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

response_ms fix

Browse source
This commit is contained in:
ishaan-jaff 2023-09-21 15:44:13 -07:00
parent 9ef783e062
commit aa6f5e13f3
1 changed files with 3 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

6
litellm/utils.py
View file

@ -142,9 +142,9 @@ class ModelResponse(OpenAIObject):
else: else:
self.created = created self.created = created
if response_ms: if response_ms:
self.response_ms = response_ms self._response_ms = response_ms
else: else:
self.response_ms = None self._response_ms = None
self.model = model self.model = model
self.usage = ( self.usage = (
usage usage
@ -639,7 +639,7 @@ def client(original_function):
) # don't interrupt execution of main thread ) # don't interrupt execution of main thread
my_thread.start() my_thread.start()
# RETURN RESULT # RETURN RESULT
result.response_ms = (end_time - start_time).total_seconds() * 1000 # return response latency in ms like openai result._response_ms = (end_time - start_time).total_seconds() * 1000 # return response latency in ms like openai
return result return result
except Exception as e: except Exception as e:
traceback_exception = traceback.format_exc() traceback_exception = traceback.format_exc()