phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-25 18:54:30 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

(Fixes) OpenAI Streaming Token Counting + Fixes usage track when litellm.turn_off_message_logging=True (#8156)

Browse source 
* working streaming usage tracking

* fix test_async_chat_openai_stream_options

* fix await asyncio.sleep(1)

* test_async_chat_azure

* fix s3 logging

* fix get_stream_options

* fix get_stream_options

* fix streaming handler

* test_stream_token_counting_with_redaction

* fix codeql concern
This commit is contained in:
Ishaan Jaff 2025-01-31 15:06:37 -08:00 • committed by GitHub
parent 38b4980018
commit ef6ab91ac2
8 changed files with 268 additions and 94 deletions
Download patch file Download diff file Expand all files Collapse all files

6
litellm/utils.py
View file

@ -166,7 +166,6 @@ with resources.open_text(
# Convert to str (if necessary)
claude_json_str = json.dumps(json_data)
import importlib.metadata
from concurrent.futures import ThreadPoolExecutor
from typing import (
TYPE_CHECKING,
Any,
@ -185,6 +184,7 @@ from typing import (
from openai import OpenAIError as OriginalError
from litellm.litellm_core_utils.thread_pool_executor import executor
from litellm.llms.base_llm.audio_transcription.transformation import (
BaseAudioTranscriptionConfig,
)
@ -235,10 +235,6 @@ from .types.router import LiteLLM_Params
####### ENVIRONMENT VARIABLES ####################
# Adjust to your specific application needs / system capabilities.
MAX_THREADS = 100
# Create a ThreadPoolExecutor
executor = ThreadPoolExecutor(max_workers=MAX_THREADS)
sentry_sdk_instance = None
capture_exception = None
add_breadcrumb = None