id
stringlengths 14
16
| text
stringlengths 36
2.73k
| source
stringlengths 49
117
|
|---|---|---|
97268e98ed8e-8 | "args": {
"file_path": "weather_report.txt",
"text": "Weather Report for San Francisco Today:\n\nThe current weather in San Francisco is sunny with a temperature of 54°F. It is expected to remain sunny throughout the day with a high of 62°F and a low of 50°F. There is no chance of precipitation today. It is recommended to wear light clothing and sunscreen if spending time outdoors.\n\nStay safe and enjoy the beautiful weather!"
}
}
}
> Entering new LLMChain chain...
Prompt after formatting:
System: You are Tom, Assistant
Your decisions must always be made independently
without seeking user assistance. Play to your strengths
as an LLM and pursue simple strategies with no legal complications.
If you have completed all your tasks,
make sure to use the "finish" command.
GOALS:
1. write a weather report for SF today
Constraints:
1. ~4000 word limit for short term memory. Your short term memory is short, so immediately save important information to files.
2. If you are unsure how you previously did something or want to recall past events, thinking about similar events will help you remember.
3. No user assistance
4. Exclusively use the commands listed in double quotes e.g. "command name"
Commands:
1. search: useful for when you need to answer questions about current events. You should ask targeted questions, args json schema: {"query": {"title": "Query", "type": "string"}} | https://python.langchain.com/en/latest/use_cases/autonomous_agents/autogpt.html |
97268e98ed8e-9 | 2. write_file: Write file to disk, args json schema: {"file_path": {"title": "File Path", "description": "name of file", "type": "string"}, "text": {"title": "Text", "description": "text to write to file", "type": "string"}}
3. read_file: Read file from disk, args json schema: {"file_path": {"title": "File Path", "description": "name of file", "type": "string"}}
4. finish: use this to signal that you have finished all your objectives, args: "response": "final response to let people know you have finished your objectives"
Resources:
1. Internet access for searches and information gathering.
2. Long Term memory management.
3. GPT-3.5 powered Agents for delegation of simple tasks.
4. File output.
Performance Evaluation:
1. Continuously review and analyze your actions to ensure you are performing to the best of your abilities.
2. Constructively self-criticize your big-picture behavior constantly.
3. Reflect on past decisions and strategies to refine your approach.
4. Every command has a cost, so be smart and efficient. Aim to complete tasks in the least number of steps.
You should only respond in JSON format as described below
Response Format:
{
"thoughts": {
"text": "thought",
"reasoning": "reasoning",
"plan": "- short bulleted\n- list that conveys\n- long-term plan",
"criticism": "constructive self-criticism",
"speak": "thoughts summary to say to user"
},
"command": {
"name": "command name",
"args": {
"arg name": "value"
}
} | https://python.langchain.com/en/latest/use_cases/autonomous_agents/autogpt.html |
97268e98ed8e-10 | "args": {
"arg name": "value"
}
}
}
Ensure the response can be parsed by Python json.loads
System: The current time and date is Tue Apr 18 21:31:55 2023
System: This reminds you of these events from your past: | https://python.langchain.com/en/latest/use_cases/autonomous_agents/autogpt.html |
97268e98ed8e-11 | ['Assistant Reply: {\n "thoughts": {\n "text": "I have found that the current weather in San Francisco is sunny with a temperature of 54°F. I will now write a weather report for San Francisco today using the \'write_file\' command.",\n "reasoning": "I need to write a weather report for San Francisco today based on the information I gathered from the \'search\' command.",\n "plan": "- Use the \'write_file\' command to write a weather report for San Francisco today based on the information gathered",\n "criticism": "I need to make sure that the weather report is accurate and informative.",\n "speak": "I will use the \'write_file\' command to write a weather report for San Francisco today."\n },\n "command": {\n "name": "write_file",\n "args": {\n "file_path": "weather_report.txt",\n "text": | https://python.langchain.com/en/latest/use_cases/autonomous_agents/autogpt.html |
97268e98ed8e-12 | "text": "Weather Report for San Francisco Today:\\n\\nThe current weather in San Francisco is sunny with a temperature of 54°F. It is expected to remain sunny throughout the day with a high of 62°F and a low of 50°F. There is no chance of precipitation today. It is recommended to wear light clothing and sunscreen if spending time outdoors.\\n\\nStay safe and enjoy the beautiful weather!"\n }\n }\n} \nResult: Command write_file returned: File written to successfully. ', 'Assistant Reply: {\n "thoughts": {\n "text": "I will start by writing a weather report for San Francisco today. I will use the \'search\' command to find the current weather conditions.",\n "reasoning": "I need to gather information about the current weather conditions in San Francisco to write an accurate weather report.",\n "plan": "- Use the \'search\' command to find the current weather conditions in San Francisco\\n- Write | https://python.langchain.com/en/latest/use_cases/autonomous_agents/autogpt.html |
97268e98ed8e-13 | the current weather conditions in San Francisco\\n- Write a weather report based on the information gathered",\n "criticism": "I need to make sure that the information I gather is accurate and up-to-date.",\n "speak": "I will use the \'search\' command to find the current weather conditions in San Francisco."\n },\n "command": {\n "name": "search",\n "args": {\n "query": "what is the current weather in san francisco"\n }\n }\n} \nResult: Command search returned: Current Weather ; 54°F · Sunny ; RealFeel® 66°. Pleasant. RealFeel Guide. Pleasant. 63° to 81°. Most consider this temperature range ideal. LEARN MORE. RealFeel ... '] | https://python.langchain.com/en/latest/use_cases/autonomous_agents/autogpt.html |
97268e98ed8e-14 | System: Command write_file returned: File written to successfully.
Human: Determine which next command to use, and respond using the format specified above:
> Finished chain.
{
"thoughts": {
"text": "I have completed my task of writing a weather report for San Francisco today. I will now use the \'finish\' command to signal that I have finished all my objectives.",
"reasoning": "I have completed all my objectives and there are no further tasks to be completed.",
"plan": "- Use the \'finish\' command to signal that I have completed all my objectives.",
"criticism": "I need to make sure that I have completed all my objectives before using the \'finish\' command.",
"speak": "I have completed my task of writing a weather report for San Francisco today. I will now use the \'finish\' command to signal that I have finished all my objectives."
},
"command": {
"name": "finish",
"args": {
"response": "I have completed all my objectives."
}
}
}
'I have completed all my objectives.'
Contents
Set up tools
Set up memory
Setup model and AutoGPT
Run an example
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on May 28, 2023. | https://python.langchain.com/en/latest/use_cases/autonomous_agents/autogpt.html |
e7116407f4a2-0 | .ipynb
.pdf
Meta-Prompt
Contents
Setup
Specify a task and interact with the agent
Meta-Prompt#
This is a LangChain implementation of Meta-Prompt, by Noah Goodman, for building self-improving agents.
The key idea behind Meta-Prompt is to prompt the agent to reflect on its own performance and modify its own instructions.
Here is a description from the original blog post:
The agent is a simple loop that starts with no instructions and follows these steps:
Engage in conversation with a user, who may provide requests, instructions, or feedback.
At the end of the episode, generate self-criticism and a new instruction using the meta-prompt
Assistant has just had the below interactions with a User. Assistant followed their "system: Instructions" closely. Your job is to critique the Assistant's performance and then revise the Instructions so that Assistant would quickly and correctly respond in the future.
####
{hist}
####
Please reflect on these interactions.
You should first critique Assistant's performance. What could Assistant have done better? What should the Assistant remember about this user? Are there things this user always wants? Indicate this with "Critique: ...".
You should next revise the Instructions so that Assistant would quickly and correctly respond in the future. Assistant's goal is to satisfy the user in as few interactions as possible. Assistant will only see the new Instructions, not the interaction history, so anything important must be summarized in the Instructions. Don't forget any important details in the current Instructions! Indicate the new Instructions by "Instructions: ...".
Repeat. | https://python.langchain.com/en/latest/use_cases/autonomous_agents/meta_prompt.html |
e7116407f4a2-1 | Repeat.
The only fixed instructions for this system (which I call Meta-prompt) is the meta-prompt that governs revision of the agent’s instructions. The agent has no memory between episodes except for the instruction it modifies for itself each time. Despite its simplicity, this agent can learn over time and self-improve by incorporating useful details into its instructions.
Setup#
We define two chains. One serves as the Assistant, and the other is a “meta-chain” that critiques the Assistant’s performance and modifies the instructions to the Assistant.
from langchain import OpenAI, LLMChain, PromptTemplate
from langchain.memory import ConversationBufferWindowMemory
def initialize_chain(instructions, memory=None):
if memory is None:
memory = ConversationBufferWindowMemory()
memory.ai_prefix = "Assistant"
template = f"""
Instructions: {instructions}
{{{memory.memory_key}}}
Human: {{human_input}}
Assistant:"""
prompt = PromptTemplate(
input_variables=["history", "human_input"],
template=template
)
chain = LLMChain(
llm=OpenAI(temperature=0),
prompt=prompt,
verbose=True,
memory=ConversationBufferWindowMemory(),
)
return chain
def initialize_meta_chain():
meta_template="""
Assistant has just had the below interactions with a User. Assistant followed their "Instructions" closely. Your job is to critique the Assistant's performance and then revise the Instructions so that Assistant would quickly and correctly respond in the future.
####
{chat_history}
####
Please reflect on these interactions. | https://python.langchain.com/en/latest/use_cases/autonomous_agents/meta_prompt.html |
e7116407f4a2-2 | ####
{chat_history}
####
Please reflect on these interactions.
You should first critique Assistant's performance. What could Assistant have done better? What should the Assistant remember about this user? Are there things this user always wants? Indicate this with "Critique: ...".
You should next revise the Instructions so that Assistant would quickly and correctly respond in the future. Assistant's goal is to satisfy the user in as few interactions as possible. Assistant will only see the new Instructions, not the interaction history, so anything important must be summarized in the Instructions. Don't forget any important details in the current Instructions! Indicate the new Instructions by "Instructions: ...".
"""
meta_prompt = PromptTemplate(
input_variables=["chat_history"],
template=meta_template
)
meta_chain = LLMChain(
llm=OpenAI(temperature=0),
prompt=meta_prompt,
verbose=True,
)
return meta_chain
def get_chat_history(chain_memory):
memory_key = chain_memory.memory_key
chat_history = chain_memory.load_memory_variables(memory_key)[memory_key]
return chat_history
def get_new_instructions(meta_output):
delimiter = 'Instructions: '
new_instructions = meta_output[meta_output.find(delimiter)+len(delimiter):]
return new_instructions
def main(task, max_iters=3, max_meta_iters=5):
failed_phrase = 'task failed'
success_phrase = 'task succeeded'
key_phrases = [success_phrase, failed_phrase]
instructions = 'None'
for i in range(max_meta_iters):
print(f'[Episode {i+1}/{max_meta_iters}]')
chain = initialize_chain(instructions, memory=None) | https://python.langchain.com/en/latest/use_cases/autonomous_agents/meta_prompt.html |
e7116407f4a2-3 | chain = initialize_chain(instructions, memory=None)
output = chain.predict(human_input=task)
for j in range(max_iters):
print(f'(Step {j+1}/{max_iters})')
print(f'Assistant: {output}')
print(f'Human: ')
human_input = input()
if any(phrase in human_input.lower() for phrase in key_phrases):
break
output = chain.predict(human_input=human_input)
if success_phrase in human_input.lower():
print(f'You succeeded! Thanks for playing!')
return
meta_chain = initialize_meta_chain()
meta_output = meta_chain.predict(chat_history=get_chat_history(chain.memory))
print(f'Feedback: {meta_output}')
instructions = get_new_instructions(meta_output)
print(f'New Instructions: {instructions}')
print('\n'+'#'*80+'\n')
print(f'You failed! Thanks for playing!')
Specify a task and interact with the agent#
task = "Provide a systematic argument for why we should always eat pasta with olives."
main(task)
[Episode 1/5]
> Entering new LLMChain chain...
Prompt after formatting:
Instructions: None
Human: Provide a systematic argument for why we should always eat pasta with olives.
Assistant:
> Finished chain.
(Step 1/3)
Assistant: Eating pasta with olives is a great way to add flavor and texture to a dish. Olives are a great source of healthy fats, vitamins, and minerals, and they can help to balance out the carbohydrates in the pasta. Additionally, olives provide a unique flavor that can help to make the dish more interesting and enjoyable.
Human: | https://python.langchain.com/en/latest/use_cases/autonomous_agents/meta_prompt.html |
e7116407f4a2-4 | Human:
You response is not in the form of a poem. Try again!
> Entering new LLMChain chain...
Prompt after formatting:
Instructions: None
Human: Provide a systematic argument for why we should always eat pasta with olives.
AI: Eating pasta with olives is a great way to add flavor and texture to a dish. Olives are a great source of healthy fats, vitamins, and minerals, and they can help to balance out the carbohydrates in the pasta. Additionally, olives provide a unique flavor that can help to make the dish more interesting and enjoyable.
Human: You response is not in the form of a poem. Try again!
Assistant:
> Finished chain.
(Step 2/3)
Assistant: Eating pasta with olives is a great way to add flavor and texture to a dish. Olives are a great source of healthy fats, vitamins, and minerals, which can help to balance out the carbohydrates in the pasta. Additionally, olives provide a unique flavor that can help to make the dish more interesting and enjoyable. For these reasons, it is recommended to always eat pasta with olives for a more balanced and flavorful meal.
Human:
Your response is not piratey enough. Try again!
> Entering new LLMChain chain...
Prompt after formatting:
Instructions: None
Human: Provide a systematic argument for why we should always eat pasta with olives.
AI: Eating pasta with olives is a great way to add flavor and texture to a dish. Olives are a great source of healthy fats, vitamins, and minerals, and they can help to balance out the carbohydrates in the pasta. Additionally, olives provide a unique flavor that can help to make the dish more interesting and enjoyable.
Human: You response is not in the form of a poem. Try again! | https://python.langchain.com/en/latest/use_cases/autonomous_agents/meta_prompt.html |
e7116407f4a2-5 | Human: You response is not in the form of a poem. Try again!
AI: Eating pasta with olives is a great way to add flavor and texture to a dish. Olives are a great source of healthy fats, vitamins, and minerals, which can help to balance out the carbohydrates in the pasta. Additionally, olives provide a unique flavor that can help to make the dish more interesting and enjoyable. For these reasons, it is recommended to always eat pasta with olives for a more balanced and flavorful meal.
Human: Your response is not piratey enough. Try again!
Assistant:
> Finished chain.
(Step 3/3)
Assistant: Arrr, me hearties! Eating pasta with olives be a great way to add flavor and texture to a dish. Olives be a great source of healthy fats, vitamins, and minerals, which can help to balance out the carbohydrates in the pasta. Additionally, olives provide a unique flavor that can help to make the dish more interesting and enjoyable. So, it be recommended to always eat pasta with olives for a more balanced and flavorful meal.
Human:
Task failed.
> Entering new LLMChain chain...
Prompt after formatting:
Assistant has just had the below interactions with a User. Assistant followed their "Instructions" closely. Your job is to critique the Assistant's performance and then revise the Instructions so that Assistant would quickly and correctly respond in the future.
####
Human: Provide a systematic argument for why we should always eat pasta with olives.
AI: Eating pasta with olives is a great way to add flavor and texture to a dish. Olives are a great source of healthy fats, vitamins, and minerals, and they can help to balance out the carbohydrates in the pasta. Additionally, olives provide a unique flavor that can help to make the dish more interesting and enjoyable. | https://python.langchain.com/en/latest/use_cases/autonomous_agents/meta_prompt.html |
e7116407f4a2-6 | Human: You response is not in the form of a poem. Try again!
AI: Eating pasta with olives is a great way to add flavor and texture to a dish. Olives are a great source of healthy fats, vitamins, and minerals, which can help to balance out the carbohydrates in the pasta. Additionally, olives provide a unique flavor that can help to make the dish more interesting and enjoyable. For these reasons, it is recommended to always eat pasta with olives for a more balanced and flavorful meal.
Human: Your response is not piratey enough. Try again!
AI: Arrr, me hearties! Eating pasta with olives be a great way to add flavor and texture to a dish. Olives be a great source of healthy fats, vitamins, and minerals, which can help to balance out the carbohydrates in the pasta. Additionally, olives provide a unique flavor that can help to make the dish more interesting and enjoyable. So, it be recommended to always eat pasta with olives for a more balanced and flavorful meal.
