{"id":16976159,"url":"https://github.com/ashvardanian/swiftsemanticsearch","last_synced_at":"2025-04-05T21:08:06.656Z","repository":{"id":191196570,"uuid":"684121083","full_name":"ashvardanian/SwiftSemanticSearch","owner":"ashvardanian","description":"Real-time on-device text-to-image and image-to-image Semantic Search with video stream camera capture using USearch \u0026 UForm AI Swift SDKs for Apple devices 🍏","archived":false,"fork":false,"pushed_at":"2024-12-20T13:32:05.000Z","size":638,"stargazers_count":114,"open_issues_count":1,"forks_count":7,"subscribers_count":5,"default_branch":"main","last_synced_at":"2025-03-29T20:06:13.112Z","etag":null,"topics":["coreml","coreml-models","image-search","ios","mobile-app","ondeviceai","onnx","rag","semantic-search","swift","swiftui","vector-search","vector-search-engine","video-search"],"latest_commit_sha":null,"homepage":"https://github.com/unum-cloud/uform","language":"Swift","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/ashvardanian.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2023-08-28T13:54:18.000Z","updated_at":"2025-03-13T11:29:18.000Z","dependencies_parsed_at":"2023-08-28T18:44:46.145Z","dependency_job_id":"65d70498-fc39-44a6-8c56-e428d0228d5b","html_url":"https://github.com/ashvardanian/SwiftSemanticSearch","commit_stats":{"total_commits":20,"total_committers":4,"mean_commits":5.0,"dds":"0.19999999999999996","last_synced_commit":"fb5e8c05eec537d73e2ad6ebc38d6908003a28e6"},"previous_names":["ashvardanian/swiftvectorsearch","ashvardanian/swiftsemanticsearch"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ashvardanian%2FSwiftSemanticSearch","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ashvardanian%2FSwiftSemanticSearch/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ashvardanian%2FSwiftSemanticSearch/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ashvardanian%2FSwiftSemanticSearch/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ashvardanian","download_url":"https://codeload.github.com/ashvardanian/SwiftSemanticSearch/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247399877,"owners_count":20932876,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["coreml","coreml-models","image-search","ios","mobile-app","ondeviceai","onnx","rag","semantic-search","swift","swiftui","vector-search","vector-search-engine","video-search"],"created_at":"2024-10-14T01:25:09.111Z","updated_at":"2025-04-05T21:08:06.616Z","avatar_url":"https://github.com/ashvardanian.png","language":"Swift","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Swift Semantic Search 🍏\n\n![Preview](https://github.com/ashvardanian/ashvardanian/blob/master/repositories/SwiftSemanticSearch.jpg?raw=true#center)\n\nThis Swift demo app shows you how to build real-time native AI-powered apps for Apple devices using Unum's Swift libraries and quantized models.\nUnder the hood, it uses [UForm](https://github.com/unum-cloud/uform) to understand and \"embed\" multimodal data, like multilingual texts and images, processing them on the fly from a camera feed.\nOnce the vector embeddings are computed, it uses [USearch](https://github.com/unum-cloud/usearch) to provide a real-time search over the semantic space.\nThat same engine also enables geo-spatial search over the coordinates of the images and has been shown to scale even to 100M+ entries on an 🍏 iPhone easily.\n\n\u003ctable\u003e\n  \u003ctr\u003e\n    \u003ctd\u003e\n      \u003cimg src=\"https://github.com/ashvardanian/ashvardanian/blob/master/demos/SwiftSemanticSearch-Dog.gif?raw=true\" alt=\"SwiftSemanticSearch demo Dog\"\u003e\n    \u003c/td\u003e\n    \u003ctd\u003e\n      \u003cimg src=\"https://github.com/ashvardanian/ashvardanian/blob/master/demos/SwiftSemanticSearch-Flowers.gif?raw=true\" alt=\"SwiftSemanticSearch demo with Flowers\"\u003e\n    \u003c/td\u003e\n  \u003c/tr\u003e\n\u003c/table\u003e\n\nThe demo app is capable of text-to-image and image-to-image search and uses `vmanot/Media` libra to fetch the camera feed, embedding, and searching frames on the fly.\nTo test the demo:\n\n```bash\n# Clone the repo\ngit clone https://github.com/ashvardanian/SwiftSemanticSearch.git\n\n# Change directory \u0026 decompress the images dataset.zip, which brings:\n#   - `images.names.txt` with newline-separated image names\n#   - `images.uform3-image-text-english-small.fbin` - precomputed embeddings\n#   - `images.uform3-image-text-english-small.usearch` - precomputed index\n#   - `images` - directory with images\ncd SwiftSemanticSearch\nunzip dataset.zip\n```\n\nAfter that, fire up the Xcode project and run the app on your fruity device!\n\n---\n\nLinks:\n\n- [Preprocessing datasets](https://github.com/ashvardanian/SwiftSemanticSearch/blob/main/images.ipynb)\n- [USearch Swift docs](https://unum-cloud.github.io/usearch/swift)\n- [Form Swift docs](https://unum-cloud.github.io/uform/swift)\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fashvardanian%2Fswiftsemanticsearch","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fashvardanian%2Fswiftsemanticsearch","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fashvardanian%2Fswiftsemanticsearch/lists"}