Struct RandomClassifier 

pub struct RandomClassifier { /* private fields */ }

Stateless weighted classifier used by random fall-through routing.

Implementations

impl RandomClassifier

pub fn new( targets: Vec<String>, weights: Option<Vec<f64>>, seed: Option<u64>, ) -> Result<Self>

Creates a classifier over ordered target names.

Missing weights default to one per target. Explicit weights are relative, follow target order, and need not sum to one. Zero disables a target. Missing seed uses entropy-backed randomness.

Errors

Returns an error when targets are empty or duplicated, or when explicit weights have the wrong length, are negative or non-finite, or contain no positive value.

Trait Implementations

impl<S> Classifier<S> for RandomClassifier

where S: Send + 'static,

fn score<'life0, 'life1, 'life2, 'life3, 'async_trait>( &'life0 self, _state: &'life1 mut S, _request: &'life2 mut Request, _driver: Option<&'life3 Driver>, ) -> Pin<Box<dyn Future<Output = Result<(Classification, Option<Response>)>> + Send + 'async_trait>>

where Self: 'async_trait, 'life0: 'async_trait, 'life1: 'async_trait, 'life2: 'async_trait, 'life3: 'async_trait,

Score the classifier’s targets given the current state and request.

fn routing_tier(&self, _selected_model: &str) -> Option<&'static str>

Stable tier represented by selected_model, when this classifier defines one.