Struct FastEmbedder 

pub struct FastEmbedder { /* private fields */ }

Production-ready semantic embedder using fastembed (ONNX Runtime)

Requires the embeddings feature to be enabled.

Example

use trueno_rag::embed::{FastEmbedder, EmbeddingModelType, Embedder};

let embedder = FastEmbedder::new(EmbeddingModelType::AllMiniLmL6V2)?;
let embedding = embedder.embed("Hello, world!")?;
assert_eq!(embedding.len(), 384);

Implementations

impl FastEmbedder

pub fn new(model_type: EmbeddingModelType) -> Result<Self>

Create a new FastEmbedder with the specified model

Downloads the model on first use if not cached.

Errors

Returns an error if model initialization fails.

pub fn default_model() -> Result<Self>

Create with default model (all-MiniLM-L6-v2)

Errors

Returns an error if model initialization fails.

pub fn model_type(&self) -> EmbeddingModelType

Get the model type

Trait Implementations

impl Clone for FastEmbedder

fn clone(&self) -> FastEmbedder

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for FastEmbedder

Available on crate feature embeddings only.

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

Formats the value using the given formatter.

impl Embedder for FastEmbedder

Available on crate feature embeddings only.

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

Embed a single text

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

Batch embed multiple texts

fn dimension(&self) -> usize

Get embedding dimension

fn model_id(&self) -> &str

Get model identifier

fn embed_query(&self, query: &str) -> Result<Vec<f32>>

Embed a query (may use query prefix)

fn embed_document(&self, document: &str) -> Result<Vec<f32>>

Embed a document (may use document prefix)

fn embed_chunks(&self, chunks: &mut [Chunk]) -> Result<()>

Embed chunks and update them in place