paperless-ngx

mirror of https://github.com/paperless-ngx/paperless-ngx.git synced 2026-08-16 07:43:22 +00:00

Files

T

Trenton HandGitHub 0e5fbc973a Enhancement: prefer existing tags, types, correspondents, and storage paths in AI suggestions (#13676 )

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.

2026-08-14 15:51:34 -07:00

migrations

Fix: make LLM index migration-check result tri-state, avoid deferred-vs-current ambiguity (#13436 )

2026-08-01 07:20:29 -07:00

tests

Enhancement: prefer existing tags, types, correspondents, and storage paths in AI suggestions (#13676 )

2026-08-14 15:51:34 -07:00

__init__.py

Feature: Paperless AI (#10319 )

2026-01-13 16:24:42 +00:00

ai_classifier.py

Enhancement: prefer existing tags, types, correspondents, and storage paths in AI suggestions (#13676 )