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.

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 uses cases: personalized healthcare, maintenance & inspection and, finally, farming 4.

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 the scalable OSCAR cluster.

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.

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 intuitively through flow-based programming techniques.

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 serverless platform.

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 Jupyter for data analysis.

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 dynamically provisioned on multiple Clouds.

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.

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

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 DEEP-Hybrid-DataCloud: the Plants species classifier, to classify plant pictures by specie.