Update app.py

app.py

@@ -1,16 +1,31 @@
 import gradio as gr
+import requests
 from llama_cpp import Llama
 
-# Load the model directly from Hugging Face’s cloud
+# Define model URL & local path
 MODEL_URL = "https://huggingface.co/TheBloke/Llama-2-7B-GGML/resolve/main/llama-7B.ggmlv3.q4_0.bin"
+MODEL_PATH = "/home/user/app/llama-7B.ggmlv3.q4_0.bin"  # Local storage path
 
-# Define OmniAI's chat function (handles two arguments: user message + history)
+# Function to download model if not present
+def download_model():
+    if not os.path.exists(MODEL_PATH):
+        print("Downloading model...")
+        response = requests.get(MODEL_URL, stream=True)
+        with open(MODEL_PATH, "wb") as f:
+            for chunk in response.iter_content(chunk_size=8192):
+                f.write(chunk)
+        print("Model downloaded successfully!")
+
+# Download model before launching OmniAI
+download_model()
+
+# Define OmniAI's chat function
 def omni_ai_chat(user_message, history):
-    llm = Llama(model_path=MODEL_URL)  # Load model dynamically
-    response = llm(user_message)  # Process only the latest prompt
+    llm = Llama(model_path=MODEL_PATH)  # Load locally downloaded model
+    response = llm(user_message)
     return response["choices"][0]["text"].strip()
 
-# Set up Gradio chatbot UI with correct formatting
+# Set up Gradio chatbot UI
 chatbot = gr.ChatInterface(fn=omni_ai_chat, title="OmniAI - Cloud AI",
                            description="Your personal AI assistant, running entirely in the cloud!",
                            type="messages")  # Fixes deprecated format warning