scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-11 22:51:28 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 124

fix: shared_sessions not being used

Browse source
This commit is contained in:
AlexsanderHamir 2025-11-17 10:51:18 -08:00
parent c8c1229859
commit 697cb09060
2 changed files with 7 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

5
litellm/llms/openai/openai.py
View file

@ -1414,6 +1414,7 @@ class OpenAIChatCompletion(BaseLLM, BaseOpenAILLM):
timeout: Union[float, httpx.Timeout],
aspeech: Optional[bool] = None,
client=None,
shared_session: Optional["ClientSession"] = None,
) -> HttpxBinaryResponseContent:
if aspeech is not None and aspeech is True:
return self.async_audio_speech(
@ -1428,6 +1429,7 @@ class OpenAIChatCompletion(BaseLLM, BaseOpenAILLM):
max_retries=max_retries,
timeout=timeout,
client=client,
shared_session=shared_session,
) # type: ignore
openai_client = self._get_openai_client(
@ -1437,6 +1439,7 @@ class OpenAIChatCompletion(BaseLLM, BaseOpenAILLM):
timeout=timeout,
max_retries=max_retries,
client=client,
shared_session=shared_session,
)
response = cast(OpenAI, openai_client).audio.speech.create(
@ -1460,6 +1463,7 @@ class OpenAIChatCompletion(BaseLLM, BaseOpenAILLM):
max_retries: int,
timeout: Union[float, httpx.Timeout],
client=None,
shared_session: Optional["ClientSession"] = None,
) -> HttpxBinaryResponseContent:
openai_client = cast(
AsyncOpenAI,
@ -1470,6 +1474,7 @@ class OpenAIChatCompletion(BaseLLM, BaseOpenAILLM):
timeout=timeout,
max_retries=max_retries,
client=client,
shared_session=shared_session,
),
)

2
litellm/main.py
View file

@ -5747,6 +5747,7 @@ def speech( # noqa: PLR0915
proxy_server_request = kwargs.get("proxy_server_request", None)
extra_headers = kwargs.get("extra_headers", None)
model_info = kwargs.get("model_info", None)
shared_session = kwargs.get("shared_session", None)
model, custom_llm_provider, dynamic_api_key, api_base = get_llm_provider(
model=model, custom_llm_provider=custom_llm_provider, api_base=api_base
) # type: ignore
@ -5856,6 +5857,7 @@ def speech( # noqa: PLR0915
timeout=timeout,
client=client, # pass AsyncOpenAI, OpenAI client
aspeech=aspeech,
shared_session=shared_session,
)
elif custom_llm_provider == "azure":
# Check if this is Azure Speech Service (Cognitive Services TTS)