NextJS 13 API接口500错误：TypeError读取headers属性失败

1. 修正配置变量拼写错误 #

代码里的configutation是拼写错误，正确应为configuration。错误的变量名会导致OpenAI客户端初始化失败，后续调用API时因缺少有效配置，出现headers未定义的报错。

修改后的配置代码：

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

const openai = new OpenAIApi(configuration);

2. 替换GPT-4的API调用方法 #

GPT-4不支持createCompletion接口（该接口仅适用于GPT-3系列模型），需改用createChatCompletion接口，同时调整参数格式为聊天消息数组：

修改try块内的代码：

const aiResult = await openai.createChatCompletion({
  model: "gpt-4",
  messages: [{ role: "user", content: prompt }],
  temperature: 0.9,
  max_tokens: 8192,
});
const aiText = aiResult.data.choices[0].message?.content?.trim() || "Something went wrong!";

3. 完善错误处理逻辑 #

原代码的catch块未返回响应，导致请求无返回值触发500错误，需在catch中返回明确的错误响应：

修改后的catch块：

catch (error: any) {
  console.error(error);
  return NextResponse.json(
    { error: error.message || "Failed to generate response" },
    { status: 500 }
  );
}

4. 验证环境变量 #

确保.env.local文件中已正确设置OPENAI_API_KEY，并且重启开发服务器让环境变量生效：

OPENAI_API_KEY=your-openai-api-key-here

完整修正后的代码 #

import { NextResponse } from "next/server";
import { Configuration, OpenAIApi } from "openai";

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

const openai = new OpenAIApi(configuration);

export async function POST(request: Request) {
  const body = await request.json();
  const { prompt } = body;

  if (!prompt || prompt === "") {
    return new Response("Please send your prompt", { status: 400 });
  }

  try {
    const aiResult = await openai.createChatCompletion({
      model: "gpt-4",
      messages: [{ role: "user", content: prompt }],
      temperature: 0.9,
      max_tokens: 8192,
    });
    const aiText = aiResult.data.choices[0].message?.content?.trim() || "Something went wrong!";

    return NextResponse.json({ text: aiText });
  } catch (error: any) {
    console.error(error);
    return NextResponse.json(
      { error: error.message || "Failed to generate response" },
      { status: 500 }
    );
  }
}

内容的提问来源于stack exchange，提问作者Chris