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

feat(slack_alerting.py): refactor region outage alerting to do model based alerting instead

Browse source 
Unable to extract azure region from api base, makes sense to start with model alerting and then move to region
This commit is contained in:
Krrish Dholakia 2024-05-24 19:10:33 -07:00
parent a8fb4e33d5
commit 4536ed6f6e
7 changed files with 119 additions and 51 deletions
Download patch file Download diff file Expand all files Collapse all files

14
litellm/router.py
View file

@ -3876,13 +3876,13 @@ class Router:
_api_base = litellm.get_api_base(
model=_model_name, optional_params=temp_litellm_params
)
asyncio.create_task(
proxy_logging_obj.slack_alerting_instance.send_alert(
message=f"Router: Cooling down Deployment:\nModel Name: `{_model_name}`\nAPI Base: `{_api_base}`\nCooldown Time: `{cooldown_time} seconds`\nException Status Code: `{str(exception_status)}`\n\nChange 'cooldown_time' + 'allowed_fails' 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",
)
)
# asyncio.create_task(
# proxy_logging_obj.slack_alerting_instance.send_alert(
# message=f"Router: Cooling down Deployment:\nModel Name: `{_model_name}`\nAPI Base: `{_api_base}`\nCooldown Time: `{cooldown_time} seconds`\nException Status Code: `{str(exception_status)}`\n\nChange 'cooldown_time' + 'allowed_fails' 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",
# )
# )
except Exception as e:
pass