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

fix exception mapping for vertex ai

Browse source
This commit is contained in:
Ishaan Jaff 2024-06-18 08:38:36 -07:00
parent fdb9b24b9f
commit 8f3bd0780b
1 changed files with 17 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

17
litellm/utils.py
View file

@ -6297,6 +6297,7 @@ def exception_type(
) )
elif ( elif (
"429 Quota exceeded" in error_str "429 Quota exceeded" in error_str
or "Quota exceeded for" in error_str
or "IndexError: list index out of range" in error_str or "IndexError: list index out of range" in error_str
or "429 Unable to submit request because the service is temporarily out of capacity." or "429 Unable to submit request because the service is temporarily out of capacity."
in error_str in error_str
@ -6339,6 +6340,22 @@ def exception_type(
), ),
), ),
) )
if original_exception.status_code == 429:
exception_mapping_worked = True
raise RateLimitError(
message=f"litellm.RateLimitError: VertexAIException - {error_str}",
model=model,
llm_provider="vertex_ai",
litellm_debug_info=extra_information,
response=httpx.Response(
status_code=429,
request=httpx.Request(
method="POST",
url=" https://cloud.google.com/vertex-ai/",
),
),
)
if original_exception.status_code == 500: if original_exception.status_code == 500:
exception_mapping_worked = True exception_mapping_worked = True
raise litellm.InternalServerError( raise litellm.InternalServerError(