dashscope-sb 多模态(图片、语音识别) 文生视频

1、pom.xml<properties>

    <java.version>17</java.version>
    <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
    <project.reporting.outputEncoding>UTF-8</project.reporting.outputEncoding>
    <spring-boot.version>3.2.0</spring-boot.version>
    <spring-ai.version>1.0.0</spring-ai.version>
    <spring-ai-alibaba.version>1.0.0.2</spring-ai-alibaba.version>
</properties>
<dependencies>
    <dependency>
        <groupId>org.springframework.boot</groupId>
        <artifactId>spring-boot-starter</artifactId>
    </dependency>
    <dependency>
        <groupId>org.springframework.boot</groupId>
        <artifactId>spring-boot-starter-web</artifactId>
    </dependency>
    <dependency>
        <groupId>org.springframework.ai</groupId>
        <artifactId>spring-ai-starter-model-deepseek</artifactId>
        <version>1.0.0</version>
    </dependency>
    <!-- 阿里云通义千问（DashScope）starter -->
    <dependency>
        <groupId>com.alibaba.cloud.ai</groupId>
        <artifactId>spring-ai-alibaba-starter-dashscope</artifactId>
    </dependency>
    <dependency>
        <groupId>org.springframework.boot</groupId>
        <artifactId>spring-boot-starter-test</artifactId>
        <scope>test</scope>
    </dependency>
   <!---文本视频sdk-->
    <dependency>
        <groupId>com.alibaba</groupId>
        <artifactId>dashscope-sdk-java</artifactId>
        <version>2.20.6</version>
    </dependency>
</dependencies>
<dependencyManagement>
    <dependencies>
        <dependency>
            <groupId>org.springframework.boot</groupId>
            <artifactId>spring-boot-dependencies</artifactId>
            <version>${spring-boot.version}</version>
            <type>pom</type>
            <scope>import</scope>
        </dependency>
    <!-- 统一管理Spring AI依赖版本 -->
        <dependency>
            <groupId>org.springframework.ai</groupId>
            <artifactId>spring-ai-bom</artifactId>
            <version>${spring-ai.version}</version>
            <type>pom</type>
            <scope>import</scope>
        </dependency>
        <dependency>
            <groupId>com.alibaba.cloud.ai</groupId>
            <artifactId>spring-ai-alibaba-bom</artifactId>
            <version>${spring-ai-alibaba.version}</version>
            <type>pom</type>
            <scope>import</scope>
        </dependency>
    </dependencies>
</dependencyManagement>

2、yml

server:
  port: 8082

spring:
  application:
    name: deepseek
        # ========== 阿里云通义千问（DashScope）配置 ==========
        #spring.ai.dashscope.api-key=${ALI_AI_KEY}
        # spring.ai.dashscope.chat.options.model= 可指定模型，如 qwen-max、qwen-plus 等
    dashscope:
      api-key: "keykey"
      #chat:
      #  options:
      #    model:

注:api-key  请用自己的key

3、controller
文生视频

import com.alibaba.dashscope.aigc.videosynthesis.VideoSynthesis;
import com.alibaba.dashscope.aigc.videosynthesis.VideoSynthesisParam;
import com.alibaba.dashscope.aigc.videosynthesis.VideoSynthesisResult;
import com.alibaba.dashscope.exception.InputRequiredException;
import com.alibaba.dashscope.exception.NoApiKeyException;
import org.springframework.stereotype.Controller;
import org.springframework.web.bind.annotation.GetMapping;
import org.springframework.web.bind.annotation.RequestMapping;
import org.springframework.web.bind.annotation.ResponseBody;

@RequestMapping("/openai")
@ResponseBody
@Controller
public class Txt2Vedio {
    @GetMapping("/simple/vedio")
    public String mult () throws NoApiKeyException, InputRequiredException {
        VideoSynthesis videoSynthesis=new VideoSynthesis();
        VideoSynthesisParam param=
                VideoSynthesisParam.builder()
                        .model("wanx2.1-t2v-turbo")//wanx2.1-t2v-puls
                        .prompt("一只小猫在月光下奔跑")
                        .size("1280*720")
                        .apiKey("sk-8718a83408d7443b9544cdfbf259280f")
                        .build();
                System.out.println("please wait....");
        VideoSynthesisResult  result=videoSynthesis.call(param);
        return result.getOutput().getVideoUrl();
    }
}

 

多模态(图片、语音识别)

import com.alibaba.cloud.ai.dashscope.chat.DashScopeChatModel;
import com.alibaba.cloud.ai.dashscope.chat.DashScopeChatOptions;
import com.alibaba.cloud.ai.dashscope.chat.MessageFormat;
import com.alibaba.cloud.ai.dashscope.common.DashScopeApiConstants;
import jakarta.annotation.Resource;
import org.springframework.ai.chat.messages.UserMessage;
import org.springframework.ai.chat.model.ChatResponse;
import org.springframework.ai.chat.prompt.Prompt;
import org.springframework.ai.content.Media;
import org.springframework.core.io.ClassPathResource;
import org.springframework.stereotype.Controller;
import org.springframework.util.MimeType;
import org.springframework.util.MimeTypeUtils;
import org.springframework.web.bind.annotation.GetMapping;
import org.springframework.web.bind.annotation.RequestMapping;
import org.springframework.web.bind.annotation.ResponseBody;

import java.util.Map;

@RequestMapping("/openai")
@ResponseBody
@Controller
public class testMultimodal {
    @Resource
    private DashScopeChatModel dashScopeChatModel;

    @GetMapping("/simple/mult")
    public String mult () {
        // flac、mp3、mp4、mpeg、mpga、m4a、ogg、wav 或 webm。
        var audioFile = new ClassPathResource("/files/output.mp3");
       // var audioFile = new ClassPathResource("/files/hello.mp3");
        Media media = new Media(new MimeType("audio", "mpeg"), audioFile);
        DashScopeChatOptions options = DashScopeChatOptions.builder().
                withMultiModel(true).
                withModel("qwen-omni-turbo").build();

        Prompt prompt= Prompt.builder().chatOptions(options)
                .messages(UserMessage.builder().media(media)
                        .metadata(Map.of(DashScopeApiConstants.MESSAGE_FORMAT, MessageFormat.VIDEO))
                        .text("识别语音文件").build())
                .build();
        ChatResponse response = dashScopeChatModel.call(prompt);
        System.out.println(response.getResult().getOutput().getText());
        return response.getResult().getOutput().getText();
    }

    @GetMapping("/simple/mult2")
    public String mult2 () {
        // flac、mp3、mp4、mpeg、mpga、m4a、ogg、wav 或 webm。
        var audioFile = new ClassPathResource("/files/xushu.jpg");
        // var audioFile = new ClassPathResource("/files/hello.mp3");
        Media media = new Media(MimeTypeUtils.IMAGE_JPEG, audioFile);
        DashScopeChatOptions options = DashScopeChatOptions.builder().
                withMultiModel(true)
                .withModel("qwen-vl-max-latest").build();

        Prompt prompt= Prompt.builder().chatOptions(options)
                .messages(UserMessage.builder().media(media)
                        .text("识别图片").build())
                .build();
        ChatResponse response = dashScopeChatModel.call(prompt);
        System.out.println(response.getResult().getOutput().getText());
        return response.getResult().getOutput().getText();
    }
}

http://localhost:8082/openai/simple/mult