Production-ready ONNX embedding generation in pure Rust using ONNX Runtime, no Python required. Supports 8+ pretrained models including all-MiniLM-L6-v2, BGE, E5, GTE with pooling strategies and GPU acceleration (CUDA, TensorRT, CoreML, WebGPU). Enables direct integration with RuVector indices for RAG pipelines and semantic similarity computation.
Loading more......
On this page
ruvector-onnx-embeddings
Native embedding generation using ONNX Runtime in pure Rust. Supports multiple pretrained models and hardware acceleration.
use ruvector_onnx_embeddings::{Embedder, PretrainedModel};
#[tokio::main]
async fn main() -> anyhow::Result<()> {
let mut embedder = Embedder::default_model().await?;
let embedding = embedder.embed_one("Hello, world!")?;
let sim = embedder.similarity(
"I love programming in Rust",
"Rust is my favorite language"
)?;
println!("Similarity: {:.4}", sim);
Ok(())
}
Open-source, free.
Explore more items related to this one