Add design spec for alpha-id ICD code suggestion PoC

Brainstormed design: free-text dictation (marker-segmented by
doctate) -> single prioritized top-10 ICD-10-GM list with tag
filtering. Two modes (C lexical baseline, A hybrid retrieval +
IONOS bge-m3 + Qwen3-VL-Reranker-8B), eval harness via synthetic
transcription errors, one-time cost-guarded embedding.

Licensed BfArM data dirs and local settings are gitignored.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
2026-05-18 15:51:55 +02:00
commit b313c94ea3
2 changed files with 200 additions and 0 deletions
+12
View File
@@ -0,0 +1,12 @@
# Lizenzierte BfArM-Referenzdaten (lokal halten, siehe downloadbedingungen-2025.pdf)
/data/
/icd-claml/
# Rust-Build
/target/
# Embedding-/Index-Cache (regenerierbar, ggf. groß; siehe Spec §4)
/index/
# Lokale, persönliche Claude-Code-Overrides (nicht teamweit)
/.claude/settings.local.json