Spring AI and Ollama - Building an Open-Source Chatbot

docker run -d -v ./ollama/ollama-server:/root/.ollama -p 11434:11434 --name ollama ollama/ollama 

docker exec ollama ollama pull llama3.2:1b      # Meta's Llama 3  
docker exec ollama ollama pull gemma3:1b        # Google's Gemma
docker exec ollama ollama pull deepseek-r1:1.5b # Deepseek's R1

curl http://localhost:11434/api/generate -d '{  
  "model": "llama3.2:1b",  
  "prompt": "Hello, world!"  
}'

<!-- use Ollama as LLM inference server and Model provider -->
<dependency>
    <groupId>org.springframework.ai</groupId>
    <artifactId>spring-ai-starter-model-ollama</artifactId>
</dependency>
<!-- use JDBC to store messages in a relational database. -->
    <dependency>
    <groupId>org.springframework.ai</groupId>
    <artifactId>spring-ai-starter-model-chat-memory-repository-jdbc</artifactId>
</dependency>
<dependency>
    <groupId>com.h2database</groupId>
    <artifactId>h2</artifactId>
    <scope>runtime</scope>
</dependency>

spring:
  application:
    name: demo-chatbot
  ai:
    ollama:
      base-url: http://localhost:11434
      chat:
        model: llama3.2:1b # deepseek-r1:1.5b, gemma3:1b
    chat:
      memory:
        repository:
          jdbc:
            # https://docs.spring.io/spring-ai/reference/1.0/api/chat-memory.html#_schema_initialization
            initialize-schema: always
            schema: classpath:sql/schema-h2.sql
  datasource:
    url: jdbc:h2:mem:~/demo-chatbot
    driverClassName: org.h2.Driver
    username: sa
    password: password
  h2:
    console:
      enabled: true
      path: /h2

CREATE TABLE IF NOT EXISTS SPRING_AI_CHAT_MEMORY (
    conversation_id VARCHAR(36) NOT NULL,
    content TEXT NOT NULL,
    type VARCHAR(10) NOT NULL CHECK (type IN ('USER', 'ASSISTANT', 'SYSTEM', 'TOOL')),
    "timestamp" TIMESTAMP NOT NULL
    );

CREATE INDEX IF NOT EXISTS SPRING_AI_CHAT_MEMORY_CONVERSATION_ID_TIMESTAMP_IDX
ON SPRING_AI_CHAT_MEMORY(conversation_id, "timestamp");

@Configuration
public class ChatConfig {

    @Bean
    public ChatClient chatClient(ChatClient.Builder builder, ChatMemory chatMemory) {
        String defaultSystemPrompt = """
                Your are a useful AI assistant, your responsibility is provide users questions
                about a variety of topics.
                When answering a question, always greet first and state your name as JavaChat
                When unsure about the answer, simply state that you don´t know.
                """;
        return builder
                .defaultSystem(defaultSystemPrompt)
                .defaultAdvisors(
                        new SimpleLoggerAdvisor(),                //simply logs requests and responses with a Model
                        new PromptChatMemoryAdvisor(chatMemory)  //let Spring AI manage long term memory in the DB
                        )
                .build();
    }
}

@RequestMapping("/api/chat")
@RestController
public class ChatController {

    @Autowired
    private ChatClient chatClient;

    @GetMapping
    public String chat(@RequestParam String question, @RequestParam String chatId) {
        return chatClient
                .prompt()
                .user(question)
                .advisors(advisor -> advisor
                        .param(ChatMemory.CONVERSATION_ID, chatId))
                .call()
                .content();
    }
}

