SpringBoot集成Ollama本地模型
目录
1. 项目准备
- 创建一个SpringBoot项目，可以使用Spring Initializr或IDE创建
- 添加必要的依赖到
pom.xml:<dependencies> <!-- Spring Boot Starter Web --> <dependency> <groupId>org.springframework.boot</groupId> <artifactId>spring-boot-starter-web</artifactId> </dependency> <!-- Lombok --> <dependency> <groupId>org.projectlombok</groupId> <artifactId>lombok</artifactId> <optional>true</optional> </dependency> <!-- WebClient --> <dependency> <groupId>org.springframework.boot</groupId> <artifactId>spring-boot-starter-webflux</artifactId> </dependency> </dependencies>
2. 创建Ollama服务客户端
package com.example.ollama.service;
import lombok.extern.slf4j.Slf4j;
import org.springframework.beans.factory.annotation.Value;
import org.springframework.stereotype.Service;
import org.springframework.web.reactive.function.client.WebClient;
import reactor.core.publisher.Flux;
import reactor.core.publisher.Mono;
import java.util.List;
import java.util.Map;
@Slf4j
@Service
public class OllamaService {
private final WebClient webClient;
public OllamaService(@Value("${ollama.api.url:http://localhost:11434}") String ollamaApiUrl) {
this.webClient = WebClient.builder()
.baseUrl(ollamaApiUrl)
.build();
}
/**
* 生成文本
*/
public Mono<String> generateText(String model, String prompt, Double temperature) {
Map<String, Object> requestBody = Map.of(
"model", model,
"prompt", prompt,
"temperature", temperature != null ? temperature : 0.7
);
return webClient.post()
.uri("/api/generate")
.bodyValue(requestBody)
.retrieve()
.bodyToMono(Map.class)
.map(response -> (String) response.get("response"));
}
/**
* 聊天对话
*/
public Mono<String> chat(String model, List<Map<String, String>> messages) {
Map<String, Object> requestBody = Map.of(
"model", model,
"messages", messages
);
return webClient.post()
.uri("/api/chat")
.bodyValue(requestBody)
.retrieve()
.bodyToMono(Map.class)
.map(response -> {
Map<String, Object> message = (Map<String, Object>) response.get("message");
return (String) message.get("content");
});
}
/**
* 流式生成文本
*/
public Flux<String> streamGenerateText(String model, String prompt, Double temperature) {
Map<String, Object> requestBody = Map.of(
"model", model,
"prompt", prompt,
"temperature", temperature != null ? temperature : 0.7,
"stream", true
);
return webClient.post()
.uri("/api/generate")
.bodyValue(requestBody)
.retrieve()
.bodyToFlux(Map.class)
.map(response -> (String) response.get("response"));
}
}
3. 创建控制器
package com.example.ollama.controller;
import com.example.ollama.service.OllamaService;
import lombok.RequiredArgsConstructor;
import org.springframework.web.bind.annotation.*;
import reactor.core.publisher.Flux;
import reactor.core.publisher.Mono;
import java.util.List;
import java.util.Map;
@RestController
@RequestMapping("/api/ollama")
@RequiredArgsConstructor
public class OllamaController {
private final OllamaService ollamaService;
@PostMapping("/generate")
public Mono<String> generateText(
@RequestParam(defaultValue = "llama2") String model,
@RequestParam String prompt,
@RequestParam(required = false) Double temperature) {
return ollamaService.generateText(model, prompt, temperature);
}
@PostMapping("/chat")
public Mono<String> chat(
@RequestParam(defaultValue = "llama2") String model,
@RequestBody List<Map<String, String>> messages) {
return ollamaService.chat(model, messages);
}
@PostMapping("/stream")
public Flux<String> streamGenerateText(
@RequestParam(defaultValue = "llama2") String model,
@RequestParam String prompt,
@RequestParam(required = false) Double temperature) {
return ollamaService.streamGenerateText(model, prompt, temperature);
}
}
4. 配置应用属性
在application.properties或application.yml中添加配置:
# Ollama API配置
ollama.api.url=http://localhost:11434
# 服务器配置
server.port=8080
5. 创建前端界面
创建一个简单的HTML页面用于与Ollama交互:
<!DOCTYPE html>
<html lang="zh-CN">
<head>
<meta charset="UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>Ollama聊天界面</title>
<style>
body {
font-family: Arial, sans-serif;
max-width: 800px;
margin: 0 auto;
padding: 20px;
}
.chat-container {
border: 1px solid #ccc;
border-radius: 5px;
padding: 20px;
margin-bottom: 20px;
height: 400px;
overflow-y: auto;
}
.message {
margin-bottom: 10px;
padding: 10px;
border-radius: 5px;
}
.user-message {
background-color: #e6f7ff;
