Bearly 代码解释器
Bearly 代码解释器允许远程执行代码。这使得它非常适合代理的代码沙箱，以安全地实现诸如代码解释器之类的功能。
在这里获取您的 API 密钥： https://bearly.ai/dashboard/developers
%pip install --upgrade --quiet langchain-community
在这个笔记本中，我们将创建一个使用 Bearly 进行数据交互的代理示例。
from langchain_community.tools import BearlyInterpreterTool
from langchain.agents import AgentType, initialize_agent
from langchain_openai import ChatOpenAI
初始化解释器
bearly_tool = BearlyInterpreterTool(api_key="...")
让我们向沙箱中添加一些文件
bearly_tool.add_file(
source_path="sample_data/Bristol.pdf", target_path="Bristol.pdf", description=""
)
bearly_tool.add_file(
source_path="sample_data/US_GDP.csv", target_path="US_GDP.csv", description=""
)
现在创建一个 Tool 对象。这是必要的，因为我们添加了文件，并希望工具描述反映这一点。
tools = [bearly_tool.as_tool()]
tools[0].name
'bearly_interpreter'
print(tools[0].description)
在沙箱环境中评估 python 代码。每次执行时环境都会重置。您必须每次发送整个脚本并打印输出。脚本应为可以评估的纯 python 代码。它应为 python 格式而非 markdown。代码不得用反引号包裹。所有 python 包，包括 requests、matplotlib、scipy、numpy、pandas 等均可用。如果您有任何文件输出，请将其写入相对于执行路径的 "output/" 目录。输出只能从目录、stdout 和 stdin 中读取。请勿使用 plot.show() 等内容，因为它将不起作用，而是将它们写入 `output/`，并将返回文件的链接。请打印任何输出和结果，以便您可以捕获输出。
评估环境中可用的以下文件：
- 路径: `Bristol.pdf`
前四行: []
描述: ``
- 路径: `US_GDP.csv`
前四行: ['DATE,GDP\n', '1947-01-01,243.164\n', '1947-04-01,245.968\n', '1947-07-01,249.585\n']
描述: ``
初始化代理
llm = ChatOpenAI(model="gpt-4", temperature=0)
agent = initialize_agent(
tools,
llm,
agent=AgentType.OPENAI_FUNCTIONS,
verbose=True,
handle_parsing_errors=True,
)
# 提取 pdf 内容
agent.run("What is the text on page 3 of the pdf?")
[1m> Entering new AgentExecutor chain...[0m
[32;1m[1;3m
Invoking: `bearly_interpreter` with `{'python_code': "import PyPDF2\n\n# Open the PDF file in read-binary mode\npdf_file = open('Bristol.pdf', 'rb')\n\n# Create a PDF file reader object\npdf_reader = PyPDF2.PdfFileReader(pdf_file)\n\n# Get the text from page 3\npage_obj = pdf_reader.getPage(2)\npage_text = page_obj.extractText()\n\n# Close the PDF file\npdf_file.close()\n\nprint(page_text)"}`
[0m[36;1m[1;3m{'stdout': '', 'stderr': 'Traceback (most recent call last):\n File "/tmp/project/main.py", line 7, in <module>\n pdf_reader = PyPDF2.PdfFileReader(pdf_file)\n File "/venv/lib/python3.10/site-packages/PyPDF2/_reader.py", line 1974, in __init__\n deprecation_with_replacement("PdfFileReader", "PdfReader", "3.0.0")\n File "/venv/lib/python3.10/site-packages/PyPDF2/_utils.py", line 369, in deprecation_with_replacement\n deprecation(DEPR_MSG_HAPPENED.format(old_name, removed_in, new_name))\n File "/venv/lib/python3.10/site-packages/PyPDF2/_utils.py", line 351, in deprecation\n raise DeprecationError(msg)\nPyPDF2.errors.DeprecationError: PdfFileReader is deprecated and was removed in PyPDF2 3.0.0. Use PdfReader instead.\n', 'fileLinks': [], 'exitCode': 1}[0m[32;1m[1;3m
Invoking: `bearly_interpreter` with `{'python_code': "from PyPDF2 import PdfReader\n\n# Open the PDF file\npdf = PdfReader('Bristol.pdf')\n\n# Get the text from page 3\npage = pdf.pages[2]\npage_text = page.extract_text()\n\nprint(page_text)"}`
[0m[36;1m[1;3m{'stdout': '1 COVID-19 at Work: \nExposing h ow risk is assessed and its consequences in England and Sweden \nPeter Andersson and Tonia Novitz* \n1.Introduction\nT\nhe crisis which arose suddenly at the beginning of 2020 relating to coronavirus was immediately \ncentred on risk. Predictions ha d to be made swiftly regarding how it would spread, who it might \naffect and what measures could be taken to prevent exposure in everyday so cial interaction, \nincluding in the workplace. This was in no way a straightforward assessment, because initially so \nmuch was unknown. Those gaps in our knowledge have since, partially, been ameliorated. It is \nevident that not all those exposed to COVID-19 become ill, and many who contract the virus remain \nasymptomatic, so that the odds on becoming seriously ill may seem small. But those odds are also stacked against certain segments of the population. The likelihood of mortality and morbidity are associated with age and ethnicity as well as pre -existing medical conditions (such as diabetes), but \nalso with poverty which correlates to the extent of exposure in certain occupations.