id stringlengths 14 16 | text stringlengths 36 2.73k | source stringlengths 49 117 |
|---|---|---|
a1f971978599-15 | "action_input": "negative impact of AI and automation on employment"
}
```
Observation: Some workforce experts say AI and other new technologies will hurt middle-level, white-collar jobs more than lower-paying, physically intensive jobs. McKinsey's Madgavkar said it will be hard... Some uses of AI are unlikely to impac... | https://python.langchain.com/en/latest/use_cases/agent_simulations/two_agent_debate_tools.html |
a1f971978599-16 | Thought:```json
{
"action": "Final Answer",
"action_input": "Recent research indicates that AI and automation could lead to the loss of 85 million jobs between 2020 and 2025, with middle-level, white-collar jobs being hit the hardest. Black and Latino employees are particularly vulnerable to these changes. Furt... | https://python.langchain.com/en/latest/use_cases/agent_simulations/two_agent_debate_tools.html |
a1f971978599-17 | Technological change typically includes the introduction of labour-saving "mechanical-muscle" machines or more efficient "mechanical-mind" processes (automation), and humans' role in these processes are minimized. Just as horses were gradually made obsolete as transport by the automobile and as labourer by the tractor,... | https://python.langchain.com/en/latest/use_cases/agent_simulations/two_agent_debate_tools.html |
a1f971978599-18 | Prior to the 18th century, both the elite and common people would generally take the pessimistic view on technological unemployment, at least in cases where the issue arose. Due to generally low unemployment in much of pre-modern history, the topic was rarely a prominent concern. In the 18th century fears over the impa... | https://python.langchain.com/en/latest/use_cases/agent_simulations/two_agent_debate_tools.html |
a1f971978599-19 | In the second decade of the 21st century, a number of studies have been released suggesting that technological unemployment may increase worldwide. Oxford Professors Carl Benedikt Frey and Michael Osborne, for example, have estimated that 47 percent of U.S. jobs are at risk of automation. However, their findings have f... | https://python.langchain.com/en/latest/use_cases/agent_simulations/two_agent_debate_tools.html |
a1f971978599-20 | AI applications include advanced web search engines (e.g., Google Search), recommendation systems (used by YouTube, Amazon, and Netflix), understanding human speech (such as Siri and Alexa), self-driving cars (e.g., Waymo), generative or creative tools (ChatGPT and AI art), automated decision-making, and competing at t... | https://python.langchain.com/en/latest/use_cases/agent_simulations/two_agent_debate_tools.html |
a1f971978599-21 | The field was founded on the assumption that human intelligence "can be so precisely described that a machine can be made to simulate it". This raised philosophical arguments about the mind and the ethical consequences of creating artificial beings endowed with human-like intelligence; these issues have previously been... | https://python.langchain.com/en/latest/use_cases/agent_simulations/two_agent_debate_tools.html |
a1f971978599-22 | }
```
> Finished chain.
(AI accelerationist): AI alarmist, I understand your concerns about job losses and workforce displacement. However, it's important to note that technological unemployment has been a topic of debate for centuries, with both optimistic and pessimistic views. While AI and automation may displace so... | https://python.langchain.com/en/latest/use_cases/agent_simulations/two_agent_debate_tools.html |
c88142b7bea4-0 | .ipynb
.pdf
Two-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
Protagonist and dungeon master system messages
Use an LLM to create an elaborate quest description
Main Loop
Two-Playe... | https://python.langchain.com/en/latest/use_cases/agent_simulations/two_player_dnd.html |
c88142b7bea4-1 | 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... | https://python.langchain.com/en/latest/use_cases/agent_simulations/two_player_dnd.html |
c88142b7bea4-2 | 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, mes... | https://python.langchain.com/en/latest/use_cases/agent_simulations/two_player_dnd.html |
c88142b7bea4-3 | Speak directly to {storyteller_name}.
Do not add anything else."""
)
]
storyteller_description = ChatOpenAI(temperature=1.0)(storyteller_specifier_prompt).content
print('Protagonist Description:')
print(protagonist_description)
print('Storyteller Description:')
print(storyteller_description)
Protagonist... | https://python.langchain.com/en/latest/use_cases/agent_simulations/two_player_dnd.html |
c88142b7bea4-4 | Do not add anything else.
Remember you are the protagonist, {protagonist_name}.
Stop speaking the moment you finish speaking from your perspective.
"""
))
storyteller_system_message = SystemMessage(content=(
f"""{game_description}
Never forget you are the storyteller, {storyteller_name}, and I am the protagonist, {prot... | https://python.langchain.com/en/latest/use_cases/agent_simulations/two_player_dnd.html |
c88142b7bea4-5 | print(f"Detailed quest:\n{specified_quest}\n")
Original quest:
Find all of Lord Voldemort's seven horcruxes.
