Struct CloudEmbedder 

pub struct CloudEmbedder { /* private fields */ }

Cloud-managed embedder. POSTs { texts: [..] } to the cloud API’s /api/embeddings endpoint, authenticating with the user’s existing CLI session token (same cloud-auth.db row that powers cloud::client::CloudClient).

This is the happy path for the OSS Free tier — users don’t have to manage an OpenAI key locally; the cloud forwards to its own configured embedding provider. Failures (network / 401 / 5xx) bubble up as CoreError::Internal so the caller can fall back to local SHA1 after retry rather than surfacing a hard error.

Implementations

impl CloudEmbedder

pub fn new(base_url: String, token: String) -> Self

pub fn with_model( base_url: String, token: String, model: String, dim: usize, ) -> Self

Trait Implementations

impl Embedder for CloudEmbedder

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.