Update app.py

app.py

@@ -1,28 +1,25 @@
 import gradio as gr
-import requests
+from transformers import pipeline
 
-API_URL = "https://api-inference.huggingface.co/models/google/flan-t5-small"
-# You can leave headers empty if model is public
-headers = {}
+# Tiny, CPU-friendly model
+chatbot_pipeline = pipeline("text-generation", model="sshleifer/tiny-gpt2")
 
 def chat(message, history=[]):
-    payload = {"inputs": message}
-    try:
-        response = requests.post(API_URL, headers=headers, json=payload, timeout=30)
-        result = response.json()
-        reply = result[0]['generated_text']
-    except Exception as e:
-        reply = f"⚠️ Error: {str(e)}"
+    result = chatbot_pipeline(message, max_new_tokens=50)
+    reply = result[0]['generated_text'].replace(message, "").strip()
     history.append((message, reply))
     return history, history
 
 with gr.Blocks() as demo:
-    gr.Markdown("## 🤖 Permanent AI Chatbot (CPU-Friendly)")
+    gr.Markdown("## 🤖 Permanent Tiny AI Chatbot")
     chat_ui = gr.Chatbot()
-    msg = gr.Textbox(label="Type your message")
+    msg = gr.Textbox(label="Type your message here")
     clear = gr.Button("Clear Chat")
 
     msg.submit(chat, [msg, chat_ui], [chat_ui, chat_ui])
     clear.click(lambda: None, None, chat_ui, queue=False)
 
 demo.launch()
+
+
+