Node.js搭建OpenAI图像生成后端遇400错误，请求协助排查

我用Node.js搭建了基于OpenAI API的图像生成后端，核心功能是根据前端传入的提示词生成图像，但持续收到OpenAI返回的400错误，功能无法正常运行。已在.env文件中配置OPENAI_API_KEY和MongoDB_URL，无法定位问题根源。

相关代码及错误信息 #

Node.js后端代码 #

import express from 'express';
import * as dotenv from 'dotenv';
import { Configuration, OpenAIApi } from 'openai';

dotenv.config();

const router=express.Router();

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

const openai= new OpenAIApi(configuration);

router.route('/').get((req,res)=>{
    res.send('Hello everyone !!')
})

router.route('/').post(async(req,res)=>{
    try {
       // 来自前端的参数
        const {prompt}=req.body;

        const aiResponse=await openai.createImage({
            prompt,
            n:1,
            size:'1024x1024',
            response_format:'b64_json',
        });

        const image=aiResponse.data.data[0].b64_json;
        res.status(200).json({photo:image});
        
    } catch (error) {
        console.error(error);
        res.status(500).send(error?.response.data.error.message || 'Something went wrong..')
        
    }
})

export default router;

React前端请求代码 #

const [formFill,setFormFill]=useState({
    name:'',
    prompt:'',
    photo:''
})

const [imgGenerate,setImgGenerate]=useState(false);
const imgCreate= async ()=>{
    if (formFill.prompt) {
      try {
        setImgGenerate(true);
        const response = await fetch('http://localhost:5000/api/v1/dalleApi', {
          method: 'POST',
          headers: {
            'Content-Type': 'application/json',
          },
          body: JSON.stringify({
            prompt: formFill.prompt,
          }),
        });

        const data = await response.json();
        setFormFill({ ...formFill, photo: `data:image/jpeg;base64,${data.photo}` });
      } catch (err) {
        alert(err);
      } finally {
        setImgGenerate(false);
      }
    } else {
      alert('Please provide a proper prompt !');
    }
}

错误响应信息 #

Request failed with status code 400
    at createError (D:\Web dev Projects\ai_image_generation_app\backend\node_modules\axios\lib\core\createError.js:16:15)
    at settle (D:\Web dev Projects\ai_image_generation_app\backend\node_modules\axios\lib\core\settle.js:17:12)
    at IncomingMessage.handleStreamEnd (D:\Web dev Projects\ai_image_generation_app\backend\node_modules\axios\lib\adapters\http.js:322:11)
    at IncomingMessage.emit (node:events:525:35)
    at endReadableNT (node:internal/streams/readable:1359:12)
    at process.processTicksAndRejections (node:internal/process/task_queues:82:21) {
  config: {
    transitional: {
      silentJSONParsing: true,
      forcedJSONParsing: true,
      clarifyTimeoutError: false
    },
    adapter: [Function: httpAdapter],
    transformRequest: [ [Function: transformRequest] ],
    transformResponse: [ [Function: transformResponse] ],
    timeout: 0,
    xsrfCookieName: 'XSRF-TOKEN',
    xsrfHeaderName: 'X-XSRF-TOKEN',
    maxContentLength: -1,
    maxBodyLength: -1,
    validateStatus: [Function: validateStatus],
    headers: {
      Accept: 'application/json, text/plain, */*',
      'Content-Type': 'application/json',
      'User-Agent': 'OpenAI/NodeJS/3.3.0',
      Authorization: 'Bearer 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',
      'Content-Length': 55
    },
    method: 'post',
    data: '{"n":1,"size":"1024x1024","response_format":"b64_json"}',
    url: 'https://api.openai.com/v1/images/generations'
  },

排查方向及解决方法 #

从错误日志的data字段能看到，发给OpenAI的请求缺少prompt参数，这是400错误的核心原因，按以下步骤排查：

• 确保Express解析JSON请求体：在你的主服务文件（如server.js）中添加express.json()中间件，否则后端无法解析前端传来的JSON格式请求体，req.body.prompt会是undefined：

  app.use(express.json());
  

• 验证prompt参数是否正常接收：在后端POST接口中添加日志，确认是否获取到前端传来的prompt：

  console.log('Received prompt:', prompt);
  

• 检查API密钥权限：确认你的OpenAI API密钥有调用images/generations接口的权限，账户是否有可用余额，无访问限制。可以用Postman直接调用OpenAI API测试密钥有效性。
• 验证prompt合规性：OpenAI会拒绝违反内容政策的prompt，若prompt包含违规内容也会返回400错误，先用简单合规的prompt（如"a cute cat sitting on a windowsill"）测试。
• 更新OpenAI包版本：当前使用的openai包为3.3.0版本，尝试更新到最新稳定版，避免版本兼容性问题：

  npm update openai
  

内容的提问来源于stack exchange，提问作者Aarush 01