phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-26 19:24:27 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

refactor: instrument 'dynamic_rate_limiting' callback on proxy

Browse source
This commit is contained in:
Krrish Dholakia 2024-06-22 00:32:29 -07:00
parent 6a7982fa40
commit 8f95381276
8 changed files with 136 additions and 28 deletions
Download patch file Download diff file Expand all files Collapse all files

9
litellm/proxy/proxy_server.py
View file

@ -2644,7 +2644,9 @@ async def startup_event():
redis_cache=redis_usage_cache
) # used by parallel request limiter for rate limiting keys across instances
proxy_logging_obj._init_litellm_callbacks() # INITIALIZE LITELLM CALLBACKS ON SERVER STARTUP <- do this to catch any logging errors on startup, not when calls are being made
proxy_logging_obj._init_litellm_callbacks(
llm_router=llm_router
) # INITIALIZE LITELLM CALLBACKS ON SERVER STARTUP <- do this to catch any logging errors on startup, not when calls are being made
if "daily_reports" in proxy_logging_obj.slack_alerting_instance.alert_types:
asyncio.create_task(
@ -3116,11 +3118,10 @@ async def chat_completion(
except Exception as e:
data["litellm_status"] = "fail" # used for alerting
verbose_proxy_logger.error(
"litellm.proxy.proxy_server.chat_completion(): Exception occured - {}".format(
get_error_message_str(e=e)
"litellm.proxy.proxy_server.chat_completion(): Exception occured - {}\n{}".format(
get_error_message_str(e=e), traceback.format_exc()
)
)
verbose_proxy_logger.debug(traceback.format_exc())
await proxy_logging_obj.post_call_failure_hook(
user_api_key_dict=user_api_key_dict, original_exception=e, request_data=data
)