardrail.

Contents

action

The guardrail action.

Type: String

Valid Values: BLOCKED | NONE

Required: Yes

confidence

The guardrail confidence.

Type: String

Valid Values: NONE | LOW | MEDIUM | HIGH

Required: Yes

type

The guardrail type.

Type: String

Valid Values: INSULTS | HATE | SEXUAL | VIOLENCE | MISCONDUCT | PROMPT_ATTACK

Required: Yes

detected

Indicates whether content that breaches the guardrail configuration is detected.

Type: Boolean

Required: No

filterStrength

The filter strength setting for the guardrail content filter.

Type: String

Valid Values: NONE | LOW | MEDIUM | HIGH

Required: No

See Also

For more information about using this API in one of the language-specific AWS SDKs, see the following: