Kevin Dubois

Infusing Generative AI in your Java Apps with LangChain4j

Turn natural language commands into executable Java code. Learn how the `@Tool` annotation in LangChain4j connects LLM prompts directly to your business logic.

Infusing Generative AI in your Java Apps with LangChain4j
#1about 3 minutes

Integrating generative AI into Java applications with LangChain4j

LangChain4j simplifies consuming AI model APIs for Java developers, avoiding the need for deep data science expertise.

#2about 3 minutes

Creating a new Quarkus project with LangChain4j

Use the Quarkus CLI to bootstrap a new Java application and add the necessary LangChain4j dependency for OpenAI integration.

#3about 2 minutes

Using prompts and AI services in LangChain4j

Define AI interactions using the @RegisterAIService annotation, system messages for context, and user messages with dynamic placeholders.

#4about 2 minutes

Managing conversational context with memory

LangChain4j uses memory to retain context across multiple calls, with the @MemoryId annotation enabling parallel conversations.

#5about 2 minutes

Connecting AI models to business logic with tools

Use the @Tool annotation to expose Java methods to the AI model, allowing it to execute business logic like sending an email.

#6about 5 minutes

Live demo of prompts, tools, and the Dev UI

A practical demonstration shows how to generate a haiku using a prompt and then use a custom tool to send it via email, verified with Mailpit.

#7about 3 minutes

Providing custom knowledge with retrieval-augmented generation (RAG)

Enhance LLM responses with your own business data by using an embedding store or Quarkus's simplified 'Easy RAG' feature.

#8about 6 minutes

Building a chatbot with a custom knowledge base

A chatbot demo uses a terms of service document via RAG to correctly enforce a business rule for booking cancellations.

#9about 2 minutes

Using local models and implementing fault tolerance

Run LLMs on your local machine with Podman AI Lab and make your application resilient to failures using SmallRye Fault Tolerance annotations.

#10about 4 minutes

Demonstrating fault tolerance with a local LLM

A final demo shows an application calling a locally-run model and triggering a fallback mechanism when the model service is unavailable.

Related jobs
Jobs that call for the skills explored in this talk.

Featured Partners

Related Videos

Create AI-Infused Java Apps with LangChain4j29:18

Create AI-Infused Java Apps with LangChain4j

Daniel Oh, Kevin Dubois

Langchain4J - An Introduction for Impatient Developers31:59

Langchain4J - An Introduction for Impatient Developers

Juarez Junior

Java Meets AI: Empowering Spring Developers to Build Intelligent Apps31:53

Java Meets AI: Empowering Spring Developers to Build Intelligent Apps

Timo Salm

Supercharge your cloud-native applications with Generative AI32:13

Supercharge your cloud-native applications with Generative AI

Cedric Clyburn

Agentic AI Systems for Critical Workloads30:01

Agentic AI Systems for Critical Workloads

Mario Fusco

Supercharge Agentic AI Apps: A DevEx-Driven Approach to Cloud-Native Scaffolding31:02

Supercharge Agentic AI Apps: A DevEx-Driven Approach to Cloud-Native Scaffolding

Daniel Oh

Building AI-Driven Spring Applications With Spring AI32:14

Building AI-Driven Spring Applications With Spring AI

Timo Salm, Sandra Ahlgrimm

Make it simple, using generative AI to accelerate learning26:54

Make it simple, using generative AI to accelerate learning

Duan Lightfoot

From learning to earning

Jobs that call for the skills explored in this talk.