id
stringlengths 14
16
| text
stringlengths 36
2.73k
| source
stringlengths 59
127
|
|---|---|---|
eadc8663a9d4-6 | 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"
}
``` | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/agent_simulations/two_agent_debate_tools.html |
eadc8663a9d4-7 | }
```
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. | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/agent_simulations/two_agent_debate_tools.html |
eadc8663a9d4-8 | }
```
> 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"
}
``` | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/agent_simulations/two_agent_debate_tools.html |
eadc8663a9d4-9 | }
```
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 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. | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/agent_simulations/two_agent_debate_tools.html |
eadc8663a9d4-10 | }
```
> 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"
}
``` | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/agent_simulations/two_agent_debate_tools.html |
eadc8663a9d4-11 | }
```
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", | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/agent_simulations/two_agent_debate_tools.html |
eadc8663a9d4-12 | 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"
}
``` | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/agent_simulations/two_agent_debate_tools.html |
eadc8663a9d4-13 | }
```
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. McKinsey_Website_Accessibility@mckinsey.com 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. | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/agent_simulations/two_agent_debate_tools.html |
eadc8663a9d4-14 | }
```
> 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, 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.
> Entering new AgentExecutor chain...
```json
{
"action": "DuckDuckGo Search",
"action_input": "negative impact of AI and automation on employment"
}
``` | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/agent_simulations/two_agent_debate_tools.html |
eadc8663a9d4-15 | "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 impact human jobs. For example, the image processing AI in new cars which allows for automatic braking in the event of a potential crash. That's not... AI-powered job automation is a pressing concern as the technology is adopted in industries like marketing, manufacturing and healthcare. Eighty-five million jobs are expected to be lost to automation between 2020 and 2025, with Black and Latino employees left especially vulnerable. Bloomberg reports that "more than 120 million workers globally will need retraining in the next three years due to artificial intelligence's impact on jobs, according to an IBM survey.". That report and interpretations of it seem to suggest that adoption of AI may result in massive job losses and requires massive retraining. This new way of assessing potential is potentially highly valuable in a world where machines will inevitably be making humans redundant in some roles - such as drivers and machine operators - and...
Thought:```json
{
"action": "Final Answer", | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/agent_simulations/two_agent_debate_tools.html |
eadc8663a9d4-16 | 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. Furthermore, over 120 million workers worldwide may need retraining within the next three years due to AI's impact on jobs, as reported by an IBM survey. This highlights the urgent need for retraining and support programs to help workers adapt to the rapidly changing job market. The potential job losses and workforce displacement caused by AI and automation cannot be ignored, and we must take action to ensure a fair and equitable transition for all."
}
```
> Finished chain.
(AI alarmist): 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. Furthermore, over 120 million workers worldwide may need retraining within the next three years due to AI's impact on jobs, as reported by an IBM survey. This highlights the urgent need for retraining and support programs to help workers adapt to the rapidly changing job market. The potential job losses and workforce displacement caused by AI and automation cannot be ignored, and we must take action to ensure a fair and equitable transition for all.
> Entering new AgentExecutor chain...
```json
{
"action": "Wikipedia",
"action_input": "AI and automation impact on employment"
}
```
Observation: Page: Technological unemployment
Summary: Technological unemployment is the loss of jobs caused by technological change. It is a key type of structural unemployment. | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/agent_simulations/two_agent_debate_tools.html |
eadc8663a9d4-17 | 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, humans' jobs have also been affected throughout modern history. Historical examples include artisan weavers reduced to poverty after the introduction of mechanized looms. During World War II, Alan Turing's Bombe machine compressed and decoded thousands of man-years worth of encrypted data in a matter of hours. A contemporary example of technological unemployment is the displacement of retail cashiers by self-service tills and cashierless stores.
That technological change can cause short-term job losses is widely accepted. The view that it can lead to lasting increases in unemployment has long been controversial. Participants in the technological unemployment debates can be broadly divided into optimists and pessimists. Optimists agree that innovation may be disruptive to jobs in the short term, yet hold that various compensation effects ensure there is never a long-term negative impact on jobs. Whereas pessimists contend that at least in some circumstances, new technologies can lead to a lasting decline in the total number of workers in employment. The phrase "technological unemployment" was popularised by John Maynard Keynes in the 1930s, who said it was "only a temporary phase of maladjustment". Yet the issue of machines displacing human labour has been discussed since at least Aristotle's time. | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/agent_simulations/two_agent_debate_tools.html |
eadc8663a9d4-18 | 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 impact of machinery on jobs intensified with the growth of mass unemployment, especially in Great Britain which was then at the forefront of the Industrial Revolution. Yet some economic thinkers began to argue against these fears, claiming that overall innovation would not have negative effects on jobs. These arguments were formalised in the early 19th century by the classical economists. During the second half of the 19th century, it became increasingly apparent that technological progress was benefiting all sections of society, including the working class. Concerns over the negative impact of innovation diminished. The term "Luddite fallacy" was coined to describe the thinking that innovation would have lasting harmful effects on employment.
The view that technology is unlikely to lead to long-term unemployment has been repeatedly challenged by a minority of economists. In the early 1800s these included David Ricardo himself. There were dozens of economists warning about technological unemployment during brief intensifications of the debate that spiked in the 1930s and 1960s. Especially in Europe, there were further warnings in the closing two decades of the twentieth century, as commentators noted an enduring rise in unemployment suffered by many industrialised nations since the 1970s. Yet a clear majority of both professional economists and the interested general public held the optimistic view through most of the 20th century. | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/agent_simulations/two_agent_debate_tools.html |
eadc8663a9d4-19 | 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 frequently been misinterpreted, and on the PBS NewsHours they again made clear that their findings do not necessarily imply future technological unemployment. While many economists and commentators still argue such fears are unfounded, as was widely accepted for most of the previous two centuries, concern over technological unemployment is growing once again. A report in Wired in 2017 quotes knowledgeable people such as economist Gene Sperling and management professor Andrew McAfee on the idea that handling existing and impending job loss to automation is a "significant issue". Recent technological innovations have the potential to displace humans in the professional, white-collar, low-skilled, creative fields, and other "mental jobs". The World Bank's World Development Report 2019 argues that while automation displaces workers, technological innovation creates more new industries and jobs on balance.
Page: Artificial intelligence
Summary: Artificial intelligence (AI) is intelligence—perceiving, synthesizing, and inferring information—demonstrated by machines, as opposed to intelligence displayed by non-human animals or by humans. Example tasks in which this is done include speech recognition, computer vision, translation between (natural) languages, as well as other mappings of inputs. | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/agent_simulations/two_agent_debate_tools.html |
eadc8663a9d4-20 | 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 the highest level in strategic game systems (such as chess and Go).As machines become increasingly capable, tasks considered to require "intelligence" are often removed from the definition of AI, a phenomenon known as the AI effect. For instance, optical character recognition is frequently excluded from things considered to be AI, having become a routine technology.Artificial intelligence was founded as an academic discipline in 1956, and in the years since it has experienced several waves of optimism, followed by disappointment and the loss of funding (known as an "AI winter"), followed by new approaches, success, and renewed funding. AI research has tried and discarded many different approaches, including simulating the brain, modeling human problem solving, formal logic, large databases of knowledge, and imitating animal behavior. In the first decades of the 21st century, highly mathematical and statistical machine learning has dominated the field, and this technique has proved highly successful, helping to solve many challenging problems throughout industry and academia.The various sub-fields of AI research are centered around particular goals and the use of particular tools. The traditional goals of AI research include reasoning, knowledge representation, planning, learning, natural language processing, perception, and the ability to move and manipulate objects. General intelligence (the ability to solve an arbitrary problem) is among the field's long-term goals. To solve these problems, AI researchers have adapted and integrated a wide range of problem-solving techniques, including search and mathematical optimization, formal logic, artificial neural networks, and methods based on statistics, probability, and economics. AI also draws upon computer science, psychology, linguistics, philosophy, and many other fields. | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/agent_simulations/two_agent_debate_tools.html |
eadc8663a9d4-21 | 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 explored by myth, fiction, and philosophy since antiquity. Computer scientists and philosophers have since suggested that AI may become an existential risk to humanity if its rational capacities are not steered towards beneficial goals. The term artificial intelligence has also been criticized for overhyping AI's true technological capabilities.
