5 Commits

Author	SHA1	Message	Date
Marcel	98ee6cf587	feat(nlp-service): wire NLP_FUZZY_THRESHOLD env var with 0-100 validation ... Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>	2026-06-08 10:56:32 +02:00
Marcel	778382cd61	feat(nlp-service): cap /parse query at 500 chars via Field(max_length=500) ... Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>	2026-06-08 10:56:32 +02:00
Marcel	d65879d273	fix(nlp-service): return generic 500 detail to prevent credential leakage ... Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>	2026-06-08 10:56:32 +02:00
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	7404284130	feat(nlp-service): FastAPI app with /parse and /health endpoints ... Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>	2026-06-08 10:56:32 +02:00