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... | 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), **... | 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 guid... | 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({"obje... | 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 ... | 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. B... | 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,... | 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 a... | 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 tre... | 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 nee... | 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 th... | 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 j... | 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, an... | 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 LLM... | 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. Inte... | 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 curre... | 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... | 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": {
"ar... | 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 c... | 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 cu... | 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 ... | 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", "desc... | 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 to... | 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 informati... | 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\' ... | 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, Vecto... | 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... | 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:
resul... | 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 = [... | 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 =... | 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"
... | 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... | 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 ... | 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.",
... | 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": "Re... | 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.
{
... | 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 ... | 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
... | 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 instruction... | 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-impro... | 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 re... | 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 hu... | 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... | 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 tha... | 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 tha... | 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... | 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 ... | 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... | 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 en... | 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
... | 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, rew... | 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-Playe... | 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... | 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, mes... | 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... | 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, {prot... | 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 heavil... | 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 lo... | 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... | 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’... | 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.generativ... | 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(embe... | 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:
tommi... | 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,... | 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 ... | 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. T... | 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 ... | 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 ... | 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 "... | 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 collea... | 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 betwe... | 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... | 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 t... | 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 questi... | 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 us... | 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,
... | 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 ... | 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 ... | 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... | 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"Specifie... | 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 anal... | 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 ... | 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 ... | 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] == ... | 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 ... | 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]
pl... | 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
d... | 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):
... | 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: ... | 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 ... | 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.s... | 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 ag... | 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,
... | 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_... | 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,
HumanMe... | 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"... | 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 SystemMe... | 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:
T... | 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 o... | https://python.langchain.com/en/latest/use_cases/agent_simulations/multiagent_authoritarian.html |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.