dragon.ai.inference.config.GuardrailsConfig

class GuardrailsConfig

Bases: object

Prompt guardrails/safety configuration.

__init__(enabled: bool = True, prompt_guard_model: str = 'meta-llama/Prompt-Guard-86M', prompt_guard_sensitivity: float = 0.5) → None

Methods

__init__([enabled, prompt_guard_model, ...])
validate()	Validate guardrails configuration.

Attributes

enabled
prompt_guard_model
prompt_guard_sensitivity

enabled: bool = True

prompt_guard_model: str = 'meta-llama/Prompt-Guard-86M'

prompt_guard_sensitivity: float = 0.5

validate() → None

Validate guardrails configuration.

__init__(enabled: bool = True, prompt_guard_model: str = 'meta-llama/Prompt-Guard-86M', prompt_guard_sensitivity: float = 0.5) → None