Update app.py

app.py

@@ -8,13 +8,27 @@ tokenizer = AutoTokenizer.from_pretrained(model_name)
 model = AutoModelForCausalLM.from_pretrained(model_name)
 
 # Streamlit app
-st.title("Blog Post Generator")
+st.title("Formatted Blog Post Generator")
 
 # User input
-prompt = st.text_area("Enter a blog post topic or starting sentence:")
-max_length = st.slider("Maximum length of generated text:", min_value=50, max_value=500, value=200, step=50)
+topic = st.text_input("Enter a blog post topic:")
+max_length = st.slider("Maximum length of generated text:", min_value=100, max_value=2000, value=500, step=50)
+
+if topic:
+    # Construct a detailed prompt
+    prompt = f"""Write a well-formatted blog post about {topic}. Use the following structure:
+
+1. Start with a main title using a single '#' symbol.
+2. Include an introduction paragraph.
+3. Use '##' for subheadings.
+4. Use bullet points ('-') for lists.
+5. Separate paragraphs with blank lines.
+6. End with a conclusion paragraph.
+
+Here's the blog post:
+
+# """
 
-if prompt:
     # Tokenize input
     input_ids = tokenizer.encode(prompt, return_tensors="pt")
 
@@ -32,5 +46,14 @@ if prompt:
 
     # Decode and display generated text
     generated_text = tokenizer.decode(output[0], skip_special_tokens=True)
+    
     st.subheader("Generated Blog Post:")
-    st.write(generated_text)
+    st.markdown(generated_text)
+
+    # Option to download the blog post
+    st.download_button(
+        label="Download Blog Post",
+        data=generated_text,
+        file_name="generated_blog_post.md",
+        mime="text/markdown"
+    )