phoenix/litellm
1
0
Fork 0
forked from phoenix/litellm-mirror
Code Pull requests Activity

Merge pull request #2347 from BerriAI/litellm_retry_rate_limited_requests

Browse source 
feat(proxy_server.py): retry if virtual key is rate limited
This commit is contained in:
Krish Dholakia 2024-03-06 19:23:11 -08:00 • committed by GitHub
commit cb8b30970b
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
7 changed files with 71 additions and 12 deletions
Download patch file Download diff file Expand all files Collapse all files

8
litellm/utils.py
View file

@ -6655,10 +6655,11 @@ def exception_type(
method="POST", url="https://api.openai.com/v1"
)
raise APIError(
status_code=500,
message=f"{exception_provider} - {message}",
llm_provider=custom_llm_provider,
model=model,
response=httpx.Response(status_code=500, request=_request),
request=_request,
)
elif hasattr(original_exception, "status_code"):
exception_mapping_worked = True
@ -7104,7 +7105,10 @@ def exception_type(
llm_provider="palm",
response=original_exception.response,
)
if "504 Deadline expired before operation could complete." in error_str:
if (
"504 Deadline expired before operation could complete." in error_str
or "504 Deadline Exceeded" in error_str
):
exception_mapping_worked = True
raise Timeout(
message=f"PalmException - {original_exception.message}",