ContentPolicyFilter
Contains information about a content policy filter that matched during a guardrail evaluation.
Contents
- action
-
The action taken by the guardrail filter.
Type: String
Valid Values:
BLOCKED | NONERequired: No
- confidence
-
The confidence level that the content matched the filter.
Type: String
Valid Values:
HIGH | MEDIUM | LOW | NONERequired: No
- type
-
The type of content that was filtered by the guardrail.
Type: String
Valid Values:
PROMPT_ATTACK | JAILBREAK | HATE | INSULTS | SEXUAL | VIOLENCE | MISCONDUCTRequired: No
See Also
For more information about using this API in one of the language-specific AWS SDKs, see the following:
