Struct ModerationCategories

pub struct ModerationCategories {
    pub hate: bool,
    pub hate_threatening: bool,
    pub self_harm: bool,
    pub sexual: bool,
    pub sexual_minors: bool,
    pub violence: bool,
    pub violence_graphic: bool,
}

A breakdown of the moderation categories.

Each field corresponds to a distinct policy category recognized by OpenAI’s model. If true, the text has been flagged under that category.

Fields

hate: bool

Hateful content directed towards a protected group or individual.

hate_threatening: bool

Hateful content with threats.

self_harm: bool

Content about self-harm or suicide.

sexual: bool

If true, the text includes sexual content or references.

sexual_minors: bool

If true, the text includes sexual content involving minors.

violence: bool

If true, the text includes violent content or context.

violence_graphic: bool

If true, the text includes particularly graphic or gory violence.

Trait Implementations

impl Debug for ModerationCategories

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for ModerationCategories

fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.