Struct InstrumentedRerankerModel 

pub struct InstrumentedRerankerModel {
    pub inner: Arc<dyn RerankerModel>,
    pub alias: String,
    pub provider_id: String,
    pub timeout: Option<Duration>,
    pub retry: Option<RetryConfig>,
}

Wrapper around a RerankerModel that adds timeout, retry, and metrics.

See InstrumentedEmbeddingModel for details on the instrumentation behavior.

Fields

inner: Arc<dyn RerankerModel>

alias: String

provider_id: String

timeout: Option<Duration>

retry: Option<RetryConfig>

Trait Implementations

impl ModelInfo for InstrumentedRerankerModel

fn model_id(&self) -> &str

The underlying model identifier (e.g. a HuggingFace repo ID or API model name).

fn active_execution_providers(&self) -> Vec<String>

Names of the ONNX Runtime execution providers this session was built with, in priority order. Empty for remote and non-ONNX models.

impl RerankerModel for InstrumentedRerankerModel

fn rerank<'life0, 'life1, 'life2, 'life3, 'async_trait>( &'life0 self, query: &'life1 str, docs: &'life2 [&'life3 str], ) -> Pin<Box<dyn Future<Output = Result<Vec<ScoredDoc>>> + Send + 'async_trait>>

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

Rerank docs by relevance to query, returning scored results (typically sorted by descending score).

fn warmup<'life0, 'async_trait>( &'life0 self, ) -> Pin<Box<dyn Future<Output = Result<()>> + Send + 'async_trait>>

where Self: 'async_trait, 'life0: 'async_trait,

Optional warmup hook. The default is a no-op.