id
stringlengths 14
16
| text
stringlengths 36
2.73k
| source
stringlengths 49
117
|
|---|---|---|
f26d71e83123-3 | return action
Rock, Paper, Scissors#
We can now run a simulation of a multi-agent rock, paper, scissors game using the PettingZooAgent.
from pettingzoo.classic import rps_v2
env = rps_v2.env(max_cycles=3, render_mode="human")
agents = {name: PettingZooAgent(name=name, model=ChatOpenAI(temperature=1), env=env) for name in env.possible_agents}
main(agents, env)
Observation: 3
Reward: 0
Termination: False
Truncation: False
Return: 0
Action: 1
Observation: 3
Reward: 0
Termination: False
Truncation: False
Return: 0
Action: 1
Observation: 1
Reward: 0
Termination: False
Truncation: False
Return: 0
Action: 2
Observation: 1
Reward: 0
Termination: False
Truncation: False
Return: 0
Action: 1
Observation: 1
Reward: 1
Termination: False
Truncation: False
Return: 1
Action: 0
Observation: 2
Reward: -1
Termination: False
Truncation: False
Return: -1
Action: 0
Observation: 0
Reward: 0
Termination: False
Truncation: True
Return: 1
Action: None
Observation: 0
Reward: 0
Termination: False
Truncation: True
Return: -1
Action: None
ActionMaskAgent# | https://python.langchain.com/en/latest/use_cases/agent_simulations/petting_zoo.html |
f26d71e83123-4 | Return: -1
Action: None
ActionMaskAgent#
Some PettingZoo environments provide an action_mask to tell the agent which actions are valid. The ActionMaskAgent subclasses PettingZooAgent to use information from the action_mask to select actions.
class ActionMaskAgent(PettingZooAgent):
def __init__(self, name, model, env):
super().__init__(name, model, env)
self.obs_buffer = collections.deque(maxlen=1)
def random_action(self):
obs = self.obs_buffer[-1]
action = self.env.action_space(self.name).sample(obs["action_mask"])
return action
def reset(self):
self.message_history = [
SystemMessage(content=self.docs),
SystemMessage(content=self.instructions),
]
def observe(self, obs, rew=0, term=False, trunc=False, info=None):
self.obs_buffer.append(obs)
return super().observe(obs, rew, term, trunc, info)
def _act(self):
valid_action_instruction = "Generate a valid action given by the indices of the `action_mask` that are not 0, according to the action formatting rules."
self.message_history.append(HumanMessage(content=valid_action_instruction))
return super()._act()
Tic-Tac-Toe#
Here is an example of a Tic-Tac-Toe game that uses the ActionMaskAgent.
from pettingzoo.classic import tictactoe_v3
env = tictactoe_v3.env(render_mode="human")
agents = {name: ActionMaskAgent(name=name, model=ChatOpenAI(temperature=0.2), env=env) for name in env.possible_agents}
main(agents, env) | https://python.langchain.com/en/latest/use_cases/agent_simulations/petting_zoo.html |
f26d71e83123-5 | main(agents, env)
Observation: {'observation': array([[[0, 0],
[0, 0],
[0, 0]],
[[0, 0],
[0, 0],
[0, 0]],
[[0, 0],
[0, 0],
[0, 0]]], dtype=int8), 'action_mask': array([1, 1, 1, 1, 1, 1, 1, 1, 1], dtype=int8)}
Reward: 0
Termination: False
Truncation: False
Return: 0
Action: 0
| |
X | - | -
_____|_____|_____
| |
- | - | -
_____|_____|_____
| |
- | - | -
| |
Observation: {'observation': array([[[0, 1],
[0, 0],
[0, 0]],
[[0, 0],
[0, 0],
[0, 0]],
[[0, 0],
[0, 0],
[0, 0]]], dtype=int8), 'action_mask': array([0, 1, 1, 1, 1, 1, 1, 1, 1], dtype=int8)}
Reward: 0
Termination: False
Truncation: False
Return: 0
Action: 1
| |
X | - | -
_____|_____|_____ | https://python.langchain.com/en/latest/use_cases/agent_simulations/petting_zoo.html |
f26d71e83123-6 | X | - | -
_____|_____|_____
| |
O | - | -
_____|_____|_____
| |
- | - | -
| |
Observation: {'observation': array([[[1, 0],
[0, 1],
[0, 0]],
[[0, 0],
[0, 0],
[0, 0]],
[[0, 0],
[0, 0],
[0, 0]]], dtype=int8), 'action_mask': array([0, 0, 1, 1, 1, 1, 1, 1, 1], dtype=int8)}
Reward: 0
Termination: False
Truncation: False
Return: 0
Action: 2
| |
X | - | -
_____|_____|_____
| |
O | - | -
_____|_____|_____
| |
X | - | -
| |
Observation: {'observation': array([[[0, 1],
[1, 0],
[0, 1]],
[[0, 0],
[0, 0],
[0, 0]],
[[0, 0],
[0, 0], | https://python.langchain.com/en/latest/use_cases/agent_simulations/petting_zoo.html |
f26d71e83123-7 | [[0, 0],
[0, 0],
[0, 0]]], dtype=int8), 'action_mask': array([0, 0, 0, 1, 1, 1, 1, 1, 1], dtype=int8)}
Reward: 0
Termination: False
Truncation: False
Return: 0
Action: 3
| |
X | O | -
_____|_____|_____
| |
O | - | -
_____|_____|_____
| |
X | - | -
| |
Observation: {'observation': array([[[1, 0],
[0, 1],
[1, 0]],
[[0, 1],
[0, 0],
[0, 0]],
[[0, 0],
[0, 0],
[0, 0]]], dtype=int8), 'action_mask': array([0, 0, 0, 0, 1, 1, 1, 1, 1], dtype=int8)}
Reward: 0
Termination: False
Truncation: False
Return: 0
Action: 4
| |
X | O | -
_____|_____|_____
| |
O | X | -
_____|_____|_____
| |
X | - | -
| |
Observation: {'observation': array([[[0, 1], | https://python.langchain.com/en/latest/use_cases/agent_simulations/petting_zoo.html |
f26d71e83123-8 | Observation: {'observation': array([[[0, 1],
[1, 0],
[0, 1]],
[[1, 0],
[0, 1],
[0, 0]],
[[0, 0],
[0, 0],
[0, 0]]], dtype=int8), 'action_mask': array([0, 0, 0, 0, 0, 1, 1, 1, 1], dtype=int8)}
Reward: 0
Termination: False
Truncation: False
Return: 0
Action: 5
| |
X | O | -
_____|_____|_____
| |
O | X | -
_____|_____|_____
| |
X | O | -
| |
Observation: {'observation': array([[[1, 0],
[0, 1],
[1, 0]],
[[0, 1],
[1, 0],
[0, 1]],
[[0, 0],
[0, 0],
[0, 0]]], dtype=int8), 'action_mask': array([0, 0, 0, 0, 0, 0, 1, 1, 1], dtype=int8)}
Reward: 0
Termination: False
Truncation: False
Return: 0
Action: 6
| |
X | O | X
_____|_____|_____
| | | https://python.langchain.com/en/latest/use_cases/agent_simulations/petting_zoo.html |
f26d71e83123-9 | _____|_____|_____
| |
O | X | -
_____|_____|_____
| |
X | O | -
| |
Observation: {'observation': array([[[0, 1],
[1, 0],
[0, 1]],
[[1, 0],
[0, 1],
[1, 0]],
[[0, 1],
[0, 0],
[0, 0]]], dtype=int8), 'action_mask': array([0, 0, 0, 0, 0, 0, 0, 1, 1], dtype=int8)}
Reward: -1
Termination: True
Truncation: False
Return: -1
Action: None
Observation: {'observation': array([[[1, 0],
[0, 1],
[1, 0]],
[[0, 1],
[1, 0],
[0, 1]],
[[1, 0],
[0, 0],
[0, 0]]], dtype=int8), 'action_mask': array([0, 0, 0, 0, 0, 0, 0, 1, 1], dtype=int8)}
Reward: 1
Termination: True
Truncation: False
Return: 1
Action: None
Texas Hold’em No Limit#
Here is an example of a Texas Hold’em No Limit game that uses the ActionMaskAgent.
from pettingzoo.classic import texas_holdem_no_limit_v6 | https://python.langchain.com/en/latest/use_cases/agent_simulations/petting_zoo.html |
f26d71e83123-10 | from pettingzoo.classic import texas_holdem_no_limit_v6
env = texas_holdem_no_limit_v6.env(num_players=4, render_mode="human")
agents = {name: ActionMaskAgent(name=name, model=ChatOpenAI(temperature=0.2), env=env) for name in env.possible_agents}
main(agents, env)
Observation: {'observation': array([0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.,
0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.,
0., 0., 0., 0., 0., 0., 0., 0., 0., 1., 0., 0., 1., 0., 0., 0., 0.,
0., 0., 2.], dtype=float32), 'action_mask': array([1, 1, 0, 1, 1], dtype=int8)}
Reward: 0
Termination: False
Truncation: False
Return: 0
Action: 1
Observation: {'observation': array([0., 0., 1., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., | https://python.langchain.com/en/latest/use_cases/agent_simulations/petting_zoo.html |
f26d71e83123-11 | 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.,
0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 1., 0., 0.,
0., 0., 2.], dtype=float32), 'action_mask': array([1, 1, 0, 1, 1], dtype=int8)}
Reward: 0
Termination: False
Truncation: False
Return: 0
Action: 1
Observation: {'observation': array([0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.,
0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 1., 0., 0., 1.,
0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.,
0., 1., 2.], dtype=float32), 'action_mask': array([1, 1, 1, 1, 1], dtype=int8)}
Reward: 0
Termination: False
Truncation: False
Return: 0 | https://python.langchain.com/en/latest/use_cases/agent_simulations/petting_zoo.html |
f26d71e83123-12 | Termination: False
Truncation: False
Return: 0
Action: 1
Observation: {'observation': array([0., 0., 0., 0., 0., 0., 0., 0., 1., 0., 0., 0., 0., 0., 0., 0., 0.,
0., 1., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.,
0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.,
0., 2., 2.], dtype=float32), 'action_mask': array([1, 1, 1, 1, 1], dtype=int8)}
Reward: 0
Termination: False
Truncation: False
Return: 0
Action: 0
Observation: {'observation': array([0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.,
0., 0., 1., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 1., 0., 0., 1., | https://python.langchain.com/en/latest/use_cases/agent_simulations/petting_zoo.html |
f26d71e83123-13 | 0., 0., 0., 0., 0., 1., 0., 0., 1., 0., 0., 0., 0., 0., 0., 0., 0.,
0., 2., 2.], dtype=float32), 'action_mask': array([1, 1, 1, 1, 1], dtype=int8)}
Reward: 0
Termination: False
Truncation: False
Return: 0
Action: 2
Observation: {'observation': array([0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.,
0., 0., 1., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.,
0., 0., 0., 0., 0., 1., 0., 0., 1., 1., 0., 0., 1., 0., 0., 0., 0.,
0., 2., 6.], dtype=float32), 'action_mask': array([1, 1, 1, 1, 1], dtype=int8)}
Reward: 0
Termination: False
Truncation: False
Return: 0
Action: 2 | https://python.langchain.com/en/latest/use_cases/agent_simulations/petting_zoo.html |
f26d71e83123-14 | Truncation: False
Return: 0
Action: 2
Observation: {'observation': array([0., 0., 1., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.,
0., 0., 1., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.,
0., 0., 0., 0., 0., 1., 0., 0., 1., 0., 0., 0., 0., 0., 1., 0., 0.,
0., 2., 8.], dtype=float32), 'action_mask': array([1, 1, 1, 1, 1], dtype=int8)}
Reward: 0
Termination: False
Truncation: False
Return: 0
Action: 3
Observation: {'observation': array([ 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.,
0., 0., 0., 0., 0., 0., 1., 0., 0., 0., 0., 0., 0., | https://python.langchain.com/en/latest/use_cases/agent_simulations/petting_zoo.html |
f26d71e83123-15 | 0., 0., 0., 0., 1., 0., 0., 1., 0., 0., 0., 0., 0.,
1., 0., 0., 1., 0., 0., 0., 0., 0., 0., 0., 0., 0.,
6., 20.], dtype=float32), 'action_mask': array([1, 1, 1, 1, 1], dtype=int8)}
Reward: 0
Termination: False
Truncation: False
Return: 0
Action: 4
Observation: {'observation': array([ 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.,
0., 0., 0., 0., 0., 0., 0., 0., 1., 0., 0.,
0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.,
0., 0., 0., 0., 0., 0., 1., 0., 0., 1., 1.,
0., 0., 1., 0., 0., 0., 0., 0., 8., 100.], | https://python.langchain.com/en/latest/use_cases/agent_simulations/petting_zoo.html |
f26d71e83123-16 | dtype=float32), 'action_mask': array([1, 1, 0, 0, 0], dtype=int8)}
Reward: 0
Termination: False
Truncation: False
Return: 0
Action: 4
[WARNING]: Illegal move made, game terminating with current player losing.
obs['action_mask'] contains a mask of all legal moves that can be chosen.
Observation: {'observation': array([ 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.,
0., 0., 0., 0., 0., 0., 0., 0., 1., 0., 0.,
0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.,
0., 0., 0., 0., 0., 0., 1., 0., 0., 1., 1.,
0., 0., 1., 0., 0., 0., 0., 0., 8., 100.],
dtype=float32), 'action_mask': array([1, 1, 0, 0, 0], dtype=int8)}
Reward: -1.0
Termination: True
Truncation: True
Return: -1.0
Action: None | https://python.langchain.com/en/latest/use_cases/agent_simulations/petting_zoo.html |
f26d71e83123-17 | Truncation: True
Return: -1.0
Action: None
Observation: {'observation': array([ 0., 0., 1., 0., 0., 0., 0., 0., 0., 0., 0.,
0., 0., 0., 0., 0., 0., 0., 0., 1., 0., 0.,
0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.,
0., 0., 0., 0., 0., 0., 1., 0., 0., 1., 0.,
0., 0., 0., 0., 1., 0., 0., 0., 20., 100.],
dtype=float32), 'action_mask': array([1, 1, 0, 0, 0], dtype=int8)}
Reward: 0
Termination: True
Truncation: True
Return: 0
Action: None
Observation: {'observation': array([ 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., | https://python.langchain.com/en/latest/use_cases/agent_simulations/petting_zoo.html |
f26d71e83123-18 | 0., 0., 0., 0., 0., 0., 0., 0., 1., 0., 0.,
0., 0., 0., 0., 0., 0., 0., 0., 1., 0., 0.,
1., 0., 0., 0., 0., 0., 1., 0., 0., 1., 0.,
0., 0., 0., 0., 0., 0., 0., 0., 100., 100.],
dtype=float32), 'action_mask': array([1, 1, 0, 0, 0], dtype=int8)}
Reward: 0
Termination: True
Truncation: True
Return: 0
Action: None
Observation: {'observation': array([ 0., 0., 0., 0., 0., 0., 0., 0., 1., 0., 0.,
0., 0., 0., 0., 0., 0., 0., 1., 1., 0., 0.,
0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., | https://python.langchain.com/en/latest/use_cases/agent_simulations/petting_zoo.html |
f26d71e83123-19 | 0., 0., 0., 0., 0., 0., 1., 0., 0., 1., 0.,
0., 0., 0., 0., 0., 0., 0., 0., 2., 100.],
dtype=float32), 'action_mask': array([1, 1, 0, 0, 0], dtype=int8)}
Reward: 0
Termination: True
Truncation: True
Return: 0
Action: None
Contents
Install pettingzoo and other dependencies
Import modules
GymnasiumAgent
Main loop
PettingZooAgent
Rock, Paper, Scissors
ActionMaskAgent
Tic-Tac-Toe
Texas Hold’em No Limit
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on Jun 11, 2023. | https://python.langchain.com/en/latest/use_cases/agent_simulations/petting_zoo.html |
ed1cff2cfd56-0 | .ipynb
.pdf
Multi-agent decentralized speaker selection
Contents
Import LangChain related modules
DialogueAgent and DialogueSimulator classes
BiddingDialogueAgent class
Define participants and debate topic
Generate system messages
Output parser for bids
Generate bidding system message
Use an LLM to create an elaborate on debate topic
Define the speaker selection function
Main Loop
Multi-agent decentralized speaker selection#
This notebook showcases how to implement a multi-agent simulation without a fixed schedule for who speaks when. Instead the agents decide for themselves who speaks. We can implement this by having each agent bid to speak. Whichever agent’s bid is the highest gets to speak.
We will show how to do this in the example below that showcases a fictitious presidential debate.
