零基础学AI大模型SpringAI教程+Springboot3.X+多案例实战：2026年Java开发者的AI实战终局指南

xml<!-- BOM统一版本管理 -->
<dependencyManagement>
    <dependencies>
        <dependency>
            <groupId>org.springframework.ai</groupId>
            <artifactId>spring-ai-bom</artifactId>
            <version>1.1.4</version>
            <type>pom</type>
            <scope>import</scope>
        </dependency>
    </dependencies>
</dependencyManagement>

<dependencies>
    <dependency>
        <groupId>org.springframework.boot</groupId>
        <artifactId>spring-boot-starter-web</artifactId>
    </dependency>
    <!-- 核心AI依赖 -->
    <dependency>
        <groupId>org.springframework.ai</groupId>
        <artifactId>spring-ai-openai-spring-boot-starter</artifactId>
    </dependency>
</dependencies>

yamlspring:
  ai:
    openai:
      api-key: ${OPENAI_API_KEY}  # 生产环境用环境变量注入！
      base-url: https://api.deepseek.com  # 切换模型只改这一行
      chat:
        options:
          model: deepseek-chat        # deepseek-chat / gpt-4o / claude-3-5-sonnet
          temperature: 0.7
          max-tokens: 1024
          timeout: 30000

java@RestController
public class AIController {
    
    private final ChatClient chatClient; // 注入即用，自动配置
    
    public AIController(ChatClient.Builder builder) {
        this.chatClient = builder.build();
    }
    
    @GetMapping("/ai/chat")
    public String chat(@RequestParam String message) {
        return chatClient.prompt()
            .user(message)
            .call()
            .content(); // 一行搞定
    }
}

javaString reply = chatClient.prompt("北京今天天气怎么样？")
    .call()
    .content();

javarecord WeatherResponse(String city, int temperature, String condition) {}

WeatherResponse weather = chatClient.prompt()
    .user("北京今天天气怎么样？")
    .call()
    .entity(WeatherResponse.class); // 直接返回Java对象！

System.out.println(weather.city());       // 北京
System.out.println(weather.temperature()); // 25

java@Bean
public VectorStore vectorStore(JdbcTemplate jdbcTemplate, EmbeddingModel embeddingModel) {
    return new PgVectorStore(jdbcTemplate, embeddingModel);
}

@Bean
public ChatClient ragChatClient(ChatClient.Builder builder, VectorStore vectorStore) {
    return builder
        .defaultSystem("你是一个专业助手")
        .defaultAdvisors(new RetrieveAdvisor(vectorStore).asAii())
        .build();
}

用户提问 → 向量检索相关文档 → 拼接Prompt → AI生成回答
         ↑                                        ↓
    PgVector/Milvus/Redis                    结构化输出

java@Tool(description = "查询商品库存")
public int getProductStock(String productId) {
    return productRepository.findById(productId)
        .map(Product::getStock)
        .orElse(0);
}

ChatResponse response = chatClient.prompt()
    .user("帮我查下SKU-12345还有多少库存？")
    .tools(new ToolCallbackProvider<>(this))
    .call()
    .chatResponse();

yamlspring:
  ai:
    openai:
      api-key: ${API_KEY}
      base-url: https://api.147api.com/v1  # 只改这一行！
      chat:
        options:
          model: gpt-4o  # 切换deepseek-v3也只改这一行