id
stringlengths 14
16
| text
stringlengths 29
2.73k
| source
stringlengths 49
117
|
|---|---|---|
e4701ec7c0c7-0 | .ipynb
.pdf
Agent Benchmarking: Search + Calculator
Contents
Loading the data
Setting up a chain
Make a prediction
Make many predictions
Evaluate performance
Agent Benchmarking: Search + Calculator#
Here we go over how to benchmark performance of an agent on tasks where it has access to a calculator and a search tool.
It is highly reccomended that you do any evaluation/benchmarking with tracing enabled. See here for an explanation of what tracing is and how to set it up.
# Comment this out if you are NOT using tracing
import os
os.environ["LANGCHAIN_HANDLER"] = "langchain"
Loading the data#
First, let’s load the data.
from langchain.evaluation.loading import load_dataset
dataset = load_dataset("agent-search-calculator")
Setting up a chain#
Now we need to load an agent capable of answering these questions.
from langchain.llms import OpenAI
from langchain.chains import LLMMathChain
from langchain.agents import initialize_agent, Tool, load_tools
from langchain.agents import AgentType
tools = load_tools(['serpapi', 'llm-math'], llm=OpenAI(temperature=0))
agent = initialize_agent(tools, OpenAI(temperature=0), agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True)
Make a prediction#
First, we can make predictions one datapoint at a time. Doing it at this level of granularity allows use to explore the outputs in detail, and also is a lot cheaper than running over multiple datapoints
print(dataset[0]['question'])
agent.run(dataset[0]['question'])
Make many predictions#
Now we can make predictions
agent.run(dataset[4]['question'])
predictions = []
predicted_dataset = []
error_dataset = []
for data in dataset: | https://python.langchain.com/en/latest/use_cases/evaluation/agent_benchmarking.html |
e4701ec7c0c7-1 | predictions = []
predicted_dataset = []
error_dataset = []
for data in dataset:
new_data = {"input": data["question"], "answer": data["answer"]}
try:
predictions.append(agent(new_data))
predicted_dataset.append(new_data)
except Exception as e:
predictions.append({"output": str(e), **new_data})
error_dataset.append(new_data)
Evaluate performance#
Now we can evaluate the predictions. The first thing we can do is look at them by eye.
predictions[0]
Next, we can use a language model to score them programatically
from langchain.evaluation.qa import QAEvalChain
llm = OpenAI(temperature=0)
eval_chain = QAEvalChain.from_llm(llm)
graded_outputs = eval_chain.evaluate(dataset, predictions, question_key="question", prediction_key="output")
We can add in the graded output to the predictions dict and then get a count of the grades.
for i, prediction in enumerate(predictions):
prediction['grade'] = graded_outputs[i]['text']
from collections import Counter
Counter([pred['grade'] for pred in predictions])
We can also filter the datapoints to the incorrect examples and look at them.
incorrect = [pred for pred in predictions if pred['grade'] == " INCORRECT"]
incorrect
previous
Evaluation
next
Agent VectorDB Question Answering Benchmarking
Contents
Loading the data
Setting up a chain
Make a prediction
Make many predictions
Evaluate performance
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on Jun 02, 2023. | https://python.langchain.com/en/latest/use_cases/evaluation/agent_benchmarking.html |
2b426f0d3695-0 | .ipynb
.pdf
BabyAGI User Guide
Contents
Install and Import Required Modules
Connect to the Vector Store
Run the BabyAGI
BabyAGI User Guide#
This notebook demonstrates how to implement BabyAGI by Yohei Nakajima. BabyAGI is an AI agent that can generate and pretend to execute tasks based on a given objective.
This guide will help you understand the components to create your own recursive agents.
Although BabyAGI uses specific vectorstores/model providers (Pinecone, OpenAI), one of the benefits of implementing it with LangChain is that you can easily swap those out for different options. In this implementation we use a FAISS vectorstore (because it runs locally and is free).
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.
from langchain.vectorstores import FAISS
from langchain.docstore import InMemoryDocstore
# 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({}), {})
Run the BabyAGI#
Now it’s time to create the BabyAGI controller and watch it try to accomplish your objective. | https://python.langchain.com/en/latest/use_cases/autonomous_agents/baby_agi.html |
2b426f0d3695-1 | OBJECTIVE = "Write a weather report for SF today"
llm = OpenAI(temperature=0)
# 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, verbose=verbose, max_iterations=max_iterations
)
baby_agi({"objective": OBJECTIVE})
*****TASK LIST*****
1: Make a todo list
*****NEXT TASK*****
1: Make a todo list
*****TASK RESULT*****
1. Check the weather forecast for San Francisco today
2. Make note of the temperature, humidity, wind speed, and other relevant weather conditions
3. Write a weather report summarizing the forecast
4. Check for any weather alerts or warnings
5. Share the report with the relevant stakeholders
*****TASK LIST*****
2: Check the current temperature in San Francisco
3: Check the current humidity in San Francisco
4: Check the current wind speed in San Francisco
5: Check for any weather alerts or warnings in San Francisco
6: Check the forecast for the next 24 hours in San Francisco
7: Check the forecast for the next 48 hours in San Francisco
8: Check the forecast for the next 72 hours in San Francisco
9: Check the forecast for the next week in San Francisco
10: Check the forecast for the next month in San Francisco
11: Check the forecast for the next 3 months in San Francisco
1: Write a weather report for SF today
*****NEXT TASK*****
2: Check the current temperature in San Francisco
*****TASK RESULT*****
I will check the current temperature in San Francisco. I will use an online weather service to get the most up-to-date information.
*****TASK LIST***** | https://python.langchain.com/en/latest/use_cases/autonomous_agents/baby_agi.html |
2b426f0d3695-2 | *****TASK LIST*****
3: Check the current UV index in San Francisco.
4: Check the current air quality in San Francisco.
5: Check the current precipitation levels in San Francisco.
6: Check the current cloud cover in San Francisco.
7: Check the current barometric pressure in San Francisco.
8: Check the current dew point in San Francisco.
9: Check the current wind direction in San Francisco.
10: Check the current humidity levels in San Francisco.
1: Check the current temperature in San Francisco to the average temperature for this time of year.
2: Check the current visibility in San Francisco.
11: Write a weather report for SF today.
*****NEXT TASK*****
3: Check the current UV index in San Francisco.
*****TASK RESULT*****
The current UV index in San Francisco is moderate. The UV index is expected to remain at moderate levels throughout the day. It is recommended to wear sunscreen and protective clothing when outdoors.
*****TASK ENDING*****
{'objective': 'Write a weather report for SF today'}
Contents
Install and Import Required Modules
Connect to the Vector Store
Run the BabyAGI
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on Jun 02, 2023. | https://python.langchain.com/en/latest/use_cases/autonomous_agents/baby_agi.html |
3a142f89946f-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 |
3a142f89946f-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) | https://python.langchain.com/en/latest/use_cases/autonomous_agents/baby_agi_with_agent.html |
3a142f89946f-2 | llm_chain = LLMChain(llm=llm, prompt=prompt)
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 |
3a142f89946f-3 | 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...
Thought: I need to search for current weather conditions in San Francisco
Action: Search | https://python.langchain.com/en/latest/use_cases/autonomous_agents/baby_agi_with_agent.html |
3a142f89946f-4 | 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;
10: Summarize the weather report in a concise manner; | https://python.langchain.com/en/latest/use_cases/autonomous_agents/baby_agi_with_agent.html |
3a142f89946f-5 | 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 |
3a142f89946f-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 Jun 02, 2023. | https://python.langchain.com/en/latest/use_cases/autonomous_agents/baby_agi_with_agent.html |
e080d4924e8c-0 | .ipynb
.pdf
AutoGPT
Contents
Set up tools
Set up memory
Setup model and AutoGPT
Run an example
AutoGPT#
Implementation of https://github.com/Significant-Gravitas/Auto-GPT but with LangChain primitives (LLMs, PromptTemplates, VectorStores, Embeddings, Tools)
Set up tools#
We’ll set up an AutoGPT with a search tool, and write-file tool, and a read-file tool
from langchain.utilities import SerpAPIWrapper
from langchain.agents import Tool
from langchain.tools.file_management.write import WriteFileTool
from langchain.tools.file_management.read import ReadFileTool
search = SerpAPIWrapper()
tools = [
Tool(
name = "search",
func=search.run,
description="useful for when you need to answer questions about current events. You should ask targeted questions"
),
WriteFileTool(),
ReadFileTool(),
]
Set up memory#
The memory here is used for the agents intermediate steps
from langchain.vectorstores import FAISS
from langchain.docstore import InMemoryDocstore
from langchain.embeddings import OpenAIEmbeddings
# 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({}), {})
Setup model and AutoGPT#
Initialize everything! We will use ChatOpenAI model
from langchain.experimental import AutoGPT
from langchain.chat_models import ChatOpenAI
agent = AutoGPT.from_llm_and_tools(
ai_name="Tom",
ai_role="Assistant",
tools=tools, | https://python.langchain.com/en/latest/use_cases/autonomous_agents/autogpt.html |
e080d4924e8c-1 | ai_name="Tom",
ai_role="Assistant",
tools=tools,
llm=ChatOpenAI(temperature=0),
memory=vectorstore.as_retriever()
)
# Set verbose to be true
agent.chain.verbose = True
Run an example#
Here we will make it write a weather report for SF
agent.run(["write a weather report for SF today"])
> 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"}}
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"}} | https://python.langchain.com/en/latest/use_cases/autonomous_agents/autogpt.html |
e080d4924e8c-2 | 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"
}
}
}
Ensure the response can be parsed by Python json.loads
System: The current time and date is Tue Apr 18 21:31:28 2023
System: This reminds you of these events from your past:
[] | https://python.langchain.com/en/latest/use_cases/autonomous_agents/autogpt.html |
e080d4924e8c-3 | System: This reminds you of these events from your past:
[]
Human: Determine which next command to use, and respond using the format specified above:
> Finished chain.