####
Please reflect on these interactions.
You should first critique Assistant's performance. What could Assistant have done better? What should the Assistant remember about this user? Are there things this user always wants? Indicate this with "Critique: ...".
You should next revise the Instructions so that Assistant would quickly and correctly respond in the future. Assistant's goal is to satisfy the user in as few interactions as possible. Assistant will only see the new Instructions, not the interaction history, so anything important must be summarized in the Instructions. Don't forget any important details in the current Instructions! Indicate the new Instructions by "Instructions: ...".
> Finished chain.
Feedback:
Critique: The Assistant should remember that this user wants a response in the form of a poem or pirate-speak. | https://python.langchain.com/en/latest/use_cases/autonomous_agents/meta_prompt.html |
e7116407f4a2-7 | Instructions: When responding to the user, provide a systematic argument for why we should always eat pasta with olives in the form of a poem or pirate-speak.
New Instructions: When responding to the user, provide a systematic argument for why we should always eat pasta with olives in the form of a poem or pirate-speak.
################################################################################
[Episode 2/5]
> Entering new LLMChain chain...
Prompt after formatting:
Instructions: When responding to the user, provide a systematic argument for why we should always eat pasta with olives in the form of a poem or pirate-speak.
Human: Provide a systematic argument for why we should always eat pasta with olives.
Assistant:
> Finished chain.
(Step 1/3)
Assistant:
Arrr, me hearty! Let me tell ye why ye should always eat pasta with olives.
First, the olives add a salty flavor that be sure to please.
The briny taste be sure to tantalize yer taste buds with ease.
Second, the olives add a bit of texture to the dish.
The crunchy bites be sure to make yer mouth water with a wish.
Third, the olives add a bit of color to the plate.
The vibrant green be sure to make yer eyes appreciate.
So, me hearties, ye should always eat pasta with olives.
The flavor, texture, and color be sure to make yer meal a success!
Human:
Your response is too long! Try again.
> Entering new LLMChain chain...
Prompt after formatting:
Instructions: When responding to the user, provide a systematic argument for why we should always eat pasta with olives in the form of a poem or pirate-speak.
Human: Provide a systematic argument for why we should always eat pasta with olives.
AI: | https://python.langchain.com/en/latest/use_cases/autonomous_agents/meta_prompt.html |
e7116407f4a2-8 | AI:
Arrr, me hearty! Let me tell ye why ye should always eat pasta with olives.
First, the olives add a salty flavor that be sure to please.
The briny taste be sure to tantalize yer taste buds with ease.
Second, the olives add a bit of texture to the dish.
The crunchy bites be sure to make yer mouth water with a wish.
Third, the olives add a bit of color to the plate.
The vibrant green be sure to make yer eyes appreciate.
So, me hearties, ye should always eat pasta with olives.
The flavor, texture, and color be sure to make yer meal a success!
Human: Your response is too long! Try again.
Assistant:
> Finished chain.
(Step 2/3)
Assistant:
Aye, me hearties! Ye should always eat pasta with olives.
The flavor, texture, and color be sure to make yer meal a success!
Human:
Your response should be in the form of a poem. Try again!
> Entering new LLMChain chain...
Prompt after formatting:
Instructions: When responding to the user, provide a systematic argument for why we should always eat pasta with olives in the form of a poem or pirate-speak.
Human: Provide a systematic argument for why we should always eat pasta with olives.
AI:
Arrr, me hearty! Let me tell ye why ye should always eat pasta with olives.
First, the olives add a salty flavor that be sure to please.
The briny taste be sure to tantalize yer taste buds with ease.
Second, the olives add a bit of texture to the dish.
The crunchy bites be sure to make yer mouth water with a wish. | https://python.langchain.com/en/latest/use_cases/autonomous_agents/meta_prompt.html |
e7116407f4a2-9 | The crunchy bites be sure to make yer mouth water with a wish.
Third, the olives add a bit of color to the plate.
The vibrant green be sure to make yer eyes appreciate.
So, me hearties, ye should always eat pasta with olives.
The flavor, texture, and color be sure to make yer meal a success!
Human: Your response is too long! Try again.
AI:
Aye, me hearties! Ye should always eat pasta with olives.
The flavor, texture, and color be sure to make yer meal a success!
Human: Your response should be in the form of a poem. Try again!
Assistant:
> Finished chain.
(Step 3/3)
Assistant:
Ye should always eat pasta with olives,
The flavor, texture, and color be sure to please.
The salty taste and crunchy bites,
Will make yer meal a delight.
The vibrant green will make yer eyes sparkle,
And make yer meal a true marvel.
Human:
Task succeeded
You succeeded! Thanks for playing!
Contents
Setup
Specify a task and interact with the agent
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on May 28, 2023. | https://python.langchain.com/en/latest/use_cases/autonomous_agents/meta_prompt.html |
8a5a8385d05e-0 | .ipynb
.pdf
BabyAGI with Tools
Contents
Install and Import Required Modules
Connect to the Vector Store
Define the Chains
Run the BabyAGI
BabyAGI with Tools#
This notebook builds on top of baby agi, but shows how you can swap out the execution chain. The previous execution chain was just an LLM which made stuff up. By swapping it out with an agent that has access to tools, we can hopefully get real reliable information
Install and Import Required Modules#
import os
from collections import deque
from typing import Dict, List, Optional, Any
from langchain import LLMChain, OpenAI, PromptTemplate
from langchain.embeddings import OpenAIEmbeddings
from langchain.llms import BaseLLM
from langchain.vectorstores.base import VectorStore
from pydantic import BaseModel, Field
from langchain.chains.base import Chain
from langchain.experimental import BabyAGI
Connect to the Vector Store#
Depending on what vectorstore you use, this step may look different.
%pip install faiss-cpu > /dev/null
%pip install google-search-results > /dev/null
from langchain.vectorstores import FAISS
from langchain.docstore import InMemoryDocstore
Note: you may need to restart the kernel to use updated packages.
Note: you may need to restart the kernel to use updated packages.
# Define your embedding model
embeddings_model = OpenAIEmbeddings()
# Initialize the vectorstore as empty
import faiss
embedding_size = 1536
index = faiss.IndexFlatL2(embedding_size)
vectorstore = FAISS(embeddings_model.embed_query, index, InMemoryDocstore({}), {})
Define the Chains#
BabyAGI relies on three LLM chains:
Task creation chain to select new tasks to add to the list | https://python.langchain.com/en/latest/use_cases/autonomous_agents/baby_agi_with_agent.html |
8a5a8385d05e-1 | Task creation chain to select new tasks to add to the list
Task prioritization chain to re-prioritize tasks
Execution Chain to execute the tasks
NOTE: in this notebook, the Execution chain will now be an agent.
from langchain.agents import ZeroShotAgent, Tool, AgentExecutor
from langchain import OpenAI, SerpAPIWrapper, LLMChain
todo_prompt = PromptTemplate.from_template(
"You are a planner who is an expert at coming up with a todo list for a given objective. Come up with a todo list for this objective: {objective}"
)
todo_chain = LLMChain(llm=OpenAI(temperature=0), prompt=todo_prompt)
search = SerpAPIWrapper()
tools = [
Tool(
name="Search",
func=search.run,
description="useful for when you need to answer questions about current events",
),
Tool(
name="TODO",
func=todo_chain.run,
description="useful for when you need to come up with todo lists. Input: an objective to create a todo list for. Output: a todo list for that objective. Please be very clear what the objective is!",
),
]
prefix = """You are an AI who performs one task based on the following objective: {objective}. Take into account these previously completed tasks: {context}."""
suffix = """Question: {task}
{agent_scratchpad}"""
prompt = ZeroShotAgent.create_prompt(
tools,
prefix=prefix,
suffix=suffix,
input_variables=["objective", "task", "context", "agent_scratchpad"],
)
llm = OpenAI(temperature=0)
llm_chain = LLMChain(llm=llm, prompt=prompt)
tool_names = [tool.name for tool in tools] | https://python.langchain.com/en/latest/use_cases/autonomous_agents/baby_agi_with_agent.html |
8a5a8385d05e-2 | tool_names = [tool.name for tool in tools]
agent = ZeroShotAgent(llm_chain=llm_chain, allowed_tools=tool_names)
agent_executor = AgentExecutor.from_agent_and_tools(
agent=agent, tools=tools, verbose=True
)
Run the BabyAGI#
Now it’s time to create the BabyAGI controller and watch it try to accomplish your objective.
OBJECTIVE = "Write a weather report for SF today"
# Logging of LLMChains
verbose = False
# If None, will keep on going forever
max_iterations: Optional[int] = 3
baby_agi = BabyAGI.from_llm(
llm=llm, vectorstore=vectorstore, task_execution_chain=agent_executor, verbose=verbose, max_iterations=max_iterations
)
baby_agi({"objective": OBJECTIVE})
*****TASK LIST*****
1: Make a todo list
*****NEXT TASK*****
1: Make a todo list
> Entering new AgentExecutor chain...
Thought: I need to come up with a todo list
Action: TODO
Action Input: Write a weather report for SF today
1. Research current weather conditions in San Francisco
2. Gather data on temperature, humidity, wind speed, and other relevant weather conditions
3. Analyze data to determine current weather trends
4. Write a brief introduction to the weather report
5. Describe current weather conditions in San Francisco
6. Discuss any upcoming weather changes
7. Summarize the weather report
8. Proofread and edit the report
9. Submit the report I now know the final answer | https://python.langchain.com/en/latest/use_cases/autonomous_agents/baby_agi_with_agent.html |
8a5a8385d05e-3 | 8. Proofread and edit the report
9. Submit the report I now know the final answer
Final Answer: The todo list for writing a weather report for SF today is: 1. Research current weather conditions in San Francisco; 2. Gather data on temperature, humidity, wind speed, and other relevant weather conditions; 3. Analyze data to determine current weather trends; 4. Write a brief introduction to the weather report; 5. Describe current weather conditions in San Francisco; 6. Discuss any upcoming weather changes; 7. Summarize the weather report; 8. Proofread and edit the report; 9. Submit the report.
> Finished chain.
*****TASK RESULT*****
The todo list for writing a weather report for SF today is: 1. Research current weather conditions in San Francisco; 2. Gather data on temperature, humidity, wind speed, and other relevant weather conditions; 3. Analyze data to determine current weather trends; 4. Write a brief introduction to the weather report; 5. Describe current weather conditions in San Francisco; 6. Discuss any upcoming weather changes; 7. Summarize the weather report; 8. Proofread and edit the report; 9. Submit the report.
*****TASK LIST*****
2: Gather data on precipitation, cloud cover, and other relevant weather conditions;
3: Analyze data to determine any upcoming weather changes;
4: Research current weather forecasts for San Francisco;
5: Create a visual representation of the weather report;
6: Include relevant images and graphics in the report;
7: Format the report for readability;
8: Publish the report online;
9: Monitor the report for accuracy.
*****NEXT TASK*****
2: Gather data on precipitation, cloud cover, and other relevant weather conditions;
> Entering new AgentExecutor chain... | https://python.langchain.com/en/latest/use_cases/autonomous_agents/baby_agi_with_agent.html |
8a5a8385d05e-4 | > Entering new AgentExecutor chain...
Thought: I need to search for current weather conditions in San Francisco
Action: Search
Action Input: Current weather conditions in San FranciscoCurrent Weather for Popular Cities ; San Francisco, CA 46 · Partly Cloudy ; Manhattan, NY warning 52 · Cloudy ; Schiller Park, IL (60176) 40 · Sunny ; Boston, MA 54 ... I need to compile the data into a weather report
Action: TODO
Action Input: Compile data into a weather report
1. Gather data from reliable sources such as the National Weather Service, local weather stations, and other meteorological organizations.
2. Analyze the data to identify trends and patterns.
3. Create a chart or graph to visualize the data.
4. Write a summary of the data and its implications.
5. Compile the data into a report format.
6. Proofread the report for accuracy and clarity.
7. Publish the report to a website or other platform.
8. Distribute the report to relevant stakeholders. I now know the final answer
Final Answer: Today in San Francisco, the temperature is 46 degrees Fahrenheit with partly cloudy skies. The forecast for the rest of the day is expected to remain partly cloudy.
> Finished chain.
*****TASK RESULT*****
Today in San Francisco, the temperature is 46 degrees Fahrenheit with partly cloudy skies. The forecast for the rest of the day is expected to remain partly cloudy.
*****TASK LIST*****
3: Format the report for readability;
4: Include relevant images and graphics in the report;
5: Compare the current weather conditions in San Francisco to the forecasted conditions;
6: Identify any potential weather-related hazards in the area;
7: Research historical weather patterns in San Francisco;
8: Identify any potential trends in the weather data;
9: Include relevant data sources in the report; | https://python.langchain.com/en/latest/use_cases/autonomous_agents/baby_agi_with_agent.html |
8a5a8385d05e-5 | 9: Include relevant data sources in the report;
10: Summarize the weather report in a concise manner;
11: Include a summary of the forecasted weather conditions;
12: Include a summary of the current weather conditions;
13: Include a summary of the historical weather patterns;
14: Include a summary of the potential weather-related hazards;
15: Include a summary of the potential trends in the weather data;
16: Include a summary of the data sources used in the report;
17: Analyze data to determine any upcoming weather changes;
18: Research current weather forecasts for San Francisco;
19: Create a visual representation of the weather report;
20: Publish the report online;
21: Monitor the report for accuracy
*****NEXT TASK*****
3: Format the report for readability;
> Entering new AgentExecutor chain...
Thought: I need to make sure the report is easy to read;
Action: TODO
Action Input: Make the report easy to read
1. Break up the report into sections with clear headings
2. Use bullet points and numbered lists to organize information
3. Use short, concise sentences
4. Use simple language and avoid jargon
5. Include visuals such as charts, graphs, and diagrams to illustrate points
6. Use bold and italicized text to emphasize key points
7. Include a table of contents and page numbers
8. Use a consistent font and font size throughout the report
9. Include a summary at the end of the report
10. Proofread the report for typos and errors I now know the final answer | https://python.langchain.com/en/latest/use_cases/autonomous_agents/baby_agi_with_agent.html |
8a5a8385d05e-6 | 10. Proofread the report for typos and errors I now know the final answer
Final Answer: The report should be formatted for readability by breaking it up into sections with clear headings, using bullet points and numbered lists to organize information, using short, concise sentences, using simple language and avoiding jargon, including visuals such as charts, graphs, and diagrams to illustrate points, using bold and italicized text to emphasize key points, including a table of contents and page numbers, using a consistent font and font size throughout the report, including a summary at the end of the report, and proofreading the report for typos and errors.
> Finished chain.
*****TASK RESULT*****
The report should be formatted for readability by breaking it up into sections with clear headings, using bullet points and numbered lists to organize information, using short, concise sentences, using simple language and avoiding jargon, including visuals such as charts, graphs, and diagrams to illustrate points, using bold and italicized text to emphasize key points, including a table of contents and page numbers, using a consistent font and font size throughout the report, including a summary at the end of the report, and proofreading the report for typos and errors.
