Flowstorm: Open-Source Platform with Hybrid Dialogue Architecture

TL;DR

Flowstorm is an open-source conversational AI platform that combines tree-based and generative dialogue architectures, enabling rapid development, customization, and reuse of conversational applications with a user-friendly interface.

Contribution

The paper introduces a novel hybrid dialogue architecture integrating tree structures with generative models and provides an open-source platform with reusable assets and extensible components.

Findings

Fast, automated dialogue execution within seconds

Effective integration of tree and generative models for dialogue management

Reusable asset library enhances development efficiency

Abstract

This paper presents a conversational AI platform called Flowstorm. Flowstorm is an open-source SaaS project suitable for creating, running, and analyzing conversational applications. Thanks to the fast and fully automated build process, the dialogues created within the platform can be executed in seconds. Furthermore, we propose a novel dialogue architecture that uses a combination of tree structures with generative models. The tree structures are also used for training NLU models suitable for specific dialogue scenarios. However, the generative models are globally used across applications and extend the functionality of the dialogue trees. Moreover, the platform functionality benefits from out-of-the-box components, such as the one responsible for extracting data from utterances or working with crawled data. Additionally, it can be extended using a custom code directly in the platform. One of the essential features of the platform is the possibility to reuse the created assets across applications. There is a library of prepared assets where each developer can contribute. All of the features are available through a user-friendly visual editor.