使用AutoGPT找到马拉松比赛的获胜时间#
- 实现自https://github.com/Significant-Gravitas/Auto-GPT (opens in a new tab)
- 使用LangChain原语（ 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)
设置工具#
- 我们将设置一个带有
search工具的AutoGPT， 和write-file工具， 和一个read-file工具， 一个浏览网页的工具， 和一个通过python REPL与CSV文件交互的工具
请在下面定义任何其他要使用的工具:tools
# 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(
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}"
使用PlayWright浏览网页
# !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()
lines = (line.strip() for line in text.splitlines())
chunks = (phrase.strip() for line in lines for phrase in line.split(" "))
results = "".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))
在网页上进行问答
帮助模型向网页提出更有针对性的问题，以避免占用其内存
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:
"""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="".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))
设置内存#（Set up memory）
- 这里的内存是用于代理中间步骤的（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({}), {})
模型和AutoGPT设置#（Setup model and AutoGPT）
模型设置（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用于查询网络#（AutoGPT for Querying the Web）
多年来我花了很多时间爬行数据源和清洗数据。让我们看看AutoGPT能否帮助解决这个问题！（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!）
以下是查找最近波士顿马拉松成绩并将其转换为表格形式的提示。（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- Generate a table with the year, name, country of origin, and times- Ensure there are no legal complications",
"criticism": "None",
"speak": "I will use the DuckDuckGo Search command to find the winning Boston Marathon times for the past 5 years."
},
"command": {
"name": "DuckDuckGo Search",
"args": {
"query": "winning Boston Marathon times for the past 5 years ending in 2022"
}
}
}
{
"thoughts": {
"text": "The DuckDuckGo Search command did not provide the specific information I need. I must switch my approach and use query_webpage command to browse a webpage containing the Boston Marathon winning times for the past 5 years.",
"reasoning": "The query_webpage command may give me more accurate and comprehensive results compared to the search command.",
"plan": "- Use query_webpage command to find the winning Boston Marathon times- Generate a table with the year, name, country of origin, and times- 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.",
"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\- Generate a table with the year, name, country of origin, and times\- 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- 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",
"text": "Year,Name,Country,Time2022,Evans Chebet,KEN,2:06:512021,Benson Kipruto,KEN,2:09:512019,Lawrence Cherono,KEN,2:07:572018,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- Process the CSV file to generate the table- 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,Time2022,Evans Chebet,KEN,2:06:512021,Benson Kipruto,KEN,2:09:512019,Lawrence Cherono,KEN,2:07:572018,Yuki Kawauchi,JPN,2:15:58"
}
}
}
{
"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- 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,Time2022,Evans Chebet,Kenya,2:06:512021,Benson Kipruto,Kenya,2:09:512020,Canceled due to COVID-19 pandemic,,2019,Lawrence Cherono,Kenya,2:07:572018,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",
"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
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
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": {
"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.'