Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Low-code from frontend to backend: Connecting conversational user interfaces to backend services via a low-code IoT platform

Irene Weber

TL;DR

An architecture with a chatbot as frontend using an IoT platform as a middleware for connections to backend services, allowing low-code or no-code development of a transactional conversational user interface from frontend to backend.

Abstract

Current chatbot development platforms and frameworks facilitate setting up the language and dialog part of chatbots, while connecting it to backend services and business functions requires substantial manual coding effort and programming skills. This paper proposes an approach to overcome this situation. It proposes an architecture with a chatbot as frontend using an IoT (Internet of Things) platform as a middleware for connections to backend services. Specifically, it elaborates and demonstrates how to combine a chatbot developed on the open source development platform Rasa with the open source platform Node-RED, allowing low-code or no-code development of a transactional conversational user interface from frontend to backend.

Low-code from frontend to backend: Connecting conversational user interfaces to backend services via a low-code IoT platform

TL;DR

An architecture with a chatbot as frontend using an IoT platform as a middleware for connections to backend services, allowing low-code or no-code development of a transactional conversational user interface from frontend to backend.

Abstract

Current chatbot development platforms and frameworks facilitate setting up the language and dialog part of chatbots, while connecting it to backend services and business functions requires substantial manual coding effort and programming skills. This paper proposes an approach to overcome this situation. It proposes an architecture with a chatbot as frontend using an IoT (Internet of Things) platform as a middleware for connections to backend services. Specifically, it elaborates and demonstrates how to combine a chatbot developed on the open source development platform Rasa with the open source platform Node-RED, allowing low-code or no-code development of a transactional conversational user interface from frontend to backend.
Paper Structure (15 sections, 6 figures)

This paper contains 15 sections, 6 figures.

Table of Contents

  1. Introduction
  2. Architecture of Conversational User Interfaces
  3. Standard architecture of a conversational user interface
  4. Proposed architecture for Rasa CUIs with Node-RED
  5. Implementing the Rasa Action Server HTTP API on Node-RED
  6. Node-RED Basics
  7. Custom nodes implementing the Rasa action server HTTP API
  8. Example application
  9. Building the action server flow
  10. HTTP Endpoint
  11. Branching into specific actions
  12. Generating responses and slot-setting events
  13. Calling external APIs
  14. Developing, deploying and debugging
  15. Discussion and future work

Figures (6)

  • Figure 1: Typical architecture of a conversational interface, adapted from mctear_conversation_2018rough_dont_2020
  • Figure 2: Architecture of a conversational user interface based on Rasa
  • Figure 3: Sample dialog, using the chatroom of scalableminds_github_2020
  • Figure 4: Node-RED Flow editor with an example flow implementing an action server, i.e., fulfillment component, for a Rasa conversational user interface. To the left, the network section of the Node-RED palette is partially visible.
  • Figure 5: Example configuration of a switch node in Node-RED
  • ...and 1 more figures