phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-25 10:44:24 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix(replicate.py): move replicate calls to being completely async

Browse source 
Closes https://github.com/BerriAI/litellm/issues/3128
This commit is contained in:
Krrish Dholakia 2024-05-16 17:24:08 -07:00
parent a2a5884df1
commit 709373b15c
5 changed files with 326 additions and 59 deletions
Download patch file Download diff file Expand all files Collapse all files

6
litellm/utils.py
View file

@ -8606,7 +8606,10 @@ def exception_type(
message=f"ReplicateException - {str(original_exception)}",
llm_provider="replicate",
model=model,
request=original_exception.request,
request=httpx.Request(
method="POST",
url="https://api.replicate.com/v1/deployments",
),
)
elif custom_llm_provider == "watsonx":
if "token_quota_reached" in error_str:
@ -11485,6 +11488,7 @@ class CustomStreamWrapper:
or self.custom_llm_provider == "vertex_ai"
or self.custom_llm_provider == "sagemaker"
or self.custom_llm_provider == "gemini"
or self.custom_llm_provider == "replicate"
or self.custom_llm_provider == "cached_response"
or self.custom_llm_provider == "predibase"
or (self.custom_llm_provider == "bedrock" and "cohere" in self.model)