# FastEmbed-rs

FastEmbed-rs is a Rust library for generating text and image vector embeddings and for reranking search results locally, using ONNX Runtime for inference and Hugging Face tokenizers for encoding, with synchronous use and no dependency on Tokio.

FastEmbed-rs is a Rust library for generating vector embeddings and reranking search results locally. It supports synchronous usage with no dependency on Tokio, uses the ort crate for ONNX inference, and uses Hugging Face's tokenizers crate for fast text encoding.

It ships a wide set of text embedding models by default, including several BAAI bge sizes, sentence-transformers models, multilingual e5 models and Qwen3 embedding models, some with quantized variants, plus sparse text embedding models such as Splade. Equivalent libraries are maintained separately for Python, Go and JavaScript for developers not working in Rust.

Website: https://docs.rs/fastembed