Code Updated

app.py

@@ -76,8 +76,7 @@ async def lifespan(app: FastAPI):
         api_key=Config.QDRANT_API_KEY
     )
     
-    # Initialize embedding service
-    embedding_service = None
+    embedding_service = EmbeddingService()  # Initialize here
     
     # Verify connections
     try:
@@ -299,7 +298,7 @@ async def chat_completions(request: ChatCompletionRequest):
         if request.stream:
             return StreamingResponse(
                 stream_chat_completion(groq_messages, request),
-                media_type="text/plain"
+                media_type="text/event-stream"
             )
         else:
             return await create_chat_completion(groq_messages, request)