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 - only run global_proxy_spend on chat completion calls

Browse source
This commit is contained in:
Ishaan Jaff 2024-04-27 14:11:00 -07:00
parent 6762d07c7f
commit e49fe47d2e
1 changed files with 9 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

10
litellm/proxy/auth/auth_checks.py
View file

@ -95,7 +95,15 @@ def common_checks(
f"'user' param not passed in. 'enforce_user_param'={general_settings['enforce_user_param']}"
)
# 7. [OPTIONAL] If 'litellm.max_budget' is set (>0), is proxy under budget
if litellm.max_budget > 0 and global_proxy_spend is not None:
if (
litellm.max_budget > 0
and global_proxy_spend is not None
# only run global budget checks for OpenAI routes
# Reason - the Admin UI should continue working if the proxy crosses it's global budget
and route in LiteLLMRoutes.openai_routes.value
and route != "/v1/models"
and route != "/models"
):
if global_proxy_spend > litellm.max_budget:
raise Exception(
f"ExceededBudget: LiteLLM Proxy has exceeded its budget. Current spend: {global_proxy_spend}; Max Budget: {litellm.max_budget}"