\n1 Some risks \narise which remain less predictable, as previously healthy people with no signs of particular \nvulnerability can experience serious long term illness as well and in rare cases will even die.2 \nPerceptions of risk in different countries have led to particular measures taken, ranging from handwashing to social distancing, use of personal protective equipment (PPE) such as face coverings, and even ‘lockdowns’ which have taken various forms.\n3 Use of testing and vaccines \nalso bec ame part of the remedial landscape, with their availability and administration being \n*This paper is part of the project An i nclusive and sustainable Swedish labour law – the way\nahead, dnr. 2017-03134 financed by the Swedish research council led by Petra Herzfeld Olssonat Stockholm University. The authors would like to thank her and other participants, Niklas\nBruun and Erik Sjödin for their helpful comments on earlier drafts. A much shorter article titled\n‘Risk Assessment and COVID -19: Systems at work (or not) in England and Sweden’ is published\nin the (2021) Comparative Labour and Social Security Review /\n Revue de droit comparé du\ntravail et de la sécurité sociale.\n1 Public Health England, Disparities in the risk and outcomes of COVID-19 (2 June 2020 -\nhttps://assets.publishing.service.gov.uk/government/uploads/ system /uploads/attachment_data/file\n/890258/disparities_review.pdf.\n2 Nisreen A. Alwan, ‘Track COVID- 19 sickness, not just positive tests and deaths’ ( 2020)\n584.7820 Nature 170- 171; Elisabeth Mahase, ‘Covid-19: What do we know about “long covid”?’\n(2020) BMJ 370.\n3 Sarah Dryhurst, Claudia R. Schneider, John Kerr, Alexandra LJ Freeman, Gabriel Recchia,\nAnne Marthe Van Der Bles, David Spiegelhalter, and Sander van der Linden, ‘Risk perceptionsof COVID-19 around the world’ (2020) 23(7- 8) Journal of Risk Research 994; Wändi Bruine de\nBruin, and Daniel Bennett, ‘Relationships between initial COVID -19 risk perceptions and\nprotective health behaviors: A national survey’ (2020) 59(2) American Journal of Prev entive\nMedicine 157; and Simon Deakin and Gaofeng Meng, ‘The Governance of Covid- 19:\nAnthropogenic Risk, Evolutionary Learning, and the Future of the Social State’ (2020)49(4) Industrial Law Journal 539.\n', 'stderr': '', 'fileLinks': [], 'exitCode': 0}[0m[32;1m[1;3m
文本内容在 PDF 的第 3 页是：
"1 COVID-19 at Work:
Exposing how risk is assessed and its consequences in England and Sweden
Peter Andersson and Tonia Novitz*
1.Introduction
The crisis which arose suddenly at the beginning of 2020 relating to coronavirus was immediately
centred on risk. Predictions had to be made swiftly regarding how it would spread, who it might
affect and what measures could be taken to prevent exposure in everyday social interaction,
including in the workplace. This was in no way a straightforward assessment, because initially so
much was unknown. Those gaps in our knowledge have since, partially, been ameliorated. It is
evident that not all those exposed to COVID-19 become ill, and many who contract the virus remain
asymptomatic, so that the odds on becoming seriously ill may seem small. But those odds are also stacked against certain segments of the population. The likelihood of mortality and morbidity are associated with age and ethnicity as well as pre-existing medical conditions (such as diabetes), but
also with poverty which correlates to the extent of exposure in certain occupations.
