全网最详细中英文ChatGPT-GPT-4示例文档-人工智能助手从0到1快速入门——官网推荐的48种最佳应用场景(附python/node.js/curl命令源代码,小白也能学)

发布时间 2023-04-10 11:47:12作者: 虎啸AI

image

ChatGPT是目前最先进的AI聊天机器人,它能够理解图片和文字,生成流畅和有趣的回答。如果你想跟上AI时代的潮流,你一定要学会使用ChatGPT。如果你想了解OpenAI最新发布的GPT-4模型,以及它如何为ChatGPT聊天机器人带来更强大的功能,那么你一定不要错过OpenAI官网推荐的48种最佳应用场景,不管你是资深开发者、初学者,你都能够从0到1快速入门,并掌握他们。

在这个AI大时代,如果不想被人颠覆,就要先颠覆别人。如果你颠覆不了别人,那你就努力运用ChatGPT提高你的技术水平和创造力。

作为一个智能语言模型,ChatGPT可以扮演各种角色,与人类进行自然语言交互。它能够很好地理解人类语言,并根据对话场景生成相应的回复,同时ChatGPT还可以模仿人类的语言风格,以便更好地与人类进行交流。ChatGPT这一强大的功能和智能化程度,将为各行各业带来更高效、更智能化的智能AI助手解决方案。

Introduce 简介

Chat 聊天
Open ended conversation with an AI assistant.
与人工智能助手的开放式对话。

setting 设置

Engine: text-davinci-003
Max tokens:150
Temperature:0.9
Top p:1.0
Frequency penalty:0.0
Presence penalty:0.6
Stop sequenceHuman: AI:

说明:
0、Engine 设置定义了你要使用的模型,例如 text-davinci-003是一个文本生成模型。这种模型可以根据输入的文本,生成新的、相关的文本。
1、Max tokens是指在请求中最多允许返回的 token 数目,比如你可以指定 chatGPT 返回最多150个 token。这可以帮助你控制输出的内容大小,以便更好地控制响应速度和结果。一般1个token约4个字符或者0.75个单词
2、Temperature 是一个参数,用于控制 chatGPT 的输出。它决定了 chatGPT 在生成文本时会多么“随意”。值越高,chatGPT 生成的文本就越不可预测;值越低,chatGPT 生成的文本就越可预测。它在0.0到2.0之间,Temperature设置为0意味着ChatGPT将会生成更加保守的回复,即更少的随机性和更多的准确性,这可以帮助你在聊天中更好地控制语义,并且可以防止ChatGPT产生不相关的内容。通常建议更改此值或 Top P,但不要同时更改这两个值。
3、Top p 是随温度采样的替代方案,称为核采样,其中模型考虑具有top_p概率质量的标记的结果。因此0.1意味着仅考虑包括前10%概率质量的记号。通常建议更改此值或 temperature,但不要同时更改这两个值。
4、Frequency penalty 是指在训练时,模型会根据词频来调整每个单词的重要性。它可以帮助模型更好地理解文本,并减少过拟合。介于-2.0和2.0之间的数字。正值会根据新标记在文本中的现有频率惩罚新标记,从而降低模型逐字重复同一行的可能性。Frequency penalty设置为0意味着模型不会对重复的词进行惩罚。它可以帮助模型生成更多的新词,而不是重复使用已有的词。
5、Presence penalty 是指在ChatGPT中,一些预先定义的条件或者状态可能会影响机器人回答的质量,介于-2.0和2.0之间的数字。正值会根据新标记到目前为止是否出现在文本中来惩罚它们,从而增加模型谈论新主题的可能性。如果将 Presence penalty 设置为 0,则表示不会有任何惩罚。
6、Stop sequence 是一种设置,通过它可以确定你的聊天会话的结束标志。当你在 ChatGPT中设置 Stop sequence为Human: 时,表示你的聊天会话结束标志是换行符(Human: )。当你在 ChatGPT中设置 Stop sequence为 AI: 时,表示你的聊天会话结束标志是注释符( AI:)。

Prompt 提示

The following is a conversation with an AI assistant. The assistant is helpful, creative, clever, and very friendly.
以下是与AI助理的对话。服务员乐于助人,有创意,聪明,非常友好。
Human: Hello, who are you?
人类:你好,你是谁?
AI: I am an AI created by OpenAI. How can I help you today?
AI:我是OpenAI创造的AI。今天有什么能帮你的吗?
Human: I'd like to cancel my subscription.
人类:我想取消订阅。
AI:

Sample response 回复样本

I understand, I can help you with canceling your subscription. Please provide me with your account details so that I can begin processing the cancellation.
我明白,我可以帮你退订。请向我提供您的帐户详细信息,以便我可以开始处理取消。

API request 接口请求

python接口请求示例

import os
import openai

openai.api_key = os.getenv("OPENAI_API_KEY")

response = openai.Completion.create(
  model="text-davinci-003",
  prompt="The following is a conversation with an AI assistant. The assistant is helpful, creative, clever, and very friendly.\n\nHuman: Hello, who are you?\nAI: I am an AI created by OpenAI. How can I help you today?\nHuman: I'd like to cancel my subscription.\nAI:",
  temperature=0.9,
  max_tokens=150,
  top_p=1,
  frequency_penalty=0.0,
  presence_penalty=0.6,
  stop=[" Human:", " AI:"]
)

node.js接口请求示例

const { Configuration, OpenAIApi } = require("openai");

const configuration = new Configuration({
  apiKey: process.env.OPENAI_API_KEY,
});
const openai = new OpenAIApi(configuration);

const response = await openai.createCompletion({
  model: "text-davinci-003",
  prompt: "The following is a conversation with an AI assistant. The assistant is helpful, creative, clever, and very friendly.\n\nHuman: Hello, who are you?\nAI: I am an AI created by OpenAI. How can I help you today?\nHuman: I'd like to cancel my subscription.\nAI:",
  temperature: 0.9,
  max_tokens: 150,
  top_p: 1,
  frequency_penalty: 0.0,
  presence_penalty: 0.6,
  stop: [" Human:", " AI:"],
});

curl命令示例

curl https://api.openai.com/v1/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -d '{
  "model": "text-davinci-003",
  "prompt": "The following is a conversation with an AI assistant. The assistant is helpful, creative, clever, and very friendly.\n\nHuman: Hello, who are you?\nAI: I am an AI created by OpenAI. How can I help you today?\nHuman: I'd like to cancel my subscription.\nAI:",
  "temperature": 0.9,
  "max_tokens": 150,
  "top_p": 1,
  "frequency_penalty": 0.0,
  "presence_penalty": 0.6,
  "stop": [" Human:", " AI:"]
}'

json格式示例

{
  "model": "text-davinci-003",
  "prompt": "The following is a conversation with an AI assistant. The assistant is helpful, creative, clever, and very friendly.\n\nHuman: Hello, who are you?\nAI: I am an AI created by OpenAI. How can I help you today?\nHuman: I'd like to cancel my subscription.\nAI:",
  "temperature": 0.9,
  "max_tokens": 150,
  "top_p": 1,
  "frequency_penalty": 0.0,
  "presence_penalty": 0.6,
  "stop": [" Human:", " AI:"]
}

其它资料下载

如果大家想继续了解人工智能相关学习路线和知识体系,欢迎大家翻阅我的另外一篇博客《重磅 | 完备的人工智能AI 学习——基础知识学习路线,所有资料免关注免套路直接网盘下载
这篇博客参考了Github知名开源平台,AI技术平台以及相关领域专家:Datawhale,ApacheCN,AI有道和黄海广博士等约有近100G相关资料,希望能帮助到所有小伙伴们。