← 返回首页 ❓ 面试题库
📑 本篇章节导航 (共9章,点击直达)
一、SSE基础原理(1-6)二、Java SSE实现(7-14)三、大模型流式响应(15-22)四、前端对接(23-28)五、背压与流量控制(29-33)六、生产环境实战(34-40)七、高级场景(41-45)八、WebSocket vs SSE深度对比(46-48)九、面试高频总结(49-50)

Q56 - SSE流式输出与大模型流式响应

共50道题 | 难度分布:★★★★☆平均 | 20K+ AI应用岗位流式输出必考

一、SSE基础原理(1-6)

SSE(Server-Sent Events)协议定义?

★★★★★


data: {"content": "你好"}

data: {"content": ",我"}

data: {"content": "是AI"}

data: [DONE]

SSE vs WebSocket vs 长轮询对比?

★★★★★

SSE事件格式详解?

★★★★


id: 1
event: token
data: {"text": "你"}

id: 2
event: token
data: {"text": "好"}

SSE浏览器兼容性?

★★★

SSE自动重连机制?

★★★★

SSE连接生命周期管理?

★★★★

二、Java SSE实现(7-14)

Spring SseEmitter使用?

★★★★★


@GetMapping("/chat/stream")
public SseEmitter streamChat(@RequestParam String message) {
    SseEmitter emitter = new SseEmitter(300_000L); // 5分钟超时
    executor.submit(() -> {
        try {
            chatService.streamChat(message, token -> {
                emitter.send(SseEmitter.event()
                    .data("{\"token\":\"" + token + "\"}")
                    .id(String.valueOf(tokenCounter++)));
            });
            emitter.send(SseEmitter.event().data("[DONE]"));
            emitter.complete();
        } catch (Exception e) {
            emitter.completeWithError(e);
        }
    });
    return emitter;
}

Spring WebFlux Flux SSE响应式实现?

★★★★★


@GetMapping(value = "/chat/stream", produces = MediaType.TEXT_EVENT_STREAM_VALUE)
public Flux<ServerSentEvent<String>> streamChat(@RequestParam String message) {
    return chatService.streamChat(message)
        .map(token -> ServerSentEvent.<String>builder()
            .data(token)
            .build())
        .concatWith(Flux.just(
            ServerSentEvent.<String>builder().data("[DONE]").build()
        ));
}

SseEmitter vs WebFlux SSE选型?

★★★★

SSE连接管理与并发控制?

★★★★

SSE中文编码问题?

★★★

SSE跨域CORS配置?

★★★★


http.authorizeHttpRequests(auth -> auth
    .requestMatchers("/chat/stream").permitAll()
);

SSE Nginx反向代理配置?

★★★★★


location /chat/stream {
    proxy_pass http://backend;
    proxy_http_version 1.1;
    proxy_set_header Connection '';
    proxy_buffering off;
    proxy_cache off;
    proxy_read_timeout 300s;
}

SSE负载均衡挑战?

★★★★

三、大模型流式响应(15-22)

LLM流式输出原理?

★★★★★

OpenAI Streaming API?

★★★★★


data: {"id":"chatcmpl-xxx","choices":[{"delta":{"content":"你"},"index":0}]}
data: {"id":"chatcmpl-xxx","choices":[{"delta":{"content":"好"},"index":0}]}
data: [DONE]

SSE格式解析大模型响应?

★★★★


let fullText = '';
eventSource.onmessage = (event) => {
    if (event.data === '[DONE]') { eventSource.close(); return; }
    const chunk = JSON.parse(event.data);
    const token = chunk.choices[0]?.delta?.content || '';
    fullText += token;
    updateUI(fullText);
};

Spring AI流式调用?

★★★★★


Flux<ChatResponse> stream = chatClient.prompt()
    .user("解释Java虚拟线程")
    .stream()
    .chatResponse();

stream.subscribe(response -> {
    String token = response.getResult().getOutput().getText();
    // 发送SSE事件
    emitter.send(SseEmitter.event().data(token));
});

ChatClient流式响应集成?

★★★★


@GetMapping(value = "/chat", produces = MediaType.TEXT_EVENT_STREAM_VALUE)
public Flux<ServerSentEvent<String>> chat(@RequestParam String message) {
    return chatClient.prompt()
        .user(message)
        .stream()
        .chatResponse()
        .map(resp -> {
            String content = resp.getResult().getOutput().getText();
            return ServerSentEvent.<String>builder().data(content).build();
        })
        .concatWithValues(
            ServerSentEvent.<String>builder().data("[DONE]").build()
        );
}

流式响应的Token计量与成本控制?

