Enum Embedder 

pub enum Embedder {
    Local {
        model: Arc<Mutex<BertModel>>,
        tokenizer: Arc<Tokenizer>,
        device: Device,
    },
    Ollama {
        client: Arc<OllamaClient>,
        model_name: String,
    },
}

Semantic embedding engine supporting multiple backends.

• Local (candle): all-MiniLM-L6-v2, 384-dim. Used at the semantic tier.
• Ollama: nomic-embed-text-v1.5, 768-dim. Used at smart/autonomous tiers.

Variants

Local

Candle-based local embedding (MiniLM-L6-v2, 384-dim)

Fields

model: Arc<Mutex<BertModel>>

tokenizer: Arc<Tokenizer>

device: Device

Ollama

Ollama-based embedding (nomic-embed-text-v1.5, 768-dim)

Fields

client: Arc<OllamaClient>

model_name: String

Implementations

impl Embedder

pub fn new() -> Result<Self>

Create a new local (candle) embedder for MiniLM-L6-v2. Downloads the model if it is not already cached.

pub fn new_local() -> Result<Self>

Create a local candle embedder (MiniLM-L6-v2, 384-dim).

pub fn new_ollama(client: Arc<OllamaClient>) -> Self

Create an Ollama-based embedder for nomic-embed-text-v1.5 (768-dim).

Requires the Ollama client to already be connected and the model pulled.

pub fn for_model( model: EmbeddingModel, ollama_client: Option<Arc<OllamaClient>>, ) -> Result<Self>

Create an embedder for the specified model.

• MiniLmL6V2 → local candle embedder
• NomicEmbedV15 → Ollama-based (requires ollama_client)

pub fn dim(&self) -> usize

Embedding vector dimensionality for this embedder.

pub fn model_description(&self) -> &str

Human-readable description of the active embedding model.

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

Generate an embedding for a single text input.

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

Generate embeddings for multiple texts in one call.

pub fn cosine_similarity(a: &[f32], b: &[f32]) -> f32

Compute cosine similarity between two embedding vectors.

pub fn fuse(primary: &[f32], secondary: &[f32], primary_weight: f32) -> Vec<f32>

Fuse a primary query embedding with a secondary context embedding via weighted linear combination (v0.6.0.0 contextual recall).

primary_weight clamped to [0.0, 1.0]. The result is returned un-normalized — cosine_similarity divides out magnitudes, so the downstream signal is direction-only. Returns primary.to_vec() when dimensions differ (graceful fallback, same policy as cosine_similarity).

Trait Implementations

impl Clone for Embedder

fn clone(&self) -> Embedder

Returns a duplicate of the value.

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

Performs copy-assignment from source.