Jump to section
Pricing

AI/ML on Red Hat OpenShift

Copy URL

AI/ML on Red Hat® OpenShift®  accelerates AI/ML workflows and the delivery of AI-powered intelligent applications with self-managed Red Hat OpenShift, or our AI/ML cloud service.

 

Red Hat OpenShift includes key capabilities to enable machine learning operations (MLOps) in a consistent way across datacenters, public cloud computing, and edge computing.

By applying DevOps and GitOps principles, organizations automate and simplify the iterative process of integrating machine learning models into software development processes, production rollout, monitoring, retraining, and redeployment for continued prediction accuracy. 

A multi-phase process to obtain the power of large volumes and a variety of data, abundant compute, and open source machine learning tools to build intelligent applications.

Data scientists are primarily responsible for ML modeling to ensure the selected model continues to provide the highest prediction accuracy. 

The key challenges data scientists face are:

  • Selecting & deploying the right ML tools (ex. Apache Spark, Jupyter notebook TensorFlow, PyTorch, etc.)
  • Complexities and time required to train, test, select, and retrain the ML model that provides the highest prediction accuracy
  • Slow execution of modeling and inferencing tasks because of lack of hardware acceleration
  • Repeated dependency on IT operations to provision and manage infrastructure
  • Collaborating with data engineers and software developers to ensure input data hygiene, and successful ML model deployment in app dev processes

Red Hat® OpenShift® is an integrated application platform for managing the AI/ML lifecycle across hybrid cloud environments and the edge. By providing self-service access to collaborative workflows, intensive computation power (GPUs), and streamlined operations, OpenShift simplifies the delivery of AI solutions consistently and at scale. 

Red Hat OpenShift AI

Red Hat OpenShift AI provides tools across the full lifecycle of AI/ML experiments and models for data scientists and developers of intelligent applications. It provides a fully supported sandbox in which to rapidly develop, train, and test machine learning (ML) models in the public cloud before deploying in production.

Empower data scientists

  • Self-service, consistent, cloud experience for data scientists across the hybrid cloud
  • Empower data scientists with the flexibility and portability to use the containerized ML tools of their choice to quickly build, scale, reproduce, and share ML models.
  • Use the most relevant ML tools via Red Hat certified Kubernetes Operators for both self-managed and our AI cloud service option.
  • Eliminate dependency on IT to provision infrastructure for iterative, compute-intensive ML modeling tasks.
  • Eliminate "lock-in" concerns with any particular cloud provider, and their menu of ML tools.
  • Tight integration with CI/CD tools allows ML models to be quickly deployed iteratively, as needed.

Accelerate compute-intensive ML modeling jobs

Integrations with popular hardware accelerators such as NVIDIA GPUs via Red Hat certified GPU operator means that OpenShift can seamlessly meet the high compute resource requirements to help select the best ML model providing the highest prediction accuracy, and ML inferencing jobs as the model experiences new data in production.

Develop intelligent apps

OpenShift’s built-in  DevOps capabilities enable MLOps to speed up delivery of AI-powered applications and simplify the iterative process of integrating ML models and continued redeployment for prediction accuracy.    

Extending OpenShift DevOps automation capabilities to the ML lifecycle enables collaboration between data scientists, software developers, and IT operations so that ML models can be quickly integrated into the development of intelligent applications. This helps boost productivity, and simplify lifecycle management for ML powered intelligent applications.

  • Building from the container model images registry with OpenShift Build.
  • Continuous, iterative development of ML model powered intelligent applications with OpenShift Pipelines.
  • Continuous deployment automation for ML models powered intelligent applications with OpenShift GitOps.
  • An image repository to version model container images and microservices with Red Hat Quay.

OpenShift is helping organizations across various industries to accelerate business and mission critical initiatives by developing intelligent applications in the hybrid cloud. Some example use cases include fraud detection, data driven health diagnostics, connected cars, oil and gas exploration, automated insurance quotes, and claims processing.

Transformative AI/ML use cases are occurring across healthcare, financial services, telecommunications, automotive, and other industries. Red Hat has cultivated a robust partner ecosystem to offer complete solutions for creating, deploying, and managing ML and deep learning models for AI-powered intelligent applications.