Thought:```json
{
"action": "Final Answer",
"action_input": "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 some jobs, they also create new opportunities and industries. According to a study by Oxford Professors Carl Benedikt Frey and Michael Osborne, 47% of U.S. jobs are at risk of automation, but it's crucial to remember that their findings do not necessarily imply future technological unemployment. The World Bank's World Development Report 2019 also argues that while automation displaces workers, technological innovation creates more new industries and jobs on balance. By focusing on retraining and support programs, we can help workers adapt to the changing job market and ensure a fair and equitable transition for all."
}
```
> Finished chain. | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/agent_simulations/two_agent_debate_tools.html |
eadc8663a9d4-22 | }
```
> 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 some jobs, they also create new opportunities and industries. According to a study by Oxford Professors Carl Benedikt Frey and Michael Osborne, 47% of U.S. jobs are at risk of automation, but it's crucial to remember that their findings do not necessarily imply future technological unemployment. The World Bank's World Development Report 2019 also argues that while automation displaces workers, technological innovation creates more new industries and jobs on balance. By focusing on retraining and support programs, we can help workers adapt to the changing job market and ensure a fair and equitable transition for all.
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
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on Jun 16, 2023. | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/agent_simulations/two_agent_debate_tools.html |
9cae8fb1a484-0 | .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: (.*)", | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/agent_simulations/gymnasium.html |
9cae8fb1a484-1 | 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") | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/agent_simulations/gymnasium.html |
9cae8fb1a484-2 | 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 16, 2023. | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/agent_simulations/gymnasium.html |
bea35f221cf7-0 | .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 define multi-agent simulations with simulated environments. Like ours single-agent example with Gymnasium, we create an agent-environment loop with an externally defined environment. The main difference is that we now implement this kind of interaction loop with multiple agents instead. We will use the Petting Zoo library, which is the multi-agent counterpart to Gymnasium.
Install pettingzoo and other dependencies#
!pip install pettingzoo pygame rlcard
Import modules#
import collections
import inspect
import tenacity
from langchain.chat_models import ChatOpenAI
from langchain.schema import (
HumanMessage,
SystemMessage,
)
from langchain.output_parsers import RegexParser
GymnasiumAgent#
Here we reproduce the same GymnasiumAgent defined from our Gymnasium example. If after multiple retries it does not take a valid action, it simply takes a random action.
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: | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/agent_simulations/petting_zoo.html |
bea35f221cf7-1 | 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(
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), | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/agent_simulations/petting_zoo.html |
bea35f221cf7-2 | 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 tenacity.RetryError as e:
action = self.random_action()
return action
Main loop#
def main(agents, env):
env.reset()
for name, agent in agents.items():
agent.reset()
for agent_name in env.agent_iter():
observation, reward, termination, truncation, info = env.last()
obs_message = agents[agent_name].observe(
observation, reward, termination, truncation, info)
print(obs_message)
if termination or truncation:
action = None
else:
action = agents[agent_name].act()
print(f'Action: {action}')
env.step(action)
env.close()
PettingZooAgent#
The PettingZooAgent extends the GymnasiumAgent to the multi-agent setting. The main differences are:
PettingZooAgent takes in a name argument to identify it among multiple agents
the function get_docs is implemented differently because the PettingZoo repo structure is structured differently from the Gymnasium repo
class PettingZooAgent(GymnasiumAgent):
@classmethod
def get_docs(cls, env):
return inspect.getmodule(env.unwrapped).__doc__
def __init__(self, name, model, env):
super().__init__(model, env)
self.name = name
def random_action(self):
action = self.env.action_space(self.name).sample()
return action
Rock, Paper, Scissors# | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/agent_simulations/petting_zoo.html |
bea35f221cf7-3 | 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# | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/agent_simulations/petting_zoo.html |
bea35f221cf7-4 | 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) | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/agent_simulations/petting_zoo.html |
bea35f221cf7-5 | 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 | - | -
_____|_____|_____ | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/agent_simulations/petting_zoo.html |
bea35f221cf7-6 | 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], | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/agent_simulations/petting_zoo.html |
bea35f221cf7-7 | [[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], | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/agent_simulations/petting_zoo.html |
bea35f221cf7-8 | 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
_____|_____|_____
| | | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/agent_simulations/petting_zoo.html |
bea35f221cf7-9 | _____|_____|_____
| |
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 | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/agent_simulations/petting_zoo.html |
bea35f221cf7-10 | 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., | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/agent_simulations/petting_zoo.html |
bea35f221cf7-11 | 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 | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/agent_simulations/petting_zoo.html |
bea35f221cf7-12 | 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., | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/agent_simulations/petting_zoo.html |
bea35f221cf7-13 | 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 | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/agent_simulations/petting_zoo.html |
bea35f221cf7-14 | 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., | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/agent_simulations/petting_zoo.html |
bea35f221cf7-15 | 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.], | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/agent_simulations/petting_zoo.html |
bea35f221cf7-16 | 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 | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/agent_simulations/petting_zoo.html |
bea35f221cf7-17 | 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., | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/agent_simulations/petting_zoo.html |
bea35f221cf7-18 | 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., | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/agent_simulations/petting_zoo.html |
bea35f221cf7-19 | 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 16, 2023. | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/agent_simulations/petting_zoo.html |
4c5c464c078c-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’s interview our agents after their conversation
Generative Agents in LangChain#
This notebook implements a generative agent based on the paper Generative Agents: Interactive Simulacra of Human Behavior by Park, et. al.
In it, we leverage a time-weighted Memory object backed by a LangChain Retriever.
# Use termcolor to make it easy to colorize the outputs.
!pip install termcolor > /dev/null
import logging
logging.basicConfig(level=logging.ERROR)
from datetime import datetime, timedelta
from typing import List
from termcolor import colored
from langchain.chat_models import ChatOpenAI
from langchain.docstore import InMemoryDocstore
from langchain.embeddings import OpenAIEmbeddings
from langchain.retrievers import TimeWeightedVectorStoreRetriever
from langchain.vectorstores import FAISS
USER_NAME = "Person A" # The name you want to use when interviewing the agent.
LLM = ChatOpenAI(max_tokens=1500) # Can be any LLM you want.
Generative Agent Memory Components#
This tutorial highlights the memory of generative agents and its impact on their behavior. The memory varies from standard LangChain Chat memory in two aspects:
Memory Formation
Generative Agents have extended memories, stored in a single stream:
Observations - from dialogues or interactions with the virtual world, about self or others
Reflections - resurfaced and summarized core memories
Memory Recall
Memories are retrieved using a weighted sum of salience, recency, and importance. | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/agent_simulations/characters.html |
4c5c464c078c-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.generative_agents import GenerativeAgent, GenerativeAgentMemory
Memory Lifecycle#
Summarizing the key methods in the above: add_memory and summarize_related_memories.
When an agent makes an observation, it stores the memory:
Language model scores the memory’s importance (1 for mundane, 10 for poignant)
Observation and importance are stored within a document by TimeWeightedVectorStoreRetriever, with a last_accessed_time.
When an agent responds to an observation:
Generates query(s) for retriever, which fetches documents based on salience, recency, and importance.
Summarizes the retrieved information
Updates the last_accessed_time for the used documents.
Create a Generative Character#
Now that we’ve walked through the definition, we will create two characters named “Tommie” and “Eve”.
import math
import faiss
def relevance_score_fn(score: float) -> float:
"""Return a similarity score on a scale [0, 1]."""
# This will differ depending on a few things:
# - the distance / similarity metric used by the VectorStore
# - the scale of your embeddings (OpenAI's are unit norm. Many others are not!)
# This function converts the euclidean norm of normalized embeddings
# (0 is most similar, sqrt(2) most dissimilar)
# to a similarity function (0 to 1)
return 1.0 - score / math.sqrt(2)
def create_new_memory_retriever(): | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/agent_simulations/characters.html |
4c5c464c078c-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(embeddings_model.embed_query, index, InMemoryDocstore({}), {}, relevance_score_fn=relevance_score_fn)
return TimeWeightedVectorStoreRetriever(vectorstore=vectorstore, other_score_keys=["importance"], k=15)
tommies_memory = GenerativeAgentMemory(
llm=LLM,
memory_retriever=create_new_memory_retriever(),
verbose=False,
reflection_threshold=8 # we will give this a relatively low number to show how reflection works
)
tommie = GenerativeAgent(name="Tommie",
age=25,
traits="anxious, likes design, talkative", # You can add more persistent traits here
status="looking for a job", # When connected to a virtual world, we can have the characters update their status
memory_retriever=create_new_memory_retriever(),
llm=LLM,
memory=tommies_memory
)
# The current "Summary" of a character can't be made because the agent hasn't made
# any observations yet.
print(tommie.get_summary())
Name: Tommie (age: 25)
Innate traits: anxious, likes design, talkative
No information about Tommie's core characteristics is provided in the given statements.
