id stringlengths 14 16 | text stringlengths 36 2.73k | source stringlengths 49 117 |
|---|---|---|
e551a6423b2e-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 |
e551a6423b2e-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 |
e551a6423b2e-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 |
e551a6423b2e-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 |
e551a6423b2e-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 |
e551a6423b2e-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 |
e551a6423b2e-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 |
e551a6423b2e-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 |
e551a6423b2e-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 |
e551a6423b2e-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 |
e551a6423b2e-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 |
e551a6423b2e-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 |
d7ca318fc65c-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#
... | https://python.langchain.com/en/latest/use_cases/agent_simulations/two_agent_debate_tools.html |
d7ca318fc65c-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_agent_debate_tools.html |
d7ca318fc65c-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_nam... | https://python.langchain.com/en/latest/use_cases/agent_simulations/two_agent_debate_tools.html |
d7ca318fc65c-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_pr... | https://python.langchain.com/en/latest/use_cases/agent_simulations/two_agent_debate_tools.html |
d7ca318fc65c-4 | 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 n... | https://python.langchain.com/en/latest/use_cases/agent_simulations/two_agent_debate_tools.html |
d7ca318fc65c-5 | 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 i... | https://python.langchain.com/en/latest/use_cases/agent_simulations/two_agent_debate_tools.html |
d7ca318fc65c-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... | https://python.langchain.com/en/latest/use_cases/agent_simulations/two_agent_debate_tools.html |
d7ca318fc65c-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 per... | https://python.langchain.com/en/latest/use_cases/agent_simulations/two_agent_debate_tools.html |
d7ca318fc65c-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 w... | https://python.langchain.com/en/latest/use_cases/agent_simulations/two_agent_debate_tools.html |
d7ca318fc65c-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. McKinsey_Website_Accessibility@mckinsey.com Manufacturing (80%) and technol... | https://python.langchain.com/en/latest/use_cases/agent_simulations/two_agent_debate_tools.html |
d7ca318fc65c-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 pres... | https://python.langchain.com/en/latest/use_cases/agent_simulations/two_agent_debate_tools.html |
d7ca318fc65c-11 | "action_input": "impact of automation and AI on employment in manufacturing"
}
```
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 ... | https://python.langchain.com/en/latest/use_cases/agent_simulations/two_agent_debate_tools.html |
d7ca318fc65c-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 opportuni... | https://python.langchain.com/en/latest/use_cases/agent_simulations/two_agent_debate_tools.html |
d7ca318fc65c-13 | "action_input": "positive impact of AI and automation on job growth"
}
```
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. McKins... | https://python.langchain.com/en/latest/use_cases/agent_simulations/two_agent_debate_tools.html |
d7ca318fc65c-14 | }
```
> Finished chain.
(AI accelerationist): 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, proc... | https://python.langchain.com/en/latest/use_cases/agent_simulations/two_agent_debate_tools.html |
d7ca318fc65c-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 |
d7ca318fc65c-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 |
d7ca318fc65c-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 |
d7ca318fc65c-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 |
d7ca318fc65c-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 |
d7ca318fc65c-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 |
d7ca318fc65c-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 |
d7ca318fc65c-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 |
258a70ab964d-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 h... | https://python.langchain.com/en/latest/use_cases/agent_simulations/multi_player_dnd.html |
258a70ab964d-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/multi_player_dnd.html |
258a70ab964d-2 | 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
mes... | https://python.langchain.com/en/latest/use_cases/agent_simulations/multi_player_dnd.html |
258a70ab964d-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}
Yo... | https://python.langchain.com/en/latest/use_cases/agent_simulations/multi_player_dnd.html |
258a70ab964d-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 fr... | https://python.langchain.com/en/latest/use_cases/agent_simulations/multi_player_dnd.html |
258a70ab964d-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... | https://python.langchain.com/en/latest/use_cases/agent_simulations/multi_player_dnd.html |
258a70ab964d-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=sto... | https://python.langchain.com/en/latest/use_cases/agent_simulations/multi_player_dnd.html |
258a70ab964d-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 Pott... | https://python.langchain.com/en/latest/use_cases/agent_simulations/multi_player_dnd.html |
258a70ab964d-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.