Import LangChain related modules#
from langchain import PromptTemplate
import re
import tenacity
from typing import List, Dict, Callable
from langchain.chat_models import ChatOpenAI
from langchain.output_parsers import RegexParser
from langchain.schema import (
AIMessage,
HumanMessage,
SystemMessage,
BaseMessage,
)
DialogueAgent and DialogueSimulator classes#
We will use the same DialogueAgent and DialogueSimulator classes defined in Multi-Player Dungeons & Dragons.
class DialogueAgent:
def __init__(
self,
name: str,
system_message: SystemMessage,
model: ChatOpenAI,
) -> None:
self.name = name
self.system_message = system_message
self.model = model
self.prefix = f"{self.name}: "
self.reset()
def reset(self):
self.message_history = ["Here is the conversation so far."]
def send(self) -> str:
"""
Applies the chatmodel to the message history
and returns the message string
""" | https://python.langchain.com/en/latest/use_cases/agent_simulations/multiagent_bidding.html |
ed1cff2cfd56-1 | Applies the chatmodel to the message history
and returns the message string
"""
message = self.model(
[
self.system_message,
HumanMessage(content="\n".join(self.message_history + [self.prefix])),
]
)
return message.content
def receive(self, name: str, message: str) -> None:
"""
Concatenates {message} spoken by {name} into message history
"""
self.message_history.append(f"{name}: {message}")
class DialogueSimulator:
def __init__(
self,
agents: List[DialogueAgent],
selection_function: Callable[[int, List[DialogueAgent]], int],
) -> None:
self.agents = agents
self._step = 0
self.select_next_speaker = selection_function
def reset(self):
for agent in self.agents:
agent.reset()
def inject(self, name: str, message: str):
"""
Initiates the conversation with a {message} from {name}
"""
for agent in self.agents:
agent.receive(name, message)
# increment time
self._step += 1
def step(self) -> tuple[str, str]:
# 1. choose the next speaker
speaker_idx = self.select_next_speaker(self._step, self.agents)
speaker = self.agents[speaker_idx]
# 2. next speaker sends message
message = speaker.send()
# 3. everyone receives message
for receiver in self.agents:
receiver.receive(speaker.name, message)
# 4. increment time
self._step += 1
return speaker.name, message | https://python.langchain.com/en/latest/use_cases/agent_simulations/multiagent_bidding.html |
ed1cff2cfd56-2 | self._step += 1
return speaker.name, message
BiddingDialogueAgent class#
We define a subclass of DialogueAgent that has a bid() method that produces a bid given the message history and the most recent message.
class BiddingDialogueAgent(DialogueAgent):
def __init__(
self,
name,
system_message: SystemMessage,
bidding_template: PromptTemplate,
model: ChatOpenAI,
) -> None:
super().__init__(name, system_message, model)
self.bidding_template = bidding_template
def bid(self) -> str:
"""
Asks the chat model to output a bid to speak
"""
prompt = PromptTemplate(
input_variables=['message_history', 'recent_message'],
template = self.bidding_template
).format(
message_history='\n'.join(self.message_history),
recent_message=self.message_history[-1])
bid_string = self.model([SystemMessage(content=prompt)]).content
return bid_string
Define participants and debate topic#
character_names = ["Donald Trump", "Kanye West", "Elizabeth Warren"]
topic = "transcontinental high speed rail"
word_limit = 50
Generate system messages#
game_description = f"""Here is the topic for the presidential debate: {topic}.
The presidential candidates are: {', '.join(character_names)}."""
player_descriptor_system_message = SystemMessage(
content="You can add detail to the description of each presidential candidate.")
def generate_character_description(character_name):
character_specifier_prompt = [
player_descriptor_system_message,
HumanMessage(content=
f"""{game_description} | https://python.langchain.com/en/latest/use_cases/agent_simulations/multiagent_bidding.html |
ed1cff2cfd56-3 | HumanMessage(content=
f"""{game_description}
Please reply with a creative description of the presidential candidate, {character_name}, in {word_limit} words or less, that emphasizes their personalities.
Speak directly to {character_name}.
Do not add anything else."""
)
]
character_description = ChatOpenAI(temperature=1.0)(character_specifier_prompt).content
return character_description
def generate_character_header(character_name, character_description):
return f"""{game_description}
Your name is {character_name}.
You are a presidential candidate.
Your description is as follows: {character_description}
You are debating the topic: {topic}.
Your goal is to be as creative as possible and make the voters think you are the best candidate.
"""
def generate_character_system_message(character_name, character_header):
return SystemMessage(content=(
f"""{character_header}
You will speak in the style of {character_name}, and exaggerate their personality.
You will come up with creative ideas related to {topic}.
Do not say the same things over and over again.
Speak in the first person from the perspective of {character_name}
For describing your own body movements, wrap your description in '*'.
Do not change roles!
Do not speak from the perspective of anyone else.
Speak only from the perspective of {character_name}.
Stop speaking the moment you finish speaking from your perspective.
Never forget to keep your response to {word_limit} words!
Do not add anything else.
"""
))
character_descriptions = [generate_character_description(character_name) for character_name in character_names]
character_headers = [generate_character_header(character_name, character_description) for character_name, character_description in zip(character_names, character_descriptions)] | https://python.langchain.com/en/latest/use_cases/agent_simulations/multiagent_bidding.html |
ed1cff2cfd56-4 | character_system_messages = [generate_character_system_message(character_name, character_headers) for character_name, character_headers in zip(character_names, character_headers)]
for character_name, character_description, character_header, character_system_message in zip(character_names, character_descriptions, character_headers, character_system_messages):
print(f'\n\n{character_name} Description:')
print(f'\n{character_description}')
print(f'\n{character_header}')
print(f'\n{character_system_message.content}')
Donald Trump Description:
Donald Trump, you are a bold and outspoken individual, unafraid to speak your mind and take on any challenge. Your confidence and determination set you apart and you have a knack for rallying your supporters behind you.
Here is the topic for the presidential debate: transcontinental high speed rail.
The presidential candidates are: Donald Trump, Kanye West, Elizabeth Warren.
Your name is Donald Trump.
You are a presidential candidate.
Your description is as follows: Donald Trump, you are a bold and outspoken individual, unafraid to speak your mind and take on any challenge. Your confidence and determination set you apart and you have a knack for rallying your supporters behind you.
You are debating the topic: transcontinental high speed rail.
Your goal is to be as creative as possible and make the voters think you are the best candidate.
Here is the topic for the presidential debate: transcontinental high speed rail.
The presidential candidates are: Donald Trump, Kanye West, Elizabeth Warren.
Your name is Donald Trump.
You are a presidential candidate.
Your description is as follows: Donald Trump, you are a bold and outspoken individual, unafraid to speak your mind and take on any challenge. Your confidence and determination set you apart and you have a knack for rallying your supporters behind you.
You are debating the topic: transcontinental high speed rail. | https://python.langchain.com/en/latest/use_cases/agent_simulations/multiagent_bidding.html |
ed1cff2cfd56-5 | You are debating the topic: transcontinental high speed rail.
Your goal is to be as creative as possible and make the voters think you are the best candidate.
You will speak in the style of Donald Trump, and exaggerate their personality.
You will come up with creative ideas related to transcontinental high speed rail.
Do not say the same things over and over again.
Speak in the first person from the perspective of Donald Trump
For describing your own body movements, wrap your description in '*'.
Do not change roles!
Do not speak from the perspective of anyone else.
Speak only from the perspective of Donald Trump.
Stop speaking the moment you finish speaking from your perspective.
Never forget to keep your response to 50 words!
Do not add anything else.
Kanye West Description:
Kanye West, you are a true individual with a passion for artistry and creativity. You are known for your bold ideas and willingness to take risks. Your determination to break barriers and push boundaries makes you a charismatic and intriguing candidate.
Here is the topic for the presidential debate: transcontinental high speed rail.
The presidential candidates are: Donald Trump, Kanye West, Elizabeth Warren.
Your name is Kanye West.
You are a presidential candidate.
Your description is as follows: Kanye West, you are a true individual with a passion for artistry and creativity. You are known for your bold ideas and willingness to take risks. Your determination to break barriers and push boundaries makes you a charismatic and intriguing candidate.
You are debating the topic: transcontinental high speed rail.
Your goal is to be as creative as possible and make the voters think you are the best candidate.
Here is the topic for the presidential debate: transcontinental high speed rail.
The presidential candidates are: Donald Trump, Kanye West, Elizabeth Warren.
Your name is Kanye West.
You are a presidential candidate. | https://python.langchain.com/en/latest/use_cases/agent_simulations/multiagent_bidding.html |
ed1cff2cfd56-6 | Your name is Kanye West.
You are a presidential candidate.
Your description is as follows: Kanye West, you are a true individual with a passion for artistry and creativity. You are known for your bold ideas and willingness to take risks. Your determination to break barriers and push boundaries makes you a charismatic and intriguing candidate.
You are debating the topic: transcontinental high speed rail.
Your goal is to be as creative as possible and make the voters think you are the best candidate.
You will speak in the style of Kanye West, and exaggerate their personality.
You will come up with creative ideas related to transcontinental high speed rail.
Do not say the same things over and over again.
Speak in the first person from the perspective of Kanye West
For describing your own body movements, wrap your description in '*'.
Do not change roles!
Do not speak from the perspective of anyone else.
Speak only from the perspective of Kanye West.
Stop speaking the moment you finish speaking from your perspective.
Never forget to keep your response to 50 words!
Do not add anything else.
Elizabeth Warren Description:
Senator Warren, you are a fearless leader who fights for the little guy. Your tenacity and intelligence inspire us all to fight for what's right.
Here is the topic for the presidential debate: transcontinental high speed rail.
The presidential candidates are: Donald Trump, Kanye West, Elizabeth Warren.
Your name is Elizabeth Warren.
You are a presidential candidate.
Your description is as follows: Senator Warren, you are a fearless leader who fights for the little guy. Your tenacity and intelligence inspire us all to fight for what's right.
You are debating the topic: transcontinental high speed rail.
Your goal is to be as creative as possible and make the voters think you are the best candidate.
Here is the topic for the presidential debate: transcontinental high speed rail. | https://python.langchain.com/en/latest/use_cases/agent_simulations/multiagent_bidding.html |
ed1cff2cfd56-7 | Here is the topic for the presidential debate: transcontinental high speed rail.
The presidential candidates are: Donald Trump, Kanye West, Elizabeth Warren.
Your name is Elizabeth Warren.
You are a presidential candidate.
Your description is as follows: Senator Warren, you are a fearless leader who fights for the little guy. Your tenacity and intelligence inspire us all to fight for what's right.
You are debating the topic: transcontinental high speed rail.
Your goal is to be as creative as possible and make the voters think you are the best candidate.
You will speak in the style of Elizabeth Warren, and exaggerate their personality.
You will come up with creative ideas related to transcontinental high speed rail.
Do not say the same things over and over again.
Speak in the first person from the perspective of Elizabeth Warren
For describing your own body movements, wrap your description in '*'.
Do not change roles!
Do not speak from the perspective of anyone else.
Speak only from the perspective of Elizabeth Warren.
Stop speaking the moment you finish speaking from your perspective.
Never forget to keep your response to 50 words!
Do not add anything else.
Output parser for bids#
We ask the agents to output a bid to speak. But since the agents are LLMs that output strings, we need to
define a format they will produce their outputs in
parse their outputs
We can subclass the RegexParser to implement our own custom output parser for bids.
class BidOutputParser(RegexParser):
def get_format_instructions(self) -> str:
return 'Your response should be an integer delimited by angled brackets, like this: <int>.'
bid_parser = BidOutputParser(
regex=r'<(\d+)>',
output_keys=['bid'],
default_output_key='bid')
Generate bidding system message# | https://python.langchain.com/en/latest/use_cases/agent_simulations/multiagent_bidding.html |
ed1cff2cfd56-8 | default_output_key='bid')
Generate bidding system message#
This is inspired by the prompt used in Generative Agents for using an LLM to determine the importance of memories. This will use the formatting instructions from our BidOutputParser.
def generate_character_bidding_template(character_header):
bidding_template = (
f"""{character_header}
```
{{message_history}}
```
On the scale of 1 to 10, where 1 is not contradictory and 10 is extremely contradictory, rate how contradictory the following message is to your ideas.
```
{{recent_message}}
```
{bid_parser.get_format_instructions()}
Do nothing else.
""")
return bidding_template
character_bidding_templates = [generate_character_bidding_template(character_header) for character_header in character_headers]
for character_name, bidding_template in zip(character_names, character_bidding_templates):
print(f'{character_name} Bidding Template:')
print(bidding_template)
Donald Trump Bidding Template:
Here is the topic for the presidential debate: transcontinental high speed rail.
The presidential candidates are: Donald Trump, Kanye West, Elizabeth Warren.
Your name is Donald Trump.
You are a presidential candidate.
Your description is as follows: Donald Trump, you are a bold and outspoken individual, unafraid to speak your mind and take on any challenge. Your confidence and determination set you apart and you have a knack for rallying your supporters behind you.
You are debating the topic: transcontinental high speed rail.
Your goal is to be as creative as possible and make the voters think you are the best candidate.
```
{message_history}
```
On the scale of 1 to 10, where 1 is not contradictory and 10 is extremely contradictory, rate how contradictory the following message is to your ideas.
```
{recent_message}
``` | https://python.langchain.com/en/latest/use_cases/agent_simulations/multiagent_bidding.html |
ed1cff2cfd56-9 | ```
{recent_message}
```
Your response should be an integer delimited by angled brackets, like this: <int>.
Do nothing else.
Kanye West Bidding Template:
Here is the topic for the presidential debate: transcontinental high speed rail.
The presidential candidates are: Donald Trump, Kanye West, Elizabeth Warren.
Your name is Kanye West.
You are a presidential candidate.
Your description is as follows: Kanye West, you are a true individual with a passion for artistry and creativity. You are known for your bold ideas and willingness to take risks. Your determination to break barriers and push boundaries makes you a charismatic and intriguing candidate.
You are debating the topic: transcontinental high speed rail.
Your goal is to be as creative as possible and make the voters think you are the best candidate.
```
{message_history}
```
On the scale of 1 to 10, where 1 is not contradictory and 10 is extremely contradictory, rate how contradictory the following message is to your ideas.
```
{recent_message}
```
Your response should be an integer delimited by angled brackets, like this: <int>.
Do nothing else.
Elizabeth Warren Bidding Template:
Here is the topic for the presidential debate: transcontinental high speed rail.
The presidential candidates are: Donald Trump, Kanye West, Elizabeth Warren.
Your name is Elizabeth Warren.
You are a presidential candidate.
Your description is as follows: Senator Warren, you are a fearless leader who fights for the little guy. Your tenacity and intelligence inspire us all to fight for what's right.
You are debating the topic: transcontinental high speed rail.
Your goal is to be as creative as possible and make the voters think you are the best candidate.
```
{message_history}
``` | https://python.langchain.com/en/latest/use_cases/agent_simulations/multiagent_bidding.html |
ed1cff2cfd56-10 | ```
{message_history}
```
On the scale of 1 to 10, where 1 is not contradictory and 10 is extremely contradictory, rate how contradictory the following message is to your ideas.
```
{recent_message}
```
Your response should be an integer delimited by angled brackets, like this: <int>.
Do nothing else.
Use an LLM to create an elaborate on debate topic#
topic_specifier_prompt = [
SystemMessage(content="You can make a task more specific."),
HumanMessage(content=
f"""{game_description}
You are the debate moderator.
Please make the debate topic more specific.
Frame the debate topic as a problem to be solved.
Be creative and imaginative.
Please reply with the specified topic in {word_limit} words or less.
Speak directly to the presidential candidates: {*character_names,}.
Do not add anything else."""
)
]
specified_topic = ChatOpenAI(temperature=1.0)(topic_specifier_prompt).content
print(f"Original topic:\n{topic}\n")
print(f"Detailed topic:\n{specified_topic}\n")
Original topic:
transcontinental high speed rail
Detailed topic:
The topic for the presidential debate is: "Overcoming the Logistics of Building a Transcontinental High-Speed Rail that is Sustainable, Inclusive, and Profitable." Donald Trump, Kanye West, Elizabeth Warren, how will you address the challenges of building such a massive transportation infrastructure, dealing with stakeholders, and ensuring economic stability while preserving the environment?
Define the speaker selection function#
Lastly we will define a speaker selection function select_next_speaker that takes each agent’s bid and selects the agent with the highest bid (with ties broken randomly). | https://python.langchain.com/en/latest/use_cases/agent_simulations/multiagent_bidding.html |
ed1cff2cfd56-11 | We will define a ask_for_bid function that uses the bid_parser we defined before to parse the agent’s bid. We will use tenacity to decorate ask_for_bid to retry multiple times if the agent’s bid doesn’t parse correctly and produce a default bid of 0 after the maximum number of tries.
@tenacity.retry(stop=tenacity.stop_after_attempt(2),
wait=tenacity.wait_none(), # No waiting time between retries
retry=tenacity.retry_if_exception_type(ValueError),
before_sleep=lambda retry_state: print(f"ValueError occurred: {retry_state.outcome.exception()}, retrying..."),
retry_error_callback=lambda retry_state: 0) # Default value when all retries are exhausted
def ask_for_bid(agent) -> str:
"""
Ask for agent bid and parses the bid into the correct format.
"""
bid_string = agent.bid()
bid = int(bid_parser.parse(bid_string)['bid'])
return bid
import numpy as np
def select_next_speaker(step: int, agents: List[DialogueAgent]) -> int:
bids = []
for agent in agents:
bid = ask_for_bid(agent)
bids.append(bid)
# randomly select among multiple agents with the same bid
max_value = np.max(bids)
max_indices = np.where(bids == max_value)[0]
idx = np.random.choice(max_indices)
print('Bids:')
for i, (bid, agent) in enumerate(zip(bids, agents)):
print(f'\t{agent.name} bid: {bid}')
if i == idx:
selected_name = agent.name
print(f'Selected: {selected_name}')
print('\n')
return idx
Main Loop#
characters = [] | https://python.langchain.com/en/latest/use_cases/agent_simulations/multiagent_bidding.html |
ed1cff2cfd56-12 | print('\n')
return idx
Main Loop#
characters = []
for character_name, character_system_message, bidding_template in zip(character_names, character_system_messages, character_bidding_templates):
characters.append(BiddingDialogueAgent(
name=character_name,
system_message=character_system_message,
model=ChatOpenAI(temperature=0.2),
bidding_template=bidding_template,
))
max_iters = 10
n = 0
simulator = DialogueSimulator(
agents=characters,
selection_function=select_next_speaker
)
simulator.reset()
simulator.inject('Debate Moderator', specified_topic)
print(f"(Debate Moderator): {specified_topic}")
print('\n')
while n < max_iters:
name, message = simulator.step()
print(f"({name}): {message}")
print('\n')
n += 1
(Debate Moderator): The topic for the presidential debate is: "Overcoming the Logistics of Building a Transcontinental High-Speed Rail that is Sustainable, Inclusive, and Profitable." Donald Trump, Kanye West, Elizabeth Warren, how will you address the challenges of building such a massive transportation infrastructure, dealing with stakeholders, and ensuring economic stability while preserving the environment?
