当前位置： 首页 > article >正文

Spring Ai 对接智谱清言结合vue(清测成功)

article 2024/10/27 12:10:22

智谱文档：智谱AI开放平台

注意:springboot版本要在3.0以上，pom.xml要配置下载的源。

pml文件如下

建议使用下科学上网~~~ 

<?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>3.3.4</version>
        <relativePath/> <!-- lookup parent from repository -->
    </parent>
    <groupId>com.example</groupId>
    <artifactId>ai-puzhi</artifactId>
    <version>0.0.1-SNAPSHOT</version>
    <name>ai-puzhi</name>
    <description>ai-puzhi</description>
    <url/>
    <licenses>
        <license/>
    </licenses>
    <developers>
        <developer/>
    </developers>
    <scm>
        <connection/>
        <developerConnection/>
        <tag/>
        <url/>
    </scm>
    <properties>
        <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
        <project.reporting.outputEncoding>UTF-8</project.reporting.outputEncoding>
        <fastjson2.version>2.0.52</fastjson2.version>
        <java.version>17</java.version>
        <spring-ai.version>1.0.3</spring-ai.version>
        <testcontainers.version>1.20.1</testcontainers.version>
    </properties>
    <dependencyManagement>
        <dependencies>
            <dependency>
                <groupId>org.springframework.ai</groupId>
                <artifactId>spring-ai-bom</artifactId>
                <version>1.0.0-M1</version>
                <type>pom</type>
                <scope>import</scope>
            </dependency>
        </dependencies>
    </dependencyManagement>
    <dependencies>
        <!-- For Lombok -->
        <dependency>
            <groupId>org.projectlombok</groupId>
            <artifactId>lombok</artifactId>
        </dependency>
        <!-- For Commons -->
        <dependency>
            <groupId>org.apache.commons</groupId>
            <artifactId>commons-lang3</artifactId>
        </dependency>
        <!-- For Caffeine -->
        <dependency>
            <groupId>com.github.ben-manes.caffeine</groupId>
            <artifactId>caffeine</artifactId>
        </dependency>
        <!-- For FastJson2 -->
        <dependency>
            <groupId>com.alibaba.fastjson2</groupId>
            <artifactId>fastjson2</artifactId>
            <version>${fastjson2.version}</version>
        </dependency>
        <dependency>
            <groupId>io.springboot.ai</groupId>
            <artifactId>spring-ai-zhipu-ai-spring-boot-starter</artifactId>
            <version>${spring-ai.version}</version>
        </dependency>
        <dependency>
            <groupId>cn.bigmodel.openapi</groupId>
            <artifactId>oapi-java-sdk</artifactId>
            <version>release-V4-2.0.2</version>
            <scope>test</scope>
        </dependency>
        <!-- For Web Server -->
        <dependency>
            <groupId>org.springframework.boot</groupId>
            <artifactId>spring-boot-starter-web</artifactId>
            <exclusions>
                <exclusion>
                    <artifactId>spring-boot-starter-tomcat</artifactId>
                    <groupId>org.springframework.boot</groupId>
                </exclusion>
            </exclusions>
        </dependency>

        <dependency>
            <groupId>org.springframework.boot</groupId>
            <artifactId>spring-boot-starter-undertow</artifactId>
        </dependency>
        <dependency>
            <groupId>org.springframework.boot</groupId>
            <artifactId>spring-boot-starter-test</artifactId>
            <scope>test</scope>
        </dependency>
        <dependency>
            <groupId>org.springframework.boot</groupId>
            <artifactId>spring-boot-devtools</artifactId>
            <scope>test</scope>
        </dependency>