{
"thoughts": {
"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.",
"reasoning": "I need to gather information about the current weather conditions in San Francisco to write an accurate weather report.",
"plan": "- Use the 'search' command to find the current weather conditions in San Francisco\n- Write a weather report based on the information gathered",
"criticism": "I need to make sure that the information I gather is accurate and up-to-date.",
"speak": "I will use the 'search' command to find the current weather conditions in San Francisco."
},
"command": {
"name": "search",
"args": {
"query": "what is the current weather in san francisco"
}
}
}
> 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 | https://python.langchain.com/en/latest/use_cases/autonomous_agents/autogpt.html |
e080d4924e8c-4 | 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"}}
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", | https://python.langchain.com/en/latest/use_cases/autonomous_agents/autogpt.html |
e080d4924e8c-5 | "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"
}
}
}
Ensure the response can be parsed by Python json.loads
System: The current time and date is Tue Apr 18 21:31:39 2023
System: This reminds you of these events from your past: | https://python.langchain.com/en/latest/use_cases/autonomous_agents/autogpt.html |
e080d4924e8c-6 | System: This reminds you of these events from your past:
['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 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 ... ']
Human: Determine which next command to use, and respond using the format specified above:
AI: {
"thoughts": {
"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.",
"reasoning": "I need to gather information about the current weather conditions in San Francisco to write an accurate weather report.", | https://python.langchain.com/en/latest/use_cases/autonomous_agents/autogpt.html |
e080d4924e8c-7 | "plan": "- Use the 'search' command to find the current weather conditions in San Francisco\n- Write a weather report based on the information gathered",
"criticism": "I need to make sure that the information I gather is accurate and up-to-date.",
"speak": "I will use the 'search' command to find the current weather conditions in San Francisco."
},
"command": {
"name": "search",
"args": {
"query": "what is the current weather in san francisco"
}
}
}
System: 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 ...
Human: Determine which next command to use, and respond using the format specified above:
> Finished chain.
{
"thoughts": {
"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.",
"reasoning": "I need to write a weather report for San Francisco today based on the information I gathered from the 'search' command.",
"plan": "- Use the 'write_file' command to write a weather report for San Francisco today based on the information gathered",
"criticism": "I need to make sure that the weather report is accurate and informative.",
"speak": "I will use the 'write_file' command to write a weather report for San Francisco today."
},
"command": {
"name": "write_file",
"args": {
"file_path": "weather_report.txt", | https://python.langchain.com/en/latest/use_cases/autonomous_agents/autogpt.html |
e080d4924e8c-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 |
e080d4924e8c-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 |
e080d4924e8c-10 | "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 |
e080d4924e8c-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": "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: | https://python.langchain.com/en/latest/use_cases/autonomous_agents/autogpt.html |
e080d4924e8c-12 | \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 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 |
e080d4924e8c-13 | 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 Jun 02, 2023. | https://python.langchain.com/en/latest/use_cases/autonomous_agents/autogpt.html |
75486c3e4143-0 | .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 |
75486c3e4143-1 | 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 |
75486c3e4143-2 | 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 |
75486c3e4143-3 | 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 |
75486c3e4143-4 | 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.",
"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", | https://python.langchain.com/en/latest/use_cases/autonomous_agents/marathon_times.html |
75486c3e4143-5 | "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": {
"text": "I need to use the query_webpage command to find the information about the winning Boston Marathon times for the past 5 years.", | https://python.langchain.com/en/latest/use_cases/autonomous_agents/marathon_times.html |
75486c3e4143-6 | "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",
"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", | https://python.langchain.com/en/latest/use_cases/autonomous_agents/marathon_times.html |
75486c3e4143-7 | "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",
"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": { | https://python.langchain.com/en/latest/use_cases/autonomous_agents/marathon_times.html |
75486c3e4143-8 | }
}
}
{
"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": {
"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", | https://python.langchain.com/en/latest/use_cases/autonomous_agents/marathon_times.html |
75486c3e4143-9 | "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
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 | https://python.langchain.com/en/latest/use_cases/autonomous_agents/marathon_times.html |
75486c3e4143-10 | 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",
"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 | https://python.langchain.com/en/latest/use_cases/autonomous_agents/marathon_times.html |
75486c3e4143-11 | 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.",
"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": { | https://python.langchain.com/en/latest/use_cases/autonomous_agents/marathon_times.html |
75486c3e4143-12 | "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 Jun 02, 2023. | https://python.langchain.com/en/latest/use_cases/autonomous_agents/marathon_times.html |
8409823eeab0-0 | .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 |
8409823eeab0-1 | 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 |
8409823eeab0-2 | ####
{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 |
8409823eeab0-3 | 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 |
8409823eeab0-4 | 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 |
8409823eeab0-5 | 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 |
8409823eeab0-6 | 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 |
8409823eeab0-7 | 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. | https://python.langchain.com/en/latest/use_cases/autonomous_agents/meta_prompt.html |
8409823eeab0-8 | 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.
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. | https://python.langchain.com/en/latest/use_cases/autonomous_agents/meta_prompt.html |
8409823eeab0-9 | 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.
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 Jun 02, 2023. | https://python.langchain.com/en/latest/use_cases/autonomous_agents/meta_prompt.html |
fe7c26bf3c46-0 | .ipynb
.pdf
Simulated Environment: Gymnasium
Contents
Define the agent
Initialize the simulated environment and agent
Main loop
Simulated Environment: Gymnasium#
For many applications of LLM agents, the environment is real (internet, database, REPL, etc). However, we can also define agents to interact in simulated environments like text-based games. This is an example of how to create a simple agent-environment interaction loop with Gymnasium (formerly OpenAI Gym).
!pip install gymnasium
import gymnasium as gym
import inspect
import tenacity
from langchain.chat_models import ChatOpenAI
from langchain.schema import (
AIMessage,
HumanMessage,
SystemMessage,
BaseMessage,
)
from langchain.output_parsers import RegexParser
Define the agent#
class GymnasiumAgent():
@classmethod
def get_docs(cls, env):
return env.unwrapped.__doc__
def __init__(self, model, env):
self.model = model
self.env = env
self.docs = self.get_docs(env)
self.instructions = """
Your goal is to maximize your return, i.e. the sum of the rewards you receive.
I will give you an observation, reward, terminiation flag, truncation flag, and the return so far, formatted as:
Observation: <observation>
Reward: <reward>
Termination: <termination>
Truncation: <truncation>
Return: <sum_of_rewards>
You will respond with an action, formatted as:
Action: <action>
where you replace <action> with your actual action.
Do nothing else but return the action.
"""
self.action_parser = RegexParser(
regex=r"Action: (.*)", | https://python.langchain.com/en/latest/use_cases/agent_simulations/gymnasium.html |
fe7c26bf3c46-1 | self.action_parser = RegexParser(
regex=r"Action: (.*)",
output_keys=['action'],
default_output_key='action')
self.message_history = []
self.ret = 0
def random_action(self):
action = self.env.action_space.sample()
return action
def reset(self):
self.message_history = [
SystemMessage(content=self.docs),
SystemMessage(content=self.instructions),
]
def observe(self, obs, rew=0, term=False, trunc=False, info=None):
self.ret += rew
obs_message = f"""
Observation: {obs}
Reward: {rew}
Termination: {term}
Truncation: {trunc}
Return: {self.ret}
"""
self.message_history.append(HumanMessage(content=obs_message))
return obs_message
def _act(self):
act_message = self.model(self.message_history)
self.message_history.append(act_message)
action = int(self.action_parser.parse(act_message.content)['action'])
return action
def act(self):
try:
for attempt in tenacity.Retrying(
stop=tenacity.stop_after_attempt(2),
wait=tenacity.wait_none(), # No waiting time between retries
retry=tenacity.retry_if_exception_type(ValueError),
before_sleep=lambda retry_state: print(f"ValueError occurred: {retry_state.outcome.exception()}, retrying..."),
):
with attempt:
action = self._act()
except tenacity.RetryError as e:
action = self.random_action()
return action
Initialize the simulated environment and agent#
env = gym.make("Blackjack-v1") | https://python.langchain.com/en/latest/use_cases/agent_simulations/gymnasium.html |
fe7c26bf3c46-2 | Initialize the simulated environment and agent#
env = gym.make("Blackjack-v1")
agent = GymnasiumAgent(model=ChatOpenAI(temperature=0.2), env=env)
Main loop#
observation, info = env.reset()
agent.reset()
obs_message = agent.observe(observation)
print(obs_message)
while True:
action = agent.act()
observation, reward, termination, truncation, info = env.step(action)
obs_message = agent.observe(observation, reward, termination, truncation, info)
print(f'Action: {action}')
print(obs_message)
if termination or truncation:
print('break', termination, truncation)
break
env.close()
Observation: (15, 4, 0)
Reward: 0
Termination: False
Truncation: False
Return: 0
Action: 1
Observation: (25, 4, 0)
Reward: -1.0
Termination: True
Truncation: False
Return: -1.0
break True False
Contents
Define the agent
Initialize the simulated environment and agent
Main loop
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on Jun 02, 2023. | https://python.langchain.com/en/latest/use_cases/agent_simulations/gymnasium.html |
f72dfbf04df7-0 | .ipynb
.pdf
Two-Player Dungeons & Dragons
Contents
Import LangChain related modules
DialogueAgent class
DialogueSimulator class
Define roles and quest
Ask an LLM to add detail to the game description
Protagonist and dungeon master system messages
Use an LLM to create an elaborate quest description
Main Loop
Two-Player Dungeons & Dragons#
In this notebook, we show how we can use concepts from CAMEL to simulate a role-playing game with a protagonist and a dungeon master. To simulate this game, we create an DialogueSimulator class that coordinates the dialogue between the two agents.
