scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-06 02:48:13 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 103

docs(alerting.md): add region-based outage alerting to docs

Browse source
This commit is contained in:
Krrish Dholakia 2024-05-25 22:04:08 -07:00
parent 4e6ca3cb6d
commit 5f50c1125d
1 changed files with 25 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

26
docs/my-website/docs/proxy/alerting.md
View file

@ -199,4 +199,28 @@ curl -X GET --location 'http://0.0.0.0:4000/health/services?service=webhook' \
* "team": The event is related to a team.
* "proxy": The event is related to a proxy.
- `event_message` *str*: A human-readable description of the event.
- `event_message` *str*: A human-readable description of the event.
## Advanced - Region-outage alerting (✨ Enterprise feature)
Setup alerts if a provider region is having an outage.
```yaml
general_settings:
alerting: ["slack"]
alert_types: ["region_outage_alerts"]
```
By default this will trigger if multiple models in a region fail 5+ requests in 1 minute. '400' status code errors are not counted (i.e. BadRequestErrors).
Control thresholds with:
```yaml
general_settings:
alerting: ["slack"]
alert_types: ["region_outage_alerts"]
alerting_args:
region_outage_alert_ttl: 60 # time-window in seconds
minor_outage_alert_threshold: 5 # number of errors to trigger a minor alert
major_outage_alert_threshold: 10 # number of errors to trigger a major alert
```