Project Installation
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.
Set-Up
1: GitHub Classroom and Clone the Student Project
If you do not have one, Create a GitHub Account: https://docs.github.com/en/get-started/onboarding/getting-started-with-your-github-account
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: https://classroom.github.com/a/YMMnQU3W . Only one member of your team (the first to join) needs to make a team in the classroom. Please use the same naming convention as your canvas group.
Clone the project repository on your local device: copy the HTTPS link from the GitHub Classroom and execute
git clone <COPY PASTE SSH LINK HERE>
inside a terminal in a folder in your user directory. If you do not have access rights check this out: https://docs.github.com/en/authentication/connecting-to-github-with-ssh/adding-a-new-ssh-key-to-your-github-account
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 → 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”
Make sure to set these preferences. Without unchecking the runtime option, it will be hard if not impossible to run your agent in Debug Mode. Checking the logging options will enable saving log files 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
dialog_mngr
in which you cloned the project, and selecting thedialogmngr-pca2025-basic.mas2g
file, clicking Open, and finally, clicking Finish.
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: Make Dialogflow agent
Dialogflow Setup Instructions
Follow these steps to get a JSON keyfile that you need for the project:
4: Make Virtual Environment
Environment Setup Instructions
Follow these steps to set up your environment for the project:
Step 1: Install Redis and PyAudio
Install Redis unless you can run redis-server.exe:
Follow the guide here to do the installation, just the install do not run stuff, just the first install paragraph:
https://redis.io/docs/latest/operate/oss_and_stack/install/install-redis/Install PyAudio:
Use the instructions provided on the PyPI page but do the pip install part in your conda environment.:
PyAudio Installation GuideInstall Espeak:
Use the instructions provided here:
Espeak Website or with Mac & Homebrew https://formulae.brew.sh/formula/espeak
Step 2: Install Anaconda or Miniconda
If you don’t already have Conda installed, download and install either:
Anaconda: A comprehensive package including Conda and many pre-installed data science libraries.
Anaconda Installation GuideMiniconda: A lightweight version of Conda with fewer pre-installed packages.
Miniconda Installation Guide
Step 3: Create the Conda Environment
Locate the YAML File:
The repository contains a pre-configuredenvironment.yaml
file for the project.Create the Environment:
Open a terminal, navigate to the repository folder, and run:conda env create -f environment.yaml
Activate the Environment:
Once the environment is created, activate it with:conda activate PCA25
Step 4: Open the Repository in an IDE
Find the Cloned Repository:
Navigate to the repository folder on your computer.Use an IDE (Recommended):
Open the project in an IDE like PyCharm it is for the best.
You can find PyCharm here: PyCharm Download. You could also use https://code.visualstudio.com/ if you really want to…
Hot Tip: JetBrains offers free professional licenses for students. Learn more and apply here:
JetBrains Free Student LicensesSet Up the Interpreter in PyCharm:
Go to File > Settings > Project > Python Interpreter.
Set the interpreter to the Conda environment (
PCA25
) you created earlier.
Step 5: Verify the Setup
Check Environment Activation: Ensure the environment is activated before running the project.
conda activate PCA25
Final Steps: Setting Up the Project in Your IDE
Step 1: Open the Terminal in the IDE
Launch your IDE (e.g., PyCharm) and open the project folder.
Open the terminal within the IDE (see pic above)
Step 2: Ensure the Conda Environment is Activated
Check if your Conda environment (
PCA25
) is activated.
You should see(PCA25)
at the beginning of the terminal prompt. If not, activate it manually:
Step 3: Navigate to the Directory for social-interaction-cloud
Change your directory to the
social-interaction-cloud
folder:Install the package using
pip
:The
.
tellspip
to install the package in the current directory (i.e.,social-interaction-cloud
).
Step 4: Return to the pca-agent-2025
Directory
Navigate back to the
pca-agent-2025
directory by moving one level up:
Step 5: Navigate to the sic_applications
Directory
Change your directory to the
sic_applications
folder:Install the package using
pip
:
Now, please go ahead and test your installation. You should be able to run the entire setup (see Run your Conversational Agent), just the MARBEL part. Do keep in mind that the basic agent does only very basic things, but you should expect to get a greeting.