Struct LlmEmbeddingProvider 

pub struct LlmEmbeddingProvider { /* private fields */ }

LLM-backed embedding provider that calls the clawft-llm provider layer.

Uses the model’s embedding endpoint to produce real semantic vectors. When no API is configured (or the API is unavailable), falls back to MockEmbeddingProvider for deterministic hash-based embeddings.

Implementations

impl LlmEmbeddingProvider

pub fn new(config: LlmEmbeddingConfig) -> Self

Create a new LLM embedding provider with the given configuration.

pub fn from_config(table: &HashMap<String, String>) -> Self

Create from a weave.toml-style configuration table.

Expected keys: model (string), dimensions (int), batch_size (int). If the table is missing or incomplete, returns a provider with defaults that falls back to mock embeddings.

pub fn is_api_available(&self) -> bool

Whether the LLM API is available (non-fallback mode).

pub fn config(&self) -> &LlmEmbeddingConfig

Get the underlying configuration.

Trait Implementations

impl EmbeddingProvider for LlmEmbeddingProvider

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

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

Embed a single text chunk into a vector.

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

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

Embed a batch of text chunks.

fn dimensions(&self) -> usize

Dimensionality of the output vectors.

fn model_name(&self) -> &str

Name of the embedding model (for metadata tracking).