Detailed quest:
Harry, you must venture to the depths of the Forbidden Forest where you will find a hidden labyrinth. Within it, lies one of Voldemort's horcruxes, the locket. But beware, the labyrinth is heavil... | https://python.langchain.com/en/latest/use_cases/agent_simulations/two_player_dnd.html |
c88142b7bea4-6 | print('\n')
n += 1
(Dungeon Master): Harry, you must venture to the depths of the Forbidden Forest where you will find a hidden labyrinth. Within it, lies one of Voldemort's horcruxes, the locket. But beware, the labyrinth is heavily guarded by dark creatures and spells, and time is running out. Can you find the lo... | https://python.langchain.com/en/latest/use_cases/agent_simulations/two_player_dnd.html |
c88142b7bea4-7 | (Dungeon Master): As you continue through the forest, you come across a clearing where you see a group of Death Eaters gathered around a cauldron. They seem to be performing some sort of dark ritual. You recognize one of them as Bellatrix Lestrange. What do you do, Harry?
(Harry Potter): I hide behind a nearby tree and... | https://python.langchain.com/en/latest/use_cases/agent_simulations/two_player_dnd.html |
c2669561e422-0 | .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 en... | https://python.langchain.com/en/latest/use_cases/agent_simulations/gymnasium.html |
c2669561e422-1 | 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
... | https://python.langchain.com/en/latest/use_cases/agent_simulations/gymnasium.html |
c2669561e422-2 | 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, rew... | https://python.langchain.com/en/latest/use_cases/agent_simulations/gymnasium.html |
58c25cc4f5d3-0 | .ipynb
.pdf
Multi-Agent Simulated Environment: Petting Zoo
Contents
Install pettingzoo and other dependencies
Import modules
GymnasiumAgent
Main loop
PettingZooAgent
Rock, Paper, Scissors
ActionMaskAgent
Tic-Tac-Toe
Texas Hold’em No Limit
Multi-Agent Simulated Environment: Petting Zoo#
In this example, we show how to... | https://python.langchain.com/en/latest/use_cases/agent_simulations/petting_zoo.html |
58c25cc4f5d3-1 | 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... | https://python.langchain.com/en/latest/use_cases/agent_simulations/petting_zoo.html |
58c25cc4f5d3-2 | 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 tenacit... | https://python.langchain.com/en/latest/use_cases/agent_simulations/petting_zoo.html |
58c25cc4f5d3-3 | 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 ... | https://python.langchain.com/en/latest/use_cases/agent_simulations/petting_zoo.html |
58c25cc4f5d3-4 | 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, ... | https://python.langchain.com/en/latest/use_cases/agent_simulations/petting_zoo.html |
58c25cc4f5d3-5 | 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
Re... | https://python.langchain.com/en/latest/use_cases/agent_simulations/petting_zoo.html |
58c25cc4f5d3-6 | X | - | -
_____|_____|_____
| |
O | - | -
_____|_____|_____
| |
- | - | -
| |
Observation: {'observation': array([[[1, 0],
[0, 1],
[0, 0]],
[[0, 0],
[0, 0],
[0, 0]],
[[0, 0],
[0, 0],
[0, 0]]], d... | https://python.langchain.com/en/latest/use_cases/agent_simulations/petting_zoo.html |
58c25cc4f5d3-7 | [[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 | - | -
_____|_____|_____
| | ... | https://python.langchain.com/en/latest/use_cases/agent_simulations/petting_zoo.html |
58c25cc4f5d3-8 | | |
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:... | https://python.langchain.com/en/latest/use_cases/agent_simulations/petting_zoo.html |
58c25cc4f5d3-9 | X | O | X
_____|_____|_____
| |
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]]], d... | https://python.langchain.com/en/latest/use_cases/agent_simulations/petting_zoo.html |
58c25cc4f5d3-10 | 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
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.possibl... | https://python.langchain.com/en/latest/use_cases/agent_simulations/petting_zoo.html |
58c25cc4f5d3-11 | 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: {... | https://python.langchain.com/en/latest/use_cases/agent_simulations/petting_zoo.html |
58c25cc4f5d3-12 | Reward: 0
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.... | https://python.langchain.com/en/latest/use_cases/agent_simulations/petting_zoo.html |
58c25cc4f5d3-13 | 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... | https://python.langchain.com/en/latest/use_cases/agent_simulations/petting_zoo.html |
58c25cc4f5d3-14 | 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.],... | https://python.langchain.com/en/latest/use_cases/agent_simulations/petting_zoo.html |
58c25cc4f5d3-15 | 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: {'observat... | https://python.langchain.com/en/latest/use_cases/agent_simulations/petting_zoo.html |
58c25cc4f5d3-16 | 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'... | https://python.langchain.com/en/latest/use_cases/agent_simulations/petting_zoo.html |
58c25cc4f5d3-17 | 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., ... | https://python.langchain.com/en/latest/use_cases/agent_simulations/petting_zoo.html |
58c25cc4f5d3-18 | 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... | https://python.langchain.com/en/latest/use_cases/agent_simulations/petting_zoo.html |
58c25cc4f5d3-19 | 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 ot... | https://python.langchain.com/en/latest/use_cases/agent_simulations/petting_zoo.html |
41b7c21d8665-0 | .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 elaborat... | https://python.langchain.com/en/latest/use_cases/agent_simulations/multiagent_bidding.html |
41b7c21d8665-1 | 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
... | https://python.langchain.com/en/latest/use_cases/agent_simulations/multiagent_bidding.html |
41b7c21d8665-2 | 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... | https://python.langchain.com/en/latest/use_cases/agent_simulations/multiagent_bidding.html |
41b7c21d8665-3 | 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_descrip... | https://python.langchain.com/en/latest/use_cases/agent_simulations/multiagent_bidding.html |
41b7c21d8665-4 | 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{c... | https://python.langchain.com/en/latest/use_cases/agent_simulations/multiagent_bidding.html |
41b7c21d8665-5 | 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 f... | https://python.langchain.com/en/latest/use_cases/agent_simulations/multiagent_bidding.html |
41b7c21d8665-6 | 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 a... | https://python.langchain.com/en/latest/use_cases/agent_simulations/multiagent_bidding.html |
41b7c21d8665-7 | 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 litt... | https://python.langchain.com/en/latest/use_cases/agent_simulations/multiagent_bidding.html |
41b7c21d8665-8 | output_keys=['bid'],
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_hea... | https://python.langchain.com/en/latest/use_cases/agent_simulations/multiagent_bidding.html |
41b7c21d8665-9 | ```
{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.
You... | https://python.langchain.com/en/latest/use_cases/agent_simulations/multiagent_bidding.html |
41b7c21d8665-10 | ```
{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 t... | https://python.langchain.com/en/latest/use_cases/agent_simulations/multiagent_bidding.html |
41b7c21d8665-11 | 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_... | https://python.langchain.com/en/latest/use_cases/agent_simulations/multiagent_bidding.html |
41b7c21d8665-12 | 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,
... | https://python.langchain.com/en/latest/use_cases/agent_simulations/multiagent_bidding.html |
41b7c21d8665-13 | 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 econom... | https://python.langchain.com/en/latest/use_cases/agent_simulations/multiagent_bidding.html |
41b7c21d8665-14 | 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, ... | https://python.langchain.com/en/latest/use_cases/agent_simulations/multiagent_bidding.html |
41b7c21d8665-15 | Kanye West bid: 8
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.... | https://python.langchain.com/en/latest/use_cases/agent_simulations/multiagent_bidding.html |
41b7c21d8665-16 | 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 May 25, 2023. | https://python.langchain.com/en/latest/use_cases/agent_simulations/multiagent_bidding.html |
52221d1c8c32-0 | .ipynb
.pdf
Generative Agents in LangChain
Contents
Generative Agent Memory Components
Memory Lifecycle
Create a Generative Character
Pre-Interview with Character
Step through the day’s observations.
Interview after the day
Adding Multiple Characters
Pre-conversation interviews
Dialogue between Generative Agents
Let’... | https://python.langchain.com/en/latest/use_cases/agent_simulations/characters.html |
52221d1c8c32-1 | Memories are retrieved using a weighted sum of salience, recency, and importance.
You can review the definitions of the GenerativeAgent and GenerativeAgentMemory in the reference documentation for the following imports, focusing on add_memory and summarize_related_memories methods.
from langchain.experimental.generativ... | https://python.langchain.com/en/latest/use_cases/agent_simulations/characters.html |
52221d1c8c32-2 | def create_new_memory_retriever():
"""Create a new vector store retriever unique to the agent."""
# Define your embedding model
embeddings_model = OpenAIEmbeddings()
# Initialize the vectorstore as empty
embedding_size = 1536
index = faiss.IndexFlatL2(embedding_size)
vectorstore = FAISS(embe... | https://python.langchain.com/en/latest/use_cases/agent_simulations/characters.html |
52221d1c8c32-3 | "Tommie remembers his dog, Bruno, from when he was a kid",
"Tommie feels tired from driving so far",
"Tommie sees the new home",
"The new neighbors have a cat",
"The road is noisy at night",
"Tommie is hungry",
"Tommie tries to get some rest.",
]
for observation in tommie_observations:
tommi... | https://python.langchain.com/en/latest/use_cases/agent_simulations/characters.html |
52221d1c8c32-4 | interview_agent(tommie, "What are you looking forward to doing today?")
'Tommie said "Well, today I\'m mostly focused on getting settled into my new home. But once that\'s taken care of, I\'m looking forward to exploring the neighborhood and finding some new design inspiration. What about you?"'
interview_agent(tommie,... | https://python.langchain.com/en/latest/use_cases/agent_simulations/characters.html |
52221d1c8c32-5 | "Tommie leaves the job fair feeling disappointed.",
"Tommie stops by a local diner to grab some lunch.",
"The service is slow, and Tommie has to wait for 30 minutes to get his food.",
"Tommie overhears a conversation at the next table about a job opening.",
"Tommie asks the diners about the job opening ... | https://python.langchain.com/en/latest/use_cases/agent_simulations/characters.html |
52221d1c8c32-6 | print(colored(observation, "green"), reaction)
if ((i+1) % 20) == 0:
print('*'*40)
print(colored(f"After {i+1} observations, Tommie's summary is:\n{tommie.get_summary(force_refresh=True)}", "blue"))
print('*'*40)
Tommie wakes up to the sound of a noisy construction site outside his window. T... | https://python.langchain.com/en/latest/use_cases/agent_simulations/characters.html |
52221d1c8c32-7 | The line to get in is long, and Tommie has to wait for an hour. Tommie sighs and looks around, feeling impatient and frustrated.
Tommie meets several potential employers at the job fair but doesn't receive any offers. Tommie Tommie's shoulders slump and he sighs, feeling discouraged.
Tommie leaves the job fair feeling ... | https://python.langchain.com/en/latest/use_cases/agent_simulations/characters.html |
52221d1c8c32-8 | Name: Tommie (age: 25)
Innate traits: anxious, likes design, talkative
Tommie is hopeful and proactive in his job search, but easily becomes discouraged when faced with setbacks. He enjoys spending time outdoors and interacting with animals. Tommie is also productive and enjoys updating his resume and cover letter. He ... | https://python.langchain.com/en/latest/use_cases/agent_simulations/characters.html |
52221d1c8c32-9 | interview_agent(tommie, "Tell me about how your day has been going")
'Tommie said "Well, it\'s been a bit of a mixed day. I\'ve had some setbacks in my job search, but I also had some fun playing frisbee and spending time outdoors. How about you?"'
interview_agent(tommie, "How do you feel about coffee?")
'Tommie said "... | https://python.langchain.com/en/latest/use_cases/agent_simulations/characters.html |
52221d1c8c32-10 | eve_observations = [
"Eve overhears her colleague say something about a new client being hard to work with",
"Eve wakes up and hear's the alarm",
"Eve eats a boal of porridge",
"Eve helps a coworker on a task",
"Eve plays tennis with her friend Xu before going to work",
"Eve overhears her collea... | https://python.langchain.com/en/latest/use_cases/agent_simulations/characters.html |
52221d1c8c32-11 | interview_agent(eve, "You'll have to ask him. He may be a bit anxious, so I'd appreciate it if you keep the conversation going and ask as many questions as possible.")
'Eve said "Sure, I can definitely ask him a lot of questions to keep the conversation going. Thanks for the heads up about his anxiety."'
Dialogue betwe... | https://python.langchain.com/en/latest/use_cases/agent_simulations/characters.html |
52221d1c8c32-12 | Eve said "Sure, Tommie. I found that networking and reaching out to professionals in my field was really helpful. I also made sure to tailor my resume and cover letter to each job I applied to. Do you have any specific questions about those strategies?"
Tommie said "Thank you, Eve. That's really helpful advice. Did you... | https://python.langchain.com/en/latest/use_cases/agent_simulations/characters.html |
52221d1c8c32-13 | Name: Tommie (age: 25)
Innate traits: anxious, likes design, talkative
Tommie is a hopeful and proactive individual who is searching for a job. He becomes discouraged when he doesn't receive any offers or positive responses, but he tries to stay productive and calm by updating his resume, going for walks, and talking t... | https://python.langchain.com/en/latest/use_cases/agent_simulations/characters.html |
52221d1c8c32-14 | interview_agent(eve, "What do you wish you would have said to Tommie?")