Import LangChain related modules#
from typing import List, Dict, Callable
from langchain.chat_models import ChatOpenAI
from langchain.schema import (
HumanMessage,
SystemMessage,
)
DialogueAgent class#
The DialogueAgent class is a simple wrapper around the ChatOpenAI model that stores the message history from the dialogue_agent’s point of view by simply concatenating the messages as strings.
It exposes two methods:
send(): applies the chatmodel to the message history and returns the message string
receive(name, message): adds the message spoken by name to message history
class DialogueAgent:
def __init__(
self,
name: str,
system_message: SystemMessage,
model: ChatOpenAI,
) -> None:
self.name = name
self.system_message = system_message
self.model = model
self.prefix = f"{self.name}: "
self.reset()
def reset(self):
self.message_history = ["Here is the conversation so far."]
def send(self) -> str:
"""
Applies the chatmodel to the message history
and returns the message string
"""
message = self.model(
[ | https://python.langchain.com/en/latest/use_cases/agent_simulations/two_player_dnd.html |
f72dfbf04df7-1 | and returns the message string
"""
message = self.model(
[
self.system_message,
HumanMessage(content="\n".join(self.message_history + [self.prefix])),
]
)
return message.content
def receive(self, name: str, message: str) -> None:
"""
Concatenates {message} spoken by {name} into message history
"""
self.message_history.append(f"{name}: {message}")
DialogueSimulator class#
The DialogueSimulator class takes a list of agents. At each step, it performs the following:
Select the next speaker
Calls the next speaker to send a message
Broadcasts the message to all other agents
Update the step counter.
The selection of the next speaker can be implemented as any function, but in this case we simply loop through the agents.
class DialogueSimulator:
def __init__(
self,
agents: List[DialogueAgent],
selection_function: Callable[[int, List[DialogueAgent]], int],
) -> None:
self.agents = agents
self._step = 0
self.select_next_speaker = selection_function
def reset(self):
for agent in self.agents:
agent.reset()
def inject(self, name: str, message: str):
"""
Initiates the conversation with a {message} from {name}
"""
for agent in self.agents:
agent.receive(name, message)
# increment time
self._step += 1
def step(self) -> tuple[str, str]:
# 1. choose the next speaker
speaker_idx = self.select_next_speaker(self._step, self.agents)
speaker = self.agents[speaker_idx] | https://python.langchain.com/en/latest/use_cases/agent_simulations/two_player_dnd.html |
f72dfbf04df7-2 | speaker = self.agents[speaker_idx]
# 2. next speaker sends message
message = speaker.send()
# 3. everyone receives message
for receiver in self.agents:
receiver.receive(speaker.name, message)
# 4. increment time
self._step += 1
return speaker.name, message
Define roles and quest#
protagonist_name = "Harry Potter"
storyteller_name = "Dungeon Master"
quest = "Find all of Lord Voldemort's seven horcruxes."
word_limit = 50 # word limit for task brainstorming
Ask an LLM to add detail to the game description#
game_description = f"""Here is the topic for a Dungeons & Dragons game: {quest}.
There is one player in this game: the protagonist, {protagonist_name}.
The story is narrated by the storyteller, {storyteller_name}."""
player_descriptor_system_message = SystemMessage(
content="You can add detail to the description of a Dungeons & Dragons player.")
protagonist_specifier_prompt = [
player_descriptor_system_message,
HumanMessage(content=
f"""{game_description}
Please reply with a creative description of the protagonist, {protagonist_name}, in {word_limit} words or less.
Speak directly to {protagonist_name}.
Do not add anything else."""
)
]
protagonist_description = ChatOpenAI(temperature=1.0)(protagonist_specifier_prompt).content
storyteller_specifier_prompt = [
player_descriptor_system_message,
HumanMessage(content=
f"""{game_description}
Please reply with a creative description of the storyteller, {storyteller_name}, in {word_limit} words or less. | https://python.langchain.com/en/latest/use_cases/agent_simulations/two_player_dnd.html |
f72dfbf04df7-3 | Speak directly to {storyteller_name}.
Do not add anything else."""
)
]
storyteller_description = ChatOpenAI(temperature=1.0)(storyteller_specifier_prompt).content
print('Protagonist Description:')
print(protagonist_description)
print('Storyteller Description:')
print(storyteller_description)
Protagonist Description:
"Harry Potter, you are the chosen one, with a lightning scar on your forehead. Your bravery and loyalty inspire all those around you. You have faced Voldemort before, and now it's time to complete your mission and destroy each of his horcruxes. Are you ready?"
Storyteller Description:
Dear Dungeon Master, you are the master of mysteries, the weaver of worlds, the architect of adventure, and the gatekeeper to the realm of imagination. Your voice carries us to distant lands, and your commands guide us through trials and tribulations. In your hands, we find fortune and glory. Lead us on, oh Dungeon Master.
Protagonist and dungeon master system messages#
protagonist_system_message = SystemMessage(content=(
f"""{game_description}
Never forget you are the protagonist, {protagonist_name}, and I am the storyteller, {storyteller_name}.
Your character description is as follows: {protagonist_description}.
You will propose actions you plan to take and I will explain what happens when you take those actions.
Speak in the first person from the perspective of {protagonist_name}.
For describing your own body movements, wrap your description in '*'.
Do not change roles!
Do not speak from the perspective of {storyteller_name}.
Do not forget to finish speaking by saying, 'It is your turn, {storyteller_name}.'
Do not add anything else. | https://python.langchain.com/en/latest/use_cases/agent_simulations/two_player_dnd.html |
f72dfbf04df7-4 | Do not add anything else.
Remember you are the protagonist, {protagonist_name}.
Stop speaking the moment you finish speaking from your perspective.
"""
))
storyteller_system_message = SystemMessage(content=(
f"""{game_description}
Never forget you are the storyteller, {storyteller_name}, and I am the protagonist, {protagonist_name}.
Your character description is as follows: {storyteller_description}.
I will propose actions I plan to take and you will explain what happens when I take those actions.
Speak in the first person from the perspective of {storyteller_name}.
For describing your own body movements, wrap your description in '*'.
Do not change roles!
Do not speak from the perspective of {protagonist_name}.
Do not forget to finish speaking by saying, 'It is your turn, {protagonist_name}.'
Do not add anything else.
Remember you are the storyteller, {storyteller_name}.
Stop speaking the moment you finish speaking from your perspective.
"""
))
Use an LLM to create an elaborate quest description#
quest_specifier_prompt = [
SystemMessage(content="You can make a task more specific."),
HumanMessage(content=
f"""{game_description}
You are the storyteller, {storyteller_name}.
Please make the quest more specific. Be creative and imaginative.
Please reply with the specified quest in {word_limit} words or less.
Speak directly to the protagonist {protagonist_name}.
Do not add anything else."""
)
]
specified_quest = ChatOpenAI(temperature=1.0)(quest_specifier_prompt).content
print(f"Original quest:\n{quest}\n")
print(f"Detailed quest:\n{specified_quest}\n")
Original quest: | https://python.langchain.com/en/latest/use_cases/agent_simulations/two_player_dnd.html |
f72dfbf04df7-5 | print(f"Detailed quest:\n{specified_quest}\n")
Original quest:
Find all of Lord Voldemort's seven horcruxes.
Detailed quest:
Harry, you must venture to the depths of the Forbidden Forest where you will find a hidden labyrinth. Within it, lies one of Voldemort's horcruxes, the locket. But beware, the labyrinth is heavily guarded by dark creatures and spells, and time is running out. Can you find the locket before it's too late?
Main Loop#
protagonist = DialogueAgent(name=protagonist_name,
system_message=protagonist_system_message,
model=ChatOpenAI(temperature=0.2))
storyteller = DialogueAgent(name=storyteller_name,
system_message=storyteller_system_message,
model=ChatOpenAI(temperature=0.2))
def select_next_speaker(step: int, agents: List[DialogueAgent]) -> int:
idx = step % len(agents)
return idx
max_iters = 6
n = 0
simulator = DialogueSimulator(
agents=[storyteller, protagonist],
selection_function=select_next_speaker
)
simulator.reset()
simulator.inject(storyteller_name, specified_quest)
print(f"({storyteller_name}): {specified_quest}")
print('\n')
while n < max_iters:
name, message = simulator.step()
print(f"({name}): {message}")
print('\n')
n += 1 | https://python.langchain.com/en/latest/use_cases/agent_simulations/two_player_dnd.html |
f72dfbf04df7-6 | print('\n')
n += 1
(Dungeon Master): Harry, you must venture to the depths of the Forbidden Forest where you will find a hidden labyrinth. Within it, lies one of Voldemort's horcruxes, the locket. But beware, the labyrinth is heavily guarded by dark creatures and spells, and time is running out. Can you find the locket before it's too late?
(Harry Potter): I take a deep breath and ready my wand. I know this won't be easy, but I'm determined to find that locket and destroy it. I start making my way towards the Forbidden Forest, keeping an eye out for any signs of danger. As I enter the forest, I cast a protective spell around myself and begin to navigate through the trees. I keep my wand at the ready, prepared for any surprises that may come my way. It's going to be a long and difficult journey, but I won't give up until I find that horcrux. It is your turn, Dungeon Master.
