Struct SentenceTransformerProvider 

pub struct SentenceTransformerProvider { /* private fields */ }

Sentence-transformer embedding provider for documentation.

Optimised for natural language paragraphs rather than code. Pre-processes markdown, splits into sentences, embeds each, and averages (mean pooling).

Implementations

impl SentenceTransformerProvider

pub const DEFAULT_MAX_TOKENS: usize = 512

Default max tokens for documentation (longer context than code).

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

Create a new sentence-transformer provider.

pub fn with_config( model_path: impl Into<PathBuf>, max_tokens: usize, split_sentences: bool, ) -> Self

Create with custom max tokens and optional sentence splitting.

pub fn split_sentences(&self) -> bool

Whether sentence splitting is enabled.

pub fn max_tokens(&self) -> usize

Max token length.

Trait Implementations

impl EmbeddingProvider for SentenceTransformerProvider

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 dimensions(&self) -> usize

Dimensionality of the output vectors.

fn model_name(&self) -> &str

Name of the embedding model (for metadata tracking).

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 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).