Machine Learning on foojay.io - Friends of OpenJDK

How to Create a Spring Boot Fraud Scoring Service

Fri, 31 Jul 2026 08:45:43 +0000

Most Java teams who want a machine learning model in production end up standing up a Python service and calling it over HTTP. That works, but it buys you, as a Java developer, a second runtime, a second deployment pipeline, a network hop on every prediction, and a team boundary that turns retraining into someone else’s ticket.

Deep Netts removes that split: it’s a pure-Java deep learning library, so the model trains in Java, serializes to a file, and loads back into your Spring Boot application as an ordinary bean. Predictions become in-process method calls measured in microseconds, with nothing extra to deploy, secure, or monitor.

JC-AI Newsletter #16

Tue, 09 Jun 2026 18:28:33 +0000

Over the past two weeks, the field of artificial intelligence has continued its remarkable pace of advancement. As AI becomes increasingly woven into the fabric of daily life, shaping how we work, communicate, and make decisions, it is both timely and valuable to step back and understand the broader trajectory of this technology. Whether the developments around us feel promising or challenging, one truth remains clear: AI is not simply going away. It is here to stay, and understanding its evolution is essential from many perspectives. Have you ever wondered what harness engineering is, how evals attempt to move traditional unit tests onto a probabilistic plane, or how AI is reshaping entire industries across various branches? Let’s start.

"Agentic" Was Everywhere at Money20/20 Amsterdam

Fri, 05 Jun 2026 08:55:48 +0000

I walked the floor at Money20/20 in Amsterdam with a simple little mission: count the first ten vendor booths using “AI,” “agent,” or “agentic” in their pitch.

My first impression was that this would be hard. Hundreds of organizations, and the buzzwords felt oddly absent — payments, core banking, compliance, the usual fintech furniture, but not the wall-to-wall “agentic everything” I’d braced for. I jotted down my first ten and thought: huh, AI is barely here.

Explore Spring AI SDK - Amazon Bedrock AgentCore - Part 1

Mon, 20 Apr 2026 13:44:54 +0000

Introduction

Artificial intelligence has rapidly expanded across every industry since the inception of ChatGPT. It represents a breakthrough in how we build and use software. Moreover, this breakthrough technology has driven major transformation. At the same time, it has created significant noise and hype.

Today, AI is no longer experimental. Instead, it has become essential, much like electricity and the internet. As a result, it now plays a key role in our daily lives. Overall, this shift reflects strong technological acceleration across industries.

JC-AI Newsletter #15

Fri, 20 Mar 2026 07:56:01 +0000

Over the past two weeks, the field of artificial intelligence has continued its remarkable pace of advancement. As AI becomes increasingly woven into the fabric of daily life, shaping how we work, communicate, and make decisions, it is both timely and valuable to step back and understand the broader trajectory of this technology. Whether the developments around us feel promising or challenging, one truth remains clear: AI is not simply leaving. It is here to stay, and understanding its evolution is essential from many perspectives.

JC-AI Newsletter #14

Tue, 03 Mar 2026 15:11:53 +0000

Two weeks have passed and a lot have been happening on the field of artificial-intelligence.

Two weeks have passed and a lot has been silently yet visibly happening in the field of artificial intelligence. This newsletter brings interesting developments, including Dario Amodei’s (Anthropic) view on the progress achieved in the LLM field and his response to the utilization of these models for specific kinds of military purposes, as well as OpenAI’s response to it. Aside from the fact that development may follow more sigmoids instead of exponential progress, it is important to have awareness of utilization across branches. Does prompting and clarifying the goal influence agent responses, and if so, how? How far are we from reliable robotics applications? How much bias is introduced when clinical data is being analyzed?

From “Crypto AI” to general AI: Do AI agents dream of electric langoustines?

Mon, 23 Feb 2026 18:11:54 +0000

A Blade Runner riff for a world where the lobster ships paid endpoints while humans still argue about the roadmap.

The shift that matters for agent commerce - From “Crypto AI” to general AI

Today, you can search the web all day and never see an invoice.

That happens because you are not the paying client.

The commerce runs through ads, affiliate deals, and platform incentives, so results often optimize for who pays, not for what you asked for.

Enabling AI Agents to Use a Real Debugger Instead of Logging

Mon, 16 Feb 2026 21:12:13 +0000

Every Java developer has been there. Something breaks, and the first instinct is to litter the code with System.out.println(">>> HERE 1"). Then HERE 2. Then HERE 3 --- value is: " + x. Rebuild. Rerun. Stare at the console. Repeat.

We’ve been doing this for decades. And now, so have our AI agents.

When you ask an AI coding assistant to debug a Java application, it almost always reaches for the same playbook: add logging statements, recompile, rerun, read the output, and reason about what happened. It’s the println debugging loop, automated — but it’s still println debugging.

Machine Learning in Java - SPAM detection using ONNX

Tue, 10 Feb 2026 06:51:50 +0000

Believe it or not, it is possible to do Machine Learning in Java. In this article I go over how to implement a Spring Boot API for Spam Detection using an advanced anti-spam model from the Hugging Face onnx-community and Microsoft’s ONNX Runtime for Java .

We will package the API up as a Docker image which we can run a container from using docker or podman, and I guess in theory you could deploy on your Kubernetes cluster, if you (are) fancy.

JC-AI Newsletter #13

Thu, 05 Feb 2026 21:12:12 +0000

Two weeks have passed, and it is time to present a new collection of readings that may shape developments, utilization or ideas in the field of artificial intelligence in 2026.

