8 Commits

Author	SHA1	Message	Date
Marcel	03d7d44e57	feat(nlp-service): replace spaCy NER with DB-backed PersonMatcher ... Rule-based pipeline: persons matched via rapidfuzz against all known names loaded from DB at startup. Fixes first-name-only extraction (Eugenie, Herbert), merged-span bug (Herbert + Eugenie de Gruyter), false positives on compound nouns, and EN/ES model failures. Date extraction unchanged (regex). No spaCy models required. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>	2026-06-08 10:56:32 +02:00
Marcel	3ddb2b278b	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>	2026-06-08 10:56:32 +02:00
Marcel	702a72d575	feat(nlp-service): keyword extraction (POS-filtered, deduped lemmas)	2026-06-08 10:56:32 +02:00
Marcel	3f74deda8c	feat(nlp-service): date range extraction with direction detection	2026-06-08 10:56:32 +02:00
Marcel	8ed2a6d95b	feat(nlp-service): role detection (sender/receiver/any)	2026-06-08 10:56:32 +02:00
Marcel	deea34c797	feat(nlp-service): NER person name extraction	2026-06-08 10:56:32 +02:00
Marcel	482a1c2863	feat(nlp-service): spaCy model loading with get_nlp/load_all_models	2026-06-08 10:56:32 +02:00
Marcel	6b0a06e8b1	feat(nlp-service): scaffold — models, requirements, CLAUDE.md ... Task 1: Create standalone FastAPI service scaffold with models, test framework, and documentation. Includes ParseRequest, ParseResponse Pydantic models matching OllamaExtraction contract, plus three passing tests validating model validation. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>	2026-06-07 10:11:34 +02:00