E2B 数据分析
E2B 的云环境 是大型语言模型的绝佳运行时沙箱。
E2B 的数据分析沙箱允许在沙盒环境中安全执行代码。这非常适合构建诸如代码解释器之类的工具，或像 ChatGPT 中那样的高级数据分析。
E2B 数据分析沙箱允许您
- 运行 Python 代码
- 通过 matplotlib 生成图表
- 在运行时动态安装 Python 包
- 在运行时动态安装系统包
- 运行 shell 命令
- 上传和下载文件
我们将创建一个简单的 OpenAI 代理，它将使用 E2B 的数据分析沙箱，使用 Python 对上传的文件执行分析。
获取您的 OpenAI API 密钥和 E2B API 密钥 并将其设置为环境变量。
您可以在 此处 找到完整的 API 文档。
您需要安装 e2b 才能开始使用
%pip install --upgrade --quiet langchain e2b langchain-community
from langchain_community.tools import E2BDataAnalysisTool
API 参考：E2BDataAnalysisTool
import os
from langchain.agents import AgentType, initialize_agent
from langchain_openai import ChatOpenAI
os.environ["E2B_API_KEY"] = "<E2B_API_KEY>"
os.environ["OPENAI_API_KEY"] = "<OPENAI_API_KEY>"
在创建 E2BDataAnalysisTool 的实例时，您可以传递回调以监听沙箱的输出。例如，在创建更具响应性的 UI 时，这很有用。特别是结合大型语言模型的流输出。
# Artifacts are charts created by matplotlib when `plt.show()` is called
def save_artifact(artifact):
print("New matplotlib chart generated:", artifact.name)
# Download the artifact as `bytes` and leave it up to the user to display them (on frontend, for example)
file = artifact.download()
basename = os.path.basename(artifact.name)
# Save the chart to the `charts` directory
with open(f"./charts/{basename}", "wb") as f:
f.write(file)
e2b_data_analysis_tool = E2BDataAnalysisTool(
# Pass environment variables to the sandbox
env_vars={"MY_SECRET": "secret_value"},
on_stdout=lambda stdout: print("stdout:", stdout),
on_stderr=lambda stderr: print("stderr:", stderr),
on_artifact=save_artifact,
)
将示例 CSV 数据文件上传到沙箱，以便我们可以使用代理对其进行分析。例如，您可以使用 此文件，其中包含有关 Netflix 电视节目的信息。
with open("./netflix.csv") as f:
remote_path = e2b_data_analysis_tool.upload_file(
file=f,
description="Data about Netflix tv shows including their title, category, director, release date, casting, age rating, etc.",
)
print(remote_path)
name='netflix.csv' remote_path='/home/user/netflix.csv' description='Data about Netflix tv shows including their title, category, director, release date, casting, age rating, etc.'
创建一个 Tool 对象并初始化 Langchain 代理。
tools = [e2b_data_analysis_tool.as_tool()]
llm = ChatOpenAI(model="gpt-4", temperature=0)
agent = initialize_agent(
tools,
llm,
agent=AgentType.OPENAI_FUNCTIONS,
verbose=True,
handle_parsing_errors=True,
)
现在我们可以询问代理有关我们之前上传的 CSV 文件的问题。
agent.run(
"What are the 5 longest movies on netflix released between 2000 and 2010? Create a chart with their lengths."
)
[1m> Entering new AgentExecutor chain...[0m
[32;1m[1;3m
Invoking: `e2b_data_analysis` with `{'python_code': "import pandas as pd\n\n# Load the data\nnetflix_data = pd.read_csv('/home/user/netflix.csv')\n\n# Convert the 'release_year' column to integer\nnetflix_data['release_year'] = netflix_data['release_year'].astype(int)\n\n# Filter the data for movies released between 2000 and 2010\nfiltered_data = netflix_data[(netflix_data['release_year'] >= 2000) & (netflix_data['release_year'] <= 2010) & (netflix_data['type'] == 'Movie')]\n\n# Remove rows where 'duration' is not available\nfiltered_data = filtered_data[filtered_data['duration'].notna()]\n\n# Convert the 'duration' column to integer\nfiltered_data['duration'] = filtered_data['duration'].str.replace(' min','').astype(int)\n\n# Get the top 5 longest movies\nlongest_movies = filtered_data.nlargest(5, 'duration')\n\n# Create a bar chart\nimport matplotlib.pyplot as plt\n\nplt.figure(figsize=(10,5))\nplt.barh(longest_movies['title'], longest_movies['duration'], color='skyblue')\nplt.xlabel('Duration (minutes)')\nplt.title('Top 5 Longest Movies on Netflix (2000-2010)')\nplt.gca().invert_yaxis()\nplt.savefig('/home/user/longest_movies.png')\n\nlongest_movies[['title', 'duration']]"}`
[0mstdout: title duration
stdout: 1019 Lagaan 224
stdout: 4573 Jodhaa Akbar 214
stdout: 2731 Kabhi Khushi Kabhie Gham 209
stdout: 2632 No Direction Home: Bob Dylan 208
stdout: 2126 What's Your Raashee? 203
