Using Spring AI to Access Deepseek Through Alibaba Cloud Model Studio - 拾光赋-拾光赋

Using Spring AI to Access Deepseek Through Alibaba Cloud Model Studio

18天前发布

04814

One day when I check the maven BOM of Spring-AI, I found a Springboot starter for Spring AI to access Dashscope, which was the former name of Alibaba Cloud Model Studio.

But the doc of Spring AI didn’t announce that, so, let’s learn to use it.

Spring AI need your jdk version >= 17

1. Apply a Api-key on Alibaba Cloud Model Studio

Alibaba Cloud Model Studio – Alibaba Cloud

A one-stop generative AI platform to build intelligent applications that understand your business, based on Qwen and other popular models

alibabacloud.com

2. Import Spring-AI

This is a new Springboot maven project

Add Spring Milestone and Snapshot Repositories

You will need to add Spring milestone and snapshot repositories to your build system. Because Spring didn’t publish it to maven center repository.


<span><repositories></span>
    <span><repository></span>
        <span><id></span>spring-milestones<span></id></span>
        <span><name></span>Spring Milestones<span></name></span>
        <span><url></span>https://repo.spring.io/milestone<span></url></span>
        <span><snapshots></span>
            <span><enabled></span>false<span></enabled></span>
        <span></snapshots></span>
    <span></repository></span>
    <span><repository></span>
        <span><id></span>spring-snapshots<span></id></span>
        <span><name></span>Spring Snapshots<span></name></span>
        <span><url></span>https://repo.spring.io/snapshot<span></url></span>
        <span><releases></span>
            <span><enabled></span>false<span></enabled></span>
        <span></releases></span>
    <span></repository></span>
<span></repositories></span>
<span><repositories></span>
    <span><repository></span>
        <span><id></span>spring-milestones<span></id></span>
        <span><name></span>Spring Milestones<span></name></span>
        <span><url></span>https://repo.spring.io/milestone<span></url></span>
        <span><snapshots></span>
            <span><enabled></span>false<span></enabled></span>
        <span></snapshots></span>
    <span></repository></span>
    <span><repository></span>
        <span><id></span>spring-snapshots<span></id></span>
        <span><name></span>Spring Snapshots<span></name></span>
        <span><url></span>https://repo.spring.io/snapshot<span></url></span>
        <span><releases></span>
            <span><enabled></span>false<span></enabled></span>
        <span></releases></span>
    <span></repository></span>
<span></repositories></span>
<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>
</repositories>

Enter fullscreen mode Exit fullscreen mode

Import Spring AI BOM to Manage the Version of Spring AI


<span><dependencyManagement></span>
    <span><dependencies></span>
        <span><dependency></span>
            <span><groupId></span>group.springframework.ai<span></groupId></span>
            <span><artifactId></span>spring-ai-bom<span></artifactId></span>
            <span><version></span>${spring-ai.version}<span></version></span>
            <span><type></span>pom<span></type></span>
            <span><scope></span>import<span></scope></span>
        <span></dependency></span>
        <span><dependency></span>
            <span><groupId></span>org.springframework.boot<span></groupId></span>
            <span><artifactId></span>spring-boot-dependencies<span></artifactId></span>
            <span><version></span>3.3.4<span></version></span>
            <span><type></span>pom<span></type></span>
            <span><scope></span>import<span></scope></span>
        <span></dependency></span>
    <span></dependencies></span>
<span></dependencyManagement></span>
<span><dependencyManagement></span>
    <span><dependencies></span>
        <span><dependency></span>
            <span><groupId></span>group.springframework.ai<span></groupId></span>
            <span><artifactId></span>spring-ai-bom<span></artifactId></span>
            <span><version></span>${spring-ai.version}<span></version></span>
            <span><type></span>pom<span></type></span>
            <span><scope></span>import<span></scope></span>
        <span></dependency></span>
        <span><dependency></span>
            <span><groupId></span>org.springframework.boot<span></groupId></span>
            <span><artifactId></span>spring-boot-dependencies<span></artifactId></span>
            <span><version></span>3.3.4<span></version></span>
            <span><type></span>pom<span></type></span>
            <span><scope></span>import<span></scope></span>
        <span></dependency></span>
    <span></dependencies></span>
<span></dependencyManagement></span>
<dependencyManagement>
    <dependencies>
        <dependency>
            <groupId>group.springframework.ai</groupId>
            <artifactId>spring-ai-bom</artifactId>
            <version>${spring-ai.version}</version>
            <type>pom</type>
            <scope>import</scope>
        </dependency>
        <dependency>
            <groupId>org.springframework.boot</groupId>
            <artifactId>spring-boot-dependencies</artifactId>
            <version>3.3.4</version>
            <type>pom</type>
            <scope>import</scope>
        </dependency>
    </dependencies>
</dependencyManagement>