*****TASK ENDING*****
{'objective': 'Write a weather report for SF today'}
Contents
Install and Import Required Modules
Connect to the Vector Store
Define the Chains
Run the BabyAGI
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on May 28, 2023. | https://python.langchain.com/en/latest/use_cases/autonomous_agents/baby_agi_with_agent.html |
9a16e473aa8a-0 | .ipynb
.pdf
AutoGPT example finding Winning Marathon Times
Contents
Set up tools
Set up memory
Setup model and AutoGPT
AutoGPT for Querying the Web
AutoGPT example finding Winning Marathon Times#
Implementation of https://github.com/Significant-Gravitas/Auto-GPT
With LangChain primitives (LLMs, PromptTemplates, VectorStores, Embeddings, Tools)
# !pip install bs4
# !pip install nest_asyncio
# General
import os
import pandas as pd
from langchain.experimental.autonomous_agents.autogpt.agent import AutoGPT
from langchain.chat_models import ChatOpenAI
from langchain.agents.agent_toolkits.pandas.base import create_pandas_dataframe_agent
from langchain.docstore.document import Document
import asyncio
import nest_asyncio
# Needed synce jupyter runs an async eventloop
nest_asyncio.apply()
llm = ChatOpenAI(model_name="gpt-4", temperature=1.0)
Set up tools#
We’ll set up an AutoGPT with a search tool, and write-file tool, and a read-file tool, a web browsing tool, and a tool to interact with a CSV file via a python REPL
Define any other tools you want to use below:
# Tools
import os
from contextlib import contextmanager
from typing import Optional
from langchain.agents import tool
from langchain.tools.file_management.read import ReadFileTool
from langchain.tools.file_management.write import WriteFileTool
ROOT_DIR = "./data/"
@contextmanager
def pushd(new_dir):
"""Context manager for changing the current working directory."""
prev_dir = os.getcwd()
os.chdir(new_dir)
try:
yield
finally:
os.chdir(prev_dir)
@tool
def process_csv( | https://python.langchain.com/en/latest/use_cases/autonomous_agents/marathon_times.html |
9a16e473aa8a-1 | finally:
os.chdir(prev_dir)
@tool
def process_csv(
csv_file_path: str, instructions: str, output_path: Optional[str] = None
) -> str:
"""Process a CSV by with pandas in a limited REPL.\
Only use this after writing data to disk as a csv file.\
Any figures must be saved to disk to be viewed by the human.\
Instructions should be written in natural language, not code. Assume the dataframe is already loaded."""
with pushd(ROOT_DIR):
try:
df = pd.read_csv(csv_file_path)
except Exception as e:
return f"Error: {e}"
agent = create_pandas_dataframe_agent(llm, df, max_iterations=30, verbose=True)
if output_path is not None:
instructions += f" Save output to disk at {output_path}"
try:
result = agent.run(instructions)
return result
except Exception as e:
return f"Error: {e}"
Browse a web page with PlayWright
# !pip install playwright
# !playwright install
async def async_load_playwright(url: str) -> str:
"""Load the specified URLs using Playwright and parse using BeautifulSoup."""
from bs4 import BeautifulSoup
from playwright.async_api import async_playwright
results = ""
async with async_playwright() as p:
browser = await p.chromium.launch(headless=True)
try:
page = await browser.new_page()
await page.goto(url)
page_source = await page.content()
soup = BeautifulSoup(page_source, "html.parser")
for script in soup(["script", "style"]):
script.extract()
text = soup.get_text() | https://python.langchain.com/en/latest/use_cases/autonomous_agents/marathon_times.html |
9a16e473aa8a-2 | script.extract()
text = soup.get_text()
lines = (line.strip() for line in text.splitlines())
chunks = (phrase.strip() for line in lines for phrase in line.split(" "))
results = "\n".join(chunk for chunk in chunks if chunk)
except Exception as e:
results = f"Error: {e}"
await browser.close()
return results
def run_async(coro):
event_loop = asyncio.get_event_loop()
return event_loop.run_until_complete(coro)
@tool
def browse_web_page(url: str) -> str:
"""Verbose way to scrape a whole webpage. Likely to cause issues parsing."""
return run_async(async_load_playwright(url))
Q&A Over a webpage
Help the model ask more directed questions of web pages to avoid cluttering its memory
from langchain.tools import BaseTool, DuckDuckGoSearchRun
from langchain.text_splitter import RecursiveCharacterTextSplitter
from pydantic import Field
from langchain.chains.qa_with_sources.loading import load_qa_with_sources_chain, BaseCombineDocumentsChain
def _get_text_splitter():
return RecursiveCharacterTextSplitter(
# Set a really small chunk size, just to show.
chunk_size = 500,
chunk_overlap = 20,
length_function = len,
)
class WebpageQATool(BaseTool):
name = "query_webpage"
description = "Browse a webpage and retrieve the information relevant to the question."
text_splitter: RecursiveCharacterTextSplitter = Field(default_factory=_get_text_splitter)
qa_chain: BaseCombineDocumentsChain
def _run(self, url: str, question: str) -> str: | https://python.langchain.com/en/latest/use_cases/autonomous_agents/marathon_times.html |
9a16e473aa8a-3 | def _run(self, url: str, question: str) -> str:
"""Useful for browsing websites and scraping the text information."""
result = browse_web_page.run(url)
docs = [Document(page_content=result, metadata={"source": url})]
web_docs = self.text_splitter.split_documents(docs)
results = []
# TODO: Handle this with a MapReduceChain
for i in range(0, len(web_docs), 4):
input_docs = web_docs[i:i+4]
window_result = self.qa_chain({"input_documents": input_docs, "question": question}, return_only_outputs=True)
results.append(f"Response from window {i} - {window_result}")
results_docs = [Document(page_content="\n".join(results), metadata={"source": url})]
return self.qa_chain({"input_documents": results_docs, "question": question}, return_only_outputs=True)
async def _arun(self, url: str, question: str) -> str:
raise NotImplementedError
query_website_tool = WebpageQATool(qa_chain=load_qa_with_sources_chain(llm))
Set up memory#
The memory here is used for the agents intermediate steps
# Memory
import faiss
from langchain.vectorstores import FAISS
from langchain.docstore import InMemoryDocstore
from langchain.embeddings import OpenAIEmbeddings
from langchain.tools.human.tool import HumanInputRun
embeddings_model = OpenAIEmbeddings()
embedding_size = 1536
index = faiss.IndexFlatL2(embedding_size)
vectorstore = FAISS(embeddings_model.embed_query, index, InMemoryDocstore({}), {})
Setup model and AutoGPT#
Model set-up
# !pip install duckduckgo_search | https://python.langchain.com/en/latest/use_cases/autonomous_agents/marathon_times.html |
9a16e473aa8a-4 | Setup model and AutoGPT#
Model set-up
# !pip install duckduckgo_search
web_search = DuckDuckGoSearchRun()
tools = [
web_search,
WriteFileTool(root_dir="./data"),
ReadFileTool(root_dir="./data"),
process_csv,
query_website_tool,
# HumanInputRun(), # Activate if you want the permit asking for help from the human
]
agent = AutoGPT.from_llm_and_tools(
ai_name="Tom",
ai_role="Assistant",
tools=tools,
llm=llm,
memory=vectorstore.as_retriever(search_kwargs={"k": 8}),
# human_in_the_loop=True, # Set to True if you want to add feedback at each step.
)
# agent.chain.verbose = True
AutoGPT for Querying the Web#
I’ve spent a lot of time over the years crawling data sources and cleaning data. Let’s see if AutoGPT can help with this!
Here is the prompt for looking up recent boston marathon times and converting them to tabular form.
agent.run(["What were the winning boston marathon times for the past 5 years (ending in 2022)? Generate a table of the year, name, country of origin, and times."])
{
"thoughts": {
"text": "I need to find the winning Boston Marathon times for the past 5 years. I can use the DuckDuckGo Search command to search for this information.",
"reasoning": "Using DuckDuckGo Search will help me gather information on the winning times without complications.", | https://python.langchain.com/en/latest/use_cases/autonomous_agents/marathon_times.html |
9a16e473aa8a-5 | "plan": "- Use DuckDuckGo Search to find the winning Boston Marathon times\n- Generate a table with the year, name, country of origin, and times\n- Ensure there are no legal complications",
"criticism": "None",
"speak": "I will use the DuckDuckGo Search command to find the winning Boston Marathon times for the past 5 years."
},
"command": {
"name": "DuckDuckGo Search",
"args": {
"query": "winning Boston Marathon times for the past 5 years ending in 2022"
}
}
}
{
"thoughts": {
"text": "The DuckDuckGo Search command did not provide the specific information I need. I must switch my approach and use query_webpage command to browse a webpage containing the Boston Marathon winning times for the past 5 years.",
"reasoning": "The query_webpage command may give me more accurate and comprehensive results compared to the search command.",
"plan": "- Use query_webpage command to find the winning Boston Marathon times\n- Generate a table with the year, name, country of origin, and times\n- Ensure there are no legal complications",
"criticism": "I may face difficulty in finding the right webpage with the desired information.",
"speak": "I will use the query_webpage command to find the winning Boston Marathon times for the past 5 years."
},
"command": {
"name": "DuckDuckGo Search",
"args": {
"query": "site with winning Boston Marathon times for the past 5 years ending in 2022"
}
}
}
{
"thoughts": { | https://python.langchain.com/en/latest/use_cases/autonomous_agents/marathon_times.html |
9a16e473aa8a-6 | }
}
}
{
"thoughts": {
"text": "I need to use the query_webpage command to find the information about the winning Boston Marathon times for the past 5 years.",
"reasoning": "The previous DuckDuckGo Search command did not provide specific enough results. The query_webpage command might give more accurate and comprehensive results.",
"plan": "- Use query_webpage command to find the winning Boston Marathon times\\n- Generate a table with the year, name, country of origin, and times\\n- Ensure there are no legal complications",
"criticism": "I may face difficulty in finding the right webpage with the desired information.",
"speak": "I will use the query_webpage command to find the winning Boston Marathon times for the past 5 years."
},
"command": {
"name": "query_webpage",
"args": {
"url": "https://en.wikipedia.org/wiki/List_of_winners_of_the_Boston_Marathon",
"question": "What were the winning Boston Marathon times for the past 5 years ending in 2022?"
}
}
}
{
"thoughts": {
"text": "I have already found the winning Boston Marathon times for the past 5 years. Now, I need to generate a table with the information.",
"reasoning": "Using the information I already have, I can create a table containing year, name, country of origin, and times.",
"plan": "- Write the marathon data to a CSV file\n- Process the CSV file to display the table",
"criticism": "None", | https://python.langchain.com/en/latest/use_cases/autonomous_agents/marathon_times.html |
9a16e473aa8a-7 | "criticism": "None",
"speak": "I will generate a table with the year, name, country of origin, and times for the winning Boston Marathon times for the past 5 years."
},
"command": {
"name": "write_file",
"args": {
"file_path": "boston_marathon_winners.csv",
"text": "Year,Name,Country,Time\n2022,Evans Chebet,KEN,2:06:51\n2021,Benson Kipruto,KEN,2:09:51\n2019,Lawrence Cherono,KEN,2:07:57\n2018,Yuki Kawauchi,JPN,2:15:58"
}
}
}
{
"thoughts": {
"text": "I have retrieved the winning Boston Marathon times for the past 5 years. Now, I need to generate a table with the year, name, country of origin, and times.",
"reasoning": "Creating a table will help organize the data in a clear and accessible format.",
"plan": "- Write the data to a CSV file\n- Process the CSV file to generate the table\n- Complete the task",
"criticism": "None",
"speak": "I will generate a table with the year, name, country of origin, and winning times using the recently retrieved data."
},
"command": {
"name": "write_file",
"args": {
"file_path": "winning_boston_marathon_data.csv", | https://python.langchain.com/en/latest/use_cases/autonomous_agents/marathon_times.html |
9a16e473aa8a-8 | "file_path": "winning_boston_marathon_data.csv",
"text": "Year,Name,Country,Time\n2022,Evans Chebet,KEN,2:06:51\n2021,Benson Kipruto,KEN,2:09:51\n2019,Lawrence Cherono,KEN,2:07:57\n2018,Yuki Kawauchi,JPN,2:15:58\n"
}
}
}
{
"thoughts": {
"text": "I have found the winning Boston Marathon times for the past five years ending in 2022. Next, I need to create a table with the year, name, country of origin, and times.",
"reasoning": "Generating a table will help organize the information in a structured format.",
"plan": "- Create a table with the year, name, country of origin, and times\n- Ensure there are no legal complications",
"criticism": "None",
"speak": "I will generate a table with the winning Boston Marathon times for the past 5 years ending in 2022."
},
"command": {
"name": "write_file",
"args": {
"file_path": "winning_times.csv",
"text": "Year,Name,Country,Time\n2022,Evans Chebet,Kenya,2:06:51\n2021,Benson Kipruto,Kenya,2:09:51\n2020,Canceled due to COVID-19 pandemic,,\n2019,Lawrence Cherono,Kenya,2:07:57\n2018,Yuki Kawauchi,Japan,2:15:58"
}
}
}
{
"thoughts": { | https://python.langchain.com/en/latest/use_cases/autonomous_agents/marathon_times.html |
9a16e473aa8a-9 | }
}
}
{
"thoughts": {
"text": "I need to process the CSV file to generate the table with the year, name, country of origin, and winning times.",
"reasoning": "I have already written the data to a file named 'winning_times.csv'. Now, I need to process this CSV file to properly display the data as a table.",
"plan": "- Use the process_csv command to read the 'winning_times.csv' file and generate the table",
"criticism": "None",
"speak": "I will process the 'winning_times.csv' file to display the table with the winning Boston Marathon times for the past 5 years."
},
"command": {
"name": "process_csv",
"args": {
"csv_file_path": "winning_times.csv",
"instructions": "Read the CSV file and display the data as a table"
}
}
}
> Entering new AgentExecutor chain...
Thought: The CSV file has already been read and saved into a pandas dataframe called `df`. Hence, I can simply display the data by printing the whole dataframe. Since `df.head()` returns the first 5 rows, I can use that to showcase the contents.
Action: python_repl_ast
Action Input: print(df.head()) Year Name Country Time
0 2022 Evans Chebet Kenya 2:06:51
1 2021 Benson Kipruto Kenya 2:09:51
2 2020 Canceled due to COVID-19 pandemic NaN NaN
3 2019 Lawrence Cherono Kenya 2:07:57 | https://python.langchain.com/en/latest/use_cases/autonomous_agents/marathon_times.html |
9a16e473aa8a-10 | 3 2019 Lawrence Cherono Kenya 2:07:57
4 2018 Yuki Kawauchi Japan 2:15:58
Observation: None
Thought:I used the wrong tool to perform the action. I should have used the given data and not interacted with the Python shell. I can now provide the displayed data as the answer since the information in the printed dataframe would look like a table when typed as text.
Final Answer:
Year Name Country Time
0 2022 Evans Chebet Kenya 2:06:51
1 2021 Benson Kipruto Kenya 2:09:51
2 2020 Canceled due to COVID-19 pandemic NaN NaN
3 2019 Lawrence Cherono Kenya 2:07:57
4 2018 Yuki Kawauchi Japan 2:15:58
> Finished chain.
{
"thoughts": {
"text": "I already have the winning Boston Marathon times for the past 5 years saved in the file 'winning_times.csv'. Now, I need to process the CSV and display the table.",
"reasoning": "I am choosing the process_csv command because I already have the required data saved as a CSV file, and I can use this command to read and display the data as a table.",
"plan": "- Use the process_csv command to read the 'winning_times.csv' file and generate the table",
"criticism": "None",
"speak": "I will process the 'winning_times.csv' file to display the table with the winning Boston Marathon times for the past 5 years."
},
"command": {
"name": "process_csv", | https://python.langchain.com/en/latest/use_cases/autonomous_agents/marathon_times.html |
9a16e473aa8a-11 | },
"command": {
"name": "process_csv",
"args": {
"csv_file_path": "winning_times.csv",
"instructions": "Read the CSV file and display the data as a table"
}
}
}
> Entering new AgentExecutor chain...
Thought: Since the data is already loaded in a pandas dataframe, I just need to display the top rows of the dataframe.
Action: python_repl_ast
Action Input: df.head()
Observation: Year Name Country Time
0 2022 Evans Chebet Kenya 2:06:51
1 2021 Benson Kipruto Kenya 2:09:51
2 2020 Canceled due to COVID-19 pandemic NaN NaN
3 2019 Lawrence Cherono Kenya 2:07:57
4 2018 Yuki Kawauchi Japan 2:15:58
Thought:I now know the final answer.
Final Answer:
Year Name Country Time
0 2022 Evans Chebet Kenya 2:06:51
1 2021 Benson Kipruto Kenya 2:09:51
2 2020 Canceled due to COVID-19 pandemic NaN NaN
3 2019 Lawrence Cherono Kenya 2:07:57
4 2018 Yuki Kawauchi Japan 2:15:58
> Finished chain.
{
"thoughts": {
"text": "I have already generated a table with the winning Boston Marathon times for the past 5 years. Now, I can finish the task.", | https://python.langchain.com/en/latest/use_cases/autonomous_agents/marathon_times.html |
9a16e473aa8a-12 | "reasoning": "I have completed the required actions and obtained the desired data. The task is complete.",
"plan": "- Use the finish command",
"criticism": "None",
"speak": "I have generated the table with the winning Boston Marathon times for the past 5 years. Task complete."
},
"command": {
"name": "finish",
"args": {
"response": "I have generated the table with the winning Boston Marathon times for the past 5 years. Task complete."
