Commit Graph

6 Commits

Author SHA1 Message Date
Marcel
cc4c81e218 feat(nlp-service): full extract() pipeline — assembles all steps
Also adds regex year-fallback in extract_dates() for de/es spaCy small
models that don't tag bare 4-digit years as DATE entities, and widens
the direction-token window to 2 tokens back to handle Spanish "antes de".

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-06-07 10:28:40 +02:00
Marcel
55f419d20f feat(nlp-service): keyword extraction (POS-filtered, deduped lemmas) 2026-06-07 10:24:35 +02:00
Marcel
53f6dcbfed feat(nlp-service): date range extraction with direction detection 2026-06-07 10:23:33 +02:00
Marcel
0ab2e2a743 feat(nlp-service): role detection (sender/receiver/any) 2026-06-07 10:22:14 +02:00
Marcel
bff16f6f1f feat(nlp-service): NER person name extraction 2026-06-07 10:21:16 +02:00
Marcel
18f028e2dd feat(nlp-service): spaCy model loading with get_nlp/load_all_models 2026-06-07 10:17:07 +02:00