phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-25 02:34:29 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix(utils.py): add response ms for async calls

Browse source
This commit is contained in:
Krrish Dholakia 2023-11-21 19:58:52 -08:00
parent 898f15af2b
commit 381fdcd37b
2 changed files with 5 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

2
litellm/utils.py
View file

@ -1370,6 +1370,8 @@ def client(original_function):
# LOG SUCCESS - handle streaming success logging in the _next_ object, remove `handle_success` once it's deprecated
threading.Thread(target=logging_obj.success_handler, args=(result, start_time, end_time)).start()
# RETURN RESULT
if isinstance(result, ModelResponse):
result._response_ms = (end_time - start_time).total_seconds() * 1000 # return response latency in ms like openai
return result
except Exception as e:
call_type = original_function.__name__