DigUp for Lawyers

Download DigUp for Mac EmbeddingGemma 2 All roles

On-device flow Schematic: DigUp uses EmbeddingGemma 2 for Lawyers 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
Find indemnity language across drafts	Index matter PDF folders; semantic query	Page jump + keyword boost for defined terms
Exhibit photo from site visit	Image embeddings	Search by what’s depicted
Deposition audio moment	30s audio windows	Jump near the spoken exchange
Privileged material concern	Local-first; no DigUp account	Only folders you choose; review README privacy

Numbered checklist

Confirm firm IT allows local AI indexes; DigUp stays on-device after ~865 MB model download.
Index only matter folders you control; exclude cloud placeholders.
Search clause intent in plain language; paste exact defined terms too.
Cross-check hits in your PDF viewer before citing.
See EmbeddingGemma 2 page for model/runtime facts.

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.