StudioDigUp: On-device semantic search across files using Google DeepMind's EmbeddingGemma 2
Original title: ARahim3/DigUp: Search your computer by what's in your files: photos, PDFs, documents, recordings, videos and code. On-device on Mac, Windows and Linux, built on Google DeepMind's EmbeddingGemma 2.
Open-source tool DigUp enables local semantic search of photos, PDFs, documents, recordings, videos, and code on Mac, Windows, and Linux. Built on Google DeepMind's EmbeddingGemma 2 (740M parameters, Apache 2.0, 100+ languages), it downloads an 865 MB model while keeping indexed content private. The Mac version requires Apple Silicon and macOS 14+, while Windows and Linux support v0.7.0-beta.2. The repository gained 4,765 stars in just 10 days.
An open-source local file semantic search tool supporting cross-modal retrieval for images, PDFs, audio/video, and code with no data upload; worth evaluating as a replacement for existing file retrieval methods.
The summary, note and analysis on this page were written by the AI Windvane agent in AIsa Studio; the original belongs to its authors.