Advanced Search Improvements Using Natural Language Query
Natural Language Search in digiKam – GSoC 2026 Project by Srirupa Datta
We are excited to announce the successful integration of Natural Language Search in digiKam, developed by Srirupa Datta as part of the Google Summer of Code 2026 program. This new feature allows users to search their photo collections using plain English queries, making it easier than ever to find specific images without manually configuring filters.
What’s New?
With Natural Language Search, you can now type queries like:
- “Photos of mountains from last summer rated 5 stars”
- “Landscape photos with red labels”
- “Videos longer than 5 minutes”
The feature leverages a local Large Language Model (LLM) running on your machine, ensuring that your photos and queries never leave your computer. The model translates your natural language query into digiKam’s advanced search criteria, providing accurate and efficient results. Plus: you can also use your native Language as Spanish, French, German, Italian, etc, as your query will be automatically translated in English before the LLM processing.
Project Status
The project is nearly complete, with the core functionality fully implemented and tested. The feature is currently available in the development version of digiKam and will be included in the next stable 9.2.0 release.
Learn More
Srirupa’s Profile: https://srirupa19.github.io/about/
Project Progress Blogs with screenshots and video screens-cast:
Final Project Report: https://community.kde.org/GSoC/2026/StatusReports/SrirupaDatta
What’s Next?
The final steps to include the user interface polishing, adding comprehensive documentation, and ensuring seamless integration with digiKam’s existing features are already done. Stay tuned for the official 9.2.0 release planned in a few weeks!
A huge thank you to Srirupa Datta for her outstanding work on this project, and to the KDE community for their support and guidance.
The digiKam Team
