Moving beyond keyword search
Traditional CKAN search matches keywords in titles, descriptions, and other metadata fields. This works well when users know the exact phrasing used by publishers. But real-world users often search differently. A person looking for ‘police reports’ might miss a dataset labelled ‘crime statistics’. Someone interested in ‘ocean pollution’ may never type ‘marine ecosystem degradation’.
Ask AI introduces semantic similarity search. Instead of matching words, it matches meaning. Behind the scenes, dataset and resource metadata – along with supported document content – are converted into vector embeddings and stored in PostgreSQL using an extension called pgvector. When a user performs a search, the system retrieves results based on semantic proximity rather than simple text overlap.
The effect is immediate:
- Broader recall without sacrificing relevance
- Discovery across inconsistent terminology
- Reduced dependence on perfect metadata alignment
For organisations managing large portals, this materially improves dataset discoverability without requiring publishers to change workflows.
Read the full article here: https://linkdigital.com.au/news/2026/03/ask-ai-link-digitals-ai-layer-for-smarter-ckan-portals/
Published by
About our partner
Link Digital
System architects of data and knowledge infrastructureFor 25 years, Link Digital has designed and run the information systems that governments, research institutions and international organisations depend on. We build open data portals and internal data hubs, host and support them, and now make them ready for people and AI to ask questions of. Founded in Australia in 2001, we work with clients worldwide, including Australia, Canada, New Zealand, the Pacific, and Latin America.Official CKAN co-stewardCKAN is a leading open source data portal platform, and Link Digital has been part of its community since 2012. Our Executive Director, Steven De Costa, and our engineers are involved across CKAN's governance, community and technical work, and our team includes the project's Core Tech Lead. We help shape the 2.12 and 3.0 roadmaps. For public sector buyers, that means open source with no vendor lock-in, and a partner with a say in the releases and long-term sustainability you will rely on.What we doAsk AI for CKAN. Ask questions in plain language and get verified answers drawn from your own data. It runs in your secure environment, never trains public models, and you control who can query which datasets. We start with an AI-readiness audit.End-to-end CKAN services. Consultancy, migration from legacy systems, hosting, support, extensions and theming, with DCAT and FAIR-aligned metadata.Managed hosting, support and maintenance. CKAN and Drupal on AWS infrastructure we architect and monitor, with security patch assessment, restore-verified backups and version currency. One team, one agreement, one invoice. We can take over portals built by others.Internal data hubs and Secure Data Exchange. Governed sharing across departments, with approval workflows, revocable data sharing agreements and a dashboard showing who is using your data.Custom CKAN and Drupal buildsStart a conversation with Link Digital: Book a consultation or request an AI-readiness audit.
Learn more
Help your peers
Share what you've learned with fellow public servants