Rasa Core

-> to BOTwiki - The Chatbot Wiki

Rasa Core forms together with Rasa NLU the Rasa Stack. He is responsible for having as natural a conversation with the user as possible. [1]


Rasa Core is responsible for the conversation flowContext-Handling, Bot-Responses and Session Management. This can be based on the Rasa NLU or other services that use the intent Recognition and Entity Extraction and make the results available to the Rasa Core. [1]


The Rasa Core holds a tracker for each session, i.e. for each user. This contains the current state of the conversations of the respective users. If the bot now receives a message, it first runs through the interpreter, which receives the original text as input and returns the input, the intent and the extracted entities. Together with the current state of the tracker, the Policy component now decides which action (Bot Response) should be executed next. This decision is not made by simple rules, but just like intents or entities, on the basis of a model trained with machine learning.

You have influence on these processes at several points. First of all this is the configuration of the interpreter, respectively the Rasa NLU. This should reliably recognize the correct intents and extract all required entities. The Policy component can also be configured Use Case specifically in a dedicated file (policy.yml).

You can choose between several policies, where you can make even more precise adjustments. The action is the Bot Responses. In doing so, the simple text can provide answers, Quick Repliespictures or action webhooks. The latter send a POST request to a predefined interface and from where the responses are sent. This allows API calls or database accesses, for example, to be realized. [2] [3]

> Back to the BOTwiki - The Chatbot Wiki


[1] https://rasa.com/docs/
[2] https://rasa.com/docs/core/policies/
[3] https://rasa.com/docs/core/architecture/