Reference documentation and code samples for the Google Cloud Model Armor V1 Client class PiAndJailbreakFilterSettings.
Prompt injection and Jailbreak Filter settings.
Generated from protobuf message google.cloud.modelarmor.v1.PiAndJailbreakFilterSettings
Namespace
Google \ Cloud \ ModelArmor \ V1Methods
__construct
Constructor.
data
array
Optional. Data for populating the Message object.
↳ filter_enforcement
int
Optional. Tells whether Prompt injection and Jailbreak filter is enabled or disabled.
↳ confidence_level
int
Optional. Confidence level for this filter. Confidence level is used to determine the threshold for the filter. If detection confidence is equal to or greater than the specified level, a positive match is reported. Confidence level will only be used if the filter is enabled.
getFilterEnforcement
Optional. Tells whether Prompt injection and Jailbreak filter is enabled or disabled.
int
setFilterEnforcement
Optional. Tells whether Prompt injection and Jailbreak filter is enabled or disabled.
var
int
$this
getConfidenceLevel
Optional. Confidence level for this filter.
Confidence level is used to determine the threshold for the filter. If detection confidence is equal to or greater than the specified level, a positive match is reported. Confidence level will only be used if the filter is enabled.
int
setConfidenceLevel
Optional. Confidence level for this filter.
Confidence level is used to determine the threshold for the filter. If detection confidence is equal to or greater than the specified level, a positive match is reported. Confidence level will only be used if the filter is enabled.
var
int
$this
