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

(fix) undo commit fd04b48

Browse source
This commit is contained in:
ishaan-jaff 2023-12-07 18:37:06 -08:00
parent 3f4fe668a8
commit f99e3a3818
1 changed files with 4 additions and 5 deletions
Download patch file Download diff file Expand all files Collapse all files

9
litellm/utils.py
View file

@ -1425,6 +1425,10 @@ def client(original_function):
return litellm.stream_chunk_builder(chunks, messages=kwargs.get("messages", None)) return litellm.stream_chunk_builder(chunks, messages=kwargs.get("messages", None))
else: else:
return result return result
elif "acompletion" in kwargs and kwargs["acompletion"] == True:
return result
elif "aembedding" in kwargs and kwargs["aembedding"] == True:
return result
### POST-CALL RULES ### ### POST-CALL RULES ###
post_call_processing(original_response=result, model=model) post_call_processing(original_response=result, model=model)
@ -1435,7 +1439,6 @@ def client(original_function):
# LOG SUCCESS - handle streaming success logging in the _next_ object, remove `handle_success` once it's deprecated # LOG SUCCESS - handle streaming success logging in the _next_ object, remove `handle_success` once it's deprecated
print_verbose(f"Wrapper: Completed Call, calling async_success_handler") print_verbose(f"Wrapper: Completed Call, calling async_success_handler")
asyncio.run(logging_obj.async_success_handler(result, start_time, end_time))
threading.Thread(target=logging_obj.success_handler, args=(result, start_time, end_time)).start() threading.Thread(target=logging_obj.success_handler, args=(result, start_time, end_time)).start()
# threading.Thread(target=logging_obj.success_handler, args=(result, start_time, end_time)).start() # threading.Thread(target=logging_obj.success_handler, args=(result, start_time, end_time)).start()
my_thread = threading.Thread( my_thread = threading.Thread(
@ -1443,10 +1446,6 @@ 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
if "acompletion" in kwargs and kwargs["acompletion"] == True:
return result
elif "aembedding" in kwargs and kwargs["aembedding"] == True:
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: