phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-25 18:54:30 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix(slack_alerting.py): don't fire spam alerts when backend api call fails

Browse source
This commit is contained in:
Krrish Dholakia 2024-05-13 10:04:43 -07:00
parent b063ef7a47
commit 13e1577753
4 changed files with 69 additions and 21 deletions
Download patch file Download diff file Expand all files Collapse all files

4
litellm/router.py
View file

@ -1413,7 +1413,7 @@ class Router:
verbose_router_logger.debug(f"Trying to fallback b/w models")
if (
hasattr(e, "status_code")
and e.status_code == 400
and e.status_code == 400 # type: ignore
and not isinstance(e, litellm.ContextWindowExceededError)
): # don't retry a malformed request
raise e
@ -3648,7 +3648,7 @@ class Router:
)
asyncio.create_task(
proxy_logging_obj.slack_alerting_instance.send_alert(
message=f"Router: Cooling down deployment: {_api_base}, for {self.cooldown_time} seconds. Got exception: {str(exception_status)}",
message=f"Router: Cooling down deployment: {_api_base}, for {self.cooldown_time} seconds. Got exception: {str(exception_status)}. Change 'cooldown_time' + 'allowed_failes' under 'Router Settings' on proxy UI, or via config - https://docs.litellm.ai/docs/proxy/reliability#fallbacks--retries--timeouts--cooldowns",
alert_type="cooldown_deployment",
level="Low",
)