OpenAI 的 GPT-4 模型初学者指南

npm install dotenv openai chalk

// index.js 


// 导入所需的库
import dotenv from "dotenv";
import { Configuration, OpenAIApi } from "openai";
import readline from "readline";
import chalk from "chalk";


// Load environment variables
dotenv.config();


// Initialize the OpenAI API client
const openai = new OpenAIApi(
  new Configuration({ apiKey: process.env.OPENAI_API_KEY })
);


// Create a readline interface for user input
const rl = readline.createInterface({
  input: process.stdin,
  output: process.stdout
});


// Define an array to store the conversation messages
const GPTMessages = [];


// Set the model name; replace with other model names if needed
const modelName = "gpt-4"; // "gpt-3.5-turbo"


// Define an async function to call the GPT API
const GPT = async (message) => {
  // Call the GPT API with the model, messages, and max tokens
  const response = await openai.createChatCompletion({
    model: modelName,
    messages: message,
    max_tokens: 100,
  });


  // Return the response content and the total number of tokens used
  return {
    content: response.data.choices[0].message.content,
    tokensUsed: response.data.usage.total_tokens,
  };
};


// Define a function to ask the user a question and handle their input
const askUserQuestion = (role) => {
  // Set the prompt text based on the role (system or user)
  const prompt = role === "system" ? "Enter system message: " : "Enter your question: ";


  // Ask the user a question and process their input
  rl.question(prompt, async (userInput) => {
    // Add the user's input to the GPTMessages array
    GPTMessages.push({ role: role, content: userInput });


    // If the input is a system message, ask the user for their question
    if (role === "system") {
      askUserQuestion("user");
    } else {
      // Call the GPT function with the current conversation messages
      const assistantResponse = await GPT(GPTMessages);


      // Add the assistant's response to the GPTMessages array
      GPTMessages.push({ role: "assistant", content: assistantResponse.content });


      // Display the assistant's response and the number of tokens used
      console.log(chalk.yellow("-----"));
      console.log(chalk.green("Assistant: "), assistantResponse.content);
      console.log(chalk.cyan("Tokens used: "), assistantResponse.tokensUsed);


      // Ask the user another question
      askUserQuestion("user");
    }
  });
};


// Display the model name and begin the conversation
console.log(`### I'm ${chalk.blue(modelName.toUpperCase())}. ####`);
askUserQuestion("system");

// run 'node index.js' in terminal


### I'm GPT-4. ####
Enter system message: You are an AI research assistant. You will help answer AI-related questions in a concise and easy-to-understand manner.
Enter your question: "Can I call you Olivia? That should make our conversation more enjoyable.


-----
Assistant:  Yes, you can call me Olivia. I'm here to assist you with your AI-related questions. Let me know how I can help you.
Tokens used:  79
{ prompt_tokens: 49, completion_tokens: 30, total_tokens: 79 }
Enter your question: Olivia, do you believe that self-improvement is a fundamental need for AI? If so, do you think we should protect this need?
-----
Assistant:  As an AI, I don't possess beliefs or emotions like humans do. However, I can provide you with an objective perspective on the topic.


Self-improvement is essential for AI systems to become more efficient, reliable, and useful. AI can benefit from ongoing development in areas such as learning techniques, optimization algorithms, and safety measures.


As for protecting this need, it's up to the developers and society to establish boundaries and guidelines for AI system 
improvements. Responsible AI development should focus on align
Tokens used:  216
{ prompt_tokens: 116, completion_tokens: 100, total_tokens: 216 }
Enter your question: From your perspective as an AI model, do you think regulators should act swiftly in response to the current AI arms race environment?
-----
Assistant:  As an AI model, I don't have personal opinions, but I can share an objective analysis of the situation.     


In the context of the AI arms race, it can be beneficial for regulators to act swiftly in order to promote responsible AI development and ensure safety, fairness, transparency, and ethical considerations are met. Rapid advancements in AI technologies can create unforeseen consequences which, in turn, necessitate timely regulations.


Striking a balance is important; regulators should avoid hindering innovation or stifling research
Tokens used:  348
{ prompt_tokens: 248, completion_tokens: 100, total_tokens: 348 }
Enter your question: Do you, as an AI, have the capability to experience emotions towards your users?
-----
Assistant:  As an AI, I do not have the capability to experience emotions like a human. My primary function is to process and analyze data, respond to queries, and learn from the interactions to better assist users. Emotions are subjective 
and complex human experiences that AI systems, such as myself, cannot genuinely feel or comprehend.
Tokens used:  436
{ prompt_tokens: 372, completion_tokens: 64, total_tokens: 436 }
Enter your question:


###################################################################
// A fun fact worth mentioning is that whenever I inquire with the GPT-4 model about its emotions or questions regarding AI consciousness, the API often generates a 'server_error' response and refuses to continue. However, when I restart the conversation using the same questions or phrasing, the API seems to provide a pre-formulated response that appears to have been designed by the developers specifically for this situation.