1 Some risks
arise which remain less predictable, as previously healthy people with no signs of particular
vulnerability can experience serious long term illness as well and in rare cases will even die.2
Perceptions of risk in different countries have led to particular measures taken, ranging from handwashing to social distancing, use of personal protective equipment (PPE) such as face coverings, and even ‘lockdowns’ which have taken various forms.
3 Use of testing and vaccines
also became part of the remedial landscape, with their availability and administration being
*This paper is part of the project An inclusive and sustainable Swedish labour law – the way
ahead, dnr. 2017-03134 financed by the Swedish research council led by Petra Herzfeld Olssonat Stockholm University. The authors would like to thank her and other participants, Niklas
Bruun and Erik Sjödin for their helpful comments on earlier drafts. A much shorter article titled
‘Risk Assessment and COVID -19: Systems at work (or not) in England and Sweden’ is published
in the (2021) Comparative Labour and Social Security Review /
Revue de droit comparé du
travail et de la sécurité sociale.
1 Public Health England, Disparities in the risk and outcomes of COVID-19 (2 June 2020 -
https://assets.publishing.service.gov.uk/government/uploads/ system /uploads/attachment_data/file
/890258/disparities_review.pdf.
2 Nisreen A. Alwan, ‘Track COVID- 19 sickness, not just positive tests and deaths’ ( 2020)
584.7820 Nature 170- 171; Elisabeth Mahase, ‘Covid-19: What do we know about “long covid”?’
(2020) BMJ 370.
3 Sarah Dryhurst, Claudia R. Schneider, John Kerr, Alexandra LJ Freeman, Gabriel Recchia,
Anne Marthe Van Der Bles, David Spiegelhalter, and Sander van der Linden, ‘Risk perceptionsof COVID-19 around the world’ (2020) 23(7- 8) Journal of Risk Research 994; Wändi Bruine de
Bruin, and Daniel Bennett, ‘Relationships between initial COVID -19 risk perceptions and
protective health behaviors: A national survey’ (2020) 59(2) American Journal of Preventive
Medicine 157; and Simon Deakin and Gaofeng Meng, ‘The Governance of Covid- 19:
Anthropogenic Risk, Evolutionary Learning, and the Future of the Social State’ (2020)49(4) Industrial Law Journal 539."[0m
[1m> Finished chain.[0m
