Spring Boot 整合AI大模型实战：手把手带你接入De

前言

随着AI大模型的快速普及，越来越多的Java开发者希望将AI能力集成到自己的项目中。本文手把手带你用Spring Boot接入DeepSeek API，实现一个具备AI对话能力的后端服务。

一、环境准备

• JDK 17+
• Spring Boot 3.x
• Maven 3.8+
• DeepSeek API Key（到 platform.deepseek.com 免费申请）

二、添加依赖

<dependency>
    <groupId>org.springframework.boot</groupId>
    <artifactId>spring-boot-starter-web</artifactId>
</dependency>
<dependency>
    <groupId>org.springframework.boot</groupId>
    <artifactId>spring-boot-starter-webflux</artifactId>
</dependency>
<dependency>
    <groupId>com.fasterxml.jackson.core</groupId>
    <artifactId>jackson-databind</artifactId>
</dependency>

三、配置 application.yml

deepseek:
  api-key: sk-xxxxxxxxxxxxxxxx
  base-url: https://api.deepseek.com
  model: deepseek-chat
  max-tokens: 2048

四、创建配置类

@Configuration
@ConfigurationProperties(prefix = "deepseek")
@Data
public class DeepSeekConfig {
    private String apiKey;
    private String baseUrl;
    private String model;
    private Integer maxTokens;

    @Bean
    public WebClient deepSeekWebClient() {
        return WebClient.builder()
            .baseUrl(baseUrl)
            .defaultHeader("Authorization", "Bearer " + apiKey)
            .defaultHeader("Content-Type", "application/json")
            .build();
    }
}

五、定义请求/响应实体

// 请求体
@Data
public class ChatRequest {
    private String model;
    private List<Message> messages;
    @JsonProperty("max_tokens")
    private Integer maxTokens;
    private Boolean stream = false;

    @Data
    @AllArgsConstructor
    public static class Message {
        private String role;  // system / user / assistant
        private String content;
    }
}

// 响应体
@Data
public class ChatResponse {
    private String id;
    private List<Choice> choices;

    @Data
    public static class Choice {
        private Message message;
    }

    @Data
    public static class Message {
        private String role;
        private String content;
    }
}

六、实现Service层

@Service
@RequiredArgsConstructor
public class DeepSeekService {

    private final WebClient deepSeekWebClient;
    private final DeepSeekConfig config;

    public String chat(String userMessage) {
        ChatRequest request = new ChatRequest();
        request.setModel(config.getModel());
        request.setMaxTokens(config.getMaxTokens());
        request.setMessages(List.of(
            new ChatRequest.Message("system", "你是一个专业Java开发助手"),
            new ChatRequest.Message("user", userMessage)
        ));

        ChatResponse response = deepSeekWebClient
            .post()
            .uri("/v1/chat/completions")
            .bodyValue(request)
            .retrieve()
            .bodyToMono(ChatResponse.class)
            .block();

        return response.getChoices().get(0).getMessage().getContent();
    }
}

七、实现Controller层

@RestController
@RequestMapping("/api/ai")
@RequiredArgsConstructor
public class AiController {

    private final DeepSeekService deepSeekService;

    @PostMapping("/chat")
    public ResponseEntity<String> chat(@RequestBody Map<String, String> body) {
        String message = body.get("message");
        String reply = deepSeekService.chat(message);
        return ResponseEntity.ok(reply);
    }
}

八、测试

curl -X POST http://localhost:8080/api/ai/chat \
  -H "Content-Type: application/json" \
  -d '{"message": "帮我写一个Spring Boot分页查询的示例"}'

总结

通过以上步骤，我们完成了Spring Boot整合DeepSeek API的全流程。后续可以进一步扩展：

• 支持流式输出（SSE）
• 加入对话历史管理
• 集成Redis缓存常用回答
• 接入其他大模型（通义千问、文心一言等）

本文由AI辅助创作。