back_office_ops · workflow
Dropbox implements semantic search with multilingual-e5-large, reducing empty search sessions by nearly 17%
Dropbox's Nautilus search engine relied on keyword matching that required users to recall exact file names or terms, missed contextually similar content, and could not serve multilingual users searching across languages.
How it works
Common implementation structure
How this type of workflow is generally built, generalized across documented cases — not tied to any one vendor's stack. Click any stage to read what happens there. Specific products that implement these stages appear in “Tools commonly seen” below.
Stage 1 · Documents indexed as embeddings
New and existing documents are mapped to vector embeddings and stored in Nautilus indices.
Tools used
Nautilusmultilingual-e5-largeMTEBKubeflow
Outcome
Semantic search powered by multilingual-e5-large delivered a nearly 17% reduction in empty search sessions and a 2% lift in search session success, and was made generally available to all Pro and Essential users in August 2024.
Results
Time savedspend less time searching
Volumenearly 17%
Running sinceAugust 2024
Grounding & classification
Source type: technical build writeup
20 fields verified against source quotes.
enterprise searchknowledge searchknowledge basemetric backednamed customerproduction runtime claimedsource backedtools describedworkflow describedsoftwareaccuracy improvementtime savedtechnical build writeupback office ops