Are you building systems that query open data portals with AI? How are you handling retrieval reliability, hallucinations, and grounding? Join a semi-closed technical session organised by the OKFN Tech Team around the CKAN Answers project — demo, code sharing, and community feedback.
The Open Knowledge Foundation (OKFN) Tech Team is running a technical consultation session next week around CKAN Answers — a project exploring how to retrieve reliable information from open data portals using LLMs.
If you're an engineer working at the intersection of CKAN and AI, this one's for you.
CKAN Answers is a project focused on the practical challenge of building systems that give accurate, grounded answers from open data portals using large language models. Patricio Del Boca presented an overview at the recent Future of Open Data conference.
Watch the full roundtable below to get context before the session.
The OKFN Tech Team will walk through the initial architecture decisions and trade-offs made so far. From there, the format is collaborative and practical.
Express your interest on the OKFN forum
Add a reply to the thread and you'll receive a calendar invitation directly.
After months of development, CKAN 2.12 is nearly ready — and it's more than just another release. As the last in the 2.x series, it lays the architectural groundwork for CKAN 3.0 while delivering meaningful improvements to file management, data store performance, and the user interface. Here's a full recap of what the core team shared at Monthly Live Session #40 on February 18, 2026.
CKAN turns 20. Explore how an open-source experiment became global data infrastructure, powering governments, research, and public-interest data worldwide.