[36;1m[1;3m{'stdout': " title duration\n1019 Lagaan 224\n4573 Jodhaa Akbar 214\n2731 Kabhi Khushi Kabhie Gham 209\n2632 No Direction Home: Bob Dylan 208\n2126 What's Your Raashee? 203", 'stderr': ''}[0m[32;1m[1;3mThe 5 longest movies on Netflix released between 2000 and 2010 are:
1. Lagaan - 224 minutes
2. Jodhaa Akbar - 214 minutes
3. Kabhi Khushi Kabhie Gham - 209 minutes
4. No Direction Home: Bob Dylan - 208 minutes
5. What's Your Raashee? - 203 minutes
Here is the chart showing their lengths:
[0m
[1m> Finished chain.[0m
"The 5 longest movies on Netflix released between 2000 and 2010 are:\n\n1. Lagaan - 224 minutes\n2. Jodhaa Akbar - 214 minutes\n3. Kabhi Khushi Kabhie Gham - 209 minutes\n4. No Direction Home: Bob Dylan - 208 minutes\n5. What's Your Raashee? - 203 minutes\n\nHere is the chart showing their lengths:\n\n"
E2B 还允许您在运行时动态安装 Python 和系统（通过 apt）包，如下所示
# Install Python package
e2b_data_analysis_tool.install_python_packages("pandas")
stdout: Requirement already satisfied: pandas in /usr/local/lib/python3.10/dist-packages (2.1.1)
stdout: Requirement already satisfied: python-dateutil>=2.8.2 in /usr/local/lib/python3.10/dist-packages (from pandas) (2.8.2)
stdout: Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.10/dist-packages (from pandas) (2023.3.post1)
stdout: Requirement already satisfied: numpy>=1.22.4 in /usr/local/lib/python3.10/dist-packages (from pandas) (1.26.1)
stdout: Requirement already satisfied: tzdata>=2022.1 in /usr/local/lib/python3.10/dist-packages (from pandas) (2023.3)
stdout: Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.10/dist-packages (from python-dateutil>=2.8.2->pandas) (1.16.0)
此外，您可以从沙箱下载任何文件，如下所示
# The path is a remote path in the sandbox
files_in_bytes = e2b_data_analysis_tool.download_file("/home/user/netflix.csv")
最后，您可以通过 run_command 在沙箱中运行任何 shell 命令。
# Install SQLite
e2b_data_analysis_tool.run_command("sudo apt update")
e2b_data_analysis_tool.install_system_packages("sqlite3")
# Check the SQLite version
output = e2b_data_analysis_tool.run_command("sqlite3 --version")
print("version: ", output["stdout"])
print("error: ", output["stderr"])
print("exit code: ", output["exit_code"])
stderr:
stderr: WARNING: apt does not have a stable CLI interface. Use with caution in scripts.
stderr:
stdout: Hit:1 http://security.ubuntu.com/ubuntu jammy-security InRelease
stdout: Hit:2 http://archive.ubuntu.com/ubuntu jammy InRelease
stdout: Hit:3 http://archive.ubuntu.com/ubuntu jammy-updates InRelease
stdout: Hit:4 http://archive.ubuntu.com/ubuntu jammy-backports InRelease
stdout: Reading package lists...
stdout: Building dependency tree...
stdout: Reading state information...
stdout: All packages are up to date.
stdout: Reading package lists...
stdout: Building dependency tree...
stdout: Reading state information...
stdout: Suggested packages:
stdout: sqlite3-doc
stdout: The following NEW packages will be installed:
stdout: sqlite3
stdout: 0 upgraded, 1 newly installed, 0 to remove and 0 not upgraded.
stdout: Need to get 768 kB of archives.
stdout: After this operation, 1873 kB of additional disk space will be used.
stdout: Get:1 http://archive.ubuntu.com/ubuntu jammy-updates/main amd64 sqlite3 amd64 3.37.2-2ubuntu0.1 [768 kB]
stderr: debconf: delaying package configuration, since apt-utils is not installed
stdout: Fetched 768 kB in 0s (2258 kB/s)
stdout: Selecting previously unselected package sqlite3.
(Reading database ... 23999 files and directories currently installed.)
stdout: Preparing to unpack .../sqlite3_3.37.2-2ubuntu0.1_amd64.deb ...
stdout: Unpacking sqlite3 (3.37.2-2ubuntu0.1) ...
stdout: Setting up sqlite3 (3.37.2-2ubuntu0.1) ...
stdout: 3.37.2 2022-01-06 13:25:41 872ba256cbf61d9290b571c0e6d82a20c224ca3ad82971edc46b29818d5dalt1
version: 3.37.2 2022-01-06 13:25:41 872ba256cbf61d9290b571c0e6d82a20c224ca3ad82971edc46b29818d5dalt1
error:
exit code: 0
代理完成后，请务必关闭沙箱
e2b_data_analysis_tool.close()