This demo project illustrates how to build a dynamic, real-time search system on iOS using the USearch vector-search library. In this example, we use 2-dimensional vectors—encoded as latitude and longitude—to find the closest Points of Interest (POIs) on a map. The search is based on the Haversine distance metric.
While this demo focuses on 2D vectors for geospatial search, the USearch library is primarily designed for higher-dimensional vectors. Combined with UForm AI models, it can power on-device, multi-lingual, and multi-modal Semantic Search applications.
git clone https://github.com/your-username/SwiftVectorSearch.git
cd SwiftVectorSearch
open SwiftVectorSearch.xcodeproj
Requirements:
- iOS 14.0 or later
- Xcode 12 or later
- Swift 5.3 or later
Feel free to adapt this template to suit the specifics of your project better!