Apple is enhancing its Spotlight Search feature in iOS 18 to make it easier for users to discover content within apps using natural language queries. Currently, Spotlight can search for content in developers’ apps, but only returns results when search terms match exactly. With the addition of semantic search capabilities, users will be able to search for content in apps using search terms that are similar in meaning.
The Core Spotlight framework allows developers to donate content they want to make searchable via Spotlight, which is stored in a private index on users’ devices that other apps cannot access. The new semantic capabilities will improve Spotlight’s understanding of developers’ content, enabling users to search for content inside apps in their own way. These types of search queries leverage machine learning models that are downloaded to the device and run in the app’s process, and can be loaded or unloaded at any time.
As users search for content, developers can help improve the rankings of their app’s search results over time by sending signals to Spotlight when an iPhone owner engages with one of their results. For example, if someone searches for a particular local hiking trail, the semantic search capabilities will be able to find results related to the user’s search query, using entities it understands like the trail’s location or specific keywords, even if they weren’t in the trail’s name and weren’t exact matches.
Developers can also set higher priorities for some of their content, as needed, allowing them to mark a trail that a user had saved as a favorite to rank higher in the search results. The end result is that users can search for a given trail using a natural language query in Spotlight, find the trail they want more easily via improved results, and then tap on a result to be taken straight to the trail’s page in the developer’s hiking trails app. This update also helps Siri better understand an app’s content.
