当前位置：首页 > news >正文

springboot3.x对接AI智谱清言

news 来源：原创 2025/6/9 7:20:26

spring引入智谱清言ai包

<!--版本管理--><dependencyManagement><dependencies><dependency><groupId>org.springframework.ai</groupId><artifactId>spring-ai-bom</artifactId><version>1.0.0-SNAPSHOT</version><type>pom</type><scope>import</scope></dependency></dependencies></dependencyManagement>

<!-- Spring AI BOM 声明了特定版本的 Spring AI依赖项的推荐版本   --><repositories><repository><id>spring-snapshots</id><name>Spring Snapshots</name><url>https://repo.spring.io/snapshot</url><releases><enabled>false</enabled></releases></repository></repositories>

<!-- 智谱清言AI --><dependency><groupId>org.springframework.ai</groupId><artifactId>spring-ai-starter-model-zhipuai</artifactId><exclusions><exclusion><groupId>io.swagger.core.v3</groupId><artifactId>swagger-annotations</artifactId></exclusion></exclusions></dependency>

这里如果使用了springdoc/swagger，需要exclude这个包，不然会出现包冲突，导致项目启动失败

spring新增智谱清言ai配置

  ai:zhipuai:api-key: xxxx # 你自己的智谱清言keybase-url: https://open.bigmodel.cn/api/paaschat:options:model: glm-4-flash # 免费模型# model: glm-4-plus #付费模型temperature: 0.5  # 响应随机性

定义智谱清言AI配置类

@Configuration
public class ZhipuAiConfig {@Beanpublic ChatClient chatClient(ChatModel chatModel) {return ChatClient.builder(chatModel).build();}
}

AiService类

@Service
public class AiServiceImpl implements AiService{private final ChatClient chatClient;public AiCheckServiceImpl(ChatClient chatClient) {this.chatClient = chatClient;}@Overridepublic String sendMessage(String message) {return chatClient.prompt().user(message).call().content();}
}

以上就完成了AiService类的编写，controller类可以通过调用sendMessage方法和智谱清言AI接口进行对话。