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
Link Digital builds open data portals and internal data hubs. A global information technology company founded in 2001, supporting government agencies, NGO, and research and academic institutions by serving as system architects of data. Link Digital is official CKAN co-stewardWith a dedicated team of developers, implementers, and contributors, Link Digital has been actively involved in the CKAN community since 2012.Their primary focus lies in expert data portal consulting, design, and building capabilities for data repository management. As a testament to our commitment, Steven De Costa, Link Digital Chairman, plays a crucial role in the CKAN project.Link Digital's Business Operating ModelLink Digital has been utilising the Entrepreneurial Operating System for Businesses (EOS) toolset to optimise our operations and build growth since March 2017. This framework enables us to achieve traction, streamline operational management, and empower our leadership team.Their expertise lies in CKAN, a Python-based framework renowned for its efficiency. Additionally, they have extensive experience with Drupal, and Amazon Web Services.Case studies of data portals and internal data hubs built by Link DigitalPacific Community's Pacific Data HubLiving Lakes Canada's Columbia Basin Water HubNew South Wales Vehicle Emission Star Rating Website Project (Drupal-based)Norwegian Public Roads AdministrationUniversity of Manitoba's Canadian Watershed Information NetworkMédecins Sans Frontières Data Sharing PlatformThe Government of New South Wales Sharing and Enabling Environmental DataQueensland Government Geoscience Data Modernisation Project (GDMP)New Zealand's geoscience regulation agency Inter-American Development Bank's Open Data Catalogue
Learn more
Help your peers
Share what you've learned with fellow public servants
Recommendations
Let’s Chat: Ethical AI Leadership in Government 3.0
Powering the Global Public Sector Community
Australian data hosting is now available for Figma customers on Enterprise
Google- Workforce transformation through IT training
