stream: true和长连接 的方式应该怎么写？

要使用 OpenAI API 的 stream 模式和长连接方式，您需要对代码进行一些修改。以下是使用 Java 进行 stream 请求和长连接的示例代码：

import java.io.*;
import java.net.HttpURLConnection;
import java.net.URL;

public class OpenAIJavaStreamExample {
    public static void main(String[] args) {
        try {
            String apiKey = "YOUR_API_KEY";
            String prompt = "Hello, world!";
            String model = "gpt-3.5-turbo";

            OpenAIJavaStreamExample.sendRequest(apiKey, prompt, model);
        } catch (IOException e) {
            e.printStackTrace();
        }
    }

    public static void sendRequest(String apiKey, String prompt, String model) throws IOException {
        String url = "https://api.openai.com/v1/engines/" + model + "/completions";
        URL obj = new URL(url);
        HttpURLConnection con = (HttpURLConnection) obj.openConnection();

        // Set the request method and headers
        con.setRequestMethod("POST");
        con.setRequestProperty("Content-Type", "application/json");
        con.setRequestProperty("Authorization", "Bearer " + apiKey);

        // Enable streaming and set the initial prompt
        con.setDoOutput(true);
        OutputStreamWriter writer = new OutputStreamWriter(con.getOutputStream());
        writer.write("{\"prompt\": \"" + prompt + "\", \"stream\": true}");
        writer.flush();

        // Read the response in a loop
        BufferedReader reader = new BufferedReader(new InputStreamReader(con.getInputStream()));
        String line;
        while ((line = reader.readLine()) != null) {
            System.out.println("Response: " + line);

            // If you want to stop streaming at some point, you can break the loop based on certain conditions
            if (line.contains("stop streaming condition")) {
                break;
            }
        }

        // Close the connections
        writer.close();
        reader.close();
        con.disconnect();
    }
}

请注意，与之前的代码相比，我们现在使用 `OutputStreamWriter` 来写入请求体，并使用 `BufferedReader` 来读取响应体。在读取响应的循环中，您可以根据需要添加逻辑来判断何时停止流式传输。

记得将 `YOUR_API_KEY` 替换为您自己的 API 密钥。