Update app.py

app.py

@@ -12,8 +12,7 @@ os.environ['PYTORCH_CUDA_ALLOC_CONF'] = 'expandable_segments:True'
 torch.cuda.empty_cache()
 torch.cuda.set_per_process_memory_fraction(0.8)  # Adjust the fraction as needed
 
-app = FastAPI(title="Deploying FastAPI Apps on Huggingface")
-app.add_middleware(CORSMiddleware, allow_origins=['*'], allow_methods=['*'], allow_headers=['*'],)
+app = FastAPI(root_path="/api/v1")
 
 ngrok.set_auth_token("1XtU01EKWysplGQ8fz54lVUQpnQ_3KKhw6YNQ5E85rxdkgXx4e")
 ngrok.kill()
@@ -106,7 +105,7 @@ async def api_home():
 
         
 # Endpoint to start a new conversation thread
-@app.post('/api/start_conversation/')
+@app.post('/start_conversation/')
 async def start_conversation(request: Request):
     data = await request.json()
     prompt = data.get('prompt')
@@ -125,7 +124,7 @@ async def start_conversation(request: Request):
 # Endpoint to get the response of a conversation thread
 
     
-@app.get('/api/get_response/{thread_id}')
+@app.get('/get_response/{thread_id}')
 async def get_response(thread_id: int):
     if thread_id not in conversations:
         raise HTTPException(status_code=404, detail="Thread not found")
@@ -141,7 +140,7 @@ async def get_response(thread_id: int):
 
 
 
-@app.post('/api/chat/')
+@app.post('/chat/')
 async def chat(request: Request):
     data = await request.json()
     prompt = data.get('prompt')