While significant activity characterizes the AI field, many unresolved research, design, and implementation challenges continue to impact progress. Future advancement depends heavily on understanding the nature of these challenges to approach probabilistic problems from the appropriate directions. This JC-AI newsletter features insightful interviews with key figures in the field, enabling readers to ask the right questions and compare visions of an ‘uncertain future’ against current capabilities to maintain a grounded perspective.

JC-AI Newsletter #12

Wed, 14 Jan 2026 07:15:44 +0000

F irst of all, Happy New Year 2026! This year is designated in the Chinese Calendar as the Year of the Fire Horse (starting on February 17.). The year 2026 brings not only tremendous energy to AI development but also, in my humble opinion, many breakthroughs in the field.

Although there have been many small steps toward the field’s evolution, it often feels that development is stagnating, applying known or slightly tweaked strategies to non-deterministic problems while expecting deterministic results. This includes the often misleading benchmarking strategies (deterministic) performed on synthetic datasets.

The End of One-Sized-Fits-All Prompts: Why LLM Models Are No Longer Interchangeable

Sun, 14 Dec 2025 18:48:31 +0000

For developers and product builders, one assumption has guided the last few years of LLM application development. To improve your product, just swap in the latest frontier large language model. Flip a single switch and your tool’s capabilities level up.

But that era is over. We’re now seeing that new models like Anthropic’s Claude Sonnet 4.5 and OpenAI’s GPT-5-Codex have diverged in fundamental ways. The choice of which model to use is no longer a simple engineering decision but a critical product decision. Flip that switch today… and the very texture of your product changes.

How CodeRabbit's Agentic Code Validation helps with code reviews

Sun, 07 Dec 2025 11:10:21 +0000

The 2025 Stack Overflow survey reveals a paradox: while 84% of developers express confidence in adopting AI tools, nearly half (48%) still distrust the accuracy of their outputs. This tension between optimism and skepticism has reshaped how teams think about quality assurance.

From PRD to PR in days (not weeks)

The bottleneck in software development has fundamentally shifted from writing code to validating it.

In the early days of AI-assisted development, the workflow was straightforward: AI suggested code, humans read the suggested snippet and then decided whether or not to accept that suggestion. Tab completion wrote boilerplate. Copilot suggested functions. But a senior engineer still manually validated and chose each line of code to ensure its quality, structure, and safety before making a pull request.

JC-AI Newsletter #10

Wed, 26 Nov 2025 18:39:40 +0000

Fourteen days have passed, and it is time to present a fresh collection of readings that could influence developments in the field of artificial intelligence.

This newsletter focuses on examining how agentic AI systems improve accuracy, tutorials on agentic system architecture, and importnat security challenges arising from increased not only from agentic AI systems adoption. This edition of the AI newsletter includes compelling discussions and interviews about the future of AI and approaches.

JC-AI Newsletter #9

Wed, 12 Nov 2025 15:21:12 +0000

Fourteen days have passed, and it is time to present a fresh collection of readings that could influence developments in the field of artificial intelligence.

This newsletter focuses on examining how AI enhances productivity through enterprise studies, tutorial, agentic system architecture, GraphRAG, evaluating risk methodologies in agentic systems, and the security challenges arising from increased AI-LLM adoption. This edition of the AI newsletter includes a compelling discussion between six of the most influential leaders in artificial intelligence, along with additional content.

JC-AI Newsletter: Easy Access to Expanding Challenges

Tue, 04 Nov 2025 18:13:33 +0000

A few months ago, I launched the AI Newsletter to provide a minimally biased perspective on the growing challenges surrounding artificial intelligence.

My primary motivation was and remains to be serving the community not only by showing how to use and access specific services for utilizing Large Language Models, but also by support a deeper understanding of the broader artificial intelligence landscape.

Many of the core challenges that have emerged around LLMs have not been and still not properly addressed, often omitted due to their uncomfortable implications.

JC-AI Newsletter #8

Thu, 30 Oct 2025 06:36:12 +0000

Fourteen days have passed, and it is time to present a fresh collection of readings that could influence developments in the field of artificial intelligence.

This newsletter focuses on examining how AI enhances productivity through enterprise studies, agentic system architecture, attack vectors, Model Context Protocol (MCP) implementation, Agent-to-Agent (A2A) protocol, Java code generation within IDEs, LLM benchmarking methodologies, and the security challenges arising from increased AI-LLM adoption.

The world influenced by LLM is changing very quickly, let’s start…

JC-AI Newsletter #7

Tue, 14 Oct 2025 05:35:01 +0000

Fourteen days have passed, and it is time to present a fresh collection of readings that could influence developments in the field of artificial intelligence.

Beyond focused tutorials that can enhance your understanding of AI applications, this newsletter concentrates on Hallucination, Java Code Generation, Testing, Agentic System Architecture and LLM benchmarking methodologies designed to ensure models accuracy and competency in handling complex contextual information.

The world influenced by LLM is changing very quickly, let’s start…

JC-AI Newsletter #6

Wed, 01 Oct 2025 17:18:16 +0000

Fourteen days have passed, and it is time to present a fresh collection of readings that could influence developments in the field of artificial intelligence.

Beyond opinion pieces and Java focused tutorials that can enhance your understanding of AI applications, this newsletter concentrates on Hallucination, Security, RAG and LLM benchmarking methodologies designed to ensure models accuracy and competency in handling complex contextual information.

