Struct DeterministicEmbedding 

pub struct DeterministicEmbedding { /* private fields */ }

A deterministic, offline bag-of-words hashing embedder for tests, examples, and demos.

Each whitespace token is FNV-1a hashed into a bucket and the resulting vector is L2-normalized, so two texts that share tokens are close under cosine similarity. It needs no model file and no network and — unlike NoopEmbedding — produces real, non-zero vectors, so it reports is_semantic_capable() == true and can back semantic/hybrid recall.

It is not a production-quality semantic model (there is no learned meaning, only lexical hashing); use OpenAI (HTTP) or ONNX embeddings for real semantic recall. Its purpose is a reproducible, dependency-free stand-in so tests and examples can exercise the vector path without an API key or model.

Implementations

impl DeterministicEmbedding

pub fn new(dimensions: usize) -> Self

Trait Implementations

impl EmbeddingProvider for DeterministicEmbedding

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

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

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

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

fn dimensions(&self) -> usize

fn is_semantic_capable(&self) -> bool

Whether this provider produces real query vectors usable for semantic (dense-similarity) recall. Defaults to true; the no-op provider — which returns all-zero vectors — overrides this to false so the recall path can refuse semantic/hybrid queries with a typed error instead of silently returning an empty result set. Real providers (OpenAI, ONNX) inherit true.