Google Launches Cloud AI Platform Pipelines

Google announced the launch of Cloud AI Platform Pipelines. Cloud AI Platform Pipelines(currently in beta) offers a way to deploy robust, repeatable ML pipelines along with monitoring, auditing, version tracking, and reproducibility.
 
The company said that Cloud AI Platform Pipelines delivers an enterprise-ready, easy to install, secure execution environment for machine learning workflows.
 
AI Platform Pipelines provides push-button installation via the Google Cloud Console, enterprise features for running ML workloads, seamless integration with Google Cloud managed services like BigQuery, Dataflow, and many others, as well as many prebuilt pipeline components (pipeline steps) for ML workflows.
 
According to Google AI Platform Pipelines comprises of two major parts, first one is the enterprise-ready infrastructure for deploying and running structured ML workflows that are integrated with GCP services; and the other one is the pipeline tools for building, debugging, and sharing pipelines and components.
 
When working with AI Platform Pipelines, you can specify a pipeline utilizing the Kubeflow Pipelines (KFP) SDK, or by customizing the TensorFlow Extended (TFX) Pipeline template with the TFX SDK. The SDK compiles the pipeline and tenders it to the Pipelines REST API.
 
 
Source: Google 
 
According to Google, the AI Pipelines REST API server does the storing and scheduling of the pipeline for execution. Another important thing to note is that AI Pipelines makes use of the Argo workflow engine in order to run the pipeline and has additional microservices to record metadata, handle components IO, and schedule pipeline runs.