Struct HttpEmbedder 

pub struct HttpEmbedder { /* private fields */ }

HTTP-based embedder using llama-server’s /v1/embeddings endpoint.

Requires llama-server started with --embeddings flag. Dimension depends on the loaded GGUF model (e.g. 384 for bge-small, 768 for bge-base, 1024 for bge-large).

Implementations

impl HttpEmbedder

pub fn new(config: EmbedderConfig) -> Self

Create a new HTTP embedder with the given config.

pub fn from_env() -> Option<Self>

Create from environment variables, if configured.

Trait Implementations

impl Embedder for HttpEmbedder

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

Embed a batch of texts into f32 vectors.

fn dimension(&self) -> usize

Get the embedding dimensionality.

fn is_available(&self) -> bool

Whether this embedder is available (model loaded, server reachable).

fn backend_name(&self) -> &'static str

Name of this embedder backend.

fn cache_namespace(&self) -> String

Identity used to namespace the persistent embedding cache.

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

Embed a single text.

fn embed_query(&self, query: &str) -> Result<Vec<f32>>

Embed a single query (alias for embed).

fn preferred_max_batch_texts(&self) -> usize

Preferred batch granularity in TEXTS for batch write paths.