Trait EmbeddingProvider 

pub trait EmbeddingProvider: Send + Sync {
    // Required methods
    fn embed(&self, text: &str) -> Result<Vec<f32>>;
    fn dimension(&self) -> usize;
    fn model_name(&self) -> &str;

    // Provided method
    fn embed_batch(&self, texts: &[String]) -> Result<Vec<Vec<f32>>> { ... }
}

Trait for text embedding generation.

Implementations should be thread-safe and reusable across concurrent contexts.

Example

use brainwires_core::EmbeddingProvider;

fn search(provider: &dyn EmbeddingProvider, query: &str) -> anyhow::Result<Vec<f32>> {
    provider.embed(query)
}

Required Methods

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

Generate an embedding for a single text.

fn dimension(&self) -> usize

Get the dimensionality of the embedding vectors.

fn model_name(&self) -> &str

Get the model name (e.g. “all-MiniLM-L6-v2”).

Provided Methods

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

Generate embeddings for a batch of texts.

Default implementation calls embed in a loop. Backends that support native batching should override this for better performance.

Implementors