tiennm99/litellm
1
0
Fork 0
mirror of https://github.com/tiennm99/litellm.git synced 2026-08-07 22:21:46 +00:00
Code Issues Packages Projects Releases Wiki Activity

(fix) proxy raise exceptions from litellm.completion()

Browse Source
This commit is contained in:
ishaan-jaff
2023-11-15 16:26:04 -08:00
parent e698f8218f
commit a18fe5a1fd
1 changed files with 13 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files
litellm/proxy/proxy_server.py
+13 -10
View File
@@ -455,16 +455,19 @@ def litellm_completion(*args, **kwargs):
kwargs["api_base"] = user_api_base
## ROUTE TO CORRECT ENDPOINT ##
router_model_names = [m["model_name"] for m in llm_model_list] if llm_model_list is not None else []
if llm_router is not None and kwargs["model"] in router_model_names: # model in router model list
if call_type == "chat_completion":
response = llm_router.completion(*args, **kwargs)
elif call_type == "text_completion":
response = llm_router.text_completion(*args, **kwargs)
else:
if call_type == "chat_completion":
response = litellm.completion(*args, **kwargs)
elif call_type == "text_completion":
response = litellm.text_completion(*args, **kwargs)
try:
if llm_router is not None and kwargs["model"] in router_model_names: # model in router model list
if call_type == "chat_completion":
response = llm_router.completion(*args, **kwargs)
elif call_type == "text_completion":
response = llm_router.text_completion(*args, **kwargs)
else:
if call_type == "chat_completion":
response = litellm.completion(*args, **kwargs)
elif call_type == "text_completion":
response = litellm.text_completion(*args, **kwargs)
except Exception as e:
raise e
if 'stream' in kwargs and kwargs['stream'] == True: # use generate_responses to stream responses
return StreamingResponse(data_generator(response), media_type='text/event-stream')
return response