Update app.py

app.py

@@ -140,6 +140,28 @@ with gr.Blocks(theme=Monochrome()) as demo:
         """
     )
 
+    with gr.Row():
+        with gr.Column():  
+           with gr.Accordion("What This Demo Does", open = True):
+            gr.Markdown("""
+          This AI Chatbot application uses Retrieval-Augmented Generation (RAG) to provide intelligent responses based on the content of uploaded PDF documents. It allows users to:
+            1. Upload multiple PDF documents
+            2. Process and index the content of these documents
+            3. Ask questions about the content
+            4. Receive AI-generated answers that are grounded in the uploaded documents
+         """)
+        with gr.Column():  
+          with gr.Accordion("How does it work?", open = True):
+            gr.Markdown("""
+          **Question Answering:**
+           - When a user asks a question, the system searches for the most relevant chunks of text from the uploaded documents.
+           - It then uses these relevant chunks as context for a large language model (LLM) to generate an answer.
+           - The LLM (in this case, GPT-4) formulates a response based on the provided context and the user's question.
+          **Pixeltable Integration:**
+           - Pixeltable is used to manage the document data, chunks, and embeddings efficiently.
+           - It provides a declarative interface for complex data operations, making it easier to build and maintain this RAG system.
+          """)
+
     with gr.Row():
         with gr.Column(scale=1):
             pdf_files = gr.File(label="Upload PDF Documents", file_count="multiple")