2. Spring AI 快速入门使用

柠裳發表於 2025-9-23 11:23:00

<h1 id="2-spring-ai-快速入门使用">2. Spring AI 快速入门使用</h1>
<p>@</p><div class="toc"><div class="toc-container-header">目录</div><ul><li>2. Spring AI 快速入门使用<ul><li>快速使用<ul><li>接入deepseek<ul><li>流式对话</li><li>options配置选项<ul><li>temperature（温度）<ul><li>建议</li></ul></li><li><font style="color: rgba(6, 8, 31, 0.88)">maxTokens </font></li><li>stop</li><li>模型推理</li></ul></li><li>原理：</li></ul></li><li>接入阿里百炼<ul><li>使用</li><li>文生图</li><li>文生语音text2audio</li><li>语音翻译audio2text</li><li>多模态</li><li>文生视频（更多功能）</li></ul></li></ul></li></ul></li><li>最后：</li></ul></div><p></p>
<h2 id="快速使用">快速使用</h2>
<ol>
<li>创建项目</li>
</ol>
<p><img alt="" loading="lazy" src="https://img2024.cnblogs.com/blog/3084824/202509/3084824-20250923112310841-499614854.png" class="lazyload"></p>
<pre><code class="language-xml"><?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>3.4.5</version>
   <relativePath/> 
</parent>
<groupId>com.xs</groupId>
<artifactId>spring-ai-GA</artifactId>
<version>0.0.1-SNAPSHOT</version>
<name>spring-ai-GA</name>
<properties>
   <java.version>17</java.version>
   <spring-ai.version>1.0.0</spring-ai.version>
</properties>
<dependencies>
   <dependency>
         <groupId>org.springframework.boot</groupId>
         <artifactId>spring-boot-starter-web</artifactId>
   </dependency>

   <dependency>
         <groupId>org.springframework.boot</groupId>
         <artifactId>spring-boot-starter-test</artifactId>
         <scope>test</scope>
   </dependency>
</dependencies>
<dependencyManagement>
   <dependencies>
      
         <dependency>
            <groupId>org.springframework.ai</groupId>
            <artifactId>spring-ai-bom</artifactId>
            <version>${spring-ai.version}</version>
            <type>pom</type>
            <scope>import</scope>
         </dependency>
   </dependencies>
</dependencyManagement>

<build>
   <plugins>
         <plugin>
            <groupId>org.springframework.boot</groupId>
            <artifactId>spring-boot-maven-plugin</artifactId>
         </plugin>
   </plugins>
</build>

</project>
</code></pre>
<h3 id="接入deepseek">接入deepseek</h3>
<ol>
<li>依赖</li>
</ol>
<pre><code class="language-xml">    <dependency>
         <groupId>org.springframework.ai</groupId>
         <artifactId>spring-ai-starter-model-deepseek</artifactId>
   </dependency>
</code></pre>
<ol>
<li>获取deepseek api-key</li>
</ol>
<ul>
<li><strong><font style="color: rgba(6, 8, 31, 0.88)">API Key</font></strong><font style="color: rgba(6, 8, 31, 0.88)">：需从 DeepSeek 创建并获取 API 密钥：</font>https://platform.deepseek.com/api_keys</li>
</ul>
<p><img alt="" loading="lazy" src="https://img2024.cnblogs.com/blog/3084824/202509/3084824-20250923112310963-1170423557.png" class="lazyload"></p>
<p><img alt="" loading="lazy" src="https://img2024.cnblogs.com/blog/3084824/202509/3084824-20250923112310849-524647092.png" class="lazyload"></p>
<ol>
<li>配置</li>
</ol>
<pre><code class="language-yaml">spring:
ai:
deepseek:
   api-key: ${DEEP_SEEK_KEY}
   chat:
   options:
      model: deepseek-chat
</code></pre>
<ol>
<li>测试</li>
</ol>
<p>spring-ai-starter-model-deepseek</artifactid> 会为你增加自动配置类，其中DeepSeekChatModel这个就是专门负责智能对话的。</p>
<pre><code class="language-java">package com.xs.springaiga;

import org.junit.jupiter.api.Test;
import org.springframework.ai.deepseek.DeepSeekChatModel;
import org.springframework.beans.factory.annotation.Autowired;
import org.springframework.boot.test.context.SpringBootTest;

