LLM on JAVAPRO International

High-Performance Vector-Search Grids with Java

Wed, 08 Apr 2026 07:00:02 +0000

The rapid rise of Generative AI has fundamentally changed how modern systems are designed. While much of the attention has focused on large language models and inference pipelines, the real differentiator in production systems lies elsewhere: in the infrastructure that delivers context to those models. Retrieval-Augmented Generation (RAG) has become the de facto pattern for enterprise GenAI. It relies on fast, scalable access to embeddings, metadata, and relationships. Yet for Java developers, building such systems at scale has remained a challenge. External vector databases introduce latency, fragmentation, and operational complexity. Distributed caches struggle with memory inefficiency and serialization overhead. Traditional databases cannot handle high-dimensional similarity search at the required speed.

AI without spaghetti: Clean architecture in the age of AI

Tue, 17 Mar 2026 07:00:01 +0000

When “Just ship it” turns into lasagna code

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.

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.

Bring AI into your Jakarta EE apps with LangChain4J-CDI (formerly SmallRye-LLM)

Wed, 25 Feb 2026 07:00:01 +0000

Goal: This article will demonstrate how to add AI features to a Jakarta EE / MicroProfile application using LangChain4J‑CDI, with simple to implement examples that runs on Payara, WildFly, Open Liberty, Helidon, Quarkus or any CDI 4.x compatible runtime.

What is LangChain4J-CDI?

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

Solutions to achieve desired results from Generative AI Models

Wed, 10 Dec 2025 07:00:03 +0000

Rise of Generative AI

Generative AI (GenAI) has gained significant prominence in the last couple of years. This technological breakthrough has created the possibility of integrating various innovative use cases into applications across domains. Organizations of all sizes, small and large, have started exploring, experimenting and adopting GenAI. Tools, frameworks and platforms are rapidly evolving and allow application developers to easily integrate GenAI capabilities into their existing applications or to build new innovative applications leveraging GenAI. There are lots of options available – GenAI capabilities available as services, foundation models, open-source models and model provider platforms that allow hosting of models.

Building Local LLM AI-Powered Applications with Quarkus, Ollama, and Testcontainers

Tue, 09 Sep 2025 07:00:01 +0000

Traditionally, many AI-powered applications rely on cloud-based APIs or centralized services for model hosting and execution. While this approach has its advantages, such as scalability and ease of use, it also introduces challenges around latency, data privacy, and dependency on third-party providers.

This is where local AI models shine. By running models directly within your application’s infrastructure, you gain greater control over performance, data security, and deployment flexibility. However, building such systems requires the right tools and frameworks to bridge the gap between traditional software development and AI model integration.

Evaluating RAG Pipelines with the RAG Triad

Wed, 14 May 2025 07:00:03 +0000

Retrieval-Augmented Generation (RAG) emerged as a dominant framework for feeding Large Language Models (LLMs) the context beyond the scope of their training data and enabling LLMs to respond with more grounded answers and fewer hallucinations based on that context.

However, designing an effective RAG pipeline can be challenging. You need to answer questions such as:

How should you parse and chunk text documents for vector embedding? What chunk size and overlay size should you use?
What vector embedding model should you use?
What retrieval method should I use to fetch the relevant context? How many documents should you retrieve by default? Does the retriever actually manage to retrieve the applicable documents?
Does the generator actually generate content that is in line with the retrieved context? What parameters (model, prompt template, temperature) work better?

The only way to objectively answer these questions is to measure how well the RAG pipeline works, but what exactly do you measure, and how do you measure it? This is the topic I’ll cover here.

Local AI with Java: AI Integration Without Cloud Dependency

Fri, 02 May 2025 07:00:03 +0000

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 JCON EUROPE 2025, the two-hour “AI-based optimization in expedition planning – a practice-oriented workshop” 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.

Focus on the Open-Source Project “Expedition Planner”

At the center is the open-source project “Expedition Planner”, 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 Ollama, utilizing Langchain4j and Retrieval Augmented Generation (RAG) to optimize task planning and equipment lists intelligently.

AI Tools for Jakarta EE

Thu, 24 Apr 2025 23:42:38 +0000

Introduction

Artificial Intelligence (AI) is transforming the world of software development, including Jakarta EE. Traditionally, developers relied on project generators, visual designers, and IDE auto-completion to build applications. However, these tools often lacked adaptability, context awareness, and efficiency. AI-powered tools such as Payara Starter and Jeddict AI Assistant are now addressing these limitations, accelerating development workflows, and empowering developers to focus on innovation. This article explores how these tools enhance Jakarta EE development, using a conference application as a practical example. Additionally, it discusses future possibilities, including AI assistants integrated with Payara Server for server setup and diagnostics.

Build AI Apps and Agents in Java: Hands-On with LangChain4j

Wed, 23 Apr 2025 07:00:02 +0000

LangChain4j is a java library to make interactions with AI models and LLMs in Java easy, with unified APIs that wrap different models. It also provides tools to let you build more complex use cases on top of basic functionality. 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.

1BRC with AI - curious and curiouser said the LLM

Wed, 15 Jan 2025 11:48:56 +0000

Did you try turning it off and on first?

(I promise this is the last 1BRC-related post). Read on to discover how large language models (LLMs) performed in generating Java code, their strengths in context-aware development, and challenges such as hallucinations and nuanced errors. Learn what makes a good AI dev tool and what makes a great IDE integration.

A definition of insanity is repeating an action and expecting a different outcome. As developers, we’re used to doing that :-) It’s part of our operating manual.

My Top 10 Principles for getting the best from AI (for developers)

Mon, 02 Dec 2024 11:56:54 +0000

AI tools for developers: principles, insights, and the importance of clean code.

Every day, I encounter a new AI tool, whether a new capability is added to an existing tool or an entirely new offering. I actively use several AI tools, including ChatGPT, Grammarly, and Amazon Q Developer, each serving different purposes. I pay for pro access to ChatGPT and Grammarly, though I sometimes consider switching to Claude.ai, which occasionally proves invaluable. s a view of AI tools for developers: my principles, insights and ultimately the realisation that development practises such as clean code is more essential than ever