phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-27 19:54:13 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

(feat) send api_base

Browse source
This commit is contained in:
ishaan-jaff 2024-03-02 11:06:03 -08:00
parent 7cc390ff37
commit 343f9d05f9
1 changed files with 25 additions and 10 deletions
Download patch file Download diff file Expand all files Collapse all files

35
litellm/proxy/utils.py
View file

@ -64,6 +64,7 @@ class ProxyLogging:
litellm.callbacks.append(self.max_parallel_request_limiter) litellm.callbacks.append(self.max_parallel_request_limiter)
litellm.callbacks.append(self.max_budget_limiter) litellm.callbacks.append(self.max_budget_limiter)
litellm.callbacks.append(self.cache_control_check) litellm.callbacks.append(self.cache_control_check)
litellm.callbacks.append(self.response_taking_too_long_callback)
for callback in litellm.callbacks: for callback in litellm.callbacks:
if callback not in litellm.input_callback: if callback not in litellm.input_callback:
litellm.input_callback.append(callback) litellm.input_callback.append(callback)
@ -142,6 +143,30 @@ class ProxyLogging:
raise e raise e
return data return data
async def response_taking_too_long_callback(
self,
kwargs, # kwargs to completion
completion_response, # response from completion
start_time,
end_time, # start/end time
):
if self.alerting is None:
return
time_difference = end_time - start_time
# Convert the timedelta to float (in seconds)
time_difference_float = time_difference.total_seconds()
litellm_params = kwargs.get("litellm_params", {})
api_base = litellm_params.get("api_base", "")
model = kwargs.get("model", "")
messages = kwargs.get("messages", "")
request_info = f"\nRequest Model: `{model}`\nAPI Base: `{api_base}`\nMessages: `{messages}`"
slow_message = f"`Responses are slow - {round(time_difference_float,2)}s response time > Alerting threshold: {self.alerting_threshold}s`"
if time_difference_float > self.alerting_threshold:
await self.alerting_handler(
message=slow_message + request_info,
level="Low",
)
async def response_taking_too_long( async def response_taking_too_long(
self, self,
start_time: Optional[float] = None, start_time: Optional[float] = None,
@ -189,16 +214,6 @@ class ProxyLogging:
level="Medium", level="Medium",
) )
elif (
type == "slow_response" and start_time is not None and end_time is not None
):
slow_message = f"`Responses are slow - {round(end_time-start_time,2)}s response time > Alerting threshold: {self.alerting_threshold}s`"
if end_time - start_time > self.alerting_threshold:
await self.alerting_handler(
message=slow_message + request_info,
level="Low",
)
async def budget_alerts( async def budget_alerts(
self, self,
type: Literal[ type: Literal[