phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-26 11:14:04 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

(fix) slack alerting - don't spam the failed cost tracking alert for the same model (#6543)

Browse source 
* fix use failing_model as cache key for failed_tracking_alert

* fix use standard logging payload for getting response cost

* fix  kwargs.get("response_cost")

* fix getting response cost
This commit is contained in:
Ishaan Jaff 2024-11-01 18:36:17 +05:30 • committed by GitHub
parent 94a2963b35
commit ab0e405453
4 changed files with 24 additions and 12 deletions
Download patch file Download diff file Expand all files Collapse all files

9
litellm/proxy/utils.py
View file

@ -667,13 +667,18 @@ class ProxyLogging:
raise e
return data
async def failed_tracking_alert(self, error_message: str):
async def failed_tracking_alert(
self,
error_message: str,
failing_model: str,
):
if self.alerting is None:
return
if self.slack_alerting_instance:
await self.slack_alerting_instance.failed_tracking_alert(
error_message=error_message
error_message=error_message,
failing_model=failing_model,
)
async def budget_alerts(