Struct EmbeddingEngine 

pub struct EmbeddingEngine { /* private fields */ }

Implementations

impl EmbeddingEngine

pub fn load(model_dir: &Path) -> Result<Self>

Load embedding model and vocabulary from a directory. Downloads model automatically from HuggingFace if not present.

Expected files (auto-downloaded):

• model.onnx — all-MiniLM-L6-v2 ONNX embedding model
• vocab.txt — WordPiece vocabulary (one token per line)

pub fn load_default() -> Result<Self>

Load from default model directory (~/.lean-ctx/models/).

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

Generate an embedding vector for a single text.

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

Generate embedding vectors for multiple texts.

pub fn dimensions(&self) -> usize

pub fn model_directory() -> PathBuf

Resolve the model directory (respects LEAN_CTX_MODELS_DIR env).

pub fn is_available() -> bool

Check if the model files are present and loadable.