Update app.py

app.py

@@ -1,26 +1,30 @@
-# Load the GPT-2 model and tokenizer
 import os
 os.system('pip install streamlit transformers torch')
+
 import streamlit as st
 from transformers import GPT2LMHeadModel, GPT2Tokenizer
 import torch
 
-
+# Load the GPT-2 model and tokenizer
 model_name = 'gpt2-large'
 tokenizer = GPT2Tokenizer.from_pretrained(model_name)
 model = GPT2LMHeadModel.from_pretrained(model_name)
 
 def generate_blog_post(topic):
-    # Encode the input topic
-    inputs = tokenizer.encode(topic, return_tensors='pt')
+    try:
+        # Encode the input topic
+        inputs = tokenizer.encode(topic, return_tensors='pt')
 
-    # Generate the blog post
-    outputs = model.generate(inputs, max_length=500, num_return_sequences=1, no_repeat_ngram_size=2, 
-                             do_sample=True, top_k=50, top_p=0.95, temperature=0.9)
+        # Generate the blog post
+        outputs = model.generate(inputs, max_length=500, num_return_sequences=1, no_repeat_ngram_size=2, 
+                                 do_sample=True, top_k=50, top_p=0.95, temperature=0.9)
 
-    # Decode the generated text
-    blog_post = tokenizer.decode(outputs[0], skip_special_tokens=True)
-    return blog_post
+        # Decode the generated text
+        blog_post = tokenizer.decode(outputs[0], skip_special_tokens=True)
+        return blog_post
+    except Exception as e:
+        st.error(f"Error: {e}")
+        return ""
 
 # Streamlit app
 st.title("Blog Post Generator")
@@ -29,5 +33,6 @@ st.write("Enter a topic to generate a blog post.")
 topic = st.text_input("Topic:")
 
 if st.button("Generate"):
-    blog_post = generate_blog_post(topic)
+    with st.spinner('Generating...'):
+        blog_post = generate_blog_post(topic)
     st.write(blog_post)