Enter fullscreen mode Exit fullscreen mode

Add spring-ai-dashscope-spring-boot-starter and Some Assistant Package


<span><dependencies></span>
    <span><dependency></span>
        <span><groupId></span>org.springframework.boot<span></groupId></span>
        <span><artifactId></span>spring-boot-starter-web<span></artifactId></span>
    <span></dependency></span>
    <span><dependency></span>
        <span><groupId></span>org.projectlombok<span></groupId></span>
        <span><artifactId></span>lombok<span></artifactId></span>
        <span><optional></span>true<span></optional></span>
    <span></dependency></span>
    <span><dependency></span>
        <span><groupId></span>org.springframework.boot<span></groupId></span>
        <span><artifactId></span>spring-boot-starter-test<span></artifactId></span>
        <span><scope></span>test<span></scope></span>
    <span></dependency></span>
    <span><dependency></span>
        <span><groupId></span>group.springframework.ai<span></groupId></span>
        <span><artifactId></span>spring-ai-dashscope-spring-boot-starter<span></artifactId></span>
    <span></dependency></span>
<span></dependencies></span>
<span><dependencies></span>
    <span><dependency></span>
        <span><groupId></span>org.springframework.boot<span></groupId></span>
        <span><artifactId></span>spring-boot-starter-web<span></artifactId></span>
    <span></dependency></span>
    <span><dependency></span>
        <span><groupId></span>org.projectlombok<span></groupId></span>
        <span><artifactId></span>lombok<span></artifactId></span>
        <span><optional></span>true<span></optional></span>
    <span></dependency></span>
    <span><dependency></span>
        <span><groupId></span>org.springframework.boot<span></groupId></span>
        <span><artifactId></span>spring-boot-starter-test<span></artifactId></span>
        <span><scope></span>test<span></scope></span>
    <span></dependency></span>
    <span><dependency></span>
        <span><groupId></span>group.springframework.ai<span></groupId></span>
        <span><artifactId></span>spring-ai-dashscope-spring-boot-starter<span></artifactId></span>
    <span></dependency></span>
<span></dependencies></span>
<dependencies>
    <dependency>
        <groupId>org.springframework.boot</groupId>
        <artifactId>spring-boot-starter-web</artifactId>
    </dependency>
    <dependency>
        <groupId>org.projectlombok</groupId>
        <artifactId>lombok</artifactId>
        <optional>true</optional>
    </dependency>
    <dependency>
        <groupId>org.springframework.boot</groupId>
        <artifactId>spring-boot-starter-test</artifactId>
        <scope>test</scope>
    </dependency>
    <dependency>
        <groupId>group.springframework.ai</groupId>
        <artifactId>spring-ai-dashscope-spring-boot-starter</artifactId>
    </dependency>
</dependencies>

Enter fullscreen mode Exit fullscreen mode

3. Write `application.yaml`


<span>spring</span><span>:</span>
  <span>ai</span><span>:</span>
    <span>dashscope</span><span>:</span>
      <span># DashScope API Key</span>
      <span>api-key</span><span>:</span> <span># TODO</span>
      <span>chat</span><span>:</span>
        <span>options</span><span>:</span>
          <span># choose the model you want to use</span>
          <span>model</span><span>:</span> <span>deepseek-v3</span>
          <span># temperature is the probability of the model to generate a new word, 0.7 is the default value</span>
          <span>temperature</span><span>:</span> <span>0.7</span>
<span>logging</span><span>:</span>
  <span>level</span><span>:</span>
    <span>root</span><span>:</span> <span>info</span>
    <span># if you want to check the log of Spring AI, you need enable this config</span>
<span># org.springframework: debug</span>
<span>server</span><span>:</span>
  <span>port</span><span>:</span> <span>9090</span>
<span>spring</span><span>:</span>
  <span>ai</span><span>:</span>
    <span>dashscope</span><span>:</span>
      <span># DashScope API Key</span>
      <span>api-key</span><span>:</span> <span># TODO</span>
      <span>chat</span><span>:</span>
        <span>options</span><span>:</span>
          <span># choose the model you want to use</span>
          <span>model</span><span>:</span> <span>deepseek-v3</span>
          <span># temperature is the probability of the model to generate a new word, 0.7 is the default value</span>
          <span>temperature</span><span>:</span> <span>0.7</span>

