openai 接口开发

简介

本文讲解如何使用openai账户，做接口开发

步骤

• 安装conda，这里不详细说明
• 准备 OPENAI_API_KEY，这个信息请在官网获取
• 配置OPENAI_API_KEY，文件~/.bash_profile末尾添加

## sk-XXXXXX 是截图的值，杜泽可以按自己的情况配置
export OPENAI_API_KEY=sk-XXXXXX

• 使用环境变量生效

source ~/.bash_profile 

• 创建环境和依赖

conda create --name openai-env python=3.11.5
conda activate openai-env
pip install openai jupyter

• 启动jupyter

# 启动本地应用
cd /path/in/applications/

jupyter notebook

• 在页面上创建一个demo.ipynb

• 创建代码

from openai import OpenAI

client = OpenAI()
#client = OpenAI(
#  api_key=os.environ['OPENAI_API_KEY'],  # this is also the default, it can be omitted
#)
completion = client.chat.completions.create(
  model="gpt-3.5-turbo",
  messages=[
    {"role": "system", "content": "You are a poetic assistant, skilled in explaining complex programming concepts with creative flair."},
    {"role": "user", "content": "Compose a poem that explains the concept of recursion in programming."}
  ]
)

print(completion.choices[0].message)

执行效果：