Conversational AI
For updates regarding how we utilize, improve upon, and explore conversational AI technologies, check out this category for related blog posts!
June 17th, 2020
5 Levels of Conversational AI: 2020 Update
Alan Nichol
Since we first published the 5 levels of AI assistants, the market and tech have changed, and it’s time for an update. End users are already telling us what they want from AI assistants, and to get to level 5 we “just” have to listen.
April 24th, 2020
New Rasa Starter Pack: IT Helpdesk
Rasa
This assistant is a great starting point for building an IT helpdesk chatbot of your own, or you can use it as a reference implementation for integrating with a customer service ticketing system.
April 20th, 2020
Visualise Word-Embeddings with Whatlies
Vincent Warmerdam
We're happy to announce that we're open sourcing a visualisation tool!
March 9th, 2020
Introducing DIET: State-of-the-art architecture outperforms BERT
Mady Mantha
With Rasa 1.8, our research team is releasing a new state-of-the-art lightweight, multitask transformer architecture for NLU: Dual Intent and Entity Transformer (DIET).
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.
December 17th, 2019
Rasa Open Source + Rasa X: Better Together
Rasa
We recently launched Rasa X, a free toolset that helps you quickly iterate on and improve the quality of your contextual assistant built using Rasa Open Source.
September 5th, 2019
Pruning BERT to accelerate inference
Samuel Sučík
After previously discussing various ways of accelerating models like BERT, in this blog post we empirically evaluate the pruning approach.…
August 27th, 2019
Build an AI Voice Assistant with Rasa and Mozilla Tools
Justina Petraitytė
What if you wanted to build and assistant that runs locally and ensures the privacy of your data? You can do it using Rasa Open Source, Mozilla DeepSpeech and Mozilla TTS tools. Check out this tutorial to find out how.
August 15th, 2019
Customizing Training Data Importing
Tobias Wochinger
Since Rasa version 1.2 you can customize the way Rasa imports training data for the model training. This tutorial shows you how to use provided out-of-the-box components or how to build your own importer module and plug it into Rasa.
August 8th, 2019
Compressing BERT for faster prediction
Samuel Sučík
Let's look at compression methods for neural networks, such as quantization and pruning. Then, we apply one to BERT using TensorFlow Lite.
June 26th, 2019
Building a Common Language for Conversational AI
Alan Nichol
We start creating a common language to talk about the structure of conversations with AI assistants.
May 21st, 2019
Algorithms Alone Won’t Solve Conversational AI
Alan Nichol
We're excited to announce Rasa X, our new product for developers in early access. Also, our open source framework Rasa is now available in 1.0
April 18th, 2019
Announcing the Rasa Contributor Program
Justina Petraitytė
The Rasa open source community is growing faster than ever. Today we are excited to announce a new community initiative - we’re introducing the Rasa Contributor Program!
April 11th, 2019
What our new funding means for our developer community
Alex Weidauer
We’ll double-down on open source, new developer tools and machine learning research to build the standard infrastructure layer for conversational AI
March 19th, 2019
Designing Rasa training stories
Justina Petraitytė
Training data is an essential part of every machine learning model. In this post, we are going to cover the best practices of designing Rasa training stories and what you should keep in mind to build your best conversational AI assistant.