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

feat(proxy/utils.py): return api base for request hanging alerts

Browse source
This commit is contained in:
Krrish Dholakia 2024-04-06 15:58:53 -07:00
parent b49e47b634
commit 6110d32b1c
7 changed files with 180 additions and 15 deletions
Download patch file Download diff file Expand all files Collapse all files

8
litellm/proxy/proxy_server.py
View file

@ -3441,13 +3441,15 @@ async def chat_completion(
) # run the moderation check in parallel to the actual llm api call
response = responses[1]
# Post Call Processing
data["litellm_status"] = "success" # used for alerting
hidden_params = getattr(response, "_hidden_params", {}) or {}
model_id = hidden_params.get("model_id", None) or ""
cache_key = hidden_params.get("cache_key", None) or ""
# Post Call Processing
if llm_router is not None:
data["deployment"] = llm_router.get_deployment(model_id=model_id)
data["litellm_status"] = "success" # used for alerting
if (
"stream" in data and data["stream"] == True
): # use generate_responses to stream responses