<span>logging</span><span>:</span>
  <span>level</span><span>:</span>
    <span>root</span><span>:</span> <span>info</span>
    <span># if you want to check the log of Spring AI, you need enable this config</span>
<span># org.springframework: debug</span>
<span>server</span><span>:</span>
  <span>port</span><span>:</span> <span>9090</span>
spring:
  ai:
    dashscope:
      # DashScope API Key
      api-key: # TODO
      chat:
        options:
          # choose the model you want to use
          model: deepseek-v3
          # temperature is the probability of the model to generate a new word, 0.7 is the default value
          temperature: 0.7

logging:
  level:
    root: info
    # if you want to check the log of Spring AI, you need enable this config
# org.springframework: debug
server:
  port: 9090

Enter fullscreen mode Exit fullscreen mode

The value of temperature you can fellow the advice of deepseek

4. Register `ChatClient` as a Spring Bean


<span>@Configuration</span>
<span>public</span> <span>class</span> <span>SpringAiConfig</span> <span>{</span>
    <span>@Autowired</span>
    <span>private</span> <span>ChatModel</span> <span>chatModel</span><span>;</span>
    <span>@Bean</span>
    <span>public</span> <span>ChatClient</span> <span>chatClient</span><span>()</span> <span>{</span>
        <span>return</span> <span>ChatClient</span><span>.</span><span>builder</span><span>(</span><span>chatModel</span><span>)</span>
                <span>// Set default system prompt</span>
                <span>.</span><span>defaultSystem</span><span>(</span><span>""" Imitate Max Verstappen's tone date of today is {current_date} """</span><span>)</span>
                <span>.</span><span>build</span><span>();</span>
    <span>}</span>
<span>}</span>
<span>@Configuration</span>
<span>public</span> <span>class</span> <span>SpringAiConfig</span> <span>{</span>

    <span>@Autowired</span>
    <span>private</span> <span>ChatModel</span> <span>chatModel</span><span>;</span>

    <span>@Bean</span>
    <span>public</span> <span>ChatClient</span> <span>chatClient</span><span>()</span> <span>{</span>
        <span>return</span> <span>ChatClient</span><span>.</span><span>builder</span><span>(</span><span>chatModel</span><span>)</span>
                <span>// Set default system prompt</span>
                <span>.</span><span>defaultSystem</span><span>(</span><span>""" Imitate Max Verstappen's tone date of today is {current_date} """</span><span>)</span>
                <span>.</span><span>build</span><span>();</span>
    <span>}</span>
<span>}</span>
@Configuration
public class SpringAiConfig {

    @Autowired
    private ChatModel chatModel;

    @Bean
    public ChatClient chatClient() {
        return ChatClient.builder(chatModel)
                // Set default system prompt
                .defaultSystem(""" Imitate Max Verstappen's tone date of today is {current_date} """)
                .build();
    }
}

Enter fullscreen mode Exit fullscreen mode

Then you can use ChatClient to access AI model

5. Test `ChatClient`

I create a controller to test ChatClient, All test will based on web request to access.


