Rasa: Open Source Language Understanding and Dialogue Management

TLDR

Rasa introduces open‑source tools Rasa NLU and Rasa Core to enable non‑specialist developers to build conversational software with machine‑learning based dialogue management and language understanding, emphasizing ease of use and minimal training data. Rasa NLU and Rasa Core are implemented as open‑source Python libraries that are extensively documented and shipped with comprehensive test suites, facilitating easy deployment and minimal training data bootstrapping. Code is available at https://github.com/RasaHQ/.

Abstract

We introduce a pair of tools, Rasa NLU and Rasa Core, which are open source python libraries for building conversational software. Their purpose is to make machine-learning based dialogue management and language understanding accessible to non-specialist software developers. In terms of design philosophy, we aim for ease of use, and bootstrapping from minimal (or no) initial training data. Both packages are extensively documented and ship with a comprehensive suite of tests. The code is available at https://github.com/RasaHQ/