Struct EvalRunModelUsage 

pub struct EvalRunModelUsage {
    pub model_name: String,
    pub invocation_count: u32,
    pub prompt_tokens: u32,
    pub completion_tokens: u32,
    pub total_tokens: u32,
    pub cached_tokens: u32,
}

Usage statistics for each model during the evaluation run.

Fields

model_name: String

The name of the model.

invocation_count: u32

The number of invocations.

prompt_tokens: u32

The number of prompt tokens used.

completion_tokens: u32

The number of completion tokens generated.

total_tokens: u32

The total number of tokens used.

cached_tokens: u32

The number of tokens retrieved from cache.

Trait Implementations

impl Clone for EvalRunModelUsage

fn clone(&self) -> EvalRunModelUsage

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for EvalRunModelUsage

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

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for EvalRunModelUsage

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl PartialEq for EvalRunModelUsage

fn eq(&self, other: &EvalRunModelUsage) -> 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 EvalRunModelUsage

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

where __S: Serializer,

Serialize this value into the given Serde serializer.

impl StructuralPartialEq for EvalRunModelUsage