phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-27 11:43:54 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix(proxy/utils.py): check cache before alerting user

Browse source
This commit is contained in:
Krrish Dholakia 2024-03-27 20:09:15 -07:00
parent 265d32679e
commit 7fe02405e0
2 changed files with 22 additions and 9 deletions
Download patch file Download diff file Expand all files Collapse all files

14
litellm/proxy/utils.py
View file

@ -298,6 +298,7 @@ class ProxyLogging:
return
else:
user_info = str(user_info)
# percent of max_budget left to spend
if user_max_budget > 0:
percent_left = (user_max_budget - user_current_spend) / user_max_budget
@ -317,22 +318,35 @@ class ProxyLogging:
)
return
## PREVENTITIVE ALERTING ## - https://github.com/BerriAI/litellm/issues/2727
# - Alert once within 28d period
# - Cache this information
# - Don't re-alert, if alert already sent
_cache: DualCache = self.call_details["user_api_key_cache"]
# check if 5% of max budget is left
if percent_left <= 0.05:
message = "5% budget left for" + user_info
result = await _cache.async_get_cache(key=message)
if result is None:
await self.alerting_handler(
message=message,
level="Medium",
)
await _cache.async_set_cache(key=message, value="SENT", ttl=2419200)
return
# check if 15% of max budget is left
if percent_left <= 0.15:
message = "15% budget left for" + user_info
result = await _cache.async_get_cache(key=message)
if result is None:
await self.alerting_handler(
message=message,
level="Low",
)
await _cache.async_set_cache(key=message, value="SENT", ttl=2419200)
return
return

1
litellm/utils.py
View file

@ -2775,7 +2775,6 @@ def client(original_function):
or isinstance(e, openai.Timeout)
or isinstance(e, openai.APIConnectionError)
):
print_verbose(f"RETRY TRIGGERED!")
kwargs["num_retries"] = num_retries
return litellm.completion_with_retries(*args, **kwargs)
elif (