Struct InstrumentedEmbeddingModel 

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

Wrapper around an EmbeddingModel that adds per-call timeout enforcement, exponential-backoff retries for transient errors, and metrics emission (model_inference.duration_seconds, model_inference.total).

Fields

inner: Arc<dyn EmbeddingModel>

alias: String

provider_id: String

timeout: Option<Duration>

retry: Option<RetryConfig>

Trait Implementations

impl EmbeddingModel for InstrumentedEmbeddingModel

fn embed<'life0, 'life1, 'async_trait>( &'life0 self, texts: Vec<&'life1 str>, ) -> Pin<Box<dyn Future<Output = Result<Vec<Vec<f32>>>> + Send + 'async_trait>>

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

Embed a batch of text strings into dense vectors.

fn dimensions(&self) -> u32

The dimensionality of the embedding vectors produced by this model.

fn model_id(&self) -> &str

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

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 (e.g. load weights into memory on first access). The default is a no-op.