Agent is a concept in Sotopia to represent decision-making entities that can interact with each other in a social environment. Agents can be human participants, AI models, or other entities. No matter which type of agent, they have the same interface to interact with the environment: the input and output are of derived types of aact.messages.DataModel.

Creating your own agents

To create your own agents, you need to subclass the BaseAgent class and implement the asynchronous aact method. The aact method takes an Observation object as input and returns an AgentAction object as output. Here is an example of a simple agent that always says "Hello, world!":

from aact import NodeFactory
from aact.messages import Text
from sotopia.experimental import BaseAgent
 
@NodeFactory.register("simple_echo_agent")  # Register the agent so that it can be used in the dataflow
class SimpleEchoAgent(BaseAgent[Text, Text]):
    def __init__(self, input_channel: str, output_channel: str, redis_url: str) -> None:
        super().__init__( # call the constructor of the base class
            input_channel_types=[(input_channel, Text)],
            output_channel_types=[(output_channel, Text)],
        )
 
    async def aact(self, observation: Text) -> Text: # major agent reactive function
        return Text(text=f"Hello, {observation.text}!")

Let me break this down for you:

1. NodeFactory is a decorator that registers the agent so that it can be used in the dataflow. Dataflow is a concept in aact that defines how nodes are interacting with each other.
2. channel is a concept in redis pubsub and aact. A node can send messages to many channels, and receive messages many channels as well. To subclass BaseAgent, you will need to feed two lists of channel-message type pairs to input_channel_types and output_channel_types respectively.
3. Inherit the BaseAgent class and specify the input and output channel types in the constructor.
4. Implement the aact method that takes an Observation object as input and returns an AgentAction object as output. In this case, the agent always says "Hello, ..."

For a running example, try out examples/experimental/tick_and_echo_agents.