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

Many free large‑model APIs are available worldwide, making them ideal for individual developers or small projects. Alibaba Cloud's Bailei (Tongyi) service offers a free quota for new users, providing a convenient entry point for beginners.

Why use the official Spring AI Alibaba starter

The Spring AI team supplies dedicated starters for major providers (e.g., Google Gemini). The spring-ai-alibaba-starter integrates Bailei without requiring OpenAI‑compatible wrappers: you only need to place the API key in the configuration file to obtain an out‑of‑the‑box ChatModel bean.

Configure JDK 17 for a single project

Keep the global JDK 8 unchanged and install JDK 17 locally. In IntelliJ IDEA:

Open Project Structure (Ctrl+Alt+Shift+S).

Set Project SDK to the extracted JDK 17 directory and choose language level 17.

Navigate to Settings → Build → Compiler → Java Compiler and set the bytecode version to 17.

These steps affect only the current project, leaving other projects on JDK 8 untouched.

Obtain an Alibaba Cloud Bailei API key

Log in to the Bailei console at https://bailian.console.aliyun.com/, select the “China North‑Beijing” region, go to the “API Key” page, create a new key, and copy it. Ensure you have completed real‑name verification first. After the free quota is exhausted, the service switches to paid mode; you can enable the “stop when free quota is used up” option to avoid unexpected charges.

Create a Spring Boot project

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

<dependency>
    <groupId>com.alibaba.cloud.ai</groupId>
    <artifactId>spring-ai-alibaba-starter</artifactId>
    <version>1.0.0-M5.1</version>
</dependency>

<repositories>
    <repository>
        <id>spring-milestones</id>
        <url>https://repo.spring.io/milestone</url>
    </repository>
</repositories>

Configure the model in application.yml (replace the placeholder with your own API key):

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

Implement a 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 and test

Start the Spring Boot application and call the /ai/generate?message=... endpoint. The response contains the AI‑generated reply from Bailei.