phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-25 10:44:24 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Litellm dev 2024 12 20 p1 (#7335)

Browse source 
* fix(utils.py): e2e azure tts cost tracking working

moves tts response obj to include hidden params (allows for litellm call id, etc. to be sent in response headers) ; fixes spend_Tracking_utils logging payload to account for non-base model use-case

Fixes https://github.com/BerriAI/litellm/issues/7223

* fix: fix linting errors

* build(model_prices_and_context_window.json): add bedrock llama 3.3

Closes https://github.com/BerriAI/litellm/issues/7329

* fix(openai.py): fix return type for sync openai httpx response

* test: update test

* fix(spend_tracking_utils.py): fix if check

* fix(spend_tracking_utils.py): fix if check

* test: improve debugging for test

* fix: fix import
This commit is contained in:
Krish Dholakia 2024-12-20 21:22:31 -08:00 • committed by GitHub
parent 522da384b6
commit 404bf2974b
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
12 changed files with 63 additions and 36 deletions
Download patch file Download diff file Expand all files Collapse all files

29
litellm/llms/openai/openai.py
View file

@ -1253,13 +1253,13 @@ class OpenAIChatCompletion(BaseLLM):
client=client,
)
response = openai_client.audio.speech.create(
response = cast(OpenAI, openai_client).audio.speech.create(
model=model,
voice=voice, # type: ignore
input=input,
**optional_params,
)
return response # type: ignore
return HttpxBinaryResponseContent(response=response.response)
async def async_audio_speech(
self,
@ -1276,13 +1276,16 @@ class OpenAIChatCompletion(BaseLLM):
client=None,
) -> HttpxBinaryResponseContent:
openai_client = self._get_openai_client(
is_async=True,
api_key=api_key,
api_base=api_base,
timeout=timeout,
max_retries=max_retries,
client=client,
openai_client = cast(
AsyncOpenAI,
self._get_openai_client(
is_async=True,
api_key=api_key,
api_base=api_base,
timeout=timeout,
max_retries=max_retries,
client=client,
),
)
response = await openai_client.audio.speech.create(
@ -1292,7 +1295,7 @@ class OpenAIChatCompletion(BaseLLM):
**optional_params,
)
return response
return HttpxBinaryResponseContent(response=response.response)
async def ahealth_check(
self,
@ -1477,7 +1480,7 @@ class OpenAIFilesAPI(BaseLLM):
openai_client: AsyncOpenAI,
) -> HttpxBinaryResponseContent:
response = await openai_client.files.content(**file_content_request)
return response
return HttpxBinaryResponseContent(response=response.response)
def file_content(
self,
@ -1515,9 +1518,9 @@ class OpenAIFilesAPI(BaseLLM):
file_content_request=file_content_request,
openai_client=openai_client,
)
response = openai_client.files.content(**file_content_request)
response = cast(OpenAI, openai_client).files.content(**file_content_request)
return response
return HttpxBinaryResponseContent(response=response.response)
async def aretrieve_file(
self,