Generisches Tool für interaktive Podcast-Mindmaps mit Audio-Playback
Dotty Dotter
cb5978132c
Phase 2: Vorberechnete semantische Similarity + API
- precompute.py: Berechnet paarweise Cosine-Similarity aller Absätze,
speichert Top-10-Nachbarn pro Absatz in semantic_links Tabelle
- API: /api/similar-precomputed/{podcast}/{episode}/{idx} — liefert
vorberechnete ähnliche Stellen in <1ms
- Getestet: 728 Absätze, 7144 Links (Threshold 0.55)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
|
2026-04-20 21:23:31 +02:00 |
|
backend
|
Phase 2: Vorberechnete semantische Similarity + API
|
2026-04-20 21:23:31 +02:00 |
|
scripts
|
#2 Obsidian-Links, #6 Soundbite-Export, #7 Timeline
|
2026-04-20 08:03:12 +02:00 |
|
webapp
|
Phase 1+2: FastAPI-Backend, SQLite, Embeddings, Semantische Suche
|
2026-04-20 10:24:53 +02:00 |
|
.gitignore
|
Phase 1+2: FastAPI-Backend, SQLite, Embeddings, Semantische Suche
|
2026-04-20 10:24:53 +02:00 |
|
docker-compose.yml
|
Phase 1+2: FastAPI-Backend, SQLite, Embeddings, Semantische Suche
|
2026-04-20 10:24:53 +02:00 |
|
Dockerfile
|
Phase 1+2: FastAPI-Backend, SQLite, Embeddings, Semantische Suche
|
2026-04-20 10:24:53 +02:00 |
|
project.example.yaml
|
Initial commit: podcast-mindmap tool
|
2026-04-20 01:25:42 +02:00 |