Kubernetes Operator for Seldon Core

Seldon Core simplifies the deployment of machine learning models (Tensorflow, Pytorch, H2o, etc.) by wrapping and converting them into REST/gRPC microservices that can be readily consumed by other applications.

It efficiently scales to support thousands of models and offers advanced features like advanced metrics, request logging, explainers, outlier detectors, A/B tests, canaries and more.

Key benefits include easy containerization, cloud-agnostic compatibility, powerful inference graph creation, metadata provenance, customizable metrics, auditability, distributed tracing, and robust security measures.

You can deploy Seldon Core in your Nebius AI Managed Service for Kubernetes clusters using this Marketplace product.

Before installing this product, create a Kubernetes cluster and a node group in it, install kubectl, and configure it to work with the created cluster.

To install the product:

1. On the cluster page in the management console, go to the Marketplace tab, select the product, and click Install.

2. Configure the application:

   • Namespace: Select a namespace or create a new one.
   • Application name: Enter an application name.

3. Click Install.

4. Wait for the application to change its status to Deployed.

For usage instructions, see prepackaged inference server examples in Seldon Core documentation.

• Deploy generative AI models for marketing content such as product descriptions and social media posts.

• Design agencies can use Seldon Core to assist in creative design tasks such as generating logo concepts, website layouts, or artwork.

• Retailers can deploy generative AI models for virtual fashion try-on experiences.

• Content creators can deploy models to generate interactive storytelling experiences, such as chatbots or choose-your-own-adventure narratives.

• Non-generative AI scenarios and more.

Nebius AI does not provide technical support for the product. If you have any issues, please refer to the developer’s information resources.