AI Suggestions previously invented near-duplicate metadata because the classification
prompt had no knowledge of the installation's own taxonomy. This surfaces
a small, ranked, permission-filtered set of existing tags/document
types/correspondents/storage paths - drawn from the document's RAG
neighbors plus its own already-assigned metadata - so the model prefers
reusing what already exists.
The LLM response schema now returns existing_ids (IDs of reused
candidates) separately from new_names (genuinely new suggestions).
Only new_names goes through localization and fuzzy name-matching;
existing_ids is resolved deterministically and never touched by the
localization pass, so exact matches can no longer be silently
corrupted by translation.
* Update doc modified time upon move and rename
* Clear the cached metadata if the filename(s) have been changed
---------
Co-authored-by: shamoon <4887959+shamoon@users.noreply.github.com>
Trenton HandGitHub
shamoonandGitHub
Antoine MérinoandGitHub