Blog

Guide to create a service in OSCAR

This is a step by step guide to show developers how to create their first service in OSCAR. Previous steps: Deploy the OSCAR cluster Follow the deployment instructions with the IM Dashboard. Alternatively, you can …

Digital Twin science made serverless: evolving OSCAR within interTwin

This post summarizes the work carried out in the InterTwin project to extend the OSCAR serverless platform across the cloud–HPC continuum. We developed DCNiOS, a Data Connector …

Bringing Serverless to Marine Science: Our Journey with OSCAR and iMagine.

The iMagine European Project uses the OSCAR serverless platform to support the scalable execution of the inference phase of marine AI models in mature thematic services. As the …

Serverless Computing for Artificial Intelligence: The OSCAR–AI4EOSC Integration Story.

The AI4EOSC European Project uses the OSCAR serverless platform to support the scalable execution of the inference phase of AI models. As the project has come to its end in August …

Composing AI Inference pipelines with Node-RED & Flowfuse

In this post, we are going to learn about composing AI inference workflows by invoking OSCAR services with Node-RED & FlowFuse. Both tools facilitate the graphical composition …

Composing AI Inference workflows based on OSCAR services with Elyra in EGI Notebooks

In this post, we will learn about composing AI inference workflows by invoking OSCAR services with Elyra. This tool is an extension for Jupyter Notebooks and facilitates the …

Integration of OSCAR in AI-SPRINT Use Cases

The AI-SPRINT European Project uses the OSCAR serverless platform to support the scalable execution of the inference phase of AI models along the computing continuum in all the …

Data-driven Processing with dCache, Apache Nifi and OSCAR

This post describes the integration between OSCAR and dCache. Data stored in dCache triggers the invocation of an OSCAR service to perform the processing of that data file within …

Design of workflows across OSCAR services with Node-RED (Part 2).

In this post, the work with Node-RED and its interaction with OSCAR services will be continued. Two workflows will be presented where you interact with OSCAR services using the …

Design of workflows across OSCAR services with Node-RED (Part 1).

In this post, we will be explaining the integration of Node-RED software with OSCAR. The necessary tools will be given to achieve workflows between OSCAR and Node-RED simply and …

Use COMPSs with OSCAR

This is a tutorial to integrate COMPSs with OSCAR. In this post, we will explain what COMPSs is and the integration with OSCAR to support parallel processing within an on-premises …

Invoking an OSCAR Service from an EGI Jupyter Notebook

In this post, we are going to showcase the usage of the OSCAR Python API, implemented to interact with OSCAR clusters and its services through EGI Notebooks, a tool based on …

Why use OSCAR as a serverless AI/ML model inference platform?

What is OSCAR? OSCAR is an open-source serverless platform for event-driven data-processing containerized applications that execute on elastic Kubernetes clusters that are …

User interfaces with Gradio for AI model inference in OSCAR services

What is Gradio? Gradio is a Python library for building user web interfaces for Machine Learning (ML) applications. Those interfaces can be customized with the components that …

FDL Composer to create a workflow with OSCAR

FDL-Composer is a tool to visually design workflows for OSCAR and SCAR. We are going to simulate the example video-process This example supports highly-scalable event-driven video …

Using OSCAR as a FaaS platform for synchronous inference of a machine learning model

This guide aims to show the usage of the OSCAR platform for Machine Learning inference using a pre-trained Convolutional Neural network classification model by …

Guide to create a service in OSCAR

This is a step by step guide to show developers how to create their first service in OSCAR. Previous steps: Deploy the OSCAR cluster Follow the deployment instructions with the IM …

Convert Text to Speech with OSCAR

This use case implements text-to-speech transformation using the OSCAR serverless platform, where an input of plain text returns an audio file. There are two examples of …

A Serverless Cloud-to-Edge Computing Continuum Approach for Edge AI inference

OSCAR is an open-source framework for data-processing serverless computing. Users upload files to an object storage which invokes a function responsible for processing each file. …

Using OSCAR as a FaaS platform for scalable asynchronous inference of a machine learning model

OSCAR is a framework to efficiently support on-premises FaaS (Functions as a Service) for general-purpose file-processing computing applications. Users upload files to a bucket and …

Deployment of an OSCAR cluster in the EGI Federated Cloud

Here we present a step by step guide to help you deploy an OSCAR cluster in the EGI Federated Cloud, specifically in the EOSC-Synergy VO. We are using the IM Dashboard, a tool …

Event-driven inference of AI models for mask detection with the OSCAR serverless platform

What is OSCAR? OSCAR is an open-source platform to support the Functions as a Service (FaaS) computing model for file-processing applications. It can be automatically deployed on …