使用Spring AI调用AI模型

zhangj1125

已于 2025-03-14 09:56:42 修改

阅读量684

点赞数 3

文章标签： spring 人工智能 java

于 2025-03-05 20:46:51 首次发布

本文链接：https://blog.youkuaiyun.com/zhangj1125/article/details/146052296

版权

简介

Spring AI是Spring推出的用于快速集成AI功能。该项目从著名的Python项目（如LangChain和LlamaIndex）中汲取灵感，经过多个版本迭代，逐渐集成了OpenAI、Google、Amazon、Baidu等大语言模型平台。 Spring AI支持将模型数据结构化输出、RAG（Retrieval-Augmented Generation）、支持对接所有主要的向量数据库（如：Apache Cassanra、Redis、Elasticsearch、PostgreSQL等），允许模型请求客户端工具和函数，支持以下模型类型：

Chat Completion
Embedding
Text to Image
Audio Transcription
Text to Speech
Moderation

部分例子

添加依赖

Spring AI 1.0 M6之后的版本已经可以直接从中央仓库下载了，添加如下BOM

    <dependencyManagement>
        <dependencies>
            <dependency>
                <groupId>org.springframework.ai</groupId>
                <artifactId>spring-ai-bom</artifactId>
                <version>1.0.0-M6</version>
                <type>pom</type>
                <scope>import</scope>
            </dependency>
        </dependencies>
    </dependencyManagement>

    <dependencies>
        <!-- openAI 服务 -->
        <dependency>
            <groupId>org.springframework.ai</groupId>
            <artifactId>spring-ai-openai-spring-boot-starter</artifactId>
        </dependency>

        <!-- 百度千帆 服务 -->
        <dependency>
            <groupId>org.springframework.ai</groupId>
            <artifactId>spring-ai-qianfan-spring-boot-starter</artifactId>
        </dependency>
    </dependencies>

对接Chat Model

@RestController
public class ChatController {
    private final OpenAiChatModel chatModel;

    @Autowired
    public ChatController(OpenAiChatModel chatModel) {
        this.chatModel = chatModel;
    }

    @GetMapping("/ai/generate")
    public Map generate(@RequestParam(value = "message", defaultValue = "Tell me a joke") String message) {
        return Map.of("generation", this.chatModel.call(message));
    }

    @GetMapping("/ai/generateStream")
    public Flux<ChatResponse> generateStream(@RequestParam(value = "message", defaultValue = "Tell me a joke") String message) {
        Prompt prompt = new Prompt(new UserMessage(message));
        return this.chatModel.stream(prompt);
    }

    
    @GetMapping("/ai/tool/calling")
    public Map toolCalling(@RequestParam(value = "message", defaultValue = "Tell me a joke") String message) {
        //目前会循环调用工具方法， 应该跟deepseek自身有关 https://api-docs.deepseek.com/zh-cn/guides/function_calling
        String response = ChatClient.create(chatModel).prompt(message).tools(new IdiomsTools()).call().content();
        return Map.of("generation", response);
    }

}

application.properties需要配置对应api key 信息


spring.ai.openai.api-key=youkey
spring.ai.openai.base-url=https://api.deepseek.com
spring.ai.openai.chat.options.model=deepseek-chat

# 千帆
spring.ai.qianfan.api-key=you api key
spring.ai.qianfan.secret-key=you secret key

使用Advisors API增强AI交互

@RestController
@RequestMapping("/qianfan/advisor")
public class QianfanAdvisorController {

    private final QianFanChatModel chatModel;
    private final ChatClient chatClient;

    @Autowired
    public QianfanAdvisorController(QianFanChatModel chatModel) {
        this.chatModel = chatModel;
        this.chatClient = ChatClient.builder(chatModel)
                .defaultAdvisors(
                        new MessageChatMemoryAdvisor(new InMemoryChatMemory()) // chat-memory advisor
                )
                .build();
    }
    @GetMapping("/ai/generate")
    public Map generate(@RequestParam(value = "message", defaultValue = "Tell me a joke") String message) {

        return Map.of("generation", this.chatClient.prompt().advisors(new LoggingAdvisor()).user(message).call().content());
    }

}