Composing Complex and Hybrid AI Solutions

TL;DR

This paper extends the Acumos system to support general AI applications by enabling flexible component integration, orchestration, and user interface assembly, facilitating easier experimentation and deployment of complex AI solutions.

Contribution

The paper introduces new features to Acumos for supporting generic AI components, orchestration, and user interfaces, expanding its applicability beyond telecommunication pipelines.

Findings

Extended Acumos supports gRPC/Protobuf interfaces.

Automated orchestration of AI component graphs.

Open source deployment available at aiexp.ai4europe.eu.

Abstract

Progress in several areas of computer science has been enabled by comfortable and efficient means of experimentation, clear interfaces, and interchangable components, for example using OpenCV for computer vision or ROS for robotics. We describe an extension of the Acumos system towards enabling the above features for general AI applications. Originally, Acumos was created for telecommunication purposes, mainly for creating linear pipelines of machine learning components. Our extensions include support for more generic components with gRPC/Protobuf interfaces, automatic orchestration of graphically assembled solutions including control loops, sub-component topologies, and event-based communication,and provisions for assembling solutions which contain user interfaces and shared storage areas. We provide examples of deployable solutions and their interfaces. The framework is deployed at http://aiexp.ai4europe.eu/ and its source code is managed as an open source Eclipse project.