@SpringBootTest
public class DeepseelTest {

@Test
public void testChat(@Autowired
                     DeepSeekChatModel chatModel) {
   String call = chatModel.call("你是谁");
   System.out.println(call);
}
}
</code></pre>
<p><img alt="" loading="lazy" src="https://img2024.cnblogs.com/blog/3084824/202509/3084824-20250923112310848-217712612.png" class="lazyload"></p>
<p>上述是一种阻塞输出方式，就是要等服务器全部处理完了，才会被响应出来。</p>
<h4 id="流式对话">流式对话</h4>
<pre><code class="language-java">@Test
public void testChat2(@Autowired
                     DeepSeekChatModel chatModel) {

   Flux<String> stream = chatModel.stream("你是谁");
   // 流式输出
   stream.toIterable().forEach(System.out::print);
}
</code></pre>
<p>流式输出，就是服务器接受到一点，就输出一点</p>
<h4 id="options配置选项">options配置选项</h4>
<h5 id="temperature温度">temperature（温度）</h5>
<p>0-2 浮点数值</p>
<p><strong><font style="color: rgba(223, 42, 63, 1)">数值越高</font></strong> 更有创造性热情</p>
<p><font style="color: rgba(47, 142, 244, 1)">数值越低</font> 保守</p>
<pre><code class="language-java">@Test
public void testChatOptions(@Autowired
                        DeepSeekChatModel chatModel) {
DeepSeekChatOptions options = DeepSeekChatOptions.builder()
                           .temperature(1.9d).build();
ChatResponse res = chatModel.call(new Prompt("请写一句诗描述清晨。", options));
System.out.println(res.getResult().getOutput().getText());
}
</code></pre>
<p>也可以通过配置文件配置</p>
<pre><code class="language-properties">spring.ai.deepseek.chat.options.temperature=0.8
</code></pre>
<p>temperature:0.2 规规矩矩，像是被应试教育出来的老实学生没有创造力</p>
<p><img alt="" loading="lazy" src="https://img2024.cnblogs.com/blog/3084824/202509/3084824-20250923112310836-2061795658.png" class="lazyload"></p>
<p>temperature:1.9 可以看出来表现欲更强，像是一个在领导面前想要表现的你.<img alt="" loading="lazy" src="https://img2024.cnblogs.com/blog/3084824/202509/3084824-20250923112310829-282140112.png" class="lazyload"></p>
<p>也可以通过提示词降低他的主观臆想：</p>
<ul>
<li><font style="color: rgba(6, 8, 31, 0.88); background-color: rgba(192, 221, 252, 0.5)">只引用可靠来源中的信息，不做任何假设或扩展描述。</font></li>
<li><font style="color: rgba(6, 8, 31, 0.88); background-color: rgba(192, 221, 252, 0.5)">请只基于已知事实回答，不要主观</font><font style="background-color: rgba(192, 221, 252, 0.5)">臆想</font><font style="color: rgba(6, 8, 31, 0.88); background-color: rgba(192, 221, 252, 0.5)">或添加额外内容。</font></li>
<li><font style="color: rgba(6, 8, 31, 0.88); background-color: rgba(192, 221, 252, 0.5)">请简明、客观地给出答案，不要进行修饰或补充未经请求的信息。</font></li>
</ul>
<h6 id="建议">建议</h6>
<table>
<thead>
<tr>
<th style="text-align: center"><strong><font style="color: rgba(6, 8, 31, 0.88)">temperature 范围</font></strong></th>
<th style="text-align: left"><strong><font style="color: rgba(6, 8, 31, 0.88)">建议业务场景</font></strong></th>
<th style="text-align: left"><strong><font style="color: rgba(6, 8, 31, 0.88)">输出风格</font></strong></th>
<th style="text-align: left"><strong><font style="color: rgba(6, 8, 31, 0.88)">说明/应用举例</font></strong></th>
</tr>
</thead>
<tbody>
<tr>
<td style="text-align: center"><font style="color: rgba(6, 8, 31, 0.88)">0.0 ~ 0.2</font></td>
<td style="text-align: left"><font style="color: rgba(6, 8, 31, 0.88)">严谨问答、代码补全、数学答题</font></td>
<td style="text-align: left"><font style="color: rgba(6, 8, 31, 0.88)">严格、确定、标准</font></td>
