phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-26 03:04:13 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix(azure.py): fix error handling for openai/azure streaming

Browse source
This commit is contained in:
Krrish Dholakia 2023-11-29 11:52:24 -08:00
parent b6bc75e27a
commit a9ed768991
4 changed files with 32 additions and 8 deletions
Download patch file Download diff file Expand all files Collapse all files

5
litellm/llms/azure.py
View file

@ -221,7 +221,7 @@ class AzureChatCompletion(BaseLLM):
timeout: Any,
azure_ad_token: Optional[str]=None,
client=None,
):
):
max_retries = data.pop("max_retries", 2)
if not isinstance(max_retries, int):
raise AzureOpenAIError(status_code=422, message="max retries must be an int")
@ -244,8 +244,7 @@ class AzureChatCompletion(BaseLLM):
azure_client = client
response = azure_client.chat.completions.create(**data)
streamwrapper = CustomStreamWrapper(completion_stream=response, model=model, custom_llm_provider="azure",logging_obj=logging_obj)
for transformed_chunk in streamwrapper:
yield transformed_chunk
return streamwrapper
async def async_streaming(self,
logging_obj,