<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Langchain4j on JAVAPRO International</title><link>https://javapro-en.svenruppert.com/tags/langchain4j/</link><description>Recent content in Langchain4j on JAVAPRO International</description><generator>Hugo</generator><language>en-US</language><lastBuildDate>Wed, 08 Jul 2026 07:00:02 +0000</lastBuildDate><atom:link href="https://javapro-en.svenruppert.com/tags/langchain4j/index.xml" rel="self" type="application/rss+xml"/><item><title>LangChain4j Agentic Workflows: From AI Calls to Multi-Agent Systems in Java</title><link>https://javapro-en.svenruppert.com/langchain4j-agentic-workflows-from-ai-calls-to-multi-agent-systems-in-java/</link><pubDate>Wed, 08 Jul 2026 07:00:02 +0000</pubDate><guid>https://javapro-en.svenruppert.com/langchain4j-agentic-workflows-from-ai-calls-to-multi-agent-systems-in-java/</guid><description>&lt;p&gt;You have built AI features into your Java application. Your model is wrapped in a service, RAG is feeding it context, tools are wired, and calls are flowing. It works. Then requirements evolve. A single prompt-and-response is no longer enough. You need steps that follow each other, branches based on decisions, retries when things fail, and multiple actions running concurrently. The question shifts from &amp;ldquo;how do I call an LLM?&amp;rdquo; to &amp;ldquo;how do I orchestrate multiple LLM-driven tasks into a coherent system?&amp;rdquo;&lt;/p&gt;</description></item><item><title>Talk to Your Data: Natural Language Data Access in Java</title><link>https://javapro-en.svenruppert.com/talk-to-your-data-natural-language-data-access-in-java/</link><pubDate>Fri, 03 Apr 2026 07:00:01 +0000</pubDate><guid>https://javapro-en.svenruppert.com/talk-to-your-data-natural-language-data-access-in-java/</guid><description>&lt;p&gt;&lt;a href="https://youtu.be/tMW5jxX6DoA"&gt;&lt;figure class="post-figure"&gt;
 &lt;img src="https://javapro-en.svenruppert.com/uploads/2026/03/2026-Magazin-Artikel-Banner-1024x213.png" alt="" loading="lazy" decoding="async"&gt;
 
 
 
&lt;/figure&gt;
&lt;/a&gt;&lt;/p&gt;
&lt;p&gt;For decades, Java developers have relied on robust frameworks to manage the complexity of enterprise applications. At the heart of this ecosystem lies &lt;strong&gt;Hibernate ORM&lt;/strong&gt;, the popular &lt;a href="https://hibernate.org/orm/"&gt;library&lt;/a&gt; for bridging the gap between object-oriented Java applications and relational databases. It allows developers to map complex domain models to database tables, and write type-safe, performant queries using the Hibernate Query Language (HQL).&lt;/p&gt;
&lt;p&gt;&lt;strong&gt;Quarkus&lt;/strong&gt; has emerged as a Java &lt;a href="https://quarkus.io/"&gt;framework&lt;/a&gt; for building applications and services, focusing on incredibly fast startup times, efficient resource consumption and developer joy.&lt;/p&gt;</description></item><item><title>Agentic AI Patterns for Enterprise Software</title><link>https://javapro-en.svenruppert.com/agentic-ai-patterns-for-enterprise-software/</link><pubDate>Tue, 31 Mar 2026 07:00:01 +0000</pubDate><guid>https://javapro-en.svenruppert.com/agentic-ai-patterns-for-enterprise-software/</guid><description>&lt;p&gt;It is no surprise that software development is increasingly shaped by the integration of AI. As the technology matures, we are moving beyond simple, monolithic AI models or single shot API calls. Modern enterprise architectures are rapidly adopting &lt;em&gt;agentic AI&lt;/em&gt; systems, which orchestrate multiple independent reasoning agents to accomplish complex, real-world tasks. This article explores these powerful patterns, covering the core concepts of agents, their coordination, orchestration models, and crucially how to implement them effectively in enterprise Java applications. &lt;/p&gt;</description></item><item><title>AI without spaghetti: Clean architecture in the age of AI</title><link>https://javapro-en.svenruppert.com/ai-without-spaghetti-clean-architecture-in-the-age-of-ai/</link><pubDate>Tue, 17 Mar 2026 07:00:01 +0000</pubDate><guid>https://javapro-en.svenruppert.com/ai-without-spaghetti-clean-architecture-in-the-age-of-ai/</guid><description>&lt;p&gt;&lt;a href="https://schedule.jcon.one/2026/session/1052623"&gt;&lt;figure class="post-figure"&gt;
 &lt;img src="https://javapro-en.svenruppert.com/uploads/2026/03/2026-Magazin-Artikel-Banner-1024x213.png" alt="" loading="lazy" decoding="async"&gt;
 
 
 
