Struct DeterministicEmbedder 

pub struct DeterministicEmbedder { /* private fields */ }

Deterministic, network-free pseudo-embedder.

Produces a stable vector from the text via a token-hashing bag-of-words projection, then L2-normalizes it so cosine distance is well-behaved. Same text → same vector, always. This makes pgvector retrieval (and ingestion) tests reproducible without any external service: a document and a query that share salient tokens land close together in the projected space.

Implementations

impl DeterministicEmbedder

pub fn new() -> DeterministicEmbedder

Build with the DEFAULT_EMBEDDING_DIM (1024).

pub fn with_dim(dim: usize) -> DeterministicEmbedder

Build with a custom dimension (must match the adapter’s vector(N)).

Trait Implementations

impl Clone for DeterministicEmbedder

fn clone(&self) -> DeterministicEmbedder

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for DeterministicEmbedder

fn fmt(&self, f: &mut Formatter<'_>) -> Result<(), Error>

Formats the value using the given formatter.

impl Default for DeterministicEmbedder

fn default() -> DeterministicEmbedder

Returns the “default value” for a type.

impl Embedder for DeterministicEmbedder

fn dim(&self) -> usize

The fixed output dimension. Must equal the vector(N) column width.

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

where 'life0: 'async_trait, 'life1: 'async_trait, DeterministicEmbedder: 'async_trait,

Embed a batch of texts. Returns texts.len() vectors, each dim() long.