Update app/llm.py

app/llm.py

@@ -8,6 +8,7 @@ import llama_cpp
 import llama_cpp.llama_tokenizer
 from pydantic import BaseModel
 from fastapi import APIRouter
+from users import current_active_user
 
 class GenModel(BaseModel):
     question: str
@@ -71,7 +72,7 @@ def health():
     
 # Chat Completion API
 @llm_router.post("/chat/", tags=["llm"])
-async def chat(chatm:ChatModel):
+async def chat(chatm:ChatModel, user: User = Depends(current_active_user)):
     try:
         st = time()
         output = llm_chat.create_chat_completion(
@@ -94,7 +95,7 @@ async def chat(chatm:ChatModel):
 
 # Chat Completion API
 @llm_router.post("/generate", tags=["llm"])
-async def generate(gen:GenModel):
+async def generate(gen:GenModel, user: User = Depends(current_active_user)):
     gen.system = "You are an helpful medical AI assistant."
     gen.temperature = 0.5
     gen.seed = 42