Struct OpenAICompatEmbedder 

pub struct OpenAICompatEmbedder {
    pub base_url: String,
    pub api_key: String,
    pub model: String,
    pub dim: usize,
    /* private fields */
}

OpenAI-compatible embedding provider.

Works with any backend that speaks the OpenAI /embeddings shape (OpenAI, Azure OpenAI, Together, DeepInfra, etc.).

Fields

base_url: String

api_key: String

model: String

dim: usize

Implementations

impl OpenAICompatEmbedder

pub fn new(base_url: String, api_key: String, model: String, dim: usize) -> Self

Trait Implementations

impl Embedder for OpenAICompatEmbedder

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

where Self: 'async_trait, 'life0: 'async_trait, 'life1: 'async_trait,

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

where Self: 'async_trait, 'life0: 'async_trait, 'life1: 'async_trait, 'life2: 'async_trait,

fn dim(&self) -> usize

fn is_semantic(&self) -> bool

Whether this embedder produces semantically meaningful vectors. Defaults to true so real embedding providers don’t have to opt in; lexical-only fallbacks override to false so hybrid retrieval knows to lean harder on the FTS baseline for keyword-heavy queries.