Embeddable AI

Caikit is an AI toolkit that enables users to manage models through a set of developer-friendly APIs.

IBM Generative AI is the Python SDK for IBM Foundation Models Studio to bring IBM Generative AI into Python programs and to also extend it with useful operations and types.

A standard cloud-agnostic model inference platform that provides pluggable production serving.

A mature, general-purpose model serving management and routing layer. Optimized for high volume, high density, and frequently changing model use cases, ModelMesh intelligently loads and unloads models to and from memory to strike a balance between responsiveness and compute.

A machine learning toolkit that makes deployments of machine learning workflows on Kubernetes simple, portable, and scalable.

An open-source platform that allows users to create, deploy, and manage machine learning workflows on Kubernetes. Kubeflow Pipelines provides a way to define and execute complex pipelines consisting of interconnected steps, enabling users to easily orchestrate the entire machine learning process from data preparation to model training, evaluation, and deployment.

Walk through the steps to deploy a stand-alone Watson NLP runtime to Google Cloud Run, a managed compute platform that lets you run containers directly on top of Google's scalable infrastructure.

Turn a web page into one with interactive help from a watsonx Assistant chatbot with a simple copy and paste operation, using code generated by the Assistant service.

A Python package that provides tensor computation and deep neural networks.

A unified framework for scaling AI and Python applications from a laptop to a Kubernetes cluster. Ray provides a compute layer for parallel processing for running distributed machine learning workflows.