This document presents the draft specification for delivering machine learning services over HTTP, developed as part of the Protocols and Structures for Inference project, which concluded in 2013. It presents the motivation for providing machine learning as a service, followed by a description of the essential and optional components of such a service.
Cite
@article{arxiv.2205.09488,
title = {PSI Draft Specification},
author = {Mark Reid and James Montgomery and Barry Drake and Avraham Ruderman},
journal= {arXiv preprint arXiv:2205.09488},
year = {2022}
}
Comments
Software specification for PSI machine learning web services. 42 pages, 2 figures