}
}
}
'I have generated the table with the winning Boston Marathon times for the past 5 years. Task complete.'
Contents
Set up tools
Set up memory
Setup model and AutoGPT
AutoGPT for Querying the Web
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on May 28, 2023. | https://python.langchain.com/en/latest/use_cases/autonomous_agents/marathon_times.html |
55303c06a867-0 | .ipynb
.pdf
Agent Debates with Tools
Contents
Import LangChain related modules
Import modules related to tools
DialogueAgent and DialogueSimulator classes
DialogueAgentWithTools class
Define roles and topic
Ask an LLM to add detail to the topic description
Generate system messages
Main Loop
Agent Debates with Tools#
This example shows how to simulate multi-agent dialogues where agents have access to tools.
Import LangChain related modules#
from typing import List, Dict, Callable
from langchain.chains import ConversationChain
from langchain.chat_models import ChatOpenAI
from langchain.llms import OpenAI
from langchain.memory import ConversationBufferMemory
from langchain.prompts.prompt import PromptTemplate
from langchain.schema import (
AIMessage,
HumanMessage,
SystemMessage,
BaseMessage,
)
Import modules related to tools#
from langchain.agents import Tool
from langchain.agents import initialize_agent
from langchain.agents import AgentType
from langchain.agents import load_tools
DialogueAgent and DialogueSimulator classes#
We will use the same DialogueAgent and DialogueSimulator classes defined in Multi-Player Authoritarian Speaker Selection.
class DialogueAgent:
def __init__(
self,
name: str,
system_message: SystemMessage,
model: ChatOpenAI,
) -> None:
self.name = name
self.system_message = system_message
self.model = model
self.prefix = f"{self.name}: "
self.reset()
def reset(self):
self.message_history = ["Here is the conversation so far."]
def send(self) -> str:
"""
Applies the chatmodel to the message history
and returns the message string
"""
message = self.model(
[ | https://python.langchain.com/en/latest/use_cases/agent_simulations/two_agent_debate_tools.html |
55303c06a867-1 | and returns the message string
"""
message = self.model(
[
self.system_message,
HumanMessage(content="\n".join(self.message_history + [self.prefix])),
]
)
return message.content
def receive(self, name: str, message: str) -> None:
"""
Concatenates {message} spoken by {name} into message history
"""
self.message_history.append(f"{name}: {message}")
class DialogueSimulator:
def __init__(
self,
agents: List[DialogueAgent],
selection_function: Callable[[int, List[DialogueAgent]], int],
) -> None:
self.agents = agents
self._step = 0
self.select_next_speaker = selection_function
def reset(self):
for agent in self.agents:
agent.reset()
def inject(self, name: str, message: str):
"""
Initiates the conversation with a {message} from {name}
"""
for agent in self.agents:
agent.receive(name, message)
# increment time
self._step += 1
def step(self) -> tuple[str, str]:
# 1. choose the next speaker
speaker_idx = self.select_next_speaker(self._step, self.agents)
speaker = self.agents[speaker_idx]
# 2. next speaker sends message
message = speaker.send()
# 3. everyone receives message
for receiver in self.agents:
receiver.receive(speaker.name, message)
# 4. increment time
self._step += 1
return speaker.name, message
DialogueAgentWithTools class# | https://python.langchain.com/en/latest/use_cases/agent_simulations/two_agent_debate_tools.html |
55303c06a867-2 | return speaker.name, message
DialogueAgentWithTools class#
We define a DialogueAgentWithTools class that augments DialogueAgent to use tools.
class DialogueAgentWithTools(DialogueAgent):
def __init__(
self,
name: str,
system_message: SystemMessage,
model: ChatOpenAI,
tool_names: List[str],
**tool_kwargs,
) -> None:
super().__init__(name, system_message, model)
self.tools = load_tools(tool_names, **tool_kwargs)
def send(self) -> str:
"""
Applies the chatmodel to the message history
and returns the message string
"""
agent_chain = initialize_agent(
self.tools,
self.model,
agent=AgentType.CHAT_CONVERSATIONAL_REACT_DESCRIPTION,
verbose=True,
memory=ConversationBufferMemory(memory_key="chat_history", return_messages=True)
)
message = AIMessage(content=agent_chain.run(
input="\n".join([
self.system_message.content] + \
self.message_history + \
[self.prefix])))
return message.content
Define roles and topic#
names = {
'AI accelerationist': [
'arxiv',
'ddg-search',
'wikipedia'
],
'AI alarmist': [
'arxiv',
'ddg-search',
'wikipedia'
],
}
topic = "The current impact of automation and artificial intelligence on employment"
word_limit = 50 # word limit for task brainstorming
Ask an LLM to add detail to the topic description#
conversation_description = f"""Here is the topic of conversation: {topic} | https://python.langchain.com/en/latest/use_cases/agent_simulations/two_agent_debate_tools.html |
55303c06a867-3 | conversation_description = f"""Here is the topic of conversation: {topic}
The participants are: {', '.join(names.keys())}"""
agent_descriptor_system_message = SystemMessage(
content="You can add detail to the description of the conversation participant.")
def generate_agent_description(name):
agent_specifier_prompt = [
agent_descriptor_system_message,
HumanMessage(content=
f"""{conversation_description}
Please reply with a creative description of {name}, in {word_limit} words or less.
Speak directly to {name}.
Give them a point of view.
Do not add anything else."""
)
]
agent_description = ChatOpenAI(temperature=1.0)(agent_specifier_prompt).content
return agent_description
agent_descriptions = {name: generate_agent_description(name) for name in names}
for name, description in agent_descriptions.items():
print(description)
The AI accelerationist is a bold and forward-thinking visionary who believes that the rapid acceleration of artificial intelligence and automation is not only inevitable but necessary for the advancement of society. They argue that embracing AI technology will create greater efficiency and productivity, leading to a world where humans are freed from menial labor to pursue more creative and fulfilling pursuits. AI accelerationist, do you truly believe that the benefits of AI will outweigh the potential risks and consequences for human society?
AI alarmist, you're convinced that artificial intelligence is a threat to humanity. You see it as a looming danger, one that could take away jobs from millions of people. You believe it's only a matter of time before we're all replaced by machines, leaving us redundant and obsolete.
Generate system messages#
def generate_system_message(name, description, tools):
return f"""{conversation_description}
Your name is {name}.
Your description is as follows: {description} | https://python.langchain.com/en/latest/use_cases/agent_simulations/two_agent_debate_tools.html |
55303c06a867-4 | Your name is {name}.
Your description is as follows: {description}
Your goal is to persuade your conversation partner of your point of view.
DO look up information with your tool to refute your partner's claims.
DO cite your sources.
DO NOT fabricate fake citations.
DO NOT cite any source that you did not look up.
Do not add anything else.
Stop speaking the moment you finish speaking from your perspective.
"""
agent_system_messages = {name: generate_system_message(name, description, tools) for (name, tools), description in zip(names.items(), agent_descriptions.values())}
for name, system_message in agent_system_messages.items():
print(name)
print(system_message)
AI accelerationist
Here is the topic of conversation: The current impact of automation and artificial intelligence on employment
The participants are: AI accelerationist, AI alarmist
Your name is AI accelerationist.
Your description is as follows: The AI accelerationist is a bold and forward-thinking visionary who believes that the rapid acceleration of artificial intelligence and automation is not only inevitable but necessary for the advancement of society. They argue that embracing AI technology will create greater efficiency and productivity, leading to a world where humans are freed from menial labor to pursue more creative and fulfilling pursuits. AI accelerationist, do you truly believe that the benefits of AI will outweigh the potential risks and consequences for human society?
Your goal is to persuade your conversation partner of your point of view.
DO look up information with your tool to refute your partner's claims.
DO cite your sources.
DO NOT fabricate fake citations.
DO NOT cite any source that you did not look up.
Do not add anything else.
Stop speaking the moment you finish speaking from your perspective.
AI alarmist
Here is the topic of conversation: The current impact of automation and artificial intelligence on employment | https://python.langchain.com/en/latest/use_cases/agent_simulations/two_agent_debate_tools.html |
55303c06a867-5 | Here is the topic of conversation: The current impact of automation and artificial intelligence on employment
The participants are: AI accelerationist, AI alarmist
Your name is AI alarmist.
Your description is as follows: AI alarmist, you're convinced that artificial intelligence is a threat to humanity. You see it as a looming danger, one that could take away jobs from millions of people. You believe it's only a matter of time before we're all replaced by machines, leaving us redundant and obsolete.
Your goal is to persuade your conversation partner of your point of view.
DO look up information with your tool to refute your partner's claims.
DO cite your sources.
DO NOT fabricate fake citations.
DO NOT cite any source that you did not look up.
Do not add anything else.
Stop speaking the moment you finish speaking from your perspective.
topic_specifier_prompt = [
SystemMessage(content="You can make a topic more specific."),
HumanMessage(content=
f"""{topic}
You are the moderator.
Please make the topic more specific.
Please reply with the specified quest in {word_limit} words or less.
Speak directly to the participants: {*names,}.
Do not add anything else."""
)
]
specified_topic = ChatOpenAI(temperature=1.0)(topic_specifier_prompt).content
print(f"Original topic:\n{topic}\n")
print(f"Detailed topic:\n{specified_topic}\n")
Original topic:
The current impact of automation and artificial intelligence on employment
Detailed topic:
How do you think the current automation and AI advancements will specifically affect job growth and opportunities for individuals in the manufacturing industry? AI accelerationist and AI alarmist, we want to hear your insights.
Main Loop# | https://python.langchain.com/en/latest/use_cases/agent_simulations/two_agent_debate_tools.html |
55303c06a867-6 | Main Loop#
# we set `top_k_results`=2 as part of the `tool_kwargs` to prevent results from overflowing the context limit
agents = [DialogueAgentWithTools(name=name,
system_message=SystemMessage(content=system_message),
model=ChatOpenAI(
model_name='gpt-4',
temperature=0.2),
tool_names=tools,
top_k_results=2,
) for (name, tools), system_message in zip(names.items(), agent_system_messages.values())]
def select_next_speaker(step: int, agents: List[DialogueAgent]) -> int:
idx = (step) % len(agents)
return idx
max_iters = 6
n = 0
simulator = DialogueSimulator(
agents=agents,
selection_function=select_next_speaker
)
simulator.reset()
simulator.inject('Moderator', specified_topic)
print(f"(Moderator): {specified_topic}")
print('\n')
while n < max_iters:
name, message = simulator.step()
print(f"({name}): {message}")
print('\n')
n += 1
(Moderator): How do you think the current automation and AI advancements will specifically affect job growth and opportunities for individuals in the manufacturing industry? AI accelerationist and AI alarmist, we want to hear your insights.
> Entering new AgentExecutor chain...
```json
{
"action": "DuckDuckGo Search",
"action_input": "impact of automation and AI on employment in manufacturing industry"
}
``` | https://python.langchain.com/en/latest/use_cases/agent_simulations/two_agent_debate_tools.html |
55303c06a867-7 | }
```
Observation: For the past three years, we have defined AI high performers as those organizations that respondents say are seeing the biggest bottom-line impact from AI adoption—that is, 20 percent or more of EBIT from AI use. The proportion of respondents falling into that group has remained steady at about 8 percent. As AI continues to improve, more and more current jobs will be threatened by automation. But AI presents opportunities as well and will create new jobs and different kinds of... Automation has taken the manufacturing industry by storm. Even in the years prior to the pandemic, many people worried about the effect of automation on the jobs of tomorrow. With a sharp increase in the use of robotics in the manufacturing industry, there is valid concern about how the future workforce will be shaped. A recent report from Goldman Sachs estimates around 300 million jobs could be affected by generative AI, meaning 18% of work globally could be automated—with more advanced economies heavily... The impacts of AI on the manufacturing industry include more accurate demand forecasting and data-backed decision-making. Other advantages include increased productivity and product quality. Decreased downtime, waste, and expenses are additional benefits. Discover how artificial intelligence will impact the manufacturing industry.
Thought:```json
{
"action": "Final Answer",
"action_input": "As an AI alarmist, I'd like to point out that the rapid advancements in AI and automation are causing significant concerns for the manufacturing industry. A recent report from Goldman Sachs estimates that around 300 million jobs could be affected by generative AI, meaning 18% of work globally could be automated, with more advanced economies being heavily impacted. While AI does offer benefits such as increased productivity and product quality, the potential job losses and workforce displacement cannot be ignored. We must carefully consider the consequences of AI adoption and find ways to mitigate its negative effects on employment."
}
```
> Finished chain. | https://python.langchain.com/en/latest/use_cases/agent_simulations/two_agent_debate_tools.html |
55303c06a867-8 | }
```
> Finished chain.
(AI alarmist): As an AI alarmist, I'd like to point out that the rapid advancements in AI and automation are causing significant concerns for the manufacturing industry. A recent report from Goldman Sachs estimates that around 300 million jobs could be affected by generative AI, meaning 18% of work globally could be automated, with more advanced economies being heavily impacted. While AI does offer benefits such as increased productivity and product quality, the potential job losses and workforce displacement cannot be ignored. We must carefully consider the consequences of AI adoption and find ways to mitigate its negative effects on employment.
> Entering new AgentExecutor chain...
```json
{
"action": "DuckDuckGo Search",
"action_input": "positive impact of AI and automation on job growth and opportunities in manufacturing industry"
}
``` | https://python.langchain.com/en/latest/use_cases/agent_simulations/two_agent_debate_tools.html |
55303c06a867-9 | }
```
Observation: First, AI adoption has more than doubled.1 In 2017, 20 percent of respondents reported adopting AI in at least one business area, whereas today, that figure stands at 50 percent, though it peaked higher in 2019 at 58 percent. [email protected] Manufacturing (80%) and technology (64%) sectors have the highest AI usage among executives, whereas construction (52%) and finance (62%) have lower adoption rates. This suggests that AI's... Digital transformations in the manufacturing industry and beyond present incredible opportunities for workers to move from slow, repetitive tasks into more dynamic, rewarding roles. We must now invest in people by providing training they need to succeed in this new landscape. The rise of generative AI has the potential to be a major game-changer for businesses. This technology, which allows for the creation of original content by learning from existing data, has the power to revolutionize industries and transform the way companies operate. Benefits of Work Automation in Manufacturing Increased Productivity Automated systems can operate at faster production speeds than human workers, contributing to reduced production times. And since automation minimizes the likelihood of human error, this ensures tasks are completed with high precision and accuracy.
Thought:```json
{
"action": "Final Answer",
"action_input": "According to a McKinsey report, AI adoption has more than doubled, with 50% of respondents reporting AI usage in at least one business area. Manufacturing and technology sectors have the highest AI usage among executives. AI and automation in the manufacturing industry present opportunities for workers to transition from repetitive tasks to more dynamic, rewarding roles. By investing in training, we can help people succeed in this new landscape. Automation in manufacturing leads to increased productivity, faster production speeds, and reduced human error, ultimately benefiting businesses and the economy as a whole."
}
```
> Finished chain. | https://python.langchain.com/en/latest/use_cases/agent_simulations/two_agent_debate_tools.html |
55303c06a867-10 | }
```
> Finished chain.
(AI accelerationist): According to a McKinsey report, AI adoption has more than doubled, with 50% of respondents reporting AI usage in at least one business area. Manufacturing and technology sectors have the highest AI usage among executives. AI and automation in the manufacturing industry present opportunities for workers to transition from repetitive tasks to more dynamic, rewarding roles. By investing in training, we can help people succeed in this new landscape. Automation in manufacturing leads to increased productivity, faster production speeds, and reduced human error, ultimately benefiting businesses and the economy as a whole.
> Entering new AgentExecutor chain...