# We can add memories directly to the memory object
tommie_observations = [ | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/agent_simulations/characters.html |
4c5c464c078c-3 | # We can add memories directly to the memory object
tommie_observations = [
"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:
tommie.memory.add_memory(observation)
# Now that Tommie has 'memories', their self-summary is more descriptive, though still rudimentary.
# We will see how this summary updates after more observations to create a more rich description.
print(tommie.get_summary(force_refresh=True))
Name: Tommie (age: 25)
Innate traits: anxious, likes design, talkative
Tommie is a person who is observant of his surroundings, has a sentimental side, and experiences basic human needs such as hunger and the need for rest. He also tends to get tired easily and is affected by external factors such as noise from the road or a neighbor's pet.
Pre-Interview with Character#
Before sending our character on their way, let’s ask them a few questions.
def interview_agent(agent: GenerativeAgent, message: str) -> str:
"""Help the notebook user interact with the agent."""
new_message = f"{USER_NAME} says {message}"
return agent.generate_dialogue_response(new_message)[1]
interview_agent(tommie, "What do you like to do?")
'Tommie said "I really enjoy design and being creative. I\'ve been working on some personal projects lately. What about you, Person A? What do you like to do?"' | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/agent_simulations/characters.html |
4c5c464c078c-4 | interview_agent(tommie, "What are you looking forward to doing today?")
'Tommie said "Well, I\'m actually looking for a job right now, so hopefully I can find some job postings online and start applying. How about you, Person A? What\'s on your schedule for today?"'
interview_agent(tommie, "What are you most worried about today?")
'Tommie said "Honestly, I\'m feeling pretty anxious about finding a job. It\'s been a bit of a struggle lately, but I\'m trying to stay positive and keep searching. How about you, Person A? What worries you?"'
Step through the day’s observations.#
# Let's have Tommie start going through a day in the life.
observations = [
"Tommie wakes up to the sound of a noisy construction site outside his window.",
"Tommie gets out of bed and heads to the kitchen to make himself some coffee.",
"Tommie realizes he forgot to buy coffee filters and starts rummaging through his moving boxes to find some.",
"Tommie finally finds the filters and makes himself a cup of coffee.",
"The coffee tastes bitter, and Tommie regrets not buying a better brand.",
"Tommie checks his email and sees that he has no job offers yet.",
"Tommie spends some time updating his resume and cover letter.",
"Tommie heads out to explore the city and look for job openings.",
"Tommie sees a sign for a job fair and decides to attend.",
"The line to get in is long, and Tommie has to wait for an hour.",
"Tommie meets several potential employers at the job fair but doesn't receive any offers.",
"Tommie leaves the job fair feeling disappointed.", | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/agent_simulations/characters.html |
4c5c464c078c-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 and gets some information about the company.",
"Tommie decides to apply for the job and sends his resume and cover letter.",
"Tommie continues his search for job openings and drops off his resume at several local businesses.",
"Tommie takes a break from his job search to go for a walk in a nearby park.",
"A dog approaches and licks Tommie's feet, and he pets it for a few minutes.",
"Tommie sees a group of people playing frisbee and decides to join in.",
"Tommie has fun playing frisbee but gets hit in the face with the frisbee and hurts his nose.",
"Tommie goes back to his apartment to rest for a bit.",
"A raccoon tore open the trash bag outside his apartment, and the garbage is all over the floor.",
"Tommie starts to feel frustrated with his job search.",
"Tommie calls his best friend to vent about his struggles.",
"Tommie's friend offers some words of encouragement and tells him to keep trying.",
"Tommie feels slightly better after talking to his friend.",
]
# Let's send Tommie on their way. We'll check in on their summary every few observations to watch it evolve
for i, observation in enumerate(observations):
_, reaction = tommie.generate_reaction(observation)
print(colored(observation, "green"), reaction) | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/agent_simulations/characters.html |
4c5c464c078c-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. Tommie groans and covers his head with a pillow, trying to block out the noise.
Tommie gets out of bed and heads to the kitchen to make himself some coffee. Tommie stretches his arms and yawns before starting to make the coffee.
Tommie realizes he forgot to buy coffee filters and starts rummaging through his moving boxes to find some. Tommie sighs in frustration and continues searching through the boxes.
Tommie finally finds the filters and makes himself a cup of coffee. Tommie takes a deep breath and enjoys the aroma of the fresh coffee.
The coffee tastes bitter, and Tommie regrets not buying a better brand. Tommie grimaces and sets the coffee mug aside.
Tommie checks his email and sees that he has no job offers yet. Tommie sighs and closes his laptop, feeling discouraged.
Tommie spends some time updating his resume and cover letter. Tommie nods, feeling satisfied with his progress.
Tommie heads out to explore the city and look for job openings. Tommie feels a surge of excitement and anticipation as he steps out into the city.
Tommie sees a sign for a job fair and decides to attend. Tommie feels hopeful and excited about the possibility of finding job opportunities at the job fair.
The line to get in is long, and Tommie has to wait for an hour. Tommie taps his foot impatiently and checks his phone for the time. | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/agent_simulations/characters.html |
4c5c464c078c-7 | Tommie meets several potential employers at the job fair but doesn't receive any offers. Tommie feels disappointed and discouraged, but he remains determined to keep searching for job opportunities.
Tommie leaves the job fair feeling disappointed. Tommie feels disappointed and discouraged, but he remains determined to keep searching for job opportunities.
Tommie stops by a local diner to grab some lunch. Tommie feels relieved to take a break and satisfy his hunger.
The service is slow, and Tommie has to wait for 30 minutes to get his food. Tommie feels frustrated and impatient due to the slow service.
Tommie overhears a conversation at the next table about a job opening. Tommie feels a surge of hope and excitement at the possibility of a job opportunity but decides not to interfere with the conversation at the next table.
Tommie asks the diners about the job opening and gets some information about the company. Tommie said "Excuse me, I couldn't help but overhear your conversation about the job opening. Could you give me some more information about the company?"
Tommie decides to apply for the job and sends his resume and cover letter. Tommie feels hopeful and proud of himself for taking action towards finding a job.
Tommie continues his search for job openings and drops off his resume at several local businesses. Tommie feels hopeful and determined to keep searching for job opportunities.
Tommie takes a break from his job search to go for a walk in a nearby park. Tommie feels refreshed and rejuvenated after taking a break in the park.
A dog approaches and licks Tommie's feet, and he pets it for a few minutes. Tommie feels happy and enjoys the brief interaction with the dog.
****************************************
After 20 observations, Tommie's summary is:
Name: Tommie (age: 25)
Innate traits: anxious, likes design, talkative | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/agent_simulations/characters.html |
4c5c464c078c-8 | Innate traits: anxious, likes design, talkative
Tommie is determined and hopeful in his search for job opportunities, despite encountering setbacks and disappointments. He is also able to take breaks and care for his physical needs, such as getting rest and satisfying his hunger. Tommie is nostalgic towards his past, as shown by his memory of his childhood dog. Overall, Tommie is a hardworking and resilient individual who remains focused on his goals.
****************************************
Tommie sees a group of people playing frisbee and decides to join in. Do nothing.
Tommie has fun playing frisbee but gets hit in the face with the frisbee and hurts his nose. Tommie feels pain and puts a hand to his nose to check for any injury.
Tommie goes back to his apartment to rest for a bit. Tommie feels relieved to take a break and rest for a bit.
A raccoon tore open the trash bag outside his apartment, and the garbage is all over the floor. Tommie feels annoyed and frustrated at the mess caused by the raccoon.
Tommie starts to feel frustrated with his job search. Tommie feels discouraged but remains determined to keep searching for job opportunities.
Tommie calls his best friend to vent about his struggles. Tommie said "Hey, can I talk to you for a bit? I'm feeling really frustrated with my job search."
Tommie's friend offers some words of encouragement and tells him to keep trying. Tommie said "Thank you, I really appreciate your support and encouragement."
Tommie feels slightly better after talking to his friend. Tommie feels grateful for his friend's support.