    </dependencies>

<!--    配置下载地址-->
    <!-- 设定远程主仓库，按设定顺序进行查找。 -->
    <repositories>
        <repository>
            <id>spring-milestones</id>
            <name>Spring Milestones</name>
            <url>https://repo.spring.io/milestone</url>
            <snapshots>
                <enabled>false</enabled>
            </snapshots>
        </repository>
        <repository>
            <id>spring-snapshots</id>
            <name>Spring Snapshots</name>
            <url>https://repo.spring.io/snapshot</url>
            <releases>
                <enabled>false</enabled>
            </releases>
        </repository>
        <repository>
            <id>central</id>
            <name>Maven Central</name>
            <url>https://repo.maven.apache.org/maven2</url>
        </repository>
    </repositories>
    <build>
        <plugins>
            <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>

yml配置文件

spring:
  application:
    name: ai-puzhi
  ai:
    zhipuai:
      api-key: 82770a63b944ae2789b679332cf32
#      model: glm-4-plus
      model: codegeex-4
    retry:
      backoff:
        max-interval: 3000
        multiplier: 2
        initial-interval: 2000
server:
  port: 9090

 获取key地址:智谱AI开放平台

 

主要代码

 

@RestController
@CrossOrigin
public class ChatController {

    private final ZhipuAiChatClient chatClient;

    @Autowired
    public ChatController(ZhipuAiChatClient chatClient) {
        this.chatClient = chatClient;
    }

    @GetMapping(value = "/v1/generate", produces = "application/json")
    public Map generate(@RequestParam(value = "message", defaultValue = "Tell me a joke") String message) {
        String call = chatClient.call(message);


        System.out.println(call);
        return Map.of("generation", call);
    }

    @GetMapping("/v1/prompt")
    public List<Generation> prompt(@RequestParam(value = "message", defaultValue = "Tell me a joke") String message) {
        PromptTemplate promptTemplate = new PromptTemplate("Tell me a {adjective} joke about {topic}");
        Prompt prompt = promptTemplate.create(Map.of("adjective", "funny", "topic", "cats"));
        return chatClient.call(prompt).getResults();
    }

    @GetMapping("/v1/chat/completions")
    public Flux<ChatResponse> chatCompletions(@RequestParam(value = "message", defaultValue = "Tell me a joke") String message) {
        Prompt prompt = new Prompt(new UserMessage(message));
        return chatClient.stream(prompt);
    }

    @GetMapping("/v1/chat/completionsTow")
    public SseEmitter chatCompletionsTow(@RequestParam(value = "message", defaultValue = "Tell me a joke") String message) {
        SseEmitter emitter = new SseEmitter();
        Prompt prompt = new Prompt(new UserMessage(message));
        // 订阅Flux并处理数据
        chatClient.stream(prompt).subscribe(
                data -> {
                    try {
                        emitter.send(data);
                    } catch (IOException e) {
                        emitter.completeWithError(e);
                    }
                },
                emitter::completeWithError,
                emitter::complete
        );
        return emitter;
    }


    @PostMapping("/v1/chat/completionsPost")
    public Flux<ChatResponse> completionsPost(@RequestBody Message msg) {
        Prompt prompt = new Prompt(new UserMessage(msg.getMsg()));

        return chatClient.stream(prompt);
    }


    @PostMapping(value = "/completionsPost", produces = MediaType.TEXT_EVENT_STREAM_VALUE)
    public void completionsPost(@RequestBody Message msg, HttpServletResponse response) throws IOException {
        Prompt prompt = new Prompt(new UserMessage(msg.getMsg()));
        // 获取 SSE 的 flux 流
        Flux<ChatResponse> flux = chatClient.stream(prompt);

        // 设置必要的 SSE 头部
        response.setHeader("Cache-Control", "no-cache");
        response.setHeader("Connection", "keep-alive");
        response.setHeader("Content-Type", "text/event-stream");

        // 获取响应输出流
        PrintWriter writer = response.getWriter();
        flux.doOnNext(chatResponse -> {
                    try {
                        // 将 ChatResponse 转换为 SSE 格式并写入响应流
                        Generation result = chatResponse.getResult();
                        AssistantMessage output = result.getOutput();
                        String content = output.getContent();
                        System.out.println("content: " + content);
                        writer.write("data: " + content + "\n\n");
                        writer.flush();
                    } catch (Exception e) {
                        // 处理异常
                        e.printStackTrace();
                    }
                })
                .doOnError(throwable -> {
                    try {
                        // 在出现错误时关闭响应流
                        writer.write("event: error\ndata: " + throwable.getMessage() + "\n\n");
                        writer.flush();
                        writer.close();
                    } catch (Exception e) {
                        // 处理异常
                        e.printStackTrace();
                    }
                })
                .doOnComplete(() -> {
                    try {
                        // 在流完成时关闭响应流
                        writer.write("event: complete\ndata: Stream completed\n\n");
                        writer.flush();
                        writer.close();
                    } catch (Exception e) {
                        // 处理异常
                        e.printStackTrace();
                    }
                })
                .subscribe(); // 订阅以启动流
    }


    @PostMapping(value = "/completionsPostNew", produces = MediaType.TEXT_EVENT_STREAM_VALUE)
    public SseEmitter completionsPostNew(@RequestBody Message msg, HttpServletResponse response) {
        SseEmitter emitter = new SseEmitter();
        UserMessage userMessage = new UserMessage(msg.getMsg());
        SystemMessage systemMessage = new SystemMessage("你是一位智能编程助手，你叫CSBlogAi。你会为用户回答关于编程、代码、计算机方面的任何问题，" +
                "并提供格式规范、可以执行、准确安全的代码，并在必要时提供详细的解释。" +
                "任务：请为输入代码提供格式规范的注释，包含多行注释和单行注释，" +
                "请注意不要改动原始代码，只需要添加注释。 请用中文回答。");
        List<org.springframework.ai.chat.messages.Message> messages = List.of(userMessage, systemMessage);
        Prompt prompt = new Prompt(messages);
        // 设置响应头
        response.setContentType(MediaType.TEXT_EVENT_STREAM_VALUE);
        // 订阅Flux并处理数据
        chatClient.stream(prompt).subscribe(
                data -> {
                    try {
                        // 发送 JSON 格式的 SSE 事件
                        emitter.send(data);
                    } catch (IOException e) {
                        emitter.completeWithError(e);
                    }
                },
                emitter::completeWithError,
                emitter::complete
        );
        return emitter;
    }