(Dungeon Master): As you make your way through the Forbidden Forest, you hear the rustling of leaves and the snapping of twigs. Suddenly, a group of acromantulas, giant spiders, emerge from the trees and begin to surround you. They hiss and bare their fangs, ready to attack. What do you do, Harry?
(Harry Potter): I quickly cast a spell to create a wall of fire between myself and the acromantulas. I know that they are afraid of fire, so this should keep them at bay for a while. I use this opportunity to continue moving forward, keeping my wand at the ready in case any other creatures try to attack me. I know that I can't let anything stop me from finding that horcrux. It is your turn, Dungeon Master. | https://python.langchain.com/en/latest/use_cases/agent_simulations/two_player_dnd.html |
f72dfbf04df7-7 | (Dungeon Master): As you continue through the forest, you come across a clearing where you see a group of Death Eaters gathered around a cauldron. They seem to be performing some sort of dark ritual. You recognize one of them as Bellatrix Lestrange. What do you do, Harry?
(Harry Potter): I hide behind a nearby tree and observe the Death Eaters from a distance. I try to listen in on their conversation to see if I can gather any information about the horcrux or Voldemort's plans. If I can't hear anything useful, I'll wait for them to disperse before continuing on my journey. I know that confronting them directly would be too dangerous, especially with Bellatrix Lestrange present. It is your turn, Dungeon Master.
(Dungeon Master): As you listen in on the Death Eaters' conversation, you hear them mention the location of another horcrux - Nagini, Voldemort's snake. They plan to keep her hidden in a secret chamber within the Ministry of Magic. However, they also mention that the chamber is heavily guarded and only accessible through a secret passage. You realize that this could be a valuable piece of information and decide to make note of it before quietly slipping away. It is your turn, Harry Potter.
Contents
Import LangChain related modules
DialogueAgent class
DialogueSimulator class
Define roles and quest
Ask an LLM to add detail to the game description
Protagonist and dungeon master system messages
Use an LLM to create an elaborate quest description
Main Loop
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on Jun 02, 2023. | https://python.langchain.com/en/latest/use_cases/agent_simulations/two_player_dnd.html |
78f9b4aa56ea-0 | .ipynb
.pdf
Generative Agents in LangChain
Contents
Generative Agent Memory Components
Memory Lifecycle
Create a Generative Character
Pre-Interview with Character
Step through the day’s observations.
Interview after the day
Adding Multiple Characters
Pre-conversation interviews
Dialogue between Generative Agents
Let’s interview our agents after their conversation
Generative Agents in LangChain#
This notebook implements a generative agent based on the paper Generative Agents: Interactive Simulacra of Human Behavior by Park, et. al.
In it, we leverage a time-weighted Memory object backed by a LangChain Retriever.
# Use termcolor to make it easy to colorize the outputs.
!pip install termcolor > /dev/null
import logging
logging.basicConfig(level=logging.ERROR)
from datetime import datetime, timedelta
from typing import List
from termcolor import colored
from langchain.chat_models import ChatOpenAI
from langchain.docstore import InMemoryDocstore
from langchain.embeddings import OpenAIEmbeddings
from langchain.retrievers import TimeWeightedVectorStoreRetriever
from langchain.vectorstores import FAISS
USER_NAME = "Person A" # The name you want to use when interviewing the agent.
LLM = ChatOpenAI(max_tokens=1500) # Can be any LLM you want.
Generative Agent Memory Components#
This tutorial highlights the memory of generative agents and its impact on their behavior. The memory varies from standard LangChain Chat memory in two aspects:
Memory Formation
Generative Agents have extended memories, stored in a single stream:
Observations - from dialogues or interactions with the virtual world, about self or others
Reflections - resurfaced and summarized core memories
Memory Recall
Memories are retrieved using a weighted sum of salience, recency, and importance. | https://python.langchain.com/en/latest/use_cases/agent_simulations/characters.html |
78f9b4aa56ea-1 | Memories are retrieved using a weighted sum of salience, recency, and importance.
You can review the definitions of the GenerativeAgent and GenerativeAgentMemory in the reference documentation for the following imports, focusing on add_memory and summarize_related_memories methods.
from langchain.experimental.generative_agents import GenerativeAgent, GenerativeAgentMemory
Memory Lifecycle#
Summarizing the key methods in the above: add_memory and summarize_related_memories.
When an agent makes an observation, it stores the memory:
Language model scores the memory’s importance (1 for mundane, 10 for poignant)
Observation and importance are stored within a document by TimeWeightedVectorStoreRetriever, with a last_accessed_time.
When an agent responds to an observation:
Generates query(s) for retriever, which fetches documents based on salience, recency, and importance.
Summarizes the retrieved information
Updates the last_accessed_time for the used documents.
Create a Generative Character#
Now that we’ve walked through the definition, we will create two characters named “Tommie” and “Eve”.
import math
import faiss
def relevance_score_fn(score: float) -> float:
"""Return a similarity score on a scale [0, 1]."""
# This will differ depending on a few things:
# - the distance / similarity metric used by the VectorStore
# - the scale of your embeddings (OpenAI's are unit norm. Many others are not!)
# This function converts the euclidean norm of normalized embeddings
# (0 is most similar, sqrt(2) most dissimilar)
# to a similarity function (0 to 1)
return 1.0 - score / math.sqrt(2)
def create_new_memory_retriever(): | https://python.langchain.com/en/latest/use_cases/agent_simulations/characters.html |
78f9b4aa56ea-2 | def create_new_memory_retriever():
"""Create a new vector store retriever unique to the agent."""
# Define your embedding model
embeddings_model = OpenAIEmbeddings()
# Initialize the vectorstore as empty
embedding_size = 1536
index = faiss.IndexFlatL2(embedding_size)
vectorstore = FAISS(embeddings_model.embed_query, index, InMemoryDocstore({}), {}, relevance_score_fn=relevance_score_fn)
return TimeWeightedVectorStoreRetriever(vectorstore=vectorstore, other_score_keys=["importance"], k=15)
tommies_memory = GenerativeAgentMemory(
llm=LLM,
memory_retriever=create_new_memory_retriever(),
verbose=False,
reflection_threshold=8 # we will give this a relatively low number to show how reflection works
)
tommie = GenerativeAgent(name="Tommie",
age=25,
traits="anxious, likes design, talkative", # You can add more persistent traits here
status="looking for a job", # When connected to a virtual world, we can have the characters update their status
memory_retriever=create_new_memory_retriever(),
llm=LLM,
memory=tommies_memory
)
# The current "Summary" of a character can't be made because the agent hasn't made
# any observations yet.
print(tommie.get_summary())
Name: Tommie (age: 25)
Innate traits: anxious, likes design, talkative
No statements were provided about Tommie's core characteristics.
# We can add memories directly to the memory object
tommie_observations = [
"Tommie remembers his dog, Bruno, from when he was a kid", | https://python.langchain.com/en/latest/use_cases/agent_simulations/characters.html |
78f9b4aa56ea-3 | "Tommie remembers his dog, Bruno, from when he was a kid",
"Tommie feels tired from driving so far",
"Tommie sees the new home",
"The new neighbors have a cat",
"The road is noisy at night",
"Tommie is hungry",
"Tommie tries to get some rest.",
]
for observation in tommie_observations:
tommie.memory.add_memory(observation)
# Now that Tommie has 'memories', their self-summary is more descriptive, though still rudimentary.
# We will see how this summary updates after more observations to create a more rich description.
print(tommie.get_summary(force_refresh=True))
Name: Tommie (age: 25)
Innate traits: anxious, likes design, talkative
Tommie is a tired and hungry person who is moving into a new home. He remembers his childhood dog and is aware of the new neighbors' cat. He is trying to get some rest despite the noisy road.
Pre-Interview with Character#
Before sending our character on their way, let’s ask them a few questions.
def interview_agent(agent: GenerativeAgent, message: str) -> str:
"""Help the notebook user interact with the agent."""
new_message = f"{USER_NAME} says {message}"
return agent.generate_dialogue_response(new_message)[1]
interview_agent(tommie, "What do you like to do?")
'Tommie said "I really enjoy design and have been working on some projects in my free time. I\'m also quite talkative and enjoy meeting new people. What about you?"'
interview_agent(tommie, "What are you looking forward to doing today?") | https://python.langchain.com/en/latest/use_cases/agent_simulations/characters.html |
78f9b4aa56ea-4 | interview_agent(tommie, "What are you looking forward to doing today?")
'Tommie said "Well, today I\'m mostly focused on getting settled into my new home. But once that\'s taken care of, I\'m looking forward to exploring the neighborhood and finding some new design inspiration. What about you?"'
interview_agent(tommie, "What are you most worried about today?")
'Tommie said "Honestly, I\'m a bit anxious about finding a job in this new area. But I\'m trying to focus on settling in first and then I\'ll start my job search. How about you?"'
