当前位置：首页 > article >正文

OpenAI API: Can I remove the line break from the response with a parameter?

article 2024/11/14 10:32:52

题意：OpenAI API：我可以通过一个参数从响应中移除换行符吗？

问题背景：

I've starting using OpenAI API in R. I downloaded the openai package. I keep getting a double linebreak in the text response. Here's an example of my code:

我开始在 R 中使用 OpenAI API，并下载了 `openai` 包。我在文本响应中总是遇到双换行符的问题。以下是我的代码示例：

library(openai)

vector = create_completion(
  model = "text-davinci-003",
  prompt = "Tell me what the weather is like in London, UK, in Celsius in 5 words.",
  max_tokens = 20,
  temperature = 0,
  echo = FALSE
)


vector_2 = vector$choices[1]

vector_2$text


[1] "\n\nRainy, mild, cool, humid."

Is there a way to get rid of this without 'correcting' the response text using other functions?

有没有办法在不使用其他函数来“修正”响应文本的情况下去除这个问题？

问题解决：

No, it's not possible. 不，可可能

The OpenAI API returns the completion with a starting \n\n by default. There's no parameter for the Completions endpoint to control this.

OpenAI API 默认会在返回的完成文本前加上 `\n\n`。对于 Completions 端点，没有参数可以控制这一点。

You need to remove the line break manually. 你需要手动去掉换行符

An example response looks like this: 一个示例响应如下所示：

{
  "id": "cmpl-uqkvlQyYK7bGYrRHQ0eXlWi7",
  "object": "text_completion",
  "created": 1589478378,
  "model": "text-davinci-003",
  "choices": [
    {
      "text": "\n\nThis is indeed a test",
      "index": 0,
      "logprobs": null,
      "finish_reason": "length"
    }
  ],
  "usage": {
    "prompt_tokens": 5,
    "completion_tokens": 7,
    "total_tokens": 12
  }
}