MariaDB AI RAG: Replacing Complex Pipeline Tooling with One REST API
April 22, 2026 at 8 AM PST | 11 AM EST | 4 PM GMT
Join our technical teardown to see how to move RAG to production without duct-taping together a fragmented AI data stack.
Moving Retrieval-Augmented Generation (RAG) from a local script to a production environment typically requires managing a sprawling stack. You end up duct-taping together document loaders, chunking libraries, embedding models, vector stores, and custom orchestration logic.
For developers and architects, this means stitching together separate systems, which adds immense complexity, new points of failure, and significant maintenance overhead.
In this technical session, we examine a cleaner architectural approach. We will look at MariaDB AI RAG, a new component in the MariaDB Enterprise Platform designed to encapsulate the complete RAG lifecycle.
What we will cover:
The Core RAG Challenges: Why moving from local scripts to production breaks traditional workflows and creates pipeline sprawl.
The Architecture of MariaDB AI RAG: How to encapsulate the complete RAG lifecycle and bypass the fragmented stack entirely.
Workflow Demo: A walkthrough of a complete RAG workflow handling data ingestion, chunking, reranking, and context retrieval—all executed through a single API.
Live Q&A: Bring your specific architecture questions to ask in real-time.
About Your Speaker Starting his coding journey at 13 with BASIC on a rudimentary black screen, Alejandro quickly transitioned to C, C++, and Java during his academic years at the National University of Colombia. Relocating first to the UK and then to Finland, Alejandro deepened his involvement in the open-source community. He's a recognized figure in Java circles, credited with articles and videos amassing millions of views, and presentations at international events.
