企业知识库问答系统(1.调用大模型)

小程 included in 项目

2025-11-12 548 words 2 minutes views

Contents

企业知识库问答系统(1.调用大模型)

技术栈

LangChain4j

Spring Boot

Java21

Maven

过程

1.项目初始化

新建maven项目，pom文件引入依赖如下

<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
  xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/maven-v4_0_0.xsd">
    <modelVersion>4.0.0</modelVersion>
    <parent>
        <groupId>org.springframework.boot</groupId>
        <artifactId>spring-boot-starter-parent</artifactId>
        <version>3.5.3</version>
        <relativePath/> <!-- lookup parent from repository -->
    </parent>
    <groupId>cn.homecj</groupId>
    <artifactId>aiLearning</artifactId>
    <version>1.0-SNAPSHOT</version>
    <name>aiLearning</name>
    <url>http://maven.apache.org</url>
    <properties>
        <java.version>21</java.version>
    </properties>
    <dependencies>
        <dependency>
            <groupId>org.springframework.boot</groupId>
            <artifactId>spring-boot-starter-web</artifactId>
        </dependency>
        <dependency>
            <groupId>dev.langchain4j</groupId>
            <artifactId>langchain4j-community-dashscope-spring-boot-starter</artifactId>
            <version>1.1.0-beta7</version>
        </dependency>
        <dependency>
            <groupId>dev.langchain4j</groupId>
            <artifactId>langchain4j</artifactId>
            <version>1.1.0</version>
        </dependency>
        <dependency>
            <groupId>dev.langchain4j</groupId>
            <artifactId>langchain4j-spring-boot-starter</artifactId>
            <version>1.1.0-beta7</version>
        </dependency>
        <dependency>
            <groupId>dev.langchain4j</groupId>
            <artifactId>langchain4j-mcp</artifactId>
            <version>1.1.0-beta7</version>
        </dependency>
        <dependency>
            <groupId>dev.langchain4j</groupId>
            <artifactId>langchain4j-reactor</artifactId>
            <version>1.1.0-beta7</version>
        </dependency>
        <dependency>
            <groupId>org.projectlombok</groupId>
            <artifactId>lombok</artifactId>
            <optional>true</optional>
        </dependency>
        <dependency>
            <groupId>org.springframework.boot</groupId>
            <artifactId>spring-boot-starter-test</artifactId>
            <scope>test</scope>
        </dependency>
    </dependencies>

    <build>
        <plugins>
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-compiler-plugin</artifactId>
                <configuration>
                    <annotationProcessorPaths>
                        <path>
                            <groupId>org.projectlombok</groupId>
                            <artifactId>lombok</artifactId>
                        </path>
                    </annotationProcessorPaths>
                </configuration>
            </plugin>
            <plugin>
                <groupId>org.springframework.boot</groupId>
                <artifactId>spring-boot-maven-plugin</artifactId>
                <configuration>
                    <excludes>
                        <exclude>
                            <groupId>org.projectlombok</groupId>
                            <artifactId>lombok</artifactId>
                        </exclude>
                    </excludes>
                </configuration>
            </plugin>
        </plugins>
    </build>
</project>

2.引入通义模型

使用langchain4j提供的ChatModel.builder，传入apiKey和modelName参数即可定义一个通义模型。这里Spring会注册bean name为myQwenChatModel，类型ChatModel的bean。

@Configuration
@ConfigurationProperties(prefix = "langchain4j.community.dashscope.chat-model")
@Data
public class QwenConfig {
    private String apiKey;

    private String modelName;


    @Bean
    public ChatModel myQwenChatModel(){
        return QwenChatModel.builder()
                .apiKey(apiKey)
                .modelName(modelName)
                .build();
    }
}

3.调用模型

调用刚才引入的模型，使用Autowired获取ChatModel类型的bean。

@Service
@Slf4j
public class Chat {
    @Autowired
    private ChatModel qwenModel;

    public static final String SYSTEM_MESSAGE = """
            你是一个聊天机器人，回复用户提出的问题。
            """;

    public String chat(String message){
        SystemMessage systemMessage = SystemMessage.from(SYSTEM_MESSAGE);
        UserMessage userMessage = UserMessage.from(message);
        ChatResponse chatResponse = qwenModel.chat(systemMessage, userMessage);
        AiMessage aiMessage = chatResponse.aiMessage();
        log.info("AI 输出：" + aiMessage.toString());
        return aiMessage.text();
    }
}

4.测试

@SpringBootTest
public class ChatTest {
    @Autowired
    private QwenChat chatTemplate;

    @Test
    void chat(){
        chatTemplate.chat("你好，你是谁");
    }
}

输出如下

2025-11-12T14:37:42.084+08:00  INFO 17560 --- [aiLearning] [           main] cn.homecj.aiLearning.ai.QwenChat         : AI 输出：AiMessage { text = "你好，我是来自阿里云的超大规模语言模型，我叫通义千问。" toolExecutionRequests = [] }