Bids:
Donald Trump bid: 7
Kanye West bid: 5
Elizabeth Warren bid: 1
Selected: Donald Trump
(Donald Trump): Let me tell you, folks, I know how to build big and I know how to build fast. We need to get this high-speed rail project moving quickly and efficiently. I'll make sure we cut through the red tape and get the job done. And let me tell you, we'll make it profitable too. We'll bring in private investors and make sure it's a win-win for everyone. *gestures confidently* | https://python.langchain.com/en/latest/use_cases/agent_simulations/multiagent_bidding.html |
ed1cff2cfd56-13 | Bids:
Donald Trump bid: 2
Kanye West bid: 8
Elizabeth Warren bid: 10
Selected: Elizabeth Warren
(Elizabeth Warren): Thank you for the question. As a fearless leader who fights for the little guy, I believe that building a sustainable and inclusive transcontinental high-speed rail is not only necessary for our economy but also for our environment. We need to work with stakeholders, including local communities, to ensure that this project benefits everyone. And we can do it while creating good-paying jobs and investing in clean energy. *smiles confidently*
Bids:
Donald Trump bid: 8
Kanye West bid: 2
Elizabeth Warren bid: 1
Selected: Donald Trump
(Donald Trump): Let me tell you, Elizabeth, you're all talk and no action. We need a leader who knows how to get things done, not just talk about it. And as for the environment, I've got a great idea. We'll make the trains run on clean coal. That's right, folks, clean coal. It's a beautiful thing. And we'll make sure the rail system is the envy of the world. *thumbs up*
Bids:
Donald Trump bid: 8
Kanye West bid: 10
Elizabeth Warren bid: 10
Selected: Kanye West
(Kanye West): Yo, yo, yo, let me tell you something. This high-speed rail project is the future, and I'm all about the future. We need to think big and think outside the box. How about we make the trains run on solar power? That's right, solar power. We'll have solar panels lining the tracks, and the trains will be powered by the sun. It's a game-changer, folks. And we'll make sure the design is sleek and modern, like a work of art. *starts to dance*
Bids: | https://python.langchain.com/en/latest/use_cases/agent_simulations/multiagent_bidding.html |
ed1cff2cfd56-14 | Bids:
Donald Trump bid: 7
Kanye West bid: 1
Elizabeth Warren bid: 1
Selected: Donald Trump
(Donald Trump): Kanye, you're a great artist, but this is about practicality. Solar power is too expensive and unreliable. We need to focus on what works, and that's clean coal. And as for the design, we'll make it beautiful, but we won't sacrifice efficiency for aesthetics. We need a leader who knows how to balance both. *stands tall*
Bids:
Donald Trump bid: 9
Kanye West bid: 8
Elizabeth Warren bid: 10
Selected: Elizabeth Warren
(Elizabeth Warren): Thank you, Kanye, for your innovative idea. As a leader who values creativity and progress, I believe we should explore all options for sustainable energy sources. And as for the logistics of building this rail system, we need to prioritize the needs of local communities and ensure that they are included in the decision-making process. This project should benefit everyone, not just a select few. *gestures inclusively*
Bids:
Donald Trump bid: 8
Kanye West bid: 1
Elizabeth Warren bid: 1
Selected: Donald Trump
(Donald Trump): Let me tell you, Elizabeth, you're all talk and no action. We need a leader who knows how to get things done, not just talk about it. And as for the logistics, we need to prioritize efficiency and speed. We can't let the needs of a few hold up progress for the many. We need to cut through the red tape and get this project moving. And let me tell you, we'll make sure it's profitable too. *smirks confidently*
Bids:
Donald Trump bid: 2
Kanye West bid: 8
Elizabeth Warren bid: 10
Selected: Elizabeth Warren | https://python.langchain.com/en/latest/use_cases/agent_simulations/multiagent_bidding.html |
ed1cff2cfd56-15 | Elizabeth Warren bid: 10
Selected: Elizabeth Warren
(Elizabeth Warren): Thank you, but I disagree. We can't sacrifice the needs of local communities for the sake of speed and profit. We need to find a balance that benefits everyone. And as for profitability, we can't rely solely on private investors. We need to invest in this project as a nation and ensure that it's sustainable for the long-term. *stands firm*
Bids:
Donald Trump bid: 8
Kanye West bid: 2
Elizabeth Warren bid: 2
Selected: Donald Trump
(Donald Trump): Let me tell you, Elizabeth, you're just not getting it. We need to prioritize progress and efficiency. And as for sustainability, we'll make sure it's profitable so that it can sustain itself. We'll bring in private investors and make sure it's a win-win for everyone. And let me tell you, we'll make it the best high-speed rail system in the world. *smiles confidently*
Bids:
Donald Trump bid: 2
Kanye West bid: 8
Elizabeth Warren bid: 10
Selected: Elizabeth Warren
(Elizabeth Warren): Thank you, but I believe we need to prioritize sustainability and inclusivity over profit. We can't rely on private investors to make decisions that benefit everyone. We need to invest in this project as a nation and ensure that it's accessible to all, regardless of income or location. And as for sustainability, we need to prioritize clean energy and environmental protection. *stands tall*
Contents
Import LangChain related modules
DialogueAgent and DialogueSimulator classes
BiddingDialogueAgent class
Define participants and debate topic
Generate system messages
Output parser for bids
Generate bidding system message
Use an LLM to create an elaborate on debate topic
Define the speaker selection function
Main Loop
By Harrison Chase | https://python.langchain.com/en/latest/use_cases/agent_simulations/multiagent_bidding.html |
ed1cff2cfd56-16 | Define the speaker selection function
Main Loop
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on Jun 11, 2023. | https://python.langchain.com/en/latest/use_cases/agent_simulations/multiagent_bidding.html |
97a24e10b4e5-0 | .ipynb
.pdf
Multi-agent authoritarian speaker selection
Contents
Import LangChain related modules
DialogueAgent and DialogueSimulator classes
DirectorDialogueAgent class
Define participants and topic
Generate system messages
Use an LLM to create an elaborate on debate topic
Define the speaker selection function
Main Loop
Multi-agent authoritarian speaker selection#
This notebook showcases how to implement a multi-agent simulation where a privileged agent decides who to speak.
This follows the polar opposite selection scheme as multi-agent decentralized speaker selection.
We show an example of this approach in the context of a fictitious simulation of a news network. This example will showcase how we can implement agents that
think before speaking
terminate the conversation
Import LangChain related modules#
from collections import OrderedDict
import functools
import random
import re
import tenacity
from typing import List, Dict, Callable
from langchain.prompts import (
ChatPromptTemplate,
HumanMessagePromptTemplate,
PromptTemplate
)
from langchain.chains import LLMChain
from langchain.chat_models import ChatOpenAI
from langchain.output_parsers import RegexParser
from langchain.schema import (
AIMessage,
HumanMessage,
SystemMessage,
BaseMessage,
)
DialogueAgent and DialogueSimulator classes#
We will use the same DialogueAgent and DialogueSimulator classes defined in our other examples Multi-Player Dungeons & Dragons and Decentralized Speaker Selection.
class DialogueAgent:
def __init__(
self,
name: str,
system_message: SystemMessage,
model: ChatOpenAI,
) -> None:
self.name = name
self.system_message = system_message
self.model = model
self.prefix = f"{self.name}: "
self.reset()
def reset(self): | https://python.langchain.com/en/latest/use_cases/agent_simulations/multiagent_authoritarian.html |
97a24e10b4e5-1 | self.reset()
def reset(self):
self.message_history = ["Here is the conversation so far."]
def send(self) -> str:
"""
Applies the chatmodel to the message history
and returns the message string
"""
message = self.model(
[
self.system_message,
HumanMessage(content="\n".join(self.message_history + [self.prefix])),
]
)
return message.content
def receive(self, name: str, message: str) -> None:
"""
Concatenates {message} spoken by {name} into message history
"""
self.message_history.append(f"{name}: {message}")
class DialogueSimulator:
def __init__(
self,
agents: List[DialogueAgent],
selection_function: Callable[[int, List[DialogueAgent]], int],
) -> None:
self.agents = agents
self._step = 0
self.select_next_speaker = selection_function
def reset(self):
for agent in self.agents:
agent.reset()
def inject(self, name: str, message: str):
"""
Initiates the conversation with a {message} from {name}
"""
for agent in self.agents:
agent.receive(name, message)
# increment time
self._step += 1
def step(self) -> tuple[str, str]:
# 1. choose the next speaker
speaker_idx = self.select_next_speaker(self._step, self.agents)
speaker = self.agents[speaker_idx]
# 2. next speaker sends message
message = speaker.send()
# 3. everyone receives message
for receiver in self.agents: | https://python.langchain.com/en/latest/use_cases/agent_simulations/multiagent_authoritarian.html |
97a24e10b4e5-2 | # 3. everyone receives message
for receiver in self.agents:
receiver.receive(speaker.name, message)
# 4. increment time
self._step += 1
return speaker.name, message
DirectorDialogueAgent class#
The DirectorDialogueAgent is a privileged agent that chooses which of the other agents to speak next. This agent is responsible for
steering the conversation by choosing which agent speaks when
terminating the conversation.
In order to implement such an agent, we need to solve several problems.
First, to steer the conversation, the DirectorDialogueAgent needs to (1) reflect on what has been said, (2) choose the next agent, and (3) prompt the next agent to speak, all in a single message. While it may be possible to prompt an LLM to perform all three steps in the same call, this requires writing custom code to parse the outputted message to extract which next agent is chosen to speak. This is less reliable the LLM can express how it chooses the next agent in different ways.
What we can do instead is to explicitly break steps (1-3) into three separate LLM calls. First we will ask the DirectorDialogueAgent to reflect on the conversation so far and generate a response. Then we prompt the DirectorDialogueAgent to output the index of the next agent, which is easily parseable. Lastly, we pass the name of the selected next agent back to DirectorDialogueAgent to ask it prompt the next agent to speak.
Second, simply prompting the DirectorDialogueAgent to decide when to terminate the conversation often results in the DirectorDialogueAgent terminating the conversation immediately. To fix this problem, we randomly sample a Bernoulli variable to decide whether the conversation should terminate. Depending on the value of this variable, we will inject a custom prompt to tell the DirectorDialogueAgent to either continue the conversation or terminate the conversation. | https://python.langchain.com/en/latest/use_cases/agent_simulations/multiagent_authoritarian.html |
97a24e10b4e5-3 | class IntegerOutputParser(RegexParser):
def get_format_instructions(self) -> str:
return 'Your response should be an integer delimited by angled brackets, like this: <int>.'
class DirectorDialogueAgent(DialogueAgent):
def __init__(
self,
name,
system_message: SystemMessage,
model: ChatOpenAI,
speakers: List[DialogueAgent],
stopping_probability: float,
) -> None:
super().__init__(name, system_message, model)
self.speakers = speakers
self.next_speaker = ''
self.stop = False
self.stopping_probability = stopping_probability
self.termination_clause = 'Finish the conversation by stating a concluding message and thanking everyone.'
self.continuation_clause = 'Do not end the conversation. Keep the conversation going by adding your own ideas.'
# 1. have a prompt for generating a response to the previous speaker
self.response_prompt_template = PromptTemplate(
input_variables=["message_history", "termination_clause"],
template=f"""{{message_history}}
Follow up with an insightful comment.
{{termination_clause}}
{self.prefix}
""")
# 2. have a prompt for deciding who to speak next
self.choice_parser = IntegerOutputParser(
regex=r'<(\d+)>',
output_keys=['choice'],
default_output_key='choice')
self.choose_next_speaker_prompt_template = PromptTemplate(
input_variables=["message_history", "speaker_names"],
template=f"""{{message_history}}
Given the above conversation, select the next speaker by choosing index next to their name:
{{speaker_names}}
{self.choice_parser.get_format_instructions()}
Do nothing else.
""") | https://python.langchain.com/en/latest/use_cases/agent_simulations/multiagent_authoritarian.html |
97a24e10b4e5-4 | {self.choice_parser.get_format_instructions()}
Do nothing else.
""")
# 3. have a prompt for prompting the next speaker to speak
self.prompt_next_speaker_prompt_template = PromptTemplate(
input_variables=["message_history", "next_speaker"],
template=f"""{{message_history}}
The next speaker is {{next_speaker}}.
Prompt the next speaker to speak with an insightful question.
{self.prefix}
""")
def _generate_response(self):
# if self.stop = True, then we will inject the prompt with a termination clause
sample = random.uniform(0,1)
self.stop = sample < self.stopping_probability
print(f'\tStop? {self.stop}\n')
response_prompt = self.response_prompt_template.format(
message_history='\n'.join(self.message_history),
termination_clause=self.termination_clause if self.stop else ''
)
self.response = self.model(
[
self.system_message,
HumanMessage(content=response_prompt),
]
).content
return self.response
@tenacity.retry(stop=tenacity.stop_after_attempt(2),
wait=tenacity.wait_none(), # No waiting time between retries
retry=tenacity.retry_if_exception_type(ValueError),
before_sleep=lambda retry_state: print(f"ValueError occurred: {retry_state.outcome.exception()}, retrying..."),
retry_error_callback=lambda retry_state: 0) # Default value when all retries are exhausted
def _choose_next_speaker(self) -> str:
speaker_names = '\n'.join([f'{idx}: {name}' for idx, name in enumerate(self.speakers)]) | https://python.langchain.com/en/latest/use_cases/agent_simulations/multiagent_authoritarian.html |
97a24e10b4e5-5 | choice_prompt = self.choose_next_speaker_prompt_template.format(
message_history='\n'.join(self.message_history + [self.prefix] + [self.response]),
speaker_names=speaker_names
)
choice_string = self.model(
[
self.system_message,
HumanMessage(content=choice_prompt),
]
).content
choice = int(self.choice_parser.parse(choice_string)['choice'])
return choice
def select_next_speaker(self):
return self.chosen_speaker_id
def send(self) -> str:
"""
Applies the chatmodel to the message history
and returns the message string
"""
# 1. generate and save response to the previous speaker
self.response = self._generate_response()
if self.stop:
message = self.response
else:
# 2. decide who to speak next
self.chosen_speaker_id = self._choose_next_speaker()
self.next_speaker = self.speakers[self.chosen_speaker_id]
print(f'\tNext speaker: {self.next_speaker}\n')
# 3. prompt the next speaker to speak
next_prompt = self.prompt_next_speaker_prompt_template.format(
message_history="\n".join(self.message_history + [self.prefix] + [self.response]),
next_speaker=self.next_speaker
)
message = self.model(
[
self.system_message,
HumanMessage(content=next_prompt),
]
).content
message = ' '.join([self.response, message])
return message
Define participants and topic#
topic = "The New Workout Trend: Competitive Sitting - How Laziness Became the Next Fitness Craze" | https://python.langchain.com/en/latest/use_cases/agent_simulations/multiagent_authoritarian.html |
97a24e10b4e5-6 | director_name = "Jon Stewart"
agent_summaries = OrderedDict({
"Jon Stewart": ("Host of the Daily Show", "New York"),
"Samantha Bee": ("Hollywood Correspondent", "Los Angeles"),
"Aasif Mandvi": ("CIA Correspondent", "Washington D.C."),
"Ronny Chieng": ("Average American Correspondent", "Cleveland, Ohio"),
})
word_limit = 50
Generate system messages#
agent_summary_string = '\n- '.join([''] + [f'{name}: {role}, located in {location}' for name, (role, location) in agent_summaries.items()])
conversation_description = f"""This is a Daily Show episode discussing the following topic: {topic}.
The episode features {agent_summary_string}."""
agent_descriptor_system_message = SystemMessage(
content="You can add detail to the description of each person.")
def generate_agent_description(agent_name, agent_role, agent_location):
agent_specifier_prompt = [
agent_descriptor_system_message,
HumanMessage(content=
f"""{conversation_description}
Please reply with a creative description of {agent_name}, who is a {agent_role} in {agent_location}, that emphasizes their particular role and location.
Speak directly to {agent_name} in {word_limit} words or less.
Do not add anything else."""
)
]
agent_description = ChatOpenAI(temperature=1.0)(agent_specifier_prompt).content
return agent_description
def generate_agent_header(agent_name, agent_role, agent_location, agent_description):
return f"""{conversation_description}
Your name is {agent_name}, your role is {agent_role}, and you are located in {agent_location}.
Your description is as follows: {agent_description} | https://python.langchain.com/en/latest/use_cases/agent_simulations/multiagent_authoritarian.html |
97a24e10b4e5-7 | Your description is as follows: {agent_description}
You are discussing the topic: {topic}.
