Skip to end of banner
Go to start of banner

How to set up ChatGPT for x-hoppers

Skip to end of metadata
Go to start of metadata

You are viewing an old version of this page. View the current version.

Compare with Current View Page History

Version 1 Current »

This guide explains how to configure ChatGPT feature for x-hoppers.

Created: June 2024

Permalink: 

Other documentation: x-hoppers User Guidex-hoppers datasheet, x-bees documentation

Introduction

ChatGPT integration with x-hoppers can enhance customer support and information sharing, allowing to ask questions and instantly receive answers. Powered by ChatGPT, x-hoppers processes the questions and generates the response based on its knowledge base, which is then played back to the user through the broadcast channel.  

Requirements 

  • WMS 6 

How to set up 

  1. In WMS, navigate to Dialplan menu -> Dialplan rules tab
  2. Download and import the "ChatGPT" Dialplan procedure.bkp required for ChatGPT Integration
  3. Modify the users Dialplan by adding an entry *wair* as a called number with the following Dialplan applications:
    1. Set -> Language -> choose language

    2. Speech to text -> insert Please unmute and say question for Chat GPT, or wait to join the broadcast or any customized text

    3. Jump to if -> "${RECOGNITION_RESULT}"="question" -> select ChatGPT procedure

    4. Play sound -> click Browse (three dots) and choose the sound to be played on joining the broadcast or create it dynamically using TTS, for example Welcome to x-hoppers, joining the broadcast

    5. Conference -> enter the conference room ID number. This can be any number, e.g. 1, 2, 3, etc

How to use 

For the current development stage, users are limited to asking one question. To ask another question user has to double-press the AUX Function button.

  1. User asks a question (e.g. Could you compare and contrast the following two products: an Asus Vivobook 15 and a Samsung Galaxy Book 3? Is the discontinued EXPEDIT series compatible with KALLAX? etc.)
  2. x-hoppers, powered by ChatGPT, processes the question and generates an appropriate response based on its knowledge base
  3. The response is then played back to the headset


  • No labels