phoenix/litellm
1
0
Fork 0
forked from phoenix/litellm-mirror
Code Pull requests Activity

feat: add cost tracking + caching for transcription calls

Browse source
This commit is contained in:
Krrish Dholakia 2024-03-09 15:43:38 -08:00
parent e10991e02b
commit fa45c569fd
8 changed files with 225 additions and 37 deletions
Download patch file Download diff file Expand all files Collapse all files

6
litellm/llms/openai.py
View file

@ -824,7 +824,8 @@ class OpenAIChatCompletion(BaseLLM):
additional_args={"complete_input_dict": data},
original_response=stringified_response,
)
final_response = convert_to_model_response_object(response_object=stringified_response, model_response_object=model_response, response_type="audio_transcription") # type: ignore
hidden_params = {"model": "whisper-1", "custom_llm_provider": "openai"}
final_response = convert_to_model_response_object(response_object=stringified_response, model_response_object=model_response, hidden_params=hidden_params, response_type="audio_transcription") # type: ignore
return final_response
async def async_audio_transcriptions(
@ -862,7 +863,8 @@ class OpenAIChatCompletion(BaseLLM):
additional_args={"complete_input_dict": data},
original_response=stringified_response,
)
return convert_to_model_response_object(response_object=stringified_response, model_response_object=model_response, response_type="audio_transcription") # type: ignore
hidden_params = {"model": "whisper-1", "custom_llm_provider": "openai"}
return convert_to_model_response_object(response_object=stringified_response, model_response_object=model_response, hidden_params=hidden_params, response_type="audio_transcription") # type: ignore
except Exception as e:
## LOGGING
logging_obj.post_call(