Struct E5EmbeddingProvider 

pub struct E5EmbeddingProvider { /* private fields */ }

e5-small-v2 provider — 384-d BERT encoder with asymmetric query/passage prefixes.

Implementations

impl E5EmbeddingProvider

pub fn new(model_path: impl Into<PathBuf>) -> Self

Create a provider pointing at an e5 ONNX model file.

Degrades to the ONNX hash fallback when the feature is off, the file is missing, or session load fails — never panics, never requires the model to construct (CI-safe).

pub fn is_runtime_available(&self) -> bool

Whether real ONNX inference is active (vs. hash fallback).

pub fn model_path(&self) -> &Path

Path to the configured ONNX model file.

pub fn prefix_passage(text: &str) -> String

Prefix a string for the passage (document) lane.

pub fn prefix_query(text: &str) -> String

Prefix a string for the query lane.

Trait Implementations

impl EmbeddingProvider for E5EmbeddingProvider

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

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

Embed a single text chunk into a vector.

fn embed_batch<'life0, 'life1, 'life2, 'async_trait>( &'life0 self, texts: &'life1 [&'life2 str], ) -> Pin<Box<dyn Future<Output = Result<Vec<Vec<f32>>, EmbeddingError>> + Send + 'async_trait>>

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

Embed a batch of text chunks.

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

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

Embed a query (asymmetric retrieval lane).

fn dimensions(&self) -> usize

Dimensionality of the output vectors.

fn model_name(&self) -> &str

Name of the embedding model (for metadata tracking).

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

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

Pre-warm the backend: run one throwaway embed so the model graph, runtime thread pool, and allocator are hot before the first real call. Best-effort — errors are swallowed (a backend with nothing to warm, like the Mock, just pays one cheap call). Intended to be called once at daemon startup so the first conversation turn doesn’t pay the model’s first-inference cost (ADR-058 Phase 5.3; mirrors the 6.2 STT pre-warm).