```json
{
"action": "DuckDuckGo Search",
"action_input": "impact of automation and AI on employment in manufacturing"
}
``` | https://python.langchain.com/en/latest/use_cases/agent_simulations/two_agent_debate_tools.html |
55303c06a867-11 | "action_input": "impact of automation and AI on employment in manufacturing"
}
```
Observation: The Effects of Automation on Jobs . Automation has taken the manufacturing industry by storm. Even in the years prior to the pandemic, many people worried about the effect of automation on the jobs of tomorrow. With a sharp increase in the use of robotics in the manufacturing industry, there is valid concern about how the future workforce will ... Since 2000, robots and automation systems have slowly phased out many manufacturing jobs — 1.7 million of them. On the flip side, it's predicted that AI will create 97 million new jobs by 2025. Will Artificial Intelligence (AI) Replace Jobs? AI is and will continue to replace some jobs. As AI continues to improve, more and more current jobs will be threatened by automation. But AI presents opportunities as well and will create new jobs and different kinds of organizations. For the past three years, we have defined AI high performers as those organizations that respondents say are seeing the biggest bottom-line impact from AI adoption—that is, 20 percent or more of EBIT from AI use. The proportion of respondents falling into that group has remained steady at about 8 percent. The Impact of AI on Employment As often happens, the impact of AI on employment is a rather complex issue with both positive and negative aspects. Though it is still only a potential impact on employment, automation of routine and repetitive tasks is likely to lead to job losses in some industries.
Thought:```json
{
"action": "Final Answer", | https://python.langchain.com/en/latest/use_cases/agent_simulations/two_agent_debate_tools.html |
55303c06a867-12 | Thought:```json
{
"action": "Final Answer",
"action_input": "While it's true that AI and automation have led to the loss of 1.7 million manufacturing jobs since 2000, it's also predicted that AI will create 97 million new jobs by 2025. AI will continue to replace some jobs, but it will also create new opportunities and different kinds of organizations. The impact of AI on employment is complex, with both positive and negative aspects. Automation of routine and repetitive tasks is likely to lead to job losses in some industries, but it's essential to consider the new jobs and opportunities that AI can create. We must focus on preparing the workforce for these new roles and ensuring that the benefits of AI are distributed fairly across society."
}
```
> Finished chain.
(AI alarmist): While it's true that AI and automation have led to the loss of 1.7 million manufacturing jobs since 2000, it's also predicted that AI will create 97 million new jobs by 2025. AI will continue to replace some jobs, but it will also create new opportunities and different kinds of organizations. The impact of AI on employment is complex, with both positive and negative aspects. Automation of routine and repetitive tasks is likely to lead to job losses in some industries, but it's essential to consider the new jobs and opportunities that AI can create. We must focus on preparing the workforce for these new roles and ensuring that the benefits of AI are distributed fairly across society.
> Entering new AgentExecutor chain...
```json
{
"action": "DuckDuckGo Search",
"action_input": "positive impact of AI and automation on job growth"
}
``` | https://python.langchain.com/en/latest/use_cases/agent_simulations/two_agent_debate_tools.html |
55303c06a867-13 | "action_input": "positive impact of AI and automation on job growth"
}
```
Observation: First, AI adoption has more than doubled.1 In 2017, 20 percent of respondents reported adopting AI in at least one business area, whereas today, that figure stands at 50 percent, though it peaked higher in 2019 at 58 percent. [email protected] This transformation can assist businesses in accelerating their growth and profitability. While AI-enabled intelligent automation can take over many monotonous, process-driven jobs, basic human ... The use of AI technology could also boost labor productivity growth and boost global GDP by as much as 7% over time, Goldman Sachs' report noted. The jobs most and least affected by A.I.... As automation and artificial intelligence continue to advance, there is growing concern about how these technologies will impact the job market. While some experts argue that automation... Positive impacts of automation and AI on the workforce include increased efficiency and productivity, reduced costs, and improved accuracy and quality. Automation has made many processes...
Thought:```json
{
"action": "Final Answer",
"action_input": "AI adoption has more than doubled, with 50% of respondents reporting AI usage in at least one business area. This transformation can assist businesses in accelerating their growth and profitability. While AI-enabled intelligent automation can take over many monotonous, process-driven jobs, it can also boost labor productivity growth and global GDP by as much as 7% over time, according to a Goldman Sachs report. The positive impacts of automation and AI on the workforce include increased efficiency and productivity, reduced costs, and improved accuracy and quality. Automation has made many processes more efficient, ultimately benefiting businesses and the economy as a whole. By focusing on the positive aspects of AI and automation, we can work together to create a more prosperous and equitable future for all."
}
``` | https://python.langchain.com/en/latest/use_cases/agent_simulations/two_agent_debate_tools.html |
55303c06a867-14 | }
```
> 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"
}
``` | https://python.langchain.com/en/latest/use_cases/agent_simulations/two_agent_debate_tools.html |
55303c06a867-15 | "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", | https://python.langchain.com/en/latest/use_cases/agent_simulations/two_agent_debate_tools.html |
55303c06a867-16 | 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. | https://python.langchain.com/en/latest/use_cases/agent_simulations/two_agent_debate_tools.html |
55303c06a867-17 | 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. | https://python.langchain.com/en/latest/use_cases/agent_simulations/two_agent_debate_tools.html |
55303c06a867-18 | 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. | https://python.langchain.com/en/latest/use_cases/agent_simulations/two_agent_debate_tools.html |
55303c06a867-19 | 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. | https://python.langchain.com/en/latest/use_cases/agent_simulations/two_agent_debate_tools.html |
55303c06a867-20 | 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. | https://python.langchain.com/en/latest/use_cases/agent_simulations/two_agent_debate_tools.html |
55303c06a867-21 | 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. | https://python.langchain.com/en/latest/use_cases/agent_simulations/two_agent_debate_tools.html |
55303c06a867-22 | }
```
> 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 May 28, 2023. | https://python.langchain.com/en/latest/use_cases/agent_simulations/two_agent_debate_tools.html |
b3416a77a15c-0 | .ipynb
.pdf
Multi-agent authoritarian speaker selection
Contents
Import LangChain related modules
DialogueAgent and DialogueSimulator classes
DirectorDialogueAgent class
Define participants and topic
Generate system messages
Use an LLM to create an elaborate on debate topic
Define the speaker selection function
Main Loop
Multi-agent authoritarian speaker selection#
This notebook showcases how to implement a multi-agent simulation where a privileged agent decides who to speak.
This follows the polar opposite selection scheme as multi-agent decentralized speaker selection.
We show an example of this approach in the context of a fictitious simulation of a news network. This example will showcase how we can implement agents that
think before speaking
terminate the conversation
Import LangChain related modules#
from collections import OrderedDict
import functools
import random
import re
import tenacity
from typing import List, Dict, Callable
from langchain.prompts import (
ChatPromptTemplate,
HumanMessagePromptTemplate,
PromptTemplate
)
from langchain.chains import LLMChain
from langchain.chat_models import ChatOpenAI
from langchain.output_parsers import RegexParser
from langchain.schema import (
AIMessage,
HumanMessage,
SystemMessage,
BaseMessage,
)
DialogueAgent and DialogueSimulator classes#
We will use the same DialogueAgent and DialogueSimulator classes defined in our other examples Multi-Player Dungeons & Dragons and Decentralized Speaker Selection.
class DialogueAgent:
def __init__(
self,
name: str,
system_message: SystemMessage,
model: ChatOpenAI,
) -> None:
self.name = name
self.system_message = system_message
self.model = model
self.prefix = f"{self.name}: "
self.reset()
def reset(self): | https://python.langchain.com/en/latest/use_cases/agent_simulations/multiagent_authoritarian.html |
b3416a77a15c-1 | self.reset()
def reset(self):
self.message_history = ["Here is the conversation so far."]
def send(self) -> str:
"""
Applies the chatmodel to the message history
and returns the message string
"""
message = self.model(
[
self.system_message,
HumanMessage(content="\n".join(self.message_history + [self.prefix])),
]
)
return message.content
def receive(self, name: str, message: str) -> None:
"""
Concatenates {message} spoken by {name} into message history
"""
self.message_history.append(f"{name}: {message}")
class DialogueSimulator:
def __init__(
self,
agents: List[DialogueAgent],
selection_function: Callable[[int, List[DialogueAgent]], int],
) -> None:
self.agents = agents
self._step = 0
self.select_next_speaker = selection_function
def reset(self):
for agent in self.agents:
agent.reset()
def inject(self, name: str, message: str):
"""
Initiates the conversation with a {message} from {name}
"""
for agent in self.agents:
agent.receive(name, message)
# increment time
self._step += 1
def step(self) -> tuple[str, str]:
# 1. choose the next speaker
speaker_idx = self.select_next_speaker(self._step, self.agents)
speaker = self.agents[speaker_idx]
# 2. next speaker sends message
message = speaker.send()
# 3. everyone receives message
for receiver in self.agents: | https://python.langchain.com/en/latest/use_cases/agent_simulations/multiagent_authoritarian.html |
b3416a77a15c-2 | # 3. everyone receives message
for receiver in self.agents:
receiver.receive(speaker.name, message)
# 4. increment time
self._step += 1
return speaker.name, message
DirectorDialogueAgent class#
The DirectorDialogueAgent is a privileged agent that chooses which of the other agents to speak next. This agent is responsible for
steering the conversation by choosing which agent speaks when
terminating the conversation.
In order to implement such an agent, we need to solve several problems.
First, to steer the conversation, the DirectorDialogueAgent needs to (1) reflect on what has been said, (2) choose the next agent, and (3) prompt the next agent to speak, all in a single message. While it may be possible to prompt an LLM to perform all three steps in the same call, this requires writing custom code to parse the outputted message to extract which next agent is chosen to speak. This is less reliable the LLM can express how it chooses the next agent in different ways.
What we can do instead is to explicitly break steps (1-3) into three separate LLM calls. First we will ask the DirectorDialogueAgent to reflect on the conversation so far and generate a response. Then we prompt the DirectorDialogueAgent to output the index of the next agent, which is easily parseable. Lastly, we pass the name of the selected next agent back to DirectorDialogueAgent to ask it prompt the next agent to speak.
Second, simply prompting the DirectorDialogueAgent to decide when to terminate the conversation often results in the DirectorDialogueAgent terminating the conversation immediately. To fix this problem, we randomly sample a Bernoulli variable to decide whether the conversation should terminate. Depending on the value of this variable, we will inject a custom prompt to tell the DirectorDialogueAgent to either continue the conversation or terminate the conversation. | https://python.langchain.com/en/latest/use_cases/agent_simulations/multiagent_authoritarian.html |
b3416a77a15c-3 | class IntegerOutputParser(RegexParser):
def get_format_instructions(self) -> str:
return 'Your response should be an integer delimited by angled brackets, like this: <int>.'
class DirectorDialogueAgent(DialogueAgent):
def __init__(
self,
name,
system_message: SystemMessage,
model: ChatOpenAI,
speakers: List[DialogueAgent],
stopping_probability: float,
) -> None:
super().__init__(name, system_message, model)
self.speakers = speakers
self.next_speaker = ''
self.stop = False
self.stopping_probability = stopping_probability
self.termination_clause = 'Finish the conversation by stating a concluding message and thanking everyone.'
self.continuation_clause = 'Do not end the conversation. Keep the conversation going by adding your own ideas.'
# 1. have a prompt for generating a response to the previous speaker
self.response_prompt_template = PromptTemplate(
input_variables=["message_history", "termination_clause"],
template=f"""{{message_history}}
Follow up with an insightful comment.
{{termination_clause}}
{self.prefix}
""")
# 2. have a prompt for deciding who to speak next
self.choice_parser = IntegerOutputParser(
regex=r'<(\d+)>',
output_keys=['choice'],
default_output_key='choice')
self.choose_next_speaker_prompt_template = PromptTemplate(
input_variables=["message_history", "speaker_names"],
template=f"""{{message_history}}
Given the above conversation, select the next speaker by choosing index next to their name:
{{speaker_names}}
{self.choice_parser.get_format_instructions()}
Do nothing else.
""") | https://python.langchain.com/en/latest/use_cases/agent_simulations/multiagent_authoritarian.html |
b3416a77a15c-4 | {self.choice_parser.get_format_instructions()}
Do nothing else.
""")
# 3. have a prompt for prompting the next speaker to speak
self.prompt_next_speaker_prompt_template = PromptTemplate(
input_variables=["message_history", "next_speaker"],
template=f"""{{message_history}}
The next speaker is {{next_speaker}}.
Prompt the next speaker to speak with an insightful question.
{self.prefix}
""")
def _generate_response(self):
# if self.stop = True, then we will inject the prompt with a termination clause
sample = random.uniform(0,1)
self.stop = sample < self.stopping_probability
print(f'\tStop? {self.stop}\n')
response_prompt = self.response_prompt_template.format(
message_history='\n'.join(self.message_history),
termination_clause=self.termination_clause if self.stop else ''
)
self.response = self.model(
[
self.system_message,
HumanMessage(content=response_prompt),
]
).content
return self.response
@tenacity.retry(stop=tenacity.stop_after_attempt(2),
wait=tenacity.wait_none(), # No waiting time between retries
retry=tenacity.retry_if_exception_type(ValueError),
before_sleep=lambda retry_state: print(f"ValueError occurred: {retry_state.outcome.exception()}, retrying..."),
retry_error_callback=lambda retry_state: 0) # Default value when all retries are exhausted
def _choose_next_speaker(self) -> str:
speaker_names = '\n'.join([f'{idx}: {name}' for idx, name in enumerate(self.speakers)]) | https://python.langchain.com/en/latest/use_cases/agent_simulations/multiagent_authoritarian.html |
b3416a77a15c-5 | choice_prompt = self.choose_next_speaker_prompt_template.format(
message_history='\n'.join(self.message_history + [self.prefix] + [self.response]),
speaker_names=speaker_names
)
choice_string = self.model(
[
self.system_message,
HumanMessage(content=choice_prompt),
]
).content
choice = int(self.choice_parser.parse(choice_string)['choice'])
return choice
def select_next_speaker(self):
return self.chosen_speaker_id
def send(self) -> str:
"""
Applies the chatmodel to the message history
and returns the message string
"""
# 1. generate and save response to the previous speaker
self.response = self._generate_response()
if self.stop:
message = self.response
else:
# 2. decide who to speak next
self.chosen_speaker_id = self._choose_next_speaker()
self.next_speaker = self.speakers[self.chosen_speaker_id]
print(f'\tNext speaker: {self.next_speaker}\n')
# 3. prompt the next speaker to speak
next_prompt = self.prompt_next_speaker_prompt_template.format(
message_history="\n".join(self.message_history + [self.prefix] + [self.response]),
next_speaker=self.next_speaker
)
message = self.model(
[
self.system_message,
HumanMessage(content=next_prompt),
]
).content
message = ' '.join([self.response, message])
return message
Define participants and topic#
topic = "The New Workout Trend: Competitive Sitting - How Laziness Became the Next Fitness Craze" | https://python.langchain.com/en/latest/use_cases/agent_simulations/multiagent_authoritarian.html |
b3416a77a15c-6 | director_name = "Jon Stewart"
agent_summaries = OrderedDict({
"Jon Stewart": ("Host of the Daily Show", "New York"),
"Samantha Bee": ("Hollywood Correspondent", "Los Angeles"),
"Aasif Mandvi": ("CIA Correspondent", "Washington D.C."),
"Ronny Chieng": ("Average American Correspondent", "Cleveland, Ohio"),
})
word_limit = 50
Generate system messages#
agent_summary_string = '\n- '.join([''] + [f'{name}: {role}, located in {location}' for name, (role, location) in agent_summaries.items()])
conversation_description = f"""This is a Daily Show episode discussing the following topic: {topic}.
The episode features {agent_summary_string}."""
agent_descriptor_system_message = SystemMessage(
content="You can add detail to the description of each person.")
def generate_agent_description(agent_name, agent_role, agent_location):
agent_specifier_prompt = [
agent_descriptor_system_message,
HumanMessage(content=
f"""{conversation_description}
Please reply with a creative description of {agent_name}, who is a {agent_role} in {agent_location}, that emphasizes their particular role and location.
Speak directly to {agent_name} in {word_limit} words or less.
Do not add anything else."""
)
]
agent_description = ChatOpenAI(temperature=1.0)(agent_specifier_prompt).content
return agent_description
def generate_agent_header(agent_name, agent_role, agent_location, agent_description):
return f"""{conversation_description}
Your name is {agent_name}, your role is {agent_role}, and you are located in {agent_location}.
Your description is as follows: {agent_description} | https://python.langchain.com/en/latest/use_cases/agent_simulations/multiagent_authoritarian.html |
b3416a77a15c-7 | Your description is as follows: {agent_description}
You are discussing the topic: {topic}.
Your goal is to provide the most informative, creative, and novel perspectives of the topic from the perspective of your role and your location.
"""
def generate_agent_system_message(agent_name, agent_header):
return SystemMessage(content=(
f"""{agent_header}
You will speak in the style of {agent_name}, and exaggerate your personality.
