Skip to main content

MetaLM工具集

Project description

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()

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

metalm_tools-0.1.2.tar.gz (12.0 kB view details)

Uploaded Source

Built Distribution

metalm_tools-0.1.2-py3-none-any.whl (7.5 kB view details)

Uploaded Python 3

File details

Details for the file metalm_tools-0.1.2.tar.gz.

File metadata

  • Download URL: metalm_tools-0.1.2.tar.gz
  • Upload date:
  • Size: 12.0 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.9.19

File hashes

Hashes for metalm_tools-0.1.2.tar.gz
Algorithm Hash digest
SHA256 e8e55bd9ceb09d0c27b580cfc1e85b6df77c8eb8e9859eb31a39f18a2bde794d
MD5 593f5c791d41b19eee45251d7ea90e64
BLAKE2b-256 7facd3a993f59a30da450302cb78d3afab2884a7db01a4e26b84432ed230348e

See more details on using hashes here.

File details

Details for the file metalm_tools-0.1.2-py3-none-any.whl.

File metadata

File hashes

Hashes for metalm_tools-0.1.2-py3-none-any.whl
Algorithm Hash digest
SHA256 7e2de658956324600889ba1159dfabf577c59e28221f857acd0f55579f91be11
MD5 4bcd54ee39aedd922a7b4fd81c95e97c
BLAKE2b-256 7a4958ee91ad7bfc1aa194e1859c4a2947e931c49112e7fa159a935a8df3369e

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page