fix(acompletion): fix acompletion raise exception issue when custom llm provider is none

litellm/main.py

@@ -154,6 +154,7 @@ async def acompletion(*args, **kwargs):
     model = args[0] if len(args) > 0 else kwargs["model"]
     ### PASS ARGS TO COMPLETION ### 
     kwargs["acompletion"] = True
+    custom_llm_provider = None
     try: 
         # Use a partial function to pass your keyword arguments
         func = partial(completion, *args, **kwargs)
@@ -190,6 +191,7 @@ async def acompletion(*args, **kwargs):
         else: 
             return response
     except Exception as e: 
+        custom_llm_provider = custom_llm_provider or "openai"
         raise exception_type(
                 model=model, custom_llm_provider=custom_llm_provider, original_exception=e, completion_kwargs=args,
             )

litellm/proxy/proxy_server.py

@@ -697,7 +697,7 @@ async def completion(request: Request, model: Optional[str] = None, user_api_key
 @router.post("/chat/completions", dependencies=[Depends(user_api_key_auth)])
 @router.post("/openai/deployments/{model:path}/chat/completions", dependencies=[Depends(user_api_key_auth)]) # azure compatible endpoint
 async def chat_completion(request: Request, model: Optional[str] = None, user_api_key_dict: dict = Depends(user_api_key_auth)):
-    global general_settings
+    global general_settings, user_debug
     try: 
         body = await request.body()
         body_str = body.decode()
@@ -734,6 +734,8 @@ async def chat_completion(request: Request, model: Optional[str] = None, user_ap
         return response
     except Exception as e: 
         print(f"\033[1;31mAn error occurred: {e}\n\n Debug this by setting `--debug`, e.g. `litellm --model gpt-3.5-turbo --debug`")
+        if user_debug: 
+            traceback.print_exc()
         error_traceback = traceback.format_exc()
         error_msg = f"{str(e)}\n\n{error_traceback}"
         try: