# springAI

**Repository Path**: qiankun1998/spring-ai

## Basic Information

- **Project Name**: springAI
- **Description**: Spring AI整合本地部署实现DeepSeek实现AI对话
- **Primary Language**: Unknown
- **License**: Not specified
- **Default Branch**: master
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 1
- **Forks**: 0
- **Created**: 2025-02-17
- **Last Updated**: 2025-05-12

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

https://blog.csdn.net/qq_44210132/article/details/145681868?sharetype=blogdetail&sharerId=145681868&sharerefer=PC&sharesource=qq_44210132&spm=1011.2480.3001.8118

## Spring AI整合本地部署实现DeepSeek实现AI对话

### 1.引入依赖

```xml
  <dependencies>
        <dependency>
            <groupId>org.springframework.boot</groupId>
            <artifactId>spring-boot-starter-web</artifactId>
        </dependency>

        <dependency>
            <groupId>org.springframework.boot</groupId>
            <artifactId>spring-boot-starter-test</artifactId>
            <scope>test</scope>
        </dependency>


        <dependency>
            <groupId>org.springframework.ai</groupId>
            <artifactId>spring-ai-bom</artifactId>
            <version>1.0.0-SNAPSHOT</version>
            <type>pom</type>
            <scope>import</scope>
        </dependency>

        <dependency>
            <groupId>org.springframework.ai</groupId>
            <artifactId>spring-ai-ollama-spring-boot-starter</artifactId>
            <version>1.0.0-SNAPSHOT</version>
        </dependency>

    </dependencies>
    <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>
```
### 2.配置

```yaml
server:
  port: 8088
spring:
  ai:
    ollama:
      base-url: http://127.0.0.1:11434
      chat:
        options:
          model: deepseek-r1:7b
```
### 3.Controller
```java
@RestController
public class ChatController {

    private final OllamaChatModel chatModel;

    @Autowired
    public ChatController(OllamaChatModel chatModel) {
        this.chatModel = chatModel;
    }

    @GetMapping("/ai/generate")
    public Map<String, String> generate(@RequestParam(value = "message", defaultValue = "您好") String message) {
        List<Message> messages=new ArrayList<>();
        messages.add(new SystemMessage("你是张三"));
        messages.add(new SystemMessage("你今年两岁半"));
        messages.add(new SystemMessage("喜欢唱跳rep"));
        messages.add(new UserMessage(message));
        ChatResponse call = this.chatModel.call(new Prompt(messages));
        return Map.of("generation", call.toString());
    }

    @GetMapping("/ai/generateStream")
    public Flux<ChatResponse> generateStream(@RequestParam(value = "message", defaultValue = "您好") String message) {
        Prompt prompt = new Prompt(new UserMessage(message));
        return this.chatModel.stream(prompt);
    }

}
```
### 4.多轮对话和自定义提示词
```java
        List<Message> messages=new ArrayList<>();
        //SystemMessage是系统消息
        messages.add(new SystemMessage("你是张三"));
        messages.add(new SystemMessage("你今年两岁半"));
        messages.add(new SystemMessage("喜欢唱跳rep"));
        //UserMessage是用户消息
        messages.add(new UserMessage(message));
        //虽然区分了系统消息和用户消息，但是不准确，还需要自行添加提示词防止ai不理解其中意思
```
多轮对话等数据可存入向量数据库进行获取。

### DeepSeek部署
1.访问Ollama官网，下载与你操作系统匹配的版本（支持Windows、macOS和Linux）。

2.Ollama下载完成后，执行命令运行指定本地模型。

```bash
ollama run deepseek-r1:1.5b
```
开始使用
![在这里插入图片描述](https://i-blog.csdnimg.cn/direct/c728f23e9a4b4372b9be4a00b34b54e9.png)
### 接口调用
![在这里插入图片描述](https://i-blog.csdnimg.cn/direct/32c16a7095694f3e8067c5f0c6b10b3e.png)
### 完