<td style="text-align: left"><font style="color: rgba(6, 8, 31, 0.88)">法律/金融答题、接口返回模板、考试答卷等</font></td>
</tr>
<tr>
<td style="text-align: center"><font style="color: rgba(6, 8, 31, 0.88)">0.3 ~ 0.6</font></td>
<td style="text-align: left"><font style="color: rgba(6, 8, 31, 0.88)">聊天机器人、日常摘要、辅助写作</font></td>
<td style="text-align: left"><font style="color: rgba(6, 8, 31, 0.88)">稍有变化、较稳妥</font></td>
<td style="text-align: left"><font style="color: rgba(6, 8, 31, 0.88)">公众号摘要、普通对话、邮件生成等</font></td>
</tr>
<tr>
<td style="text-align: center"><font style="color: rgba(6, 8, 31, 0.88)">0.7 ~ 1.0</font></td>
<td style="text-align: left"><font style="color: rgba(6, 8, 31, 0.88)">创作内容、广告文案、标题生成</font></td>
<td style="text-align: left"><font style="color: rgba(6, 8, 31, 0.88)">丰富、有创意、灵活</font></td>
<td style="text-align: left"><font style="color: rgba(6, 8, 31, 0.88)">诗歌、短文案、趣味对话、产品描述等</font></td>
</tr>
<tr>
<td style="text-align: center"><font style="color: rgba(6, 8, 31, 0.88)">1.1 ~ 1.5</font></td>
<td style="text-align: left"><font style="color: rgba(6, 8, 31, 0.88)">脑洞风格、头脑风暴、灵感碰撞场景</font></td>
<td style="text-align: left"><font style="color: rgba(6, 8, 31, 0.88)">大开脑洞、变化极强</font></td>
<td style="text-align: left"><font style="color: rgba(6, 8, 31, 0.88)">故事创作、异想天开的推荐语、多样化内容</font></td>
</tr>
</tbody>
</table>
<hr>
<p><strong><font style="color: rgba(6, 8, 31, 0.88)">说明：</font></strong></p>
<ul>
<li><font style="color: rgba(6, 8, 31, 0.88)">温度越低，输出越收敛和中规中矩；</font></li>
<li><font style="color: rgba(6, 8, 31, 0.88)">温度越高，输出越多变、富有惊喜但有风险；</font></li>
<li><font style="color: rgba(6, 8, 31, 0.88)">实战用法一般建议选 </font><strong><font style="color: rgba(6, 8, 31, 0.88)">0.5~0.8</font></strong><font style="color: rgba(6, 8, 31, 0.88)"> 作为日常生产起点，需要根据业务不断测试调整。</font></li>
</ul>
<h5 id="maxtokens-"><font style="color: rgba(6, 8, 31, 0.88)">maxTokens </font></h5>
<p>默认低 token</p>
<p><code>maxTokens</code>: 限制AI模型生成的最大token数（近似理解为字数上限）。</p>
<ul>
<li><font style="color: rgba(6, 8, 31, 0.88)">需要简洁回复、打分、列表、短摘要等，建议小值（如10~50）。</font></li>
<li><font style="color: rgba(6, 8, 31, 0.88)">防止用户跑长对话导致无关内容或花费过多token费用。</font></li>
<li><font style="color: rgba(6, 8, 31, 0.88)">如果遇到生成内容经常被截断，可以适当配置更大maxTokens。</font></li>
</ul>
<h5 id="stop">stop</h5>
<p>截断你不想输出的内容比如：</p>
<pre><code class="language-yaml">spring:
ai:
deepseek:
   api-key: ${DEEP_SEEK_KEY}
   chat:
   options:
      model: deepseek-chat
      max-tokens: 20
      stop:
         - "\n" #只想一行
         - "。" #只想一句话
         - "政治"#敏感词
         - "最后最总结一下"#这种AI惯用的模板词，减少AI词汇，让文章更拟人
</code></pre>
<h5 id="模型推理">模型推理</h5>
<p>设置深度思考，思考的内容有个专业名词叫：<font style="color: rgba(25, 30, 30, 1)">Chain of Thought (CoT)</font></p>
<p><img alt="" loading="lazy" src="https://img2024.cnblogs.com/blog/3084824/202509/3084824-20250923112310860-656421391.png" class="lazyload"></p>
<p>在deepseek中， deepseek-reasoner模型是深度思考模型：</p>
<p><img alt="" loading="lazy" src="https://img2024.cnblogs.com/blog/3084824/202509/3084824-20250923112310883-965329067.png" class="lazyload"></p>
<pre><code class="language-java">@Test
public void deepSeekReasonerExample(@Autowired DeepSeekChatModel deepSeekChatModel) {
   DeepSeekChatOptions options = DeepSeekChatOptions.builder()
            .model("deepseek-reasoner").build();

