Rasa recently announced their new major release Rasa Open Source 3.0, to help build better conversational AI of the future. It separates the model architecture from the framework architecture, enabling developers to run arbitrary model architectures. It also comes with several enhancements focused on improving the developer experience when building conversational AI assistants with Rasa.

The revamped computational backend empowers to experiment with architectures, reducing maintenance costs and enabling collaborative development at scale. There have also been improvements to slot mappings that will make it easier to implement desired slot behaviour as well as forms. 

A new experimental feature known as ‘Markers’ has also been introduced, which is intended to help figure out how to add a “semantic layer” on top of the tracker store of events that makes it easier to identify and track situations of interest in conversations.

The new graph architecture aims to make it easier to understand the relationship between the NLU and policy components in the pipeline. It is now much easier to define and modify the dependencies between the training pipeline components. The beauty of graph architecture is that it makes it possible to save trained components on disc. This means that if a change is made to a specific component, only that component will need to be retrained. This should save a lot of computational resources and reduce training time.

In the past, if you had an entity and a slot defined with the same name, Rasa would automatically fill the slot with the value of the extracted entity. While this sometimes saves a little bit of development time, it has often led to undesired behaviours (slots being filled in when they shouldn’t have been) and confusion when implementing forms with slot mappings.

With Rasa Open Source 3.0, this behaviour has been updated. From now on, it will be necessary to define global slot mappings for all slots defined in a domain file. Those mappings will have to be defined inside of the slots section of your domain.

Markers are conditions that allow you to describe and mark points of interest in the dialogue for evaluating your assistant. With markers, developers will be able to describe specific points, like when an action has been executed, the intent has been classified correctly, or a slot has been set.

With every Rasa Open Source release, Rasa aims to make it easier for developers to build conversational AI assistants. The team says that the new features and improvements were crucial to making sure that the changes made tackle the most pressing needs of the developer community.