如何保持 GPT-3 API 响应的格式？答案

【问题标题】：How to keep the format of OpenAI API response?如何保持 GPT-3 API 响应的格式？
【发布时间】：2023-01-11 23:08:03
【问题描述】：

当我使用 GPT3 的 playground 时，我经常得到带有编号列表和段落格式的结果，如下所示：

Here's what the above class is doing:

1. It creates a directory for the log file if it doesn't exist.
2. It checks that the log file is newline-terminated.
3. It writes a newline-terminated JSON object to the log file.
4. It reads the log file and returns a dictionary with the following

- list 1
- list 2
- list 3
- list 4

但是，当我直接使用他们的 API 并从 json 结果中提取响应时，我得到了很难阅读的塞满文本版本，如下所示：

Here's what the above class is doing:1. It creates a directory for the log file if it doesn't exist.2. It checks that the log file is newline-terminated.3. It writes a newline-terminated JSON object to the log file.4. It reads the log file and returns a dictionary with the following-list 1-list 2-list 3- list4

我的问题是，人们如何保留 GPT 结果的格式，以便它们以更整洁、更易读的方式显示？

【问题讨论】：

标签： gpt-3

【解决方案1】：

选项一：Edits endpoint

如果您运行test.py，OpenAI API 将返回以下完成信息：

测试.py

import openai

openai.api_key = "<OPENAI_API_KEY>"

response = openai.Edit.create(
  model = "text-davinci-edit-001",
  input = "I have three items:1. First item.2. Second item.3. Third item.",
  instruction = "Make numbered list"
)

content = response['choices'][0]['text']

print(content)

选项 2：处理

自己处理从 Completions endpoint 获得的完成（即，编写 Python 代码）。

【讨论】：