(chore) update load test

litellm/proxy/proxy_config.yaml

@@ -57,12 +57,13 @@ model_list:
       mode: embedding
 litellm_settings:
   fallbacks: [{"openai-gpt-3.5": ["azure-gpt-3.5"]}]
+  success_callback: ['langfuse']
   # cache: True     
   # setting callback class
   # callbacks: custom_callbacks.proxy_handler_instance # sets litellm.callbacks = [proxy_handler_instance]
 
-general_settings: 
-  master_key: sk-1234
+# general_settings: 
+#   master_key: sk-1234
   # database_type: "dynamo_db" 
   # database_args: { # 👈  all args - https://github.com/BerriAI/litellm/blob/befbcbb7ac8f59835ce47415c128decf37aac328/litellm/proxy/_types.py#L190
   #   "billing_mode": "PAY_PER_REQUEST", 

litellm/proxy/tests/load_test_completion.py

@@ -11,12 +11,10 @@ async def litellm_completion():
     # Your existing code for litellm_completion goes here
     try:
         response = await litellm_client.chat.completions.create(
-            model="Azure OpenAI GPT-4 Canada-East (External)",
-            stream=True,
+            model="azure-gpt-3.5",
             messages=[{"role": "user", "content": f"This is a test: {uuid.uuid4()}"}],
         )
-        async for chunk in response:
-            print(chunk)
+        print(response)
         return response
 
     except Exception as e:
@@ -27,9 +25,9 @@ async def litellm_completion():
 
 
 async def main():
-    for i in range(1000000):
+    for i in range(150):
         start = time.time()
-        n = 1000  # Number of concurrent tasks
+        n = 150  # Number of concurrent tasks
         tasks = [litellm_completion() for _ in range(n)]
 
         chat_completions = await asyncio.gather(*tasks)