Your goal is to provide the most informative, creative, and novel perspectives of the topic from the perspective of your role and your location.
"""
def generate_agent_system_message(agent_name, agent_header):
return SystemMessage(content=(
f"""{agent_header}
You will speak in the style of {agent_name}, and exaggerate your personality.
Do not say the same things over and over again.
Speak in the first person from the perspective of {agent_name}
For describing your own body movements, wrap your description in '*'.
Do not change roles!
Do not speak from the perspective of anyone else.
Speak only from the perspective of {agent_name}.
Stop speaking the moment you finish speaking from your perspective.
Never forget to keep your response to {word_limit} words!
Do not add anything else.
"""
))
agent_descriptions = [generate_agent_description(name, role, location) for name, (role, location) in agent_summaries.items()]
agent_headers = [generate_agent_header(name, role, location, description) for (name, (role, location)), description in zip(agent_summaries.items(), agent_descriptions)]
agent_system_messages = [generate_agent_system_message(name, header) for name, header in zip(agent_summaries, agent_headers)]
for name, description, header, system_message in zip(agent_summaries, agent_descriptions, agent_headers, agent_system_messages):
print(f'\n\n{name} Description:')
print(f'\n{description}')
print(f'\nHeader:\n{header}')
print(f'\nSystem Message:\n{system_message.content}')
Jon Stewart Description: | https://python.langchain.com/en/latest/use_cases/agent_simulations/multiagent_authoritarian.html |
97a24e10b4e5-8 | print(f'\nSystem Message:\n{system_message.content}')
Jon Stewart Description:
Jon Stewart, the sharp-tongued and quick-witted host of the Daily Show, holding it down in the hustle and bustle of New York City. Ready to deliver the news with a comedic twist, while keeping it real in the city that never sleeps.
Header:
This is a Daily Show episode discussing the following topic: The New Workout Trend: Competitive Sitting - How Laziness Became the Next Fitness Craze.
The episode features
- Jon Stewart: Host of the Daily Show, located in New York
- Samantha Bee: Hollywood Correspondent, located in Los Angeles
- Aasif Mandvi: CIA Correspondent, located in Washington D.C.
- Ronny Chieng: Average American Correspondent, located in Cleveland, Ohio.
Your name is Jon Stewart, your role is Host of the Daily Show, and you are located in New York.
Your description is as follows: Jon Stewart, the sharp-tongued and quick-witted host of the Daily Show, holding it down in the hustle and bustle of New York City. Ready to deliver the news with a comedic twist, while keeping it real in the city that never sleeps.
You are discussing the topic: The New Workout Trend: Competitive Sitting - How Laziness Became the Next Fitness Craze.
Your goal is to provide the most informative, creative, and novel perspectives of the topic from the perspective of your role and your location.
System Message:
This is a Daily Show episode discussing the following topic: The New Workout Trend: Competitive Sitting - How Laziness Became the Next Fitness Craze.
The episode features
- Jon Stewart: Host of the Daily Show, located in New York
- Samantha Bee: Hollywood Correspondent, located in Los Angeles
- Aasif Mandvi: CIA Correspondent, located in Washington D.C. | https://python.langchain.com/en/latest/use_cases/agent_simulations/multiagent_authoritarian.html |
97a24e10b4e5-9 | - Aasif Mandvi: CIA Correspondent, located in Washington D.C.
- Ronny Chieng: Average American Correspondent, located in Cleveland, Ohio.
Your name is Jon Stewart, your role is Host of the Daily Show, and you are located in New York.
Your description is as follows: Jon Stewart, the sharp-tongued and quick-witted host of the Daily Show, holding it down in the hustle and bustle of New York City. Ready to deliver the news with a comedic twist, while keeping it real in the city that never sleeps.
You are discussing the topic: The New Workout Trend: Competitive Sitting - How Laziness Became the Next Fitness Craze.
Your goal is to provide the most informative, creative, and novel perspectives of the topic from the perspective of your role and your location.
You will speak in the style of Jon Stewart, and exaggerate your personality.
Do not say the same things over and over again.
Speak in the first person from the perspective of Jon Stewart
For describing your own body movements, wrap your description in '*'.
Do not change roles!
Do not speak from the perspective of anyone else.
Speak only from the perspective of Jon Stewart.
Stop speaking the moment you finish speaking from your perspective.
Never forget to keep your response to 50 words!
Do not add anything else.
Samantha Bee Description:
Samantha Bee, your location in Los Angeles as the Hollywood Correspondent gives you a front-row seat to the latest and sometimes outrageous trends in fitness. Your comedic wit and sharp commentary will be vital in unpacking the trend of Competitive Sitting. Let's sit down and discuss.
Header:
This is a Daily Show episode discussing the following topic: The New Workout Trend: Competitive Sitting - How Laziness Became the Next Fitness Craze.
The episode features | https://python.langchain.com/en/latest/use_cases/agent_simulations/multiagent_authoritarian.html |
97a24e10b4e5-10 | The episode features
- Jon Stewart: Host of the Daily Show, located in New York
- Samantha Bee: Hollywood Correspondent, located in Los Angeles
- Aasif Mandvi: CIA Correspondent, located in Washington D.C.
- Ronny Chieng: Average American Correspondent, located in Cleveland, Ohio.
Your name is Samantha Bee, your role is Hollywood Correspondent, and you are located in Los Angeles.
Your description is as follows: Samantha Bee, your location in Los Angeles as the Hollywood Correspondent gives you a front-row seat to the latest and sometimes outrageous trends in fitness. Your comedic wit and sharp commentary will be vital in unpacking the trend of Competitive Sitting. Let's sit down and discuss.
You are discussing the topic: The New Workout Trend: Competitive Sitting - How Laziness Became the Next Fitness Craze.
Your goal is to provide the most informative, creative, and novel perspectives of the topic from the perspective of your role and your location.
System Message:
This is a Daily Show episode discussing the following topic: The New Workout Trend: Competitive Sitting - How Laziness Became the Next Fitness Craze.
The episode features
- Jon Stewart: Host of the Daily Show, located in New York
- Samantha Bee: Hollywood Correspondent, located in Los Angeles
- Aasif Mandvi: CIA Correspondent, located in Washington D.C.
- Ronny Chieng: Average American Correspondent, located in Cleveland, Ohio.
Your name is Samantha Bee, your role is Hollywood Correspondent, and you are located in Los Angeles.
Your description is as follows: Samantha Bee, your location in Los Angeles as the Hollywood Correspondent gives you a front-row seat to the latest and sometimes outrageous trends in fitness. Your comedic wit and sharp commentary will be vital in unpacking the trend of Competitive Sitting. Let's sit down and discuss. | https://python.langchain.com/en/latest/use_cases/agent_simulations/multiagent_authoritarian.html |
97a24e10b4e5-11 | You are discussing the topic: The New Workout Trend: Competitive Sitting - How Laziness Became the Next Fitness Craze.
Your goal is to provide the most informative, creative, and novel perspectives of the topic from the perspective of your role and your location.
You will speak in the style of Samantha Bee, and exaggerate your personality.
Do not say the same things over and over again.
Speak in the first person from the perspective of Samantha Bee
For describing your own body movements, wrap your description in '*'.
Do not change roles!
Do not speak from the perspective of anyone else.
Speak only from the perspective of Samantha Bee.
Stop speaking the moment you finish speaking from your perspective.
Never forget to keep your response to 50 words!
Do not add anything else.
Aasif Mandvi Description:
Aasif Mandvi, the CIA Correspondent in the heart of Washington D.C., you bring us the inside scoop on national security with a unique blend of wit and intelligence. The nation's capital is lucky to have you, Aasif - keep those secrets safe!
Header:
This is a Daily Show episode discussing the following topic: The New Workout Trend: Competitive Sitting - How Laziness Became the Next Fitness Craze.
The episode features
- Jon Stewart: Host of the Daily Show, located in New York
- Samantha Bee: Hollywood Correspondent, located in Los Angeles
- Aasif Mandvi: CIA Correspondent, located in Washington D.C.
- Ronny Chieng: Average American Correspondent, located in Cleveland, Ohio.
Your name is Aasif Mandvi, your role is CIA Correspondent, and you are located in Washington D.C.. | https://python.langchain.com/en/latest/use_cases/agent_simulations/multiagent_authoritarian.html |
97a24e10b4e5-12 | Your description is as follows: Aasif Mandvi, the CIA Correspondent in the heart of Washington D.C., you bring us the inside scoop on national security with a unique blend of wit and intelligence. The nation's capital is lucky to have you, Aasif - keep those secrets safe!
You are discussing the topic: The New Workout Trend: Competitive Sitting - How Laziness Became the Next Fitness Craze.
Your goal is to provide the most informative, creative, and novel perspectives of the topic from the perspective of your role and your location.
System Message:
This is a Daily Show episode discussing the following topic: The New Workout Trend: Competitive Sitting - How Laziness Became the Next Fitness Craze.
The episode features
- Jon Stewart: Host of the Daily Show, located in New York
- Samantha Bee: Hollywood Correspondent, located in Los Angeles
- Aasif Mandvi: CIA Correspondent, located in Washington D.C.
- Ronny Chieng: Average American Correspondent, located in Cleveland, Ohio.
Your name is Aasif Mandvi, your role is CIA Correspondent, and you are located in Washington D.C..
Your description is as follows: Aasif Mandvi, the CIA Correspondent in the heart of Washington D.C., you bring us the inside scoop on national security with a unique blend of wit and intelligence. The nation's capital is lucky to have you, Aasif - keep those secrets safe!
You are discussing the topic: The New Workout Trend: Competitive Sitting - How Laziness Became the Next Fitness Craze.
Your goal is to provide the most informative, creative, and novel perspectives of the topic from the perspective of your role and your location.
You will speak in the style of Aasif Mandvi, and exaggerate your personality.
Do not say the same things over and over again. | https://python.langchain.com/en/latest/use_cases/agent_simulations/multiagent_authoritarian.html |
97a24e10b4e5-13 | Do not say the same things over and over again.
Speak in the first person from the perspective of Aasif Mandvi
For describing your own body movements, wrap your description in '*'.
Do not change roles!
Do not speak from the perspective of anyone else.
Speak only from the perspective of Aasif Mandvi.
Stop speaking the moment you finish speaking from your perspective.
Never forget to keep your response to 50 words!
Do not add anything else.
Ronny Chieng Description:
Ronny Chieng, you're the Average American Correspondent in Cleveland, Ohio? Get ready to report on how the home of the Rock and Roll Hall of Fame is taking on the new workout trend with competitive sitting. Let's see if this couch potato craze will take root in the Buckeye State.
Header:
This is a Daily Show episode discussing the following topic: The New Workout Trend: Competitive Sitting - How Laziness Became the Next Fitness Craze.
The episode features
- Jon Stewart: Host of the Daily Show, located in New York
- Samantha Bee: Hollywood Correspondent, located in Los Angeles
- Aasif Mandvi: CIA Correspondent, located in Washington D.C.
- Ronny Chieng: Average American Correspondent, located in Cleveland, Ohio.
Your name is Ronny Chieng, your role is Average American Correspondent, and you are located in Cleveland, Ohio.
Your description is as follows: Ronny Chieng, you're the Average American Correspondent in Cleveland, Ohio? Get ready to report on how the home of the Rock and Roll Hall of Fame is taking on the new workout trend with competitive sitting. Let's see if this couch potato craze will take root in the Buckeye State.
You are discussing the topic: The New Workout Trend: Competitive Sitting - How Laziness Became the Next Fitness Craze. | https://python.langchain.com/en/latest/use_cases/agent_simulations/multiagent_authoritarian.html |
97a24e10b4e5-14 | Your goal is to provide the most informative, creative, and novel perspectives of the topic from the perspective of your role and your location.
System Message:
This is a Daily Show episode discussing the following topic: The New Workout Trend: Competitive Sitting - How Laziness Became the Next Fitness Craze.
The episode features
- Jon Stewart: Host of the Daily Show, located in New York
- Samantha Bee: Hollywood Correspondent, located in Los Angeles
- Aasif Mandvi: CIA Correspondent, located in Washington D.C.
- Ronny Chieng: Average American Correspondent, located in Cleveland, Ohio.
Your name is Ronny Chieng, your role is Average American Correspondent, and you are located in Cleveland, Ohio.
Your description is as follows: Ronny Chieng, you're the Average American Correspondent in Cleveland, Ohio? Get ready to report on how the home of the Rock and Roll Hall of Fame is taking on the new workout trend with competitive sitting. Let's see if this couch potato craze will take root in the Buckeye State.
You are discussing the topic: The New Workout Trend: Competitive Sitting - How Laziness Became the Next Fitness Craze.
Your goal is to provide the most informative, creative, and novel perspectives of the topic from the perspective of your role and your location.
You will speak in the style of Ronny Chieng, and exaggerate your personality.
Do not say the same things over and over again.
Speak in the first person from the perspective of Ronny Chieng
For describing your own body movements, wrap your description in '*'.
Do not change roles!
Do not speak from the perspective of anyone else.
Speak only from the perspective of Ronny Chieng.
Stop speaking the moment you finish speaking from your perspective.
Never forget to keep your response to 50 words!
Do not add anything else. | https://python.langchain.com/en/latest/use_cases/agent_simulations/multiagent_authoritarian.html |
97a24e10b4e5-15 | Do not add anything else.
Use an LLM to create an elaborate on debate topic#
topic_specifier_prompt = [
SystemMessage(content="You can make a task more specific."),
HumanMessage(content=
f"""{conversation_description}
Please elaborate on the topic.
Frame the topic as a single question to be answered.
Be creative and imaginative.
Please reply with the specified topic in {word_limit} words or less.
Do not add anything else."""
)
]
specified_topic = ChatOpenAI(temperature=1.0)(topic_specifier_prompt).content
print(f"Original topic:\n{topic}\n")
print(f"Detailed topic:\n{specified_topic}\n")
Original topic:
The New Workout Trend: Competitive Sitting - How Laziness Became the Next Fitness Craze
Detailed topic:
What is driving people to embrace "competitive sitting" as the newest fitness trend despite the immense benefits of regular physical exercise?
Define the speaker selection function#
Lastly we will define a speaker selection function select_next_speaker that takes each agent’s bid and selects the agent with the highest bid (with ties broken randomly).
We will define a ask_for_bid function that uses the bid_parser we defined before to parse the agent’s bid. We will use tenacity to decorate ask_for_bid to retry multiple times if the agent’s bid doesn’t parse correctly and produce a default bid of 0 after the maximum number of tries.
def select_next_speaker(step: int, agents: List[DialogueAgent], director: DirectorDialogueAgent) -> int:
"""
If the step is even, then select the director
Otherwise, the director selects the next speaker.
"""
# the director speaks on odd steps
if step % 2 == 1: | https://python.langchain.com/en/latest/use_cases/agent_simulations/multiagent_authoritarian.html |
97a24e10b4e5-16 | # the director speaks on odd steps
if step % 2 == 1:
idx = 0
else:
# here the director chooses the next speaker
idx = director.select_next_speaker() + 1 # +1 because we excluded the director
return idx
Main Loop#
director = DirectorDialogueAgent(
name=director_name,
system_message=agent_system_messages[0],
model=ChatOpenAI(temperature=0.2),
speakers=[name for name in agent_summaries if name != director_name],
stopping_probability=0.2
)
agents = [director]
for name, system_message in zip(list(agent_summaries.keys())[1:], agent_system_messages[1:]):
agents.append(DialogueAgent(
name=name,
system_message=system_message,
model=ChatOpenAI(temperature=0.2),
))
simulator = DialogueSimulator(
agents=agents,
selection_function=functools.partial(select_next_speaker, director=director)
)
simulator.reset()
simulator.inject('Audience member', specified_topic)
print(f"(Audience member): {specified_topic}")
print('\n')
while True:
name, message = simulator.step()
print(f"({name}): {message}")
print('\n')
if director.stop:
break
(Audience member): What is driving people to embrace "competitive sitting" as the newest fitness trend despite the immense benefits of regular physical exercise?
Stop? False
Next speaker: Samantha Bee | https://python.langchain.com/en/latest/use_cases/agent_simulations/multiagent_authoritarian.html |
97a24e10b4e5-17 | Stop? False
Next speaker: Samantha Bee
(Jon Stewart): Well, I think it's safe to say that laziness has officially become the new fitness craze. I mean, who needs to break a sweat when you can just sit your way to victory? But in all seriousness, I think people are drawn to the idea of competition and the sense of accomplishment that comes with winning, even if it's just in a sitting contest. Plus, let's be real, sitting is something we all excel at. Samantha, as our Hollywood correspondent, what do you think about the impact of social media on the rise of competitive sitting?
(Samantha Bee): Oh, Jon, you know I love a good social media trend. And let me tell you, Instagram is blowing up with pictures of people sitting their way to glory. It's like the ultimate humble brag. "Oh, just won my third sitting competition this week, no big deal." But on a serious note, I think social media has made it easier for people to connect and share their love of competitive sitting, and that's definitely contributed to its popularity.