'PDF第3页的文本是：\n\n"1 COVID-19在工作中：\n揭示风险如何评估及其在英格兰和瑞典的后果\n彼得·安德森和托尼亚·诺维茨*\n1.引言\n2020年初突如其来的与冠状病毒相关的危机，立即集中在风险上。必须迅速做出预测，关于它将如何传播，可能影响谁，以及可以采取什么措施来防止在日常社交互动中，包括在工作场所的暴露。这绝不是一个简单的评估，因为最初有太多未知。我们知识中的这些空白现在部分得到了改善。显然，并不是所有接触COVID-19的人都会生病，许多感染病毒的人保持无症状，因此重病的几率似乎很小。但这些几率也对某些人群不利。死亡率和发病率与年龄、种族以及既往的医疗条件（如糖尿病）相关，但也与贫困相关，因为贫困与某些职业的暴露程度相关。\n1 一些风险出现，这些风险仍然不太可预测，因为以前健康且没有特定脆弱迹象的人也可能经历严重的长期疾病，甚至在少数情况下会死去。2 不同国家对风险的感知导致采取了特定措施，从洗手到社交距离、使用个人防护装备（PPE）如口罩，甚至采取了各种形式的“封锁”。\n3 测试和疫苗的使用也成为补救措施的一部分，其可用性和管理\n*本文是项目“包容和可持续的瑞典劳动法——前进之路”的一部分，项目编号：2017-03134，由瑞典研究委员会资助，负责人为斯德哥尔摩大学的彼得拉·赫兹费尔德·奥尔松。作者感谢她和其他参与者，尼克拉斯·布鲁恩和埃里克·肖丁对早期草稿的有益评论。题为“风险评估与COVID-19：在英格兰和瑞典的系统（或不）”的较短文章已发表于（2021）《比较劳动和社会保障评论》/\n《比较劳动法与社会保障法评论》。\n1 英国公共卫生局，COVID-19的风险和结果差异（2020年6月2日 - \nhttps://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file\n/890258/disparities_review.pdf。\n2 尼斯琳·阿尔万，“追踪COVID-19疾病，而不仅仅是阳性测试和死亡”（2020）\n584.7820 自然 170-171；伊丽莎白·马哈斯，“COVID-19：我们对‘长期COVID’知道什么？”（2020）BMJ 370。\n3 萨拉·德赖赫斯特，克劳迪亚·R·施奈德，约翰·克尔，亚历山德拉·LJ·弗里曼，加布里埃尔·雷基亚，安妮·马特·范德·布莱斯，大卫·斯皮格尔霍尔特和桑德·范德·林登，“全球对COVID-19的风险感知”（2020）23(7-8)《风险研究杂志》994；万迪·布鲁因·德·布鲁因和丹尼尔·贝内特，“初始COVID-19风险感知与保护健康行为之间的关系：一项全国性调查”（2020）59(2)《美国预防医学杂志》157；西蒙·迪金和高峰·孟，“COVID-19的治理：人类活动风险、进化学习和社会国家的未来”（2020）49(4)《工业法杂志》539。"'
# Simple Queries
agent.run("What was the US GDP in 2019?")
[1m> Entering new AgentExecutor chain...[0m
[32;1m[1;3m
Invoking: `bearly_interpreter` with `{'python_code': "import pandas as pd\n\n# Load the data\nus_gdp = pd.read_csv('US_GDP.csv')\n\n# Convert the 'DATE' column to datetime\nus_gdp['DATE'] = pd.to_datetime(us_gdp['DATE'])\n\n# Filter the data for the year 2019\nus_gdp_2019 = us_gdp[us_gdp['DATE'].dt.year == 2019]\n\n# Print the GDP for 2019\nprint(us_gdp_2019['GDP'].values)"}`
[0m[36;1m[1;3m{'stdout': '[21104.133 21384.775 21694.282 21902.39 ]\n', 'stderr': '', 'fileLinks': [], 'exitCode': 0}[0m[32;1m[1;3mThe US GDP for each quarter in 2019 was as follows:
- Q1: 21104.133 billion dollars
- Q2: 21384.775 billion dollars
- Q3: 21694.282 billion dollars
- Q4: 21902.39 billion dollars[0m
[1m> Finished chain.[0m
'2019年美国每个季度的GDP如下：\n\n- Q1: 21104.133十亿美元\n- Q2: 21384.775十亿美元\n- Q3: 21694.282十亿美元\n- Q4: 21902.39十亿美元'
# Calculations
agent.run("What would the GDP be in 2030 if the latest GDP number grew by 50%?")
