phoenix/litellm
1
0
Fork 0
forked from phoenix/litellm-mirror
Code Pull requests Activity

(fix) only alert users when requests are hanging

Browse source
This commit is contained in:
ishaan-jaff 2024-01-24 15:58:07 -08:00
parent 6c13776701
commit b993c62144
2 changed files with 15 additions and 8 deletions
Download patch file Download diff file Expand all files Collapse all files

4
litellm/proxy/proxy_server.py
View file

@ -1863,6 +1863,8 @@ async def chat_completion(
else: # router is not set
response = await litellm.acompletion(**data)
# Post Call Processing
data["litellm_status"] = "success" # used for alerting
if hasattr(response, "_hidden_params"):
model_id = response._hidden_params.get("model_id", None) or ""
else:
@ -2048,6 +2050,7 @@ async def embeddings(
response = await litellm.aembedding(**data)
### ALERTING ###
data["litellm_status"] = "success" # used for alerting
end_time = time.time()
asyncio.create_task(
proxy_logging_obj.response_taking_too_long(
@ -2163,6 +2166,7 @@ async def image_generation(
response = await litellm.aimage_generation(**data)
### ALERTING ###
data["litellm_status"] = "success" # used for alerting
end_time = time.time()
asyncio.create_task(
proxy_logging_obj.response_taking_too_long(