Update app.py

app.py

@@ -1,21 +1,13 @@
 import os
 import threading
-import subprocess
 import gradio as gr
 from llama_index.llms.ollama import Ollama
 from llama_index.core.llms import ChatMessage
 
-# Fonction pour démarrer le serveur Ollama
-def start_ollama():
-    os.environ['OLLAMA_HOST'] = '127.0.0.1:11434'
-    os.environ['OLLAMA_ORIGINS'] = '*'
-    subprocess.run(["ollama", "serve"])
+# Configurer le proxy Ollama
+os.environ['OLLAMA_HOST'] = '127.0.0.1:11434'
+os.environ['OLLAMA_ORIGINS'] = '*'
 
-# Démarrer le serveur Ollama dans un thread séparé
-ollama_thread = threading.Thread(target=start_ollama)
-ollama_thread.start()
-
-# Initialiser le modèle Ollama
 llm = Ollama(model="llama3", request_timeout=120.0)
 
 def get_completion(prompt):
@@ -50,4 +42,4 @@ chat_interface = gr.Interface(fn=generate_chat_response, inputs=chat_input, outp
 app = gr.TabbedInterface([single_interface, chat_interface], ["Single Completion", "Chat"])
 
 if __name__ == "__main__":
-    app.launch(server_name="0.0.0.0", server_port=7860)
+    app.launch(server_name="0.0.0.0", server_port=7860, share=True)