fix(perf): add missing shared_sessions to audio/transcriptions (#16858)

This took longer than expected because the fake LLM endpoint on railway was deliverying bad performance when deployed due to some issue with railway.

litellm/llms/custom_httpx/llm_http_handler.py

@@ -1140,6 +1140,7 @@ class BaseLLMHTTPHandler:
         atranscription: bool = False,
         headers: Optional[Dict[str, Any]] = None,
         provider_config: Optional[BaseAudioTranscriptionConfig] = None,
+        shared_session: Optional["ClientSession"] = None,
     ) -> Union[TranscriptionResponse, Coroutine[Any, Any, TranscriptionResponse]]:
         if provider_config is None:
             raise ValueError(
@@ -1162,6 +1163,7 @@ class BaseLLMHTTPHandler:
                 client=client,
                 headers=headers,
                 provider_config=provider_config,
+                shared_session=shared_session,
             )
 
         # Prepare the request
@@ -1226,6 +1228,7 @@ class BaseLLMHTTPHandler:
         client: Optional[Union[HTTPHandler, AsyncHTTPHandler]] = None,
         headers: Optional[Dict[str, Any]] = None,
         provider_config: Optional[BaseAudioTranscriptionConfig] = None,
+        shared_session: Optional["ClientSession"] = None,
     ) -> TranscriptionResponse:
         if provider_config is None:
             raise ValueError(
@@ -1254,6 +1257,7 @@ class BaseLLMHTTPHandler:
             async_httpx_client = get_async_httpx_client(
                 llm_provider=litellm.LlmProviders(custom_llm_provider),
                 params={"ssl_verify": litellm_params.get("ssl_verify", None)},
+                shared_session=shared_session,
             )
         else:
             async_httpx_client = client

litellm/llms/openai/transcriptions/handler.py

@@ -1,10 +1,13 @@
-from typing import Optional, Union, cast
+from typing import TYPE_CHECKING, Optional, Union, cast
 
 import httpx
 from openai import AsyncOpenAI, OpenAI
 from pydantic import BaseModel
 
 import litellm
+
+if TYPE_CHECKING:
+    from aiohttp import ClientSession
 from litellm.litellm_core_utils.audio_utils.utils import get_audio_file_name
 from litellm.litellm_core_utils.litellm_logging import Logging as LiteLLMLoggingObj
 from litellm.llms.base_llm.audio_transcription.transformation import (
@@ -89,6 +92,7 @@ class OpenAIAudioTranscription(OpenAIChatCompletion):
         client=None,
         atranscription: bool = False,
         provider_config: Optional[BaseAudioTranscriptionConfig] = None,
+        shared_session: Optional["ClientSession"] = None,
     ) -> TranscriptionResponse:
         """
         Handle audio transcription request
@@ -116,6 +120,7 @@ class OpenAIAudioTranscription(OpenAIChatCompletion):
                 client=client,
                 max_retries=max_retries,
                 logging_obj=logging_obj,
+                shared_session=shared_session,
             )
 
         openai_client: OpenAI = self._get_openai_client(  # type: ignore
@@ -170,6 +175,7 @@ class OpenAIAudioTranscription(OpenAIChatCompletion):
         api_base: Optional[str] = None,
         client=None,
         max_retries=None,
+        shared_session: Optional["ClientSession"] = None,
     ):
         try:
             openai_aclient: AsyncOpenAI = self._get_openai_client(  # type: ignore
@@ -179,6 +185,7 @@ class OpenAIAudioTranscription(OpenAIChatCompletion):
                 timeout=timeout,
                 max_retries=max_retries,
                 client=client,
+                shared_session=shared_session,
             )
 
             ## LOGGING

litellm/main.py

@@ -5516,6 +5516,7 @@ def transcription(
     atranscription = kwargs.pop("atranscription", False)
     litellm_logging_obj: LiteLLMLoggingObj = kwargs.get("litellm_logging_obj")  # type: ignore
     extra_headers = kwargs.get("extra_headers", None)
+    shared_session = kwargs.get("shared_session", None)
     kwargs.pop("tags", [])
     non_default_params = get_non_default_transcription_params(kwargs)
 
@@ -5653,6 +5654,7 @@ def transcription(
             api_key=api_key,
             provider_config=provider_config,
             litellm_params=litellm_params_dict,
+            shared_session=shared_session,
         )
     elif provider_config is not None:
         response = base_llm_http_handler.audio_transcriptions(
@@ -5679,6 +5681,7 @@ def transcription(
             custom_llm_provider=custom_llm_provider,
             headers={},
             provider_config=provider_config,
+            shared_session=shared_session,
         )
 
     # Calculate and add duration if response is missing it