★★★★

流式中断恢复与错误处理?

★★★★

多模型流式适配?

★★★★

四、前端对接(23-28)

EventSource API使用与限制?

★★★★


const source = new EventSource('/chat/stream?message=hello');
source.onmessage = (event) => { console.log(event.data); };
source.onerror = () => { source.close(); };

fetch + ReadableStream实现POST SSE?

★★★★★


async function streamChat(message) {
    const response = await fetch('/chat/stream', {
        method: 'POST',
        headers: {
            'Content-Type': 'application/json',
            'Authorization': 'Bearer ' + token
        },
        body: JSON.stringify({ message })
    });
    const reader = response.body.getReader();
    const decoder = new TextDecoder();
    let buffer = '';
    while (true) {
        const { done, value } = await reader.read();
        if (done) break;
        buffer += decoder.decode(value, { stream: true });
        const lines = buffer.split('\n\n');
        buffer = lines.pop();
        for (const line of lines) {
            const data = line.replace(/^data: /, '');
            if (data === '[DONE]') return;
            const chunk = JSON.parse(data);
            appendToken(chunk.choices[0].delta.content);
        }
    }
}

流式Markdown渲染?

★★★★


let fullText = '';
let renderTimer = null;
function appendToken(token) {
    fullText += token;
    clearTimeout(renderTimer);
    renderTimer = setTimeout(() => {
        document.getElementById('output').innerHTML = marked.parse(fullText);
    }, 50);
}

流式代码高亮?

★★★

流式输出打字机效果实现?

★★★★


const tokenQueue = [];
let isTyping = false;
function enqueueToken(token) {
    tokenQueue.push(...token.split(''));
    if (!isTyping) typeNext();
}
function typeNext() {
    if (tokenQueue.length === 0) { isTyping = false; return; }
    isTyping = true;
    appendChar(tokenQueue.shift());
    setTimeout(typeNext, 30);
}

前端中断流式请求?

★★★★


const controller = new AbortController();
fetch('/chat/stream', { signal: controller.signal, ... });
// 用户点击停止按钮
controller.abort();

五、背压与流量控制(29-33)

Reactive Streams背压机制?

★★★★

Flux背压策略选择?

★★★


chatService.streamChat(message)
    .onBackpressureLatest()
    .subscribe(token -> emitter.send(token));

LLM生成速度 vs 前端消费速度不匹配处理?

★★★★

流式场景下的内存管理?

★★★

大并发流式连接的资源控制?

★★★★

六、生产环境实战(34-40)

Spring AI + SSE完整实现示例?

★★★★★


@RestController
@RequestMapping("/api/chat")
public class ChatController {
    private final ChatClient chatClient;

    @GetMapping(value = "/stream", produces = MediaType.TEXT_EVENT_STREAM_VALUE)
    public Flux<ServerSentEvent<String>> streamChat(
            @RequestParam String message,
            @RequestParam(defaultValue = "default") String model) {
        return chatClient.prompt()
            .user(message)
            .stream()
            .chatResponse()
            .map(resp -> {
                String content = resp.getResult().getOutput().getText();
                return ServerSentEvent.<String>builder()
                    .data(Map.of("token", content).toString())
                    .build();
            })
            .concatWithValues(
                ServerSentEvent.<String>builder()
                    .event("done").data("").build()
            )
            .onErrorResume(e -> Flux.just(
                ServerSentEvent.<String>builder()
                    .event("error").data(e.getMessage()).build()
            ));
    }
}

流式对话历史持久化?

★★★★

流式输出的监控?

★★★★

流式场景的限流策略?

★★★★

长连接资源泄漏排查?

★★★★

SSE在K8s环境中的超时配置?

★★★★

流式输出的端到端链路追踪?

★★★★

七、高级场景(41-45)

多轮对话的流式上下文管理?

★★★★

Agent多步推理的流式输出编排?

★★★★


event: thinking\ndata: {"step":1,"content":"需要查询数据库..."}
event: tool_call\ndata: {"tool":"sql_query","args":"SELECT ..."}
event: tool_result\ndata: {"result":"[...]"}
event: answer\ndata: {"token":"根据查询结果..."}

Function Calling结果与流式文本混合输出?

★★★★

多模型并行生成的流式聚合?

★★★

流式RAG管道?

★★★★

八、WebSocket vs SSE深度对比(46-48)

协议层对比?

★★★★

AI聊天场景选型:为什么多数选SSE?

★★★★★

全双工AI交互场景?

★★★

九、面试高频总结(49-50)

SSE流式输出面试高频8连问?

★★★★★

设计一个AI聊天系统的流式架构?

★★★★★