Skip to main content

EmbeddingProvider

pulsehive_core::embedding

Trait EmbeddingProvider 

Source 
pub trait EmbeddingProvider: Send + Sync {
    // Required methods
    fn embed<'life0, 'life1, 'async_trait>(
        &'life0 self,
        text: &'life1 str,
    ) -> Pin<Box<dyn Future<Output = Result<Vec<f32>>> + Send + 'async_trait>>
       where Self: 'async_trait,
             'life0: 'async_trait,
             'life1: 'async_trait;
    fn dimensions(&self) -> usize;

    // Provided method
    fn embed_batch<'life0, 'life1, 'life2, 'async_trait>(
        &'life0 self,
        texts: &'life1 [&'life2 str],
    ) -> Pin<Box<dyn Future<Output = Result<Vec<Vec<f32>>>> + Send + 'async_trait>>
       where Self: 'async_trait,
             'life0: 'async_trait,
             'life1: 'async_trait,
             'life2: 'async_trait { ... }
}
Expand description

Trait for domain-specific embedding model implementations.

Provides text-to-vector embeddings for semantic search and similarity computation. When registered with HiveMind, all experiences are embedded via this provider before storage in PulseDB (External mode).

Must be Send + Sync for concurrent use across Tokio tasks.

§Default batch implementation

embed_batch has a default implementation that calls embed sequentially. Override it for providers that support native batching (e.g., OpenAI, Cohere).

Required Methods§

Source

fn embed<'life0, 'life1, 'async_trait>( &'life0 self, text: &'life1 str, ) -> Pin<Box<dyn Future<Output = Result<Vec<f32>>> + Send + 'async_trait>>
where Self: 'async_trait, 'life0: 'async_trait, 'life1: 'async_trait,

Embed a single text string into a vector.

Source

fn dimensions(&self) -> usize

Return the dimensionality of embeddings produced by this provider.

Must be constant for a given provider instance. Used to configure PulseDB’s HNSW index when opening in External mode.

Provided Methods§

Source

fn embed_batch<'life0, 'life1, 'life2, 'async_trait>( &'life0 self, texts: &'life1 [&'life2 str], ) -> Pin<Box<dyn Future<Output = Result<Vec<Vec<f32>>>> + Send + 'async_trait>>
where Self: 'async_trait, 'life0: 'async_trait, 'life1: 'async_trait, 'life2: 'async_trait,

Embed a batch of text strings.

Default implementation calls embed sequentially. Override for providers that support native batch embedding (significantly faster for large batches).

Dyn Compatibility§

This trait is dyn compatible.

In older versions of Rust, dyn compatibility was called "object safety".

Implementors§