Skip to main content

MetaLM-tools

metalm的工具集,当前只有代码解释器这一个工具。

案例:

from metalm_tools import MetaLMInterpreterTool
import time 
import json

packages=['numpy','pandas']
#画图
c = """
import matplotlib.pyplot as plt
import time

# 数据
x = [1, 2, 3, 4, 5]
y = [1, 4, 9, 16, 25]

# 创建折线图
plt.plot(x, y, marker='o')

# 添加标题和轴标签
plt.title("Simple Line Plot")
plt.xlabel("X Axis")
plt.ylabel("Y Axis")

# 显示图形
plt.grid(True)  # 显示网格线
plt.show()
plt.savefig('test1.png')
x = [1, 2, 3, 4, 5]
y = [1, 4, 9, 16, 25]

# 创建折线图
plt.plot(x, y, marker='o')

# 添加标题和轴标签
plt.title("Simple Line Plot")
plt.xlabel("X Axis")
plt.ylabel("Y Axis")

# 显示图形
plt.grid(True)  # 显示网格线
plt.show()
plt.savefig('test2.png')

for i in x:
    print(i)
    time.sleep(1)
"""
#操作csv
c2 = """
import pandas as pd

# 读取CSV文件
df = pd.read_csv('/codebox/1.csv')

# 获取前5行
df_first_five = df.head(5)

# 保存前5行到新的CSV文件
df_first_five.to_csv('output_file.csv', index=False)

print("前5行已保存到 'output_file.csv'")

"""

tool = MetaLMInterpreterTool(<服务url>,'empty')
print(tool.session.session_id)
tool.install_python_packages(packages)
res1 = tool.upload_files([<上传文件>],['这是要分析的数据'])
res2 = tool.upload_files([<上传图片>],['这是图片'])
print('path:',res1,res2)
rsp = tool._run(c2)
rsp = json.loads(rsp)
print(rsp)
tbyte = tool.download_files(['output_file.csv'])
print(tbyte)

rsp = tool._run(c)
rsp = json.loads(rsp)
print(rsp)

tool.close()

Metadata

Release files for metalm-tools 0.1.2

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for metalm-tools 0.1.2
File Size Uploaded Provenance Actions
metalm_tools-0.1.2.tar.gz 12.0 kB Without provenance Details for metalm_tools-0.1.2.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for metalm-tools 0.1.2
File Interpreter ABI Platform Actions
metalm_tools-0.1.2-py3-none-any.whl Python 3 none any Details for metalm_tools-0.1.2-py3-none-any.whl

Total release size: 19.5 kB

Release files / metalm_tools-0.1.2.tar.gz

Download URL metalm_tools-0.1.2.tar.gz
Size 12.0 kB
Tags Source
SHA-256 checksum
How to use checksums
e8e55bd9ceb09d0c27b580cfc1e85b6df77c8eb8e9859eb31a39f18a2bde794d
BLAKE2b-256 checksum
How to use checksums
7facd3a993f59a30da450302cb78d3afab2884a7db01a4e26b84432ed230348e
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/4.0.2 CPython/3.9.19

Release files / metalm_tools-0.1.2-py3-none-any.whl

Download URL metalm_tools-0.1.2-py3-none-any.whl
Size 7.5 kB
Tags Python 3
SHA-256 checksum
How to use checksums
7e2de658956324600889ba1159dfabf577c59e28221f857acd0f55579f91be11
BLAKE2b-256 checksum
How to use checksums
7a4958ee91ad7bfc1aa194e1859c4a2947e931c49112e7fa159a935a8df3369e
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/4.0.2 CPython/3.9.19

Security for metalm-tools 0.1.2

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page