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

Details of the content filter used in the Guardrail.

Contents

action

The action placed on the content by the Guardrail filter.

Type: String

Valid Values: BLOCKED

Required: No

confidence

The confidence level regarding the content detected in the filter by the Guardrail.

Type: String

Valid Values: NONE | LOW | MEDIUM | HIGH

Required: No

type

The type of content detected in the filter by the Guardrail.

Type: String

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

Required: No

See Also

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