当前位置: 首页 > news >正文

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

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}
}


http://www.mrgr.cn/news/18748.html

相关文章:

  • js之深度理解扩展运算符(Spread Operator)
  • RAG项目实战
  • 算法笔试-编程练习-M-01-24
  • idea2023.3安装不上通义灵码(插件无法下载)解决方法(非常简单)
  • Linux 进程概念 进程状态 fock函数讲解
  • 刷题记录(2)
  • ABAP OO面向对象设计
  • 【数据结构】Set的使用与注意事项
  • SpringBoot集成Redis——RedisTemplate
  • 科研习惯 [4] 学会表达
  • 大规模语言模型开发基础与实践
  • 宠物智能家居监测器的融合
  • vue3项目快速了解
  • geoserver介绍
  • 日志系统(最新版)
  • 【综合架构】Part 5.2 Ansible
  • HTTP“请求”和“响应”的报头及正文详解
  • std::future和std::promise详解(原理、应用、源码)
  • C++项目详细分析_WebServer
  • tailwindcss在vue2中安装配置流程