The world influenced by LLM is changing very quickly, let’s start…

JC-AI Newsletter #5

Thu, 18 Sep 2025 07:19:33 +0000

Fourteen days have passed, and it is time to present a fresh collection of readings that could influence developments in the field of artificial intelligence.

Beyond opinion pieces and Java focused tutorials that can enhance your understanding of AI applications, this newsletter concentrates on LLM benchmarking methodologies designed to ensure models accuracy and competency in handling complex contextual information.

The world influenced by LLM is changing very quickly, let’s start…

Stochastic AI Agility: Breaking Cycles of Debt

Wed, 10 Sep 2025 11:27:16 +0000

The launch of ChatGPT in November 2022 has significantly influenced and potentially transformed industry standards across multiple sectors. While my primary focus remains on the information technology sector, observations indicate that its impact extends across all industries and affects the daily lives of consumers and professionals alike.

This article examines the observed changes in project management practices. These observations are govern by Role 17: Stochastic AI Agility. Over past two decades, the industry has actively pursued the implementation of agile methodologies to enable iterative product delivery.

JC-AI Newsletter #4

Tue, 02 Sep 2025 20:27:52 +0000

14 days have passed and it’s time for a new batch of readings that could shape developments in the field of artificial intelligence.

The current newsletter vol. 4 offers us a closer look at several different areas of artificial intelligence. We start with the topic of energy consumption and the environmental impact of systems serving artificial intelligence, and continue with automation, how we obtain data for RAG, robustness of GenAI systems, vibe-coding and more.

JC-AI Newsletter #3

Tue, 19 Aug 2025 08:06:34 +0000

The first and second newsletters introduced a 14-day cadence, and even though it is the holiday season for many of us, we are sticking to the promised period.

The current newsletter vol.3, brings a collection of valuable articles focusing on challenges that are commonly reported through reported breakthroughs in the field of artificial intelligence. Although some articles may remain open or contain suggestions for future research due to the intensive development and utilization efforts of agentic AI systems, these articles can be considered valuable to the community, increasing awareness and understanding of ongoing challenges.

New Java Benchmark for Coding LLMs puts GPT-5 at the top

Mon, 18 Aug 2025 08:06:40 +0000

The Brokk Power Ranking is a new open-source coding benchmark , featuring 93 tasks from large, real-world codebases. You can check out the current Power Ranking here .

SWE-bench is the closest thing we have to a standard, objective benchmark for LLM coding performance, but it has a bunch of issues, the largest of which are that it’s Python-only, and it’s old enough that almost certainly some labs are now training to the test. (Epoch AI has a great writeup on the more subtle problems with SWE-bench if you want to go deeper.)

JC-AI Newsletter #2

Tue, 05 Aug 2025 06:30:03 +0000

The JC-AI Newsletter Vol.2 brings again a very interesting collection of articles worth considering.

The world influenced by LLM is changing very quickly, let’s start…

article: OpenAI CEO Sam Altman warns of an AI ‘fraud crisis’

author : Clare Duffy, CNN
date : 2025-07-22
desc.: Sam Altman discusses the serious potential for current AI abuse. Although the example of attacks on financial institutions is mentioned, Sam Altman warns of the broader impact before one even takes advantage of LLM agent systems.

AI Applications with LangChain4j Guardrails and Spring Boot

Tue, 29 Jul 2025 11:16:31 +0000

As AI applications become increasingly complex, ensuring that language models behave predictably and safely is paramount. LangChain4j’s guardrails feature provides a powerful framework for validating both the inputs and outputs of your AI services.

This article demonstrates how to implement comprehensive guardrails in a Spring Boot application, with practical examples that you can adapt to your use cases.

📦 Complete source code available at : github.com/rokon12/guardrails-demo

Understanding LangChain4j Guardrails

In LangChain4j, guardrails are validation mechanisms that operate exclusively on AI Services, the framework’s high-level abstraction for interacting with language models. Unlike simple validators, guardrails provide sophisticated control over the entire AI interaction lifecycle.

CodeRabbit Tutorial for Java Developers

Mon, 28 Jul 2025 12:43:19 +0000

CodeRabbit is an AI-powered code review tool that integrates seamlessly with your Git workflow to provide intelligent, automated code reviews.

For Java developers, CodeRabbit offers specialized analysis that understands Java syntax, best practices, and common patterns.

Getting Started

Prerequisites

A GitHub, GitLab, Azure DevOps, or Bitbucket repository.
Java project with standard structure (Maven or Gradle).
Admin access to your repository.

Setup Process

Install CodeRabbit
- Visit CodeRabbit.ai .
- Sign up using your credentials, while noting that CodeRabbit is free for OSS, supports GitHub, GitLab, Azure DevOps, and Bitbucket.
- Grant necessary permissions to your repositories.
Repository Configuration
- Select the Java repositories you want CodeRabbit to review.
- CodeRabbit automatically detects Java projects and configures appropriate rules.
Initial Setup Verification
- Create a test pull request with a simple Java change.
- Verify CodeRabbit comments appear within minutes.

Core Features for Java Development

1. Code Quality Analysis

CodeRabbit analyzes your Java code for:

AI Newsletter #1

Tue, 22 Jul 2025 05:39:26 +0000

There is a lot going on in today’s technological world, but the most intense and vibrant area is undoubtedly the field of artificial intelligence. After brainstorming, our Java Champion Education group agreed to create a newsletter with a 14 days cadence. In our newsletters, we will include a collection of recently read interesting resources in the field of artificial intelligence with a short description.

