DigUp for Office Clerks — Find Forms, Scans & Emails by Meaning

Download DigUp for Mac EmbeddingGemma 2 All roles

On-device flow Schematic: DigUp uses EmbeddingGemma 2 for Office clerks and admins local search

Original schematic — DigUp indexes local files with EmbeddingGemma 2 (llama.cpp).

Sourced snapshot (2026-10-15)

Fact	Value	Source
Model	EmbeddingGemma 2 · ~740M params · ~865 MB Q8 via llama.cpp	Google AI · DigUp README
Vector space	768-d shared multimodal space	Google AI · DigUp README
Mac / Win·Linux	0.6.1 · 0.7.0-beta.1	GitHub Releases
Stars / forks	~3,768 / ~254	GitHub API

Pain → DigUp workflow → tip

Pain	DigUp + EmbeddingGemma 2 workflow	Tip
Which PDF has the leave form?	Index HR/forms folders; query “annual leave application”	Opens at the matching page
Phone photo of a stamped receipt	Index camera roll / work Photos export	Find by what’s depicted — not filename
Policy buried in a 200-page handbook	PDF page embeddings + keyword boost	Long PDFs: first 30 pages fast, up to 5,000/file (README)
Voice memo of a manager request	Audio ~30s windows in shared space	Jump near the spoken moment

Numbered checklist

Download DigUp for your OS; complete the ~865 MB EmbeddingGemma 2 first run.
Add only work folders you are allowed to index (skip personal cloud placeholders).
Grant Full Disk Access on Mac if Desktop/Documents stay empty.
Search in plain language; keep exact form numbers as keywords too.
Use overnight indexing hours so daytime stays responsive.

Why EmbeddingGemma 2 matters here

Google’s EmbeddingGemma 2 (~740M, unified 768-d multimodal space) is what DigUp runs via llama.cpp (~865 MB Q8 package). One query can rank images, PDF pages, audio windows, video frames, and optional code — see the local multimodal guide and model page. digup.run is not Google-official.