&lt;/figure&gt;
&lt;/a&gt;&lt;/p&gt;
&lt;h2 id="when-just-ship-it-turns-into-lasagna-code"&gt;When “Just ship it” turns into lasagna code&lt;/h2&gt;
&lt;p&gt;We start with a familiar scene: a small experiment that grows faster than its architecture can handle. This is exactly the kind of situation where clean architecture becomes essential. Like layering pasta without checking the recipe, we kept adding features until the structure began to wobble.&lt;/p&gt;
&lt;p&gt;At first everything seems perfectly reasonable. A quick integration with an API, a prompt that produces surprisingly good results. Suddenly the prototype starts solving real problems. The codebase grows organically: a helper class here, a service there.  Maybe a controller that does just a little bit more than it probably should.&lt;/p&gt;</description></item><item><title>High-Demand Workshops at JCON EUROPE 2026 – Tickets Available Now</title><link>https://javapro-en.svenruppert.com/high-demand-workshops-at-jcon-europe-2026-tickets-available-now/</link><pubDate>Mon, 16 Mar 2026 12:00:01 +0000</pubDate><guid>https://javapro-en.svenruppert.com/high-demand-workshops-at-jcon-europe-2026-tickets-available-now/</guid><description>&lt;p&gt;&lt;strong&gt;Cologne&lt;/strong&gt; – JCON EUROPE returns to its venue from April 20-23, once again offering an extensive program for Java enthusiasts. In addition to over 100 speakers and sessions, Monday, April 20, is fully dedicated to hands-on, expert-led &lt;a href="https://schedule.jcon.one/2026/schedule"&gt;workshops&lt;/a&gt;.&lt;/p&gt;
&lt;p&gt;Each workshop is a two-hour deep dive into cutting-edge technologies and real-world development topics. Participants can choose from a total of seven different sessions across two time slots: 1:00–3:00 PM and 4:00–6:00 PM. A coffee break in between provides room for informal networking.&lt;/p&gt;</description></item><item><title>Bring AI into your Jakarta EE apps with LangChain4J-CDI (formerly SmallRye-LLM)</title><link>https://javapro-en.svenruppert.com/bring-ai-into-your-jakarta-ee-apps-with-langchain4j-cdi-formerly-smallrye-llm/</link><pubDate>Wed, 25 Feb 2026 07:00:01 +0000</pubDate><guid>https://javapro-en.svenruppert.com/bring-ai-into-your-jakarta-ee-apps-with-langchain4j-cdi-formerly-smallrye-llm/</guid><description>&lt;p&gt;&lt;strong&gt;Goal&lt;/strong&gt;: This article will demonstrate how to add AI features to a Jakarta EE / MicroProfile application using &lt;strong&gt;LangChain4J‑CDI&lt;/strong&gt;, with simple to implement examples that runs on Payara, WildFly, Open Liberty, Helidon, Quarkus or any CDI 4.x compatible runtime.&lt;/p&gt;
&lt;h2 id="what-is-langchain4j-cdi"&gt;What is LangChain4J-CDI?&lt;/h2&gt;
&lt;p&gt;Langchain4J is a Java library that simplifies the integration of AI and LLMs easier, and with their feature of AI services it provides a declarative and type-safe API for developers to define interfaces that represent AI services, abstracting away the complexities of direct LLM communication&lt;/p&gt;</description></item><item><title>LangChain4j Production-ready features with Quarkus</title><link>https://javapro-en.svenruppert.com/langchain4j-production-ready-features-with-quarkus/</link><pubDate>Thu, 20 Nov 2025 07:00:02 +0000</pubDate><guid>https://javapro-en.svenruppert.com/langchain4j-production-ready-features-with-quarkus/</guid><description>&lt;p&gt;Have you already read the article &amp;ldquo;&lt;strong&gt;Build AI Apps and Agents in Java: Hands-On with LangChain4j&amp;rdquo;&lt;/strong&gt; by Lize Raes in the “30 Years of Java” edition - part 1 - of that magazine? If so, you&amp;rsquo;re familiar with what LangChain4j is for.&lt;/p&gt;
&lt;p&gt;If not, don&amp;rsquo;t worry—I included the link at the end of this article. I recommend reading it before continuing with this one.&lt;/p&gt;
&lt;p&gt;In this article, we&amp;rsquo;ll explore and demonstrate important LangChain4j production-ready features using Quarkus, a lightweight Java framework that integrates seamlessly with LangChain4j.&lt;/p&gt;</description></item><item><title>Local AI with Java: AI Integration Without Cloud Dependency</title><link>https://javapro-en.svenruppert.com/local-ai-with-java-ai-integration-without-cloud-dependency/</link><pubDate>Fri, 02 May 2025 07:00:03 +0000</pubDate><guid>https://javapro-en.svenruppert.com/local-ai-with-java-ai-integration-without-cloud-dependency/</guid><description>&lt;p&gt;The future of artificial intelligence is local. Increasingly, companies are turning to local AI models to ensure data privacy, offline capabilities, and independence from cloud providers. At &lt;a href="https://2025.europe.jcon.one/"&gt;JCON EUROPE 2025&lt;/a&gt;, the two-hour “&lt;a href="https://schedule.jcon.one/session/894517"&gt;AI-based optimization in expedition planning – a practice-oriented workshop&lt;/a&gt;” with Sven Ruppert will demonstrate exactly how to implement this in Java: high-performance, privacy-friendly AI features – directly in your own application, entirely without cloud services.&lt;/p&gt;
&lt;h2 id="focus-on-the-open-source-project-expedition-planner"&gt;Focus on the Open-Source Project “Expedition Planner”&lt;/h2&gt;
&lt;p&gt;At the center is the open-source project &lt;strong&gt;“Expedition Planner&lt;/strong&gt;”, a Java-based web application designed for planning and organizing expeditions. However, this isn’t just theory: participants will work on real-world use cases, integrating local AI models with &lt;strong&gt;Ollama&lt;/strong&gt;, utilizing &lt;strong&gt;Langchain4j&lt;/strong&gt; and &lt;strong&gt;Retrieval Augmented Generation (RAG)&lt;/strong&gt; to optimize task planning and equipment lists intelligently.&lt;/p&gt;</description></item><item><title>Build AI Apps and Agents in Java: Hands-On with LangChain4j</title><link>https://javapro-en.svenruppert.com/build-ai-apps-and-agents-in-java-hands-on-with-langchain4j/</link><pubDate>Wed, 23 Apr 2025 07:00:02 +0000</pubDate><guid>https://javapro-en.svenruppert.com/build-ai-apps-and-agents-in-java-hands-on-with-langchain4j/</guid><description>&lt;p&gt;&lt;a href="https://www.youtube.com/watch?v=bLX9IChLWSc&amp;amp;list=PLFeSAZzYdUodZjQy6a3pCBl43UUem8_E3&amp;amp;index=15"&gt;&lt;figure class="post-figure"&gt;
 &lt;img src="https://javapro-en.svenruppert.com/uploads/2025/03/Magazin-Artikel-Banner-2-1024x214.jpg" alt="" loading="lazy" decoding="async"&gt;
 
