The Rasa Blog
Welcome to the new home of the Rasa Blog!
February 21st, 2020
Unpacking the TED Policy in Rasa Open Source
Karen White
We’ll explore dialogue management by taking a close look at one of the machine learning policies used in Rasa Open Source: The Transformer Embedding Dialogue Policy, or TED.
February 20th, 2020
The Humans Behind the Bots: Sam Gaus
Rasa
The people of Rasa come together from diverse backgrounds to solve today’s most interesting challenges in NLP and building AI assistants. Today we’re talking with Sam Gaus, Full Stack Engineer at Rasa.
February 13th, 2020
The Rasa Masterclass Handbook: Episode 11
Rasa
In this episode, we’ll make the assistant available to real users on two publicly accessible messaging channels: Telegram and a website chat widget.
February 5th, 2020
Welcome back, Sara!
Rasa
If you’ve visited the Rasa documentation site lately, you may have noticed a familiar (feathery) face. Sara, the Rasa demo assistant, is back.
February 4th, 2020
Rasa Community Superhero Spotlight: Souvik Ghosh
Emma Jade Wightman
Souvik has an outstanding track record of supporting the Rasa community. He's the only member to obtain the Aficionado badge, which is only achieved by visiting the forum for 100 consecutive days.
January 28th, 2020
Train on Larger Datasets Using Less Memory with Sparse Features
Tanja Bunk
With Rasa 1.6.0 we released sparse features for the NLU pipeline. In this short blog post, we explain what sparse features are and show that we now can train on larger datasets using less memory.
January 28th, 2020
Model Testing and CI for Conversational AI Software
Alan Nichol
An AI assistant is a product, and just because that product uses machine learning doesn’t mean you should give up on good software engineering habits.
January 23rd, 2020
The Rasa Masterclass Handbook: Episode 10
Rasa
In this episode, we will cover inviting guest testers to talk to your assistant, reviewing the collected conversations, and improving your assistant based on those conversations.
January 22nd, 2020
The Rasa Masterclass Handbook: Episode 9
Rasa
In this episode we’ll discuss why you should use Rasa X, demonstrate how to deploy Rasa X to Google Cloud Platform, and connect the Rasa X instance to the medicare locator assistant.
January 16th, 2020
Link Rasa X with Git-Based Development Workflows
Rasa
As of Rasa X version 0.23.0, we’ve added a new feature that allows developers to version training data by connecting Rasa X with a Git repository on a remote server.
January 15th, 2020
The Humans Behind the Bots: Ella Rohm-Ensing
Rasa
The people of Rasa come together from diverse backgrounds to solve today’s most interesting challenges in NLP and building AI assistants. Today we’re talking with Ella Rohm-Ensing, Solutions Architect at Rasa.
January 14th, 2020
The Rasa Masterclass Handbook: Episode 8
Rasa
In Episode 8, we focus on developing the medicare locator assistant by adding custom actions that interface with backend integrations, implementing FormAction, and adding a fallback policy.
January 10th, 2020
The Rasa Masterclass Handbook: Episode 7
Rasa
In Episode 7 of the Rasa Masterclass, we cover dialogue policies. Policies are components that train the dialogue model, and they play a very important role in determining its behavior.
January 3rd, 2020
The Rasa Masterclass Handbook: Episode 6
Rasa
In Episode 6 of the Rasa Masterclass, we cover essential components in building dialogue management models with Rasa, including domain, custom actions, slots, and more.
January 2nd, 2020
The Rasa Masterclass Handbook: Episode 5
Rasa
In Episode 5 of the Rasa Masterclass, we introduce dialogue management, which is controlled by a component called Rasa core. Dialogue management is the function that controls the next action the assistant takes during a conversation.