Blog
I write about Java, software architecture, design patterns, applied artificial intelligence, RAG, AI agents and software engineering. Through my articles, I share feedback, technical analyzes and concrete approaches to design robust, maintainable and useful applications.
RAG with Spring AI: Building a Data Ingestion Pipeline
RAG (Retrieval-Augmented Generation) enriches LLM responses with your own data. In this article, we build the ingestion pipeline: reading documents, splitting into chunks, generating embeddings, and storing them in PostgreSQL/PGVector.
Giving Memory to Your AI: Managing Conversational Context with Spring AI
LLMs are stateless by nature: each request is processed independently. Spring AI solves this problem through the Chat Memory system and the Advisor pattern. In this article, we implement a chatbot with conversational memory in just a few lines of code.
ChatClient API: Getting Started with the Spring AI ChatClient
The ChatClient is the main entry point for interacting with AI models in Spring AI. In this article, we explore its usage through three sub-modules: a simple prompt with token tracking, a REST controller with multi-model streaming, and multimodality support.
Spring AI in Action: Integrating LLM Capabilities into Your Java Applications
Spring AI is a framework that simplifies the integration of artificial intelligence capabilities into Spring applications. In this introductory article to the 'Spring AI in Action' series, we explore the challenges of LLM integration in Java, the benefits of Spring AI, and the architecture of the demo project based on Spring Boot 4 and Spring AI 2.0.0-M2.
Toon4j: Reduce your LLM token costs by 30 to 70% with Java
In the era of language models (LLMs), every token counts. Whether we're building AI applications, optimizing our API costs, or managing context windows, the way we structure our data can have a significant impact on performance and cost. It is in this context that we discover Toon4j, a library […]
Spring Boot 4: RestClientAutoConfiguration has not disappeared, it has moved!
As part of migrating our Spring Boot 3.x projects to version 4, we noticed frequent confusion regarding the RestClientAutoConfiguration class. Many developers believe that this class has been removed, when in reality it was simply relocated as part of a major architectural overhaul. In this article, we […]
Secrets of LLM Inference: Strategic Dive into Query Parameters
Language models (LLMs) have revolutionized the field of natural language processing (NLP) with their ability to produce human-like text, offering among other things translation, content creation, and informed question answering, supported by immense textual data sets.
