Rapid Development of Compositional AI
Software Engineering
2023-02-14 v1 Artificial Intelligence
Abstract
Compositional AI systems, which combine multiple artificial intelligence components together with other application components to solve a larger problem, have no known pattern of development and are often approached in a bespoke and ad hoc style. This makes development slower and harder to reuse for future applications. To support the full rapid development cycle of compositional AI applications, we have developed a novel framework called (Bee)* (written as a regular expression and pronounced as "beestar"). We illustrate how (Bee)* supports building integrated, scalable, and interactive compositional AI applications with a simplified developer experience.
Cite
@article{arxiv.2302.05941,
title = {Rapid Development of Compositional AI},
author = {Lee Martie and Jessie Rosenberg and Veronique Demers and Gaoyuan Zhang and Onkar Bhardwaj and John Henning and Aditya Prasad and Matt Stallone and Ja Young Lee and Lucy Yip and Damilola Adesina and Elahe Paikari and Oscar Resendiz and Sarah Shaw and David Cox},
journal= {arXiv preprint arXiv:2302.05941},
year = {2023}
}
Comments
Accepted to ICSE 2023, NIER track