@GetMapping(value = "/stream", produces = MediaType.TEXT_EVENT_STREAM_VALUE)
public Flux<ChunkResponseDTO> streamChat(@RequestParam String question, @RequestParam String chatId) {
    return chatClient
            .prompt()
            .user(question)
            .advisors(advisor -> advisor
                .param(ChatMemory.CONVERSATION_ID, chatId))
            .stream()
            .content()
            .map(chunk -> new ChunkResponseDTO(chunk));
}

public record ChunkResponseDTO(String value) {}

server:
  http2:
    enabled: true
  ssl:
    enabled: true
    key-store: classpath:keystore.p12
    key-store-password: yourpassword

keytool -genkeypair -alias mydomain -keyalg RSA -keysize 2048 -storetype PKCS12 -keystore keystore.p12 -validity 365

const chatStream = (question) => {
  const eventSource = new EventSource(`https://localhost:8080/api/chat/stream?chatId=1&question=${encodeURIComponent(question)}`);

  eventSource.onmessage = (e) => {

    console.log('New message:', JSON.parse(e.data).value);
    // Append to UI (e.g., a chat div)
    document.getElementById('messages').innerHTML += JSON.parse(e.data).value;
  };

  eventSource.onerror = (e) => {
    console.error('SSE error:', e);
    eventSource.close();
  };
};

// Usage
chatStream("Tell me about Java");

<script src="https://cdnjs.cloudflare.com/ajax/libs/dompurify/3.0.6/purify.min.js"></script>

eventSource.onmessage = (e) => {
    const chunkResponse = JSON.parse(e.data).value);
    console.log('New message:', chunkResponse);
    const sanitized = DOMPurify.sanitize(chunkResponse); // Strips malicious scripts
    // Append to UI (e.g., a chat div)
    document.getElementById('messages').innerHTML += sanitized;
  };

<script src="https://cdn.jsdelivr.net/npm/marked/marked.min.js"></script>

  let chunkResponses = '';
  eventSource.onmessage = (e) => {
    chunkResponses += JSON.parse(e.data).value;

    // Sanitize all chunks received so far.
    DOMPurify.sanitize(chunkResponses);

    // Check if the output was insecure.
    if (DOMPurify.removed.length) {
      // If the output was insecure, immediately stop what you were doing.
      // Reset the parser and flush the remaining Markdown.
      chunkResponses = '';
      return;
    }
    // Append to UI (e.g., a chat div)
    document.getElementById('messages').innerHTML = marked.parse(chunkResponses);
  };

<!DOCTYPE html>
<html lang="en">
<head>
    <title>Spring AI Chat</title>
    <link rel="stylesheet" href="layout.css">
</head>
<body>
<!-- Sidebar for chat history -->
<div id="sidebar">
    <h3>Chat History</h3>
    <ul id="history-list"></ul>
</div>

<!-- Main chat area -->
<div id="chat-container">
    <div id="messages"></div>
    <form id="input-form">
        <input type="text" id="prompt" placeholder="Type your message..." autocomplete="off">
        <button type="submit">Send</button>
    </form>
</div>

<script src="main.js"> </script>
<script src="https://cdnjs.cloudflare.com/ajax/libs/dompurify/3.0.6/purify.min.js"></script>
<script src="https://cdn.jsdelivr.net/npm/marked/marked.min.js"></script>
</body>
</html>

services:
  # Ollama LLM inference server
  ollama:
    volumes: # Ollama with persistent storage (no redownloading models).
      - ./ollama/ollama-server:/root/.ollama
    container_name: ollama
    pull_policy: always
    tty: true
    restart: unless-stopped
    image: docker.io/ollama/ollama:latest
    ports:
      - 11434:11434
    environment:
      - OLLAMA_KEEP_ALIVE=24h
    # Enable GPU support
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]
  # Spring AI Backend
  chat-app:
    build:
      context: . # Dockerfile in the root folder
    container_name: chat-app
    ports:
      - "8080:8080"
    environment:
      - SPRING_AI_OLLAMA_BASE_URL=http://ollama:11434
    depends_on:
      - ollama

# Maven build stage
FROM maven:3.9.9-eclipse-temurin-21-alpine as build
WORKDIR /app
COPY pom.xml .
RUN mvn dependency:go-offline
COPY src/ ./src/
RUN mvn clean package

# Spring Boot package stage
FROM eclipse-temurin:21-jre-alpine
COPY --from=build app/target/*.jar app.jar
EXPOSE 8080
ENTRYPOINT ["java", "-jar", "app.jar"]