Product Updates
Check out the latest and greatest of our product updates including feature updates, updates to our product strategy, and deep dives into existing product capabilities.
December 28th, 2022
Rasa Wrap: Product Recap 2022
Lauren Goerz
Here at Rasa, our mission is to empower the world’s largest brands to interpret people’s needs with open and extensible conversational AI. This past year we have demonstrated our commitment to our mission by focusing our efforts to help our customers scale their enterprise conversational AI products. Here are some of our key product milestones from 2022.
October 24th, 2022
Introducing Rasa Pro
Lauren Goerz
The Rasa Platform is made up of two product lines. Rasa Pro, our conversational AI infrastructure suite powered by Open Source, as well as Rasa X/Enterprise, our user interface. Together, these products form one platform for the automation of conversational customer experience.
August 22nd, 2022
Behind the Release Notes: Rasa X/Enterprise 1.2
Lauren Goerz
Explore the newest features in Rasa X/Enterprise 1.2. We've enhanced the annotation experience to increase productivity, and made improvements to our integrated version control (IVC) feature to ensure your progress is saved every time.
June 23rd, 2022
Behind the Release Notes: Rasa Open Source 3.2
Lauren Goerz
With over 25+ million downloads, the Rasa Open Source Framework is one of the most widely adopted conversational AI frameworks in the world. With the release of Rasa Open Source 3.2, we want to highlight some of the key improvements and fixes that we have made to advance our Open Source Framework.
October 8th, 2021
Let’s Talk about TensorFlow 2.6
Vincent Warmerdam
Rasa will upgrade from Tensorflow 2.3 to Tensorflow 2.6 as of Rasa Open Source version 2.8.9. In this blog post, we’d like to highlight why the upgrade is needed and we’d also like to advise users on what to expect. The upgrade is required due to security concerns but it may have consequences on training times in the short term.
August 12th, 2021
Non-English Tools for Rasa NLU
Vincent Warmerdam
The Rasa community spans the globe, so we often get questions on optimising a Rasa pipeline for a wide variety of languages. Rasa is…
June 22nd, 2021
Now Available in Rasa Open Source: Conditional Response Variations
Karen White
We're excited to announce the experimental release of conditional response variations, now available in Rasa Open Source 2.6.
June 10th, 2021
Rasa X Two Years Later: CDD, Data, and Customer Experience
Alan Nichol
Reflecting on changes to the market and the product in the two years since Rasa X was released.
April 19th, 2021
Why Rasa uses Sparse Layers in Transformers
Johannes Mosig
Vladimir Vlasov
Feed forward neural network layers are typically fully connected, or _dense_. But do we actually need to connect every input with every output? And if not, which inputs should we connect to which outputs?
March 4th, 2021
Exploring Semantic Map Embeddings / Part II
Rasa
Johannes Mosig
In this second part of our series on semantic maps, we show how to create them and see how they perform as featurizers for DIET.
February 24th, 2021
Exploring Semantic Map Embeddings / Part I
Johannes Mosig
We explore a new sparse text embedding that has some interesting properties.
February 23rd, 2021
Improve Your Training Data with Actionable Insights
Karen White
Insights analyzes your training data and suggests next steps to improve your data set.
December 8th, 2020
Introducing a New Rich-Text Editor for Managing Responses
Karen White
With the release of Rasa X 0.34.0, we’re excited to announce that the Responses screen has a new look and improved user experience.
October 27th, 2020
Get Creative with Rasa Playground: Build Assistants Interactively
Karen White
We’ve recently launched the Rasa Playground, an interactive prototyping tool built right into the Rasa docs.
October 16th, 2020
Introducing the Unified Rule Policy
Karen White
With the Rule Policy, we draw a clearer distinction between policies that use predefined logic and those that learn to predict the assistant’s next action from data.