发表机构
Jina AI by Elastic（Elastic旗下的Jina AI）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
omni-macos是一款在Apple Silicon端侧运行的全模态搜索系统，可在用户Mac设备上处理多模态数据搜索，数据不离开设备，适配不同硬件规格的Mac并优化内存使用。
AI 中文摘要
将文本、代码、文档、图像、音频和视频嵌入同一表示空间的搜索引擎，其编码器运行及索引存储通常需依赖服务器。本文提出omni-macos，该系统可在用户存储文件的Mac设备上运行完整引擎、编码器、索引及存储，文件、查询或向量均不会离开设备。它在用户设置的内存预算内整合后台索引器与交互式搜索框：仅重新编码编辑变更的块，用户输入时向GPU交付更小单元，通过量化副本响应查询并辅以精确重排序，还将内存预算传递至使用统一内存的分配器。研究在5台Mac上测试各机制，这些设备的加速器宽度相差8倍、内存相差32倍，每台设备均索引自身本地文件。
英文摘要
We present omni-macos, a search engine that embeds text, code, documents, images, audio and video into one representation space and runs its encoder, index and store on the Mac that already holds the files, so no indexed file, no typed query and no vector ever leaves the machine. It keeps a background indexer and an interactive search box inside one memory budget the user sets: it embeds and stores each distinct chunk once, re-encodes only the chunks an edit changes, hands the GPU smaller units while the user is typing, answers queries from a one-bit replica of the index with exact rescoring, and propagates that budget to the allocators that draw on unified memory. We measure on five Macs spanning an eightfold range of accelerator width and a thirty-twofold range of memory, each indexing the files it already holds.
Comments17 pages, 6 figures, 9 tables
