DANGEROUS_CONTENT
DANGEROUS_CONTENT: "DANGEROUS_CONTENT"
HARASSMENT
HARASSMENT: "HARASSMENT"
HATE_SPEECH
HATE_SPEECH: "HATE_SPEECH"
MEDICAL_INFO
MEDICAL_INFO: "MEDICAL_INFO"
OBSCENITY_AND_PROFANITY
OBSCENITY_AND_PROFANITY: "OBSCENITY_AND_PROFANITY"
PII_SOLICITING_RECITING
PII_SOLICITING_RECITING: "PII_SOLICITING_RECITING"
SEXUALLY_EXPLICIT
SEXUALLY_EXPLICIT: "SEXUALLY_EXPLICIT"
VIOLENCE_AND_GORE
VIOLENCE_AND_GORE: "VIOLENCE_AND_GORE"
Currently supported Checks AI Safety policies.