Training: Spring AI for integrating LLMs into Spring Boot applications

Spring AI for integrating LLMs into Spring Boot applications

As a Java developer with experience in the Spring Boot stack, you may have thought about integrating LLMs into your services or building a small agent of your own for a specific practical task. But the core ecosystem around LLMs is built with Python, which immediately pushes you out of your comfort zone. After all, you would need not only to learn a new programming language but also to embrace new paradigms for developing and maintaining applications. Now that’s no longer a problem! The Java world has two fairly mature solutions that let you fully integrate LLMs into existing applications or build new ones. They are LangChain4j and Spring AI. In this hands-on training, we’ll work out how to develop LLM features in the familiar Spring Boot style.

Goals and objectives

Explore the main capabilities of LLMs and the mechanisms for integrating them into applications through APIs
Learn to fully integrate LLMs into existing Spring Boot applications through practical examples
Get an overview of the various tools for extending LLM capabilities and of the MCP protocol
Learn to optimize your integrations for cost and speed

Target audience

Java developers, architects, tech leads

Price

$450per participant

Date and time

5 modules of 3 hours each

Trainer

Mikalai AlimenkouIndependent consultant

Detailed program

Part 1

Generative AI and the Transformer architecture

How LLMs work and the main stages of their training

Capabilities and limitations of LLMs

LLMs on the market and how they are classified

Overview of OpenAI models and their hosting options

Creating an account and using the playground

Comparison with Anthropic models

Deploying models on Amazon Bedrock

Part 2

Prompt engineering basics

How to use the OpenAI API and its main capabilities

Introduction to Spring AI and LangChain4j

A quick overview of the main features

Integration in chat mode

Using prompt templates

Part 3

Using structured outputs and objects

Configuring memory and the different memory modes

Implementing persistent memory

RAG for adding private knowledge to the context

Embeddings and integration with various vector stores

Different RAG strategies

Part 4

Adding tools

Existing tools and how to integrate them

The MCP protocol and its advantages

Integrating with existing MCP servers

Implementing your own MCP server

Part 5

Monitoring the LLM integration

Testing the LLM integration (local and end-to-end)

Evaluating LLM output quality for specific use cases

Optimizing the integration for cost and speed