Update app.py

app.py

@@ -1,6 +1,4 @@
-from llama_cpp.server.app import create_app, Settings
-from fastapi.responses import HTMLResponse
-import os
+import subprocess
 import requests
 from llama_cpp import Llama
 import gradio as gr
@@ -10,16 +8,6 @@ response = requests.get(url)
 with open("./model.gguf", mode="wb") as file:
   file.write(response.content)
 
-app = create_app(
-    Settings(
-        n_threads=2,  # set to number of cpu cores
-        model="./model.gguf",
-        embedding=False
-    )
-)
-
-print(app)
-
 llm = Llama(model_path="./model.gguf")
 def response(input_text, history):
     output = llm(f"Q: {input_text} A:", max_tokens=256, stop=["Q:", "\n"], echo=True)
@@ -27,3 +15,7 @@ def response(input_text, history):
 
 gr.ChatInterface(response).queue().launch(share=True) #False, server_name="0.0.0.0", server_port=7864)
 
+command = ["python3", "-m", "llama_cpp.server", "--model", "./model.gguf", "--host", "0.0.0.0", "--port", "2600"]
+subprocess.Popen(command)
+
+print("Hello world")