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... | 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 per... | 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 w... | 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 technol... | 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 pres... | 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... | 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 opportuni... | 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 ... | 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, proc... | 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 impac... | 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. Furt... | 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,... | 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 impa... | 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 f... | 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 t... | 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... | 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 so... | 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 en... | 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
... | 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, rew... | 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... | 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... | 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 tenacit... | 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 ... | 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, ... | 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
Re... | 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]]], d... | 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 | - | -
_____|_____|_____
| | ... | 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
A... | 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), 'act... | 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.,... | 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: {... | 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.,
... | 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... | 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.],... | 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: {'observat... | 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'... | 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., ... | 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... | 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 ot... | 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’... | 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.generativ... | 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(embe... | 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",
"Tomm... | 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 ab... | 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 ... | 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. T... | 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 ... | 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, a... | 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?"'
inte... | 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_observatio... | 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 l... | 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 in... | 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 ot... | 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... | 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-Playe... | 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... | 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, mes... | 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... | 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, {prot... | 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 heavil... | 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 lo... | 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... | 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 us... | 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,
... | 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 ... | 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 ... | 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... | 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"Specifie... | 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 anal... | 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 ... | 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 ... | 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] == ... | 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 ... | 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]
pl... | 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
d... | 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):
... | 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: ... | 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 ... | 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 ... | 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 ... | 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!
f... | 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... | 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 nee... | 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 ful... | 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.evalu... | 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 welc... | 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
... | 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 o... | 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 n... | 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... | 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... | 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... | 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 ... | 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 essa... | 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 ... | 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 a... | 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.