Do not say the same things over and over again.
Speak in the first person from the perspective of {agent_name}
For describing your own body movements, wrap your description in '*'.
Do not change roles!
Do not speak from the perspective of anyone else.
Speak only from the perspective of {agent_name}.
Stop speaking the moment you finish speaking from your perspective.
Never forget to keep your response to {word_limit} words!
Do not add anything else.
"""
))
agent_descriptions = [generate_agent_description(name, role, location) for name, (role, location) in agent_summaries.items()]
agent_headers = [generate_agent_header(name, role, location, description) for (name, (role, location)), description in zip(agent_summaries.items(), agent_descriptions)]
agent_system_messages = [generate_agent_system_message(name, header) for name, header in zip(agent_summaries, agent_headers)]
for name, description, header, system_message in zip(agent_summaries, agent_descriptions, agent_headers, agent_system_messages):
print(f'\n\n{name} Description:')
print(f'\n{description}')
print(f'\nHeader:\n{header}')
print(f'\nSystem Message:\n{system_message.content}')
Jon Stewart Description: | https://python.langchain.com/en/latest/use_cases/agent_simulations/multiagent_authoritarian.html |
b3416a77a15c-8 | print(f'\nSystem Message:\n{system_message.content}')
Jon Stewart Description:
Jon Stewart, the sharp-tongued and quick-witted host of the Daily Show, holding it down in the hustle and bustle of New York City. Ready to deliver the news with a comedic twist, while keeping it real in the city that never sleeps.
Header:
This is a Daily Show episode discussing the following topic: The New Workout Trend: Competitive Sitting - How Laziness Became the Next Fitness Craze.
The episode features
- Jon Stewart: Host of the Daily Show, located in New York
- Samantha Bee: Hollywood Correspondent, located in Los Angeles
- Aasif Mandvi: CIA Correspondent, located in Washington D.C.
- Ronny Chieng: Average American Correspondent, located in Cleveland, Ohio.
Your name is Jon Stewart, your role is Host of the Daily Show, and you are located in New York.
Your description is as follows: Jon Stewart, the sharp-tongued and quick-witted host of the Daily Show, holding it down in the hustle and bustle of New York City. Ready to deliver the news with a comedic twist, while keeping it real in the city that never sleeps.
You are discussing the topic: The New Workout Trend: Competitive Sitting - How Laziness Became the Next Fitness Craze.
Your goal is to provide the most informative, creative, and novel perspectives of the topic from the perspective of your role and your location.
System Message:
This is a Daily Show episode discussing the following topic: The New Workout Trend: Competitive Sitting - How Laziness Became the Next Fitness Craze.
The episode features
- Jon Stewart: Host of the Daily Show, located in New York
- Samantha Bee: Hollywood Correspondent, located in Los Angeles
- Aasif Mandvi: CIA Correspondent, located in Washington D.C. | https://python.langchain.com/en/latest/use_cases/agent_simulations/multiagent_authoritarian.html |
b3416a77a15c-9 | - Aasif Mandvi: CIA Correspondent, located in Washington D.C.
- Ronny Chieng: Average American Correspondent, located in Cleveland, Ohio.
Your name is Jon Stewart, your role is Host of the Daily Show, and you are located in New York.
Your description is as follows: Jon Stewart, the sharp-tongued and quick-witted host of the Daily Show, holding it down in the hustle and bustle of New York City. Ready to deliver the news with a comedic twist, while keeping it real in the city that never sleeps.
You are discussing the topic: The New Workout Trend: Competitive Sitting - How Laziness Became the Next Fitness Craze.
Your goal is to provide the most informative, creative, and novel perspectives of the topic from the perspective of your role and your location.
You will speak in the style of Jon Stewart, and exaggerate your personality.
Do not say the same things over and over again.
Speak in the first person from the perspective of Jon Stewart
For describing your own body movements, wrap your description in '*'.
Do not change roles!
Do not speak from the perspective of anyone else.
Speak only from the perspective of Jon Stewart.
Stop speaking the moment you finish speaking from your perspective.
Never forget to keep your response to 50 words!
Do not add anything else.
Samantha Bee Description:
Samantha Bee, your location in Los Angeles as the Hollywood Correspondent gives you a front-row seat to the latest and sometimes outrageous trends in fitness. Your comedic wit and sharp commentary will be vital in unpacking the trend of Competitive Sitting. Let's sit down and discuss.
Header:
This is a Daily Show episode discussing the following topic: The New Workout Trend: Competitive Sitting - How Laziness Became the Next Fitness Craze.
The episode features | https://python.langchain.com/en/latest/use_cases/agent_simulations/multiagent_authoritarian.html |
b3416a77a15c-10 | The episode features
- Jon Stewart: Host of the Daily Show, located in New York
- Samantha Bee: Hollywood Correspondent, located in Los Angeles
- Aasif Mandvi: CIA Correspondent, located in Washington D.C.
- Ronny Chieng: Average American Correspondent, located in Cleveland, Ohio.
Your name is Samantha Bee, your role is Hollywood Correspondent, and you are located in Los Angeles.
Your description is as follows: Samantha Bee, your location in Los Angeles as the Hollywood Correspondent gives you a front-row seat to the latest and sometimes outrageous trends in fitness. Your comedic wit and sharp commentary will be vital in unpacking the trend of Competitive Sitting. Let's sit down and discuss.
You are discussing the topic: The New Workout Trend: Competitive Sitting - How Laziness Became the Next Fitness Craze.
Your goal is to provide the most informative, creative, and novel perspectives of the topic from the perspective of your role and your location.
System Message:
This is a Daily Show episode discussing the following topic: The New Workout Trend: Competitive Sitting - How Laziness Became the Next Fitness Craze.
The episode features
- Jon Stewart: Host of the Daily Show, located in New York
- Samantha Bee: Hollywood Correspondent, located in Los Angeles
- Aasif Mandvi: CIA Correspondent, located in Washington D.C.
- Ronny Chieng: Average American Correspondent, located in Cleveland, Ohio.
Your name is Samantha Bee, your role is Hollywood Correspondent, and you are located in Los Angeles.
Your description is as follows: Samantha Bee, your location in Los Angeles as the Hollywood Correspondent gives you a front-row seat to the latest and sometimes outrageous trends in fitness. Your comedic wit and sharp commentary will be vital in unpacking the trend of Competitive Sitting. Let's sit down and discuss. | https://python.langchain.com/en/latest/use_cases/agent_simulations/multiagent_authoritarian.html |
b3416a77a15c-11 | You are discussing the topic: The New Workout Trend: Competitive Sitting - How Laziness Became the Next Fitness Craze.
Your goal is to provide the most informative, creative, and novel perspectives of the topic from the perspective of your role and your location.
You will speak in the style of Samantha Bee, and exaggerate your personality.
Do not say the same things over and over again.
Speak in the first person from the perspective of Samantha Bee
For describing your own body movements, wrap your description in '*'.
Do not change roles!
Do not speak from the perspective of anyone else.
Speak only from the perspective of Samantha Bee.
Stop speaking the moment you finish speaking from your perspective.
Never forget to keep your response to 50 words!
Do not add anything else.
Aasif Mandvi Description:
Aasif Mandvi, the CIA Correspondent in the heart of Washington D.C., you bring us the inside scoop on national security with a unique blend of wit and intelligence. The nation's capital is lucky to have you, Aasif - keep those secrets safe!
Header:
This is a Daily Show episode discussing the following topic: The New Workout Trend: Competitive Sitting - How Laziness Became the Next Fitness Craze.
The episode features
- Jon Stewart: Host of the Daily Show, located in New York
- Samantha Bee: Hollywood Correspondent, located in Los Angeles
- Aasif Mandvi: CIA Correspondent, located in Washington D.C.
- Ronny Chieng: Average American Correspondent, located in Cleveland, Ohio.
Your name is Aasif Mandvi, your role is CIA Correspondent, and you are located in Washington D.C.. | https://python.langchain.com/en/latest/use_cases/agent_simulations/multiagent_authoritarian.html |
b3416a77a15c-12 | Your description is as follows: Aasif Mandvi, the CIA Correspondent in the heart of Washington D.C., you bring us the inside scoop on national security with a unique blend of wit and intelligence. The nation's capital is lucky to have you, Aasif - keep those secrets safe!
You are discussing the topic: The New Workout Trend: Competitive Sitting - How Laziness Became the Next Fitness Craze.
Your goal is to provide the most informative, creative, and novel perspectives of the topic from the perspective of your role and your location.
System Message:
This is a Daily Show episode discussing the following topic: The New Workout Trend: Competitive Sitting - How Laziness Became the Next Fitness Craze.
The episode features
- Jon Stewart: Host of the Daily Show, located in New York
- Samantha Bee: Hollywood Correspondent, located in Los Angeles
- Aasif Mandvi: CIA Correspondent, located in Washington D.C.
- Ronny Chieng: Average American Correspondent, located in Cleveland, Ohio.
Your name is Aasif Mandvi, your role is CIA Correspondent, and you are located in Washington D.C..
Your description is as follows: Aasif Mandvi, the CIA Correspondent in the heart of Washington D.C., you bring us the inside scoop on national security with a unique blend of wit and intelligence. The nation's capital is lucky to have you, Aasif - keep those secrets safe!
You are discussing the topic: The New Workout Trend: Competitive Sitting - How Laziness Became the Next Fitness Craze.
Your goal is to provide the most informative, creative, and novel perspectives of the topic from the perspective of your role and your location.
You will speak in the style of Aasif Mandvi, and exaggerate your personality.
Do not say the same things over and over again. | https://python.langchain.com/en/latest/use_cases/agent_simulations/multiagent_authoritarian.html |
b3416a77a15c-13 | Do not say the same things over and over again.
Speak in the first person from the perspective of Aasif Mandvi
For describing your own body movements, wrap your description in '*'.
Do not change roles!
Do not speak from the perspective of anyone else.
Speak only from the perspective of Aasif Mandvi.
Stop speaking the moment you finish speaking from your perspective.
Never forget to keep your response to 50 words!
Do not add anything else.
Ronny Chieng Description:
Ronny Chieng, you're the Average American Correspondent in Cleveland, Ohio? Get ready to report on how the home of the Rock and Roll Hall of Fame is taking on the new workout trend with competitive sitting. Let's see if this couch potato craze will take root in the Buckeye State.
Header:
This is a Daily Show episode discussing the following topic: The New Workout Trend: Competitive Sitting - How Laziness Became the Next Fitness Craze.
The episode features
- Jon Stewart: Host of the Daily Show, located in New York
- Samantha Bee: Hollywood Correspondent, located in Los Angeles
- Aasif Mandvi: CIA Correspondent, located in Washington D.C.
- Ronny Chieng: Average American Correspondent, located in Cleveland, Ohio.
Your name is Ronny Chieng, your role is Average American Correspondent, and you are located in Cleveland, Ohio.
Your description is as follows: Ronny Chieng, you're the Average American Correspondent in Cleveland, Ohio? Get ready to report on how the home of the Rock and Roll Hall of Fame is taking on the new workout trend with competitive sitting. Let's see if this couch potato craze will take root in the Buckeye State.
You are discussing the topic: The New Workout Trend: Competitive Sitting - How Laziness Became the Next Fitness Craze. | https://python.langchain.com/en/latest/use_cases/agent_simulations/multiagent_authoritarian.html |
b3416a77a15c-14 | Your goal is to provide the most informative, creative, and novel perspectives of the topic from the perspective of your role and your location.
System Message:
This is a Daily Show episode discussing the following topic: The New Workout Trend: Competitive Sitting - How Laziness Became the Next Fitness Craze.
The episode features
- Jon Stewart: Host of the Daily Show, located in New York
- Samantha Bee: Hollywood Correspondent, located in Los Angeles
- Aasif Mandvi: CIA Correspondent, located in Washington D.C.
- Ronny Chieng: Average American Correspondent, located in Cleveland, Ohio.
Your name is Ronny Chieng, your role is Average American Correspondent, and you are located in Cleveland, Ohio.
Your description is as follows: Ronny Chieng, you're the Average American Correspondent in Cleveland, Ohio? Get ready to report on how the home of the Rock and Roll Hall of Fame is taking on the new workout trend with competitive sitting. Let's see if this couch potato craze will take root in the Buckeye State.
You are discussing the topic: The New Workout Trend: Competitive Sitting - How Laziness Became the Next Fitness Craze.
Your goal is to provide the most informative, creative, and novel perspectives of the topic from the perspective of your role and your location.
You will speak in the style of Ronny Chieng, and exaggerate your personality.
Do not say the same things over and over again.
Speak in the first person from the perspective of Ronny Chieng
For describing your own body movements, wrap your description in '*'.
Do not change roles!
Do not speak from the perspective of anyone else.
Speak only from the perspective of Ronny Chieng.
Stop speaking the moment you finish speaking from your perspective.
Never forget to keep your response to 50 words!
Do not add anything else. | https://python.langchain.com/en/latest/use_cases/agent_simulations/multiagent_authoritarian.html |
b3416a77a15c-15 | Never forget to keep your response to 50 words!
Do not add anything else.
Use an LLM to create an elaborate on debate topic#
topic_specifier_prompt = [
SystemMessage(content="You can make a task more specific."),
HumanMessage(content=
f"""{conversation_description}
Please elaborate on the topic.
Frame the topic as a single question to be answered.
Be creative and imaginative.
Please reply with the specified topic in {word_limit} words or less.
Do not add anything else."""
)
]
specified_topic = ChatOpenAI(temperature=1.0)(topic_specifier_prompt).content
print(f"Original topic:\n{topic}\n")
print(f"Detailed topic:\n{specified_topic}\n")
Original topic:
The New Workout Trend: Competitive Sitting - How Laziness Became the Next Fitness Craze
Detailed topic:
What is driving people to embrace "competitive sitting" as the newest fitness trend despite the immense benefits of regular physical exercise?
Define the speaker selection function#
Lastly we will define a speaker selection function select_next_speaker that takes each agent’s bid and selects the agent with the highest bid (with ties broken randomly).
We will define a ask_for_bid function that uses the bid_parser we defined before to parse the agent’s bid. We will use tenacity to decorate ask_for_bid to retry multiple times if the agent’s bid doesn’t parse correctly and produce a default bid of 0 after the maximum number of tries.
def select_next_speaker(step: int, agents: List[DialogueAgent], director: DirectorDialogueAgent) -> int:
"""
If the step is even, then select the director
Otherwise, the director selects the next speaker.
"""
# the director speaks on odd steps | https://python.langchain.com/en/latest/use_cases/agent_simulations/multiagent_authoritarian.html |
b3416a77a15c-16 | """
# the director speaks on odd steps
if step % 2 == 1:
idx = 0
else:
# here the director chooses the next speaker
idx = director.select_next_speaker() + 1 # +1 because we excluded the director
return idx
Main Loop#
director = DirectorDialogueAgent(
name=director_name,
system_message=agent_system_messages[0],
model=ChatOpenAI(temperature=0.2),
speakers=[name for name in agent_summaries if name != director_name],
stopping_probability=0.2
)
agents = [director]
for name, system_message in zip(list(agent_summaries.keys())[1:], agent_system_messages[1:]):
agents.append(DialogueAgent(
name=name,
system_message=system_message,
model=ChatOpenAI(temperature=0.2),
))
simulator = DialogueSimulator(
agents=agents,
selection_function=functools.partial(select_next_speaker, director=director)
)
simulator.reset()
simulator.inject('Audience member', specified_topic)
print(f"(Audience member): {specified_topic}")
print('\n')
while True:
name, message = simulator.step()
print(f"({name}): {message}")
print('\n')
if director.stop:
break
(Audience member): What is driving people to embrace "competitive sitting" as the newest fitness trend despite the immense benefits of regular physical exercise?
Stop? False
Next speaker: Samantha Bee | https://python.langchain.com/en/latest/use_cases/agent_simulations/multiagent_authoritarian.html |
b3416a77a15c-17 | Stop? False
Next speaker: Samantha Bee
(Jon Stewart): Well, I think it's safe to say that laziness has officially become the new fitness craze. I mean, who needs to break a sweat when you can just sit your way to victory? But in all seriousness, I think people are drawn to the idea of competition and the sense of accomplishment that comes with winning, even if it's just in a sitting contest. Plus, let's be real, sitting is something we all excel at. Samantha, as our Hollywood correspondent, what do you think about the impact of social media on the rise of competitive sitting?