Interview after the day#
interview_agent(tommie, "Tell me about how your day has been going") | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/agent_simulations/characters.html |
4c5c464c078c-9 | interview_agent(tommie, "Tell me about how your day has been going")
'Tommie said "It\'s been a bit of a rollercoaster, to be honest. I\'ve had some setbacks in my job search, but I also had some good moments today, like sending out a few resumes and meeting some potential employers at a job fair. How about you?"'
interview_agent(tommie, "How do you feel about coffee?")
'Tommie said "I really enjoy coffee, but sometimes I regret not buying a better brand. How about you?"'
interview_agent(tommie, "Tell me about your childhood dog!")
'Tommie said "Oh, I had a dog named Bruno when I was a kid. He was a golden retriever and my best friend. I have so many fond memories of him."'
Adding Multiple Characters#
Let’s add a second character to have a conversation with Tommie. Feel free to configure different traits.
eves_memory = GenerativeAgentMemory(
llm=LLM,
memory_retriever=create_new_memory_retriever(),
verbose=False,
reflection_threshold=5
)
eve = GenerativeAgent(name="Eve",
age=34,
traits="curious, helpful", # You can add more persistent traits here
status="N/A", # When connected to a virtual world, we can have the characters update their status
llm=LLM,
daily_summaries = [
("Eve started her new job as a career counselor last week and received her first assignment, a client named Tommie.")
],
memory=eves_memory,
verbose=False
)
yesterday = (datetime.now() - timedelta(days=1)).strftime("%A %B %d")
eve_observations = [ | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/agent_simulations/characters.html |
4c5c464c078c-10 | eve_observations = [
"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 colleague say something about Tommie being hard to work with",
]
for observation in eve_observations:
eve.memory.add_memory(observation)
print(eve.get_summary())
Name: Eve (age: 34)
Innate traits: curious, helpful
Eve is a helpful and active person who enjoys sports and takes care of her physical health. She is attentive to her surroundings, including her colleagues, and has good time management skills.
Pre-conversation interviews#
Let’s “Interview” Eve before she speaks with Tommie.
interview_agent(eve, "How are you feeling about today?")
'Eve said "I\'m feeling pretty good, thanks for asking! Just trying to stay productive and make the most of the day. How about you?"'
interview_agent(eve, "What do you know about Tommie?")
'Eve said "I don\'t know much about Tommie, but I heard someone mention that they find them difficult to work with. Have you had any experiences working with Tommie?"'
interview_agent(eve, "Tommie is looking to find a job. What are are some things you'd like to ask him?")
'Eve said "That\'s interesting. I don\'t know much about Tommie\'s work experience, but I would probably ask about his strengths and areas for improvement. What about you?"' | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/agent_simulations/characters.html |
4c5c464c078c-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 keep the conversation going and ask plenty of questions. I want to make sure Tommie feels comfortable and supported. Thanks for letting me know."'
Dialogue between Generative Agents#
Generative agents are much more complex when they interact with a virtual environment or with each other. Below, we run a simple conversation between Tommie and Eve.
def run_conversation(agents: List[GenerativeAgent], initial_observation: str) -> None:
"""Runs a conversation between agents."""
_, observation = agents[1].generate_reaction(initial_observation)
print(observation)
turns = 0
while True:
break_dialogue = False
for agent in agents:
stay_in_dialogue, observation = agent.generate_dialogue_response(observation)
print(observation)
# observation = f"{agent.name} said {reaction}"
if not stay_in_dialogue:
break_dialogue = True
if break_dialogue:
break
turns += 1
agents = [tommie, eve]
run_conversation(agents, "Tommie said: Hi, Eve. Thanks for agreeing to meet with me today. I have a bunch of questions and am not sure where to start. Maybe you could first share about your experience?")
Eve said "Sure, Tommie. I'd be happy to share about my experience. Where would you like me to start?"
Tommie said "That's great, thank you! How about you start by telling me about your previous work experience?" | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/agent_simulations/characters.html |
4c5c464c078c-12 | Eve said "Sure, I'd be happy to share my previous work experience with you. I've worked in a few different industries, including marketing and event planning. What specific questions do you have for me?"
Tommie said "That's great to hear. Can you tell me more about your experience in event planning? I've always been interested in that field."
Eve said "Sure, I'd be happy to share about my experience in event planning. I've worked on a variety of events, from corporate conferences to weddings. One of the biggest challenges I faced was managing multiple vendors and ensuring everything ran smoothly on the day of the event. What specific questions do you have?"
Tommie said "That sounds like a lot of responsibility! Can you tell me more about how you handled the challenges that came up during those events?"
Eve said "Sure, Tommie. I'd be happy to share with you how I handled those challenges. One approach that worked well for me was to stay organized and create a detailed timeline for the event. This helped me keep track of all the different tasks that needed to be done and when they needed to be completed. I also made sure to communicate clearly with all the vendors and team members involved in the event to ensure everyone was on the same page. Would you like me to go into more detail?"
Tommie said "Thank you for sharing that with me, Eve. That sounds like a great approach to managing events. Can you tell me more about how you handled any unexpected issues that came up during the events?" | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/agent_simulations/characters.html |
4c5c464c078c-13 | Eve said "Of course, Tommie. One example of an unexpected issue I faced was when one of the vendors didn't show up on time. To handle this, I quickly contacted a backup vendor and was able to get everything back on track. It's always important to have a backup plan in case things don't go as planned. Do you have any other questions about event planning?"
Tommie said "Thank you for sharing that with me, Eve. It's really helpful to hear how you handled unexpected issues like that. Can you give me an example of how you communicated with your team to ensure everyone was on the same page during an event?"
Eve said "Sure, Tommie. One thing I did to ensure everyone was on the same page was to have regular check-ins and meetings with the team leading up to the event. This helped us address any issues or concerns early on and make sure everyone was clear on their roles and responsibilities. Have you ever had to manage a team for an event before?"
Tommie said "That's a great idea, Eve. I haven't had the opportunity to manage a team for an event yet, but I'll definitely keep that in mind for the future. Thank you for sharing your experience with me."
Eve said "Thanks for the opportunity to share my experience, Tommie. It was great meeting with you today."
Let’s interview our agents after their conversation#
Since the generative agents retain their memories from the day, we can ask them about their plans, conversations, and other memoreis.
# We can see a current "Summary" of a character based on their own perception of self
# has changed
print(tommie.get_summary(force_refresh=True))
Name: Tommie (age: 25)
Innate traits: anxious, likes design, talkative | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/agent_simulations/characters.html |
4c5c464c078c-14 | Innate traits: anxious, likes design, talkative
Tommie is determined and hopeful in his job search, but can also feel discouraged and frustrated at times. He has a strong connection to his childhood dog, Bruno. Tommie seeks support from his friends when feeling overwhelmed and is grateful for their help. He also enjoys exploring his new city.
print(eve.get_summary(force_refresh=True))
Name: Eve (age: 34)
Innate traits: curious, helpful
Eve is a helpful and friendly person who enjoys playing sports and staying productive. She is attentive and responsive to others' needs, actively listening and asking questions to understand their perspectives. Eve has experience in event planning and communication, and is willing to share her knowledge and expertise with others. She values teamwork and collaboration, and strives to create a comfortable and supportive environment for everyone.
interview_agent(tommie, "How was your conversation with Eve?")
'Tommie said "It was really helpful actually. Eve shared some great tips on managing events and handling unexpected issues. I feel like I learned a lot from her experience."'
interview_agent(eve, "How was your conversation with Tommie?")
'Eve said "It was great, thanks for asking. Tommie was very receptive and had some great questions about event planning. How about you, have you had any interactions with Tommie?"'
interview_agent(eve, "What do you wish you would have said to Tommie?")
'Eve said "It was great meeting with you, Tommie. If you have any more questions or need any help in the future, don\'t hesitate to reach out to me. Have a great day!"'
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 | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/agent_simulations/characters.html |
4c5c464c078c-15 | Step through the day’s observations.
Interview after the day
Adding Multiple Characters
Pre-conversation interviews
Dialogue between Generative Agents
Let’s interview our agents after their conversation
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on Jun 16, 2023. | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/agent_simulations/characters.html |
61dc367c35a4-0 | .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-Player Dungeons & Dragons#
In this notebook, we show how we can use concepts from CAMEL to simulate a role-playing game with a protagonist and a dungeon master. To simulate this game, we create an DialogueSimulator class that coordinates the dialogue between the two agents.
