🚀 Spring AI + Spring Boot: How I Built a Local ChatGPT with LangChain4j & Ollama (2025 Setup Guide)

🧠 Everyone talks about AI integrations — but most developers still don’t know how to wire up Spring Boot with LLMs properly.
In this post, I’ll show you exactly how I built a fully local ChatGPT-style service inside my Spring Boot 3.3 app using LangChain4j + Ollama — no API costs, no latency, no vendor lock.

🔍 Why This Guide Matters

In 2025, AI-driven applications are no longer “nice-to-have.”
If your Spring Boot microservice can summarize logs, interpret metrics, or generate reports autonomously, you’re already ahead.

And thanks to LangChain4j, we can now integrate LLMs directly into Java, bringing the same magic as LangChain in Python — but with Spring Boot’s stability.

⚙️ Step 1: Setup Dependencies

In your pom.xml:

<dependencies>
  <dependency>
    <groupId>dev.langchain4j</groupId>
    <artifactId>langchain4j-spring-boot-starter</artifactId>
    <version>0.32.0</version>
  </dependency>
<!-- For local model via Ollama -->
  <dependency>
    <groupId>dev.langchain4j</groupId>
    <artifactId>langchain4j-ollama</artifactId>
    <version>0.32.0</version>
  </dependency>
  <!-- Spring…