SOLIS -- The MLOps journey from data acquisition to actionable insights

TL;DR

This paper discusses SOLIS, a comprehensive MLOps pipeline that automates deployment, adapts to live data, and supports multiple models across edge and cloud environments, addressing real-world production challenges.

Contribution

It introduces a unified, flexible deployment pipeline supporting live configuration, multi-model serving, and cross-platform integration for real-world MLOps applications.

Findings

Supports live data adaptation and configuration

Enables multi-model deployment on edge and cloud

Uses cross-platform frameworks for flexibility

Abstract

Machine Learning operations is unarguably a very important and also one of the hottest topics in Artificial Intelligence lately. Being able to define very clear hypotheses for actual real-life problems that can be addressed by machine learning models, collecting and curating large amounts of data for model training and validation followed by model architecture search and actual optimization and finally presenting the results fits very well the scenario of Data Science experiments. This approach however does not supply the needed procedures and pipelines for the actual deployment of machine learning capabilities in real production grade systems. Automating live configuration mechanisms, on the fly adapting to live or offline data capture and consumption, serving multiple models in parallel either on edge or cloud architectures, addressing specific limitations of GPU memory or compute power, post-processing inference or prediction results and serving those either as APIs or with IoT based communication stacks in the same end-to-end pipeline are the real challenges that we try to address in this particular paper. In this paper we present a unified deployment pipeline and freedom-to-operate approach that supports all above requirements while using basic cross-platform tensor framework and script language engines.