Update app.py

app.py

@@ -2,7 +2,6 @@ import os
 import gradio as gr
 from huggingface_hub import InferenceClient
 
-
 # Configuration
 MODEL_NAME = "EleutherAI/gpt-neo-125M"  # A relatively small model
 HF_API_TOKEN = os.environ.get("HF_API_TOKEN", "")  # Your Hugging Face API token
@@ -23,6 +22,33 @@ if HF_API_TOKEN:
 else:
     print("Warning: HF_API_TOKEN not set. Using limited functionality.")
 
+def generate_response(user_input):
+    """Generate a response from the model based on user input"""
+    if not user_input.strip():
+        return "Please enter a message to get a response from NORTHERN_AI."
+    
+    prompt = f"{SYSTEM_PROMPT}\n\nUser: {user_input}\nNORTHERN_AI:"
+    
+    try:
+        if client:
+            # Use Hugging Face's Inference API
+            response = client.text_generation(
+                prompt,
+                model=MODEL_NAME,
+                max_new_tokens=150,
+                temperature=0.7,
+                top_p=0.95,
+                repetition_penalty=1.1
+            )
+            # Extract just the assistant's response
+            result = response.split("NORTHERN_AI:")[-1].strip()
+            return result
+        else:
+            return "AI service is currently unavailable. Please check your API token configuration."
+    except Exception as e:
+        print(f"Error generating response: {e}")
+        return f"Sorry, I encountered an error while generating a response. Please try again later."
+
 # For demonstration purposes, we'll use a simpler model approach
 # that doesn't require an API key but still provides responses
 def get_ai_response(message):