Struct OpenAICompatibleEmbeddingEngine 

pub struct OpenAICompatibleEmbeddingEngine { /* private fields */ }

Embedding engine that calls an OpenAI-compatible /v1/embeddings HTTP endpoint.

Works with:

• OpenAI (https://api.openai.com)
• Azure OpenAI (set api_version in config)
• vLLM, llama.cpp, TEI, LocalAI (any OpenAI-compatible server)

URL normalisation

The base_url is derived from config.endpoint and is always normalised to end with /v1 so that the final request URL is {base_url}/embeddings.

The following transformations are applied in order:

1. Strip a trailing /
2. If the URL ends with /v1/embeddings, strip the /embeddings suffix.
3. If the URL does not end with /v1, append /v1.

Retry behaviour

Transient errors (HTTP 429, 5xx, network errors) are retried with exponential back-off (starting at 2 s, doubling up to 128 s, plus a uniform random jitter in [0, wait_secs)) for up to 128 s total.

Implementations

impl OpenAICompatibleEmbeddingEngine

pub fn new(config: &EmbeddingConfig) -> EmbeddingResult<Self>

Construct a new engine from the given EmbeddingConfig.

Returns EmbeddingError::ConfigError if the reqwest client cannot be built (e.g. invalid TLS configuration).

Trait Implementations

impl EmbeddingEngine for OpenAICompatibleEmbeddingEngine

fn embed<'life0, 'life1, 'life2, 'async_trait>( &'life0 self, texts: &'life1 [&'life2 str], ) -> Pin<Box<dyn Future<Output = EmbeddingResult<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 into normalized vectors

fn dimension(&self) -> usize

Get the dimensionality of embeddings produced by this engine

fn batch_size(&self) -> usize

Get the optimal batch size for this engine

fn max_sequence_length(&self) -> usize

Get the maximum sequence length (in tokens) supported