Back to Repositories

Testing TongYi Chat Model Integration in ruoyi-vue-pro

This test suite validates the integration and functionality of the TongYiChatModel, a chat model implementation for the Alibaba Cloud Tongyi AI service. It focuses on testing both synchronous and streaming chat interactions with specific Chinese language capabilities.

Test Coverage Overview

The test suite provides comprehensive coverage of TongYiChatModel functionality:

Synchronous chat message processing using call() method
Asynchronous streaming responses using stream() method
System and user message handling
Chinese language processing with specific focus on classical Chinese text generation

Implementation Analysis

The testing approach utilizes JUnit 5 framework with a focus on integration testing patterns:

BeforeEach setup for MessageManager initialization
Mock API key configuration
Reactive programming testing with Flux
Test case isolation with @Disabled annotations

Technical Details

Testing infrastructure includes:

JUnit Jupiter test framework
Alibaba Cloud AI SDK integration
Hutool reflection utilities
Spring AI chat message abstractions
Reactor Core for reactive streams testing

Best Practices Demonstrated

The test suite exemplifies several testing best practices:

Proper test initialization and cleanup
Clear test case separation
Explicit test data preparation
Comprehensive API testing coverage
Proper handling of asynchronous operations

yunaiv/ruoyi-vue-pro

yudao-module-ai/yudao-spring-boot-starter-ai/src/test/java/cn/iocoder/yudao/framework/ai/chat/TongYiChatModelTests.java

            
package cn.iocoder.yudao.framework.ai.chat;

import cn.hutool.core.util.ReflectUtil;
import com.alibaba.cloud.ai.tongyi.chat.TongYiChatModel;
import com.alibaba.cloud.ai.tongyi.chat.TongYiChatOptions;
import com.alibaba.dashscope.aigc.generation.Generation;
import com.alibaba.dashscope.common.MessageManager;
import com.alibaba.dashscope.utils.Constants;
import org.junit.jupiter.api.BeforeEach;
import org.junit.jupiter.api.Disabled;
import org.junit.jupiter.api.Test;
import org.springframework.ai.chat.messages.Message;
import org.springframework.ai.chat.messages.SystemMessage;
import org.springframework.ai.chat.messages.UserMessage;
import org.springframework.ai.chat.model.ChatResponse;
import org.springframework.ai.chat.prompt.Prompt;
import reactor.core.publisher.Flux;

import java.util.ArrayList;
import java.util.List;

/**
 * {@link TongYiChatModel} 集成测试类
 *
 * @author fansili
 */
public class TongYiChatModelTests {

    private final Generation generation = new Generation();
    private final TongYiChatModel chatModel = new TongYiChatModel(generation,
            TongYiChatOptions.builder().withModel("qwen1.5-72b-chat").build());

    static {
        Constants.apiKey = "sk-Zsd81gZYg7";
    }

    @BeforeEach
    public void before() {
        // 防止 TongYiChatModel 调用空指针
        ReflectUtil.setFieldValue(chatModel, "msgManager", new MessageManager());
    }

    @Test
    @Disabled
    public void testCall() {
        // 准备参数
        List<Message> messages = new ArrayList<>();
        messages.add(new SystemMessage("你是一个优质的文言文作者，用文言文描述着各城市的人文风景。"));
        messages.add(new UserMessage("1 + 1 = ？"));

        // 调用
        ChatResponse response = chatModel.call(new Prompt(messages));
        // 打印结果
        System.out.println(response);
        System.out.println(response.getResult().getOutput());
    }

    @Test
    @Disabled
    public void testStream() {
        // 准备参数
        List<Message> messages = new ArrayList<>();
        messages.add(new SystemMessage("你是一个优质的文言文作者，用文言文描述着各城市的人文风景。"));
        messages.add(new UserMessage("1 + 1 = ？"));

        // 调用
        Flux<ChatResponse> flux = chatModel.stream(new Prompt(messages));
        // 打印结果
        flux.doOnNext(response -> {
//            System.out.println(response);
            System.out.println(response.getResult().getOutput());
        }).then().block();
    }

}