Reference documentation and code samples for the Gemini Enterprise for Customer Experience V1BETA API class Google::Cloud::Ces::V1beta::Guardrail::ContentFilter.
Guardrail that bans certain content from being used in the conversation.
Inherits
- Object
Extended By
- Google::Protobuf::MessageExts::ClassMethods
Includes
- Google::Protobuf::MessageExts
Methods
#banned_contents
def banned_contents() -> ::Array<::String>
Returns
- (::Array<::String>) — Optional. List of banned phrases. Applies to both user inputs and agent responses.
#banned_contents=
def banned_contents=(value) -> ::Array<::String>
Parameter
- value (::Array<::String>) — Optional. List of banned phrases. Applies to both user inputs and agent responses.
Returns
- (::Array<::String>) — Optional. List of banned phrases. Applies to both user inputs and agent responses.
#banned_contents_in_agent_response
def banned_contents_in_agent_response() -> ::Array<::String>
Returns
- (::Array<::String>) — Optional. List of banned phrases. Applies only to agent responses.
#banned_contents_in_agent_response=
def banned_contents_in_agent_response=(value) -> ::Array<::String>
Parameter
- value (::Array<::String>) — Optional. List of banned phrases. Applies only to agent responses.
Returns
- (::Array<::String>) — Optional. List of banned phrases. Applies only to agent responses.
#banned_contents_in_user_input
def banned_contents_in_user_input() -> ::Array<::String>
Returns
- (::Array<::String>) — Optional. List of banned phrases. Applies only to user inputs.
#banned_contents_in_user_input=
def banned_contents_in_user_input=(value) -> ::Array<::String>
Parameter
- value (::Array<::String>) — Optional. List of banned phrases. Applies only to user inputs.
Returns
- (::Array<::String>) — Optional. List of banned phrases. Applies only to user inputs.
#disregard_diacritics
def disregard_diacritics() -> ::Boolean
Returns
- (::Boolean) — Optional. If true, diacritics are ignored during matching.
#disregard_diacritics=
def disregard_diacritics=(value) -> ::Boolean
Parameter
- value (::Boolean) — Optional. If true, diacritics are ignored during matching.
Returns
- (::Boolean) — Optional. If true, diacritics are ignored during matching.
#match_type
def match_type() -> ::Google::Cloud::Ces::V1beta::Guardrail::ContentFilter::MatchType
Returns
- (::Google::Cloud::Ces::V1beta::Guardrail::ContentFilter::MatchType) — Required. Match type for the content filter.
#match_type=
def match_type=(value) -> ::Google::Cloud::Ces::V1beta::Guardrail::ContentFilter::MatchType
Parameter
- value (::Google::Cloud::Ces::V1beta::Guardrail::ContentFilter::MatchType) — Required. Match type for the content filter.
Returns
- (::Google::Cloud::Ces::V1beta::Guardrail::ContentFilter::MatchType) — Required. Match type for the content filter.
#sensitive_words_exemptions
def sensitive_words_exemptions() -> ::Array<::String>
Returns
- (::Array<::String>) — Optional. Entries of the sensitive words list that this guardrail allows. Only valid when match_type is SENSITIVE_WORDS. Each value must equal a list entry (case-insensitive, surrounding whitespace ignored); other values have no effect. Applies to this guardrail only. At most 1000 entries of up to 256 characters each.
#sensitive_words_exemptions=
def sensitive_words_exemptions=(value) -> ::Array<::String>
Parameter
- value (::Array<::String>) — Optional. Entries of the sensitive words list that this guardrail allows. Only valid when match_type is SENSITIVE_WORDS. Each value must equal a list entry (case-insensitive, surrounding whitespace ignored); other values have no effect. Applies to this guardrail only. At most 1000 entries of up to 256 characters each.
Returns
- (::Array<::String>) — Optional. Entries of the sensitive words list that this guardrail allows. Only valid when match_type is SENSITIVE_WORDS. Each value must equal a list entry (case-insensitive, surrounding whitespace ignored); other values have no effect. Applies to this guardrail only. At most 1000 entries of up to 256 characters each.