Giovanni Panice
Java Runtimes & Integrations @IBM | SWE | Debezium | Opentelemetry | Ticino Software Craft Organizer
Naples, Italy
Actions
Member of the Technical Staff for Java Runtimes & Integrations @IBM (former Red Hat) and core team member of Debezium. He has tackled complex engineering challenges in systems requiring high reliability and scalability, including smarter flight pricing systems, infrastructure forecasting through large-scale metric analysis, and securing UAV navigation through anomaly detection.
He has worked in domains such as travel tech, enterprise infrastructure and aerospace, all of which share a need for resilient, distributed systems that handle demanding workloads. His current focus is on improving performance and usability in Debezium, through native builds, Quarkus integration and deep work on Debezium internals.
Beyond his work at IBM, he co-organizes the Ticino Software Craft Meetup, a community that promotes knowledge sharing and continuous learning around software quality and engineering practices.
Area of Expertise
Topics
From Change Data Capture to AI: Feeding Your RAG with Debezium
Large Language Models (LLMs) are powerful for reasoning and natural language generation, but their effectiveness depends on access to fresh, relevant data. Keeping models up-to-date through retraining or fine-tuning introduces a compatibility challenge: operational data typically exists in formats unsuitable for LLM consumption, requiring transformations into structured representations before it can be used effectively.
This session demonstrates how to bridge that gap by using Debezium as the backbone of a Retrieval-Augmented Generation (RAG) pipeline. We’ll dive into the mechanics of capturing transactional changes from relational databases, converting text fields into vector embeddings via Debezium’s Embeddings SMT, and streaming them into a vector database for efficient retrieval.
Come To Code 2026 Sessionize Event
Please note that Sessionize is not responsible for the accuracy or validity of the data provided by speakers. If you suspect this profile to be fake or spam, please let us know.
Jump to top