wb
b26fff0d0f
- Replace Ollama-native API (/api/generate) with OpenAI-compatible /v1/chat/completions — works with Ollama, OpenAI, Groq, LM Studio, LocalAI, and any other OpenAI-compatible endpoint - New providers table: name, base_url, optional API key, default flag - Settings page: add/delete/set-default providers; rename LLM params from ollama_* to llm_* settings keys - Per-prompt: choose provider from dropdown, model load button fetches from that provider's /v1/models - <think>…</think> tags extracted for live thinking display (works with Ollama thinking models and DeepSeek-R1 style responses) - Existing OLLAMA_BASE_URL env var seeds the initial provider on first start for backward compat Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
diarization-ui
Eigenes UI-Projekt (separates Repo/Container) für:
- Upload Audio
- Aufruf von
transcribe-diarizeAPI - Speichern in SQLite
- LLM-Auswertung via Ollama (Qwen)
- Projekte/Prompts/Dokumente verwalten
Container Registry
Image ist veröffentlicht unter:
registry.aquantico.lan/claw/diarization-ui:latest
Hinweis: Registry-Zertifikat ist self-signed. Ggf.
--tls-verify=false(Podman) oder insecure registry konfigurieren.
.env
API_BASE=http://gx10.aquantico.lan:8093
OLLAMA_BASE_URL=http://gx10.aquantico.lan:11434
OLLAMA_MODEL=qwen3.5:9b
DB_PATH=/data/ui.db
Lokal bauen/starten
cp .env.example .env
docker compose up -d --build
UI: http://127.0.0.1:8094/
Deployment auf anderem Server (mit Registry-Image)
Beispiel docker-compose.yml (ähnlich zu deinem Traefik-Setup):
version: "3.8"
services:
diarization-ui:
image: registry.aquantico.lan/claw/diarization-ui:latest
container_name: diarization-ui
restart: always
environment:
- API_BASE=http://gx10.aquantico.lan:8093
- OLLAMA_BASE_URL=http://gx10.aquantico.lan:11434
- OLLAMA_MODEL=qwen3.5:9b
- DB_PATH=/data/ui.db
volumes:
- diarization_ui_data:/data
ports:
- "8094:8094"
networks:
- traefik
labels:
- "traefik.enable=true"
- "traefik.http.routers.diarization-ui.rule=Host(`voicelog.aquantico.lan`)"
- "traefik.http.routers.diarization-ui.entrypoints=websecure"
- "traefik.http.routers.diarization-ui.tls=true"
- "traefik.http.services.diarization-ui.loadbalancer.server.port=8094"
networks:
traefik:
external: true
volumes:
diarization_ui_data:
Dann starten:
docker compose pull
docker compose up -d
Podman Pull/Run mit Registry-Image
podman login registry.aquantico.lan --tls-verify=false
podman pull --tls-verify=false registry.aquantico.lan/claw/diarization-ui:latest
podman rm -f diarization-ui || true
podman run -d --name diarization-ui -p 18094:8094 \
-e API_BASE=http://gx10.aquantico.lan:8093 \
-e OLLAMA_BASE_URL=http://gx10.aquantico.lan:11434 \
-e OLLAMA_MODEL=qwen3.5:9b \
-e DB_PATH=/data/ui.db \
-v diarization_ui_data:/data \
registry.aquantico.lan/claw/diarization-ui:latest