Merge pull request #2484 from BerriAI/litellm_fix_langfuse_default

[Proxy-High Traffic] Fix using Langfuse in high traffic

litellm/integrations/langfuse.py

@@ -33,6 +33,7 @@ class LangFuseLogger:
             host=self.langfuse_host,
             release=self.langfuse_release,
             debug=self.langfuse_debug,
+            flush_interval=1,  # flush interval in seconds
         )
 
         if os.getenv("UPSTREAM_LANGFUSE_SECRET_KEY") is not None:
@@ -147,8 +148,6 @@ class LangFuseLogger:
                     input,
                     response_obj,
                 )
-
-            self.Langfuse.flush()
             print_verbose(
                 f"Langfuse Layer Logging - final response object: {response_obj}"
             )

litellm/proxy/proxy_load_test/locustfile.py

@@ -8,6 +8,7 @@ class MyUser(HttpUser):
     def chat_completion(self):
         headers = {
             "Content-Type": "application/json",
+            "Authorization": f"Bearer sk-1234",
             # Include any additional headers you may need for authentication, etc.
         }
 

litellm/proxy/proxy_load_test/openai_endpoint.py

@@ -6,6 +6,7 @@ from fastapi import FastAPI, Request, status, HTTPException, Depends
 from fastapi.responses import StreamingResponse
 from fastapi.security import OAuth2PasswordBearer
 from fastapi.middleware.cors import CORSMiddleware
+import uuid
 
 app = FastAPI()
 
@@ -23,7 +24,7 @@ app.add_middleware(
 @app.post("/v1/chat/completions")
 async def completion(request: Request):
     return {
-        "id": "chatcmpl-123",
+        "id": f"chatcmpl-{uuid.uuid4().hex}",
         "object": "chat.completion",
         "created": 1677652288,
         "model": "gpt-3.5-turbo-0125",