Struct FastEmbedEmbedder 

pub struct FastEmbedEmbedder { /* private fields */ }

FastEmbed embedder using BGE-M3.

Uses the fastembed-rs library for real semantic embeddings. The model is lazily loaded on first embed call to preserve cold start time.

BGE-M3 provides:

• 1024 dimensions (vs 384 for MiniLM)
• 8192 token context (vs ~512 for MiniLM)
• Better multilingual support

Examples

use rlm_rs::embedding::FastEmbedEmbedder;

let embedder = FastEmbedEmbedder::new()?;
let embedding = embedder.embed("Hello, world!")?;
assert_eq!(embedding.len(), 1024);

Implementations

impl FastEmbedEmbedder

pub fn new() -> Result<Self>

Creates a new FastEmbed embedder.

Note: Model is lazily loaded on first embed() call.

Errors

Returns an error if model initialization fails.

pub const fn model_name(&self) -> &'static str

Returns the model name.

Trait Implementations

impl Embedder for FastEmbedEmbedder

fn dimensions(&self) -> usize

Returns the embedding dimensions.

fn model_name(&self) -> &'static str

Returns the model name/version identifier.

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

Generates an embedding for the given text.

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

Generates embeddings for multiple texts.