   Prompt prompt = new Prompt("请写一句诗描述清晨。", options);
   ChatResponse res = deepSeekChatModel.call(prompt);

   DeepSeekAssistantMessage assistantMessage =(DeepSeekAssistantMessage)res.getResult().getOutput();

   String reasoningContent = assistantMessage.getReasoningContent();
   String content = assistantMessage.getText();

   System.out.println(reasoningContent);
   System.out.println("--------------------------------------------");
   System.out.println(content);

}

@Test
public void deepSeekReasonerStreamExample(@Autowired DeepSeekChatModel deepSeekChatModel) {
   DeepSeekChatOptions options = DeepSeekChatOptions.builder()
            .model("deepseek-reasoner").build();

   Prompt prompt = new Prompt("请写一句诗描述清晨。", options);
   Flux<ChatResponse> stream = deepSeekChatModel.stream(prompt);

   stream.toIterable().forEach(res -> {
         DeepSeekAssistantMessage assistantMessage =(DeepSeekAssistantMessage)res.getResult().getOutput();
         String reasoningContent = assistantMessage.getReasoningContent();
         System.out.print(reasoningContent);
   });
   System.out.println("--------------------------------------------");
   stream.toIterable().forEach(res -> {
         DeepSeekAssistantMessage assistantMessage =(DeepSeekAssistantMessage)res.getResult().getOutput();
         String content = assistantMessage.getText();
         System.out.print(content);
   });

}
</code></pre>
<p>也可以在配置文件中配置</p>
<pre><code class="language-properties">spring.ai.deepseek.chat.options.model= deepseek-reasoner
</code></pre>
<h4 id="原理">原理：</h4>
<p><img alt="" loading="lazy" src="https://img2024.cnblogs.com/blog/3084824/202509/3084824-20250923112310829-1111134963.png" class="lazyload"></p>
<ol>
<li>当调用chatModel.call</li>
</ol>
<pre><code class="language-java">default String call(String message) {
Prompt prompt = new Prompt(new UserMessage(message));
Generation generation = call(prompt).getResult();
return (generation != null) ? generation.getOutput().getText() : "";
}
</code></pre>
<pre><code>1. 首先会将提示词解析到Prompt对象中（用于远程请求的messages）
</code></pre>
<p><img alt="" loading="lazy" src="https://img2024.cnblogs.com/blog/3084824/202509/3084824-20250923112310816-235675555.png" class="lazyload"></p>
<ol>
<li>调用deepseekModel#call---> internalCall方法</li>
</ol>
<pre><code class="language-java">public ChatResponse internalCall(Prompt prompt, ChatResponse previousChatResponse) {

// a
ChatCompletionRequest request = createRequest(prompt, false);

//..省略
ResponseEntity<ChatCompletion> completionEntity = this.retryTemplate
// b
.execute(ctx -> this.deepSeekApi.chatCompletionEntity(request));

var chatCompletion = completionEntity.getBody();
//..省略
ChatResponse chatResponse = new ChatResponse(generations,
                                             from(completionEntity.getBody(), accumulatedUsage));

observationContext.setResponse(chatResponse);

return chatResponse;
//.. 省略
return response;
}
</code></pre>
<pre><code>1. 通过createRequest封装为远程请求所需的json对象
2. 通过spring retry 重试机制去远程请求
</code></pre>
<p>deepseekthis.deepSeekApi.chatCompletionEntity(request)</p>
<pre><code class="language-java">// 通过restClient 进行远程请求
public ResponseEntity<ChatCompletion> chatCompletionEntity(ChatCompletionRequest chatRequest) {

