LoCoML: A Framework for Real-World ML Inference Pipelines

TL;DR

LoCoML is a low-code framework that simplifies integrating diverse machine learning models into real-world applications, especially in large-scale, collaborative projects involving multiple AI technologies across many languages.

Contribution

The paper introduces LoCoML, a novel low-code framework that addresses the complexity of integrating heterogeneous ML models in large-scale, collaborative environments.

Findings

LoCoML adds minimal computational overhead.

It effectively simplifies ML model integration in large-scale projects.

Practical insights support low-code as a viable solution for collaborative ML systems.

Abstract

The widespread adoption of machine learning (ML) has brought forth diverse models with varying architectures, and data requirements, introducing new challenges in integrating these systems into real-world applications. Traditional solutions often struggle to manage the complexities of connecting heterogeneous models, especially when dealing with varied technical specifications. These limitations are amplified in large-scale, collaborative projects where stakeholders contribute models with different technical specifications. To address these challenges, we developed LoCoML, a low-code framework designed to simplify the integration of diverse ML models within the context of the \textit{Bhashini Project} - a large-scale initiative aimed at integrating AI-driven language technologies such as automatic speech recognition, machine translation, text-to-speech, and optical character recognition to support seamless communication across more than 20 languages. Initial evaluations show that LoCoML adds only a small amount of computational load, making it efficient and effective for large-scale ML integration. Our practical insights show that a low-code approach can be a practical solution for connecting multiple ML models in a collaborative environment.