Real-time Data Collection and Processing using AI/ML on OpenShift AI

Learning path | 3 resources | Published on May 3, 2024
Alex Krikos Ramakrishna Yekulla

In this learning exercise, we'll explore how to set up a robust system for processing live image streams using Apache Kafka, OpenShift AI, and PostgreSQL. By leveraging all components, we are developing a computer vision system for pet inventory management in retail settings. We simulate pet shop environments using camera data to train a model that can accurately detect and track animals within the store. This will ensure real-time inventory monitoring and potentially improve animal welfare by minimizing the risk of misplaced pets.

Try it in our Sandbox

  1. Overview: Real-time Data Collection and Processing using AI/ML on OpenShift AI
  2. Prerequisites and step-by-step guide Page
  3. Additional resources Page

Overview: Real-time Data Collection and Processing using AI/ML on OpenShift AI

Real-time Data Collection

In today's digital landscape, the demand for real-time data processing is ever-increasing, especially with the proliferation of multimedia content. One area where real-time processing is crucial is in handling live image streams, where timely analysis and action are required. 

Building on the foundation established in the previous learning exercise, we configured OpenShift AI. This involves creating a Data Science project and launching a Jupyter Notebook environment. For a refresher on the initial setup, please refer to the first learning exercise link. 

This learning exercise will run on Red Hat OpenShift AI, available both as a managed service or self-managed offering.