return this.restClient.post()
.uri(this.getEndpoint(chatRequest))
.body(chatRequest)
.retrieve()
.toEntity(ChatCompletion.class);
}
</code></pre>
<pre><code>1. 封装响应数据
</code></pre>
<h3 id="接入阿里百炼">接入阿里百炼</h3>
<p>https://bailian.console.aliyun.com/?tab=home#/home</p>
<p><img alt="" loading="lazy" src="https://img2024.cnblogs.com/blog/3084824/202509/3084824-20250923112310893-283496480.png" class="lazyload"></p>
<p>阿里自己的团队维护spring-ai-alibaba. 但是也必须依赖spring-ai 。好处是扩展度更高，坏处是必须是springai先出来， spring-ai-alibaba.延迟几天出来。</p>
<p>如果需要接入阿里的百炼平台，就必须用该组件</p>
<h4 id="使用">使用</h4>
<ol>
<li>申请api-key</li>
</ol>
<p><font style="color: rgba(24, 24, 24, 1)">在调用前，您需要</font>开通模型服务并获取API Key<font style="color: rgba(24, 24, 24, 1)">，再</font>配置API Key到环境变量<font style="color: rgba(24, 24, 24, 1)">。</font></p>
<ol>
<li>依赖</li>
</ol>
<pre><code class="language-xml"><dependencyManagement>
<dependencies>

<dependency>
   <groupId>com.alibaba.cloud.ai</groupId>
   <artifactId>spring-ai-alibaba-bom</artifactId>
   <version>1.0.0.2</version>
   <type>pom</type>
   <scope>import</scope>
</dependency>
</dependencies>
</dependencyManagement>

<dependencies>

<dependency>
<groupId>com.alibaba.cloud.ai</groupId>
<artifactId>spring-ai-alibaba-starter-dashscope</artifactId>
</dependency>
</dependencies>
</code></pre>
<ol>
<li>配置</li>
</ol>
<p>不配置指定通义千问的模型名的话，也是会自动配置一个默认模型名。</p>
<pre><code class="language-yaml">spring:
ai:
dashscope:
   api-key: ${AI_DASHSCOPE_API_KEY}
</code></pre>
<ol>
<li>使用</li>
</ol>
<pre><code class="language-java">@Test
public void testQwen(@Autowired DashScopeChatModel dashScopeChatModel) {

   String content = dashScopeChatModel.call("你好你是谁");
   System.out.println(content);
}
</code></pre>
<h4 id="文生图">文生图</h4>
<pre><code class="language-java">@Test
public void text2Img(
   // 注意：这里是图片生成使用的是 DashScopeImageModel 也是被自动装配了。
      @Autowired DashScopeImageModel imageModel) {
   DashScopeImageOptions imageOptions = DashScopeImageOptions.builder()
            .withModel("wanx2.1-t2i-turbo").build();// 构建配置项

   // 返回一个图片想 Response 返回类
   ImageResponse imageResponse = imageModel.call(
            new ImagePrompt("小兔子", imageOptions));
   String imageUrl = imageResponse.getResult().getOutput().getUrl();

   // 图片url
   System.out.println(imageUrl);

   // 图片base64
   // imageResponse.getResult().getOutput().getB64Json();

   /*
   按文件流相应
   InputStream in = url.openStream();

   response.setHeader("Content-Type", MediaType.IMAGE_PNG_VALUE);
   response.getOutputStream().write(in.readAllBytes());
   response.getOutputStream().flush();*/
}
</code></pre>
<h4 id="文生语音text2audio">文生语音text2audio</h4>
<pre><code class="language-java">
// https://bailian.console.aliyun.com/?spm=5176.29619931.J__Z58Z6CX7MY__Ll8p1ZOR.1.74cd59fcXOTaDL&tab=doc#/doc/?type=model&url=https%3A%2F%2Fhelp.aliyun.com%2Fdocument_detail%2F2842586.html&renderType=iframe
@Test
public void testText2Audio(
   //DashScopeSpeechSynthesisModel 自动装配生成语言类
   @Autowired DashScopeSpeechSynthesisModel speechSynthesisModel) throws IOException {
   // 语言配置项，.出来
   DashScopeSpeechSynthesisOptions options = DashScopeSpeechSynthesisOptions.builder()
            //.voice() // 人声
            //.speed() // 语速
            //.model() // 模型
            //.responseFormat(DashScopeSpeechSynthesisApi.ResponseFormat.MP3)
            .build();

   SpeechSynthesisResponse response = speechSynthesisModel.call(
            new SpeechSynthesisPrompt("大家好，我是李华。",options)
   );

   File file = new File( System.getProperty("user.dir") + "/output.mp3");
   try (FileOutputStream fos = new FileOutputStream(file)) {
         // 响应的语言的二进制流
         ByteBuffer byteBuffer = response.getResult().getOutput().getAudio();
         // 保存到我们,根路径下
         fos.write(byteBuffer.array());
   }
   catch (IOException e) {
         throw new IOException(e.getMessage());
   }
}
</code></pre>
<h4 id="语音翻译audio2text">语音翻译audio2text</h4>
<pre><code class="language-java">// 这个设置的是一个远程的 url 文本内容
private static final String AUDIO_RESOURCES_URL = "https://dashscope.oss-cn-beijing.aliyuncs.com/samples/audio/paraformer/hello_world_female2.wav";