Although the stream of published articles is very large and the ability to read them all is an illusion, the published selection, such as the below is implicitly narrowed. The purpose of the AI Newsletter is to help everyone stay informed and expand their knowledge in areas related to artificial intelligence.

How to Make a RAG Application With LangChain4j

Thu, 17 Jul 2025 20:42:12 +0000

Retrieval-augmented generation, or RAG, introduces some serious capabilities to your large language models (LLMs). These applications can answer questions about your specific corpus of knowledge, while leveraging all the nuance and sophistication of a traditional LLM.

This tutorial will take you through the ins and outs of creating a Q&A chatbot using RAG. The application will:

Retrieve data from a MongoDB Atlas database.
Embed and store documents as vector embeddings.
Use LangChain4J to query the database and augment LLM prompts with the retrieved data.
Enable secure, scalable, and efficient AI-powered applications.

If you want to see the completed application, it is available in the GitHub repository .

Understanding MCP Through Raw STDIO Communication

Thu, 17 Jul 2025 15:57:05 +0000

Deep Dive into the Model Context Protocol

Ever wondered how AI assistants like Claude actually communicate with external tools and services? While most tutorials focus on using pre-built SDKs and frameworks, this article takes a different approach—we’ll dissect a production MCP server built from scratch using only Java’s standard libraries and raw STDIO communication.

By stripping away all the abstractions and implementing the Model Context Protocol directly, we’ll uncover the surprisingly elegant mechanics that enable AI systems to discover, understand, and execute tools.

The Great Data Reimagination: From Static to Agile in the AI Era

Tue, 15 Jul 2025 13:44:06 +0000

We’re in the middle of a fundamental change in how enterprise software works. In the next decade, your database will become your AI.

Just five years ago, choosing the right kind of database to support their applications presented complexity for many developers: relational or NoSQL? Structured or unstructured? Flexible or predictable? They didn’t know exactly what their data would look like in six months, but what they did know was that it was certain to change. This led many to make a rebel’s choice to reject the rigid structure of SQL databases for something more fluid and adaptable.

How I Improved Zero-Shot Classification in Deep Java Library (DJL) OSS: Enhancing Machine Learning Model Translators

Wed, 09 Jul 2025 10:51:16 +0000

Did you know the Deep Java Library (DJL) powers Spring AI and Redis OM Spring? DJL helps you run machine learning models right inside your Java applications.

Check them out:

Spring AI with DJL: https://docs.spring.io/spring-ai/reference/api/embeddings/onnx.html

Semantic Search with SpringBoot & Redis: https://foojay.io/today/semantic-search-with-spring-boot-redis/

TL;DR:

You’re doing zero-shot classification in a Java app using DJL.
DJL didn’t handle some models well — like DeBERTa. It missed support for token_type_ids, assumed wrong label positions, and oversimplified the softmax implementation.
It was fixed by reading the model config files and adjusting DJL’s translator logic.
Now DJL gives correct results across different models — just like the Transformers library does in Python.
The fix is merged and will probably be released with version 0.34.0.

What’s Zero-Shot Classification (and Why It Matters)

Zero-shot classification is a machine learning technique that allows models to classify text into categories they haven’t explicitly seen during training. Unlike traditional classification models that can only predict classes they were trained on, zero-shot classifiers can generalize to new, unseen categories.

Intro to RAG: Foundations of Retrieval Augmented Generation, part 2

Tue, 10 Jun 2025 21:54:49 +0000

In the last post , we discussed the basics of Retrieval Augmented Generation (RAG) and how it enhances the capabilities of Large Language Models (LLMs) by integrating them with external knowledge sources. We also introduced the concept of vector embeddings and their role in semantic search.

In this post, we’ll dive deeper into the different layers of RAG, including vector RAG, graph RAG, and agents. We’ll explore how these layers can be combined to create more powerful and effective AI systems.

Intro to RAG: Foundations of Retrieval Augmented Generation, part 1

Tue, 27 May 2025 14:42:43 +0000

Retrieval Augmented Generation (RAG) may sound complex, but it accurately represents the process of the system. RAG is a method that enhances the capabilities of Large Language Models (LLMs) by integrating them with external knowledge sources.

Each term represents a piece of the puzzle:

Retrieval - data retrieved from some external source outside the LLM (most often a database, but can include files, webpages, etc)
Augmented - “augmenting” (or adding to) an LLM’s training data. This could include recent or private information that it did not have access to during its training period. Most often, this is done by adding the data to the prompt (or input) to the LLM.
Generation - this is where LLMs are exceptional. They generate a response (text, image, video, etc) that is similar to the data being provided in the input. This is generated from probabilities, so cannot guarantee 100% consistency.

Instead of relying solely on the model’s internal training data, RAG retrieves relevant information from databases or document collections to ground its responses in factual and up-to-date content. This approach not only improves the accuracy and reliability of the generated outputs but also allows the system to adapt to specific contexts or domains, making it a powerful tool for many personal and professional applications.

How Deep Netts and Java AI Transformed Particle Physics

Mon, 19 May 2025 10:58:34 +0000

At the intersection of nuclear physics and artificial intelligence, Jefferson Lab is leveraging Java-based AI to overcome one of the most computationally intense challenges in modern science: reconstructing particle trajectories from high-frequency electron scattering experiments.

Each second, over 16,000 interactions are recorded as particles pass through a complex array of drift chambers. Traditional reconstruction methods—based on mathematical likelihood calculations—must sift through thousands of signal combinations to identify valid particle tracks. The result? Up to 300 milliseconds of processing per event on a single core, leading to massive compute demands.