NTT East logo

To deliver edge computing data analysis to regional businesses and organizations, NTT East recently launched their Video AI service running on Red Hat OpenShift. 

Through NTT’s edge computing initiative, organizations and businesses integrating the latest AI capabilities were able to increase their sales by 144% and decrease shoplifting by 30-40% while improving customer service.

Galicia logo

Working with Red Hat Consulting, Banco Galicia built an AI-based intelligent natural language processing (NLP) solution on Red Hat OpenShift, and was able to cut verification times from days to minutes with 90% accuracy and cut application downtime by 40%.

The combined power of Red Hat OpenShift and NVIDIA AI Enterprise software suite running on NVIDIA-Certified Systems offers a scalable platform that helps accelerate a diverse range of AI use cases. This platform includes key technologies from NVIDIA and Red Hat to securely deploy, manage, and scale AI workloads consistently across the hybrid cloud, on bare metal, or virtualized environments.

Solution Pattern

AI applications with Red Hat and NVIDIA AI Enterprise

Create a RAG application

Red Hat OpenShift AI is a platform for building data science projects and serving AI-enabled applications. You can integrate all the tools you need to support retrieval-augmented generation (RAG), a method for getting AI answers from your own reference documents. When you connect OpenShift AI with NVIDIA AI Enterprise, you can experiment with large language models (LLMs) to find the optimal model for your application.

Build a pipeline for documents

To make use of RAG, you first need to ingest your documents into a vector database. In our example app, we embed a set of product documents in a Redis database. Since these documents change frequently, we can create a pipeline for this process that we’ll run periodically, so we always have the latest versions of the documents.

Browse the LLM catalog

NVIDIA AI Enterprise gives you access to a catalog of different LLMs, so you can try different choices and select the model that delivers the best results. The models are hosted in the NVIDIA API catalog. Once you’ve set up an API token, you can deploy a model using the NVIDIA NIM model serving platform directly from OpenShift AI.

Choose the right model

As you test different LLMs, your users can rate each generated response. You can set up a Grafana monitoring dashboard to compare the ratings, as well as latency and response time for each model. Then you can use that data to choose the best LLM to use in production.

Download pdf icon

An architecture diagram shows an application built using Red Hat OpenShift AI and NVIDIA AI Enterprise. Components include OpenShift GitOps for connecting to GitHub and handling DevOps interactions, Grafana for monitoring, OpenShift AI for data science, Redis as a vector database, and Quay as an image registry. These components all flow to the app frontend and backend. These components are built on Red Hat OpenShift AI, with an integration with ai.nvidia.com.

Keep reading

Checklist

Top 5 ways to implement MLOps successfully in your organization

Learn how Red Hat OpenShift can help you on your MLOps implementation journey.

Special Study

The Total Economic Impact™ of Red Hat Hybrid Cloud Platform for MLOps

This commissioned study, conducted by Forrester Consulting on behalf of Red Hat, revealed a 210% ROI over 3 years for a composite organization.

E-book

Top considerations for building a production-ready AI/ML environment

Start your business transformation with this resource, which discusses artificial intelligence, machine learning, and deep learning for actionable data analysis.

More about OpenShift

Products

Red Hat® OpenShift® provides a centralized collaboration platform to help your organization scale DevOps.

Red Hat® Developer Hub provides the tools to build an internal developer platform, a critical part of maintaining a DevOps culture.

Red Hat® Trusted Software Supply Chain helps organizations build security into the software development life cycle from the start.

Red Hat® Ansible® Automation Platform automates the major stages of CI/CD pipelines, becoming the activating tool of DevOps methodologies.

Resources

Training

Free training course

Running Containers with Red Hat Technical Overview

Free training course

Developing Cloud-Native Applications with Microservices Architectures

Free training course

Containers, Kubernetes and Red Hat OpenShift Technical Overview

Interactive labs

Learn about Red Hat® OpenShift with step-by-step interactive lessons designed for hands-on practitioners.