chatgpt 接口使用（一）

brightming2023-08-02 8:27

使用api实现功能

参考链接：https://platform.openai.com/examples

安装库：

pip3 install openai

例如：

python 复制代码

import os
import openai

openai.api_key = os.getenv("OPENAI_API_KEY")
response = openai.ChatCompletion.create(
  model="gpt-3.5-turbo",
  messages=[
    {
      "role": "system",
      "content": "You will be provided with unstructured data, and your task is to parse it into CSV format."
    },
    {
      "role": "user",
      "content": "There are many fruits that were found on the recently discovered planet Goocrux. There are neoskizzles that grow there, which are purple and taste like candy. There are also loheckles, which are a grayish blue fruit and are very tart, a little bit like a lemon. Pounits are a bright green color and are more savory than sweet. There are also plenty of loopnovas which are a neon pink flavor and taste like cotton candy. Finally, there are fruits called glowls, which have a very sour and bitter taste which is acidic and caustic, and a pale orange tinge to them."
    }
  ],
  temperature=0,
  max_tokens=256
)

print(response)

输出：

json 复制代码

{
  "id": "chatcmpl-7hwS9AKlAdarpkhXq3vHJAqnAETvz",
  "object": "chat.completion",
  "created": 1690707153,
  "model": "gpt-3.5-turbo-0613",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Fruit,Color,Taste\nneoskizzles,purple,candy\nloheckles,grayish blue,tart\npounits,bright green,savory\nloopnovas,neon pink,cotton candy\nglowls,pale orange,sour and bitter"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 161,
    "completion_tokens": 58,
    "total_tokens": 219
  }
}

利用私有数据

参考：

https://github.com/langchain-ai/langchain

https://github.com/techleadhd/chatgpt-retrieval

pip3 install langchain openai chromadb tiktoken unstructured

在chatgpt-retrieval测试：

python 复制代码

python3 chatgpt.py "what is my dog's name"

出现错误：

bash 复制代码

Chroma requires sqlite3 >= 3.35.0

解决方法：

1、安装

bash 复制代码

pip3 install pysqlite3-binary

2、根据出错的引用文件，找到

修改如下：

再次执行：