Getting Started: The Tools Used

The Project MAS builds upon the material taught in the Multi-Agent Systems course. You will use some additional tools and software to develop your recipe recommendation agent in this project. We provide a brief overview of the tools you need to use throughout the project:

Dialogflow: We use Google Dialogflow for translating spoken user utterances into text by means of automatic speech recognition, for classifying these texts by means of intent recognition, and for generating the speech of the agent. One of your main tasks will be designing an intent scheme and adding entities for making sense of what a user says. You will need to specify these in a Dialogflow agent, which you need to create at the start of the project.
GitHub: We use GitHub classroom to provide you with the initial agent code. GitHub is a development platform. You need to join the GitHub classroom and use it for developing and sharing your code.
MARBEL: You will develop your recipe recommendation agent using MARBEL and SWI Prolog. The MARBEL agent implements a dialog engine that you will use. You do not need to change this agent, but you are allowed to modify it if you like. The focus will be mostly on using Prolog to provide the agent with the knowledge it needs and to make it smarter by providing it with some logic related to its task.
SIC: We will make use of the Social Interaction Cloud (SIC) which runs in a Docker container. The agent will connect with this infrastructure to be able to interface with a browser for displaying a webpage for visual support and Dialogflow for voice-based user interaction. For programming, the browser, Bootstrap, a front-end open-source toolkit for building websites will be used.

To get started with this project, you (and your group members) need to set up the software tools listed.

3: Install MARBEL

We assume that you have already installed Eclipse and the MARBEL plug-in. If not, please follow the instructions here. Please check whether you are using the latest version of the plug-in by using the Eclipse menu (Help → Check for Updates).
INSTRUCTIONS ON GIT REPO AND DOWNLOAD OF PROJECT FILE
Launch Eclipse, make a new workspace, and import (select File then Import) the MARBEL dialog manager project from GitHub.
Add the downloaded JSON key file of your Dialogflow agent to the project directory.
In the.mas2g file, specify as flowkey the name of the JSON key file, and as flow agent the agent ID (click here to see more details).

5: Launch the conversational agent system

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 sic-local in the docker folder.
Enter java -jar computer-browser.jar and hit enter. This will lead to a new browser window. Press ‘Ok’ without filling in a password.
Run the .mas2g file.
Check the boxes ending with ‘browser' and 'robot’ in the subsequently appearing window, and press 'OK'.

After running java -jar computer-browser.jar a pop-up should appear like the one in the left-hand corner of the picture below. Click okay without filling in a username and password.

Then a google chrome window should open. It should say it is being controlled by automated test software and display long string of random characters. In your terminal it should say ‘ChromeDriver was started successfully’ in one of the lines.

When you run the .mas2g file in your agent, another popup should appear like the one in the left-hand corner of the picture below. The empty box should be ticked next to the browser code that matches your google chrome window code, and then you hit OK

You should now see a window rendering the browser plug-in and hear the agent start talking. The rest now is up to you!