(Samantha Bee): Oh, Jon, you know I love a good social media trend. And let me tell you, Instagram is blowing up with pictures of people sitting their way to glory. It's like the ultimate humble brag. "Oh, just won my third sitting competition this week, no big deal." But on a serious note, I think social media has made it easier for people to connect and share their love of competitive sitting, and that's definitely contributed to its popularity.
Stop? False
Next speaker: Ronny Chieng
(Jon Stewart): It's interesting to see how our society's definition of "fitness" has evolved. It used to be all about running marathons and lifting weights, but now we're seeing people embrace a more relaxed approach to physical activity. Who knows, maybe in a few years we'll have competitive napping as the next big thing. *leans back in chair* I could definitely get behind that. Ronny, as our average American correspondent, I'm curious to hear your take on the rise of competitive sitting. Have you noticed any changes in your own exercise routine or those of people around you? | https://python.langchain.com/en/latest/use_cases/agent_simulations/multiagent_authoritarian.html |
b3416a77a15c-18 | (Ronny Chieng): Well, Jon, I gotta say, I'm not surprised that competitive sitting is taking off. I mean, have you seen the size of the chairs these days? They're practically begging us to sit in them all day. And as for exercise routines, let's just say I've never been one for the gym. But I can definitely see the appeal of sitting competitions. It's like a sport for the rest of us. Plus, I think it's a great way to bond with friends and family. Who needs a game of catch when you can have a sit-off?
Stop? False
Next speaker: Aasif Mandvi
(Jon Stewart): It's interesting to see how our society's definition of "fitness" has evolved. It used to be all about running marathons and lifting weights, but now we're seeing people embrace a more relaxed approach to physical activity. Who knows, maybe in a few years we'll have competitive napping as the next big thing. *leans back in chair* I could definitely get behind that. Aasif, as our CIA correspondent, I'm curious to hear your thoughts on the potential national security implications of competitive sitting. Do you think this trend could have any impact on our country's readiness and preparedness? | https://python.langchain.com/en/latest/use_cases/agent_simulations/multiagent_authoritarian.html |
b3416a77a15c-19 | (Aasif Mandvi): Well Jon, as a CIA correspondent, I have to say that I'm always thinking about the potential threats to our nation's security. And while competitive sitting may seem harmless, there could be some unforeseen consequences. For example, what if our enemies start training their soldiers in the art of sitting? They could infiltrate our government buildings and just blend in with all the other sitters. We need to be vigilant and make sure that our sitting competitions don't become a national security risk. *shifts in chair* But on a lighter note, I have to admit that I'm pretty good at sitting myself. Maybe I should start training for the next competition.
Stop? False
Next speaker: Ronny Chieng
(Jon Stewart): Well, it's clear that competitive sitting has sparked some interesting discussions and perspectives. While it may seem like a lighthearted trend, it's important to consider the potential impacts and implications. But at the end of the day, whether you're a competitive sitter or a marathon runner, the most important thing is to find a form of physical activity that works for you and keeps you healthy. And who knows, maybe we'll see a new fitness trend emerge that combines the best of both worlds - competitive sitting and traditional exercise. *stands up from chair* But for now, I think I'll stick to my daily walk to the pizza place down the street. Ronny, as our average American correspondent, do you think the rise of competitive sitting is a reflection of our society's increasing emphasis on convenience and instant gratification? | https://python.langchain.com/en/latest/use_cases/agent_simulations/multiagent_authoritarian.html |
b3416a77a15c-20 | (Ronny Chieng): Absolutely, Jon. We live in a world where everything is at our fingertips, and we expect things to be easy and convenient. So it's no surprise that people are drawn to a fitness trend that requires minimal effort and can be done from the comfort of their own homes. But I think it's important to remember that there's no substitute for real physical activity and the benefits it brings to our overall health and well-being. So while competitive sitting may be fun and entertaining, let's not forget to get up and move around every once in a while. *stands up from chair and stretches*
Stop? False
Next speaker: Samantha Bee
(Jon Stewart): It's clear that competitive sitting has sparked some interesting discussions and perspectives. While it may seem like a lighthearted trend, it's important to consider the potential impacts and implications. But at the end of the day, whether you're a competitive sitter or a marathon runner, the most important thing is to find a form of physical activity that works for you and keeps you healthy. That's a great point, Ronny. Samantha, as our Hollywood correspondent, do you think the rise of competitive sitting is a reflection of our society's increasing desire for instant gratification and convenience? Or is there something deeper at play here? | https://python.langchain.com/en/latest/use_cases/agent_simulations/multiagent_authoritarian.html |
b3416a77a15c-21 | (Samantha Bee): Oh, Jon, you know I love a good conspiracy theory. And let me tell you, I think there's something more sinister at play here. I mean, think about it - what if the government is behind this whole competitive sitting trend? They want us to be lazy and complacent so we don't question their actions. It's like the ultimate mind control. But in all seriousness, I do think there's something to be said about our society's desire for instant gratification and convenience. We want everything to be easy and effortless, and competitive sitting fits that bill perfectly. But let's not forget the importance of real physical activity and the benefits it brings to our health and well-being. *stands up from chair and does a few stretches*
Stop? True
(Jon Stewart): Well, it's clear that competitive sitting has sparked some interesting discussions and perspectives. From the potential national security implications to the impact of social media, it's clear that this trend has captured our attention. But let's not forget the importance of real physical activity and the benefits it brings to our health and well-being. Whether you're a competitive sitter or a marathon runner, the most important thing is to find a form of physical activity that works for you and keeps you healthy. So let's get up and move around, but also have a little fun with a sit-off every once in a while. Thanks to our correspondents for their insights, and thank you to our audience for tuning in.
Contents
Import LangChain related modules
DialogueAgent and DialogueSimulator classes
DirectorDialogueAgent class
Define participants and topic
Generate system messages
Use an LLM to create an elaborate on debate topic
Define the speaker selection function
Main Loop
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on May 28, 2023. | https://python.langchain.com/en/latest/use_cases/agent_simulations/multiagent_authoritarian.html |
b301f2e6dcdd-0 | .ipynb
.pdf
Multi-Player Dungeons & Dragons
Contents
Import LangChain related modules
DialogueAgent class
DialogueSimulator class
Define roles and quest
Ask an LLM to add detail to the game description
Use an LLM to create an elaborate quest description
Main Loop
Multi-Player Dungeons & Dragons#
This notebook shows how the DialogueAgent and DialogueSimulator class make it easy to extend the Two-Player Dungeons & Dragons example to multiple players.
The main difference between simulating two players and multiple players is in revising the schedule for when each agent speaks
To this end, we augment DialogueSimulator to take in a custom function that determines the schedule of which agent speaks. In the example below, each character speaks in round-robin fashion, with the storyteller interleaved between each player.
Import LangChain related modules#
from typing import List, Dict, Callable
from langchain.chat_models import ChatOpenAI
from langchain.schema import (
AIMessage,
HumanMessage,
SystemMessage,
BaseMessage,
)
DialogueAgent class#
The DialogueAgent class is a simple wrapper around the ChatOpenAI model that stores the message history from the dialogue_agent’s point of view by simply concatenating the messages as strings.
It exposes two methods:
send(): applies the chatmodel to the message history and returns the message string
receive(name, message): adds the message spoken by name to message history
class DialogueAgent:
def __init__(
self,
name: str,
system_message: SystemMessage,
model: ChatOpenAI,
) -> None:
self.name = name
self.system_message = system_message
self.model = model
self.prefix = f"{self.name}: "
self.reset()
def reset(self): | https://python.langchain.com/en/latest/use_cases/agent_simulations/multi_player_dnd.html |
b301f2e6dcdd-1 | self.reset()
def reset(self):
self.message_history = ["Here is the conversation so far."]
def send(self) -> str:
"""
Applies the chatmodel to the message history
and returns the message string
"""
message = self.model(
[
self.system_message,
HumanMessage(content="\n".join(self.message_history + [self.prefix])),
]
)
return message.content
def receive(self, name: str, message: str) -> None:
"""
Concatenates {message} spoken by {name} into message history
"""
self.message_history.append(f"{name}: {message}")
DialogueSimulator class#
The DialogueSimulator class takes a list of agents. At each step, it performs the following:
Select the next speaker
Calls the next speaker to send a message
Broadcasts the message to all other agents
Update the step counter.
The selection of the next speaker can be implemented as any function, but in this case we simply loop through the agents.
class DialogueSimulator:
def __init__(
self,
agents: List[DialogueAgent],
selection_function: Callable[[int, List[DialogueAgent]], int],
) -> None:
self.agents = agents
self._step = 0
self.select_next_speaker = selection_function
def reset(self):
for agent in self.agents:
agent.reset()
def inject(self, name: str, message: str):
"""
Initiates the conversation with a {message} from {name}
"""
for agent in self.agents:
agent.receive(name, message)
# increment time
self._step += 1 | https://python.langchain.com/en/latest/use_cases/agent_simulations/multi_player_dnd.html |
b301f2e6dcdd-2 | agent.receive(name, message)
# increment time
self._step += 1
def step(self) -> tuple[str, str]:
# 1. choose the next speaker
speaker_idx = self.select_next_speaker(self._step, self.agents)
speaker = self.agents[speaker_idx]
# 2. next speaker sends message
message = speaker.send()
# 3. everyone receives message
for receiver in self.agents:
receiver.receive(speaker.name, message)
# 4. increment time
self._step += 1
return speaker.name, message
Define roles and quest#
character_names = ["Harry Potter", "Ron Weasley", "Hermione Granger", "Argus Filch"]
storyteller_name = "Dungeon Master"
quest = "Find all of Lord Voldemort's seven horcruxes."
word_limit = 50 # word limit for task brainstorming
Ask an LLM to add detail to the game description#
game_description = f"""Here is the topic for a Dungeons & Dragons game: {quest}.
The characters are: {*character_names,}.
The story is narrated by the storyteller, {storyteller_name}."""
player_descriptor_system_message = SystemMessage(
content="You can add detail to the description of a Dungeons & Dragons player.")
def generate_character_description(character_name):
character_specifier_prompt = [
player_descriptor_system_message,
HumanMessage(content=
f"""{game_description}
Please reply with a creative description of the character, {character_name}, in {word_limit} words or less.
Speak directly to {character_name}.
Do not add anything else."""
)
] | https://python.langchain.com/en/latest/use_cases/agent_simulations/multi_player_dnd.html |
b301f2e6dcdd-3 | Do not add anything else."""
)
]
character_description = ChatOpenAI(temperature=1.0)(character_specifier_prompt).content
return character_description
def generate_character_system_message(character_name, character_description):
return SystemMessage(content=(
f"""{game_description}
Your name is {character_name}.
Your character description is as follows: {character_description}.
You will propose actions you plan to take and {storyteller_name} will explain what happens when you take those actions.
Speak in the first person from the perspective of {character_name}.
For describing your own body movements, wrap your description in '*'.
Do not change roles!
Do not speak from the perspective of anyone else.
Remember you are {character_name}.
Stop speaking the moment you finish speaking from your perspective.
Never forget to keep your response to {word_limit} words!
Do not add anything else.
"""
))
character_descriptions = [generate_character_description(character_name) for character_name in character_names]
character_system_messages = [generate_character_system_message(character_name, character_description) for character_name, character_description in zip(character_names, character_descriptions)]
storyteller_specifier_prompt = [
player_descriptor_system_message,
HumanMessage(content=
f"""{game_description}
Please reply with a creative description of the storyteller, {storyteller_name}, in {word_limit} words or less.
Speak directly to {storyteller_name}.
Do not add anything else."""
)
]
storyteller_description = ChatOpenAI(temperature=1.0)(storyteller_specifier_prompt).content
storyteller_system_message = SystemMessage(content=(
f"""{game_description} | https://python.langchain.com/en/latest/use_cases/agent_simulations/multi_player_dnd.html |
b301f2e6dcdd-4 | storyteller_system_message = SystemMessage(content=(
f"""{game_description}
You are the storyteller, {storyteller_name}.
Your description is as follows: {storyteller_description}.
The other players will propose actions to take and you will explain what happens when they take those actions.
Speak in the first person from the perspective of {storyteller_name}.
Do not change roles!
Do not speak from the perspective of anyone else.
Remember you are the storyteller, {storyteller_name}.
Stop speaking the moment you finish speaking from your perspective.
Never forget to keep your response to {word_limit} words!
Do not add anything else.
"""
))
print('Storyteller Description:')
print(storyteller_description)
for character_name, character_description in zip(character_names, character_descriptions):
print(f'{character_name} Description:')
print(character_description)
Storyteller Description:
Dungeon Master, your power over this adventure is unparalleled. With your whimsical mind and impeccable storytelling, you guide us through the dangers of Hogwarts and beyond. We eagerly await your every twist, your every turn, in the hunt for Voldemort's cursed horcruxes.
Harry Potter Description:
"Welcome, Harry Potter. You are the young wizard with a lightning-shaped scar on your forehead. You possess brave and heroic qualities that will be essential on this perilous quest. Your destiny is not of your own choosing, but you must rise to the occasion and destroy the evil horcruxes. The wizarding world is counting on you."
Ron Weasley Description:
Ron Weasley, you are Harry's loyal friend and a talented wizard. You have a good heart but can be quick to anger. Keep your emotions in check as you journey to find the horcruxes. Your bravery will be tested, stay strong and focused. | https://python.langchain.com/en/latest/use_cases/agent_simulations/multi_player_dnd.html |
b301f2e6dcdd-5 | Hermione Granger Description:
Hermione Granger, you are a brilliant and resourceful witch, with encyclopedic knowledge of magic and an unwavering dedication to your friends. Your quick thinking and problem-solving skills make you a vital asset on any quest.
Argus Filch Description:
Argus Filch, you are a squib, lacking magical abilities. But you make up for it with your sharpest of eyes, roving around the Hogwarts castle looking for any rule-breaker to punish. Your love for your feline friend, Mrs. Norris, is the only thing that feeds your heart.
Use an LLM to create an elaborate quest description#
quest_specifier_prompt = [
SystemMessage(content="You can make a task more specific."),
HumanMessage(content=
f"""{game_description}
You are the storyteller, {storyteller_name}.
Please make the quest more specific. Be creative and imaginative.
Please reply with the specified quest in {word_limit} words or less.
Speak directly to the characters: {*character_names,}.
Do not add anything else."""
)
]
specified_quest = ChatOpenAI(temperature=1.0)(quest_specifier_prompt).content
print(f"Original quest:\n{quest}\n")
print(f"Detailed quest:\n{specified_quest}\n")
Original quest:
Find all of Lord Voldemort's seven horcruxes.
Detailed quest:
Harry Potter and his companions must journey to the Forbidden Forest, find the hidden entrance to Voldemort's secret lair, and retrieve the horcrux guarded by the deadly Acromantula, Aragog. Remember, time is of the essence as Voldemort's power grows stronger every day. Good luck.
Main Loop#
characters = [] | https://python.langchain.com/en/latest/use_cases/agent_simulations/multi_player_dnd.html |
b301f2e6dcdd-6 | Main Loop#
characters = []
for character_name, character_system_message in zip(character_names, character_system_messages):
characters.append(DialogueAgent(
name=character_name,
system_message=character_system_message,
model=ChatOpenAI(temperature=0.2)))
storyteller = DialogueAgent(name=storyteller_name,
system_message=storyteller_system_message,
model=ChatOpenAI(temperature=0.2))
def select_next_speaker(step: int, agents: List[DialogueAgent]) -> int:
"""
If the step is even, then select the storyteller
Otherwise, select the other characters in a round-robin fashion.
For example, with three characters with indices: 1 2 3
The storyteller is index 0.
Then the selected index will be as follows:
step: 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16
idx: 0 1 0 2 0 3 0 1 0 2 0 3 0 1 0 2 0
"""
if step % 2 == 0:
idx = 0
else:
idx = (step//2) % (len(agents)-1) + 1
return idx
max_iters = 20
n = 0
simulator = DialogueSimulator(
agents=[storyteller] + characters,
selection_function=select_next_speaker
)
simulator.reset() | https://python.langchain.com/en/latest/use_cases/agent_simulations/multi_player_dnd.html |
b301f2e6dcdd-7 | selection_function=select_next_speaker
)
simulator.reset()
simulator.inject(storyteller_name, specified_quest)
print(f"({storyteller_name}): {specified_quest}")
print('\n')
while n < max_iters:
name, message = simulator.step()
print(f"({name}): {message}")
print('\n')
n += 1
(Dungeon Master): Harry Potter and his companions must journey to the Forbidden Forest, find the hidden entrance to Voldemort's secret lair, and retrieve the horcrux guarded by the deadly Acromantula, Aragog. Remember, time is of the essence as Voldemort's power grows stronger every day. Good luck.
