Version: 3.x

Deploying a Rasa Assistant

This section explains when and how to deploy an assistant built with Rasa. It will allow you to make your assistant available to users and set you up with a production-ready environment.

note

Are you unfamiliar with Docker, Kubernetes and Helm? Check out "Understanding Rasa Deployments" on our YouTube channel.

When to Deploy Your Assistant

The best time to deploy your assistant and make it available to test users is once it can handle the most important happy paths or is what we call a minimum viable assistant. Then you can use incoming conversations to inform further development of your assistant.

Connecting your deployed assistant to Rasa X makes it easy to share your assistant with test users via the share your assistant feature in Rasa X. Then, when you're ready to make your assistant available via one or more Messaging and Voice Channels, you can add them to your existing deployment set up. See the Rasa X Installation Guide to learn how to deploy Rasa X and connect it to your Rasa Open Source deployment.

Recommended Deployment Method

The Rasa Helm chart is the production ready method to deploy your assistant on a Kubernetes or Openshift cluster. For details, see the deployment instructions.

Cluster Requirements

To install the Rasa Helm chart, you need an existing Kubernetes cluster or OpenShift cluster. If you don't have one yet, you can get a managed cluster from a cloud provider like:

If you are looking for a lightweight, non-production cluster that can run on a single machine, check out the instructions for using Rasa Ephemeral Installer (REI). REI will help you set up a local Kubernetes cluster on which you can deploy your assistant using the Rasa Helm chart.

Alternative Deployment Methods

The following deployment methods are not suited to a production deployment, but can be useful for development and testing: