Update app.py

app.py

@@ -1,28 +1,44 @@
+import os
 import gradio as gr
 from llama_cpp import Llama
+import requests
 
-# Load the model (Ensure the GGUF file is in the same directory)
-model = Llama(model_path="./phi-2.Q4_K_M.gguf")  # Update path if needed
-try:
-    model = Llama(model_path=model_path)  # Load the quantized model
-except ValueError as e:
-    print(f"Error loading model: {e}")
-    exit()
+# Define model details
+MODEL_DIR = "/home/user/app/models/"
+MODEL_PATH = MODEL_DIR + "phi-2.Q4_K_M.gguf"
+MODEL_URL = "https://huggingface.co/TheBloke/Phi-2-GGUF/resolve/main/phi-2.Q4_K_M.gguf"
 
-# Function to process user queries
-def solve_problem(prompt):
-    output = model(prompt, max_tokens=512)
+# Ensure the model directory exists
+os.makedirs(MODEL_DIR, exist_ok=True)
+
+# Download the model if not available
+if not os.path.exists(MODEL_PATH):
+    print("Model not found! Downloading...")
+    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("Download complete!")
+
+# Load the model
+print("Loading model...")
+model = Llama(model_path=MODEL_PATH)
+print("Model loaded successfully!")
+
+# Define function for Gradio interface
+def chat_with_model(prompt):
+    output = model(prompt, max_tokens=256)
     return output["choices"][0]["text"]
 
-# Set up Gradio UI
+# Create Gradio interface
 iface = gr.Interface(
-    fn=solve_problem,
-    inputs="text",
+    fn=chat_with_model,
+    inputs=gr.Textbox(lines=2, placeholder="Ask your question here..."),
     outputs="text",
-    title="Phi-2 AI Solver",
-    description="Ask me any JEE/NEET-level questions!",
+    title="Phi-2 AI Assistant",
+    description="Ask anything and get detailed responses!",
 )
 
-# Launch the app
+# Launch the interface
 if __name__ == "__main__":
     iface.launch()