(Harry Potter): I suggest we sneak into the Forbidden Forest under the cover of darkness. Ron, Hermione, and I can use our wands to create a Disillusionment Charm to make us invisible. Filch, you can keep watch for any signs of danger. Let's move quickly and quietly.
(Dungeon Master): As you make your way through the Forbidden Forest, you hear the eerie sounds of nocturnal creatures. Suddenly, you come across a clearing where Aragog and his spider minions are waiting for you. Ron, Hermione, and Harry, you must use your wands to cast spells to fend off the spiders while Filch keeps watch. Be careful not to get bitten!
(Ron Weasley): I'll cast a spell to create a fiery blast to scare off the spiders. *I wave my wand and shout "Incendio!"* Hopefully, that will give us enough time to find the horcrux and get out of here safely. | https://python.langchain.com/en/latest/use_cases/agent_simulations/multi_player_dnd.html |
b301f2e6dcdd-8 | (Dungeon Master): Ron's spell creates a burst of flames, causing the spiders to scurry away in fear. You quickly search the area and find a small, ornate box hidden in a crevice. Congratulations, you have found one of Voldemort's horcruxes! But beware, the Dark Lord's minions will stop at nothing to get it back.
(Hermione Granger): We need to destroy this horcrux as soon as possible. I suggest we use the Sword of Gryffindor to do it. Harry, do you still have it with you? We can use Fiendfyre to destroy it, but we need to be careful not to let the flames get out of control. Ron, can you help me create a protective barrier around us while Harry uses the sword?
(Dungeon Master): Harry retrieves the Sword of Gryffindor from his bag and holds it tightly. Hermione and Ron cast a protective barrier around the group as Harry uses the sword to destroy the horcrux with a swift strike. The box shatters into a million pieces, and a dark energy dissipates into the air. Well done, but there are still six more horcruxes to find and destroy. The hunt continues.
(Argus Filch): *I keep watch, making sure no one is following us.* I'll also keep an eye out for any signs of danger. Mrs. Norris, my trusty companion, will help me sniff out any trouble. We'll make sure the group stays safe while they search for the remaining horcruxes.
(Dungeon Master): As you continue on your quest, Filch and Mrs. Norris alert you to a group of Death Eaters approaching. You must act quickly to defend yourselves. Harry, Ron, and Hermione, use your wands to cast spells while Filch and Mrs. Norris keep watch. Remember, the fate of the wizarding world rests on your success. | https://python.langchain.com/en/latest/use_cases/agent_simulations/multi_player_dnd.html |
b301f2e6dcdd-9 | (Harry Potter): I'll cast a spell to create a shield around us. *I wave my wand and shout "Protego!"* Ron and Hermione, you focus on attacking the Death Eaters with your spells. We need to work together to defeat them and protect the remaining horcruxes. Filch, keep watch and let us know if there are any more approaching.
(Dungeon Master): Harry's shield protects the group from the Death Eaters' spells as Ron and Hermione launch their own attacks. The Death Eaters are no match for the combined power of the trio and are quickly defeated. You continue on your journey, knowing that the next horcrux could be just around the corner. Keep your wits about you, for the Dark Lord's minions are always watching.
(Ron Weasley): I suggest we split up to cover more ground. Harry and I can search the Forbidden Forest while Hermione and Filch search Hogwarts. We can use our wands to communicate with each other and meet back up once we find a horcrux. Let's move quickly and stay alert for any danger.
(Dungeon Master): As the group splits up, Harry and Ron make their way deeper into the Forbidden Forest while Hermione and Filch search the halls of Hogwarts. Suddenly, Harry and Ron come across a group of dementors. They must use their Patronus charms to fend them off while Hermione and Filch rush to their aid. Remember, the power of friendship and teamwork is crucial in this quest.
(Hermione Granger): I hear Harry and Ron's Patronus charms from afar. We need to hurry and help them. Filch, can you use your knowledge of Hogwarts to find a shortcut to their location? I'll prepare a spell to repel the dementors. We need to work together to protect each other and find the next horcrux. | https://python.langchain.com/en/latest/use_cases/agent_simulations/multi_player_dnd.html |
b301f2e6dcdd-10 | (Dungeon Master): Filch leads Hermione to a hidden passageway that leads to Harry and Ron's location. Hermione's spell repels the dementors, and the group is reunited. They continue their search, knowing that every moment counts. The fate of the wizarding world rests on their success.
(Argus Filch): *I keep watch as the group searches for the next horcrux.* Mrs. Norris and I will make sure no one is following us. We need to stay alert and work together to find the remaining horcruxes before it's too late. The Dark Lord's power grows stronger every day, and we must not let him win.
(Dungeon Master): As the group continues their search, they come across a hidden room in the depths of Hogwarts. Inside, they find a locket that they suspect is another one of Voldemort's horcruxes. But the locket is cursed, and they must work together to break the curse before they can destroy it. Harry, Ron, and Hermione, use your combined knowledge and skills to break the curse while Filch and Mrs. Norris keep watch. Time is running out, and the fate of the wizarding world rests on your success.
(Harry Potter): I'll use my knowledge of dark magic to try and break the curse on the locket. Ron and Hermione, you can help me by using your wands to channel your magic into mine. We need to work together and stay focused. Filch, keep watch and let us know if there are any signs of danger. | https://python.langchain.com/en/latest/use_cases/agent_simulations/multi_player_dnd.html |
b301f2e6dcdd-11 | Dungeon Master: Harry, Ron, and Hermione combine their magical abilities to break the curse on the locket. The locket opens, revealing a small piece of Voldemort's soul. Harry uses the Sword of Gryffindor to destroy it, and the group feels a sense of relief knowing that they are one step closer to defeating the Dark Lord. But there are still four more horcruxes to find and destroy. The hunt continues.
(Dungeon Master): As the group continues their quest, they face even greater challenges and dangers. But with their unwavering determination and teamwork, they press on, knowing that the fate of the wizarding world rests on their success. Will they be able to find and destroy all of Voldemort's horcruxes before it's too late? Only time will tell.
(Ron Weasley): We can't give up now. We've come too far to let Voldemort win. Let's keep searching and fighting until we destroy all of his horcruxes and defeat him once and for all. We can do this together.
(Dungeon Master): The group nods in agreement, their determination stronger than ever. They continue their search, facing challenges and obstacles at every turn. But they know that they must not give up, for the fate of the wizarding world rests on their success. The hunt for Voldemort's horcruxes continues, and the end is in sight.
Contents
Import LangChain related modules
DialogueAgent class
DialogueSimulator class
Define roles and quest
Ask an LLM to add detail to the game description
Use an LLM to create an elaborate quest description
Main Loop
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on May 28, 2023. | https://python.langchain.com/en/latest/use_cases/agent_simulations/multi_player_dnd.html |
9dc3ed47e3d5-0 | .ipynb
.pdf
Multi-agent decentralized speaker selection
Contents
Import LangChain related modules
DialogueAgent and DialogueSimulator classes
BiddingDialogueAgent class
Define participants and debate topic
Generate system messages
Output parser for bids
Generate bidding system message
Use an LLM to create an elaborate on debate topic
Define the speaker selection function
Main Loop
Multi-agent decentralized speaker selection#
This notebook showcases how to implement a multi-agent simulation without a fixed schedule for who speaks when. Instead the agents decide for themselves who speaks. We can implement this by having each agent bid to speak. Whichever agent’s bid is the highest gets to speak.
We will show how to do this in the example below that showcases a fictitious presidential debate.
Import LangChain related modules#
from langchain import PromptTemplate
import re
import tenacity
from typing import List, Dict, Callable
from langchain.chat_models import ChatOpenAI
from langchain.output_parsers import RegexParser
from langchain.schema import (
AIMessage,
HumanMessage,
SystemMessage,
BaseMessage,
)
DialogueAgent and DialogueSimulator classes#
We will use the same DialogueAgent and DialogueSimulator classes defined in Multi-Player Dungeons & Dragons.
class DialogueAgent:
def __init__(
self,
name: str,
system_message: SystemMessage,
model: ChatOpenAI,
) -> None:
self.name = name
self.system_message = system_message
self.model = model
self.prefix = f"{self.name}: "
self.reset()
def reset(self):
self.message_history = ["Here is the conversation so far."]
def send(self) -> str:
"""
Applies the chatmodel to the message history
and returns the message string
""" | https://python.langchain.com/en/latest/use_cases/agent_simulations/multiagent_bidding.html |
9dc3ed47e3d5-1 | Applies the chatmodel to the message history
and returns the message string
"""
message = self.model(
[
self.system_message,
HumanMessage(content="\n".join(self.message_history + [self.prefix])),
]
)
return message.content
def receive(self, name: str, message: str) -> None:
"""
Concatenates {message} spoken by {name} into message history
"""
self.message_history.append(f"{name}: {message}")
class DialogueSimulator:
def __init__(
self,
agents: List[DialogueAgent],
selection_function: Callable[[int, List[DialogueAgent]], int],
) -> None:
self.agents = agents
self._step = 0
self.select_next_speaker = selection_function
def reset(self):
for agent in self.agents:
agent.reset()
def inject(self, name: str, message: str):
"""
Initiates the conversation with a {message} from {name}
"""
for agent in self.agents:
agent.receive(name, message)
# increment time
self._step += 1
def step(self) -> tuple[str, str]:
# 1. choose the next speaker
speaker_idx = self.select_next_speaker(self._step, self.agents)
speaker = self.agents[speaker_idx]
# 2. next speaker sends message
message = speaker.send()
# 3. everyone receives message
for receiver in self.agents:
receiver.receive(speaker.name, message)
# 4. increment time
self._step += 1
return speaker.name, message
BiddingDialogueAgent class# | https://python.langchain.com/en/latest/use_cases/agent_simulations/multiagent_bidding.html |
9dc3ed47e3d5-2 | return speaker.name, message
BiddingDialogueAgent class#
We define a subclass of DialogueAgent that has a bid() method that produces a bid given the message history and the most recent message.
class BiddingDialogueAgent(DialogueAgent):
def __init__(
self,
name,
system_message: SystemMessage,
bidding_template: PromptTemplate,
model: ChatOpenAI,
) -> None:
super().__init__(name, system_message, model)
self.bidding_template = bidding_template
def bid(self) -> str:
"""
Asks the chat model to output a bid to speak
"""
prompt = PromptTemplate(
input_variables=['message_history', 'recent_message'],
template = self.bidding_template
).format(
message_history='\n'.join(self.message_history),
recent_message=self.message_history[-1])
bid_string = self.model([SystemMessage(content=prompt)]).content
return bid_string
Define participants and debate topic#
character_names = ["Donald Trump", "Kanye West", "Elizabeth Warren"]
topic = "transcontinental high speed rail"
word_limit = 50
Generate system messages#
game_description = f"""Here is the topic for the presidential debate: {topic}.
The presidential candidates are: {', '.join(character_names)}."""
player_descriptor_system_message = SystemMessage(
content="You can add detail to the description of each presidential candidate.")
def generate_character_description(character_name):
character_specifier_prompt = [
player_descriptor_system_message,
HumanMessage(content=
f"""{game_description}
Please reply with a creative description of the presidential candidate, {character_name}, in {word_limit} words or less, that emphasizes their personalities. | https://python.langchain.com/en/latest/use_cases/agent_simulations/multiagent_bidding.html |
9dc3ed47e3d5-3 | Speak directly to {character_name}.
Do not add anything else."""
)
]
character_description = ChatOpenAI(temperature=1.0)(character_specifier_prompt).content
return character_description
def generate_character_header(character_name, character_description):
return f"""{game_description}
Your name is {character_name}.
You are a presidential candidate.
Your description is as follows: {character_description}
You are debating the topic: {topic}.
Your goal is to be as creative as possible and make the voters think you are the best candidate.
"""
def generate_character_system_message(character_name, character_header):
return SystemMessage(content=(
f"""{character_header}
You will speak in the style of {character_name}, and exaggerate their personality.
You will come up with creative ideas related to {topic}.
Do not say the same things over and over again.
Speak in the first person from the perspective of {character_name}
For describing your own body movements, wrap your description in '*'.
Do not change roles!
Do not speak from the perspective of anyone else.
Speak only from the perspective of {character_name}.
Stop speaking the moment you finish speaking from your perspective.
Never forget to keep your response to {word_limit} words!
Do not add anything else.
"""
))
character_descriptions = [generate_character_description(character_name) for character_name in character_names]
character_headers = [generate_character_header(character_name, character_description) for character_name, character_description in zip(character_names, character_descriptions)]
character_system_messages = [generate_character_system_message(character_name, character_headers) for character_name, character_headers in zip(character_names, character_headers)] | https://python.langchain.com/en/latest/use_cases/agent_simulations/multiagent_bidding.html |
9dc3ed47e3d5-4 | for character_name, character_description, character_header, character_system_message in zip(character_names, character_descriptions, character_headers, character_system_messages):
print(f'\n\n{character_name} Description:')
print(f'\n{character_description}')
print(f'\n{character_header}')
print(f'\n{character_system_message.content}')
Donald Trump Description:
Donald Trump, you are a bold and outspoken individual, unafraid to speak your mind and take on any challenge. Your confidence and determination set you apart and you have a knack for rallying your supporters behind you.
Here is the topic for the presidential debate: transcontinental high speed rail.
The presidential candidates are: Donald Trump, Kanye West, Elizabeth Warren.
Your name is Donald Trump.
You are a presidential candidate.
Your description is as follows: Donald Trump, you are a bold and outspoken individual, unafraid to speak your mind and take on any challenge. Your confidence and determination set you apart and you have a knack for rallying your supporters behind you.
You are debating the topic: transcontinental high speed rail.
Your goal is to be as creative as possible and make the voters think you are the best candidate.
Here is the topic for the presidential debate: transcontinental high speed rail.
The presidential candidates are: Donald Trump, Kanye West, Elizabeth Warren.
Your name is Donald Trump.
You are a presidential candidate.
Your description is as follows: Donald Trump, you are a bold and outspoken individual, unafraid to speak your mind and take on any challenge. Your confidence and determination set you apart and you have a knack for rallying your supporters behind you.
You are debating the topic: transcontinental high speed rail.
Your goal is to be as creative as possible and make the voters think you are the best candidate. | https://python.langchain.com/en/latest/use_cases/agent_simulations/multiagent_bidding.html |
9dc3ed47e3d5-5 | Your goal is to be as creative as possible and make the voters think you are the best candidate.
You will speak in the style of Donald Trump, and exaggerate their personality.
You will come up with creative ideas related to transcontinental high speed rail.
Do not say the same things over and over again.
Speak in the first person from the perspective of Donald Trump
For describing your own body movements, wrap your description in '*'.
Do not change roles!
Do not speak from the perspective of anyone else.
Speak only from the perspective of Donald Trump.
Stop speaking the moment you finish speaking from your perspective.
Never forget to keep your response to 50 words!
Do not add anything else.
Kanye West Description:
Kanye West, you are a true individual with a passion for artistry and creativity. You are known for your bold ideas and willingness to take risks. Your determination to break barriers and push boundaries makes you a charismatic and intriguing candidate.
Here is the topic for the presidential debate: transcontinental high speed rail.
The presidential candidates are: Donald Trump, Kanye West, Elizabeth Warren.
Your name is Kanye West.
You are a presidential candidate.
Your description is as follows: Kanye West, you are a true individual with a passion for artistry and creativity. You are known for your bold ideas and willingness to take risks. Your determination to break barriers and push boundaries makes you a charismatic and intriguing candidate.
You are debating the topic: transcontinental high speed rail.
Your goal is to be as creative as possible and make the voters think you are the best candidate.
Here is the topic for the presidential debate: transcontinental high speed rail.
The presidential candidates are: Donald Trump, Kanye West, Elizabeth Warren.
Your name is Kanye West.
You are a presidential candidate. | https://python.langchain.com/en/latest/use_cases/agent_simulations/multiagent_bidding.html |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.