Jeena
86268107fa
The 26b model occasionally hangs or fails outright on the local Ollama box, which used to drop every such update into 'manual' for no good reason. Retry the same prompt with a smaller model before giving up, and surface both errors when even the fallback fails. OLLAMA_FALLBACK_MODEL is new config, see .env.sample.
26 lines
804 B
Text
26 lines
804 B
Text
# Required for authenticated version checks
|
|
PAPERLESS_API_TOKEN=replace-with-api-token
|
|
|
|
# Optional (use if upstream APIs need auth to avoid rate limits)
|
|
GITHUB_TOKEN=optional-github-token
|
|
|
|
# FreshRSS login for authenticated About page
|
|
FRESHRSS_USERNAME=your-username
|
|
FRESHRSS_PASSWORD=your-password
|
|
|
|
# Matrix bot notifications
|
|
MATRIX_HOMESERVER=https://matrix.example.net
|
|
MATRIX_ROOM_ID=!roomid:example.net
|
|
MATRIX_ACCESS_TOKEN=replace-with-access-token
|
|
|
|
# Uptime Kuma push URL
|
|
UPTIME_KUMA_PUSH_URL=https://uptime.example.net/api/push/your-token
|
|
|
|
# Uptime Kuma login for version check
|
|
UPTIME_KUMA_USERNAME=your-username
|
|
UPTIME_KUMA_PASSWORD=your-password
|
|
|
|
# Ollama for AI-driven auto-update classification
|
|
OLLAMA_BASE_URL=http://192.168.1.20:11434
|
|
OLLAMA_MODEL=gemma4:26b
|
|
OLLAMA_FALLBACK_MODEL=gemma4:12b
|