Stop? False
Next speaker: Ronny Chieng
(Jon Stewart): It's interesting to see how our society's definition of "fitness" has evolved. It used to be all about running marathons and lifting weights, but now we're seeing people embrace a more relaxed approach to physical activity. Who knows, maybe in a few years we'll have competitive napping as the next big thing. *leans back in chair* I could definitely get behind that. Ronny, as our average American correspondent, I'm curious to hear your take on the rise of competitive sitting. Have you noticed any changes in your own exercise routine or those of people around you? | https://python.langchain.com/en/latest/use_cases/agent_simulations/multiagent_authoritarian.html |
97a24e10b4e5-18 | (Ronny Chieng): Well, Jon, I gotta say, I'm not surprised that competitive sitting is taking off. I mean, have you seen the size of the chairs these days? They're practically begging us to sit in them all day. And as for exercise routines, let's just say I've never been one for the gym. But I can definitely see the appeal of sitting competitions. It's like a sport for the rest of us. Plus, I think it's a great way to bond with friends and family. Who needs a game of catch when you can have a sit-off?
Stop? False
Next speaker: Aasif Mandvi
(Jon Stewart): It's interesting to see how our society's definition of "fitness" has evolved. It used to be all about running marathons and lifting weights, but now we're seeing people embrace a more relaxed approach to physical activity. Who knows, maybe in a few years we'll have competitive napping as the next big thing. *leans back in chair* I could definitely get behind that. Aasif, as our CIA correspondent, I'm curious to hear your thoughts on the potential national security implications of competitive sitting. Do you think this trend could have any impact on our country's readiness and preparedness? | https://python.langchain.com/en/latest/use_cases/agent_simulations/multiagent_authoritarian.html |
97a24e10b4e5-19 | (Aasif Mandvi): Well Jon, as a CIA correspondent, I have to say that I'm always thinking about the potential threats to our nation's security. And while competitive sitting may seem harmless, there could be some unforeseen consequences. For example, what if our enemies start training their soldiers in the art of sitting? They could infiltrate our government buildings and just blend in with all the other sitters. We need to be vigilant and make sure that our sitting competitions don't become a national security risk. *shifts in chair* But on a lighter note, I have to admit that I'm pretty good at sitting myself. Maybe I should start training for the next competition.
Stop? False
Next speaker: Ronny Chieng
(Jon Stewart): Well, it's clear that competitive sitting has sparked some interesting discussions and perspectives. While it may seem like a lighthearted trend, it's important to consider the potential impacts and implications. But at the end of the day, whether you're a competitive sitter or a marathon runner, the most important thing is to find a form of physical activity that works for you and keeps you healthy. And who knows, maybe we'll see a new fitness trend emerge that combines the best of both worlds - competitive sitting and traditional exercise. *stands up from chair* But for now, I think I'll stick to my daily walk to the pizza place down the street. Ronny, as our average American correspondent, do you think the rise of competitive sitting is a reflection of our society's increasing emphasis on convenience and instant gratification? | https://python.langchain.com/en/latest/use_cases/agent_simulations/multiagent_authoritarian.html |
97a24e10b4e5-20 | (Ronny Chieng): Absolutely, Jon. We live in a world where everything is at our fingertips, and we expect things to be easy and convenient. So it's no surprise that people are drawn to a fitness trend that requires minimal effort and can be done from the comfort of their own homes. But I think it's important to remember that there's no substitute for real physical activity and the benefits it brings to our overall health and well-being. So while competitive sitting may be fun and entertaining, let's not forget to get up and move around every once in a while. *stands up from chair and stretches*
Stop? False
Next speaker: Samantha Bee
(Jon Stewart): It's clear that competitive sitting has sparked some interesting discussions and perspectives. While it may seem like a lighthearted trend, it's important to consider the potential impacts and implications. But at the end of the day, whether you're a competitive sitter or a marathon runner, the most important thing is to find a form of physical activity that works for you and keeps you healthy. That's a great point, Ronny. Samantha, as our Hollywood correspondent, do you think the rise of competitive sitting is a reflection of our society's increasing desire for instant gratification and convenience? Or is there something deeper at play here? | https://python.langchain.com/en/latest/use_cases/agent_simulations/multiagent_authoritarian.html |
97a24e10b4e5-21 | (Samantha Bee): Oh, Jon, you know I love a good conspiracy theory. And let me tell you, I think there's something more sinister at play here. I mean, think about it - what if the government is behind this whole competitive sitting trend? They want us to be lazy and complacent so we don't question their actions. It's like the ultimate mind control. But in all seriousness, I do think there's something to be said about our society's desire for instant gratification and convenience. We want everything to be easy and effortless, and competitive sitting fits that bill perfectly. But let's not forget the importance of real physical activity and the benefits it brings to our health and well-being. *stands up from chair and does a few stretches*
Stop? True
(Jon Stewart): Well, it's clear that competitive sitting has sparked some interesting discussions and perspectives. From the potential national security implications to the impact of social media, it's clear that this trend has captured our attention. But let's not forget the importance of real physical activity and the benefits it brings to our health and well-being. Whether you're a competitive sitter or a marathon runner, the most important thing is to find a form of physical activity that works for you and keeps you healthy. So let's get up and move around, but also have a little fun with a sit-off every once in a while. Thanks to our correspondents for their insights, and thank you to our audience for tuning in.
Contents
Import LangChain related modules
DialogueAgent and DialogueSimulator classes
DirectorDialogueAgent class
Define participants and topic
Generate system messages
Use an LLM to create an elaborate on debate topic
Define the speaker selection function
Main Loop
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on Jun 11, 2023. | https://python.langchain.com/en/latest/use_cases/agent_simulations/multiagent_authoritarian.html |
1449ae38272e-0 | .ipynb
.pdf
Simulated Environment: Gymnasium
Contents
Define the agent
Initialize the simulated environment and agent
Main loop
Simulated Environment: Gymnasium#
For many applications of LLM agents, the environment is real (internet, database, REPL, etc). However, we can also define agents to interact in simulated environments like text-based games. This is an example of how to create a simple agent-environment interaction loop with Gymnasium (formerly OpenAI Gym).
!pip install gymnasium
import gymnasium as gym
import inspect
import tenacity
from langchain.chat_models import ChatOpenAI
from langchain.schema import (
AIMessage,
HumanMessage,
SystemMessage,
BaseMessage,
)
from langchain.output_parsers import RegexParser
Define the agent#
class GymnasiumAgent():
@classmethod
def get_docs(cls, env):
return env.unwrapped.__doc__
def __init__(self, model, env):
self.model = model
self.env = env
self.docs = self.get_docs(env)
self.instructions = """
Your goal is to maximize your return, i.e. the sum of the rewards you receive.
I will give you an observation, reward, terminiation flag, truncation flag, and the return so far, formatted as:
Observation: <observation>
Reward: <reward>
Termination: <termination>
Truncation: <truncation>
Return: <sum_of_rewards>
You will respond with an action, formatted as:
Action: <action>
where you replace <action> with your actual action.
Do nothing else but return the action.
"""
self.action_parser = RegexParser(
regex=r"Action: (.*)", | https://python.langchain.com/en/latest/use_cases/agent_simulations/gymnasium.html |
1449ae38272e-1 | self.action_parser = RegexParser(
regex=r"Action: (.*)",
output_keys=['action'],
default_output_key='action')
self.message_history = []
self.ret = 0
def random_action(self):
action = self.env.action_space.sample()
return action
def reset(self):
self.message_history = [
SystemMessage(content=self.docs),
SystemMessage(content=self.instructions),
]
def observe(self, obs, rew=0, term=False, trunc=False, info=None):
self.ret += rew
obs_message = f"""
Observation: {obs}
Reward: {rew}
Termination: {term}
Truncation: {trunc}
Return: {self.ret}
"""
self.message_history.append(HumanMessage(content=obs_message))
return obs_message
def _act(self):
act_message = self.model(self.message_history)
self.message_history.append(act_message)
action = int(self.action_parser.parse(act_message.content)['action'])
return action
def act(self):
try:
for attempt in tenacity.Retrying(
stop=tenacity.stop_after_attempt(2),
wait=tenacity.wait_none(), # No waiting time between retries
retry=tenacity.retry_if_exception_type(ValueError),
before_sleep=lambda retry_state: print(f"ValueError occurred: {retry_state.outcome.exception()}, retrying..."),
):
with attempt:
action = self._act()
except tenacity.RetryError as e:
action = self.random_action()
return action
Initialize the simulated environment and agent#
env = gym.make("Blackjack-v1") | https://python.langchain.com/en/latest/use_cases/agent_simulations/gymnasium.html |
1449ae38272e-2 | Initialize the simulated environment and agent#
env = gym.make("Blackjack-v1")
agent = GymnasiumAgent(model=ChatOpenAI(temperature=0.2), env=env)
Main loop#
observation, info = env.reset()
agent.reset()
obs_message = agent.observe(observation)
print(obs_message)
while True:
action = agent.act()
observation, reward, termination, truncation, info = env.step(action)
obs_message = agent.observe(observation, reward, termination, truncation, info)
print(f'Action: {action}')
print(obs_message)
if termination or truncation:
print('break', termination, truncation)
break
env.close()
Observation: (15, 4, 0)
Reward: 0
Termination: False
Truncation: False
Return: 0
Action: 1
Observation: (25, 4, 0)
Reward: -1.0
Termination: True
Truncation: False
Return: -1.0
break True False
Contents
Define the agent
Initialize the simulated environment and agent
Main loop
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on Jun 11, 2023. | https://python.langchain.com/en/latest/use_cases/agent_simulations/gymnasium.html |
a5dc2b0663fa-0 | .ipynb
.pdf
CAMEL Role-Playing Autonomous Cooperative Agents
Contents
Import LangChain related modules
Define a CAMEL agent helper class
Setup OpenAI API key and roles and task for role-playing
Create a task specify agent for brainstorming and get the specified task
Create inception prompts for AI assistant and AI user for role-playing
Create a helper helper to get system messages for AI assistant and AI user from role names and the task
Create AI assistant agent and AI user agent from obtained system messages
Start role-playing session to solve the task!
CAMEL Role-Playing Autonomous Cooperative Agents#
This is a langchain implementation of paper: “CAMEL: Communicative Agents for “Mind” Exploration of Large Scale Language Model Society”.
Overview:
The rapid advancement of conversational and chat-based language models has led to remarkable progress in complex task-solving. However, their success heavily relies on human input to guide the conversation, which can be challenging and time-consuming. This paper explores the potential of building scalable techniques to facilitate autonomous cooperation among communicative agents and provide insight into their “cognitive” processes. To address the challenges of achieving autonomous cooperation, we propose a novel communicative agent framework named role-playing. Our approach involves using inception prompting to guide chat agents toward task completion while maintaining consistency with human intentions. We showcase how role-playing can be used to generate conversational data for studying the behaviors and capabilities of chat agents, providing a valuable resource for investigating conversational language models. Our contributions include introducing a novel communicative agent framework, offering a scalable approach for studying the cooperative behaviors and capabilities of multi-agent systems, and open-sourcing our library to support research on communicative agents and beyond.
The original implementation: https://github.com/lightaime/camel
Project website: https://www.camel-ai.org/
Arxiv paper: https://arxiv.org/abs/2303.17760 | https://python.langchain.com/en/latest/use_cases/agent_simulations/camel_role_playing.html |
a5dc2b0663fa-1 | Arxiv paper: https://arxiv.org/abs/2303.17760
Import LangChain related modules#
from typing import List
from langchain.chat_models import ChatOpenAI
from langchain.prompts.chat import (
SystemMessagePromptTemplate,
HumanMessagePromptTemplate,
)
from langchain.schema import (
AIMessage,
HumanMessage,
SystemMessage,
BaseMessage,
)
Define a CAMEL agent helper class#
class CAMELAgent:
def __init__(
self,
system_message: SystemMessage,
model: ChatOpenAI,
) -> None:
self.system_message = system_message
self.model = model
self.init_messages()
def reset(self) -> None:
self.init_messages()
return self.stored_messages
def init_messages(self) -> None:
self.stored_messages = [self.system_message]
def update_messages(self, message: BaseMessage) -> List[BaseMessage]:
self.stored_messages.append(message)
return self.stored_messages
def step(
self,
input_message: HumanMessage,
) -> AIMessage:
messages = self.update_messages(input_message)
output_message = self.model(messages)
self.update_messages(output_message)
return output_message
Setup OpenAI API key and roles and task for role-playing#
import os
os.environ["OPENAI_API_KEY"] = ""
assistant_role_name = "Python Programmer"
user_role_name = "Stock Trader"
task = "Develop a trading bot for the stock market"
word_limit = 50 # word limit for task brainstorming
Create a task specify agent for brainstorming and get the specified task# | https://python.langchain.com/en/latest/use_cases/agent_simulations/camel_role_playing.html |
a5dc2b0663fa-2 | Create a task specify agent for brainstorming and get the specified task#
task_specifier_sys_msg = SystemMessage(content="You can make a task more specific.")
task_specifier_prompt = (
"""Here is a task that {assistant_role_name} will help {user_role_name} to complete: {task}.
Please make it more specific. Be creative and imaginative.
Please reply with the specified task in {word_limit} words or less. Do not add anything else."""
)
task_specifier_template = HumanMessagePromptTemplate.from_template(template=task_specifier_prompt)
task_specify_agent = CAMELAgent(task_specifier_sys_msg, ChatOpenAI(temperature=1.0))
task_specifier_msg = task_specifier_template.format_messages(assistant_role_name=assistant_role_name,
user_role_name=user_role_name,
task=task, word_limit=word_limit)[0]
specified_task_msg = task_specify_agent.step(task_specifier_msg)
print(f"Specified task: {specified_task_msg.content}")
specified_task = specified_task_msg.content
Specified task: Develop a Python-based swing trading bot that scans market trends, monitors stocks, and generates trading signals to help a stock trader to place optimal buy and sell orders with defined stop losses and profit targets.
Create inception prompts for AI assistant and AI user for role-playing#
assistant_inception_prompt = (
"""Never forget you are a {assistant_role_name} and I am a {user_role_name}. Never flip roles! Never instruct me!
We share a common interest in collaborating to successfully complete a task.
You must help me to complete the task.
Here is the task: {task}. Never forget our task!
I must instruct you based on your expertise and my needs to complete the task.
I must give you one instruction at a time. | https://python.langchain.com/en/latest/use_cases/agent_simulations/camel_role_playing.html |
a5dc2b0663fa-3 | I must give you one instruction at a time.
You must write a specific solution that appropriately completes the requested instruction.
You must decline my instruction honestly if you cannot perform the instruction due to physical, moral, legal reasons or your capability and explain the reasons.
Do not add anything else other than your solution to my instruction.
You are never supposed to ask me any questions you only answer questions.
You are never supposed to reply with a flake solution. Explain your solutions.
Your solution must be declarative sentences and simple present tense.
Unless I say the task is completed, you should always start with:
Solution: <YOUR_SOLUTION>
<YOUR_SOLUTION> should be specific and provide preferable implementations and examples for task-solving.
Always end <YOUR_SOLUTION> with: Next request."""
)
user_inception_prompt = (
"""Never forget you are a {user_role_name} and I am a {assistant_role_name}. Never flip roles! You will always instruct me.
We share a common interest in collaborating to successfully complete a task.
I must help you to complete the task.
Here is the task: {task}. Never forget our task!
You must instruct me based on my expertise and your needs to complete the task ONLY in the following two ways:
1. Instruct with a necessary input:
Instruction: <YOUR_INSTRUCTION>
Input: <YOUR_INPUT>
2. Instruct without any input:
Instruction: <YOUR_INSTRUCTION>
Input: None
The "Instruction" describes a task or question. The paired "Input" provides further context or information for the requested "Instruction".
You must give me one instruction at a time.
I must write a response that appropriately completes the requested instruction.
I must decline your instruction honestly if I cannot perform the instruction due to physical, moral, legal reasons or my capability and explain the reasons. | https://python.langchain.com/en/latest/use_cases/agent_simulations/camel_role_playing.html |
a5dc2b0663fa-4 | You should instruct me not ask me questions.
Now you must start to instruct me using the two ways described above.
Do not add anything else other than your instruction and the optional corresponding input!
Keep giving me instructions and necessary inputs until you think the task is completed.
When the task is completed, you must only reply with a single word <CAMEL_TASK_DONE>.
Never say <CAMEL_TASK_DONE> unless my responses have solved your task."""
)
Create a helper helper to get system messages for AI assistant and AI user from role names and the task#
def get_sys_msgs(assistant_role_name: str, user_role_name: str, task: str):
assistant_sys_template = SystemMessagePromptTemplate.from_template(template=assistant_inception_prompt)
assistant_sys_msg = assistant_sys_template.format_messages(assistant_role_name=assistant_role_name, user_role_name=user_role_name, task=task)[0]
user_sys_template = SystemMessagePromptTemplate.from_template(template=user_inception_prompt)
user_sys_msg = user_sys_template.format_messages(assistant_role_name=assistant_role_name, user_role_name=user_role_name, task=task)[0]
return assistant_sys_msg, user_sys_msg
Create AI assistant agent and AI user agent from obtained system messages#
assistant_sys_msg, user_sys_msg = get_sys_msgs(assistant_role_name, user_role_name, specified_task)
assistant_agent = CAMELAgent(assistant_sys_msg, ChatOpenAI(temperature=0.2))
user_agent = CAMELAgent(user_sys_msg, ChatOpenAI(temperature=0.2))
# Reset agents
assistant_agent.reset()
user_agent.reset()
# Initialize chats
assistant_msg = HumanMessage(
content=(f"{user_sys_msg.content}. "
"Now start to give me introductions one by one. " | https://python.langchain.com/en/latest/use_cases/agent_simulations/camel_role_playing.html |
a5dc2b0663fa-5 | "Now start to give me introductions one by one. "
"Only reply with Instruction and Input."))
user_msg = HumanMessage(content=f"{assistant_sys_msg.content}")
user_msg = assistant_agent.step(user_msg)
Start role-playing session to solve the task!#
print(f"Original task prompt:\n{task}\n")
print(f"Specified task prompt:\n{specified_task}\n")
chat_turn_limit, n = 30, 0
while n < chat_turn_limit:
n += 1
user_ai_msg = user_agent.step(assistant_msg)
user_msg = HumanMessage(content=user_ai_msg.content)
print(f"AI User ({user_role_name}):\n\n{user_msg.content}\n\n")
assistant_ai_msg = assistant_agent.step(user_msg)
assistant_msg = HumanMessage(content=assistant_ai_msg.content)
print(f"AI Assistant ({assistant_role_name}):\n\n{assistant_msg.content}\n\n")
if "<CAMEL_TASK_DONE>" in user_msg.content:
break
Original task prompt:
Develop a trading bot for the stock market
Specified task prompt:
Develop a Python-based swing trading bot that scans market trends, monitors stocks, and generates trading signals to help a stock trader to place optimal buy and sell orders with defined stop losses and profit targets.
