setted the n_threads

main.py

@@ -1,4 +1,5 @@
 from fastapi import FastAPI, HTTPException
+from fastapi.middleware.cors import CORSMiddleware
 from models import SQLContext
 from llama_cpp import Llama
 import logging
@@ -6,12 +7,18 @@ import logging
 llm = Llama(
     model_path="./quantized_model/sql_gpt_quantized.gguf", 
     n_ctx=512,
-    n_threads=1,
+    n_threads=4
     n_gpu_layers=-1
 )
 
 app = FastAPI()
-
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=["*"],  # Allow your frontend origin
+    allow_credentials=True,
+    allow_methods=["*"],  # Allow all methods
+    allow_headers=["*"],  # Allow all headers
+)
 @app.get("/")
 def root():
     return {"Hello": "World"}