(Hermi... | https://python.langchain.com/en/latest/use_cases/agent_simulations/multi_player_dnd.html |
258a70ab964d-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 approachi... | https://python.langchain.com/en/latest/use_cases/agent_simulations/multi_player_dnd.html |
258a70ab964d-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 th... | https://python.langchain.com/en/latest/use_cases/agent_simulations/multi_player_dnd.html |
258a70ab964d-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 Lo... | https://python.langchain.com/en/latest/use_cases/agent_simulations/multi_player_dnd.html |
05a9e2fdae07-0 | .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 |
05a9e2fdae07-1 | 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 |
05a9e2fdae07-2 | # 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 |
05a9e2fdae07-3 | 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 |
05a9e2fdae07-4 | {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 |
05a9e2fdae07-5 | 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 |
05a9e2fdae07-6 | 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 |
05a9e2fdae07-7 | 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 |
05a9e2fdae07-8 | 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 |
05a9e2fdae07-9 | - 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 |
05a9e2fdae07-10 | 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 |
05a9e2fdae07-11 | 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 |
05a9e2fdae07-12 | 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 |
05a9e2fdae07-13 | 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 m... | https://python.langchain.com/en/latest/use_cases/agent_simulations/multiagent_authoritarian.html |
05a9e2fdae07-14 | 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 episo... | https://python.langchain.com/en/latest/use_cases/agent_simulations/multiagent_authoritarian.html |
05a9e2fdae07-15 | Never forget to keep your response to 50 words!
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... | https://python.langchain.com/en/latest/use_cases/agent_simulations/multiagent_authoritarian.html |
05a9e2fdae07-16 | """
# 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, ... | https://python.langchain.com/en/latest/use_cases/agent_simulations/multiagent_authoritarian.html |
05a9e2fdae07-17 | 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 acco... | https://python.langchain.com/en/latest/use_cases/agent_simulations/multiagent_authoritarian.html |
05a9e2fdae07-18 | (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 app... | https://python.langchain.com/en/latest/use_cases/agent_simulations/multiagent_authoritarian.html |
05a9e2fdae07-19 | (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 sittin... | https://python.langchain.com/en/latest/use_cases/agent_simulations/multiagent_authoritarian.html |
05a9e2fdae07-20 | (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... | https://python.langchain.com/en/latest/use_cases/agent_simulations/multiagent_authoritarian.html |
05a9e2fdae07-21 | (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 li... | https://python.langchain.com/en/latest/use_cases/agent_simulations/multiagent_authoritarian.html |
ec0126fe62c8-0 | .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 |
ec0126fe62c8-1 | 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 |
ec0126fe62c8-2 | 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 |
ec0126fe62c8-3 | 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 |
ec0126fe62c8-4 | 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 |
ec0126fe62c8-5 | 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 |
ec0126fe62c8-6 | 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 |
ec0126fe62c8-7 | (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 |
6ae5c4274ea1-0 | .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 |
6ae5c4274ea1-1 | 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 |
6ae5c4274ea1-2 | 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 |
6ae5c4274ea1-3 | 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 |
6ae5c4274ea1-4 | 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 |
6ae5c4274ea1-5 | 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 |
6ae5c4274ea1-6 | 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 |
6ae5c4274ea1-7 | [[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 |
6ae5c4274ea1-8 | | |
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 |
6ae5c4274ea1-9 | 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 |
6ae5c4274ea1-10 | 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 |
6ae5c4274ea1-11 | 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 |
6ae5c4274ea1-12 | 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 |
6ae5c4274ea1-13 | 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 |
6ae5c4274ea1-14 | 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 |
6ae5c4274ea1-15 | 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 |
6ae5c4274ea1-16 | 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 |
6ae5c4274ea1-17 | 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 |
6ae5c4274ea1-18 | 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 |
6ae5c4274ea1-19 | 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 |
a93f150bed4a-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 |
a93f150bed4a-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 |
a93f150bed4a-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 |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.