Enum InferenceOutputs 

pub enum InferenceOutputs {
    Text(Vec<String>),
    Vectors(Vec<Vec<f32>>),
    Scores(Vec<f64>),
}

Per-row outputs of a batch. Homogeneous for a given request: a classify or generate batch yields text; an embed batch — or a local classifier’s raw logits awaiting softmax in the adapter — yields numeric vectors; a sentiment batch yields one scalar score per row (the adapter’s output, never a raw provider shape).

Variants

Text(Vec<String>)

One text output per input row.

Vectors(Vec<Vec<f32>>)

One numeric vector per input row (embeddings, or classifier logits).

Scores(Vec<f64>)

One scalar score per input row. Produced by the adapter for ai_sentiment (continuous, in [-1, 1]); providers never return this shape directly.

Implementations

impl InferenceOutputs

pub fn len(&self) -> usize

Number of rows produced. Must equal the request’s input count.

pub fn is_empty(&self) -> bool

Whether no rows were produced.

Trait Implementations

impl Clone for InferenceOutputs

fn clone(&self) -> InferenceOutputs

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for InferenceOutputs

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

Formats the value using the given formatter.

impl PartialEq for InferenceOutputs

fn eq(&self, other: &InferenceOutputs) -> 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 StructuralPartialEq for InferenceOutputs