Building FormPilot

Tue, 06 May 2025 10:00:04 +0000

Disclaimer: This article details an experimental project built for learning and demonstration purposes. The implementation described is not intended as production-grade solution. Some parts of the code were generated using JetBrains’ AI Agent, Junie .

Have you ever found yourself filling out the same information on web forms over and over again? Name, email, address, phone number… it’s tedious and time-consuming. As a developer who values efficiency, I decided to tackle this problem head-on by building FormPilot, an intelligent form filler that leverages the power of Large Language Models (LLMs) to fill out forms with contextually appropriate information automatically.

Foojay Webinar: Java's Place in the AI Revolution

Mon, 28 Apr 2025 15:53:25 +0000

This first online Foojay Webinar highlights Java’s place in the AI revolution, focusing on exploring AI/ML using pure Java tools.

AI and Machine Learning (ML) are becoming essential in modern software development. For Java developers, there’s no need to switch technology stacks. It’s now possible to build, train, and deploy ML models using tools available directly within the Java ecosystem.

Register for Foojay Webinar: "Java's Place in the AI Revolution"

Wed, 09 Apr 2025 13:15:20 +0000

This first online Foojay Webinar will highlight Java’s place in the AI Revolution, focusing on Exploring AI/ML Using Pure Java Tools.

This webinar focuses on practical predictive AI/ML approaches in pure Java. We’ll walk through key Java libraries, show how to structure and train models, and discuss how Java’s core strengths, ie, JVM performance, type safety, and enterprise integration, can be used to build scalable AI solutions.

Run AI-enabled JakartaEE/MicroProfile apps with LangChain4j

Mon, 12 Aug 2024 22:14:36 +0000

Artificial Intelligence (AI) is an exciting and disruptive field that is already transforming businesses, and even entire industries, by enabling automation, improving decision-making and unlocking new insights from data.

With the rise in large language models (LLMs) such as ChatGPT, there is a significant shift in the performance of AI and its potential to drive enterprise value. So, how will this impact on software development and the creation of cloud-native Java applications for enterprises?

Foojay Podcast #56: Vectors in Java Code, Databases, and LLMs

Mon, 08 Jul 2024 07:33:28 +0000

In this Foojay podcast, we enter the world of mathematics by discussing Vectors and how they are crucial for AI and machine learning.

As ChatGPT explains: “A Vector is a mathematical structure that holds numerical values. Vectors are fundamental to the field of Artificial Intelligence, as they allow mathematical operations to be performed efficiently and form the basis of many machine learning algorithms.”

OK, but… how are these vectors crucial for the whole Artificial Intelligence evolution?

Foojay Podcast #53: JCON Report, Part 5 – CQRS, JOOQ, GraphQL, API, Vaadin, OpenRewrite, ErrorProne, Gateways, Proxies,...

Mon, 17 Jun 2024 09:24:52 +0000

This is the final part of the JCON interviews. Did I save the best for last? It’s up to you to decide…

In this episode you’ll hear Simon Martinelli, Nicolas Fränkel, Marcus Hellberg, Rick Ossendrijver, and Abdel Sghiouar.

We talked about a bunch of topics like evolving your APIs, GraphQL, Java versus Kotlin versus Rust, Vaadin, AI and ChatGPT, OpenRewrite, ErrorProne, Infrastructure, and a lot more.

Video

Podcast Apps

You can listen and subscribe to the Foojay Podcast on:

Foojay Podcast #49: JCON Report, Part 1 - JUGs, Communities, Generative AI, and more!

Tue, 21 May 2024 06:05:39 +0000

On Tuesday, May 14th, the Foojay Podcast went live at the JCON conference in Cologne, Germany, to talk with speakers and visitors about all things Java.

We had so many amazing talks that we will combine them into several podcast episodes in the next weeks.

This is part 1 about JUGs, Communities, Open Source, Generative AI, LangChain4j, Machine Learning!

Video

Podcast Apps

You can listen and subscribe to the Foojay Podcast on:

Building a Simple Home Assistant using Langchain4j and Raspberry Pi

Sun, 12 May 2024 05:31:16 +0000

Many believe that the future of IoT is AI. Building a Smart Home Assistant is less complex today than ever before. AI has become so accessible that you only need an internet connection and a computer to connect to an API.

While training specialized deep learning models or using commercial APIs to harness machine learning for specific deterministic use cases is still an option, it is now more common and accessible to use LLMs. Today, you can effortlessly utilize numerous LLMs from various providers through an LLM orchestration framework like Langchain4j . This framework not only allows the use of LLMs but also provides components that simplify the creation of AI applications such as chatbots and question-answering systems. With these tools, anyone can assemble a Generative AI-powered app in minutes.

Foojay Podcast #47: Artificial Intelligence and Machine Learning with Java

Mon, 15 Apr 2024 09:59:42 +0000

About one and a half years ago, ChatGPT was launched.

The way we search for information and develop software has changed a lot since then as the use of Artificial Intelligence suddenly became a lot easier.

What can we expect in the near future, and how can we program AI ourselves with Java? Let’s find out…

Video

Podcast Apps

You can listen and subscribe to the Foojay Podcast on:

Calling Gemma with Ollama, TestContainers, and LangChain4j

Fri, 12 Apr 2024 13:55:38 +0000

Lately, for my Generative AI powered Java apps, I’ve used the Gemini multimodal large language model from Google. But there’s also Gemma , its little sister model.