<span>@RestController</span>
<span>@RequiredArgsConstructor</span>
<span>@RequestMapping</span><span>(</span><span>"/ai"</span><span>)</span>
<span>@Slf4j</span>
<span>public</span> <span>class</span> <span>AiController</span> <span>{</span>
    <span>private</span> <span>final</span> <span>ChatClient</span> <span>chatClient</span><span>;</span>
<span>}</span>
<span>@RestController</span>
<span>@RequiredArgsConstructor</span>
<span>@RequestMapping</span><span>(</span><span>"/ai"</span><span>)</span>
<span>@Slf4j</span>
<span>public</span> <span>class</span> <span>AiController</span> <span>{</span>

    <span>private</span> <span>final</span> <span>ChatClient</span> <span>chatClient</span><span>;</span>

<span>}</span>
@RestController
@RequiredArgsConstructor
@RequestMapping("/ai")
@Slf4j
public class AiController {

    private final ChatClient chatClient;

}

Enter fullscreen mode Exit fullscreen mode

Let’s start Spring AI with a normal chat


<span>@GetMapping</span><span>(</span><span>"/chat"</span><span>)</span>
<span>public</span> <span>String</span> <span>chat</span><span>(</span><span>@RequestParam</span><span>(</span><span>value</span> <span>=</span> <span>"msg"</span><span>)</span> <span>String</span> <span>msg</span><span>)</span> <span>{</span>
    <span>log</span><span>.</span><span>info</span><span>(</span><span>"msg: {}"</span><span>,</span> <span>msg</span><span>);</span>
    <span>return</span> <span>chatClient</span><span>.</span><span>prompt</span><span>()</span>
            <span>.</span><span>user</span><span>(</span><span>msg</span><span>)</span>
            <span>// config default system's current date</span>
            <span>.</span><span>system</span><span>(</span><span>promptSystemSpec</span> <span>-></span> <span>promptSystemSpec</span><span>.</span><span>param</span><span>(</span><span>"current_date"</span><span>,</span> <span>LocalDateTime</span><span>.</span><span>now</span><span>()))</span>
            <span>.</span><span>call</span><span>()</span>
            <span>.</span><span>content</span><span>();</span>
<span>}</span>
<span>@GetMapping</span><span>(</span><span>"/chat"</span><span>)</span>
<span>public</span> <span>String</span> <span>chat</span><span>(</span><span>@RequestParam</span><span>(</span><span>value</span> <span>=</span> <span>"msg"</span><span>)</span> <span>String</span> <span>msg</span><span>)</span> <span>{</span>
    <span>log</span><span>.</span><span>info</span><span>(</span><span>"msg: {}"</span><span>,</span> <span>msg</span><span>);</span>
    <span>return</span> <span>chatClient</span><span>.</span><span>prompt</span><span>()</span>
            <span>.</span><span>user</span><span>(</span><span>msg</span><span>)</span>
            <span>// config default system's current date</span>
            <span>.</span><span>system</span><span>(</span><span>promptSystemSpec</span> <span>-></span> <span>promptSystemSpec</span><span>.</span><span>param</span><span>(</span><span>"current_date"</span><span>,</span> <span>LocalDateTime</span><span>.</span><span>now</span><span>()))</span>
            <span>.</span><span>call</span><span>()</span>
            <span>.</span><span>content</span><span>();</span>
<span>}</span>
@GetMapping("/chat")
public String chat(@RequestParam(value = "msg") String msg) {
    log.info("msg: {}", msg);
    return chatClient.prompt()
            .user(msg)
            // config default system's current date
            .system(promptSystemSpec -> promptSystemSpec.param("current_date", LocalDateTime.now()))
            .call()
            .content();
}

Enter fullscreen mode Exit fullscreen mode

Start the project and test it using postman

How amazing it is!!!

If you want to learn the advance of Spring AI, follow me and I will publish it later.

原文链接：Using Spring AI to Access Deepseek Through Alibaba Cloud Model Studio

展开阅读全文

© 版权声明

文章版权声明 1、本网站名称：拾光赋
2、本站永久网址：https://www.blogs.ink
3、本网站的文章部分内容可能来源于网络，仅供大家学习与参考，如有侵权，请联系站长QQ：805375623进行删除处理。
4、本站一切资源不代表本站立场，并不代表本站赞同其观点和对其真实性负责。
5、本站一律禁止以任何方式发布或转载任何违法的相关信息，访客发现请向站长举报
6、本站资源大多存储在云盘，如发现链接失效，请联系我们我们会第一时间更新。

THE END

Java（EN）
# java # AI # backend # web

喜欢就支持一下吧

Nothing in the world is difficult if you put your heart into it.

世上无难事，只怕有心人

相关推荐

评论抢沙发

请登录后发表评论

暂无评论内容