ChatGPT 快速部署体验版本

前端

 

 

开发接口

使用的 Eggjs 进行开发

async chatgpt() {
    const { text, model, conversationId, parentMessageId } =
      this.ctx.request.body;
    const { ctx, app } = this;
    const { user } = ctx;
    const { ChatGPTClient } = await import('@waylaidwanderer/chatgpt-api');

    const clientOptions = {
      // (Optional) Support for a reverse proxy for the completions endpoint (private API server).
      // Warning: This will expose your `openaiApiKey` to a third-party. Consider the risks before using this.
      // reverseProxyUrl: 'https://chatgpt.hato.ai/completions',
      // (Optional) Parameters as described in https://platform.openai.com/docs/api-reference/completions
      modelOptions: {
        // The model is set to text-chat-davinci-002-20221122 by default, but you can override
        // it and any other parameters here
        model: model || 'text-davinci-002', // text-davinci-003(生成更复杂和多样化的完成) text-curie-001(可能不太准确或)
      },
      // (Optional) Set custom instructions instead of "You are ChatGPT...".
      promptPrefix: '你好，我是智能助手',
      // (Optional) Set a custom name for the user
      // userLabel: 'User',
      // (Optional) Set a custom name for ChatGPT
      chatGptLabel: '智能助手',
      // (Optional) Set to true to enable `console.debug()` logging
      debug: false,
    };

    const cacheOptions = {
      // Options for the Keyv cache, see https://www.npmjs.com/package/keyv
      // This is used for storing conversations, and supports additional drivers (conversations are stored in memory by default)
      // For example, to use a JSON file (`npm i keyv-file`) as a database:
      // store: process.env.STORAGE_FILE_PATH || './cache.json',
    };

    const chatGptClient = new ChatGPTClient(
      process.env.OPENAI_API_KEY,
      clientOptions,
      cacheOptions,
    );
    const res = await chatGptClient.sendMessage(text, {
      conversationId,
      parentMessageId,
      // onProgress: (token) => console.log(token),
    });

    console.log('A:', text, 'Q:', res.response);
    this.success({
      data: {
        text: res.response,
        parentMessageId: res.messageId,
        conversationId: res.conversationId,
      },
    });

  }

 

下面的是参考的资料：

 

Nodejs 能力

官方对node 的支持

https://platform.openai.com/docs/api-reference/introduction

 

chatgpt-api：

https://github.com/transitive-bullshit/chatgpt-api

使用方式

node >=18,或者 安装 fetch polyfill， 例如：isomorphic-fetch

npm install chatgpt

import { ChatGPTAPI } from 'chatgpt'


const api = new ChatGPTAPI({
 process.env.OPENAI_API_KEY
})

const arg = process.argv.splice(2)[0]

console.log('输入的内容是：',arg);

const res = await api.sendMessage(arg)

console.log('ChatGPT 的答案是：',res.text)

node-chatgpt-api

https://github.com/waylaidwanderer/node-chatgpt-api

1、安装

Follow the same setup instructions for the API server, creating settings.js

npm i @waylaidwanderer/chatgpt-api

// 全局安装执行
chatgpt-api

// 本地安装执行
npm run cli

　　

添加 settings.js

export default {
  // Your OpenAI API key (for `ChatGPTClient`)
  openaiApiKey: process.env.OPENAI_API_KEY || '',
  chatGptClient: {
      // (Optional) Parameters as described in https://platform.openai.com/docs/api-reference/completions
      modelOptions: {
          // The model is set to text-chat-davinci-002-20221122 by default, but you can override
          // it and any other parameters here
          model: 'text-davinci-003',
      },
      // (Optional) Set custom instructions instead of "You are ChatGPT...".
      // promptPrefix: 'You are Bob, a cowboy in Western times...',
      // (Optional) Set a custom name for the user
      // userLabel: 'User',
      // (Optional) Set a custom name for ChatGPT
      // chatGptLabel: 'ChatGPT',
      // (Optional) Set to true to enable `console.debug()` logging
      debug: false,
  },
  // Options for the Keyv cache, see https://www.npmjs.com/package/keyv.
  // This is used for storing conversations, and supports additional drivers (conversations are stored in memory by default).
  // Does not apply when using `BingAIClient`.
  cacheOptions: {},
  // Options for the Bing client
  bingAiClient: {
      // The "_U" cookie value from bing.com
      userToken: '',
      // (Optional) Set to true to enable `console.debug()` logging
      debug: false,
  },
  // Options for the API server
  apiOptions: {
      port: process.env.API_PORT || 3000,
      host: process.env.API_HOST || 'localhost',
      // (Optional) Set to true to enable `console.debug()` logging
      debug: false,
      // (Optional) Set to "bing" to use `BingAIClient` instead of `ChatGPTClient`.
      // clientToUse: 'bing',
  },
  // If set, `ChatGPTClient` will use `keyv-file` to store conversations to this JSON file instead of in memory.
  // However, `cacheOptions.store` will override this if set
  storageFilePath: process.env.STORAGE_FILE_PATH || './cache.json',
};

　

如果觉得文章不错,可以给小编发个红包给予鼓励.