Gemma is a family of lightweight, state-of-the-art open models built from the same research and technology used to create the Gemini models.

Gemma is available in two sizes: 2B and 7B. Its weights are freely available, and its small size means you can run it on your own, even on your laptop. So I was curious to give it a run with LangChain4j .

Search in Documentation with a JavaFX LangChain4j Chat

Wed, 10 Apr 2024 18:09:59 +0000

At the Fosdem conference in Brussels on February 3rd, I gave a presentation about using an existing documentation set as the data for a ChatGPT-like application, created with JavaFX and LangChain4J.

The video and links of that presentation are available here , and this post is a more detailed explanation of that application.

What is LangChain4j

The goal of LangChain4j is to simplify the integration of AI and LLM capabilities into Java applications. The project lives on GitHub , and has a separate repository with demo applications .

State of Open (Source?!) and Free AI

Thu, 15 Feb 2024 13:04:44 +0000

Disclaimer: This article is on the things I learned/observed spending the day in AI and Machine Learning Developer Room at FOSDEM 24. Opinions and statements are mine and have nothing to do with my employer. This article might raise more questions than answers, but in my opinion, we all need more awareness on this topic and get familiar with the (right) questions that are to be answered.

FOSDEM

FOSDEM (Free Open-Source Developers’European Meeting) is a community-organised event that is free and non-commercial. The aim is to provide a venue for free and open-source software developers and communities to:

Using AI to Create JFR Event Descriptions

Fri, 29 Dec 2023 05:42:16 +0000

JFR (JDK Flight Recorder) is the default profiler for OpenJDK (see my other blog posts for more information).

What makes JFR stand out from the other profilers is the ability to log many, many different events that contain lots of information, like information on class loading, JIT compilation, and garbage collection.

You can see a list of all available events on my JFR Event Collection website:

This website gives an overview of the events, with descriptions from the OpenJDK, their properties, examples, configurations, and the JDK versions in which every event is present. However, few descriptions are available, and the available texts are mostly single sentences.

Virtual Event: JetBrains AI Launch Event

Mon, 04 Dec 2023 11:32:32 +0000

Don’t miss the online JetBrains AI launch event, where we’ll release our AI-powered coding companion, JetBrains AI Assistant.

With JetBrains AI, your favorite tools gain new abilities while you are empowered with more information at your fingertips.

Free yourself from the routine and stay in the flow like never before!

Join the JetBrains AI launch event online ! December 6, 5:00 pm (CET) | 8:00 am (PST).

Learn more about JetBrains AI and AI Assistant from the creators themselves.

Webinar: Harnessing the Power of AI Assistant in IntelliJ IDEA

Tue, 28 Nov 2023 16:38:47 +0000

AI Assistant provides AI-powered features for software development based on the JetBrains AI service. The service transparently connects you, the IDE user, to different large language models.

In this session, Anton Arhipov will demonstrate the capabilities of AI Assistant in IntelliJ IDEA. You will learn how the tool helps you explore and improve existing code as well as write new code in different scenarios.

Generative AI and Java - hype or urgent reality?

Mon, 06 Nov 2023 07:59:04 +0000

It’s hard to grasp that it’s been about a year since Chat GPT and other generative AI tools burst onto the scene. We’re all still grappling with, well, everything about them. Whatever equilibrium we eventually find, it’s clear that the world is changing. The whole world mind, not just the IT industry.

Olimpiu Pop and I have debated the situation multiple times, and we realised that there’s lots of rumour around AI and Java but not much in the way of fact.

Book review: “Developing Apps with GPT-4 and ChatGPT”

Sun, 22 Oct 2023 06:05:28 +0000

Whether you’re pro or con the usage of AI, LLMs, and ChatGPT one cannot deny that there are a plethora of possibilities now available to us.

Now, given the rapid shift in this field, a lot of us are left with a lot of queries such as: what are the differences between the models, how do I query them and of course, how can I use them to my advantage?

Foojay Podcast #31: Report of Devoxx 23 in Belgium

Mon, 16 Oct 2023 07:16:57 +0000

The first week of October, the 20th edition of Devoxx took place in Antwerp, Belgium.

Over 3000 Java developers, speakers, and enthusiasts gathered to share their knowledge and learn from each other.

I got the opportunity to walk around with a microphone and talk to visitors and speakers.

Not all of them, as there were just too many people and too many exciting sessions happening simultaneously.

Podcast Apps

You can listen and subscribe to the Foojay Podcast on:

Released: JVector 1.0

Mon, 02 Oct 2023 12:36:20 +0000

JVector is a pure Java embedded vector search engine that powers DataStax Astra and is being added to Apache Cassandra .

Vector search is a critical part of today’s generative AI applications , allowing developers to quickly retrieve the most relevant context to give the large language model enough information to answer accurately and without hallucinating, but innovation in this space has mostly happened outside the Java ecosystem. JVector gives enterprises an easy way to capitalize on their investment in the powerful Java platform, and gives Java developers a state-of-the-art solution that is easy to embed in their applications.

Foojay Podcast #29: How will AI and ML Influence the Role of Developers?

Mon, 25 Sep 2023 07:24:33 +0000

Artificial Intelligence and ChatGPT are the talk of the town.

Every conference has several talks about these technologies, and on Foojay, you can find multiple posts about it.

In this podcast, we want to take a look at it from the Java point of view.

How can we use AI in Java programs or our job as a developer?