@Test
public void testAudio2Text(
         @Autowired
         DashScopeAudioTranscriptionModel transcriptionModel
) throws MalformedURLException {
   DashScopeAudioTranscriptionOptions transcriptionOptions = DashScopeAudioTranscriptionOptions.builder()
            //.withModel() 模型
            .build();
   AudioTranscriptionPrompt prompt = new AudioTranscriptionPrompt(
            new UrlResource(AUDIO_RESOURCES_URL),
            transcriptionOptions
   );
   AudioTranscriptionResponse response = transcriptionModel.call(
            prompt
   );

   System.out.println(response.getResult().getOutput());

}
</code></pre>
<h4 id="多模态">多模态</h4>
<p>图片，语音，视频传给大模型让大模型识别，理解其中的内容。</p>
<pre><code class="language-java">@Test
public void testMultimodal(@Autowired DashScopeChatModel dashScopeChatModel
                     ) throws MalformedURLException {
// flac、mp3、mp4、mpeg、mpga、m4a、ogg、wav 或 webm。
var audioFile = new ClassPathResource("/files/xushu.png");

// MimeTypeUtils.IMAGE_JPEG 表示我们传递的文件类型
Media media = new Media(MimeTypeUtils.IMAGE_JPEG, audioFile);
DashScopeChatOptions options = DashScopeChatOptions.builder()
.withMultiModel(true)// 使用多模态要设置为 true
.withModel("qwen-vl-max-latest").build();

Promptprompt= Prompt.builder().chatOptions(options)
.messages(UserMessage.builder().media(media)
         // 设置提示词为“识别图片”
         .text("识别图片").build())
.build();
ChatResponse response = dashScopeChatModel.call(prompt);

System.out.println(response.getResult().getOutput().getText());
}
</code></pre>
<h4 id="文生视频更多功能">文生视频（更多功能）</h4>
<p>因为这里的 Spring AI 目前并没有提供文生视频的 Modles 内容，需要接入第三方的依赖，使用第三方 API。</p>
<pre><code class="language-xml"><dependency>
<groupId>com.alibaba</groupId>
<artifactId>dashscope-sdk-java</artifactId>

<version>the-latest-version</version>
<version>2.20.6</version>
</dependency>
</code></pre>
<pre><code class="language-java">@Test
public void text2Video() throws ApiException, NoApiKeyException, InputRequiredException {
   VideoSynthesis vs = new VideoSynthesis();
   VideoSynthesisParam param =
            VideoSynthesisParam.builder()
                     .model("wanx2.1-t2v-turbo")
                     .prompt("一只小猫在月光下奔跑")
                     .size("1280*720")
         // 因为这里我们接入的是第三方API，对应的key并没有采用application.yaml的配置
      // 所以需要我们手动，System.getenv() 获取到环境变量当中的key值
                     .apiKey(System.getenv("ALI_AI_KEY"))
                     .build();
   System.out.println("please wait...");
   VideoSynthesisResult result = vs.call(param);
   System.out.println(result.getOutput().getVideoUrl());
}
</code></pre>
<p>更多的内容可以去参考阿里云百炼广场 https://bailian.console.aliyun.com/?tab=home#/home 当中的 SDK，以及提供的一些 Demo 进行配置操作。</p>
<h1 id="最后">最后：</h1>
<blockquote>
<p>“在这个最后的篇章中，我要表达我对每一位读者的感激之情。你们的关注和回复是我创作的动力源泉，我从你们身上吸取了无尽的灵感与勇气。我会将你们的鼓励留在心底，继续在其他的领域奋斗。感谢你们，我们总会在某个时刻再次相遇。”</p>
<p><img alt="在这里插入图片描述" loading="lazy" src="https://img2024.cnblogs.com/blog/3084824/202509/3084824-20250923112310849-921022573.gif" class="lazyload"></p>
</blockquote><br><br>
来源：https://www.cnblogs.com/TheMagicalRainbowSea/p/19106841

頁: [1]

琼殿技术论坛's Archiver

2. Spring AI 快速入门使用