AIGC盛行,带你轻松调用开发
作者:mmseoamin日期:2024-01-23

文章目录

  • 前言
  • 一、📖AIGC简介
  • 二、📣开通体验
    • 开通模型获取API-KEY
    • 三、📝基于java实现调用
      • 1.设置API-KEY
      • 2.体验大语言模型
        • 多轮对话演示
        • 补充流式输出
        • 3.体验通义千问VL
          • 使用官方提供照片
          • 本地文件
          • 多轮对话
          • 流式输出
          • 总结

            前言

            本篇文章基于java和阿里云的通义千问大模型手把手带你使用AIGC开发,实现文本对话和图像分析。


            一、📖AIGC简介

            你知道什么是AIGC吗?不知道?没关系,我来告诉你:

            • AIGC就是由AI自动创作生成的内容(AI Generated Content),比如图片、视频、音乐、文字等。AIGC就像一支神奇的画笔,拥有无限的创造力。这支画笔的特别之处在于,它是由AI打造的。AI利用它的理解力、想象力和创作力,根据指定的需求和风格,创作出各种内容:文章、短篇小说、报告、音乐、图像,甚至是视频。AIGC的出现,打开了一个全新的创作世界,为人们提供了无数的可能性。
            • AI,就是人工智能。它的目标是让机器能够像人一样有智能,能够看、听、说、想、做。要实现这个目标,AI需要用到重要的技术:深度学习、NLP(自然语言处理)、神经网络和生成式对抗网络(GAN)。

            🌤️通过上面的讲诉,无论你曾经不知道还是模棱两可,现在应该大概了解了,下面带你走进AIGC,用程序员的身份打开AIGC。

            二、📣开通体验

            开通模型获取API-KEY

            大家不要害怕开通不会产生收费,本文讲述的完全是免费就可使用的方法。

            登录阿里云进入控制台后,鼠标移到下图位置

            AIGC盛行,带你轻松调用开发,在这里插入图片描述,第1张

            然后出现如下界面,找到人工智能与机器学习下的模型服务灵积,点击

            AIGC盛行,带你轻松调用开发,在这里插入图片描述,第2张

            参照开发文档,开通DashScope并创建API-KEY

            AIGC盛行,带你轻松调用开发,在这里插入图片描述,第3张

            总结文档上的开通步骤如下:

            在控制台中点击总览,去开通

            AIGC盛行,带你轻松调用开发,在这里插入图片描述,第4张

            立开通(大家不要怕,这是不会产生扣费的)

            AIGC盛行,带你轻松调用开发,在这里插入图片描述,第5张

            开通后,点击 管理中心 的 API-KEY 菜单项,然后创建新的API-KEY

            AIGC盛行,带你轻松调用开发,在这里插入图片描述,第6张

            就会有个Accesskeyid和Secret值(这俩值要记住真正的开发中有用,本文章没用到)的弹窗,然后点击已创建的AIP-KEY查看并复制,这个会用到。

            AIGC盛行,带你轻松调用开发,在这里插入图片描述,第7张

            AIGC盛行,带你轻松调用开发,在这里插入图片描述,第8张

            三、📝基于java实现调用

            📣打开IDEA,开始操作了

            1.设置API-KEY

            先了解以下如何设置API-KEY值的:

            import com.alibaba.dashscope.utils.Constants;
            Constants.apiKey="这就是你的API-KEY的值(上面复制的)";
            

            2.体验大语言模型

            多轮对话演示

            创建一个测试类:

            AIGC盛行,带你轻松调用开发,在这里插入图片描述,第9张

            代码如下:

            import com.alibaba.dashscope.aigc.generation.Generation;
            import com.alibaba.dashscope.aigc.generation.GenerationResult;
            import com.alibaba.dashscope.aigc.generation.models.QwenParam;
            import com.alibaba.dashscope.common.Message;
            import com.alibaba.dashscope.common.MessageManager;
            import com.alibaba.dashscope.common.Role;
            import com.alibaba.dashscope.exception.ApiException;
            import com.alibaba.dashscope.exception.InputRequiredException;
            import com.alibaba.dashscope.exception.NoApiKeyException;
            import com.alibaba.dashscope.utils.Constants;
            import com.alibaba.dashscope.utils.JsonUtils;
            import org.mockito.internal.matchers.Contains;
            import java.awt.*;
            class test {
                public static void callWithMessage()
                        throws NoApiKeyException, ApiException, InputRequiredException {
                    // 设置API-KEY值
                    Constants.apiKey="你的API-KEY值";
                    Generation gen = new Generation();
                    MessageManager msgManager = new MessageManager(10);
                    Message systemMsg =
                            Message.builder().role(Role.SYSTEM.getValue()).content("You are a helpful assistant.").build();//告知模型他是个助手(设置角色)
                    Message userMsg = Message.builder().role(Role.USER.getValue()).content("你好,周末去哪里玩?").build();//对话问题
                    msgManager.add(systemMsg);
                    msgManager.add(userMsg);
                    QwenParam param =
                            QwenParam.builder().model(Generation.Models.QWEN_PLUS).messages(msgManager.get())
                                    .resultFormat(QwenParam.ResultFormat.MESSAGE)
                                    .topP(0.8)
                                    .enableSearch(true)
                                    .build();
                    GenerationResult result = gen.call(param);
                    System.out.println(result);//输出回复
                    msgManager.add(result);
                    System.out.println(JsonUtils.toJson(result));//JSON格式输出回复
                    param.setPrompt("找个近点的");//继续问题
                    param.setMessages(msgManager.get());
                    result = gen.call(param);
                    System.out.println(result);
                    System.out.println(JsonUtils.toJson(result));
                }
                public static void main(String[] args){
                    try {
                        callWithMessage();
                    } catch (ApiException | NoApiKeyException | InputRequiredException e) {
                        System.out.println(e.getMessage());
                    }
                    System.exit(0);
                }
            }
            

            上诉代码就是向模型提问周末去哪玩,模型给出回复后,又继续说让他说个近点的地方

            AIGC盛行,带你轻松调用开发,在这里插入图片描述,第10张

            AIGC盛行,带你轻松调用开发,在这里插入图片描述,第11张

            补充流式输出

            import java.util.Arrays;
            import java.util.concurrent.Semaphore;
            import com.alibaba.dashscope.aigc.generation.Generation;
            import com.alibaba.dashscope.aigc.generation.GenerationResult;
            import com.alibaba.dashscope.aigc.generation.models.QwenParam;
            import com.alibaba.dashscope.common.Message;
            import com.alibaba.dashscope.common.ResultCallback;
            import com.alibaba.dashscope.common.Role;
            import com.alibaba.dashscope.exception.ApiException;
            import com.alibaba.dashscope.exception.InputRequiredException;
            import com.alibaba.dashscope.exception.NoApiKeyException;
            import com.alibaba.dashscope.utils.JsonUtils;
            import io.reactivex.Flowable;
            import com.alibaba.dashscope.utils.Constants;
            public class Main {
              public static void streamCallWithMessage()
                  throws NoApiKeyException, ApiException, InputRequiredException {
                 Constants.apiKey="你的API-KEY值";
                Generation gen = new Generation();
                Message userMsg = Message
                .builder()
                .role(Role.USER.getValue())
                .content("如何做西红柿炖牛腩?")
                .build();
                QwenParam param =
                    QwenParam.builder().model(Generation.Models.QWEN_PLUS).messages(Arrays.asList(userMsg))
                        .resultFormat(QwenParam.ResultFormat.MESSAGE)
                        .topP(0.8)
                        .enableSearch(true)
                        .incrementalOutput(true) // get streaming output incrementally
                        .build();
                Flowable result = gen.streamCall(param);
                StringBuilder fullContent = new StringBuilder();
                result.blockingForEach(message -> {
                  fullContent.append(message.getOutput().getChoices().get(0).getMessage().getContent());
                  System.out.println(JsonUtils.toJson(message));
                });
                System.out.println("Full content: \n" + fullContent.toString());
              }
              public static void streamCallWithCallback()
                  throws NoApiKeyException, ApiException, InputRequiredException,InterruptedException {
                Generation gen = new Generation();
                Message userMsg = Message
                .builder()
                .role(Role.USER.getValue())
                .content("如何做西红柿炖牛腩?")
                .build();
                QwenParam param = QwenParam
                .builder()
                .model(Generation.Models.QWEN_PLUS)
                .resultFormat(QwenParam.ResultFormat.MESSAGE)
                .messages(Arrays.asList(userMsg))
                .topP(0.8)
                .incrementalOutput(true) // get streaming output incrementally
                .build();
                Semaphore semaphore = new Semaphore(0);
                StringBuilder fullContent = new StringBuilder();
                gen.streamCall(param, new ResultCallback() {
                  @Override
                  public void onEvent(GenerationResult message) {
                    fullContent.append(message.getOutput().getChoices().get(0).getMessage().getContent());
                    System.out.println(message);
                  }
                  @Override
                  public void onError(Exception err){
                    System.out.println(String.format("Exception: %s", err.getMessage()));
                    semaphore.release();
                  }
                  @Override
                  public void onComplete(){
                    System.out.println("Completed");
                    semaphore.release();
                  }
                  