}

前端主要代码

//get使用 
getChatCompletions() {
        // 关闭之前的SSE连接（如果存在）
        if (this.eventSource) {
          this.eventSource.close();
        }
        let msg = this.userInput.replace(/\s+/g, '')
        let url = `http://localhost:9090/v1/chat/completionsTow?message=${msg}`
        // // 创建一个新的EventSource连接
        this.eventSource = new EventSource(url);
        let user = this.$store.state.UserInfo
        let userObj = {
          user: {
            userName: user.nickname,
            avatar: user.avatar,
            content: this.userInput
          },
          chat: {
            avatar: "https://blog-chen.oss-cn-shanghai.aliyuncs.com/favicon.ico",
            aiName: "CsBlog-Ai",
            content: []
          }
        }
        this.chatResponses.push(userObj)
        this.userInput = ''; // 清空输入框
        // 监听消息事件
        this.eventSource.onmessage = event => {
          const chatResponse = JSON.parse(event.data);
          if (chatResponse.result.output.content.trim() != '') {
            // 获取最后有的数组
            let length = this.chatResponses.length
            this.chatResponses[length - 1].chat.content.push(chatResponse.result.output.content)
            // this.chatResponses.push(chatResponse.result.output.content);
            this.$nextTick(() => {
              prism.highlightAll();// 全局代码高亮
              // 滚动到底部
              this.observeContentChanges()
            });
          }
        };
        // 监听错误事件
        this.eventSource.onerror = error => {
          // 将chatResponses添加到localStorage中
          console.log("关闭eventSource");
          if (this.chatResponses.length != 0) {
            localStorage.setItem(user.id, JSON.stringify(this.chatResponses))
          }
          this.eventSource.close();
        };
      },
//post使用
      SendAi() {
        this.abortController = new AbortController();
        const signal = this.abortController.signal;
        console.log(signal);
        // 添加到数组中
        let user = this.$store.state.UserInfo
        let userObj = {
          user: {
            userName: user.nickname,
            avatar: user.avatar,
            content: this.userInput
          },
          chat: {
            avatar: "https://blog-c",
            aiName: "CsBlog-Ai",
            content: []
          }
        }
        this.chatResponses.push(userObj)
        let sendMsg = this.userInput.replace(/\s+/g, '')
        this.userInput = ''; // 清空输入框
        fetchEventSource('http://localhost:9090/completionsPostNew', {
          method: 'POST',
          headers: {
            'Content-Type': 'application/json',
            'Cache-Control': 'no-cache',
            'Connection': 'keep-alive'
          },
          body: JSON.stringify({ msg: sendMsg }),
          onmessage: (event) => {
            const chatResponse = JSON.parse(event.data);
            if (chatResponse.result.output.content.trim() != '') {
              // 获取最后有的数组
              let length = this.chatResponses.length
              this.chatResponses[length - 1].chat.content.push(chatResponse.result.output.content)
              this.$nextTick(() => {
                prism.highlightAll();// 全局代码高亮
                // 滚动到底部
                this.observeContentChanges()
              });
            }
          },
          onopen: async (response) => {
            if (response.ok && response.headers.get('content-type') === 'text/event-stream') {
              return; // 连接成功
            } else if (response.status >= 400 && response.status < 500 && response.status === 429) {
              this.abortController.abort();
              throw new Error('Client-side error');
            } else {
              this.abortController.abort();
              throw new Error('Retriable error');
            }
          },
          onerror: (event) => {
            if (event.target.readyState === EventSource.CLOSED) {
              console.error('Connection was closed by the server.');
            } else {
              console.error('Error occurred:', event);
            }
          },
          onclose: () => {
            if (this.chatResponses.length != 0) {
              localStorage.setItem(user.id, JSON.stringify(this.chatResponses))
            }
            console.log('Connection closed.');
          },
          signal: signal
        });
      }
    },
    beforeDestroy() {
      this.abortController.abort();
    },

 需要源码的私信~~~


http://www.kler.cn/news/367238.html

相关文章：

  • nginx 修改配置
  • Linux常用命令1
  • 《Windows PE》7.4 资源表应用
  • 强大！Spring Boot 3.3 集成 PDFBox 轻松实现电子签章功能！
  • Unity（四十八）：Unity与Web双向交互
  • 人脸应用实例：性别年龄预测
  • 面向对象高级-继承
  • 世界时钟是怎么创建的？如何在桌面添加一个世界时钟
  • 双十一宝妈购物清单来了，请收下这篇好物攻略！
  • 【15】协方差
  • 《深入浅出HTTPS​》读书笔记（1）：web
  • Jmeter自动化实战
  • 使用Python实现智能火山活动监测模型
  • 241026-RHEL如何以root身份卸载Docker
  • 改进YOLOv8系列：引入低照度图像增强网络Retinexformer | 优化低光照目标检测那题
  • 06. 函数
  • C#里使用最高性的网络通讯例子
  • echarts实现 水库高程模拟图表
  • Qt的信号槽机制学习一
  • k8s 部署 mysql 故障恢复记录
  • 【ESP32S3】VSCode 开发环境搭建
  • 打卡图论10.24
  • Qt元对象系统 —— 属性系统
  • 【论文阅读】Tabbed Out: Subverting the Android Custom Tab Security Model
  • 6.stm32 OLED显示屏
  • spring响应式编程