phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-24 10:14:26 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

(fix) azure: remove max retries before completion

Browse source
This commit is contained in:
ishaan-jaff 2023-11-29 16:09:21 -08:00
parent 66bc0fc343
commit 9bf603889f
1 changed files with 1 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

2
litellm/llms/azure.py
View file

@ -133,6 +133,7 @@ class AzureChatCompletion(BaseLLM):
"complete_input_dict": data,
},
)
max_retries = data.pop("max_retries", 2)
if acompletion is True:
if optional_params.get("stream", False):
return self.async_streaming(logging_obj=logging_obj, api_base=api_base, data=data, model=model, api_key=api_key, api_version=api_version, azure_ad_token=azure_ad_token, timeout=timeout, client=client)
@ -141,7 +142,6 @@ class AzureChatCompletion(BaseLLM):
elif "stream" in optional_params and optional_params["stream"] == True:
return self.streaming(logging_obj=logging_obj, api_base=api_base, data=data, model=model, api_key=api_key, api_version=api_version, azure_ad_token=azure_ad_token, timeout=timeout, client=client)
else:
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")
# init AzureOpenAI Client