                });
                semaphore.acquire();
                System.out.println("Full content: \n" + fullContent.toString());
              }
              public static void main(String[] args) {
                try {
                  streamCallWithMessage();
                } catch (ApiException | NoApiKeyException | InputRequiredException e) {
                  System.out.println(e.getMessage());
                }
                try {
                  streamCallWithCallback();
                } catch (ApiException | NoApiKeyException | InputRequiredException | InterruptedException e) {
                  System.out.println(e.getMessage());
                }
                System.exit(0);
              }
            }
            

            3.体验通义千问VL

            下面使用接口实现图片解析

            使用官方提供照片

            首先大家看一下官方提供的图片:

            AIGC盛行,带你轻松调用开发,在这里插入图片描述,第12张

            /**
             * @Version: 1.0.0
             * @Author: Dragon_王
             * @ClassName: test1
             * @Description: TODO描述
             * @Date: 2023/12/28 17:41
             */
            import java.util.Arrays;
            import java.util.Collections;
            import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversation;
            import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversationParam;
            import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversationResult;
            import com.alibaba.dashscope.common.MultiModalMessage;
            import com.alibaba.dashscope.common.Role;
            import com.alibaba.dashscope.exception.ApiException;
            import com.alibaba.dashscope.exception.NoApiKeyException;
            import com.alibaba.dashscope.exception.UploadFileException;
            import com.alibaba.dashscope.utils.Constants;
            class test1 {
                public static void simpleMultiModalConversationCall()
                        throws ApiException, NoApiKeyException, UploadFileException {
                    Constants.apiKey="你的api-key";
                    MultiModalConversation conv = new MultiModalConversation();
                    MultiModalMessage userMessage = MultiModalMessage.builder().role(Role.USER.getValue())
                            .content(Arrays.asList(Collections.singletonMap("image", "https://dashscope.oss-cn-beijing.aliyuncs.com/images/dog_and_girl.jpeg"),
                                    Collections.singletonMap("text", "这是什么?"))).build();// 对话的问题
                    MultiModalConversationParam param = MultiModalConversationParam.builder()
                            .model(MultiModalConversation.Models.QWEN_VL_PLUS)
                            .message(userMessage)
                            .build();
                    MultiModalConversationResult result = conv.call(param);
                    System.out.println(result);
                }
                public static void main(String[] args) {
                    try {
                        simpleMultiModalConversationCall();
                    } catch (ApiException | NoApiKeyException | UploadFileException e) {
                        System.out.println(e.getMessage());
                    }
                    System.exit(0);
                }
            }
            

            AIGC盛行,带你轻松调用开发,在这里插入图片描述,第13张

            本地文件

            import java.util.Arrays;
            import java.util.HashMap;
            import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversation;
            import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversationParam;
            import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversationResult;
            import com.alibaba.dashscope.common.MultiModalMessage;
            import com.alibaba.dashscope.common.Role;
            import com.alibaba.dashscope.exception.ApiException;
            import com.alibaba.dashscope.exception.NoApiKeyException;
            import com.alibaba.dashscope.exception.UploadFileException;
            import io.reactivex.Flowable;
            import com.alibaba.dashscope.utils.Constants;
            public class MultiModalConversationLocalFile2 {
                /**
                 * sample of use local file
                 * Windows file format: file:///D:/test/images/test.png
                 * Linux & Mac format: file://The_absolute_local_path
                 * 
                 */
                public static void callWithLocalFile()
                        throws ApiException, NoApiKeyException, UploadFileException {
                    Constants.apiKey="你的api-key";
                    String localFilePath = "file://The_file_absolute_path"; 
                    MultiModalConversation conv = new MultiModalConversation();
                    // must create mutable map.
                    MultiModalMessage userMessage = MultiModalMessage.builder().role(Role.USER.getValue())
                    .content(Arrays.asList(new HashMap(){{put("image", localFilePath);}}, 
                    new HashMap(){{put("text", "这是什么?");}})).build();// 对话问题
                    MultiModalConversationParam param = MultiModalConversationParam.builder()
                            .model(MultiModalConversation.Models.QWEN_VL_PLUS)
                            .message(userMessage)
                            .build();
                    Flowable result = conv.streamCall(param);
                    result.blockingForEach(item -> {
                        System.out.println(item);
                    });
                }
                public static void main(String[] args) {
                    try {
                        callWithLocalFile();
                    } catch (ApiException | NoApiKeyException | UploadFileException e) {
                        System.out.println(e.getMessage());
                    }
                    System.exit(0);
                }
            }
            

