Rasa Masterclass Series

The Rasa Masterclass is a video series (and supplemental blog series) that takes viewers through the process of building an AI assistant, all the way from idea to production. Hosted by Rasa Head of Developer Relations Justina Petraityte, each episode focuses on a key concept of building sophisticated AI assistants with Rasa and applies those learnings to a hands-on project. At the end of the series, viewers will have built a fully-functioning AI assistant that can locate medical facilities in US cities. 

Download the ebook: get our 170-page companion guide to the Rasa Masterclass video series—no email required.

Intro to conversational AI assistants and Rasa 

In this episode, you'll learn: what a contextual assistant is and how it differs from other types of assistants, how to install Rasa, the different components of Rasa and what they do, and how to get started building an AI assistant with Rasa.

Creating the NLU training data

In this episode, you'll learn: the basics of conversation design, how to format your assistant’s NLU training data, and how to define intents and entities.

Training the NLU model: pre-configured pipelines

In this episode, you'll learn: what a processing pipeline is, which pre-configured pipelines to get started with, how to train your first NLU model, and how to interpret the output of the model.

Training the NLU models: understanding pipeline components

In this episode, you'll learn: about training pipeline components, developer's frequently asked questions when training NLU models, and what’s happening under the hood when a model is trained.

Intro to dialogue management with Rasa

In this episode, you'll learn: why machine learning based dialogue management scales better than the rule based approach, and the fundamentals of creating training stories for dialogue management models.

Domain, custom actions, and slots

In this episode, you'll learn: about domains and how to define one, how to create custom actions, how to use slots and which types are available in Rasa, and how to train and test your first dialogue management model.

Dialogue Policies

In this episode, you'll learn: which training policies are available in Rasa, how to configure them, and in which situations you would use one policy over another.

Implementing custom actions with backend integrations, forms and fallback

In this episode you'l learn: how to implement custom actions, how to implement the `FormAction` method, and how to enable your assistant to fail gracefully.


Additional Resources

Improving the assistant: Setting up the Rasa X

In this episode, you'll learn: how to set up Rasa X , how to use Rasa X integrated version control, and how to deploy Rasa X on a server and connect your assistant to it.

Improving the assistant: sharing with real testers

In this episode, you'll learn: how to invite guest testers to talk to your assistant, how Rasa X enables you to review conversations, and how to improve your assistant based on real conversations.

Connecting an assistant to external messaging channels

In this episode, you'll learn: how you can connect your assistant to external channels like Telegram and your own custom website and allow a wide audience of users to talk to your assistant.

Rasa masterclass handbook episode 11
Additional Resources

Deploying Rasa X in a Cluster Environment

There are two ways to deploy Rasa X on a server - using Docker Compose or Kubernetes/OpenShift. In this episode, you'll learn: the step-by-step process of how you can deploy Rasa X with Kubernetes.

The Recap

In this episode, we will  summarize everything we've learned through the series.


Additional Resources