Flowstorm: Open-Source Platform with Hybrid Dialogue Architecture
Jan Pichl, Petr Marek, Jakub Konr\'ad, Petr Lorenc, Ond\v{r}ej Kobza,, Tom\'a\v{s} Zaj\'i\v{c}ek, Jan \v{S}ediv\'y

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.…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
MethodsLib