            多轮对话

            import java.util.ArrayList;
            import java.util.Arrays;
            import java.util.Collections;
            import java.util.List;
            import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversation;
            import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversationParam;
            import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversationResult;
            import com.alibaba.dashscope.common.MultiModalMessage;
            import com.alibaba.dashscope.common.Role;
            import com.alibaba.dashscope.exception.ApiException;
            import com.alibaba.dashscope.exception.NoApiKeyException;
            import com.alibaba.dashscope.exception.UploadFileException;
            import com.alibaba.dashscope.utils.Constants;
            public class Main {
                private static final String modelName = "qwen-vl-plus";
                public static void MultiRoundConversationCall() throws ApiException, NoApiKeyException, UploadFileException {
                	Constants.apiKey="你的api-key";
                    MultiModalConversation conv = new MultiModalConversation();
                    MultiModalMessage systemMessage = MultiModalMessage.builder().role(Role.SYSTEM.getValue())
                    .content(Arrays.asList(Collections.singletonMap("text", "You are a helpful assistant."))).build();
                    MultiModalMessage userMessage = MultiModalMessage.builder().role(Role.USER.getValue())
                    .content(Arrays.asList(Collections.singletonMap("image", "https://dashscope.oss-cn-beijing.aliyuncs.com/images/dog_and_girl.jpeg"), 
                    Collections.singletonMap("text", "图片里有什么动物?"))).build();// 第一个对话问题
                    List messages = new ArrayList<>();
                    messages.add(systemMessage);
                    messages.add(userMessage);
                    MultiModalConversationParam param = MultiModalConversationParam.builder()
                            .model(MultiModalConversationUsage2.modelName)
                            .messages(messages)
                            .build();
                    MultiModalConversationResult result = conv.call(param);
                    System.out.println(result);
                    // add the result to conversation
                    messages.add(result.getOutput().getChoices().get(0).getMessage());
                    MultiModalMessage msg = MultiModalMessage.builder().role(Role.USER.getValue())
                    .content(Arrays.asList(Collections.singletonMap("text", "图片动物是什么?"))).build();// 第二个对话问题
                    messages.add(msg);
                    // new messages
                    param.setMessages((List)messages);
                    result = conv.call(param);
                    System.out.print(result);
                }
                public static void main(String[] args) {
                    try {
                        MultiRoundConversationCall();
                    } catch (ApiException | NoApiKeyException | UploadFileException e) {
                        System.out.println(e.getMessage());
                    }
                    System.exit(0);
                
            

            流式输出

            只是输出采用的方式不一样

            import java.util.Arrays;
            import java.util.HashMap;
            import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversation;
            import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversationParam;
            import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversationResult;
            import com.alibaba.dashscope.common.MultiModalMessage;
            import com.alibaba.dashscope.common.Role;
            import com.alibaba.dashscope.exception.ApiException;
            import com.alibaba.dashscope.exception.NoApiKeyException;
            import com.alibaba.dashscope.exception.UploadFileException;
            import io.reactivex.Flowable;
            import com.alibaba.dashscope.utils.Constants;
            public class MultiModalConversationStream {
                public static void streamCall()
                        throws ApiException, NoApiKeyException, UploadFileException {
                    Constants.apiKey="你的api-key";
                    MultiModalConversation conv = new MultiModalConversation();
                    // must create mutable map.
                    MultiModalMessage userMessage = MultiModalMessage.builder().role(Role.USER.getValue())
                    .content(Arrays.asList(new HashMap(){{put("image", "https://dashscope.oss-cn-beijing.aliyuncs.com/images/dog_and_girl.jpeg");}}, 
                    new HashMap(){{put("text", "基于这幅图,讲一个故事");}})).build();
                    MultiModalConversationParam param = MultiModalConversationParam.builder()
                            .model(MultiModalConversation.Models.QWEN_VL_PLUS)
                            .message(userMessage)
                            .build();
                    Flowable result = conv.streamCall(param);
                    result.blockingForEach(item -> {
                        System.out.println(item);
                    });
                }
                public static void main(String[] args) {
                    try {
                        streamCall();
                    } catch (ApiException | NoApiKeyException | UploadFileException e) {
                        System.out.println(e.getMessage());
                    }
                    System.exit(0);
                }
            }
            

            总结

            上面就是使用java调用通义千问大模型的案例,上诉代码都可以运行,如果想改变问题,就将对话问题修改就行。如果再自己写一个UI界面的话,你就拥有了自己的AIGC了(虽然是调用的API🌤️)。