margin-left: 20%;
}
.ai-message {
background-color: #f0f0f0;
margin-right: 20%;
}
.input-container {
display: flex;
}
#message-input {
flex-grow: 1;
padding: 10px;
border: 1px solid #ccc;
border-radius: 5px;
margin-right: 10px;
}
button {
padding: 10px 20px;
background-color: #4CAF50;
color: white;
border: none;
border-radius: 5px;
cursor: pointer;
}
button:hover {
background-color: #45a049;
}
</style>
</head>
<body>
<h1>Ollama聊天界面</h1>
<div class="chat-container" id="chat-container"></div>
<div class="input-container">
<input type="text" id="message-input" placeholder="输入消息...">
<button onclick="sendMessage()">发送</button>
</div>
<script>
const chatContainer = document.getElementById('chat-container');
const messageInput = document.getElementById('message-input');
// 按Enter键发送消息
messageInput.addEventListener('keypress', function(e) {
if (e.key === 'Enter') {
sendMessage();
}
});
function sendMessage() {
const message = messageInput.value.trim();
if (!message) return;
// 添加用户消息到聊天界面
addMessage(message, 'user');
messageInput.value = '';
// 发送消息到后端
fetch('/api/ollama/chat', {
method: 'POST',
headers: {
'Content-Type': 'application/json'
},
body: JSON.stringify([
{
'role': 'user',
'content': message
}
])
})
.then(response => response.text())
.then(response => {
// 添加AI回复到聊天界面
addMessage(response, 'ai');
})
.catch(error => {
console.error('Error:', error);
addMessage('发生错误，请稍后重试。', 'ai');
});
}
function addMessage(message, sender) {
const messageDiv = document.createElement('div');
messageDiv.classList.add('message');
messageDiv.classList.add(sender === 'user' ? 'user-message' : 'ai-message');
messageDiv.textContent = message;
chatContainer.appendChild(messageDiv);
chatContainer.scrollTop = chatContainer.scrollHeight;
}
</script>
</body>
</html>
6. 添加静态资源支持
在SpringBoot应用中添加静态资源支持:
package com.example.ollama.config;
import org.springframework.context.annotation.Configuration;
import org.springframework.web.servlet.config.annotation.ResourceHandlerRegistry;
import org.springframework.web.servlet.config.annotation.WebMvcConfigurer;
@Configuration
public class WebConfig implements WebMvcConfigurer {
@Override
public void addResourceHandlers(ResourceHandlerRegistry registry) {
registry.addResourceHandler("/**")
.addResourceLocations("classpath:/static/");
}
}
7. 完整项目结构
src/
├── main/
│ ├── java/
│ │ └── com/
│ │ └── example/
│ │ └── ollama/
│ │ ├── OllamaApplication.java
│ │ ├── controller/
│ │ │ └── OllamaController.java
│ │ ├── service/
│ │ │ └── OllamaService.java
│ │ └── config/
│ │ └── WebConfig.java
│ └── resources/
│ ├── static/
│ │ └── index.html
│ └── application.properties
8. 启动应用
- 确保Ollama服务已启动并运行在默认端口(11434)
- 运行SpringBoot应用
- 访问
http://localhost:8080查看聊天界面
9. 高级功能扩展
9.1 添加模型选择功能
@GetMapping("/models")
public Mono<List<String>> listModels() {
return webClient.get()
.uri("/api/tags")
.retrieve()
.bodyToMono(Map.class)
.map(response -> {
List<Map<String, Object>> models = (List<Map<String, Object>>) response.get("models");
return models.stream()
.map(model -> (String) model.get("name"))
.collect(Collectors.toList());
});
}
9.2 添加流式响应支持
@GetMapping(value = "/stream-chat", produces = MediaType.TEXT_EVENT_STREAM_VALUE)
public Flux<ServerSentEvent<String>> streamChat(
@RequestParam(defaultValue = "llama2") String model,
@RequestParam String message) {
return ollamaService.streamGenerateText(model, message, 0.7)
.map(response -> ServerSentEvent.<String>builder()
.data(response)
.build());
}
9.3 添加会话管理
@Service
public class ChatSessionService {
private final Map<String, List<Map<String, String>>> sessions = new ConcurrentHashMap<>();
public List<Map<String, String>> getOrCreateSession(String sessionId) {
return sessions.computeIfAbsent(sessionId, k -> new ArrayList<>());
}
public void addMessage(String sessionId, String role, String content) {
List<Map<String, String>> messages = getOrCreateSession(sessionId);
messages.add(Map.of("role", role, "content", content));
}
public void clearSession(String sessionId) {
sessions.remove(sessionId);
}
}
10. 部署注意事项
- 确保服务器上已安装并运行Ollama服务
- 配置适当的防火墙规则，允许SpringBoot应用访问Ollama服务
- 在生产环境中使用HTTPS保护API通信
- 考虑添加身份验证和授权机制
- 监控Ollama服务的资源使用情况，避免过载
11. 性能优化
- 使用连接池管理WebClient连接
- 实现请求缓存，避免重复请求
- 使用异步处理提高并发能力
- 考虑使用响应式编程模式处理流式响应