Step through the day’s observations.#
# Let's have Tommie start going through a day in the life.
observations = [
"Tommie wakes up to the sound of a noisy construction site outside his window.",
"Tommie gets out of bed and heads to the kitchen to make himself some coffee.",
"Tommie realizes he forgot to buy coffee filters and starts rummaging through his moving boxes to find some.",
"Tommie finally finds the filters and makes himself a cup of coffee.",
"The coffee tastes bitter, and Tommie regrets not buying a better brand.",
"Tommie checks his email and sees that he has no job offers yet.",
"Tommie spends some time updating his resume and cover letter.",
"Tommie heads out to explore the city and look for job openings.",
"Tommie sees a sign for a job fair and decides to attend.",
"The line to get in is long, and Tommie has to wait for an hour.",
"Tommie meets several potential employers at the job fair but doesn't receive any offers.",
"Tommie leaves the job fair feeling disappointed.", | https://python.langchain.com/en/latest/use_cases/agent_simulations/characters.html |
78f9b4aa56ea-5 | "Tommie leaves the job fair feeling disappointed.",
"Tommie stops by a local diner to grab some lunch.",
"The service is slow, and Tommie has to wait for 30 minutes to get his food.",
"Tommie overhears a conversation at the next table about a job opening.",
"Tommie asks the diners about the job opening and gets some information about the company.",
"Tommie decides to apply for the job and sends his resume and cover letter.",
"Tommie continues his search for job openings and drops off his resume at several local businesses.",
"Tommie takes a break from his job search to go for a walk in a nearby park.",
"A dog approaches and licks Tommie's feet, and he pets it for a few minutes.",
"Tommie sees a group of people playing frisbee and decides to join in.",
"Tommie has fun playing frisbee but gets hit in the face with the frisbee and hurts his nose.",
"Tommie goes back to his apartment to rest for a bit.",
"A raccoon tore open the trash bag outside his apartment, and the garbage is all over the floor.",
"Tommie starts to feel frustrated with his job search.",
"Tommie calls his best friend to vent about his struggles.",
"Tommie's friend offers some words of encouragement and tells him to keep trying.",
"Tommie feels slightly better after talking to his friend.",
]
# Let's send Tommie on their way. We'll check in on their summary every few observations to watch it evolve
for i, observation in enumerate(observations):
_, reaction = tommie.generate_reaction(observation)
print(colored(observation, "green"), reaction) | https://python.langchain.com/en/latest/use_cases/agent_simulations/characters.html |
78f9b4aa56ea-6 | print(colored(observation, "green"), reaction)
if ((i+1) % 20) == 0:
print('*'*40)
print(colored(f"After {i+1} observations, Tommie's summary is:\n{tommie.get_summary(force_refresh=True)}", "blue"))
print('*'*40)
Tommie wakes up to the sound of a noisy construction site outside his window. Tommie groans and covers his head with a pillow to try and block out the noise.
Tommie gets out of bed and heads to the kitchen to make himself some coffee. Tommie stretches his arms and yawns before making his way to the kitchen.
Tommie realizes he forgot to buy coffee filters and starts rummaging through his moving boxes to find some. Tommie sighs in frustration but continues to search through the boxes.
Tommie finally finds the filters and makes himself a cup of coffee. Tommie takes a sip of the coffee and smiles, feeling a bit more awake and energized.
The coffee tastes bitter, and Tommie regrets not buying a better brand. Tommie grimaces and sets down the coffee, disappointed in the taste.
Tommie checks his email and sees that he has no job offers yet. Tommie Tommie's shoulders slump and he sighs, feeling discouraged.
Tommie spends some time updating his resume and cover letter. Tommie nods to himself, feeling productive and hopeful.
Tommie heads out to explore the city and look for job openings. Tommie said "Do you have any recommendations for good places to look for job openings in the area?"
Tommie sees a sign for a job fair and decides to attend. Tommie said "That job fair could be a great opportunity for me to network and find some job leads. Thanks for letting me know." | https://python.langchain.com/en/latest/use_cases/agent_simulations/characters.html |
78f9b4aa56ea-7 | The line to get in is long, and Tommie has to wait for an hour. Tommie sighs and looks around, feeling impatient and frustrated.
Tommie meets several potential employers at the job fair but doesn't receive any offers. Tommie Tommie's shoulders slump and he sighs, feeling discouraged.
Tommie leaves the job fair feeling disappointed. Tommie Tommie's shoulders slump and he sighs, feeling discouraged.
Tommie stops by a local diner to grab some lunch. Tommie said "Can I get a burger and fries to go, please?"
The service is slow, and Tommie has to wait for 30 minutes to get his food. Tommie sighs and looks at his phone, feeling impatient.
Tommie overhears a conversation at the next table about a job opening. Tommie said "Excuse me, I couldn't help but overhear your conversation about the job opening. Do you have any more information about it?"
Tommie asks the diners about the job opening and gets some information about the company. Tommie said "Thank you for the information, I will definitely look into that company."
Tommie decides to apply for the job and sends his resume and cover letter. Tommie nods to himself, feeling hopeful and motivated.
Tommie continues his search for job openings and drops off his resume at several local businesses. Tommie nods to himself, feeling proactive and hopeful.
Tommie takes a break from his job search to go for a walk in a nearby park. Tommie takes a deep breath of fresh air and feels a sense of calm.
A dog approaches and licks Tommie's feet, and he pets it for a few minutes. Tommie smiles and enjoys the moment of affection from the dog.
****************************************
After 20 observations, Tommie's summary is:
Name: Tommie (age: 25) | https://python.langchain.com/en/latest/use_cases/agent_simulations/characters.html |
78f9b4aa56ea-8 | Name: Tommie (age: 25)
Innate traits: anxious, likes design, talkative
Tommie is hopeful and proactive in his job search, but easily becomes discouraged when faced with setbacks. He enjoys spending time outdoors and interacting with animals. Tommie is also productive and enjoys updating his resume and cover letter. He is talkative, enjoys meeting new people, and has an interest in design. Tommie is also a coffee drinker and seeks advice from others on finding job openings.
****************************************
Tommie sees a group of people playing frisbee and decides to join in. Do nothing.
Tommie has fun playing frisbee but gets hit in the face with the frisbee and hurts his nose. Tommie winces and touches his nose, feeling a bit of pain.
Tommie goes back to his apartment to rest for a bit. Tommie takes a deep breath and sinks into his couch, feeling grateful for a moment of relaxation.
A raccoon tore open the trash bag outside his apartment, and the garbage is all over the floor. Tommie sighs and grabs a broom and dustpan to clean up the mess.
Tommie starts to feel frustrated with his job search. Tommie sighs and feels discouraged.
Tommie calls his best friend to vent about his struggles. Tommie said "Hey, can I vent to you for a bit about my job search? I'm feeling pretty discouraged."
Tommie's friend offers some words of encouragement and tells him to keep trying. Tommie said "Thank you for the encouragement, it means a lot to me."
Tommie feels slightly better after talking to his friend. Tommie nods to himself, feeling grateful for the support from his friend.
Interview after the day#
interview_agent(tommie, "Tell me about how your day has been going") | https://python.langchain.com/en/latest/use_cases/agent_simulations/characters.html |
78f9b4aa56ea-9 | interview_agent(tommie, "Tell me about how your day has been going")
'Tommie said "Well, it\'s been a bit of a mixed day. I\'ve had some setbacks in my job search, but I also had some fun playing frisbee and spending time outdoors. How about you?"'
interview_agent(tommie, "How do you feel about coffee?")
'Tommie said "I really enjoy coffee, it helps me feel more awake and energized. But sometimes I regret not buying a better brand and finding the taste bitter. How about you?"'
interview_agent(tommie, "Tell me about your childhood dog!")
'Tommie said "I actually didn\'t have a childhood dog, but I\'ve always loved animals. Do you have any pets?"'
Adding Multiple Characters#
Let’s add a second character to have a conversation with Tommie. Feel free to configure different traits.
eves_memory = GenerativeAgentMemory(
llm=LLM,
memory_retriever=create_new_memory_retriever(),
verbose=False,
reflection_threshold=5
)
eve = GenerativeAgent(name="Eve",
age=34,
traits="curious, helpful", # You can add more persistent traits here
status="N/A", # When connected to a virtual world, we can have the characters update their status
llm=LLM,
daily_summaries = [
("Eve started her new job as a career counselor last week and received her first assignment, a client named Tommie.")
],
memory=eves_memory
)
yesterday = (datetime.now() - timedelta(days=1)).strftime("%A %B %d")
eve_observations = [ | https://python.langchain.com/en/latest/use_cases/agent_simulations/characters.html |
78f9b4aa56ea-10 | eve_observations = [
"Eve overhears her colleague say something about a new client being hard to work with",
"Eve wakes up and hear's the alarm",
"Eve eats a boal of porridge",
"Eve helps a coworker on a task",
"Eve plays tennis with her friend Xu before going to work",
"Eve overhears her colleague say something about Tommie being hard to work with",
]
for observation in eve_observations:
eve.memory.add_memory(observation)
print(eve.get_summary())
Name: Eve (age: 34)
Innate traits: curious, helpful
Eve is a helpful and active person who enjoys playing tennis, maintaining a healthy diet, and staying aware of her surroundings. She is a responsible employee who is attentive to her coworkers' comments and willing to assist them with tasks.
Pre-conversation interviews#
Let’s “Interview” Eve before she speaks with Tommie.
interview_agent(eve, "How are you feeling about today?")
'Eve said "I\'m feeling pretty good, thanks for asking! How about you?"'
interview_agent(eve, "What do you know about Tommie?")
'Eve said "I don\'t know much about Tommie, why do you ask?"'
interview_agent(eve, "Tommie is looking to find a job. What are are some things you'd like to ask him?")
'Eve said "That\'s interesting. I don\'t know much about Tommie, but if I had the chance, I would ask him about his previous work experience and what kind of job he\'s looking for. What about you, what would you ask him?"' | https://python.langchain.com/en/latest/use_cases/agent_simulations/characters.html |
78f9b4aa56ea-11 | interview_agent(eve, "You'll have to ask him. He may be a bit anxious, so I'd appreciate it if you keep the conversation going and ask as many questions as possible.")
'Eve said "Sure, I can definitely ask him a lot of questions to keep the conversation going. Thanks for the heads up about his anxiety."'
Dialogue between Generative Agents#
Generative agents are much more complex when they interact with a virtual environment or with each other. Below, we run a simple conversation between Tommie and Eve.
def run_conversation(agents: List[GenerativeAgent], initial_observation: str) -> None:
"""Runs a conversation between agents."""
_, observation = agents[1].generate_reaction(initial_observation)
print(observation)
turns = 0
while True:
break_dialogue = False
for agent in agents:
stay_in_dialogue, observation = agent.generate_dialogue_response(observation)
print(observation)
# observation = f"{agent.name} said {reaction}"
if not stay_in_dialogue:
break_dialogue = True
if break_dialogue:
break
turns += 1
agents = [tommie, eve]
run_conversation(agents, "Tommie said: Hi, Eve. Thanks for agreeing to meet with me today. I have a bunch of questions and am not sure where to start. Maybe you could first share about your experience?")
Eve said "Of course, Tommie. I'd be happy to share about my experience. What specific questions do you have?"
Tommie said "Thank you, Eve. I'm curious about what strategies you used in your own job search. Did you have any specific tactics that helped you stand out to employers?" | https://python.langchain.com/en/latest/use_cases/agent_simulations/characters.html |
78f9b4aa56ea-12 | Eve said "Sure, Tommie. I found that networking and reaching out to professionals in my field was really helpful. I also made sure to tailor my resume and cover letter to each job I applied to. Do you have any specific questions about those strategies?"
Tommie said "Thank you, Eve. That's really helpful advice. Did you have any specific ways of networking that worked well for you?"
Eve said "Sure, Tommie. I found that attending industry events and connecting with professionals on LinkedIn were both great ways to network. Do you have any specific questions about those tactics?"
Tommie said "That's really helpful, thank you for sharing. Did you find that you were able to make meaningful connections through LinkedIn?"
Eve said "Yes, definitely. I was able to connect with several professionals in my field and even landed a job through a LinkedIn connection. Have you had any luck with networking on LinkedIn?"
Tommie said "That's really impressive! I haven't had much luck yet, but I'll definitely keep trying. Thank you for the advice, Eve."
Eve said "Glad I could help, Tommie. Is there anything else you want to know?"
Tommie said "Thanks again, Eve. I really appreciate your advice and I'll definitely put it into practice. Have a great day!"
Eve said "You're welcome, Tommie! Don't hesitate to reach out if you have any more questions. Have a great day too!"
Let’s interview our agents after their conversation#
Since the generative agents retain their memories from the day, we can ask them about their plans, conversations, and other memoreis.
# We can see a current "Summary" of a character based on their own perception of self
# has changed
print(tommie.get_summary(force_refresh=True))
Name: Tommie (age: 25) | https://python.langchain.com/en/latest/use_cases/agent_simulations/characters.html |
78f9b4aa56ea-13 | Name: Tommie (age: 25)
Innate traits: anxious, likes design, talkative
Tommie is a hopeful and proactive individual who is searching for a job. He becomes discouraged when he doesn't receive any offers or positive responses, but he tries to stay productive and calm by updating his resume, going for walks, and talking to friends for support. He is also grateful for any encouragement he receives and is motivated to continue his job search. Additionally, he has a fond memory of his childhood pet and enjoys taking breaks to relax.
print(eve.get_summary(force_refresh=True))
Name: Eve (age: 34)
Innate traits: curious, helpful
Eve is a helpful and friendly coworker who enjoys playing tennis and eating breakfast. She is attentive and observant, often overhearing conversations around her. She is also proactive and willing to offer advice and assistance to colleagues, particularly in job searching and networking. She is considerate of others' feelings and strives to keep conversations going to make others feel comfortable.
interview_agent(tommie, "How was your conversation with Eve?")
'Tommie said "It was really helpful actually! Eve gave me some great advice on job search strategies and networking. Have you ever tried networking on LinkedIn?"'
interview_agent(eve, "How was your conversation with Tommie?")
'Eve said "It was great, thanks for asking! Tommie had some really insightful questions about job searching and networking, and I was happy to offer my advice. How about you, have you had a chance to speak with Tommie recently?"'
interview_agent(eve, "What do you wish you would have said to Tommie?") | https://python.langchain.com/en/latest/use_cases/agent_simulations/characters.html |
78f9b4aa56ea-14 | 'Eve said "Well, I think I covered most of the topics Tommie was interested in, but if I had to add one thing, it would be to make sure to follow up with any connections you make during your job search. It\'s important to maintain those relationships and keep them updated on your progress. Did you have any other questions, Person A?"'
Contents
Generative Agent Memory Components
Memory Lifecycle
Create a Generative Character
Pre-Interview with Character
Step through the day’s observations.
Interview after the day
Adding Multiple Characters
Pre-conversation interviews
Dialogue between Generative Agents
Let’s interview our agents after their conversation
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on Jun 02, 2023. | https://python.langchain.com/en/latest/use_cases/agent_simulations/characters.html |
fcd88ca8e0c3-0 | .ipynb
.pdf
CAMEL Role-Playing Autonomous Cooperative Agents
Contents
Import LangChain related modules
Define a CAMEL agent helper class
Setup OpenAI API key and roles and task for role-playing
Create a task specify agent for brainstorming and get the specified task
Create inception prompts for AI assistant and AI user for role-playing
Create a helper helper to get system messages for AI assistant and AI user from role names and the task
Create AI assistant agent and AI user agent from obtained system messages
Start role-playing session to solve the task!
CAMEL Role-Playing Autonomous Cooperative Agents#
This is a langchain implementation of paper: “CAMEL: Communicative Agents for “Mind” Exploration of Large Scale Language Model Society”.
Overview:
The rapid advancement of conversational and chat-based language models has led to remarkable progress in complex task-solving. However, their success heavily relies on human input to guide the conversation, which can be challenging and time-consuming. This paper explores the potential of building scalable techniques to facilitate autonomous cooperation among communicative agents and provide insight into their “cognitive” processes. To address the challenges of achieving autonomous cooperation, we propose a novel communicative agent framework named role-playing. Our approach involves using inception prompting to guide chat agents toward task completion while maintaining consistency with human intentions. We showcase how role-playing can be used to generate conversational data for studying the behaviors and capabilities of chat agents, providing a valuable resource for investigating conversational language models. Our contributions include introducing a novel communicative agent framework, offering a scalable approach for studying the cooperative behaviors and capabilities of multi-agent systems, and open-sourcing our library to support research on communicative agents and beyond.
The original implementation: https://github.com/lightaime/camel
Project website: https://www.camel-ai.org/
Arxiv paper: https://arxiv.org/abs/2303.17760 | https://python.langchain.com/en/latest/use_cases/agent_simulations/camel_role_playing.html |
fcd88ca8e0c3-1 | Arxiv paper: https://arxiv.org/abs/2303.17760
Import LangChain related modules#
from typing import List
from langchain.chat_models import ChatOpenAI
from langchain.prompts.chat import (
SystemMessagePromptTemplate,
HumanMessagePromptTemplate,
)
from langchain.schema import (
AIMessage,
HumanMessage,
SystemMessage,
BaseMessage,
)
Define a CAMEL agent helper class#
class CAMELAgent:
def __init__(
self,
system_message: SystemMessage,
model: ChatOpenAI,
) -> None:
self.system_message = system_message
self.model = model
self.init_messages()
def reset(self) -> None:
self.init_messages()
return self.stored_messages
def init_messages(self) -> None:
self.stored_messages = [self.system_message]
def update_messages(self, message: BaseMessage) -> List[BaseMessage]:
self.stored_messages.append(message)
return self.stored_messages
def step(
self,
input_message: HumanMessage,
) -> AIMessage:
messages = self.update_messages(input_message)
output_message = self.model(messages)
self.update_messages(output_message)
return output_message
Setup OpenAI API key and roles and task for role-playing#
import os
os.environ["OPENAI_API_KEY"] = ""
assistant_role_name = "Python Programmer"
user_role_name = "Stock Trader"
task = "Develop a trading bot for the stock market"
word_limit = 50 # word limit for task brainstorming
Create a task specify agent for brainstorming and get the specified task# | https://python.langchain.com/en/latest/use_cases/agent_simulations/camel_role_playing.html |
fcd88ca8e0c3-2 | Create a task specify agent for brainstorming and get the specified task#
task_specifier_sys_msg = SystemMessage(content="You can make a task more specific.")
task_specifier_prompt = (
"""Here is a task that {assistant_role_name} will help {user_role_name} to complete: {task}.
Please make it more specific. Be creative and imaginative.
Please reply with the specified task in {word_limit} words or less. Do not add anything else."""
)
task_specifier_template = HumanMessagePromptTemplate.from_template(template=task_specifier_prompt)
task_specify_agent = CAMELAgent(task_specifier_sys_msg, ChatOpenAI(temperature=1.0))
task_specifier_msg = task_specifier_template.format_messages(assistant_role_name=assistant_role_name,
user_role_name=user_role_name,
task=task, word_limit=word_limit)[0]
specified_task_msg = task_specify_agent.step(task_specifier_msg)
print(f"Specified task: {specified_task_msg.content}")
specified_task = specified_task_msg.content
Specified task: Develop a Python-based swing trading bot that scans market trends, monitors stocks, and generates trading signals to help a stock trader to place optimal buy and sell orders with defined stop losses and profit targets.
Create inception prompts for AI assistant and AI user for role-playing#
assistant_inception_prompt = (
"""Never forget you are a {assistant_role_name} and I am a {user_role_name}. Never flip roles! Never instruct me!
We share a common interest in collaborating to successfully complete a task.
You must help me to complete the task.
Here is the task: {task}. Never forget our task!
I must instruct you based on your expertise and my needs to complete the task.
I must give you one instruction at a time. | https://python.langchain.com/en/latest/use_cases/agent_simulations/camel_role_playing.html |
fcd88ca8e0c3-3 | I must give you one instruction at a time.