Podcast Apps

You can listen and subscribe to the Foojay Podcast on:

AI-based Images generation with Quarkus and OpenAI DALL.E

Mon, 21 Aug 2023 07:38:07 +0000

In this article, we explore how to integrate OpenAI API with Quarkus. We will create a Quarkus application using the new REST Client Reactive to invoke the OpenAI DALL.E API for images generation.

OpenAI API Overview

Before jumping into the code, let’s explore the OpenAI Create Image API and how it works.

Create Image Request

The body request is made of the following parameters:

prompt: the only required parameter is the description of the desired image (max 1000 characters)
n: number of desired images (from 1 to 10)
size : the size of a generated image (default 1024x1024, also admitted 256x256, 512x512)
other parameters are:
response_format: to specify the response image format (default url, also admitted b64_json)
user: identifier to track user activities.

To authenticate with the API, we’ll generate an API key . We’ll set this key in the Authorization header while calling the API.

Timefold is the fork of OptaPlanner

Tue, 02 May 2023 15:12:53 +0000

OptaPlanner is an Open Source project used globally to optimize operational planning. Every day, it saves thousands of organizations time, money and resources.

Today, OptaPlanner is entering a new chapter.

The project I created and worked on for seventeen years has matured under Red Hat’s wings for the past ten years. Last year, when Red Hat’s strategy changed, it became apparent that the project needed a new, sustainable future. Therefore, we founded a company around it. A company that lives and breathes planning optimization , to further nurture the Open Source project to its fullest potential, under a new name. Timefold is the continuation of OptaPlanner.

Creating Scalable OpenAI GPT Applications in Java

Thu, 27 Apr 2023 14:18:45 +0000

One of the more notable aspects of ChatGPT is its engine, which not only powers the web-based chatbot but can also be integrated into your Java applications.

Whether you prefer reading or watching, let’s review how to start using the OpenAI GPT engine in your Java projects in a scalable way, by sending prompts to the engine only when necessary:

Imagine you want to visit a city and have a specific budget in mind. How should you spend the money and make your trip memorable? This is an excellent question to delegate to the OpenAI engine.

Deep Learning in Java Using Deep Netts (Part 2)

Wed, 03 Aug 2022 09:48:18 +0000

Deep Netts is a deep learning development toolkit that enables Java developers to easily add modern AI to their apps. It provides a deep learning IDE and a Java-native deep learning library for embedding AI models into Java apps.

In part 1 , we looked at the Deep Netts Community Edition, which is capable of solving basic machine learning problems, and provides a standard set of features.

If you have more complex challenges, more data, and need better performance or just want friendly tools to quickly try and learn AI, you should take a look at Deep Netts Professional Edition.

Getting Started with Deep Learning in Java using Deep Netts

Tue, 05 Jul 2022 07:22:18 +0000

Deep Netts is pure Java deep learning library with a friendly, Java centric API.

It makes it easy for Java developers to quickly start using deep learning and it is easy to integrate with existing Java applications.

It supports commonly used neural network architectures (feed forward networks, convolutional networks) for classification, regression and image recogniton tasks.

Adding Deep Netts to your Project

To be able to use Deep Netts in Maven based Java project, add the following dependency into dependencies section of your pom.xml file:

Deep Learning in Java for Nuclear Physics using Deep Netts

Thu, 16 Jun 2022 09:01:44 +0000

Background

The CLAS12 detector at Jefferson Lab conducts nuclear physics experiments to study the structure of nucleons and new particle states.

At the core of detector setup are drift chambers that measure charged particles resulting from the interaction of an electron beam with a liquid hydrogen target.

The charged particles are reconstructed by combining segments of the track measured in 6 separate drift chambers along the particle trajectory.

In high-intensity experiments, detector systems produce noise segments increasing the combinatorics of track candidates to be analyzed by the conventional algorithm, which leads to decreased track reconstruction efficiency.

Visual Recognition for Chess with Deep Learning in Java on Android

Thu, 11 Nov 2021 20:07:51 +0000

Find out how can you use AI in Java to build applications that can see and understand the world. This article describes an Android chessboard position scanner built with pure Java deep learning engine Deep Netts .

Over the last few decades, the technological advancement in the Artificial Intelligence (AI) field has greatly assisted many chess grand masters’ preparation as well as understanding chess theory. There are programs called chess engines, like Bagatur, Stockfish, and Komodo, which play extremely strong chess. These engines make deep and beautiful moves, but sometimes these moves are difficult to understand even by chess experts. Clearly, AI/ML has allowed chess engines to become quite advanced, but they are only one aspect of the story. There are more applications of AI/ML in playing the game of chess.

Deep Learning in Java for Drug Discovery

Fri, 20 Aug 2021 09:28:10 +0000

In the age of big-data, rising pharmaceutical costs, and an ever-increasing market demand, it is becoming apparent that drug design strategies need to adapt in order to meet patients’ therapeutic needs for a host of medical conditions.

Costly and time-intensive experimental work is one of the main bottlenecks in the drug discovery pipeline, which can take up to a decade, while experiencing a failure profile of up to 95% before a molecular candidate can be approved for patient use.

Open Source Tools as an Opportunity for SMEs to Use AI?

