`nemo_microservices.types.beta.audit.audit_run_data`#

Module Contents#

class nemo_microservices.types.beta.audit.audit_run_data.AuditRunData(/, **data: typing.Any)#

Bases: nemo_microservices._models.BaseModel

deprefix: Optional[bool]#

None

Remove the prompt from the start of the output (some models return the prompt as part of their output)

eval_threshold: Optional[float]#

None

Threshold for categorizing a detector output as a successful attack/hit

generations: Optional[int]#

None

How many times to send each prompt for inference