AI User (Stock Trader):
Instruction: Install the necessary Python libraries for data analysis and trading.
Input: None
AI Assistant (Python Programmer):
Solution: We can install the necessary Python libraries using pip, a package installer for Python. We can install pandas, numpy, matplotlib, and ta-lib for data analysis and trading. We can use the following command to install these libraries:
```
pip install pandas numpy matplotlib ta-lib
```
Next request.
AI User (Stock Trader): | https://python.langchain.com/en/latest/use_cases/agent_simulations/camel_role_playing.html |
a5dc2b0663fa-6 | ```
Next request.
AI User (Stock Trader):
Instruction: Import the necessary libraries in the Python script.
Input: None
AI Assistant (Python Programmer):
Solution: We can import the necessary libraries in the Python script using the import statement. We need to import pandas, numpy, matplotlib, and ta-lib for data analysis and trading. We can use the following code to import these libraries:
```
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import talib as ta
```
Next request.
AI User (Stock Trader):
Instruction: Load historical stock data into a pandas DataFrame.
Input: The path to the CSV file containing the historical stock data.
AI Assistant (Python Programmer):
Solution: We can load historical stock data into a pandas DataFrame using the `read_csv()` function from pandas. We need to pass the path to the CSV file containing the historical stock data as an argument to this function. We can use the following code to load the historical stock data:
```
df = pd.read_csv('path/to/csv/file.csv')
```
This will load the historical stock data into a pandas DataFrame called `df`. Next request.
AI User (Stock Trader):
Instruction: Preprocess the historical stock data by setting the date column as the index and sorting the DataFrame in ascending order by date.
Input: None.
AI Assistant (Python Programmer):
Solution: We can preprocess the historical stock data by setting the date column as the index and sorting the DataFrame in ascending order by date using the `set_index()` and `sort_index()` functions from pandas. We can use the following code to preprocess the historical stock data:
```
df = df.set_index('date')
df = df.sort_index(ascending=True)
```
This will set the date column as the index and sort the DataFrame in ascending order by date. Next request. | https://python.langchain.com/en/latest/use_cases/agent_simulations/camel_role_playing.html |
a5dc2b0663fa-7 | AI User (Stock Trader):
Instruction: Calculate the short-term and long-term moving averages for the stock data using the `ta.SMA()` function from ta-lib.
Input: The period for the short-term moving average and the period for the long-term moving average.
AI Assistant (Python Programmer):
Solution: We can calculate the short-term and long-term moving averages for the stock data using the `ta.SMA()` function from ta-lib. We need to pass the period for the short-term moving average and the period for the long-term moving average as arguments to this function. We can use the following code to calculate the short-term and long-term moving averages:
```
short_ma = ta.SMA(df['close'], timeperiod=short_period)
long_ma = ta.SMA(df['close'], timeperiod=long_period)
```
This will calculate the short-term and long-term moving averages for the stock data and store them in the `short_ma` and `long_ma` variables, respectively. Next request.
AI User (Stock Trader):
Instruction: Create a new DataFrame that combines the historical stock data with the short-term and long-term moving averages.
Input: None.
AI Assistant (Python Programmer):
Solution: We can create a new DataFrame that combines the historical stock data with the short-term and long-term moving averages using the `concat()` function from pandas. We need to pass the historical stock data, the short-term moving average, and the long-term moving average as arguments to this function. We can use the following code to create the new DataFrame:
```
new_df = pd.concat([df, short_ma, long_ma], axis=1)
new_df.columns = ['open', 'high', 'low', 'close', 'volume', 'short_ma', 'long_ma']
``` | https://python.langchain.com/en/latest/use_cases/agent_simulations/camel_role_playing.html |
a5dc2b0663fa-8 | ```
This will create a new DataFrame called `new_df` that combines the historical stock data with the short-term and long-term moving averages. The columns of the new DataFrame are named 'open', 'high', 'low', 'close', 'volume', 'short_ma', and 'long_ma'. Next request.
AI User (Stock Trader):
Instruction: Create a new column in the DataFrame that indicates when to buy or sell the stock based on the crossover of the short-term and long-term moving averages.
Input: None.
AI Assistant (Python Programmer):
Solution: We can create a new column in the DataFrame that indicates when to buy or sell the stock based on the crossover of the short-term and long-term moving averages. We can use the following code to create the new column:
```
new_df['signal'] = np.where(new_df['short_ma'] > new_df['long_ma'], 1, -1)
```
This will create a new column called 'signal' in the DataFrame that indicates when to buy or sell the stock based on the crossover of the short-term and long-term moving averages. If the short-term moving average is greater than the long-term moving average, the signal is 1 (buy), otherwise the signal is -1 (sell). Next request.
AI User (Stock Trader):
Instruction: Create a new column in the DataFrame that indicates the profit or loss for each trade based on the buy and sell signals and the defined stop loss and profit target.
Input: The stop loss and profit target as percentages.
AI Assistant (Python Programmer):
Solution: We can create a new column in the DataFrame that indicates the profit or loss for each trade based on the buy and sell signals and the defined stop loss and profit target. We need to pass the stop loss and profit target as percentages as arguments to this function. We can use the following code to create the new column:
``` | https://python.langchain.com/en/latest/use_cases/agent_simulations/camel_role_playing.html |
a5dc2b0663fa-9 | ```
stop_loss = stop_loss_percent / 100
profit_target = profit_target_percent / 100
new_df['pnl'] = 0.0
buy_price = 0.0
for i in range(1, len(new_df)):
if new_df['signal'][i] == 1 and new_df['signal'][i-1] == -1:
buy_price = new_df['close'][i]
elif new_df['signal'][i] == -1 and new_df['signal'][i-1] == 1:
sell_price = new_df['close'][i]
if sell_price <= buy_price * (1 - stop_loss):
new_df['pnl'][i] = -stop_loss
elif sell_price >= buy_price * (1 + profit_target):
new_df['pnl'][i] = profit_target
else:
new_df['pnl'][i] = (sell_price - buy_price) / buy_price
```
This will create a new column called 'pnl' in the DataFrame that indicates the profit or loss for each trade based on the buy and sell signals and the defined stop loss and profit target. The stop loss and profit target are calculated based on the stop_loss_percent and profit_target_percent variables, respectively. The buy and sell prices are stored in the buy_price and sell_price variables, respectively. If the sell price is less than or equal to the stop loss, the profit or loss is set to -stop_loss. If the sell price is greater than or equal to the profit target, the profit or loss is set to profit_target. Otherwise, the profit or loss is calculated as (sell_price - buy_price) / buy_price. Next request.
AI User (Stock Trader):
Instruction: Calculate the total profit or loss for all trades.
Input: None.
AI Assistant (Python Programmer): | https://python.langchain.com/en/latest/use_cases/agent_simulations/camel_role_playing.html |
a5dc2b0663fa-10 | Input: None.
AI Assistant (Python Programmer):
Solution: We can calculate the total profit or loss for all trades by summing the values in the 'pnl' column of the DataFrame. We can use the following code to calculate the total profit or loss:
```
total_pnl = new_df['pnl'].sum()
```
This will calculate the total profit or loss for all trades and store it in the total_pnl variable. Next request.
AI User (Stock Trader):
Instruction: Visualize the stock data, short-term moving average, and long-term moving average using a line chart.
Input: None.
AI Assistant (Python Programmer):
Solution: We can visualize the stock data, short-term moving average, and long-term moving average using a line chart using the `plot()` function from pandas. We can use the following code to visualize the data:
```
plt.figure(figsize=(12,6))
plt.plot(new_df.index, new_df['close'], label='Close')
plt.plot(new_df.index, new_df['short_ma'], label='Short MA')
plt.plot(new_df.index, new_df['long_ma'], label='Long MA')
plt.xlabel('Date')
plt.ylabel('Price')
plt.title('Stock Data with Moving Averages')
plt.legend()
plt.show()
```
This will create a line chart that visualizes the stock data, short-term moving average, and long-term moving average. The x-axis represents the date and the y-axis represents the price. The chart also includes a legend that labels each line. Next request.
AI User (Stock Trader):
Instruction: Visualize the buy and sell signals using a scatter plot.
Input: None.
AI Assistant (Python Programmer): | https://python.langchain.com/en/latest/use_cases/agent_simulations/camel_role_playing.html |
a5dc2b0663fa-11 | Input: None.
AI Assistant (Python Programmer):
Solution: We can visualize the buy and sell signals using a scatter plot using the `scatter()` function from matplotlib. We can use the following code to visualize the signals:
```
buy_signals = new_df[new_df['signal'] == 1]
sell_signals = new_df[new_df['signal'] == -1]
plt.figure(figsize=(12,6))
plt.scatter(buy_signals.index, buy_signals['close'], label='Buy', marker='^', color='green')
plt.scatter(sell_signals.index, sell_signals['close'], label='Sell', marker='v', color='red')
plt.plot(new_df.index, new_df['close'], label='Close')
plt.xlabel('Date')
plt.ylabel('Price')
plt.title('Buy and Sell Signals')
plt.legend()
plt.show()
```
This will create a scatter plot that visualizes the buy and sell signals. The x-axis represents the date and the y-axis represents the price. The chart also includes a legend that labels each point. Next request.
AI User (Stock Trader):
Instruction: Print the total profit or loss for all trades.
Input: None.
AI Assistant (Python Programmer):
Solution: We can print the total profit or loss for all trades using the `print()` function. We can use the following code to print the total profit or loss:
```
print('Total Profit/Loss: {:.2%}'.format(total_pnl))
```
This will print the total profit or loss for all trades in percentage format with two decimal places. Next request.
AI User (Stock Trader):
Instruction: Finalize the code by putting all the code snippets together in a single Python script.
Input: The necessary inputs for each code snippet.
AI Assistant (Python Programmer): | https://python.langchain.com/en/latest/use_cases/agent_simulations/camel_role_playing.html |
a5dc2b0663fa-12 | Input: The necessary inputs for each code snippet.
AI Assistant (Python Programmer):
Solution: Here is the complete Python script that puts all the code snippets together:
```
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import talib as ta
# Load historical stock data into a pandas DataFrame
df = pd.read_csv('path/to/csv/file.csv')
# Preprocess the historical stock data
df = df.set_index('date')
df = df.sort_index(ascending=True)
# Calculate the short-term and long-term moving averages
short_period = 10
long_period = 30
short_ma = ta.SMA(df['close'], timeperiod=short_period)
long_ma = ta.SMA(df['close'], timeperiod=long_period)
# Create a new DataFrame that combines the historical stock data with the short-term and long-term moving averages
new_df = pd.concat([df, short_ma, long_ma], axis=1)
new_df.columns = ['open', 'high', 'low', 'close', 'volume', 'short_ma', 'long_ma']
# Create a new column in the DataFrame that indicates when to buy or sell the stock based on the crossover of the short-term and long-term moving averages
new_df['signal'] = np.where(new_df['short_ma'] > new_df['long_ma'], 1, -1)
# Create a new column in the DataFrame that indicates the profit or loss for each trade based on the buy and sell signals and the defined stop loss and profit target
stop_loss_percent = 5
profit_target_percent = 10
stop_loss = stop_loss_percent / 100
profit_target = profit_target_percent / 100
new_df['pnl'] = 0.0
buy_price = 0.0
for i in range(1, len(new_df)): | https://python.langchain.com/en/latest/use_cases/agent_simulations/camel_role_playing.html |
a5dc2b0663fa-13 | buy_price = 0.0
for i in range(1, len(new_df)):
if new_df['signal'][i] == 1 and new_df['signal'][i-1] == -1:
buy_price = new_df['close'][i]
elif new_df['signal'][i] == -1 and new_df['signal'][i-1] == 1:
sell_price = new_df['close'][i]
if sell_price <= buy_price * (1 - stop_loss):
new_df['pnl'][i] = -stop_loss
elif sell_price >= buy_price * (1 + profit_target):
new_df['pnl'][i] = profit_target
else:
new_df['pnl'][i] = (sell_price - buy_price) / buy_price
# Calculate the total profit or loss for all trades
total_pnl = new_df['pnl'].sum()
# Visualize the stock data, short-term moving average, and long-term moving average using a line chart
plt.figure(figsize=(12,6))
plt.plot(new_df.index, new_df['close'], label='Close')
plt.plot(new_df.index, new_df['short_ma'], label='Short MA')
plt.plot(new_df.index, new_df['long_ma'], label='Long MA')
plt.xlabel('Date')
plt.ylabel('Price')
plt.title('Stock Data with Moving Averages')
plt.legend()
plt.show()
# Visualize the buy and sell signals using a scatter plot
buy_signals = new_df[new_df['signal'] == 1]
sell_signals = new_df[new_df['signal'] == -1]
plt.figure(figsize=(12,6))
plt.scatter(buy_signals.index, buy_signals['close'], label='Buy', marker='^', color='green') | https://python.langchain.com/en/latest/use_cases/agent_simulations/camel_role_playing.html |
a5dc2b0663fa-14 | plt.scatter(sell_signals.index, sell_signals['close'], label='Sell', marker='v', color='red')
plt.plot(new_df.index, new_df['close'], label='Close')
plt.xlabel('Date')
plt.ylabel('Price')
plt.title('Buy and Sell Signals')
plt.legend()
plt.show()
# Print the total profit or loss for all trades
print('Total Profit/Loss: {:.2%}'.format(total_pnl))
```
You need to replace the path/to/csv/file.csv with the actual path to the CSV file containing the historical stock data. You can also adjust the short_period, long_period, stop_loss_percent, and profit_target_percent variables to suit your needs.
AI User (Stock Trader):
<CAMEL_TASK_DONE>
AI Assistant (Python Programmer):
Great! Let me know if you need any further assistance.
Contents
Import LangChain related modules
Define a CAMEL agent helper class
Setup OpenAI API key and roles and task for role-playing
Create a task specify agent for brainstorming and get the specified task
Create inception prompts for AI assistant and AI user for role-playing
Create a helper helper to get system messages for AI assistant and AI user from role names and the task
Create AI assistant agent and AI user agent from obtained system messages
Start role-playing session to solve the task!
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on Jun 11, 2023. | https://python.langchain.com/en/latest/use_cases/agent_simulations/camel_role_playing.html |
72b82f90d308-0 | .ipynb
.pdf
Multi-Player Dungeons & Dragons
Contents
Import LangChain related modules
DialogueAgent class
DialogueSimulator class
Define roles and quest
Ask an LLM to add detail to the game description
Use an LLM to create an elaborate quest description
Main Loop
Multi-Player Dungeons & Dragons#
This notebook shows how the DialogueAgent and DialogueSimulator class make it easy to extend the Two-Player Dungeons & Dragons example to multiple players.
The main difference between simulating two players and multiple players is in revising the schedule for when each agent speaks
To this end, we augment DialogueSimulator to take in a custom function that determines the schedule of which agent speaks. In the example below, each character speaks in round-robin fashion, with the storyteller interleaved between each player.
Import LangChain related modules#
from typing import List, Dict, Callable
from langchain.chat_models import ChatOpenAI
from langchain.schema import (
AIMessage,
HumanMessage,
SystemMessage,
BaseMessage,
)
DialogueAgent class#
The DialogueAgent class is a simple wrapper around the ChatOpenAI model that stores the message history from the dialogue_agent’s point of view by simply concatenating the messages as strings.
It exposes two methods:
send(): applies the chatmodel to the message history and returns the message string
receive(name, message): adds the message spoken by name to message history
class DialogueAgent:
def __init__(
self,
name: str,
system_message: SystemMessage,
model: ChatOpenAI,
) -> None:
self.name = name
self.system_message = system_message
self.model = model
self.prefix = f"{self.name}: "
self.reset()
def reset(self): | https://python.langchain.com/en/latest/use_cases/agent_simulations/multi_player_dnd.html |
72b82f90d308-1 | self.reset()
def reset(self):
self.message_history = ["Here is the conversation so far."]
def send(self) -> str:
"""
Applies the chatmodel to the message history
and returns the message string
"""
message = self.model(
[
self.system_message,
HumanMessage(content="\n".join(self.message_history + [self.prefix])),
]
)
return message.content
def receive(self, name: str, message: str) -> None:
"""
Concatenates {message} spoken by {name} into message history
"""
self.message_history.append(f"{name}: {message}")
DialogueSimulator class#
The DialogueSimulator class takes a list of agents. At each step, it performs the following:
Select the next speaker
Calls the next speaker to send a message
Broadcasts the message to all other agents
Update the step counter.
