Update app.py

app.py

@@ -1,28 +1,33 @@
 import streamlit as st
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
-# Load the model and tokenizer (e.g., a GPT model from Hugging Face)
+# Load the model and tokenizer (optimized for caching in Streamlit)
 @st.cache_resource
 def load_model():
-    model_name = "microsoft/DialoGPT-small"  # Replace with your chosen model
+    model_name = "microsoft/DialoGPT-small"  # A conversational model from Hugging Face
     tokenizer = AutoTokenizer.from_pretrained(model_name)
     model = AutoModelForCausalLM.from_pretrained(model_name)
     return tokenizer, model
 
-# Initialize model and tokenizer
+# Load model and tokenizer
 tokenizer, model = load_model()
 
-# Streamlit app layout
-st.title("🤖 Friendly Chatbot")
-st.write("Hi! I'm your friendly chatbot. Ask me anything or just say hello! 😊")
+# Streamlit App Layout
+st.title("🤖 Friendly English Chatbot")
+st.subheader("Hi! I'm here to chat with you. Feel free to ask me anything or just say hello! 😊")
 
 # User input
-user_input = st.text_input("You:", placeholder="Type your message here...")
+user_input = st.text_input("Your Message:", placeholder="Type your message here...")
 
-# Generate response
 if user_input:
+    # Encode the user's input and generate a response
     inputs = tokenizer.encode(user_input + tokenizer.eos_token, return_tensors="pt")
-    response = model.generate(inputs, max_length=50, num_return_sequences=1, pad_token_id=tokenizer.eos_token_id)
-    bot_reply = tokenizer.decode(response[0], skip_special_tokens=True)
-    st.text_area("Chatbot:", value=bot_reply, height=100)
+    response = model.generate(inputs, max_length=100, num_return_sequences=1, pad_token_id=tokenizer.eos_token_id)
+    chatbot_reply = tokenizer.decode(response[0], skip_special_tokens=True)
+    
+    # Display the chatbot's response
+    st.text_area("Chatbot Reply:", value=chatbot_reply, height=150)
 
+# Footer
+st.markdown("---")
+st.caption("Powered by Hugging Face and Streamlit")