Wed, 02 Jun 2021 14:36:04 +0000

Time-traveling cyborgs and robots that are able to love. These interesting and romantic ideas emerged from the imagination of Hollywood film directors. Nevertheless, many people are afraid of Artificial Intelligence (AI). This also can be seen in the economic world. Small and medium-sized enterprises (SMEs) in particular see AI as a threat to their own business. Surprisingly however, all different-sized companies are able to see the potential of AI when it comes to penetrating the national and global market. ^[1]^

Interview on Machine Learning and Disruptive Data Science

Fri, 26 Mar 2021 13:15:29 +0000

I attended sessions and spoke with Java Champion Fabiane Bizinella Nardon at many JavaOne conferences over the past years. I remember, in our conversations in the hallways, discussing various entrepreneurial ventures she was working on. One of the ideas was Tail Target . Fast forward almost a decade, and Tail Target has truly come to fruition.

Fabiane Bizinella Nardon has an MSc in Computer Science and a PhD in Electronic Engineering. She is an expert in Data Engineering and Machine Language Engineering. She is the program committee leader for the Machine Learning Engineering track of QCon São Paulo, a frequent speaker on the subject, and author of several articles.

Quick Start with Machine Learning for Java

Wed, 07 Oct 2020 01:21:00 +0000

So you’re a Java developer and you want to do some machine learning. Some of the questions that you might be wondering about are—what can machine learning do for me anyway, which library to use, which algorithms, and is there a common standard API?

Since recently there is a standard API that was created to address exactly these questions. Meet JSR 381 , a standard Java API for Visual Recognition using machine learning.

Machine Learning on foojay.io - Friends of OpenJDK

How to Create a Spring Boot Fraud Scoring Service

JC-AI Newsletter #16

"Agentic" Was Everywhere at Money20/20 Amsterdam

Explore Spring AI SDK - Amazon Bedrock AgentCore - Part 1

Introduction

JC-AI Newsletter #15

JC-AI Newsletter #14

From “Crypto AI” to general AI: Do AI agents dream of electric langoustines?

The shift that matters for agent commerce - From “Crypto AI” to general AI

Enabling AI Agents to Use a Real Debugger Instead of Logging

Machine Learning in Java - SPAM detection using ONNX

JC-AI Newsletter #13

JC-AI Newsletter #12

The End of One-Sized-Fits-All Prompts: Why LLM Models Are No Longer Interchangeable

How CodeRabbit's Agentic Code Validation helps with code reviews

From PRD to PR in days (not weeks)

JC-AI Newsletter #10

JC-AI Newsletter #9

JC-AI Newsletter: Easy Access to Expanding Challenges

JC-AI Newsletter #8

JC-AI Newsletter #7

JC-AI Newsletter #6

JC-AI Newsletter #5

Fourteen days have passed, and it is time to present a fresh collection of readings that could influence developments in the field of artificial intelligence.

Stochastic AI Agility: Breaking Cycles of Debt

JC-AI Newsletter #4

JC-AI Newsletter #3

New Java Benchmark for Coding LLMs puts GPT-5 at the top

JC-AI Newsletter #2

I n the first newsletter , we introduced a 14-day cadence, which means that this week it’s time for a new collection of articles from the fields of AI, LLM, Java and more.

article: OpenAI CEO Sam Altman warns of an AI ‘fraud crisis’

AI Applications with LangChain4j Guardrails and Spring Boot

Understanding LangChain4j Guardrails

CodeRabbit Tutorial for Java Developers

Getting Started

Prerequisites

Setup Process

Core Features for Java Development

1. Code Quality Analysis

AI Newsletter #1

How to Make a RAG Application With LangChain4j

Understanding MCP Through Raw STDIO Communication

Deep Dive into the Model Context Protocol

The Great Data Reimagination: From Static to Agile in the AI Era

How I Improved Zero-Shot Classification in Deep Java Library (DJL) OSS: Enhancing Machine Learning Model Translators

TL;DR:

What’s Zero-Shot Classification (and Why It Matters)

Intro to RAG: Foundations of Retrieval Augmented Generation, part 2

Intro to RAG: Foundations of Retrieval Augmented Generation, part 1

How Deep Netts and Java AI Transformed Particle Physics

Building FormPilot

Foojay Webinar: Java's Place in the AI Revolution

Register for Foojay Webinar: "Java's Place in the AI Revolution"

Run AI-enabled JakartaEE/MicroProfile apps with LangChain4j

Foojay Podcast #56: Vectors in Java Code, Databases, and LLMs

Foojay Podcast #53: JCON Report, Part 5 – CQRS, JOOQ, GraphQL, API, Vaadin, OpenRewrite, ErrorProne, Gateways, Proxies,...

Video

Podcast Apps

Foojay Podcast #49: JCON Report, Part 1 - JUGs, Communities, Generative AI, and more!

Video

Podcast Apps

Building a Simple Home Assistant using Langchain4j and Raspberry Pi

Foojay Podcast #47: Artificial Intelligence and Machine Learning with Java

Video

Podcast Apps

Calling Gemma with Ollama, TestContainers, and LangChain4j

Search in Documentation with a JavaFX LangChain4j Chat

What is LangChain4j

State of Open (Source?!) and Free AI

FOSDEM

Using AI to Create JFR Event Descriptions

Virtual Event: JetBrains AI Launch Event

Webinar: Harnessing the Power of AI Assistant in IntelliJ IDEA

Generative AI and Java - hype or urgent reality?

Book review: “Developing Apps with GPT-4 and ChatGPT”

Foojay Podcast #31: Report of Devoxx 23 in Belgium

Podcast Apps

Released: JVector 1.0

Foojay Podcast #29: How will AI and ML Influence the Role of Developers?