@xueyu1125: Holy crap, someone on GitHub made a search Mac App based on the Google EmbeddingGemma2 small model Way more accurate th…
Summary
一位网友在 GitHub 上发现了一款基于 Google EmbeddingGemma2 小模型的 Mac 搜索应用,称其准确度远超系统自带 Spotlight,支持文件名、文件内容、图片和音频搜索。
Similar Articles
Open-source Mac app that runs EmbeddingGemma 2 locally to search your files by what’s in them
DigUp 是一款免费开源的 Mac 应用,本地运行 Google DeepMind 的 EmbeddingGemma 2 模型,通过文本、图像、音频和视频的统一嵌入空间实现语义搜索你的本地文件。
@xueyu1125: I've noticed that everyone is underestimating EmbeddingGemma 2, and underestimating Embedding models in general. The op…
The author argues that EmbeddingGemma 2 and embedding models in general are being underestimated, highlighting the open-source DigUp project — a Mac search app built on Google's EmbeddingGemma 2 that outperforms Spotlight with content, image, and audio search — and suggests embeddings could also improve RAG knowledge base search.
LSearch - Spotlight for windows with embedding
LSearch 是一个 Windows 上的 Spotlight 风格搜索工具,使用 EmbeddingGemma 2 (270M) 嵌入模型,并组合了两个微调的 Qwen 3.5 4B 模型(分别针对编码和 agentic 任务)构成 MoE,用于代码修复。
@FeitengLi: Compiled a list of open-source resources for #EmbeddingGemma2: • DigUp: Search for documents, images, audio, and video …
Feiteng Li 分享了一份针对 EmbeddingGemma2 的开源资源清单,涵盖 DigUp、Recall 等本地多模态搜索应用、决策模型微调方案,以及 llama.cpp、MLX、LiteRT、Transformers.js 等多端部署路径。相关仓库已开源并欢迎社区贡献。
@aigclink: Someone turned Google's EmbeddingGemma 2 into a speech recognition model, achieving an astonishingly fast on-device inf…
有人将谷歌的 EmbeddingGemma 2 改造为语音识别模型,通过在冻结参数的嵌入模型上训练轻量级 Reader,把语音转写从生成问题变成检索问题,在 M3 MacBook Air 上实现 288× 实时速度(1 小时音频约 13 秒转写),WER 约 5%,可能重塑端侧 STT 市场。