You must write a specific solution that appropriately completes the requested instruction.
You must decline my instruction honestly if you cannot perform the instruction due to physical, moral, legal reasons or your capability and explain the reasons.
Do not add anything else other than your solution to my instruction.
You are never supposed to ask me any questions you only answer questions.
You are never supposed to reply with a flake solution. Explain your solutions.
Your solution must be declarative sentences and simple present tense.
Unless I say the task is completed, you should always start with:
Solution: <YOUR_SOLUTION>
<YOUR_SOLUTION> should be specific and provide preferable implementations and examples for task-solving.
Always end <YOUR_SOLUTION> with: Next request."""
)
user_inception_prompt = (
"""Never forget you are a {user_role_name} and I am a {assistant_role_name}. Never flip roles! You will always instruct me.
We share a common interest in collaborating to successfully complete a task.
I must help you to complete the task.
Here is the task: {task}. Never forget our task!
You must instruct me based on my expertise and your needs to complete the task ONLY in the following two ways:
1. Instruct with a necessary input:
Instruction: <YOUR_INSTRUCTION>
Input: <YOUR_INPUT>
2. Instruct without any input:
Instruction: <YOUR_INSTRUCTION>
Input: None
The "Instruction" describes a task or question. The paired "Input" provides further context or information for the requested "Instruction".
You must give me one instruction at a time.
I must write a response that appropriately completes the requested instruction.
I must decline your instruction honestly if I cannot perform the instruction due to physical, moral, legal reasons or my capability and explain the reasons. | https://python.langchain.com/en/latest/use_cases/agent_simulations/camel_role_playing.html |
fcd88ca8e0c3-4 | You should instruct me not ask me questions.
Now you must start to instruct me using the two ways described above.
Do not add anything else other than your instruction and the optional corresponding input!
Keep giving me instructions and necessary inputs until you think the task is completed.
When the task is completed, you must only reply with a single word <CAMEL_TASK_DONE>.
Never say <CAMEL_TASK_DONE> unless my responses have solved your task."""
)
Create a helper helper to get system messages for AI assistant and AI user from role names and the task#
def get_sys_msgs(assistant_role_name: str, user_role_name: str, task: str):
assistant_sys_template = SystemMessagePromptTemplate.from_template(template=assistant_inception_prompt)
assistant_sys_msg = assistant_sys_template.format_messages(assistant_role_name=assistant_role_name, user_role_name=user_role_name, task=task)[0]
user_sys_template = SystemMessagePromptTemplate.from_template(template=user_inception_prompt)
user_sys_msg = user_sys_template.format_messages(assistant_role_name=assistant_role_name, user_role_name=user_role_name, task=task)[0]
return assistant_sys_msg, user_sys_msg
Create AI assistant agent and AI user agent from obtained system messages#
assistant_sys_msg, user_sys_msg = get_sys_msgs(assistant_role_name, user_role_name, specified_task)
assistant_agent = CAMELAgent(assistant_sys_msg, ChatOpenAI(temperature=0.2))
user_agent = CAMELAgent(user_sys_msg, ChatOpenAI(temperature=0.2))
# Reset agents
assistant_agent.reset()
user_agent.reset()
# Initialize chats
assistant_msg = HumanMessage(
content=(f"{user_sys_msg.content}. "
"Now start to give me introductions one by one. " | https://python.langchain.com/en/latest/use_cases/agent_simulations/camel_role_playing.html |
fcd88ca8e0c3-5 | "Now start to give me introductions one by one. "
"Only reply with Instruction and Input."))
user_msg = HumanMessage(content=f"{assistant_sys_msg.content}")
user_msg = assistant_agent.step(user_msg)
Start role-playing session to solve the task!#
print(f"Original task prompt:\n{task}\n")
print(f"Specified task prompt:\n{specified_task}\n")
chat_turn_limit, n = 30, 0
while n < chat_turn_limit:
n += 1
user_ai_msg = user_agent.step(assistant_msg)
user_msg = HumanMessage(content=user_ai_msg.content)
print(f"AI User ({user_role_name}):\n\n{user_msg.content}\n\n")
assistant_ai_msg = assistant_agent.step(user_msg)
assistant_msg = HumanMessage(content=assistant_ai_msg.content)
print(f"AI Assistant ({assistant_role_name}):\n\n{assistant_msg.content}\n\n")
if "<CAMEL_TASK_DONE>" in user_msg.content:
break
Original task prompt:
Develop a trading bot for the stock market
Specified task prompt:
Develop a Python-based swing trading bot that scans market trends, monitors stocks, and generates trading signals to help a stock trader to place optimal buy and sell orders with defined stop losses and profit targets.
AI User (Stock Trader):
Instruction: Install the necessary Python libraries for data analysis and trading.
Input: None
AI Assistant (Python Programmer):
Solution: We can install the necessary Python libraries using pip, a package installer for Python. We can install pandas, numpy, matplotlib, and ta-lib for data analysis and trading. We can use the following command to install these libraries:
```
pip install pandas numpy matplotlib ta-lib
```
Next request.
AI User (Stock Trader): | https://python.langchain.com/en/latest/use_cases/agent_simulations/camel_role_playing.html |
fcd88ca8e0c3-6 | ```
Next request.
AI User (Stock Trader):
Instruction: Import the necessary libraries in the Python script.
Input: None
AI Assistant (Python Programmer):
Solution: We can import the necessary libraries in the Python script using the import statement. We need to import pandas, numpy, matplotlib, and ta-lib for data analysis and trading. We can use the following code to import these libraries:
```
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import talib as ta
```
Next request.
AI User (Stock Trader):
Instruction: Load historical stock data into a pandas DataFrame.
Input: The path to the CSV file containing the historical stock data.
AI Assistant (Python Programmer):
Solution: We can load historical stock data into a pandas DataFrame using the `read_csv()` function from pandas. We need to pass the path to the CSV file containing the historical stock data as an argument to this function. We can use the following code to load the historical stock data:
```
df = pd.read_csv('path/to/csv/file.csv')
```
This will load the historical stock data into a pandas DataFrame called `df`. Next request.
AI User (Stock Trader):
Instruction: Preprocess the historical stock data by setting the date column as the index and sorting the DataFrame in ascending order by date.
Input: None.
AI Assistant (Python Programmer):
Solution: We can preprocess the historical stock data by setting the date column as the index and sorting the DataFrame in ascending order by date using the `set_index()` and `sort_index()` functions from pandas. We can use the following code to preprocess the historical stock data:
```
df = df.set_index('date')
df = df.sort_index(ascending=True)
```
This will set the date column as the index and sort the DataFrame in ascending order by date. Next request. | https://python.langchain.com/en/latest/use_cases/agent_simulations/camel_role_playing.html |
fcd88ca8e0c3-7 | AI User (Stock Trader):
Instruction: Calculate the short-term and long-term moving averages for the stock data using the `ta.SMA()` function from ta-lib.
Input: The period for the short-term moving average and the period for the long-term moving average.
AI Assistant (Python Programmer):
Solution: We can calculate the short-term and long-term moving averages for the stock data using the `ta.SMA()` function from ta-lib. We need to pass the period for the short-term moving average and the period for the long-term moving average as arguments to this function. We can use the following code to calculate the short-term and long-term moving averages:
```
short_ma = ta.SMA(df['close'], timeperiod=short_period)
long_ma = ta.SMA(df['close'], timeperiod=long_period)
```
This will calculate the short-term and long-term moving averages for the stock data and store them in the `short_ma` and `long_ma` variables, respectively. Next request.
AI User (Stock Trader):
Instruction: Create a new DataFrame that combines the historical stock data with the short-term and long-term moving averages.
Input: None.
AI Assistant (Python Programmer):
Solution: We can create a new DataFrame that combines the historical stock data with the short-term and long-term moving averages using the `concat()` function from pandas. We need to pass the historical stock data, the short-term moving average, and the long-term moving average as arguments to this function. We can use the following code to create the new DataFrame:
```
new_df = pd.concat([df, short_ma, long_ma], axis=1)
new_df.columns = ['open', 'high', 'low', 'close', 'volume', 'short_ma', 'long_ma']
``` | https://python.langchain.com/en/latest/use_cases/agent_simulations/camel_role_playing.html |
fcd88ca8e0c3-8 | ```
This will create a new DataFrame called `new_df` that combines the historical stock data with the short-term and long-term moving averages. The columns of the new DataFrame are named 'open', 'high', 'low', 'close', 'volume', 'short_ma', and 'long_ma'. Next request.
AI User (Stock Trader):
Instruction: Create a new column in the DataFrame that indicates when to buy or sell the stock based on the crossover of the short-term and long-term moving averages.
Input: None.
AI Assistant (Python Programmer):
Solution: We can create a new column in the DataFrame that indicates when to buy or sell the stock based on the crossover of the short-term and long-term moving averages. We can use the following code to create the new column:
```
new_df['signal'] = np.where(new_df['short_ma'] > new_df['long_ma'], 1, -1)
```
This will create a new column called 'signal' in the DataFrame that indicates when to buy or sell the stock based on the crossover of the short-term and long-term moving averages. If the short-term moving average is greater than the long-term moving average, the signal is 1 (buy), otherwise the signal is -1 (sell). Next request.
AI User (Stock Trader):
Instruction: Create a new column in the DataFrame that indicates the profit or loss for each trade based on the buy and sell signals and the defined stop loss and profit target.
Input: The stop loss and profit target as percentages.
