Struct SimpleEmbeddingModel 

pub struct SimpleEmbeddingModel { /* private fields */ }

Simple embedding model based on token frequency statistics.

This is a deterministic, in-memory embedding implementation:

• Maintains a fixed-size vocabulary (dimension slots).
• Each token is hashed into one of the dimension slots using FNV-1a.
• The embedding vector is the L2-normalized token-frequency histogram.

This is NOT a neural embedding (no semantic knowledge), but it is a real, deterministic, reproducible vector representation suitable for testing similarity-search pipelines end-to-end.

Implementations

impl SimpleEmbeddingModel

pub fn new(name: impl Into<String>, dimension: usize) -> Self

pub fn vocabulary_size(&self) -> usize

Trait Implementations

impl EmbeddingModel for SimpleEmbeddingModel

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

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

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

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

fn dimension(&self) -> usize

fn model_name(&self) -> &str