I recently acquired Netatmo smart radiator valves to manage my rooms’ temperature remotely. I’m not skilled at manual tasks, but I could easily replace the old thermo-static valves. I then registered the smart ones in the Netatmo app. Finally, I …
-
Brokk: AI for Large (Java) Codebases
Table of Contents Sidebar: Under the HoodRecommendationsWorking with GitSidebar: LLM ModelsThe Edit Loop There are two reasons that AI makes mistakes writing code: The LLM just isn’t smart enough to tackle the problem effectively, and it simply gets the answer …
-
Testing MongoDB Atlas Search Java Apps Using TestContainers
Table of Contents What is MongoDB Atlas Search, anyway?Local development and testing with MongoDB Atlas SearchWhat’s TestContainers?Let’s write some code!Simple CRUD data access and unit testsMongoDB Atlas Search with seed data and index waitAdvanced seed data loading: MongoDB Database ToolsLoading …
-
10 Best Practises For Jakarta EE Performance Optimization
Table of Contents Quick ComparisonSecrets of Performance Tuning Java on Kubernetes by Bruno BorgesNext Steps With this article, we start a series where we compiled 10 best practices for performance optimizations and suggestions how to implement them using Jakarta EE & Eclipse GlassFish. Enjoy …
-
How to send prompts in bulk with Spring AI and Java Virtual Threads
Table of Contents Here’s the flow:Virtual Threads for Massive ParallelismSpring AI Prompt CallProcessing in BatchesHandling Errors GracefullyProcess Results in BulkFull ImplementationStay curious! TL;DR: You’re building an AI-powered app that needs to send lots of prompts to OpenAI. Instead of sending …
-
How Deep Netts and Java AI Transformed Particle Physics at US DoE, Jefferson Lab
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 …
-
How to Deploy a Vaadin Application as a WAR on Tomcat 11
Table of Contents Step 1: Download Tomcat 11Step 2: Create a New Vaadin ProjectStep 3: Adjust the pom.xmlStep 4: Update the Spring Boot Application ClassStep 5: Build the Application for ProductionStep 6: Deploy the WAR to TomcatConclusion If you want to …
-
What is RAG, and How to Secure It
Table of Contents Why use RAGHow RAG Works1. Retrieval2. GenerationSecurity implications of using RAGPrompt injection through retrieved contentData poisoningAccess control gaps in retrievalLeaking PII to third-party modelsCaching risks and session bleedContradictory or low-quality informationProactive and remediation strategies for securing RAGSanitize …
-
GenAI blood, sweat, and tears: Loading data to Pinecone
Table of Contents Getting startedIssue #1: APIs, SDKs, and rapid changeIssue #2: ConfigIssue #3: JSON formatIssue #4: Loading data to Pinecone1. Metadata keysAlternative embeddings – Book descriptionsWrapping up!Resources As someone who is pretty familiar with relational and graph databases, I …
-
Building FormPilot: My Journey Creating an AI-Powered Form Filler with RAG, LangChain4j, and Ollama
Table of Contents The InspirationThe ArchitectureGetting Started: Setting Up Your EnvironmentPart 1: Installing and Running Ollama LocallyPart 2: Creating the Spring Boot Project via Spring InitializrImplementing RAG with LangChain4jThe Magic of LangChain4j’s @AiServiceIntegrating with OllamaBuilding the Chrome ExtensionSetting up the …
-
Local AI with Spring: Building Privacy-First Agents Using Ollama
Table of Contents IntroductionConfiguring OllamaSpring AI + Ollama: a perfect match!Setting up the projectEnough talk, show me the codeA quick detour on FastMCPConclusion Introduction Building local AI agents with Spring AI and Ollama has emerged as a game-changer for developers …