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(router.py): disable cooldowns

Browse source 
allow admin to disable model cooldowns
This commit is contained in:
Krrish Dholakia 2024-07-01 15:03:10 -07:00
parent 43af7fc985
commit 459d294e21
3 changed files with 88 additions and 13 deletions
Download patch file Download diff file Expand all files Collapse all files

9
litellm/main.py
View file

@ -476,6 +476,15 @@ def mock_completion(
model=model, # type: ignore
request=httpx.Request(method="POST", url="https://api.openai.com/v1/"),
)
elif (
isinstance(mock_response, str) and mock_response == "litellm.RateLimitError"
):
raise litellm.RateLimitError(
message="this is a mock rate limit error",
status_code=getattr(mock_response, "status_code", 429), # type: ignore
llm_provider=getattr(mock_response, "llm_provider", custom_llm_provider or "openai"), # type: ignore
model=model,
)
time_delay = kwargs.get("mock_delay", None)
if time_delay is not None:
time.sleep(time_delay)