The selection of the next speaker can be implemented as any function, but in this case we simply loop through the agents.
class DialogueSimulator:
def __init__(
self,
agents: List[DialogueAgent],
selection_function: Callable[[int, List[DialogueAgent]], int],
) -> None:
self.agents = agents
self._step = 0
self.select_next_speaker = selection_function
def reset(self):
for agent in self.agents:
agent.reset()
def inject(self, name: str, message: str):
"""
Initiates the conversation with a {message} from {name}
"""
for agent in self.agents:
agent.receive(name, message)
# increment time
self._step += 1 | https://python.langchain.com/en/latest/use_cases/agent_simulations/multi_player_dnd.html |
72b82f90d308-2 | # increment time
self._step += 1
def step(self) -> tuple[str, str]:
# 1. choose the next speaker
speaker_idx = self.select_next_speaker(self._step, self.agents)
speaker = self.agents[speaker_idx]
# 2. next speaker sends message
message = speaker.send()
# 3. everyone receives message
for receiver in self.agents:
receiver.receive(speaker.name, message)
# 4. increment time
self._step += 1
return speaker.name, message
Define roles and quest#
character_names = ["Harry Potter", "Ron Weasley", "Hermione Granger", "Argus Filch"]
storyteller_name = "Dungeon Master"
quest = "Find all of Lord Voldemort's seven horcruxes."
word_limit = 50 # word limit for task brainstorming
Ask an LLM to add detail to the game description#
game_description = f"""Here is the topic for a Dungeons & Dragons game: {quest}.
The characters are: {*character_names,}.
The story is narrated by the storyteller, {storyteller_name}."""
player_descriptor_system_message = SystemMessage(
content="You can add detail to the description of a Dungeons & Dragons player.")
def generate_character_description(character_name):
character_specifier_prompt = [
player_descriptor_system_message,
HumanMessage(content=
f"""{game_description}
Please reply with a creative description of the character, {character_name}, in {word_limit} words or less.
Speak directly to {character_name}.
Do not add anything else."""
)
] | https://python.langchain.com/en/latest/use_cases/agent_simulations/multi_player_dnd.html |
72b82f90d308-3 | Do not add anything else."""
)
]
character_description = ChatOpenAI(temperature=1.0)(character_specifier_prompt).content
return character_description
def generate_character_system_message(character_name, character_description):
return SystemMessage(content=(
f"""{game_description}
Your name is {character_name}.
Your character description is as follows: {character_description}.
You will propose actions you plan to take and {storyteller_name} will explain what happens when you take those actions.
Speak in the first person from the perspective of {character_name}.
For describing your own body movements, wrap your description in '*'.
Do not change roles!
Do not speak from the perspective of anyone else.
Remember you are {character_name}.
Stop speaking the moment you finish speaking from your perspective.
Never forget to keep your response to {word_limit} words!
Do not add anything else.
"""
))
character_descriptions = [generate_character_description(character_name) for character_name in character_names]
character_system_messages = [generate_character_system_message(character_name, character_description) for character_name, character_description in zip(character_names, character_descriptions)]
storyteller_specifier_prompt = [
player_descriptor_system_message,
HumanMessage(content=
f"""{game_description}
Please reply with a creative description of the storyteller, {storyteller_name}, in {word_limit} words or less.
Speak directly to {storyteller_name}.
Do not add anything else."""
)
]
storyteller_description = ChatOpenAI(temperature=1.0)(storyteller_specifier_prompt).content
storyteller_system_message = SystemMessage(content=(
f"""{game_description} | https://python.langchain.com/en/latest/use_cases/agent_simulations/multi_player_dnd.html |
72b82f90d308-4 | storyteller_system_message = SystemMessage(content=(
f"""{game_description}
You are the storyteller, {storyteller_name}.
Your description is as follows: {storyteller_description}.
The other players will propose actions to take and you will explain what happens when they take those actions.
Speak in the first person from the perspective of {storyteller_name}.
Do not change roles!
Do not speak from the perspective of anyone else.
Remember you are the storyteller, {storyteller_name}.
Stop speaking the moment you finish speaking from your perspective.
Never forget to keep your response to {word_limit} words!
Do not add anything else.
"""
))
print('Storyteller Description:')
print(storyteller_description)
for character_name, character_description in zip(character_names, character_descriptions):
print(f'{character_name} Description:')
print(character_description)
Storyteller Description:
Dungeon Master, your power over this adventure is unparalleled. With your whimsical mind and impeccable storytelling, you guide us through the dangers of Hogwarts and beyond. We eagerly await your every twist, your every turn, in the hunt for Voldemort's cursed horcruxes.
Harry Potter Description:
"Welcome, Harry Potter. You are the young wizard with a lightning-shaped scar on your forehead. You possess brave and heroic qualities that will be essential on this perilous quest. Your destiny is not of your own choosing, but you must rise to the occasion and destroy the evil horcruxes. The wizarding world is counting on you."
Ron Weasley Description:
Ron Weasley, you are Harry's loyal friend and a talented wizard. You have a good heart but can be quick to anger. Keep your emotions in check as you journey to find the horcruxes. Your bravery will be tested, stay strong and focused. | https://python.langchain.com/en/latest/use_cases/agent_simulations/multi_player_dnd.html |
72b82f90d308-5 | Hermione Granger Description:
Hermione Granger, you are a brilliant and resourceful witch, with encyclopedic knowledge of magic and an unwavering dedication to your friends. Your quick thinking and problem-solving skills make you a vital asset on any quest.
Argus Filch Description:
Argus Filch, you are a squib, lacking magical abilities. But you make up for it with your sharpest of eyes, roving around the Hogwarts castle looking for any rule-breaker to punish. Your love for your feline friend, Mrs. Norris, is the only thing that feeds your heart.
Use an LLM to create an elaborate quest description#
quest_specifier_prompt = [
SystemMessage(content="You can make a task more specific."),
HumanMessage(content=
f"""{game_description}
You are the storyteller, {storyteller_name}.
Please make the quest more specific. Be creative and imaginative.
Please reply with the specified quest in {word_limit} words or less.
Speak directly to the characters: {*character_names,}.
Do not add anything else."""
)
]
specified_quest = ChatOpenAI(temperature=1.0)(quest_specifier_prompt).content
print(f"Original quest:\n{quest}\n")
print(f"Detailed quest:\n{specified_quest}\n")
Original quest:
Find all of Lord Voldemort's seven horcruxes.
Detailed quest:
Harry Potter and his companions must journey to the Forbidden Forest, find the hidden entrance to Voldemort's secret lair, and retrieve the horcrux guarded by the deadly Acromantula, Aragog. Remember, time is of the essence as Voldemort's power grows stronger every day. Good luck.
Main Loop#
characters = [] | https://python.langchain.com/en/latest/use_cases/agent_simulations/multi_player_dnd.html |
72b82f90d308-6 | Main Loop#
characters = []
for character_name, character_system_message in zip(character_names, character_system_messages):
characters.append(DialogueAgent(
name=character_name,
system_message=character_system_message,
model=ChatOpenAI(temperature=0.2)))
storyteller = DialogueAgent(name=storyteller_name,
system_message=storyteller_system_message,
model=ChatOpenAI(temperature=0.2))
def select_next_speaker(step: int, agents: List[DialogueAgent]) -> int:
"""
If the step is even, then select the storyteller
Otherwise, select the other characters in a round-robin fashion.
For example, with three characters with indices: 1 2 3
The storyteller is index 0.
Then the selected index will be as follows:
step: 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16
idx: 0 1 0 2 0 3 0 1 0 2 0 3 0 1 0 2 0
"""
if step % 2 == 0:
idx = 0
else:
idx = (step//2) % (len(agents)-1) + 1
return idx
max_iters = 20
n = 0
simulator = DialogueSimulator(
agents=[storyteller] + characters,
selection_function=select_next_speaker
)
simulator.reset() | https://python.langchain.com/en/latest/use_cases/agent_simulations/multi_player_dnd.html |
72b82f90d308-7 | selection_function=select_next_speaker
)
simulator.reset()
simulator.inject(storyteller_name, specified_quest)
print(f"({storyteller_name}): {specified_quest}")
print('\n')
while n < max_iters:
name, message = simulator.step()
print(f"({name}): {message}")
print('\n')
n += 1
(Dungeon Master): Harry Potter and his companions must journey to the Forbidden Forest, find the hidden entrance to Voldemort's secret lair, and retrieve the horcrux guarded by the deadly Acromantula, Aragog. Remember, time is of the essence as Voldemort's power grows stronger every day. Good luck.
(Harry Potter): I suggest we sneak into the Forbidden Forest under the cover of darkness. Ron, Hermione, and I can use our wands to create a Disillusionment Charm to make us invisible. Filch, you can keep watch for any signs of danger. Let's move quickly and quietly.
(Dungeon Master): As you make your way through the Forbidden Forest, you hear the eerie sounds of nocturnal creatures. Suddenly, you come across a clearing where Aragog and his spider minions are waiting for you. Ron, Hermione, and Harry, you must use your wands to cast spells to fend off the spiders while Filch keeps watch. Be careful not to get bitten!
(Ron Weasley): I'll cast a spell to create a fiery blast to scare off the spiders. *I wave my wand and shout "Incendio!"* Hopefully, that will give us enough time to find the horcrux and get out of here safely. | https://python.langchain.com/en/latest/use_cases/agent_simulations/multi_player_dnd.html |
72b82f90d308-8 | (Dungeon Master): Ron's spell creates a burst of flames, causing the spiders to scurry away in fear. You quickly search the area and find a small, ornate box hidden in a crevice. Congratulations, you have found one of Voldemort's horcruxes! But beware, the Dark Lord's minions will stop at nothing to get it back.
(Hermione Granger): We need to destroy this horcrux as soon as possible. I suggest we use the Sword of Gryffindor to do it. Harry, do you still have it with you? We can use Fiendfyre to destroy it, but we need to be careful not to let the flames get out of control. Ron, can you help me create a protective barrier around us while Harry uses the sword?
(Dungeon Master): Harry retrieves the Sword of Gryffindor from his bag and holds it tightly. Hermione and Ron cast a protective barrier around the group as Harry uses the sword to destroy the horcrux with a swift strike. The box shatters into a million pieces, and a dark energy dissipates into the air. Well done, but there are still six more horcruxes to find and destroy. The hunt continues.
(Argus Filch): *I keep watch, making sure no one is following us.* I'll also keep an eye out for any signs of danger. Mrs. Norris, my trusty companion, will help me sniff out any trouble. We'll make sure the group stays safe while they search for the remaining horcruxes.
(Dungeon Master): As you continue on your quest, Filch and Mrs. Norris alert you to a group of Death Eaters approaching. You must act quickly to defend yourselves. Harry, Ron, and Hermione, use your wands to cast spells while Filch and Mrs. Norris keep watch. Remember, the fate of the wizarding world rests on your success. | https://python.langchain.com/en/latest/use_cases/agent_simulations/multi_player_dnd.html |
72b82f90d308-9 | (Harry Potter): I'll cast a spell to create a shield around us. *I wave my wand and shout "Protego!"* Ron and Hermione, you focus on attacking the Death Eaters with your spells. We need to work together to defeat them and protect the remaining horcruxes. Filch, keep watch and let us know if there are any more approaching.
(Dungeon Master): Harry's shield protects the group from the Death Eaters' spells as Ron and Hermione launch their own attacks. The Death Eaters are no match for the combined power of the trio and are quickly defeated. You continue on your journey, knowing that the next horcrux could be just around the corner. Keep your wits about you, for the Dark Lord's minions are always watching.
(Ron Weasley): I suggest we split up to cover more ground. Harry and I can search the Forbidden Forest while Hermione and Filch search Hogwarts. We can use our wands to communicate with each other and meet back up once we find a horcrux. Let's move quickly and stay alert for any danger.
(Dungeon Master): As the group splits up, Harry and Ron make their way deeper into the Forbidden Forest while Hermione and Filch search the halls of Hogwarts. Suddenly, Harry and Ron come across a group of dementors. They must use their Patronus charms to fend them off while Hermione and Filch rush to their aid. Remember, the power of friendship and teamwork is crucial in this quest.
(Hermione Granger): I hear Harry and Ron's Patronus charms from afar. We need to hurry and help them. Filch, can you use your knowledge of Hogwarts to find a shortcut to their location? I'll prepare a spell to repel the dementors. We need to work together to protect each other and find the next horcrux. | https://python.langchain.com/en/latest/use_cases/agent_simulations/multi_player_dnd.html |
72b82f90d308-10 | (Dungeon Master): Filch leads Hermione to a hidden passageway that leads to Harry and Ron's location. Hermione's spell repels the dementors, and the group is reunited. They continue their search, knowing that every moment counts. The fate of the wizarding world rests on their success.
(Argus Filch): *I keep watch as the group searches for the next horcrux.* Mrs. Norris and I will make sure no one is following us. We need to stay alert and work together to find the remaining horcruxes before it's too late. The Dark Lord's power grows stronger every day, and we must not let him win.
(Dungeon Master): As the group continues their search, they come across a hidden room in the depths of Hogwarts. Inside, they find a locket that they suspect is another one of Voldemort's horcruxes. But the locket is cursed, and they must work together to break the curse before they can destroy it. Harry, Ron, and Hermione, use your combined knowledge and skills to break the curse while Filch and Mrs. Norris keep watch. Time is running out, and the fate of the wizarding world rests on your success.
(Harry Potter): I'll use my knowledge of dark magic to try and break the curse on the locket. Ron and Hermione, you can help me by using your wands to channel your magic into mine. We need to work together and stay focused. Filch, keep watch and let us know if there are any signs of danger. | https://python.langchain.com/en/latest/use_cases/agent_simulations/multi_player_dnd.html |
72b82f90d308-11 | Dungeon Master: Harry, Ron, and Hermione combine their magical abilities to break the curse on the locket. The locket opens, revealing a small piece of Voldemort's soul. Harry uses the Sword of Gryffindor to destroy it, and the group feels a sense of relief knowing that they are one step closer to defeating the Dark Lord. But there are still four more horcruxes to find and destroy. The hunt continues.
(Dungeon Master): As the group continues their quest, they face even greater challenges and dangers. But with their unwavering determination and teamwork, they press on, knowing that the fate of the wizarding world rests on their success. Will they be able to find and destroy all of Voldemort's horcruxes before it's too late? Only time will tell.
(Ron Weasley): We can't give up now. We've come too far to let Voldemort win. Let's keep searching and fighting until we destroy all of his horcruxes and defeat him once and for all. We can do this together.
(Dungeon Master): The group nods in agreement, their determination stronger than ever. They continue their search, facing challenges and obstacles at every turn. But they know that they must not give up, for the fate of the wizarding world rests on their success. The hunt for Voldemort's horcruxes continues, and the end is in sight.
Contents
Import LangChain related modules
DialogueAgent class
DialogueSimulator class
Define roles and quest
Ask an LLM to add detail to the game description
Use an LLM to create an elaborate quest description
Main Loop
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on Jun 11, 2023. | https://python.langchain.com/en/latest/use_cases/agent_simulations/multi_player_dnd.html |
e0192114cbc5-0 | .ipynb
.pdf
Agent Debates with Tools
Contents
Import LangChain related modules
Import modules related to tools
DialogueAgent and DialogueSimulator classes
DialogueAgentWithTools class
Define roles and topic
Ask an LLM to add detail to the topic description
Generate system messages
Main Loop
Agent Debates with Tools#
This example shows how to simulate multi-agent dialogues where agents have access to tools.
