Spring AI Alibaba 快速入门指南

对于国内 Java 程序员来说，使用 Spring AI Alibaba 上手比较容易，申请一个阿里云百炼的 Key 就可以进行测试。

申请阿里云百炼 Api Key

访问阿里云百炼平台控制台，使用账号登录后，选择 模型服务 里面的 密钥管理。

创建 API Key，该 Key 将在后续开发中频繁使用。

项目搭建

项目结构

采用 Maven 多模块结构。

父 pom 文件

在父 pom 文件中做项目依赖包的版本管理。

<?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 http://maven.apache.org/xsd/maven-4.0.0.xsd">
    <modelVersion>4.0.0</modelVersion>
    <groupId>org.demo.ai</groupId>
    <artifactId>spring-ai-alibaba</artifactId>
    <version>${revision}</version>
    <packaging>pom</packaging>
    <description>Spring AI Alibaba Examples</description>
    <properties>
        <revision>1.0.0</revision>
        <java.version>17</java.version>
        <spring-ai.version>1.0.0</spring-ai.version>
        <spring-ai-alibaba.version>1.0.0.3</spring-ai-alibaba.version>
        <spring-boot.version>3.5.5</spring-boot.version>
    </properties>
    <modules>
        <module>boot-ai-helloworld</module>
    </modules>
    <dependencyManagement>
        <dependencies>
            <dependency>
                <groupId>org.springframework.boot</groupId>
                <artifactId>spring-boot-dependencies</artifactId>
                <version>${spring-boot.version}</version>
                <type>pom</type>
                <scope>import</scope>
            </dependency>
            <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>
    <repositories>
        <repository>
            <id>aliyunmaven</id>
            <name>aliyun</name>
            <url>https://maven.aliyun.com/repository/public</url>
        </repository>
    </repositories>
</project>

子模块 boot-ai-helloworld

子 pom 文件

<?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 http://maven.apache.org/xsd/maven-4.0.0.xsd">
    <modelVersion>4.0.0</modelVersion>
    <parent>
        <groupId>org.demo.ai</groupId>
        <artifactId>spring-ai-alibaba</artifactId>
        <version>${revision}</version>
        <relativePath>../pom.xml</relativePath>
    </parent>
    <artifactId>boot-ai-helloworld</artifactId>
    <version>${revision}</version>
    <dependencies>
        <dependency>
            <groupId>org.springframework.boot</groupId>
            <artifactId>spring-boot-starter-web</artifactId>
        </dependency>
        <dependency>
            <groupId>com.alibaba.cloud.ai</groupId>
            <artifactId>spring-ai-alibaba-starter-dashscope</artifactId>
        </dependency>
    </dependencies>
</project>

配置文件

server:
  port: 18080
spring:
  application:
    name: spring-ai-alibaba-helloworld
  ai:
    dashscope:
      api-key: {替换成阿里云百炼上的 API Key}

启动类

package org.demo.ai.bailian;

import org.springframework.boot.SpringApplication;
import org.springframework.boot.autoconfigure.SpringBootApplication;

@SpringBootApplication
public class BailianAgentApplication {
    public static void main(String[] args) {
        SpringApplication.run(BailianAgentApplication.class, args);
    }
}

Controller 层

使用 ChatClient 类与大模型交互。

package org.demo.ai.bailian.controller;

import com.alibaba.cloud.ai.dashscope.chat.DashScopeChatOptions;
import jakarta.servlet.http.HttpServletResponse;
import org.springframework.ai.chat.client.ChatClient;
import org.springframework.ai.chat.client.advisor.MessageChatMemoryAdvisor;
import org.springframework.ai.chat.client.advisor.SimpleLoggerAdvisor;
import org.springframework.ai.chat.memory.ChatMemory;
import org.springframework.ai.chat.memory.MessageWindowChatMemory;
import org.springframework.web.bind.annotation.*;
import reactor.core.publisher.Flux;

@RestController
@RequestMapping("/helloworld")
public class HelloworldController {

    private static final String DEFAULT_PROMPT = "你是一个博学的智能聊天助手，请根据用户提问回答！";
    private final ChatClient dashScopeChatClient;

    public HelloworldController(ChatClient.Builder chatClientBuilder) {
        this.dashScopeChatClient = chatClientBuilder
                .defaultSystem(DEFAULT_PROMPT)
                .defaultAdvisors(MessageChatMemoryAdvisor.builder(MessageWindowChatMemory.builder().build()).build())
                .defaultAdvisors(new SimpleLoggerAdvisor())
                .defaultOptions(DashScopeChatOptions.builder().withTopP(0.7).build())
                .build();
    }

    /**
     * ChatClient 简单调用
     */
    @GetMapping("/simple/chat")
    public String simpleChat(@RequestParam(value = "query", defaultValue = "你好") String query) {
        return dashScopeChatClient.prompt(query).call().content();
    }

    /**
     * ChatClient 流式调用
     */
    @GetMapping("/stream/chat")
    public Flux<String> streamChat(@RequestParam(value = "query", defaultValue = "你好") String query,
                                   HttpServletResponse response) {
        response.setCharacterEncoding("UTF-8");
        return dashScopeChatClient.prompt(query).stream().content();
    }

    /**
     * ChatClient 使用自定义的 Advisor 实现功能增强
     */
    @GetMapping("/advisor/chat/{conversationId}")
    public Flux<String> advisorChat(HttpServletResponse response,
                                    @PathVariable String conversationId,
                                    @RequestParam String query) {
        response.setCharacterEncoding("UTF-8");
        return this.dashScopeChatClient
                .prompt(query)
                .advisors(a -> a.param(ChatMemory.CONVERSATION_ID, conversationId))
                .stream()
                .content();
    }
}

测试

测试一：访问简单 chat

访问链接：/helloworld/simple/chat

测试二：访问流式输出

访问链接：/helloworld/stream/chat

测试三：带有记忆的输出

1. 先访问：/helloworld/advisor/chat/123?query=你好，我叫 jack
2. 再访问：/helloworld/advisor/chat/123?query=我叫什么名字？

通过设置 conversationId 参数，将对话历史记录存储到 ChatMemory 中，后续对话会将之前的历史记录作为上下文。