ashvardanian/SwiftSemanticSearch
Real-time on-device text-to-image and image-to-image Semantic Search with video stream camera capture using USearch & UForm AI Swift SDKs for Apple devices 🍏
Combines quantized multimodal embeddings (via UForm) with approximate nearest neighbor search (via USearch) to enable sub-millisecond semantic queries directly on-device, including geo-spatial filtering over image coordinates. Processes camera frames in real-time by computing vector embeddings on-the-fly and indexing them into USearch, which scales to 100M+ entries on mobile hardware. Leverages precomputed embedding indices and multilingual model support to minimize computational overhead while maintaining native SwiftUI integration.
149 stars. No commits in the last 6 months.
Stars
149
Forks
11
Language
Swift
License
—
Category
Last pushed
Dec 20, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/ashvardanian/SwiftSemanticSearch"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
ssrajadh/sentrysearch
Semantic search over videos using Gemini Embedding 2.
hayabhay/frogbase
Transform audio-visual content into navigable knowledge.
zilliz-bootcamp/audio_search
This project use PANNs for audio tagging and sound event detection, and finally get audio...
kyegomez/Pegasus
PegasusX: The Future of Multimodal Embeddings 🦄 🦄
tomfalainen/word_spotting
Semantic and Verbatim Word Spotting in Torch