Update app.py

app.py

@@ -118,17 +118,19 @@ custom_css = """
 with gr.Blocks(css=custom_css,fill_width=True) as demo:
     gr.Markdown("""
     # I’m Shalini ☺️ # 
-    This is a chatbot built on a Retrieval-Augmented Generation (RAG) pipeline for a specific document — the English textbook Kaleidoscope 📚.
-    Ask questions, and the chatbot will retrieve relevant information directly from the selected chapter 📝.
+    This chatbot uses a Retrieval-Augmented Generation (RAG) pipeline.  
+    It is built for the English textbook *Kaleidoscope* 📚.  
+    You can ask questions, and it will retrieve relevant answers from the selected chapter 📝.  
     
     How to use:
     
-    1.Select the chapter from the dropdown menu 📂.
-    2.Type your question in the chat box 💬.
-    3.Receive answers generated using RAG from the document content ⚡.
+    1. Select the chapter from the dropdown menu 📂  
+    2. Type your question in the chat box 💬  
+    3. Receive answers generated using RAG from the document content ⚡  
     
     Powered by LangChain 🛠️, Qdrant 🗄️, and LLaMA 🧠 for fast, accurate, and context-aware responses.
-    """,elem_id="welcome_markdown")
+    """, elem_id="welcome_markdown")
+
     
     chapter_dir={"Broken Images":"Dataset/Drama/Broken_images.pdf", 
                  "Blood":"Dataset/Poems/Blood.pdf",