Category Archives: Gen AI
I had the delight of being accepted to talk about “Making AI transparent with RAG on your own data” at foss-north 2025 in Gothenburg, Sweden. On April 14th at Chalmers University, I got to share with a full room on how AI RAG is done with MariaDB Vector, kicking off with a use case about scaling Wikipedia editing with GenAI.
Improving Wikipedia with RAG
I presented a use case example from my experience of editing Wikipedia at scale with GenAI for non-profit Projekt Fredrika.
…
Continue reading “MariaDB Vector and RAG at foss-north 2025”
We had the pleasure on Friday to take individual calls with everybody who submitted to the ideation phase of the MariaDB AI RAG hackathon.
The ideation phase deadline passed last week, and we are happy to share that we received several promising submissions for both the innovation track and the integration track. Innovation involves applications using MariaDB Vector, like RAG, and integration being enabling MariaDB Vector in an existing framework.
Participants range from individual contributors to even a corporate team. Some already have some experience with AI, and some are newcomers to RAG.
…
The ideation phase of the MariaDB AI RAG Hackathon is nearing its deadline on Monday (by end of March).
We have several cool submissions so far. One is about combining the Knowledge Graph and LLMs, using MariaDB Vector Nearest Neighbour Search. Another one is about an “advanced context diff”, identifying the differences between two text corpuses based not on their literal wording, but on their content.
All of the current submissions are in the Innovation track. We would particularly like submissions in the Integration track – to add MariaDB to frameworks such as these, or other apps.
…
One week left to join the AI RAG Hackathon with MariaDB Vector and Python!
Winners get to demo at the Helsinki Python meetup in May, receive merit and publicity from MariaDB Foundation and Open Ocean Capital, and prizes from Finnish verkkokauppa.com.
To participate, gather a team (1-5 people) and submit an idea by the end of March for one of the two tracks. You then have until May 5th to develop the idea before the meetup 27th May.
- Integration track: Enable MariaDB Vector in an existing open source project or AI-framework.
…
We are excited to announce a hackathon with MariaDB Vector and Python. Since we are reaching outside our bubble, let’s start from the beginning:
MariaDB, the open-source database powers the world’s most demanding applications, from Wikipedia to global financial institutions. Now MariaDB Vector is bringing AI-ready vector search natively into the open-source database world. MySQL users ahoy:
Our hackathon is your chance to explore AI possibilities with MariaDB Vector and Python. Whether you’re a developer, data scientist, or AI enthusiast, MariaDB Foundation invites you to build innovative AI applications, compete for prizes, and showcase your work.
…
Continue reading “Join our AI Hackathon with MariaDB Vector”
Back from Brussels! With a bit of time to reflect, I’d like to share the aftertaste from our MariaDB Day, our very own FOSDEM Fringe Event. Prepare for an information-packed blog entry with links to the presentations, including live recordings and often the slide decks.
Billionaire controversy cancelled
Brussels during the first weekend of February is a hotbed of Open Source. The weather might not be hot, in contrast to the discussions in the corridors and rooms of the ULB university. The hottest topic expected – boycotting the presentation of Twitter founder Jack Dorsey – didn’t really happen.
…
We’re no mind readers, so from time to time, we like to do polls. Polls are quantitative in nature, so coming up with the right question is not enough – we need to do a bit of mind reading in coming up with the alternatives.
Quick development of text based RAG apps
Our hypothesis was that RAG is the cool thing to do with vector based databases, and specifically text based RAG. The conference talks we’ve given on MariaDB Vector (such as at the 24th SFSCON in Bozen, Südtirol, Italy on 8 Nov 2024) have stressed the value of easily being able to develop AI applications that answer user prompts based on knowledge in a specific text mass, not on the overall training data of an LLM.
…
Continue reading “What do you expect from vector storage in databases?”
The day has come that you have been waiting for since the ChatGPT hype began: You can now build creative AI apps using your own data in MariaDB Server! By creating embeddings of your own data and storing them in your own MariaDB Server, you can develop RAG solutions where LLMs can efficiently execute prompts based on your own specific data as context.
Why RAG?
Retrieval-Augmented Generation (RAG) creates more accurate, fact-based GenAI answers based on data of your own choice, such as your own manuals, articles or other text corpses. RAG answers are more accurate and fact-based than general Large Language Models (LLM) without having to train or fine-tune a model.
…
Continue reading “Try RAG with MariaDB Vector on your own MariaDB data!”