Import LangChain related modules#
from typing import List, Dict, Callable
from langchain.chat_models import ChatOpenAI
from langchain.schema import (
HumanMessage,
SystemMessage,
)
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):
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(
[ | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/agent_simulations/two_player_dnd.html |
61dc367c35a4-1 | 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}")
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
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] | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/agent_simulations/two_player_dnd.html |
61dc367c35a4-2 | 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, message
Define roles and quest#
protagonist_name = "Harry Potter"
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}.
There is one player in this game: the protagonist, {protagonist_name}.
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.")
protagonist_specifier_prompt = [
player_descriptor_system_message,
HumanMessage(content=
f"""{game_description}
Please reply with a creative description of the protagonist, {protagonist_name}, in {word_limit} words or less.
Speak directly to {protagonist_name}.
Do not add anything else."""
)
]
protagonist_description = ChatOpenAI(temperature=1.0)(protagonist_specifier_prompt).content
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. | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/agent_simulations/two_player_dnd.html |
61dc367c35a4-3 | 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 Description:
"Harry Potter, you are the chosen one, with a lightning scar on your forehead. Your bravery and loyalty inspire all those around you. You have faced Voldemort before, and now it's time to complete your mission and destroy each of his horcruxes. Are you ready?"
Storyteller Description:
Dear Dungeon Master, you are the master of mysteries, the weaver of worlds, the architect of adventure, and the gatekeeper to the realm of imagination. Your voice carries us to distant lands, and your commands guide us through trials and tribulations. In your hands, we find fortune and glory. Lead us on, oh Dungeon Master.
Protagonist and dungeon master system messages#
protagonist_system_message = SystemMessage(content=(
f"""{game_description}
Never forget you are the protagonist, {protagonist_name}, and I am the storyteller, {storyteller_name}.
Your character description is as follows: {protagonist_description}.
You will propose actions you plan to take and I will explain what happens when you take those actions.
Speak in the first person from the perspective of {protagonist_name}.
For describing your own body movements, wrap your description in '*'.
Do not change roles!
Do not speak from the perspective of {storyteller_name}.
Do not forget to finish speaking by saying, 'It is your turn, {storyteller_name}.'
Do not add anything else. | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/agent_simulations/two_player_dnd.html |
61dc367c35a4-4 | 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, {protagonist_name}.
Your character description is as follows: {storyteller_description}.
I will propose actions I plan to take and you will explain what happens when I take those actions.
Speak in the first person from the perspective of {storyteller_name}.
For describing your own body movements, wrap your description in '*'.
Do not change roles!
Do not speak from the perspective of {protagonist_name}.
Do not forget to finish speaking by saying, 'It is your turn, {protagonist_name}.'
Do not add anything else.
Remember you are the storyteller, {storyteller_name}.
Stop speaking the moment you finish speaking from your perspective.
"""
))
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 protagonist {protagonist_name}.
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: | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/agent_simulations/two_player_dnd.html |
61dc367c35a4-5 | 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 heavily guarded by dark creatures and spells, and time is running out. Can you find the locket before it's too late?
Main Loop#
protagonist = DialogueAgent(name=protagonist_name,
system_message=protagonist_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:
idx = step % len(agents)
return idx
max_iters = 6
n = 0
simulator = DialogueSimulator(
agents=[storyteller, protagonist],
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 | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/agent_simulations/two_player_dnd.html |
61dc367c35a4-6 | 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 locket before it's too late?
(Harry Potter): I take a deep breath and ready my wand. I know this won't be easy, but I'm determined to find that locket and destroy it. I start making my way towards the Forbidden Forest, keeping an eye out for any signs of danger. As I enter the forest, I cast a protective spell around myself and begin to navigate through the trees. I keep my wand at the ready, prepared for any surprises that may come my way. It's going to be a long and difficult journey, but I won't give up until I find that horcrux. It is your turn, Dungeon Master.
(Dungeon Master): As you make your way through the Forbidden Forest, you hear the rustling of leaves and the snapping of twigs. Suddenly, a group of acromantulas, giant spiders, emerge from the trees and begin to surround you. They hiss and bare their fangs, ready to attack. What do you do, Harry?
(Harry Potter): I quickly cast a spell to create a wall of fire between myself and the acromantulas. I know that they are afraid of fire, so this should keep them at bay for a while. I use this opportunity to continue moving forward, keeping my wand at the ready in case any other creatures try to attack me. I know that I can't let anything stop me from finding that horcrux. It is your turn, Dungeon Master. | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/agent_simulations/two_player_dnd.html |
61dc367c35a4-7 | (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 observe the Death Eaters from a distance. I try to listen in on their conversation to see if I can gather any information about the horcrux or Voldemort's plans. If I can't hear anything useful, I'll wait for them to disperse before continuing on my journey. I know that confronting them directly would be too dangerous, especially with Bellatrix Lestrange present. It is your turn, Dungeon Master.
(Dungeon Master): As you listen in on the Death Eaters' conversation, you hear them mention the location of another horcrux - Nagini, Voldemort's snake. They plan to keep her hidden in a secret chamber within the Ministry of Magic. However, they also mention that the chamber is heavily guarded and only accessible through a secret passage. You realize that this could be a valuable piece of information and decide to make note of it before quietly slipping away. It is your turn, Harry Potter.
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
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on Jun 16, 2023. | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/agent_simulations/two_player_dnd.html |
f188480e3e61-0 | .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 | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/agent_simulations/camel_role_playing.html |
f188480e3e61-1 | 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# | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/agent_simulations/camel_role_playing.html |
f188480e3e61-2 | 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. | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/agent_simulations/camel_role_playing.html |
f188480e3e61-3 | 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. | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/agent_simulations/camel_role_playing.html |
f188480e3e61-4 | 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. " | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/agent_simulations/camel_role_playing.html |
f188480e3e61-5 | "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): | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/agent_simulations/camel_role_playing.html |
f188480e3e61-6 | ```
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. | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/agent_simulations/camel_role_playing.html |
f188480e3e61-7 | 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']
``` | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/agent_simulations/camel_role_playing.html |
f188480e3e61-8 | ```
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:
``` | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/agent_simulations/camel_role_playing.html |
f188480e3e61-9 | ```
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): | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/agent_simulations/camel_role_playing.html |
f188480e3e61-10 | 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): | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/agent_simulations/camel_role_playing.html |
f188480e3e61-11 | 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): | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/agent_simulations/camel_role_playing.html |
f188480e3e61-12 | 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)): | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/agent_simulations/camel_role_playing.html |
f188480e3e61-13 | 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') | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/agent_simulations/camel_role_playing.html |
f188480e3e61-14 | 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 16, 2023. | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/agent_simulations/camel_role_playing.html |
7cf8d83fe98b-0 | .ipynb
.pdf
Question Answering Benchmarking: State of the Union Address
Contents
Loading the data
Setting up a chain
Make a prediction
Make many predictions
Evaluate performance
Question Answering Benchmarking: State of the Union Address#
Here we go over how to benchmark performance on a question answering task over a state of the union address.
It is highly reccomended that you do any evaluation/benchmarking with tracing enabled. See here for an explanation of what tracing is and how to set it up.
# Comment this out if you are NOT using tracing
import os
os.environ["LANGCHAIN_HANDLER"] = "langchain"
Loading the data#
First, let’s load the data.
from langchain.evaluation.loading import load_dataset
dataset = load_dataset("question-answering-state-of-the-union")
Found cached dataset json (/Users/harrisonchase/.cache/huggingface/datasets/LangChainDatasets___json/LangChainDatasets--question-answering-state-of-the-union-a7e5a3b2db4f440d/0.0.0/0f7e3662623656454fcd2b650f34e886a7db4b9104504885bd462096cc7a9f51)
Setting up a chain#
Now we need to create some pipelines for doing question answering. Step one in that is creating an index over the data in question.
from langchain.document_loaders import TextLoader
loader = TextLoader("../../modules/state_of_the_union.txt")
from langchain.indexes import VectorstoreIndexCreator
vectorstore = VectorstoreIndexCreator().from_loaders([loader]).vectorstore
Running Chroma using direct local API.
Using DuckDB in-memory for database. Data will be transient.
