自然语言到 OpenAI API

创建代码以使用自然语言指令调用 OpenAI API。

""" Util 暴露了以下内容： util.openai() -> 验证并返回 openai 模块，该模块具有以下功能： openai.Completion.create( prompt="<my prompt>", # The prompt to start completion from max_tokens=123, # 生成的最大令牌数 temperature=1.0 # 随机性的度量 echo=True, # 除了生成的完成之外是否返回提示 ) """ import util """ 创建一个 OpenAI 完成开始来自提示“Once upon an AI”，不超过 5 个标记。不包括提示。“”“ 

 示例响应

openai = util.openai() completion = openai.Completion.create(prompt="Once upon an AI", max_tokens=5, echo=False) """

Python
 

import os
import openai

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

response = openai.Completion.create(
  model="text-davinci-003",
  prompt="\"\"\"\nUtil exposes the following:\nutil.openai() -> authenticates & returns the openai module, which has the following functions:\nopenai.Completion.create(\n    prompt=\"<my prompt>\", # The prompt to start completing from\n    max_tokens=123, # The max number of tokens to generate\n    temperature=1.0 # A measure of randomness\n    echo=True, # Whether to return the prompt in addition to the generated completion\n)\n\"\"\"\nimport util\n\"\"\"\nCreate an OpenAI completion starting from the prompt \"Once upon an AI\", no more than 5 tokens. Does not include the prompt.\n\"\"\"\n",
  temperature=0,
  max_tokens=64,
  top_p=1.0,
  frequency_penalty=0.0,
  presence_penalty=0.0,
  stop=["\"\"\""]
)

JavaScript

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: "\"\"\"\nUtil exposes the following:\nutil.openai() -> authenticates & returns the openai module, which has the following functions:\nopenai.Completion.create(\n    prompt=\"<my prompt>\", # The prompt to start completing from\n    max_tokens=123, # The max number of tokens to generate\n    temperature=1.0 # A measure of randomness\n    echo=True, # Whether to return the prompt in addition to the generated completion\n)\n\"\"\"\nimport util\n\"\"\"\nCreate an OpenAI completion starting from the prompt \"Once upon an AI\", no more than 5 tokens. Does not include the prompt.\n\"\"\"\n",
  temperature: 0,
  max_tokens: 64,
  top_p: 1.0,
  frequency_penalty: 0.0,
  presence_penalty: 0.0,
  stop: ["\"\"\""],
});

curl https://api.openai.com/v1/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -d '{
  "model": "text-davinci-003",
  "prompt": "\"\"\"\nUtil exposes the following:\nutil.openai() -> authenticates & returns the openai module, which has the following functions:\nopenai.Completion.create(\n    prompt=\"<my prompt>\", # The prompt to start completing from\n    max_tokens=123, # The max number of tokens to generate\n    temperature=1.0 # A measure of randomness\n    echo=True, # Whether to return the prompt in addition to the generated completion\n)\n\"\"\"\nimport util\n\"\"\"\nCreate an OpenAI completion starting from the prompt \"Once upon an AI\", no more than 5 tokens. Does not include the prompt.\n\"\"\"\n",
  "temperature": 0,
  "max_tokens": 64,
  "top_p": 1.0,
  "frequency_penalty": 0.0,
  "presence_penalty": 0.0,
  "stop": ["\"\"\""]
}'