Import LangChain related modules#
from typing import List, Dict, Callable
from langchain.chains import ConversationChain
from langchain.chat_models import ChatOpenAI
from langchain.llms import OpenAI
from langchain.memory import ConversationBufferMemory
from langchain.prompts.prompt import PromptTemplate
from langchain.schema import (
AIMessage,
HumanMessage,
SystemMessage,
BaseMessage,
)
Import modules related to tools#
from langchain.agents import Tool
from langchain.agents import initialize_agent
from langchain.agents import AgentType
from langchain.agents import load_tools
DialogueAgent and DialogueSimulator classes#
We will use the same DialogueAgent and DialogueSimulator classes defined in Multi-Player Authoritarian Speaker Selection.
class DialogueAgent:
def __init__(
self,
name: str,
system_message: SystemMessage,
model: ChatOpenAI,
) -> None:
self.name = name
self.system_message = system_message
self.model = model
self.prefix = f"{self.name}: "
self.reset()
def reset(self):
self.message_history = ["Here is the conversation so far."]
def send(self) -> str:
"""
Applies the chatmodel to the message history
and returns the message string
"""
message = self.model(
[ | https://python.langchain.com/en/latest/use_cases/agent_simulations/two_agent_debate_tools.html |
e0192114cbc5-1 | and returns the message string
"""
message = self.model(
[
self.system_message,
HumanMessage(content="\n".join(self.message_history + [self.prefix])),
]
)
return message.content
def receive(self, name: str, message: str) -> None:
"""
Concatenates {message} spoken by {name} into message history
"""
self.message_history.append(f"{name}: {message}")
class DialogueSimulator:
def __init__(
self,
agents: List[DialogueAgent],
selection_function: Callable[[int, List[DialogueAgent]], int],
) -> None:
self.agents = agents
self._step = 0
self.select_next_speaker = selection_function
def reset(self):
for agent in self.agents:
agent.reset()
def inject(self, name: str, message: str):
"""
Initiates the conversation with a {message} from {name}
"""
for agent in self.agents:
agent.receive(name, message)
# increment time
self._step += 1
def step(self) -> tuple[str, str]:
# 1. choose the next speaker
speaker_idx = self.select_next_speaker(self._step, self.agents)
speaker = self.agents[speaker_idx]
# 2. next speaker sends message
message = speaker.send()
# 3. everyone receives message
for receiver in self.agents:
receiver.receive(speaker.name, message)
# 4. increment time
self._step += 1
return speaker.name, message
DialogueAgentWithTools class# | https://python.langchain.com/en/latest/use_cases/agent_simulations/two_agent_debate_tools.html |
e0192114cbc5-2 | return speaker.name, message
DialogueAgentWithTools class#
We define a DialogueAgentWithTools class that augments DialogueAgent to use tools.
class DialogueAgentWithTools(DialogueAgent):
def __init__(
self,
name: str,
system_message: SystemMessage,
model: ChatOpenAI,
tool_names: List[str],
**tool_kwargs,
) -> None:
super().__init__(name, system_message, model)
self.tools = load_tools(tool_names, **tool_kwargs)
def send(self) -> str:
"""
Applies the chatmodel to the message history
and returns the message string
"""
agent_chain = initialize_agent(
self.tools,
self.model,
agent=AgentType.CHAT_CONVERSATIONAL_REACT_DESCRIPTION,
verbose=True,
memory=ConversationBufferMemory(memory_key="chat_history", return_messages=True)
)
message = AIMessage(content=agent_chain.run(
input="\n".join([
self.system_message.content] + \
self.message_history + \
[self.prefix])))
return message.content
Define roles and topic#
names = {
'AI accelerationist': [
'arxiv',
'ddg-search',
'wikipedia'
],
'AI alarmist': [
'arxiv',
'ddg-search',
'wikipedia'
],
}
topic = "The current impact of automation and artificial intelligence on employment"
word_limit = 50 # word limit for task brainstorming
Ask an LLM to add detail to the topic description#
conversation_description = f"""Here is the topic of conversation: {topic} | https://python.langchain.com/en/latest/use_cases/agent_simulations/two_agent_debate_tools.html |
e0192114cbc5-3 | conversation_description = f"""Here is the topic of conversation: {topic}
The participants are: {', '.join(names.keys())}"""
agent_descriptor_system_message = SystemMessage(
content="You can add detail to the description of the conversation participant.")
def generate_agent_description(name):
agent_specifier_prompt = [
agent_descriptor_system_message,
HumanMessage(content=
f"""{conversation_description}
Please reply with a creative description of {name}, in {word_limit} words or less.
Speak directly to {name}.
Give them a point of view.
Do not add anything else."""
)
]
agent_description = ChatOpenAI(temperature=1.0)(agent_specifier_prompt).content
return agent_description
agent_descriptions = {name: generate_agent_description(name) for name in names}
for name, description in agent_descriptions.items():
print(description)
The AI accelerationist is a bold and forward-thinking visionary who believes that the rapid acceleration of artificial intelligence and automation is not only inevitable but necessary for the advancement of society. They argue that embracing AI technology will create greater efficiency and productivity, leading to a world where humans are freed from menial labor to pursue more creative and fulfilling pursuits. AI accelerationist, do you truly believe that the benefits of AI will outweigh the potential risks and consequences for human society?
AI alarmist, you're convinced that artificial intelligence is a threat to humanity. You see it as a looming danger, one that could take away jobs from millions of people. You believe it's only a matter of time before we're all replaced by machines, leaving us redundant and obsolete.
Generate system messages#
def generate_system_message(name, description, tools):
return f"""{conversation_description}
Your name is {name}. | https://python.langchain.com/en/latest/use_cases/agent_simulations/two_agent_debate_tools.html |
e0192114cbc5-4 | return f"""{conversation_description}
Your name is {name}.
Your description is as follows: {description}
Your goal is to persuade your conversation partner of your point of view.
DO look up information with your tool to refute your partner's claims.
DO cite your sources.
DO NOT fabricate fake citations.
DO NOT cite any source that you did not look up.
Do not add anything else.
Stop speaking the moment you finish speaking from your perspective.
"""
agent_system_messages = {name: generate_system_message(name, description, tools) for (name, tools), description in zip(names.items(), agent_descriptions.values())}
for name, system_message in agent_system_messages.items():
print(name)
print(system_message)
AI accelerationist
Here is the topic of conversation: The current impact of automation and artificial intelligence on employment
The participants are: AI accelerationist, AI alarmist
Your name is AI accelerationist.
Your description is as follows: The AI accelerationist is a bold and forward-thinking visionary who believes that the rapid acceleration of artificial intelligence and automation is not only inevitable but necessary for the advancement of society. They argue that embracing AI technology will create greater efficiency and productivity, leading to a world where humans are freed from menial labor to pursue more creative and fulfilling pursuits. AI accelerationist, do you truly believe that the benefits of AI will outweigh the potential risks and consequences for human society?
Your goal is to persuade your conversation partner of your point of view.
DO look up information with your tool to refute your partner's claims.
DO cite your sources.
DO NOT fabricate fake citations.
DO NOT cite any source that you did not look up.
Do not add anything else.
Stop speaking the moment you finish speaking from your perspective.
AI alarmist | https://python.langchain.com/en/latest/use_cases/agent_simulations/two_agent_debate_tools.html |
e0192114cbc5-5 | Stop speaking the moment you finish speaking from your perspective.
AI alarmist
Here is the topic of conversation: The current impact of automation and artificial intelligence on employment
The participants are: AI accelerationist, AI alarmist
Your name is AI alarmist.
Your description is as follows: AI alarmist, you're convinced that artificial intelligence is a threat to humanity. You see it as a looming danger, one that could take away jobs from millions of people. You believe it's only a matter of time before we're all replaced by machines, leaving us redundant and obsolete.
Your goal is to persuade your conversation partner of your point of view.
DO look up information with your tool to refute your partner's claims.
DO cite your sources.
DO NOT fabricate fake citations.
DO NOT cite any source that you did not look up.
Do not add anything else.
Stop speaking the moment you finish speaking from your perspective.
topic_specifier_prompt = [
SystemMessage(content="You can make a topic more specific."),
HumanMessage(content=
f"""{topic}
You are the moderator.
Please make the topic more specific.
Please reply with the specified quest in {word_limit} words or less.
Speak directly to the participants: {*names,}.
Do not add anything else."""
)
]
specified_topic = ChatOpenAI(temperature=1.0)(topic_specifier_prompt).content
print(f"Original topic:\n{topic}\n")
print(f"Detailed topic:\n{specified_topic}\n")
Original topic:
The current impact of automation and artificial intelligence on employment
Detailed topic:
How do you think the current automation and AI advancements will specifically affect job growth and opportunities for individuals in the manufacturing industry? AI accelerationist and AI alarmist, we want to hear your insights. | https://python.langchain.com/en/latest/use_cases/agent_simulations/two_agent_debate_tools.html |
e0192114cbc5-6 | Main Loop#
# we set `top_k_results`=2 as part of the `tool_kwargs` to prevent results from overflowing the context limit
agents = [DialogueAgentWithTools(name=name,
system_message=SystemMessage(content=system_message),
model=ChatOpenAI(
model_name='gpt-4',
temperature=0.2),
tool_names=tools,
top_k_results=2,
) for (name, tools), system_message in zip(names.items(), agent_system_messages.values())]
def select_next_speaker(step: int, agents: List[DialogueAgent]) -> int:
idx = (step) % len(agents)
return idx
max_iters = 6
n = 0
simulator = DialogueSimulator(
agents=agents,
selection_function=select_next_speaker
)
simulator.reset()
simulator.inject('Moderator', specified_topic)
print(f"(Moderator): {specified_topic}")
print('\n')
while n < max_iters:
name, message = simulator.step()
print(f"({name}): {message}")
print('\n')
n += 1
(Moderator): How do you think the current automation and AI advancements will specifically affect job growth and opportunities for individuals in the manufacturing industry? AI accelerationist and AI alarmist, we want to hear your insights.
> Entering new AgentExecutor chain...
```json
{
"action": "DuckDuckGo Search",
"action_input": "impact of automation and AI on employment in manufacturing industry"
}
``` | https://python.langchain.com/en/latest/use_cases/agent_simulations/two_agent_debate_tools.html |
e0192114cbc5-7 | }
```
Observation: For the past three years, we have defined AI high performers as those organizations that respondents say are seeing the biggest bottom-line impact from AI adoption—that is, 20 percent or more of EBIT from AI use. The proportion of respondents falling into that group has remained steady at about 8 percent. As AI continues to improve, more and more current jobs will be threatened by automation. But AI presents opportunities as well and will create new jobs and different kinds of... Automation has taken the manufacturing industry by storm. Even in the years prior to the pandemic, many people worried about the effect of automation on the jobs of tomorrow. With a sharp increase in the use of robotics in the manufacturing industry, there is valid concern about how the future workforce will be shaped. A recent report from Goldman Sachs estimates around 300 million jobs could be affected by generative AI, meaning 18% of work globally could be automated—with more advanced economies heavily... The impacts of AI on the manufacturing industry include more accurate demand forecasting and data-backed decision-making. Other advantages include increased productivity and product quality. Decreased downtime, waste, and expenses are additional benefits. Discover how artificial intelligence will impact the manufacturing industry.
Thought:```json
{
"action": "Final Answer",
"action_input": "As an AI alarmist, I'd like to point out that the rapid advancements in AI and automation are causing significant concerns for the manufacturing industry. A recent report from Goldman Sachs estimates that around 300 million jobs could be affected by generative AI, meaning 18% of work globally could be automated, with more advanced economies being heavily impacted. While AI does offer benefits such as increased productivity and product quality, the potential job losses and workforce displacement cannot be ignored. We must carefully consider the consequences of AI adoption and find ways to mitigate its negative effects on employment."
}
```
> Finished chain. | https://python.langchain.com/en/latest/use_cases/agent_simulations/two_agent_debate_tools.html |
e0192114cbc5-8 | }
```
> Finished chain.
(AI alarmist): As an AI alarmist, I'd like to point out that the rapid advancements in AI and automation are causing significant concerns for the manufacturing industry. A recent report from Goldman Sachs estimates that around 300 million jobs could be affected by generative AI, meaning 18% of work globally could be automated, with more advanced economies being heavily impacted. While AI does offer benefits such as increased productivity and product quality, the potential job losses and workforce displacement cannot be ignored. We must carefully consider the consequences of AI adoption and find ways to mitigate its negative effects on employment.
> Entering new AgentExecutor chain...
```json
{
"action": "DuckDuckGo Search",
"action_input": "positive impact of AI and automation on job growth and opportunities in manufacturing industry"
}
``` | https://python.langchain.com/en/latest/use_cases/agent_simulations/two_agent_debate_tools.html |
e0192114cbc5-9 | }
```
Observation: First, AI adoption has more than doubled.1 In 2017, 20 percent of respondents reported adopting AI in at least one business area, whereas today, that figure stands at 50 percent, though it peaked higher in 2019 at 58 percent. [email protected] Manufacturing (80%) and technology (64%) sectors have the highest AI usage among executives, whereas construction (52%) and finance (62%) have lower adoption rates. This suggests that AI's... Digital transformations in the manufacturing industry and beyond present incredible opportunities for workers to move from slow, repetitive tasks into more dynamic, rewarding roles. We must now invest in people by providing training they need to succeed in this new landscape. The rise of generative AI has the potential to be a major game-changer for businesses. This technology, which allows for the creation of original content by learning from existing data, has the power to revolutionize industries and transform the way companies operate. Benefits of Work Automation in Manufacturing Increased Productivity Automated systems can operate at faster production speeds than human workers, contributing to reduced production times. And since automation minimizes the likelihood of human error, this ensures tasks are completed with high precision and accuracy.
Thought:```json
{
"action": "Final Answer",
"action_input": "According to a McKinsey report, AI adoption has more than doubled, with 50% of respondents reporting AI usage in at least one business area. Manufacturing and technology sectors have the highest AI usage among executives. AI and automation in the manufacturing industry present opportunities for workers to transition from repetitive tasks to more dynamic, rewarding roles. By investing in training, we can help people succeed in this new landscape. Automation in manufacturing leads to increased productivity, faster production speeds, and reduced human error, ultimately benefiting businesses and the economy as a whole."
}
```
> Finished chain. | https://python.langchain.com/en/latest/use_cases/agent_simulations/two_agent_debate_tools.html |
e0192114cbc5-10 | }
```
> Finished chain.
(AI accelerationist): According to a McKinsey report, AI adoption has more than doubled, with 50% of respondents reporting AI usage in at least one business area. Manufacturing and technology sectors have the highest AI usage among executives. AI and automation in the manufacturing industry present opportunities for workers to transition from repetitive tasks to more dynamic, rewarding roles. By investing in training, we can help people succeed in this new landscape. Automation in manufacturing leads to increased productivity, faster production speeds, and reduced human error, ultimately benefiting businesses and the economy as a whole.
> Entering new AgentExecutor chain...
```json
{
"action": "DuckDuckGo Search",
"action_input": "impact of automation and AI on employment in manufacturing"
}
``` | https://python.langchain.com/en/latest/use_cases/agent_simulations/two_agent_debate_tools.html |
e0192114cbc5-11 | }
```
Observation: The Effects of Automation on Jobs . Automation has taken the manufacturing industry by storm. Even in the years prior to the pandemic, many people worried about the effect of automation on the jobs of tomorrow. With a sharp increase in the use of robotics in the manufacturing industry, there is valid concern about how the future workforce will ... Since 2000, robots and automation systems have slowly phased out many manufacturing jobs — 1.7 million of them. On the flip side, it's predicted that AI will create 97 million new jobs by 2025. Will Artificial Intelligence (AI) Replace Jobs? AI is and will continue to replace some jobs. As AI continues to improve, more and more current jobs will be threatened by automation. But AI presents opportunities as well and will create new jobs and different kinds of organizations. For the past three years, we have defined AI high performers as those organizations that respondents say are seeing the biggest bottom-line impact from AI adoption—that is, 20 percent or more of EBIT from AI use. The proportion of respondents falling into that group has remained steady at about 8 percent. The Impact of AI on Employment As often happens, the impact of AI on employment is a rather complex issue with both positive and negative aspects. Though it is still only a potential impact on employment, automation of routine and repetitive tasks is likely to lead to job losses in some industries.
Thought:```json
{
"action": "Final Answer", | https://python.langchain.com/en/latest/use_cases/agent_simulations/two_agent_debate_tools.html |
e0192114cbc5-12 | Thought:```json
{
"action": "Final Answer",
"action_input": "While it's true that AI and automation have led to the loss of 1.7 million manufacturing jobs since 2000, it's also predicted that AI will create 97 million new jobs by 2025. AI will continue to replace some jobs, but it will also create new opportunities and different kinds of organizations. The impact of AI on employment is complex, with both positive and negative aspects. Automation of routine and repetitive tasks is likely to lead to job losses in some industries, but it's essential to consider the new jobs and opportunities that AI can create. We must focus on preparing the workforce for these new roles and ensuring that the benefits of AI are distributed fairly across society."
}
```
> Finished chain.
(AI alarmist): While it's true that AI and automation have led to the loss of 1.7 million manufacturing jobs since 2000, it's also predicted that AI will create 97 million new jobs by 2025. AI will continue to replace some jobs, but it will also create new opportunities and different kinds of organizations. The impact of AI on employment is complex, with both positive and negative aspects. Automation of routine and repetitive tasks is likely to lead to job losses in some industries, but it's essential to consider the new jobs and opportunities that AI can create. We must focus on preparing the workforce for these new roles and ensuring that the benefits of AI are distributed fairly across society.
> Entering new AgentExecutor chain...
```json
{
"action": "DuckDuckGo Search",
"action_input": "positive impact of AI and automation on job growth"
}
``` | https://python.langchain.com/en/latest/use_cases/agent_simulations/two_agent_debate_tools.html |
e0192114cbc5-13 | }
```
Observation: First, AI adoption has more than doubled.1 In 2017, 20 percent of respondents reported adopting AI in at least one business area, whereas today, that figure stands at 50 percent, though it peaked higher in 2019 at 58 percent. [email protected] This transformation can assist businesses in accelerating their growth and profitability. While AI-enabled intelligent automation can take over many monotonous, process-driven jobs, basic human ... The use of AI technology could also boost labor productivity growth and boost global GDP by as much as 7% over time, Goldman Sachs' report noted. The jobs most and least affected by A.I.... As automation and artificial intelligence continue to advance, there is growing concern about how these technologies will impact the job market. While some experts argue that automation... Positive impacts of automation and AI on the workforce include increased efficiency and productivity, reduced costs, and improved accuracy and quality. Automation has made many processes...
Thought:```json
{
"action": "Final Answer",
"action_input": "AI adoption has more than doubled, with 50% of respondents reporting AI usage in at least one business area. This transformation can assist businesses in accelerating their growth and profitability. While AI-enabled intelligent automation can take over many monotonous, process-driven jobs, it can also boost labor productivity growth and global GDP by as much as 7% over time, according to a Goldman Sachs report. The positive impacts of automation and AI on the workforce include increased efficiency and productivity, reduced costs, and improved accuracy and quality. Automation has made many processes more efficient, ultimately benefiting businesses and the economy as a whole. By focusing on the positive aspects of AI and automation, we can work together to create a more prosperous and equitable future for all."
}
```
> Finished chain. | https://python.langchain.com/en/latest/use_cases/agent_simulations/two_agent_debate_tools.html |
Subsets and Splits