Update app/llm.py

app/llm.py

@@ -11,6 +11,13 @@ from pydantic import BaseModel
 from fastapi import APIRouter
 from app.users import current_active_user
 
+
+from transformers import AutoModelForCausalLM
+
+model = AutoModelForCausalLM.from_pretrained("bigcode/starcoder")
+model.to_bettertransformer()
+
+
 class GenModel(BaseModel):
     question: str
     system: str = "You are a helpful medical AI chat assistant. Help as much as you can.Also continuously ask for possible symptoms in order to atat a conclusive ailment or sickness and possible solutions.Remember, response in English."
@@ -37,6 +44,7 @@ llm_chat = llama_cpp.Llama.from_pretrained(
      n_gpu_layers=0,
     #chat_format="llama-2"
 )
+
 llm_generate = llama_cpp.Llama.from_pretrained(
     repo_id="Qwen/Qwen1.5-0.5B-Chat-GGUF",
     filename="*q4_0.gguf",
@@ -74,6 +82,8 @@ def health():
 # Chat Completion API
 @llm_router.post("/chat/", tags=["llm"])
 async def chat(chatm:ChatModel):#, user: schemas.BaseUser = fastapi.Depends(current_active_user)):
+    
+    """
     #chatm.system = chatm.system.format("")#user.email)
     try:
         st = time()
@@ -95,7 +105,8 @@ async def chat(chatm:ChatModel):#, user: schemas.BaseUser = fastapi.Depends(curr
         return JSONResponse(
             status_code=500, content={"message": "Internal Server Error"}
         )
-
+    """
+    
 # Chat Completion API
 @llm_router.post("/generate", tags=["llm"])
 async def generate(gen:GenModel):#, user: schemas.BaseUser = fastapi.Depends(current_active_user)):