Spring Ai Auto Pull Model

Ollama AI Models and Spring AI are different entities that communicate via Rest Services. The Spring Ai auto pull Model mechanism fetches the Models from the repository if not available. This feature is particularly useful for development and testing purposes and deploying the application on new Servers.

GGUF Hugging Face provides thousands of free Models

The Spring Ai Auto pull Model supports 3 strategies.

Auto Pulling is not recommended in the Production Envirment

Spring Ai Auto Pulling Model allows us to configure the Model pulling properties as well such as timeout and max retries, if required we can pull multiple additional Models as well.

Application initialization will only happen after the Model is pulled, this might slow down the startup for the first time.

Along with the main Model, The Spring Ai pulls additional Models by setting the properties spring.ai.ollama.init.chat.additional-models.

package com.example.springai.controller;

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

@RestController
public class SpringAiController {
    private final ChatClient chatClient;

    public SpringAiController(ChatClient.Builder chatClient) {
        this.chatClient = chatClient.build();
    }

    @GetMapping("/hello")
    String hello() {
        String helloPrompt = "Hello, I am learning Ai with Spring";
        return this.chatClient.prompt().user(helloPrompt).call().content();
    }
}

package com.example.springai;

import org.springframework.boot.SpringApplication;
import org.springframework.boot.autoconfigure.SpringBootApplication;

@SpringBootApplication
public class SpringAiApplication {
    public static void main(String[] args) {
        SpringApplication.run(SpringAiApplication.class, args);
    }
}

spring.application.name=SpringAi
spring.docker.compose.lifecycle-management=start-only
spring.threads.virtual.enabled=true
# If running the Ollama Docker Instance separately, then set this property
spring.docker.compose.enabled=false
#Auto-pulling Models
spring.ai.ollama.init.pull-model-strategy=when_missing
spring.ai.ollama.init.timeout=15m
spring.ai.ollama.init.max-retries=3
# The default Ollama Model in Spring Ai is mistral, but it can be changed by setting the below property.
spring.ai.ollama.chat.options.model=llama3.1
# If additional Models are required, then set this property
#spring.ai.ollama.init.chat.additional-models=llama3.2, qwen2.5

services:
  ollama-model:
    image: ollama/ollama:latest
    container_name: ollama_container
    ports:
      - 11434:11434/tcp
    healthcheck:
      test: ollama --version || exit 1
    command: serve
    volumes:
      - ./ollama/ollama:/root/.ollama
      - ./entrypoint.sh:/entrypoint.sh
    pull_policy: missing
    tty: true
    restart: no
    entrypoint: [ "/usr/bin/bash", "/entrypoint.sh" ]

  open-webui:
    image: ghcr.io/open-webui/open-webui:main
    container_name: open_webui_container
    environment:
      WEBUI_AUTH: false
    ports:
      - "8081:8080"
    extra_hosts:
      - "host.docker.internal:host-gateway"
    volumes:
      - open-webui:/app/backend/data
    restart: no

volumes:
  open-webui:

#!/bin/bash
# Start Ollama in the background.
/bin/ollama serve &
# Record Process ID.
pid=$!
# Pause for Ollama to start.
sleep 5
# The default Ollama Model in Spring Ai is mistral, but it can be changed in the applications property file. Make sure to download the same Model here
echo "🔴 Retrieve llama3.1 model..."
ollama pull mistral
echo "🟢 Done!"
# Wait for the Ollama process to finish.
wait $pid

<?xml version="1.0" encoding="UTF-8"?>
<project xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns="http://maven.apache.org/POM/4.0.0"
         xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 https://maven.apache.org/xsd/maven-4.0.0.xsd">
    <modelVersion>4.0.0</modelVersion>
    <parent>
        <groupId>org.springframework.boot</groupId>
        <artifactId>spring-boot-starter-parent</artifactId>
        <version>3.3.2</version>
        <relativePath/>
    </parent>
    <groupId>com.example.springai</groupId>
    <artifactId>auto_pulling_models</artifactId>
    <version>0.0.1-SNAPSHOT</version>
    <name>Auto-pulling Models</name>
    <description>Demo project for Spring Boot</description>

    <properties>
        <java.version>21</java.version>
        <spring-ai.version>1.0.0-SNAPSHOT</spring-ai.version>
    </properties>
    <dependencies>
        <dependency>
            <groupId>org.springframework.boot</groupId>
            <artifactId>spring-boot-starter-web</artifactId>
        </dependency>
        <dependency>
            <groupId>org.springframework.ai</groupId>
            <artifactId>spring-ai-ollama-spring-boot-starter</artifactId>
        </dependency>
        <dependency>
            <groupId>org.springframework.boot</groupId>
            <artifactId>spring-boot-docker-compose</artifactId>
            <scope>runtime</scope>
            <optional>true</optional>
        </dependency>
        <dependency>
            <groupId>org.springframework.boot</groupId>
            <artifactId>spring-boot-starter-test</artifactId>
            <scope>test</scope>
        </dependency>
    </dependencies>
    <dependencyManagement>
        <dependencies>
            <dependency>
                <groupId>org.springframework.ai</groupId>
                <artifactId>spring-ai-bom</artifactId>
                <version>${spring-ai.version}</version>
                <type>pom</type>
                <scope>import</scope>
            </dependency>
        </dependencies>
    </dependencyManagement>

    <build>
        <plugins>
            <plugin>
                <groupId>org.springframework.boot</groupId>
                <artifactId>spring-boot-maven-plugin</artifactId>
                <configuration>
                    <mainClass>com.example.springai.SpringAiApplication</mainClass>
                    <excludes>
                        <exclude>
                            <groupId>org.projectlombok</groupId>
                            <artifactId>lombok</artifactId>
                        </exclude>
                    </excludes>
                </configuration>
            </plugin>
        </plugins>
    </build>
    <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>
</project>

Run the curl to see the Spring Ai Auto Pull Model

curl --location 'http://localhost:8080/hello'