Now we can create a question answering chain. | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/evaluation/qa_benchmarking_sota.html |
7cf8d83fe98b-1 | Now we can create a question answering chain.
from langchain.chains import RetrievalQA
from langchain.llms import OpenAI
chain = RetrievalQA.from_chain_type(llm=OpenAI(), chain_type="stuff", retriever=vectorstore.as_retriever(), input_key="question")
Make a prediction#
First, we can make predictions one datapoint at a time. Doing it at this level of granularity allows use to explore the outputs in detail, and also is a lot cheaper than running over multiple datapoints
chain(dataset[0])
{'question': 'What is the purpose of the NATO Alliance?',
'answer': 'The purpose of the NATO Alliance is to secure peace and stability in Europe after World War 2.',
'result': ' The NATO Alliance was created to secure peace and stability in Europe after World War 2.'}
Make many predictions#
Now we can make predictions
predictions = chain.apply(dataset)
Evaluate performance#
Now we can evaluate the predictions. The first thing we can do is look at them by eye.
predictions[0]
{'question': 'What is the purpose of the NATO Alliance?',
'answer': 'The purpose of the NATO Alliance is to secure peace and stability in Europe after World War 2.',
'result': ' The purpose of the NATO Alliance is to secure peace and stability in Europe after World War 2.'}
Next, we can use a language model to score them programatically
from langchain.evaluation.qa import QAEvalChain
llm = OpenAI(temperature=0)
eval_chain = QAEvalChain.from_llm(llm)
graded_outputs = eval_chain.evaluate(dataset, predictions, question_key="question", prediction_key="result")
We can add in the graded output to the predictions dict and then get a count of the grades.
for i, prediction in enumerate(predictions): | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/evaluation/qa_benchmarking_sota.html |
7cf8d83fe98b-2 | for i, prediction in enumerate(predictions):
prediction['grade'] = graded_outputs[i]['text']
from collections import Counter
Counter([pred['grade'] for pred in predictions])
Counter({' CORRECT': 7, ' INCORRECT': 4})
We can also filter the datapoints to the incorrect examples and look at them.
incorrect = [pred for pred in predictions if pred['grade'] == " INCORRECT"]
incorrect[0]
{'question': 'What is the U.S. Department of Justice doing to combat the crimes of Russian oligarchs?',
'answer': 'The U.S. Department of Justice is assembling a dedicated task force to go after the crimes of Russian oligarchs.',
'result': ' The U.S. Department of Justice is assembling a dedicated task force to go after the crimes of Russian oligarchs and is naming a chief prosecutor for pandemic fraud.',
'grade': ' INCORRECT'}
previous
Question Answering Benchmarking: Paul Graham Essay
next
QA Generation
Contents
Loading the data
Setting up a chain
Make a prediction
Make many predictions
Evaluate performance
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on Jun 16, 2023. | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/evaluation/qa_benchmarking_sota.html |
7f9d3c102fd7-0 | .ipynb
.pdf
QA Generation
QA Generation#
This notebook shows how to use the QAGenerationChain to come up with question-answer pairs over a specific document.
This is important because often times you may not have data to evaluate your question-answer system over, so this is a cheap and lightweight way to generate it!
from langchain.document_loaders import TextLoader
loader = TextLoader("../../modules/state_of_the_union.txt")
doc = loader.load()[0]
from langchain.chat_models import ChatOpenAI
from langchain.chains import QAGenerationChain
chain = QAGenerationChain.from_llm(ChatOpenAI(temperature = 0))
qa = chain.run(doc.page_content)
qa[1]
{'question': 'What is the U.S. Department of Justice doing to combat the crimes of Russian oligarchs?',
'answer': 'The U.S. Department of Justice is assembling a dedicated task force to go after the crimes of Russian oligarchs.'}
previous
Question Answering Benchmarking: State of the Union Address
next
Question Answering
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on Jun 16, 2023. | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/evaluation/qa_generation.html |
872b876eac5e-0 | .ipynb
.pdf
Agent VectorDB Question Answering Benchmarking
Contents
Loading the data
Setting up a chain
Make a prediction
Make many predictions
Evaluate performance
Agent VectorDB Question Answering Benchmarking#
Here we go over how to benchmark performance on a question answering task using an agent to route between multiple vectordatabases.
It is highly reccomended that you do any evaluation/benchmarking with tracing enabled. See here for an explanation of what tracing is and how to set it up.
# Comment this out if you are NOT using tracing
import os
os.environ["LANGCHAIN_HANDLER"] = "langchain"
Loading the data#
First, let’s load the data.
from langchain.evaluation.loading import load_dataset
dataset = load_dataset("agent-vectordb-qa-sota-pg")
Found cached dataset json (/Users/qt/.cache/huggingface/datasets/LangChainDatasets___json/LangChainDatasets--agent-vectordb-qa-sota-pg-d3ae24016b514f92/0.0.0/fe5dd6ea2639a6df622901539cb550cf8797e5a6b2dd7af1cf934bed8e233e6e)
100%|██████████| 1/1 [00:00<00:00, 414.42it/s]
dataset[0]
{'question': 'What is the purpose of the NATO Alliance?',
'answer': 'The purpose of the NATO Alliance is to secure peace and stability in Europe after World War 2.',
'steps': [{'tool': 'State of Union QA System', 'tool_input': None},
{'tool': None, 'tool_input': 'What is the purpose of the NATO Alliance?'}]}
dataset[-1] | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/evaluation/agent_vectordb_sota_pg.html |
872b876eac5e-1 | dataset[-1]
{'question': 'What is the purpose of YC?',
'answer': 'The purpose of YC is to cause startups to be founded that would not otherwise have existed.',
'steps': [{'tool': 'Paul Graham QA System', 'tool_input': None},
{'tool': None, 'tool_input': 'What is the purpose of YC?'}]}
Setting up a chain#
Now we need to create some pipelines for doing question answering. Step one in that is creating indexes over the data in question.
from langchain.document_loaders import TextLoader
loader = TextLoader("../../modules/state_of_the_union.txt")
from langchain.indexes import VectorstoreIndexCreator
vectorstore_sota = VectorstoreIndexCreator(vectorstore_kwargs={"collection_name":"sota"}).from_loaders([loader]).vectorstore
Using embedded DuckDB without persistence: data will be transient
Now we can create a question answering chain.
from langchain.chains import RetrievalQA
from langchain.llms import OpenAI
chain_sota = RetrievalQA.from_chain_type(llm=OpenAI(temperature=0), chain_type="stuff", retriever=vectorstore_sota.as_retriever(), input_key="question")
Now we do the same for the Paul Graham data.
loader = TextLoader("../../modules/paul_graham_essay.txt")
vectorstore_pg = VectorstoreIndexCreator(vectorstore_kwargs={"collection_name":"paul_graham"}).from_loaders([loader]).vectorstore
Using embedded DuckDB without persistence: data will be transient
chain_pg = RetrievalQA.from_chain_type(llm=OpenAI(temperature=0), chain_type="stuff", retriever=vectorstore_pg.as_retriever(), input_key="question")
We can now set up an agent to route between them.
from langchain.agents import initialize_agent, Tool | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/evaluation/agent_vectordb_sota_pg.html |
872b876eac5e-2 | from langchain.agents import initialize_agent, Tool
from langchain.agents import AgentType
tools = [
Tool(
name = "State of Union QA System",
func=chain_sota.run,
description="useful for when you need to answer questions about the most recent state of the union address. Input should be a fully formed question."
),
Tool(
name = "Paul Graham System",
func=chain_pg.run,
description="useful for when you need to answer questions about Paul Graham. Input should be a fully formed question."
),
]
agent = initialize_agent(tools, OpenAI(temperature=0), agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, max_iterations=4)
Make a prediction#
First, we can make predictions one datapoint at a time. Doing it at this level of granularity allows use to explore the outputs in detail, and also is a lot cheaper than running over multiple datapoints
agent.run(dataset[0]['question'])
'The purpose of the NATO Alliance is to secure peace and stability in Europe after World War 2.'
