phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-26 19:24:27 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix use router level client for OpenAI / Azure transcription calls

Browse source
This commit is contained in:
Ishaan Jaff 2024-07-02 12:33:31 -07:00
parent f7e12f551e
commit c7f278f686
1 changed files with 16 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

17
litellm/main.py
View file

@ -48,6 +48,7 @@ from litellm import ( # type: ignore
get_litellm_params, get_litellm_params,
get_optional_params, get_optional_params,
) )
from litellm.litellm_core_utils.litellm_logging import Logging as LiteLLMLoggingObj
from litellm.utils import ( from litellm.utils import (
CustomStreamWrapper, CustomStreamWrapper,
Usage, Usage,
@ -4251,7 +4252,7 @@ def transcription(
api_base: Optional[str] = None, api_base: Optional[str] = None,
api_version: Optional[str] = None, api_version: Optional[str] = None,
max_retries: Optional[int] = None, max_retries: Optional[int] = None,
litellm_logging_obj=None, litellm_logging_obj: Optional[LiteLLMLoggingObj] = None,
custom_llm_provider=None, custom_llm_provider=None,
**kwargs, **kwargs,
): ):
@ -4266,6 +4267,18 @@ def transcription(
proxy_server_request = kwargs.get("proxy_server_request", None) proxy_server_request = kwargs.get("proxy_server_request", None)
model_info = kwargs.get("model_info", None) model_info = kwargs.get("model_info", None)
metadata = kwargs.get("metadata", {}) metadata = kwargs.get("metadata", {})
client: Optional[
Union[
openai.AsyncOpenAI,
openai.OpenAI,
openai.AzureOpenAI,
openai.AsyncAzureOpenAI,
]
] = kwargs.pop("client", None)
if litellm_logging_obj:
litellm_logging_obj.model_call_details["client"] = str(client)
if max_retries is None: if max_retries is None:
max_retries = openai.DEFAULT_MAX_RETRIES max_retries = openai.DEFAULT_MAX_RETRIES
@ -4305,6 +4318,7 @@ def transcription(
optional_params=optional_params, optional_params=optional_params,
model_response=model_response, model_response=model_response,
atranscription=atranscription, atranscription=atranscription,
client=client,
timeout=timeout, timeout=timeout,
logging_obj=litellm_logging_obj, logging_obj=litellm_logging_obj,
api_base=api_base, api_base=api_base,
@ -4338,6 +4352,7 @@ def transcription(
optional_params=optional_params, optional_params=optional_params,
model_response=model_response, model_response=model_response,
atranscription=atranscription, atranscription=atranscription,
client=client,
timeout=timeout, timeout=timeout,
logging_obj=litellm_logging_obj, logging_obj=litellm_logging_obj,
max_retries=max_retries, max_retries=max_retries,