Versions Compared

Key

  • This line was added.
  • This line was removed.
  • Formatting was changed.

The Project CA 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 will use git, Dialogflow, Prolog and , MARBEL, and Bootstrap for visuals. For more on these, see the Project Background Knowledge. To connect these different tools, 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. Below you’ll find the instructions for setting up everything on your computer.

Set-Up

1: Join Discord and GitHub Classroom and Clone the Student Project

Info

Hot Tip: GitHub has a great education package if you sign up with your student email https://education.github.com/pack#offers

  • Join the GitHub classroom via this link: LINK STILL NEEDS TO BE ADDED. WE’LL ANNOUNCE THIS VIA CANVAS https://classroom.github.com/a/HP8FeZ1C. Only one member of your team (the first to join) needs to make a team in the classroom. Please use the following naming convention: group-n, where n is your group number.

  • Clone the project repository on your local device: copy the HTTPS link from the GitHub Classroom and execute git clone <COPY PASTE HTTPS LINK HERE> inside a terminal in a folder in your user directory.

2: Install MARBEL

  • You may have already installed Eclipse and the MARBEL plug-in. If so, please check whether you are using the latest version of the plug-in by using the Eclipse menu (Help → Check for Updates). If not, pleasehttps://goalapl.atlassian.net/wiki/spaces/GOAL/pages/2143977473/Download+and+Install+the+MARBEL+Plugin.

  • Launch Eclipse (You can choose to create a new workspace if you like).

  • Go to Window → Preferences (or on Mac: Eclipse → Settings) → MARBEL Logging and check the box for the `Write logs to files’ option; then go to MARBEL Runtime and uncheck the box for `Include initial KR updates’.

  • Additionally, navigate to the Logging (should be right above Runtime) and check your logging preferences. The following boxes under Logging should be checked:

    • Under Log Handling “Show an action history whilst debugging”, “Show a console per agent whilst debugging”

    • Under Logging Options “The reasoning cycle separator”, Going to sleep or waking up”, “User-specified actions that have been executed”, “Initializing changes in KR”, “Changes in the KR”

Note

Make sure to set the these preferences. Without unchecking the runtime option, it will be hard if not impossible to run your agent in Debug Mode. Checking the logging option options will enable saving log files to a folder automatically, which will be useful for analyzing your agent’s behavior (conversations) and is needed to collect the required conversation data. Also note your Logging Directory!

  • Import the MARBEL dialog manager project in Eclipse by selecting File → Import → MARBEL Agent Programming → Existing MARBEL Project, clicking Next, browsing to the agent folder in which you cloned the project, and selecting the dialogmngr.mas2g file, clicking Open, and finally, clicking Finish.

Note

Do not check the option Copy into workspace! If you import the project into Eclipse, you should be able to see on what branch you are working in your git repository and be able to make use of git functionality available in Eclipse.

3: Install SIC

Please follow the instructions on the SIC Installation page.

Note

Make sure to install SIC in a different folder than your Eclipse workspace.

Note

Only works with Google Chrome, which you therefore also need and can download here:https://www.google.com/chrome/.

4: Run it!

You are now ready to run your agent. Check out this page on how to run your agent Run your Conversational Agent.