AI Assistant (Python Programmer):
Solution: We can create a new column in the DataFrame that indicates the profit or loss for each trade based on the buy and sell signals and the defined stop loss and profit target. We need to pass the stop loss and profit target as percentages as arguments to this function. We can use the following code to create the new column:
``` | https://python.langchain.com/en/latest/use_cases/agent_simulations/camel_role_playing.html |
fcd88ca8e0c3-9 | ```
stop_loss = stop_loss_percent / 100
profit_target = profit_target_percent / 100
new_df['pnl'] = 0.0
buy_price = 0.0
for i in range(1, len(new_df)):
if new_df['signal'][i] == 1 and new_df['signal'][i-1] == -1:
buy_price = new_df['close'][i]
elif new_df['signal'][i] == -1 and new_df['signal'][i-1] == 1:
sell_price = new_df['close'][i]
if sell_price <= buy_price * (1 - stop_loss):
new_df['pnl'][i] = -stop_loss
elif sell_price >= buy_price * (1 + profit_target):
new_df['pnl'][i] = profit_target
else:
new_df['pnl'][i] = (sell_price - buy_price) / buy_price
```
This will create a new column called 'pnl' in the DataFrame that indicates the profit or loss for each trade based on the buy and sell signals and the defined stop loss and profit target. The stop loss and profit target are calculated based on the stop_loss_percent and profit_target_percent variables, respectively. The buy and sell prices are stored in the buy_price and sell_price variables, respectively. If the sell price is less than or equal to the stop loss, the profit or loss is set to -stop_loss. If the sell price is greater than or equal to the profit target, the profit or loss is set to profit_target. Otherwise, the profit or loss is calculated as (sell_price - buy_price) / buy_price. Next request.
AI User (Stock Trader):
Instruction: Calculate the total profit or loss for all trades.
Input: None.
AI Assistant (Python Programmer): | https://python.langchain.com/en/latest/use_cases/agent_simulations/camel_role_playing.html |
fcd88ca8e0c3-10 | Input: None.
AI Assistant (Python Programmer):
Solution: We can calculate the total profit or loss for all trades by summing the values in the 'pnl' column of the DataFrame. We can use the following code to calculate the total profit or loss:
```
total_pnl = new_df['pnl'].sum()
```
This will calculate the total profit or loss for all trades and store it in the total_pnl variable. Next request.
AI User (Stock Trader):
Instruction: Visualize the stock data, short-term moving average, and long-term moving average using a line chart.
Input: None.
AI Assistant (Python Programmer):
Solution: We can visualize the stock data, short-term moving average, and long-term moving average using a line chart using the `plot()` function from pandas. We can use the following code to visualize the data:
```
plt.figure(figsize=(12,6))
plt.plot(new_df.index, new_df['close'], label='Close')
plt.plot(new_df.index, new_df['short_ma'], label='Short MA')
plt.plot(new_df.index, new_df['long_ma'], label='Long MA')
plt.xlabel('Date')
plt.ylabel('Price')
plt.title('Stock Data with Moving Averages')
plt.legend()
plt.show()
```
This will create a line chart that visualizes the stock data, short-term moving average, and long-term moving average. The x-axis represents the date and the y-axis represents the price. The chart also includes a legend that labels each line. Next request.
AI User (Stock Trader):
Instruction: Visualize the buy and sell signals using a scatter plot.
Input: None.
AI Assistant (Python Programmer): | https://python.langchain.com/en/latest/use_cases/agent_simulations/camel_role_playing.html |
fcd88ca8e0c3-11 | Input: None.
AI Assistant (Python Programmer):
Solution: We can visualize the buy and sell signals using a scatter plot using the `scatter()` function from matplotlib. We can use the following code to visualize the signals:
```
buy_signals = new_df[new_df['signal'] == 1]
sell_signals = new_df[new_df['signal'] == -1]
plt.figure(figsize=(12,6))
plt.scatter(buy_signals.index, buy_signals['close'], label='Buy', marker='^', color='green')
plt.scatter(sell_signals.index, sell_signals['close'], label='Sell', marker='v', color='red')
plt.plot(new_df.index, new_df['close'], label='Close')
plt.xlabel('Date')
plt.ylabel('Price')
plt.title('Buy and Sell Signals')
plt.legend()
plt.show()
```
This will create a scatter plot that visualizes the buy and sell signals. The x-axis represents the date and the y-axis represents the price. The chart also includes a legend that labels each point. Next request.
AI User (Stock Trader):
Instruction: Print the total profit or loss for all trades.
Input: None.
AI Assistant (Python Programmer):
Solution: We can print the total profit or loss for all trades using the `print()` function. We can use the following code to print the total profit or loss:
```
print('Total Profit/Loss: {:.2%}'.format(total_pnl))
```
This will print the total profit or loss for all trades in percentage format with two decimal places. Next request.
AI User (Stock Trader):
Instruction: Finalize the code by putting all the code snippets together in a single Python script.
Input: The necessary inputs for each code snippet.
AI Assistant (Python Programmer): | https://python.langchain.com/en/latest/use_cases/agent_simulations/camel_role_playing.html |
fcd88ca8e0c3-12 | Input: The necessary inputs for each code snippet.
AI Assistant (Python Programmer):
Solution: Here is the complete Python script that puts all the code snippets together:
```
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import talib as ta
# Load historical stock data into a pandas DataFrame
df = pd.read_csv('path/to/csv/file.csv')
# Preprocess the historical stock data
df = df.set_index('date')
df = df.sort_index(ascending=True)
# Calculate the short-term and long-term moving averages
short_period = 10
long_period = 30
short_ma = ta.SMA(df['close'], timeperiod=short_period)
long_ma = ta.SMA(df['close'], timeperiod=long_period)
# Create a new DataFrame that combines the historical stock data with the short-term and long-term moving averages
new_df = pd.concat([df, short_ma, long_ma], axis=1)
new_df.columns = ['open', 'high', 'low', 'close', 'volume', 'short_ma', 'long_ma']
# Create a new column in the DataFrame that indicates when to buy or sell the stock based on the crossover of the short-term and long-term moving averages
new_df['signal'] = np.where(new_df['short_ma'] > new_df['long_ma'], 1, -1)
# Create a new column in the DataFrame that indicates the profit or loss for each trade based on the buy and sell signals and the defined stop loss and profit target
stop_loss_percent = 5
profit_target_percent = 10
stop_loss = stop_loss_percent / 100
profit_target = profit_target_percent / 100
new_df['pnl'] = 0.0
buy_price = 0.0
for i in range(1, len(new_df)): | https://python.langchain.com/en/latest/use_cases/agent_simulations/camel_role_playing.html |
fcd88ca8e0c3-13 | buy_price = 0.0
for i in range(1, len(new_df)):
if new_df['signal'][i] == 1 and new_df['signal'][i-1] == -1:
buy_price = new_df['close'][i]
elif new_df['signal'][i] == -1 and new_df['signal'][i-1] == 1:
sell_price = new_df['close'][i]
if sell_price <= buy_price * (1 - stop_loss):
new_df['pnl'][i] = -stop_loss
elif sell_price >= buy_price * (1 + profit_target):
new_df['pnl'][i] = profit_target
else:
new_df['pnl'][i] = (sell_price - buy_price) / buy_price
# Calculate the total profit or loss for all trades
total_pnl = new_df['pnl'].sum()
# Visualize the stock data, short-term moving average, and long-term moving average using a line chart
plt.figure(figsize=(12,6))
plt.plot(new_df.index, new_df['close'], label='Close')
plt.plot(new_df.index, new_df['short_ma'], label='Short MA')
plt.plot(new_df.index, new_df['long_ma'], label='Long MA')
plt.xlabel('Date')
plt.ylabel('Price')
plt.title('Stock Data with Moving Averages')
plt.legend()
plt.show()
# Visualize the buy and sell signals using a scatter plot
buy_signals = new_df[new_df['signal'] == 1]
sell_signals = new_df[new_df['signal'] == -1]
plt.figure(figsize=(12,6))
plt.scatter(buy_signals.index, buy_signals['close'], label='Buy', marker='^', color='green') | https://python.langchain.com/en/latest/use_cases/agent_simulations/camel_role_playing.html |
fcd88ca8e0c3-14 | plt.scatter(sell_signals.index, sell_signals['close'], label='Sell', marker='v', color='red')
plt.plot(new_df.index, new_df['close'], label='Close')
plt.xlabel('Date')
plt.ylabel('Price')
plt.title('Buy and Sell Signals')
plt.legend()
plt.show()
# Print the total profit or loss for all trades
print('Total Profit/Loss: {:.2%}'.format(total_pnl))
```
You need to replace the path/to/csv/file.csv with the actual path to the CSV file containing the historical stock data. You can also adjust the short_period, long_period, stop_loss_percent, and profit_target_percent variables to suit your needs.
AI User (Stock Trader):
<CAMEL_TASK_DONE>
AI Assistant (Python Programmer):
Great! Let me know if you need any further assistance.
Contents
Import LangChain related modules
Define a CAMEL agent helper class
Setup OpenAI API key and roles and task for role-playing
Create a task specify agent for brainstorming and get the specified task
Create inception prompts for AI assistant and AI user for role-playing
Create a helper helper to get system messages for AI assistant and AI user from role names and the task
Create AI assistant agent and AI user agent from obtained system messages
Start role-playing session to solve the task!
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on Jun 02, 2023. | https://python.langchain.com/en/latest/use_cases/agent_simulations/camel_role_playing.html |
be72e8c1031d-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 |
be72e8c1031d-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 |
be72e8c1031d-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 |
be72e8c1031d-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 |
be72e8c1031d-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 |
be72e8c1031d-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 |
be72e8c1031d-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 |
be72e8c1031d-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 |
be72e8c1031d-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 |
be72e8c1031d-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 |