Chat-IBN-RASA: Building an Intent Translator for Packet-Optical Networks based on RASA
Celso H. Cesila, Rossano P. Pinto, Kayol S. Mayer, Andrés F. Escallón-Portilla, Darli A. A. Mello, Dalton S. Arantes, Christian Esteve Rothenberg
Abstract
This work presents Chat-IBN-RASA, a conversational AI chatbot based on the open-source RASA framework, acting as an Intent Translator component for Intent-Based Networking (IBN) architectures. The IBN-driven RASA chatbot allows users to interact with the network management system using high-level language communication without the need for in-depth technical knowledge of the network. The chatbot is trained using Natural Language Understanding (NLU) models, a defined domain, stories, and custom actions for API communication and database queries. We present the prototype implementation in a use case of survivability intents in packet-optical networks. The custom actions featured include communication with the network database, path computation, and the recommended path for intent deployment, considering availability, protection type, data rate, and link distances.