Struct ProblemClassification 

pub struct ProblemClassification {
    pub class: ProblemClass,
    pub matched_keywords: Vec<String>,
    pub defaulted: bool,
    pub tiebroken: bool,
}

Result of classifying an intent.

Fields

class: ProblemClass

matched_keywords: Vec<String>

The trigger words that fired to produce this class. Empty if the classifier fell back to the default. Useful for traces and explanations.

defaulted: bool

True if no keyword matched and the classifier defaulted (without a tiebreaker resolving the ambiguity).

tiebroken: bool

True if a ClassifierTiebreaker was consulted to resolve an ambiguous keyword pass. A consumer that audits selections may prefer to surface tiebroken classifications differently from keyword-driven ones (lower confidence, may flip on retry).

Trait Implementations

impl Clone for ProblemClassification

fn clone(&self) -> ProblemClassification

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for ProblemClassification

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

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for ProblemClassification

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl PartialEq for ProblemClassification

fn eq(&self, other: &ProblemClassification) -> bool

Tests for self and other values to be equal, and is used by ==.

fn ne(&self, other: &Rhs) -> bool

Tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.

impl Serialize for ProblemClassification

fn serialize<__S>(&self, __serializer: __S) -> Result<__S::Ok, __S::Error>

where __S: Serializer,

Serialize this value into the given Serde serializer.

impl Eq for ProblemClassification

impl StructuralPartialEq for ProblemClassification