kozistr/triton-grpc-proxy-rs

Proxy server for triton gRPC server that inferences embedding model in Rust

33
/ 100
Emerging

This project helps developers serve machine learning models that generate embeddings from text. It takes raw text inputs and outputs numerical vector representations (embeddings) that can be used for tasks like search, recommendation, or classification. It's designed for developers building applications that need fast and efficient access to text embedding models.

No commits in the last 6 months.

Use this if you are a developer looking for a fast, simple, and dependency-free way to expose a text embedding model (like BAAI/bge-m3) via a gRPC API, abstracting away the complexities of the Triton Inference Server.

Not ideal if you need to serve non-embedding models, require custom pre-processing logic beyond simple text conversion, or are not comfortable with Rust or Docker deployments.

Machine Learning Infrastructure Text Embeddings API Development Microservices AI Model Deployment
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 11 / 25

How are scores calculated?

Stars

21

Forks

3

Language

Rust

License

Apache-2.0

Last pushed

Aug 10, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/kozistr/triton-grpc-proxy-rs"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.