Generative Agents

To set up the environment, you need to generate a utils.py file with your OpenAI API key and install the required packages.

1. In the reverie/backend_server folder, create a file named utils.py and paste the content below, replacing <Your OpenAI API> with your key and <Name> with your name:

# Copy and paste your OpenAI API Key
openai_api_key = "<Your OpenAI API>"
# Put your name
key_owner = "<Name>"

maze_assets_loc = "../../environment/frontend_server/static_dirs/assets"
env_matrix = f"{maze_assets_loc}/the_ville/matrix"
env_visuals = f"{maze_assets_loc}/the_ville/visuals"

fs_storage = "../../environment/frontend_server/storage"
fs_temp_storage = "../../environment/frontend_server/temp_storage"

collision_block_id = "32125"

# Verbose 
debug = True

1. Install the dependencies from requirements.txt (preferably in a virtual environment).

pip install -r requirements.txt

To run a simulation, you need to start two servers concurrently.

1. Start the environment server (Django):

cd environment/frontend_server
python manage.py runserver

Then open http://localhost:8000/ in your browser to verify it's running.

1. In a new terminal, start the simulation server:

cd reverie/backend_server
python reverie.py

When prompted, enter the forked simulation name, e.g., base_the_ville_isabella_maria_klaus, then a new simulation name, e.g., test-simulation.

1. In the browser, go to http://localhost:8000/simulator_home. In the simulation server, type run <step-count> to run the simulation (e.g., run 100).

2. To save and exit, type fin. To replay, visit http://localhost:8000/replay/<simulation-name>/<starting-time-step>/.