Skip to content

GuardrailContentPolicy

Structure Class

GuardrailContentPolicy dataclass

Bases: _SerdeShape

Contains details about how to handle harmful content.

This data type is used in the following API operations:

Attributes

filters class-attribute instance-attribute
filters: list[GuardrailContentFilter] | None = ...

Contains the type of the content filter and how strongly it should apply to prompts and model responses.

tier class-attribute instance-attribute
tier: GuardrailContentFiltersTier | None = ...

The tier that your guardrail uses for content filters.