Java(Spring boot)集成智谱AI聊天(简易版)

1.准备工作

智谱AI开放平台 (bigmodel.cn)

进入智谱AI开放平台，注册登录后，找到右上角API秘钥，生成一个调用的秘钥即可

同时需要注意的是智谱官网会给新用户赠送token包，可以暂时免费体验更聪明更快速的大模型，但这些体验一般来说都是一个月左右**(找到右上角财务点击找到资源包管理可以看到套餐)**

如果只是短期需求可以使用，但如果长期使用的话，建议还是使用也是可以免费调用的API大模型，例如glm-4-flash，下面就以这个模型为例子展开

2.代码开发

(1)pom.xml文件

<?xml version="1.0" encoding="UTF-8"?>
<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 https://maven.apache.org/xsd/maven-4.0.0.xsd">
    <modelVersion>4.0.0</modelVersion>
    <parent>
        <groupId>org.springframework.boot</groupId>
        <artifactId>spring-boot-starter-parent</artifactId>
        <version>2.4.2</version>
        <relativePath/> <!-- lookup parent from repository -->
    </parent>
    <groupId>com.example</groupId>
    <artifactId>AiChat</artifactId>
    <version>0.0.1-SNAPSHOT</version>
    <name>AiChat</name>
    <description>Demo project for Spring Boot</description>
    <url/>
    <licenses>
        <license/>
    </licenses>
    <developers>
        <developer/>
    </developers>
    <scm>
        <connection/>
        <developerConnection/>
        <tag/>
        <url/>
    </scm>
    <properties>
        <java.version>17</java.version>
    </properties>
    <dependencies>
        <dependency>
            <groupId>org.springframework.boot</groupId>
            <artifactId>spring-boot-starter-web</artifactId>
        </dependency>
        <dependency>
            <groupId>org.mybatis.spring.boot</groupId>
            <artifactId>mybatis-spring-boot-starter</artifactId>
            <version>3.0.3</version>
        </dependency>

        <dependency>
            <groupId>cn.bigmodel.openapi</groupId>
            <artifactId>oapi-java-sdk</artifactId>
            <version>release-V4-2.0.2</version>
        </dependency>
        <dependency>
            <groupId>org.springframework.boot</groupId>
            <artifactId>spring-boot-starter-test</artifactId>
            <scope>test</scope>
        </dependency>
        <dependency>
            <groupId>org.mybatis.spring.boot</groupId>
            <artifactId>mybatis-spring-boot-starter-test</artifactId>
            <version>3.0.3</version>
            <scope>test</scope>
        </dependency>
        <!--lombok-->
        <dependency>
            <groupId>org.projectlombok</groupId>
            <artifactId>lombok</artifactId>
            <version>1.18.24</version>
        </dependency>
    </dependencies>

</project>

(2)application.properties文件 (记得把自己的API秘钥填上哈)

spring.application.name=AiChat
zhipuai.api.key=   #API密钥
server.port=8066

(3)ZhipuAIService代码 (通过调用 Zhipu AI API 来处理用户消息，获取 AI 的回复并返回。构建请求，发送给 API，解析响应数据，并提取返回的内容)

import com.fasterxml.jackson.core.type.TypeReference;
import com.fasterxml.jackson.databind.ObjectMapper;
import com.zhipu.oapi.ClientV4;
import com.zhipu.oapi.Constants;
import com.zhipu.oapi.service.v4.model.ChatCompletionRequest;
import com.zhipu.oapi.service.v4.model.ChatMessage;
import com.zhipu.oapi.service.v4.model.ModelApiResponse;
import org.springframework.beans.factory.annotation.Value;
import org.springframework.stereotype.Service;
import java.util.ArrayList;
import java.util.List;
import java.util.Map;
@Service
public class ZhipuAIService {
    private final ClientV4 client;
    private final ObjectMapper objectMapper;
    public ZhipuAIService(@Value("${zhipuai.api.key}") String apiKey) {
        this.client = new ClientV4.Builder(apiKey).build();
        this.objectMapper = new ObjectMapper();
    }
    //构建信息
    public String invokeChatCompletion(String userMessage) {
        List<ChatMessage> messages = new ArrayList<>();
        ChatMessage chatMessage = new ChatMessage("user", userMessage);
        messages.add(chatMessage);
        ChatCompletionRequest chatCompletionRequest = ChatCompletionRequest.builder()
                //表明使用的模型
                .model("glm-4-flash")
                 //表示不使用流式响应
                .stream(Boolean.FALSE)
                .invokeMethod(Constants.invokeMethod)
                .messages(messages)
                .requestId("request-id-" + System.currentTimeMillis())
                .build();
        ModelApiResponse response = client.invokeModelApi(chatCompletionRequest);
        try {
            // 将response的数据转换为Map
            String jsonString = objectMapper.writeValueAsString(response.getData());
            Map<String, Object> dataMap = objectMapper.readValue(jsonString, new TypeReference<Map<String, Object>>() {});
            // 提取内容
            if (dataMap.containsKey("choices")) {
                List<Map<String, Object>> choices = (List<Map<String, Object>>) dataMap.get("choices");
                if (!choices.isEmpty()) {
                    Map<String, Object> firstChoice = choices.get(0);
                    Map<String, Object> message = (Map<String, Object>) firstChoice.get("message");
                    if (message != null && message.containsKey("content")) {
                        return (String) message.get("content");
                    }
                }
            }
            return "找不到内容";
        } catch (Exception e) {
            return "响应错误";
        }
    }
}

(4)ZhipuAiController代码 （**处理 HTTP POST 请求，将用户输入传递给

ZhipuAIService

，并返回 AI 的回复。它对输入进行 URL 解码，以确保正确处理）**

import org.springframework.web.bind.annotation.PostMapping;
import org.springframework.web.bind.annotation.RequestBody;
import org.springframework.web.bind.annotation.RequestMapping;
import org.springframework.web.bind.annotation.RestController;

import java.io.UnsupportedEncodingException;
import java.net.URLDecoder;
import java.nio.charset.StandardCharsets;

@RestController
@RequestMapping("/chat")
public class ZhipuAiController {

    private final ZhipuAIService zhipuAiService;

    public ZhipuAiController(ZhipuAIService zhipuAiService) {
        this.zhipuAiService = zhipuAiService;
    }

    @PostMapping("/ask")
    public String chat(@RequestBody String userInput) {
        try {
            // 对接收到的userInput进行URL解码
            userInput = URLDecoder.decode(userInput, StandardCharsets.UTF_8.toString());
        } catch (UnsupportedEncodingException e) {
            return "解码错误";
        }
        String response = zhipuAiService.invokeChatCompletion(userInput);
        return response;
    }

}

3.PostMan或者ApiFox测试效果

至此不出意外应该集成AI聊天功能了，当然了如果想用例如GLM-4这种更好的大模型其实也是可以在代码里稍加修改的，就是要记得体验期是有限的哈

.model(Constants.ModelChatGLM4)

为了确保万一，我们还可以在费用账单里查看明细，避免错误扣费

希望可以帮到有需要的小伙伴啦