全網最詳細中英文ChatGPT-GPT-4示例文件-食譜智慧生成從0到1快速入門——官網推薦的48種最佳應用場景(附python/node.js/curl命令原始碼,小白也能學)

虎嘯AI發表於2023-04-10

Image

ChatGPT是目前最先進的AI聊天機器人,它能夠理解圖片和文字,生成流暢和有趣的回答。如果你想跟上AI時代的潮流,你一定要學會使用ChatGPT。如果你想了解OpenAI最新發布的GPT-4模型,以及它如何為ChatGPT聊天機器人帶來更強大的功能,那麼你一定不要錯過OpenAI官網推薦的48種最佳應用場景,不管你是資深開發者、初學者,你都能夠從0到1快速入門,並掌握他們。

在這個AI大時代,如果不想被人顛覆,就要先顛覆別人。如果你顛覆不了別人,那你就努力運用ChatGPT提高你的技術水平和創造力。

ChatGPT的訓練資料涵蓋了大量的食材和食譜,可以透過結合大量的料理方法,快速地為使用者生成符合自己口味的食譜。所以在和美食相關的行業,ChatGPT可以根據使用者的各種美食需求,為其提供美味又有營養的餐食搭配,幫助使用者更輕鬆地製作美食,享受美味。

Introduce 簡介

Recipe creator (eat at your own risk) 食譜創造者(吃東西的風險自負)
Create a recipe from a list of ingredients.
根據配料列表建立食譜。

setting 設定

Engine: text-davinci-003
Max tokens:120
Temperature:0.3
Top p:1.0
Frequency penalty:0.0
Presence penalty:0.0

說明:
0、Engine 設定定義了你要使用的模型,例如 text-davinci-003是一個文字生成模型。這種模型可以根據輸入的文字,生成新的、相關的文字。
1、Max tokens是指在請求中最多允許返回的 token 數目,比如你可以指定 chatGPT 返回最多120個 token。這可以幫助你控制輸出的內容大小,以便更好地控制響應速度和結果。一般1個token約4個字元或者0.75個單詞
2、Temperature 是一個引數,用於控制 chatGPT 的輸出。它決定了 chatGPT 在生成文字時會多麼“隨意”。值越高,chatGPT 生成的文字就越不可預測;值越低,chatGPT 生成的文字就越可預測。它在0.0到2.0之間,Temperature設定為0意味著ChatGPT將會生成更加保守的回覆,即更少的隨機性和更多的準確性,這可以幫助你在聊天中更好地控制語義,並且可以防止ChatGPT產生不相關的內容。通常建議更改此值或 Top P,但不要同時更改這兩個值。
3、Top p 是隨溫度取樣的替代方案,稱為核取樣,其中模型考慮具有top_p機率質量的標記的結果。因此0.1意味著僅考慮包括前10%機率質量的記號。通常建議更改此值或 temperature,但不要同時更改這兩個值。
4、Frequency penalty 是指在訓練時,模型會根據詞頻來調整每個單詞的重要性。它可以幫助模型更好地理解文字,並減少過擬合。介於-2.0和2.0之間的數字。正值會根據新標記在文字中的現有頻率懲罰新標記,從而降低模型逐字重複同一行的可能性。Frequency penalty設定為0意味著模型不會對重複的詞進行懲罰。它可以幫助模型生成更多的新詞,而不是重複使用已有的詞。
5、Presence penalty 是指在ChatGPT中,一些預先定義的條件或者狀態可能會影響機器人回答的質量,介於-2.0和2.0之間的數字。正值會根據新標記到目前為止是否出現在文字中來懲罰它們,從而增加模型談論新主題的可能性。如果將 Presence penalty 設定為 0,則表示不會有任何懲罰。

Prompt 提示

Write a recipe based on these ingredients and instructions:
Frito Pie 墨西哥玉米片派
Ingredients: 成分
Fritos 玉米煎餅
Chili 辣椒
Shredded cheddar cheese 切達乾酪絲
Sweet white or red onions, diced small 甜的白色或紅色洋蔥,切成小塊
Sour cream 酸奶油
Instructions: 說明:

Sample response 回覆樣本

  1. Preheat oven to 350 degrees F.
  2. Spread a layer of Fritos in the bottom of a 9x13 inch baking dish.
  3. Top the Fritos with a layer of chili.
  4. Sprinkle the chili with shredded cheddar cheese.
  5. Sprinkle the cheese with diced onions.
  6. Bake in preheated oven for 25 minutes.
  7. Remove from oven and top with a dollop of sour cream.
  8. Serve warm. Enjoy!
    1.烤箱預熱到華氏350度。
    2.在一個9 x13英寸的烤盤底部鋪上一層玉米煎餅。
    3.在炸玉米餅上放一層辣椒。
    4.在辣椒上撒上切達乾酪絲。
    5.在乳酪上撒上洋蔥丁。
    6.入預熱烤箱烤25分鐘。
    7.從烤箱中取出,在上面放一團酸奶油。
    8.趁熱食用。好好享受吧!

API request 介面請求

python介面請求示例

import os
import openai

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

response = openai.Completion.create(
  model="text-davinci-003",
  prompt="Write a recipe based on these ingredients and instructions:\n\nFrito Pie\n\nIngredients:\nFritos\nChili\nShredded cheddar cheese\nSweet white or red onions, diced small\nSour cream\n\nInstructions:",
  temperature=0.3,
  max_tokens=120,
  top_p=1.0,
  frequency_penalty=0.0,
  presence_penalty=0.0
)

node.js介面請求示例

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: "Write a recipe based on these ingredients and instructions:\n\nFrito Pie\n\nIngredients:\nFritos\nChili\nShredded cheddar cheese\nSweet white or red onions, diced small\nSour cream\n\nInstructions:",
  temperature: 0.3,
  max_tokens: 120,
  top_p: 1.0,
  frequency_penalty: 0.0,
  presence_penalty: 0.0,
});

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": "Write a recipe based on these ingredients and instructions:\n\nFrito Pie\n\nIngredients:\nFritos\nChili\nShredded cheddar cheese\nSweet white or red onions, diced small\nSour cream\n\nInstructions:",
  "temperature": 0.3,
  "max_tokens": 120,
  "top_p": 1.0,
  "frequency_penalty": 0.0,
  "presence_penalty": 0.0
}'

json格式示例

{
  "model": "text-davinci-003",
  "prompt": "Write a recipe based on these ingredients and instructions:\n\nFrito Pie\n\nIngredients:\nFritos\nChili\nShredded cheddar cheese\nSweet white or red onions, diced small\nSour cream\n\nInstructions:",
  "temperature": 0.3,
  "max_tokens": 120,
  "top_p": 1.0,
  "frequency_penalty": 0.0,
  "presence_penalty": 0.0
}

其它資料下載

如果大家想繼續瞭解人工智慧相關學習路線和知識體系,歡迎大家翻閱我的另外一篇部落格《重磅 | 完備的人工智慧AI 學習——基礎知識學習路線,所有資料免關注免套路直接網盤下載
這篇部落格參考了Github知名開源平臺,AI技術平臺以及相關領域專家:Datawhale,ApacheCN,AI有道和黃海廣博士等約有近100G相關資料,希望能幫助到所有小夥伴們。

相關文章