OpenAI ChatGPT (GPT-3.5) API 错误 404：“请求失败，状态代码 404”

Question

我正在开发一个 ChatGPT-App，使用 React 和 Axios 向 OpenAI 的 GPT-3.5 API 发出 API 请求。但是，我在尝试发出请求时遇到 404 错误。我希望有人可以帮助我确定问题并指导我如何解决它。以下是 App.js 和 index.js 代码和错误消息：

前端

应用程序.js

function App() {
  const [messages, setMessages] = useState([]);
  const [input, setInput] = useState("");

  const sendMessage = async () => {
    if (input.trim() === "") return;
  
    const userInput = input; // Store user input in a temporary variable
    setMessages([...messages, { type: "user", text: userInput }]);
    setInput("");
  
    try {
      const response = await axios.post("http://localhost:5000/api/chat", { text: userInput });
      const gptResponse = response.data.message;
      setMessages((prevMessages) => [
        ...prevMessages,
        { type: "chatgpt", text: gptResponse },
      ]);
    } catch (error) {
      console.error("Error:", error);
    }
  };

后端

索引.js

const express = require("express");
const axios = require("axios");
const cors = require("cors");

const app = express();
app.use(express.json());
app.use(cors());

const openai_api_key = "MYOPENAI-APIKEY";
const headers = {
  "Content-Type": "application/json",
  "Authorization": `Bearer ${openai_api_key}`,
};

app.post("/api/chat", async (req, res) => {
  try {
    const input = req.body.text;
    const response = await axios.post(
      "https://api.openai.com/v1/engines/davinci-codex/completions",
      {
        prompt: `User: ${input}\nChatGPT: `,
        max_tokens: 150,
        temperature: 0.7,
        n: 1,
      },
      { headers }
    );

    const gptResponse = response.data.choices[0].text.trim();
    res.json({ message: gptResponse });
  } catch (error) {
    console.error("Error:", error);
    res.status(500).json({ error: "An error occurred while processing your request." });
  }
});

const PORT = process.env.PORT || 5000;
app.listen(PORT, () => {
  console.log(`Server started on port ${PORT}`);
});

错误信息： AxiosError: Request failed with status code 404

我已经验证 API 密钥是正确的，URL 也应该是正确的。谁能指出导致此错误的正确方向？任何帮助将不胜感激。谢谢你！

Answer 1

聊天完成 API（即 GPT-3.5 API）和完成 API（即 GPT-3 API）之间存在三个主要区别。

\n

如果您使用 OpenAI 库（NodeJS或Python）

\n

注意：OpenAI NodeJS SDK于2023年8月16日发布v4，是对SDK的完全重写。下面的代码根据您当前拥有的版本而有所不同。请参阅迁移指南。v3v4

\n

差异如下：

\n

\n
1. 功能\n
   \n
   • 完成 API:\n
     \n
     • OpenAI NodeJS SDK v3：openai.createCompletion
     \n
     • OpenAI NodeJS SDK v4：openai.completions.create
     \n
     \n
   \n
   • 聊天完成 API:\n
     \n
     • OpenAI NodeJS SDK v3：openai.createChatCompletion
     \n
     • OpenAI NodeJS SDK v4：openai.chat.completions.create
     \n
     \n
   \n
   \n
\n
2. 参数prompt(Completions API) 替换为messages参数 (Chat Completions API)
\n
3. 响应访问\n
   \n
   • 完成 API:\n
     \n
     • OpenAI NodeJS SDK v3：return response.data.choices[0].text;
     \n
     • OpenAI NodeJS SDK v4：return response.choices[0].text;
     \n
     \n
   \n
   • 聊天完成 API:\n
     \n
     • OpenAI NodeJS SDK v3：return response.data.choices[0].message.content;
     \n
     • OpenAI NodeJS SDK v4：return response.choices[0].message.content;
     \n
     \n
   \n
   \n
\n

\n

工作示例（NodeJS）

\n

\xe2\x80\xa2 如果您有 OpenAI NodeJS SDK v3：

\n

const { Configuration, OpenAIApi } = require(\'openai\');\n\nconst configuration = new Configuration({\n  apiKey: \'sk-xxxxxxxxxxxxxxxxxxxx\',\n});\n\nconst openai = new OpenAIApi(configuration);\n\nasync function getChatGptResponse(request) {\n  try {\n    const response = await openai.createChatCompletion({\n      model: \'gpt-3.5-turbo\',\n      messages: [{ role: \'user\', content: \'Hello!\' }],\n    });\n\n    console.log(response.data.choices[0].message.content);\n    return response.data.choices[0].message.content;\n  } catch (err) {\n    console.log(\'Error: \' + err);\n    return err;\n  }\n}\n\ngetChatGptResponse();\n

\n

\xe2\x80\xa2 如果您有 OpenAI NodeJS SDK v4：

\n

import OpenAI from \'openai\';\n\nconst openai = new OpenAI({\n  apiKey: \'sk-xxxxxxxxxxxxxxxxxxxx\',\n});\n\nasync function getChatGptResponse(request) {\n  try {\n    const response = await openai.chat.completions.create({\n      model: \'gpt-3.5-turbo\',\n      messages: [{ role: \'user\', content: \'Hello!\' }],\n    });\n\n    console.log(response.choices[0].message.content);\n    return response.choices[0].message.content;\n  } catch (err) {\n    console.log(\'Error: \' + err);\n    return err;\n  }\n}\n\ngetChatGptResponse();\n

\n
\n

如果您没有使用 OpenAI 库

\n

差异如下：

\n

\n
1. API 终结点\n
   \n
   • 完成 API：https://api.openai.com/v1/completions
   \n
   • 聊天完成 API：https://api.openai.com/v1/chat/completions
   \n
   \n
\n
2. 参数prompt(Completions API) 替换为messages参数 (Chat Completions API)
\n
3. 响应访问\n
   \n
   • 完成 API:\n
     \n
     • OpenAI NodeJS SDK v3：
       const chatGptResponse = response.data.choices[0].text;
     \n
     • OpenAI NodeJS SDK v4：
       const chatGptResponse = response.choices[0].text;
     \n
     \n
   \n
   • 聊天完成 API:\n
     \n
     • OpenAI NodeJS SDK v3：
       const chatGptResponse = response.data.choices[0].message.content;
     \n
     • OpenAI NodeJS SDK v4：
       const chatGptResponse = response.choices[0].message.content;
     \n
     \n
   \n
   \n
\n

\n

工作示例

\n

\xe2\x80\xa2 如果您有 OpenAI NodeJS SDK v3：

\n

const express = require(\'express\');\nconst axios = require(\'axios\');\nconst cors = require(\'cors\');\n\nconst app = express();\napp.use(express.json());\napp.use(cors());\n\nconst openaiApiKey = \'sk-xxxxxxxxxxxxxxxxxxxx\';\n\nconst headers = {\n  \'Content-Type\': \'application/json\',\n  \'Authorization\': `Bearer ${openaiApiKey}`,\n};\n\napp.post(\'/api/chat\', async (req, res) => {\n  try {\n    const input = req.body.text;\n\n    const response = await axios.post(\n      \'https://api.openai.com/v1/chat/completions\',\n      {\n        model: \'gpt-3.5-turbo\',\n        messages: [{role: \'user\', content: `${input}`}],\n      },\n      { headers }\n    );\n\n    const chatGptResponse = response.data.choices[0].message.content;\n\n    console.log(chatGptResponse);\n    res.status(200).json({ message: chatGptResponse });\n  } catch (err) {\n    console.log(\'Error: \' + err);\n    res.status(500).json({ error: \'An error occurred while processing your request\' });\n  }\n});\n\nconst PORT = process.env.PORT || 5000;\napp.listen(PORT, () => {\n  console.log(`Server started on port ${PORT}`);\n});\n

\n

\xe2\x80\xa2 如果您有 OpenAI NodeJS SDK v4：

\n

const express = require(\'express\');\nconst axios = require(\'axios\');\nconst cors = require(\'cors\');\n\nconst app = express();\napp.use(express.json());\napp.use(cors());\n\nconst openaiApiKey = \'sk-xxxxxxxxxxxxxxxxxxxx\';\n\nconst headers = {\n  \'Content-Type\': \'application/json\',\n  \'Authorization\': `Bearer ${openaiApiKey}`,\n};\n\napp.post(\'/api/chat\', async (req, res) => {\n  try {\n    const input = req.body.text;\n\n    const response = await axios.post(\n      \'https://api.openai.com/v1/chat/completions\',\n      {\n        model: \'gpt-3.5-turbo\',\n        messages: [{role: \'user\', content: `${input}`}],\n      },\n      { headers }\n    );\n\n    const chatGptResponse = response.choices[0].message.content;\n\n    console.log(chatGptResponse);\n    res.status(200).json({ message: chatGptResponse });\n  } catch (err) {\n    console.log(\'Error: \' + err);\n    res.status(500).json({ error: \'An error occurred while processing your request\' });\n  }\n});\n\nconst PORT = process.env.PORT || 5000;\napp.listen(PORT, () => {\n  console.log(`Server started on port ${PORT}`);\n});\n

\n