GuardrailContextualGroundingFilter
The details for the guardrails contextual grounding filter.
Contents
- action
-
The action performed by the guardrails contextual grounding filter.
Type: String
Valid Values:
BLOCKED | NONERequired: Yes
- score
-
The score generated by contextual grounding filter.
Type: Double
Valid Range: Minimum value of 0. Maximum value of 1.
Required: Yes
- threshold
-
The threshold used by contextual grounding filter to determine whether the content is grounded or not.
Type: Double
Valid Range: Minimum value of 0. Maximum value of 1.
Required: Yes
- type
-
The contextual grounding filter type.
Type: String
Valid Values:
GROUNDING | RELEVANCERequired: Yes
See Also
For more information about using this API in one of the language-specific AWS SDKs, see the following:
