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

« Previous Version 4 Next »

Environmental Setup

To work on the project assignment, you will need to have installed / set-up the following components:

  1. The GOAL plug-in for Eclipse. We assume that you have already installed Eclipse and this plug-in, otherwise please follow instructions here. Be sure to create a new project whilst using the latest version of the Eclipse plug-in (Help → Check for Updates).

  2. The Social Interaction Cloud (SIC) framework. For this, you can follow the instructions here.
    Browser software for displaying the chat window. Has been confirmed to work only with Google Chrome (can be downloaded here).

  3. A cooking assistant designed using Dialogflow. For this, you can follow the instructions here.

Launching a Chatbot

We assume here that you have installed the SIC framework and know how to navigate to a folder in a terminal, and in addition to have created a Dialogflow agent and downloaded its .json keyfile (see here for an explanation). To launch the chatbot provided to you, do the following:

  • Open a command terminal and navigate to the folder where you cloned the docker project

  • Enter docker-compose up dialogflow webserver and hit enter.

  • Open a second terminal and navigate to the subfolder cbsr-local in the docker folder.

  • Enter java -jar computer-browser.jar and hit enter. This will lead to a new Google chrome window.

  • Launch Eclipse and import the GOAL dialog manager project (including the .json keyfile of your Dialogflow agent).

  • In the .mas2g file, specify as flowkey the name of the .json keyfile, and as flowagent the agent ID (click here to see more details).

  • Run the .mas2g file.

  • Press okay in the appearing Connection information window without specifying a password.

  • Check the box ending with 'tablet' in the subsequently appearing window, and press 'OK'.

  • You should now see a chat window rendering in the browser plug-in, as below. Note that the chatbot will initially not open the conversation with a greeting, but a recipe instruction.


  • No labels