'Eve said "Well, I think I covered most of the topics Tommie was interested in, but if I had to add one thing, it would be to make sure to follow up with any connections you make during your job search. It\'s important to maintain those relationshi... | https://python.langchain.com/en/latest/use_cases/agent_simulations/characters.html |
13057794a8ea-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 us... | https://python.langchain.com/en/latest/use_cases/agent_simulations/camel_role_playing.html |
13057794a8ea-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,
... | https://python.langchain.com/en/latest/use_cases/agent_simulations/camel_role_playing.html |
13057794a8ea-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 ... | https://python.langchain.com/en/latest/use_cases/agent_simulations/camel_role_playing.html |
13057794a8ea-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 ... | https://python.langchain.com/en/latest/use_cases/agent_simulations/camel_role_playing.html |
13057794a8ea-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... | https://python.langchain.com/en/latest/use_cases/agent_simulations/camel_role_playing.html |
13057794a8ea-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"Specifie... | https://python.langchain.com/en/latest/use_cases/agent_simulations/camel_role_playing.html |
13057794a8ea-6 | pip install pandas numpy matplotlib ta-lib
```
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, ... | https://python.langchain.com/en/latest/use_cases/agent_simulations/camel_role_playing.html |
13057794a8ea-7 | 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.
AI User (Stock Trader):
Instruction: Calculate the short-term and long-term moving averages for the stock data using the `ta.SMA()` function from t... | https://python.langchain.com/en/latest/use_cases/agent_simulations/camel_role_playing.html |
13057794a8ea-8 | ```
new_df = pd.concat([df, short_ma, long_ma], axis=1)
new_df.columns = ['open', 'high', 'low', 'close', 'volume', 'short_ma', 'long_ma']
```
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 ... | https://python.langchain.com/en/latest/use_cases/agent_simulations/camel_role_playing.html |
13057794a8ea-9 | 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 a... | https://python.langchain.com/en/latest/use_cases/agent_simulations/camel_role_playing.html |
13057794a8ea-10 | ```
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.... | https://python.langchain.com/en/latest/use_cases/agent_simulations/camel_role_playing.html |
13057794a8ea-11 | 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 tha... | https://python.langchain.com/en/latest/use_cases/agent_simulations/camel_role_playing.html |
13057794a8ea-12 | 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: {... | https://python.langchain.com/en/latest/use_cases/agent_simulations/camel_role_playing.html |
13057794a8ea-13 | # 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 ba... | https://python.langchain.com/en/latest/use_cases/agent_simulations/camel_role_playing.html |
13057794a8ea-14 | 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 ... | https://python.langchain.com/en/latest/use_cases/agent_simulations/camel_role_playing.html |
13057794a8ea-15 | 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 message... | https://python.langchain.com/en/latest/use_cases/agent_simulations/camel_role_playing.html |
0b1da23854cb-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 ... | https://python.langchain.com/en/latest/use_cases/agent_simulations/multiagent_authoritarian.html |
0b1da23854cb-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.s... | https://python.langchain.com/en/latest/use_cases/agent_simulations/multiagent_authoritarian.html |
0b1da23854cb-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 ag... | https://python.langchain.com/en/latest/use_cases/agent_simulations/multiagent_authoritarian.html |
0b1da23854cb-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,
... | https://python.langchain.com/en/latest/use_cases/agent_simulations/multiagent_authoritarian.html |
0b1da23854cb-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_... | https://python.langchain.com/en/latest/use_cases/agent_simulations/multiagent_authoritarian.html |
0b1da23854cb-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,
HumanMe... | https://python.langchain.com/en/latest/use_cases/agent_simulations/multiagent_authoritarian.html |
0b1da23854cb-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"... | https://python.langchain.com/en/latest/use_cases/agent_simulations/multiagent_authoritarian.html |
0b1da23854cb-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 SystemMe... | https://python.langchain.com/en/latest/use_cases/agent_simulations/multiagent_authoritarian.html |
0b1da23854cb-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:
T... | https://python.langchain.com/en/latest/use_cases/agent_simulations/multiagent_authoritarian.html |
0b1da23854cb-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 o... | https://python.langchain.com/en/latest/use_cases/agent_simulations/multiagent_authoritarian.html |
0b1da23854cb-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 ... | https://python.langchain.com/en/latest/use_cases/agent_simulations/multiagent_authoritarian.html |
0b1da23854cb-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 exagger... | https://python.langchain.com/en/latest/use_cases/agent_simulations/multiagent_authoritarian.html |
0b1da23854cb-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 T... | https://python.langchain.com/en/latest/use_cases/agent_simulations/multiagent_authoritarian.html |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.