Rasa

-> to BOTwiki - The Chatbot Wiki

Rasa is a Conversational AI Platform, which provides open source software to create Contextual AI Assistants and Chatbots with the Rasa Stack. In addition to the free Rasa Stack, there is also the Rasa Platform. This also relies on the Rasa Stack, but offers enterprise customers additional features such as a user interface with functionalities such as the Training Data, Admin, Conversations and Models API. Rasa is developed by the eponymous start up with headquarters in Berlin, and there are over 300 contributors who bring Rasa forward in the open source sense. [1][2]

Structure of the Rasa Stack

The Rasa Stack will be installed in Rasa NLU and Rasa Core divided. These are designed in such a way that they can be used completely independently of each other. This allows only part of the architecture to be built on Rasa and additional services to be integrated. Despite this fact, the two components are very well matched to each other and are therefore quickly configured. The Rasa NLU takes over the tasks of the intent Recognition and Entity Extraction, Rasa Core on the other hand, the complete session management, Context handling and bot responses. [3]

Advantages and disadvantages of Rasa

The first thing to address is the advantage of open source thinking. On the one hand, you are not dependent on paid licenses, and on the other hand, a very high use case-specific configuration is possible by viewing the entire source code. For example, industry-specific terms such as "cash" and "balance", which have the same meaning in the banking environment, but generally need to be distinguished, can be better represented in a chatbot. Of course, this also results in the fact that one has to deal with it more intensively in order to get an optimal solution when comparing it with finished solutions such as Dialogflow from Google or LUIS from Microsoft.
In addition to ready-to-configure solutions, they also offer hosting of the service. Because unlike these cloud solutions, Rasa On Premise runs. This gives you complete control over the data generated by the chatbot, but a powerful server must also be made available. Another advantage is the possibility to use Rasa completely offline. Thus the use in offline systems, for example IoT devices, is convertible. [4]

> Back to the BOTwiki - The Chatbot Wiki

Sources

[1] https://www.gartner.com/en/documents/3879492
[2] https://rasa.com/about
[3] https://rasa.com/docs/
[4] https://rasa.com/docs/