Module fastembed 

Local ONNX embedding provider via fastembed-rs.

Wraps fastembed::TextEmbedding behind the EmbeddingProvider trait. Models are downloaded from HuggingFace on first use and cached locally.

use llm_kernel::embedding::{EmbeddingModel, FastembedProvider};
use llm_kernel::embedding::EmbeddingProvider;

let provider = FastembedProvider::new(EmbeddingModel::BGESmallENV15, None)?;
let result = provider.embed("hello world")?;
assert_eq!(result.vector.len(), 384);

Structs

FastembedProvider

Local ONNX embedding provider backed by fastembed-rs.