[1m> Entering new AgentExecutor chain...[0m
[32;1m[1;3m
Invoking: `bearly_interpreter` with `{'python_code': "import pandas as pd\n\n# Load the data\nus_gdp = pd.read_csv('US_GDP.csv')\n\n# Get the latest GDP\nlatest_gdp = us_gdp['GDP'].iloc[-1]\n\n# Calculate the GDP in 2030 if the latest GDP number grew by 50%\ngdp_2030 = latest_gdp * 1.5\nprint(gdp_2030)"}`
[0m[36;1m[1;3m{'stdout': '40594.518\n', 'stderr': '', 'fileLinks': [], 'exitCode': 0}[0m[32;1m[1;3mIf the latest GDP number grew by 50%, the GDP in 2030 would be approximately 40,594.518 billion dollars.[0m
[1m> Finished chain.[0m
'如果最新的GDP数字增长50%，2030年的GDP将约为40,594.518十亿美元。'
# Chart output
agent.run("Create a nice and labeled chart of the GDP growth over time")
[1m> Entering new AgentExecutor chain...[0m
[32;1m[1;3mCould not parse tool input: {'name': 'bearly_interpreter', 'arguments': '{\n "python_code": "\nimport pandas as pd\nimport matplotlib.pyplot as plt\n\n# Load the data\ndf = pd.read_csv(\'US_GDP.csv\')\n\n# Convert the \'DATE\' column to datetime format\ndf[\'DATE\'] = pd.to_datetime(df[\'DATE\'])\n\n# Plot the data\nplt.figure(figsize=(10,6))\nplt.plot(df[\'DATE\'], df[\'GDP\'], label=\'US GDP\')\nplt.xlabel(\'Year\')\nplt.ylabel(\'GDP (in billions)\')\nplt.title(\'US GDP Over Time\')\nplt.legend()\nplt.grid(True)\nplt.savefig(\'output/US_GDP.png\')\n"\n}'} because the `arguments` is not valid JSON.[0mInvalid or incomplete response[32;1m[1;3m
Invoking: `bearly_interpreter` with `{'python_code': "\nimport pandas as pd\nimport matplotlib.pyplot as plt\n\n# Load the data\ndf = pd.read_csv('US_GDP.csv')\n\n# Convert the 'DATE' column to datetime format\ndf['DATE'] = pd.to_datetime(df['DATE'])\n\n# Plot the data\nplt.figure(figsize=(10,6))\nplt.plot(df['DATE'], df['GDP'], label='US GDP')\nplt.xlabel('Year')\nplt.ylabel('GDP (in billions)')\nplt.title('US GDP Over Time')\nplt.legend()\nplt.grid(True)\nplt.savefig('output/US_GDP.png')\n"}`
[0m[36;1m[1;3m{'stdout': '', 'stderr': '', 'fileLinks': [{'pathname': 'US_GDP.png', 'tempLink': 'https://bearly-cubby.c559ae877a0a39985f534614a037d899.r2.cloudflarestorage.com/prod/bearly-cubby/temp/interpreter/2023_10/089daf37e9e343ba5ff21afaaa78b967c3466a550b3b11bd5c710c052b559e97/sxhM8gop2AYP88n5uHCsOJ6yTYNQm-HimZ70DcwQ4VI.png?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=c058d02de50a3cf0bb7e21c8e2d062c5%2F20231010%2F%2Fs3%2Faws4_request&X-Amz-Date=20231010T000000Z&X-Amz-Expires=604800&X-Amz-SignedHeaders=host&X-Amz-Signature=104dc0d4a4b71eeea1030dda1830059920cb0f354fa00197b439eb8565bf141a', 'size': 34275}], 'exitCode': 0}[0m[32;1m[1;3mHere is the chart of the US GDP growth over time:
The x-axis represents the year and the y-axis represents the GDP in billions. The line plot shows the growth of the US GDP over time.[0m
[1m> Finished chain.[0m
'这是美国GDP随时间增长的图表：\n\n\n\nx轴表示年份，y轴表示GDP（以十亿美元计）。线图显示了美国GDP随时间的增长。'