 
 
&lt;/figure&gt;
&lt;/a&gt;&lt;/p&gt;
&lt;p&gt;LangChain4j is a java library to make &lt;strong&gt;interactions with AI models and LLMs in Java&lt;/strong&gt; easy, with unified APIs that wrap different models. It also provides tools to let you build more &lt;strong&gt;complex use cases on top of basic functionality&lt;/strong&gt;. At this 2nd anniversary of LangChain4j, we are thrilled to give you a walkthrough of the functionality that enables you to build basic and advanced AI-powered apps in Java.&lt;/p&gt;</description></item><item><title>AI-Powered Form Wizards: Chat, Click, Done</title><link>https://javapro-en.svenruppert.com/ai-powered-form-wizards-chat-click-done/</link><pubDate>Tue, 15 Apr 2025 10:00:23 +0000</pubDate><guid>https://javapro-en.svenruppert.com/ai-powered-form-wizards-chat-click-done/</guid><description>&lt;p&gt;&lt;a href="https://schedule.jcon.one/session/794986"&gt;&lt;figure class="post-figure"&gt;
 &lt;img src="https://javapro-en.svenruppert.com/uploads/2025/04/Magazin-Artikel-Banner-2-1024x214.jpg" alt="" loading="lazy" decoding="async"&gt;
 
 
 
&lt;/figure&gt;
&lt;/a&gt;&lt;/p&gt;
&lt;h2 id="transforming-form-filling-into-a-conversational-experience"&gt;Transforming Form Filling into a Conversational Experience&lt;/h2&gt;
&lt;p&gt;Forms are everywhere—tax declarations, job applications, or even signing up for a new service. Although some forms are simple, many include ambiguous fields, complicated logic, or subpar design. This may frustrate users and make them more likely to make mistakes. Completing paperwork shouldn&amp;rsquo;t be like solving a puzzle&lt;/p&gt;
&lt;p&gt;Traditional forms, with their rigid structures and often confusing layouts, present a significant hurdle for users. Our objective was to dismantle this static paradigm and replace it with a dynamic, conversational interface. Instead of forcing users to navigate a pre-defined maze of fields, we envisioned an interactive experience where an AI assistant adapts in real-time. This approach fundamentally shifts the burden of data entry and validation. A user chatting with an AI can dramatically reduce errors and streamline the overall process. Imagine a conversation, not a questionnaire, where the AI guides you through each step.&lt;/p&gt;</description></item><item><title>Securing the Future of AI: Authorization for Java RAG Systems using LangChain4j and OpenFGA</title><link>https://javapro-en.svenruppert.com/securing-the-future-of-ai-authorization-for-java-rag-systems-using-langchain4j-and-openfga/</link><pubDate>Mon, 14 Apr 2025 07:00:02 +0000</pubDate><guid>https://javapro-en.svenruppert.com/securing-the-future-of-ai-authorization-for-java-rag-systems-using-langchain4j-and-openfga/</guid><description>In this post, we explore how to build a robust Java-based RAG system by integrating LangChain4j with OpenFGA for fine-grained, relationship-based access control. Learn how to tackle the unique security challenges of RAG applications—from dynamic context and complex document relationships to real-time authorization checks—and follow step-by-step examples that show you how to implement a secure syst</description></item></channel></rss>