Struct HashEmbedder 

pub struct HashEmbedder { /* private fields */ }

A deterministic, dependency-free embedder using the feature-hashing trick: each token is hashed into one of dim buckets and the resulting bag-of-words vector is L2-normalised. It is lexical, not semantic — its job is to make the trait, storage, ingest and ranking code testable without a model, and to serve as a crude offline fallback. The real semantic quality comes from the model2vec backend.

Implementations

impl HashEmbedder

pub fn new(dim: usize) -> Self

Trait Implementations

impl Default for HashEmbedder

fn default() -> Self

Returns the “default value” for a type.

impl Embedder for HashEmbedder

fn embed(&self, texts: &[&str]) -> Result<Vec<Vec<f32>>>

Embed a batch of texts. out[i] corresponds to texts[i].

fn model_id(&self) -> &str

Stable identifier of the model (stored per vector so a model change can trigger a re-embed and we never compare vectors across models).

fn dim(&self) -> usize

Output dimensionality.

fn embed_one(&self, text: &str) -> Result<Vec<f32>>

Convenience: embed a single text.