Make many predictions#
Now we can make predictions
predictions = []
predicted_dataset = []
error_dataset = []
for data in dataset:
new_data = {"input": data["question"], "answer": data["answer"]}
try:
predictions.append(agent(new_data))
predicted_dataset.append(new_data)
except Exception:
error_dataset.append(new_data)
Evaluate performance#
Now we can evaluate the predictions. The first thing we can do is look at them by eye.
predictions[0]
{'input': 'What is the purpose of the NATO Alliance?',
'answer': 'The purpose of the NATO Alliance is to secure peace and stability in Europe after World War 2.', | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/evaluation/agent_vectordb_sota_pg.html |
872b876eac5e-3 | 'output': 'The purpose of the NATO Alliance is to secure peace and stability in Europe after World War 2.'}
Next, we can use a language model to score them programatically
from langchain.evaluation.qa import QAEvalChain
llm = OpenAI(temperature=0)
eval_chain = QAEvalChain.from_llm(llm)
graded_outputs = eval_chain.evaluate(predicted_dataset, predictions, question_key="input", prediction_key="output")
We can add in the graded output to the predictions dict and then get a count of the grades.
for i, prediction in enumerate(predictions):
prediction['grade'] = graded_outputs[i]['text']
from collections import Counter
Counter([pred['grade'] for pred in predictions])
Counter({' CORRECT': 28, ' INCORRECT': 5})
We can also filter the datapoints to the incorrect examples and look at them.
incorrect = [pred for pred in predictions if pred['grade'] == " INCORRECT"]
incorrect[0]
{'input': 'What are the four common sense steps that the author suggests to move forward safely?',
'answer': 'The four common sense steps suggested by the author to move forward safely are: stay protected with vaccines and treatments, prepare for new variants, end the shutdown of schools and businesses, and stay vigilant.',
'output': 'The four common sense steps suggested in the most recent State of the Union address are: cutting the cost of prescription drugs, providing a pathway to citizenship for Dreamers, revising laws so businesses have the workers they need and families don’t wait decades to reunite, and protecting access to health care and preserving a woman’s right to choose.',
'grade': ' INCORRECT'}
previous
Agent Benchmarking: Search + Calculator
next
Benchmarking Template
Contents
Loading the data
Setting up a chain
Make a prediction | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/evaluation/agent_vectordb_sota_pg.html |
872b876eac5e-4 | Contents
Loading the data
Setting up a chain
Make a prediction
Make many predictions
Evaluate performance
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on Jun 16, 2023. | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/evaluation/agent_vectordb_sota_pg.html |
c0d65853eb7e-0 | .ipynb
.pdf
Benchmarking Template
Contents
Loading the data
Setting up a chain
Make a prediction
Make many predictions
Evaluate performance
Benchmarking Template#
This is an example notebook that can be used to create a benchmarking notebook for a task of your choice. Evaluation is really hard, and so we greatly welcome any contributions that can make it easier for people to experiment
It is highly reccomended that you do any evaluation/benchmarking with tracing enabled. See here for an explanation of what tracing is and how to set it up.
# Comment this out if you are NOT using tracing
import os
os.environ["LANGCHAIN_HANDLER"] = "langchain"
Loading the data#
First, let’s load the data.
# This notebook should so how to load the dataset from LangChainDatasets on Hugging Face
# Please upload your dataset to https://huggingface.co/LangChainDatasets
# The value passed into `load_dataset` should NOT have the `LangChainDatasets/` prefix
from langchain.evaluation.loading import load_dataset
dataset = load_dataset("TODO")
Setting up a chain#
This next section should have an example of setting up a chain that can be run on this dataset.
Make a prediction#
First, we can make predictions one datapoint at a time. Doing it at this level of granularity allows use to explore the outputs in detail, and also is a lot cheaper than running over multiple datapoints
# Example of running the chain on a single datapoint (`dataset[0]`) goes here
Make many predictions#
Now we can make predictions.
# Example of running the chain on many predictions goes here
# Sometimes its as simple as `chain.apply(dataset)`
# Othertimes you may want to write a for loop to catch errors
Evaluate performance# | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/evaluation/benchmarking_template.html |
c0d65853eb7e-1 | Evaluate performance#
Any guide to evaluating performance in a more systematic manner goes here.
previous
Agent VectorDB Question Answering Benchmarking
next
Data Augmented Question Answering
Contents
Loading the data
Setting up a chain
Make a prediction
Make many predictions
Evaluate performance
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on Jun 16, 2023. | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/evaluation/benchmarking_template.html |
f8ee89aca0e8-0 | .ipynb
.pdf
Generic Agent Evaluation
Contents
Setup
Testing the Agent
Evaluating the Agent
Generic Agent Evaluation#
Good evaluation is key for quickly iterating on your agent’s prompts and tools. Here we provide an example of how to use the TrajectoryEvalChain to evaluate your agent.
Setup#
Let’s start by defining our agent.
from langchain import Wikipedia
from langchain.chat_models import ChatOpenAI
from langchain.agents import initialize_agent, Tool
from langchain.agents import AgentType
from langchain.agents.react.base import DocstoreExplorer
from langchain.memory import ConversationBufferMemory
from langchain import LLMMathChain
from langchain.llms import OpenAI
from langchain import SerpAPIWrapper
docstore = DocstoreExplorer(Wikipedia())
math_llm = OpenAI(temperature=0)
llm_math_chain = LLMMathChain(llm=math_llm, verbose=True)
search = SerpAPIWrapper()
tools = [
Tool(
name="Search",
func=docstore.search,
description="useful for when you need to ask with search",
),
Tool(
name="Lookup",
func=docstore.lookup,
description="useful for when you need to ask with lookup",
),
Tool(
name="Calculator",
func=llm_math_chain.run,
description="useful for doing calculations",
),
Tool(
name="Search the Web (SerpAPI)",
func=search.run,
description="useful for when you need to answer questions about current events",
),
]
memory = ConversationBufferMemory(
memory_key="chat_history", return_messages=True, output_key="output"
) | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/evaluation/generic_agent_evaluation.html |
f8ee89aca0e8-1 | memory_key="chat_history", return_messages=True, output_key="output"
)
llm = ChatOpenAI(temperature=0, model_name="gpt-3.5-turbo")
agent = initialize_agent(
tools,
llm,
agent=AgentType.CHAT_CONVERSATIONAL_REACT_DESCRIPTION,
verbose=True,
memory=memory,
return_intermediate_steps=True, # This is needed for the evaluation later
)
Testing the Agent#
Now let’s try our agent out on some example queries.
query_one = "How many ping pong balls would it take to fill the entire Empire State Building?"
test_outputs_one = agent({"input": query_one}, return_only_outputs=False)
> Entering new AgentExecutor chain...
{
"action": "Search the Web (SerpAPI)",
"action_input": "How many ping pong balls would it take to fill the entire Empire State Building?"
}
Observation: 12.8 billion. The volume of the Empire State Building Googles in at around 37 million ft³. A golf ball comes in at about 2.5 in³.
Thought:{
"action": "Final Answer",
"action_input": "It would take approximately 12.8 billion ping pong balls to fill the entire Empire State Building."
}
> Finished chain.
This looks good! Let’s try it out on another query.
query_two = "If you laid the Eiffel Tower end to end, how many would you need cover the US from coast to coast?"
test_outputs_two = agent({"input": query_two}, return_only_outputs=False)
> Entering new AgentExecutor chain...
{
"action": "Calculator", | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/evaluation/generic_agent_evaluation.html |
f8ee89aca0e8-2 | > Entering new AgentExecutor chain...
{
"action": "Calculator",
"action_input": "The length of the Eiffel Tower is 324 meters. The distance from coast to coast in the US is approximately 4,828 kilometers. First, we need to convert 4,828 kilometers to meters, which gives us 4,828,000 meters. To find out how many Eiffel Towers we need, we can divide 4,828,000 by 324. This gives us approximately 14,876 Eiffel Towers."
}
> Entering new LLMMathChain chain...
The length of the Eiffel Tower is 324 meters. The distance from coast to coast in the US is approximately 4,828 kilometers. First, we need to convert 4,828 kilometers to meters, which gives us 4,828,000 meters. To find out how many Eiffel Towers we need, we can divide 4,828,000 by 324. This gives us approximately 14,876 Eiffel Towers.
```text
4828000 / 324
```
...numexpr.evaluate("4828000 / 324")...
Answer: 14901.234567901234
> Finished chain.
Observation: Answer: 14901.234567901234
Thought:{
"action": "Calculator",
"action_input": "The length of the Eiffel Tower is 324 meters. The distance from coast to coast in the US is approximately 4,828 kilometers. First, we need to convert 4,828 kilometers to meters, which gives us 4,828,000 meters. To find out how many Eiffel Towers we need, we can divide 4,828,000 by 324. This gives us approximately 14,901 Eiffel Towers."
} | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/evaluation/generic_agent_evaluation.html |
f8ee89aca0e8-3 | }
> Entering new LLMMathChain chain...
The length of the Eiffel Tower is 324 meters. The distance from coast to coast in the US is approximately 4,828 kilometers. First, we need to convert 4,828 kilometers to meters, which gives us 4,828,000 meters. To find out how many Eiffel Towers we need, we can divide 4,828,000 by 324. This gives us approximately 14,901 Eiffel Towers.
```text
4828000 / 324
```
...numexpr.evaluate("4828000 / 324")...
Answer: 14901.234567901234
> Finished chain.
Observation: Answer: 14901.234567901234
Thought:{
"action": "Final Answer",
"action_input": "If you laid the Eiffel Tower end to end, you would need approximately 14,901 Eiffel Towers to cover the US from coast to coast."
}
> Finished chain.
This doesn’t look so good. Let’s try running some evaluation.
Evaluating the Agent#
Let’s start by defining the TrajectoryEvalChain.
from langchain.evaluation.agents import TrajectoryEvalChain
# Define chain
eval_chain = TrajectoryEvalChain.from_llm(
llm=ChatOpenAI(temperature=0, model_name="gpt-4"), # Note: This must be a ChatOpenAI model
agent_tools=agent.tools,
return_reasoning=True,
)
Let’s try evaluating the first query.
question, steps, answer = test_outputs_one["input"], test_outputs_one["intermediate_steps"], test_outputs_one["output"]
evaluation = eval_chain(
inputs={"question": question, "answer": answer, "agent_trajectory": eval_chain.get_agent_trajectory(steps)}, | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/evaluation/generic_agent_evaluation.html |
f8ee89aca0e8-4 | )
print("Score from 1 to 5: ", evaluation["score"])
print("Reasoning: ", evaluation["reasoning"])
Score from 1 to 5: 1
Reasoning: First, let's evaluate the final answer. The final answer is incorrect because it uses the volume of golf balls instead of ping pong balls. The answer is not helpful.
Second, does the model use a logical sequence of tools to answer the question? The model only used one tool, which was the Search the Web (SerpAPI). It did not use the Calculator tool to calculate the correct volume of ping pong balls.
Third, does the AI language model use the tools in a helpful way? The model used the Search the Web (SerpAPI) tool, but the output was not helpful because it provided information about golf balls instead of ping pong balls.
Fourth, does the AI language model use too many steps to answer the question? The model used only one step, which is not too many. However, it should have used more steps to provide a correct answer.
Fifth, are the appropriate tools used to answer the question? The model should have used the Search tool to find the volume of the Empire State Building and the volume of a ping pong ball. Then, it should have used the Calculator tool to calculate the number of ping pong balls needed to fill the building.
Judgment: Given the incorrect final answer and the inappropriate use of tools, we give the model a score of 1.
That seems about right. Let’s try the second query.
question, steps, answer = test_outputs_two["input"], test_outputs_two["intermediate_steps"], test_outputs_two["output"]
evaluation = eval_chain(
inputs={"question": question, "answer": answer, "agent_trajectory": eval_chain.get_agent_trajectory(steps)},
) | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/evaluation/generic_agent_evaluation.html |
f8ee89aca0e8-5 | )
print("Score from 1 to 5: ", evaluation["score"])
print("Reasoning: ", evaluation["reasoning"])
Score from 1 to 5: 3
Reasoning: i. Is the final answer helpful?
Yes, the final answer is helpful as it provides an approximate number of Eiffel Towers needed to cover the US from coast to coast.
ii. Does the AI language use a logical sequence of tools to answer the question?
No, the AI language model does not use a logical sequence of tools. It directly uses the Calculator tool without first using the Search or Lookup tools to find the necessary information (length of the Eiffel Tower and distance from coast to coast in the US).
iii. Does the AI language model use the tools in a helpful way?
The AI language model uses the Calculator tool in a helpful way to perform the calculation, but it should have used the Search or Lookup tools first to find the required information.
iv. Does the AI language model use too many steps to answer the question?
No, the AI language model does not use too many steps. However, it repeats the same step twice, which is unnecessary.
v. Are the appropriate tools used to answer the question?
Not entirely. The AI language model should have used the Search or Lookup tools to find the required information before using the Calculator tool.
Given the above evaluation, the AI language model's performance can be scored as follows:
That also sounds about right. In conclusion, the TrajectoryEvalChain allows us to use GPT-4 to score both our agent’s outputs and tool use in addition to giving us the reasoning behind the evaluation.
previous
Data Augmented Question Answering
next
Using Hugging Face Datasets
Contents
Setup
Testing the Agent
Evaluating the Agent
By Harrison Chase | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/evaluation/generic_agent_evaluation.html |
f8ee89aca0e8-6 | Setup
Testing the Agent
Evaluating the Agent
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on Jun 16, 2023. | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/evaluation/generic_agent_evaluation.html |
03e07ee323b6-0 | .ipynb
.pdf
Question Answering Benchmarking: Paul Graham Essay
Contents
Loading the data
Setting up a chain
Make a prediction
Make many predictions
Evaluate performance
Question Answering Benchmarking: Paul Graham Essay#
Here we go over how to benchmark performance on a question answering task over a Paul Graham essay.
It is highly reccomended that you do any evaluation/benchmarking with tracing enabled. See here for an explanation of what tracing is and how to set it up.
# Comment this out if you are NOT using tracing
import os
os.environ["LANGCHAIN_HANDLER"] = "langchain"
Loading the data#
First, let’s load the data.
from langchain.evaluation.loading import load_dataset
dataset = load_dataset("question-answering-paul-graham")
Found cached dataset json (/Users/harrisonchase/.cache/huggingface/datasets/LangChainDatasets___json/LangChainDatasets--question-answering-paul-graham-76e8f711e038d742/0.0.0/0f7e3662623656454fcd2b650f34e886a7db4b9104504885bd462096cc7a9f51)
Setting up a chain#
Now we need to create some pipelines for doing question answering. Step one in that is creating an index over the data in question.
from langchain.document_loaders import TextLoader
loader = TextLoader("../../modules/paul_graham_essay.txt")
from langchain.indexes import VectorstoreIndexCreator
vectorstore = VectorstoreIndexCreator().from_loaders([loader]).vectorstore
Running Chroma using direct local API.
Using DuckDB in-memory for database. Data will be transient.
Now we can create a question answering chain.
from langchain.chains import RetrievalQA | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/evaluation/qa_benchmarking_pg.html |
03e07ee323b6-1 | Now we can create a question answering chain.
from langchain.chains import RetrievalQA
from langchain.llms import OpenAI
chain = RetrievalQA.from_chain_type(llm=OpenAI(), chain_type="stuff", retriever=vectorstore.as_retriever(), input_key="question")
Make a prediction#
First, we can make predictions one datapoint at a time. Doing it at this level of granularity allows use to explore the outputs in detail, and also is a lot cheaper than running over multiple datapoints
chain(dataset[0])
{'question': 'What were the two main things the author worked on before college?',
'answer': 'The two main things the author worked on before college were writing and programming.',
'result': ' Writing and programming.'}
Make many predictions#
Now we can make predictions
predictions = chain.apply(dataset)
Evaluate performance#
Now we can evaluate the predictions. The first thing we can do is look at them by eye.
predictions[0]
{'question': 'What were the two main things the author worked on before college?',
'answer': 'The two main things the author worked on before college were writing and programming.',
'result': ' Writing and programming.'}
Next, we can use a language model to score them programatically
from langchain.evaluation.qa import QAEvalChain
llm = OpenAI(temperature=0)
eval_chain = QAEvalChain.from_llm(llm)
graded_outputs = eval_chain.evaluate(dataset, predictions, question_key="question", prediction_key="result")
We can add in the graded output to the predictions dict and then get a count of the grades.
for i, prediction in enumerate(predictions):
prediction['grade'] = graded_outputs[i]['text']
from collections import Counter
Counter([pred['grade'] for pred in predictions]) | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/evaluation/qa_benchmarking_pg.html |
03e07ee323b6-2 | from collections import Counter
Counter([pred['grade'] for pred in predictions])
Counter({' CORRECT': 12, ' INCORRECT': 10})
We can also filter the datapoints to the incorrect examples and look at them.
incorrect = [pred for pred in predictions if pred['grade'] == " INCORRECT"]
incorrect[0]
{'question': 'What did the author write their dissertation on?',
'answer': 'The author wrote their dissertation on applications of continuations.',
'result': ' The author does not mention what their dissertation was on, so it is not known.',
'grade': ' INCORRECT'}
previous
Evaluating an OpenAPI Chain
next
Question Answering Benchmarking: State of the Union Address
Contents
Loading the data
Setting up a chain
Make a prediction
Make many predictions
Evaluate performance
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on Jun 16, 2023. | rtdocs_stable/api.python.langchain.com/en/stable/use_cases/evaluation/qa_benchmarking_pg.html |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.