使用Deepseek4j接入阿里云百煉DeepSeek R1
Spring有Spring AI這個項目，不過這里找到了另一個項目Deepseek4j，也是個Spring starter，提供了一個基礎(chǔ)框架用來承接各種ds大模型，可以對接包括本地部署的Ollama r1，騰訊、硅基流動、阿里、火山引擎這些版本的R1模型或V3模型，比較方便。以下是一個簡單實踐。
前端ai.html --> 后端SpringBoot + Deepseek4j --> 阿里云大模型服務(wù)平臺百煉上的Deepseek R1滿血版
實踐過程
- 先去阿里云大模型服務(wù)平臺“百煉”上進(jìn)行注冊，獲得API_KEY
- 本地搭建SpringBoot + Deepseek4j，通過API_KEY去調(diào)用百煉大模型服務(wù)。
pom.xml 增加如下依賴，其他依賴略，SpringMVC項目或WebFlux都可以。
<dependency>
<groupId>io.github.pig-mesh.ai</groupId>
<artifactId>deepseek-spring-boot-starter</artifactId>
<version>1.4.2</version>
</dependency>
controller
import io.github.pigmesh.ai.deepseek.core.DeepSeekClient;
import io.github.pigmesh.ai.deepseek.core.chat.ChatCompletionResponse;
import lombok.extern.slf4j.Slf4j;
import org.springframework.beans.factory.annotation.Autowired;
import org.springframework.http.MediaType;
import org.springframework.web.bind.annotation.GetMapping;
import org.springframework.web.bind.annotation.RequestMapping;
import org.springframework.web.bind.annotation.RestController;
import reactor.core.publisher.Flux;
@Slf4j
@RestController
@RequestMapping("ai")
public class AiController {
@Autowired
private DeepSeekClient deepSeekClient;
@GetMapping(value = "/chat", produces = MediaType.TEXT_EVENT_STREAM_VALUE)
public Flux<ChatCompletionResponse> chat(String prompt) {
return deepSeekClient.chatFluxCompletion(prompt);
}
}
application.properties配置文件
deepseek.base-url=https://dashscope.aliyuncs.com/compatible-mode/v1
deepseek.model=deepseek-r1
deepseek.api-key=百煉上申請的API_KEY
deepseek.log-requests=true
deepseek.log-responses=true
deepseek.connect-timeout=10
deepseek.read-timeout=30
deepseek.call-timeout=60
- 簡單寫個測試問答api頁面ai.html
<!DOCTYPE html>
<html lang="zh-CN">
<head>
<meta charset="UTF-8">
<title>AI 問答測試頁面（優(yōu)化版）</title>
<style>
body {
font-family: Arial, sans-serif;
margin: 20px;
max-width: 800px;
}
textarea {
width: 100%;
height: 100px;
margin: 10px 0;
padding: 8px;
box-sizing: border-box;
}
.response-area {
border: 1px solid #ddd;
border-radius: 4px;
margin: 10px 0;
padding: 10px;
background-color: #f8f9fa;
}
#reasoning {
background-color: #fff;
max-height: 200px;
overflow-y: auto;
}
#answer {
white-space: pre-wrap;
min-height: 100px;
}
.toggle-header {
cursor: pointer;
color: #666;
padding: 5px;
background-color: #f0f0f0;
border-radius: 3px;
margin: 5px 0;
}
button {
padding: 10px 20px;
background-color: #007bff;
color: white;
border: none;
border-radius: 4px;
cursor: pointer;
}
button:hover {
background-color: #0056b3;
}
</style>
</head>
<body>
<h1>AI 問答 API 測試</h1>
<textarea id="prompt" placeholder="請輸入問題..."></textarea><br>
<button id="send">發(fā)送</button>
<h2>回答結(jié)果：</h2>
<div class="response-area" id="answer"></div>
<details>
<summary class="toggle-header">推理過程（點擊展開）</summary>
<div class="response-area" id="reasoning"></div>
</details>
<script>
let eventSource = null;
document.getElementById('send').addEventListener('click', function() {
const prompt = document.getElementById('prompt').value;
if (!prompt) {
alert("請輸入問題");
return;
}
// 關(guān)閉已有連接
if (eventSource) {
eventSource.close();
}
// 清空顯示區(qū)域
document.getElementById('answer').textContent = "";
document.getElementById('reasoning').textContent = "";
const url = `/ai/chat?prompt=${encodeURIComponent(prompt)}`;
eventSource = new EventSource(url);
eventSource.onmessage = (e) => {
try {
const data = JSON.parse(e.data);
const delta = data.choices[0].delta;
// 處理推理內(nèi)容
if (delta.reasoning_content !== undefined) {
const reasoningElement = document.getElementById('reasoning');
reasoningElement.textContent += delta.reasoning_content;
reasoningElement.scrollTop = reasoningElement.scrollHeight;
}
// 處理最終回答
if (delta.content !== undefined) {
const answerElement = document.getElementById('answer');
answerElement.textContent += delta.content;
answerElement.scrollTop = answerElement.scrollHeight;
}
} catch (err) {
console.error('數(shù)據(jù)解析錯誤:', err);
}
};
eventSource.onerror = (e) => {
console.error("SSE連接錯誤:", e);
if (eventSource) {
eventSource.close();
eventSource = null;
}
};
});
</script>
</body>
</html>
效果：
參考
前端如何與后端響應(yīng)式類型API交互
https://blog.csdn.net/waiter456/article/details/141114447
https://www.ruanyifeng.com/blog/2017/05/server-sent_events.html
Spring AI整合
https://javaai.pig4cloud.com/deepseek/bailian
http://www.rzrgm.cn/guoxiaoyu/p/18700826
通過阿里云百煉平臺調(diào)用DeepSeek-R1 滿血版 API
https://www.aliyun.com/solution/tech-solution/deepseek-r1-for-platforms
Spring AI 從Java視角下學(xué)習(xí)大模型的不錯的切入口
https://www.zhihu.com/column/c_1853261396491517952
浙公網(wǎng)安備 33010602011771號