mirror of
https://github.com/BerriAI/litellm.git
synced 2025-04-26 11:14:04 +00:00
fix(main.py): support max retries for transcription calls
This commit is contained in:
parent
c3e4af76cf
commit
ceabf726b0
3 changed files with 7 additions and 3 deletions
|
@ -799,6 +799,7 @@ class AzureChatCompletion(BaseLLM):
|
|||
optional_params: dict,
|
||||
model_response: TranscriptionResponse,
|
||||
timeout: float,
|
||||
max_retries: int,
|
||||
api_key: Optional[str] = None,
|
||||
api_base: Optional[str] = None,
|
||||
api_version: Optional[str] = None,
|
||||
|
@ -817,8 +818,6 @@ class AzureChatCompletion(BaseLLM):
|
|||
"timeout": timeout,
|
||||
}
|
||||
|
||||
max_retries = optional_params.pop("max_retries", None)
|
||||
|
||||
azure_client_params = select_azure_base_url_or_endpoint(
|
||||
azure_client_params=azure_client_params
|
||||
)
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue