Getting Started with AI Chat in Spring Boot Using Spring AI Alibaba and Alibaba Cloud Baileian

Many large‑model APIs offer free quotas that are ideal for individual developers or small projects. Alibaba Cloud’s Baileian (Tongyi) provides a free tier for new users, making it a convenient entry point for AI experiments.

The official Spring AI Alibaba starter enables seamless integration without needing OpenAI‑compatible adapters. By adding the starter dependency and configuring the API key, a ready‑to‑use ChatModel bean is created.

Setting Up JDK 17 for a Single Project

Keep the global JDK 8 unchanged and install JDK 17 locally. Extract the JDK to a directory without adding it to PATH or modifying system environment variables. In IntelliJ IDEA, open Project Structure (Ctrl+Alt+Shift+S), set the Project SDK to the JDK 17 directory, and set the language level to 17. Then, in Settings → Build → Compiler → Java Compiler , set the bytecode version to 17, ensuring only this project uses the newer JDK.

Obtaining an Alibaba Cloud Baileian API Key

Log in to the Baileian console at https://bailian.console.aliyun.com/, select the “North China 2 (Beijing)” region, navigate to the “API Key” page, create a new key, and copy it. Complete real‑name verification first. To avoid unexpected charges after the free quota is exhausted, enable the “stop when free quota is used up” option.

Creating the Spring Boot Project

Add the spring-ai-alibaba-starter dependency and the Spring Milestones repository to pom.xml:

org.springframework.boot:spring-boot-starter-parent:3.2.5
com.example:spring-ai-alibaba-bailian:1.0
    17
    1.0.0-M5.1
        org.springframework.boot:spring-boot-starter-web
        com.alibaba.cloud.ai:spring-ai-alibaba-starter:1.0.0-M5.1
        spring-milestones
        https://repo.spring.io/milestone

In application.yml, configure the API key and model:

spring:
  ai:
    dashscope:
      api-key: YOUR_API_KEY
    chat:
      options:
        model: qwen-max

Create a simple chat controller:

package com.badao.ai.controller;

import org.springframework.ai.chat.client.ChatClient;
import org.springframework.web.bind.annotation.GetMapping;
import org.springframework.web.bind.annotation.RequestParam;
import org.springframework.web.bind.annotation.RestController;

@RestController
public class ChatController {
    private final ChatClient chatClient;
    public ChatController(ChatClient.Builder builder) {
        this.chatClient = builder.build();
    }
    @GetMapping("/ai/generate")
    public String generate(@RequestParam(value = "message", defaultValue = "你好") String message) {
        return chatClient.prompt()
                .user(message)
                .call()
                .content();
    }
}

Run the application and test the /ai/generate endpoint. The following screenshot shows a successful response: