Update app.py

app.py

@@ -278,77 +278,97 @@ def upload_file(file_obj):
     return list_file_path
 
 
+import gradio as gr
+
 def demo():
     with gr.Blocks(theme="base") as demo:
         vector_db = gr.State()
         qa_chain = gr.State()
         collection_name = gr.State()
         
-        # Update the introduction with BookMyDarshan branding
         gr.Markdown(
-        """<center><h2>BookMyDarshan: Your Personalized Spiritual Assistant</h2></center>
-        <h3>Explore Sacred Texts and Enhance Your Spiritual Journey</h3>""")
-        
+            """<center><h2>PDF-based Chatbot</h2></center>
+            <h3>Ask any questions about your PDF documents</h3>"""
+        )
         gr.Markdown(
-        """<b>About BookMyDarshan.in:</b> We are a Hyderabad-based startup dedicated to providing pilgrims with exceptional temple darshan experiences. 
-        Our platform offers a comprehensive suite of spiritual and religious services, customized to meet your devotional needs.<br><br>
-        <b>Note:</b> This spiritual assistant uses state-of-the-art AI to help you explore and understand your uploaded spiritual documents. 
-        With a blend of technology and tradition, this tool assists in connecting you more deeply with your faith.<br>""")
-        
-        with gr.Tab("Step 1 - Upload Your Spiritual Texts"):
-            with gr.Row():
-                document = gr.Files(height=100, file_count="multiple", file_types=["pdf"], interactive=True, label="Upload your spiritual PDFs (e.g., scriptures, pilgrim guides)")
+            """<b>Note:</b> This AI assistant uses LangChain and open-source LLMs for retrieval-augmented generation (RAG) from your PDF documents. 
+            The UI shows multiple steps to help you understand the RAG workflow. This chatbot considers past questions when generating answers (via conversational memory) 
+            and includes document references for clarity.<br>
+            <br><b>Warning:</b> This demo uses free CPU Basic hardware from Hugging Face, so some steps may take time."""
+        )
 
-        with gr.Tab("Step 2 - Process Document"):
-            with gr.Row():
-                db_btn = gr.Radio(["ChromaDB"], label="Vector database type", value="ChromaDB", type="index", info="Choose your vector database")
-            with gr.Accordion("Advanced options - Document text splitter", open=False):
-                with gr.Row():
-                    slider_chunk_size = gr.Slider(minimum=100, maximum=1000, value=600, step=20, label="Chunk size", info="Size of text chunks to process", interactive=True)
-                with gr.Row():
-                    slider_chunk_overlap = gr.Slider(minimum=10, maximum=200, value=40, step=10, label="Chunk overlap", info="Overlap between text chunks", interactive=True)
-            with gr.Row():
-                db_progress = gr.Textbox(label="Database initialization status", value="None")
-            with gr.Row():
-                db_btn = gr.Button("Generate Spiritual Knowledge Database")
+        with gr.Tab("Step 1: Upload PDF"):
+            document = gr.Files(label="Upload your PDF documents", file_count="multiple", file_types=["pdf"], interactive=True)
 
-        with gr.Tab("Step 3 - Set Up Your Assistant"):
-            with gr.Row():
-                llm_btn = gr.Radio(list_llm_simple, \
-                    label="LLM models", value=list_llm_simple[0], type="index", info="Choose an AI model to assist your queries")
-            with gr.Accordion("Advanced options - AI model settings", open=False):
-                with gr.Row():
-                    slider_temperature = gr.Slider(minimum=0.01, maximum=1.0, value=0.7, step=0.1, label="Response Creativity", info="Controls the creativity of the model", interactive=True)
-                with gr.Row():
-                    slider_maxtokens = gr.Slider(minimum=224, maximum=4096, value=1024, step=32, label="Max Tokens", info="Maximum response length", interactive=True)
-                with gr.Row():
-                    slider_topk = gr.Slider(minimum=1, maximum=10, value=3, step=1, label="Top-k Responses", info="Number of alternative answers generated", interactive=True)
-            with gr.Row():
-                llm_progress = gr.Textbox(value="None", label="Assistant Initialization Status")
-            with gr.Row():
-                qachain_btn = gr.Button("Initialize Your Spiritual Assistant")
+        with gr.Tab("Step 2: Process Document"):
+            db_btn = gr.Radio(["ChromaDB"], label="Select Vector Database", value="ChromaDB", info="Choose your vector database")
+            with gr.Accordion("Advanced Options: Text Splitter", open=False):
+                slider_chunk_size = gr.Slider(minimum=100, maximum=1000, value=600, step=20, label="Chunk Size", info="Adjust chunk size for text splitting")
+                slider_chunk_overlap = gr.Slider(minimum=10, maximum=200, value=40, step=10, label="Chunk Overlap", info="Adjust overlap between chunks")
+            db_progress = gr.Textbox(label="Vector Database Initialization Status", value="None", interactive=False)
+            generate_db_btn = gr.Button("Generate Vector Database")
+
+        with gr.Tab("Step 3: Initialize QA Chain"):
+            llm_btn = gr.Radio(["LLM Model 1", "LLM Model 2"], label="Select LLM Model", value="LLM Model 1", info="Choose the LLM model")
+            with gr.Accordion("Advanced Options: LLM Model", open=False):
+                slider_temperature = gr.Slider(minimum=0.01, maximum=1.0, value=0.7, step=0.1, label="Temperature", info="Adjust the model's creativity level")
+                slider_maxtokens = gr.Slider(minimum=224, maximum=4096, value=1024, step=32, label="Max Tokens", info="Set the maximum number of tokens")
+                slider_topk = gr.Slider(minimum=1, maximum=10, value=3, step=1, label="Top-K Samples", info="Select the number of top-k samples")
+            llm_progress = gr.Textbox(label="QA Chain Initialization Status", value="None", interactive=False)
+            qachain_btn = gr.Button("Initialize QA Chain")
 
-        with gr.Tab("Step 4 - Engage with the Assistant"):
-            chatbot = gr.Chatbot(height=300)
-            with gr.Accordion("Advanced - Document References", open=False):
+        with gr.Tab("Step 4: Chatbot"):
+            chatbot = gr.Chatbot(label="Chat with your PDF", height=300)
+            with gr.Accordion("Advanced: Document References", open=False):
                 with gr.Row():
-                    doc_source1 = gr.Textbox(label="Reference 1", lines=2, container=True, scale=20)
-                    source1_page = gr.Number(label="Page", scale=1)
+                    doc_source1 = gr.Textbox(label="Reference 1", lines=2)
+                    source1_page = gr.Number(label="Page", interactive=True)
                 with gr.Row():
-                    doc_source2 = gr.Textbox(label="Reference 2", lines=2, container=True, scale=20)
-                    source2_page = gr.Number(label="Page", scale=1)
+                    doc_source2 = gr.Textbox(label="Reference 2", lines=2)
+                    source2_page = gr.Number(label="Page", interactive=True)
                 with gr.Row():
-                    doc_source3 = gr.Textbox(label="Reference 3", lines=2, container=True, scale=20)
-                    source3_page = gr.Number(label="Page", scale=1)
+                    doc_source3 = gr.Textbox(label="Reference 3", lines=2)
+                    source3_page = gr.Number(label="Page", interactive=True)
+            msg = gr.Textbox(placeholder="Type your question here...", label="Ask a Question", container=True)
             with gr.Row():
-                msg = gr.Textbox(placeholder="Type your query (e.g., 'What is this scripture about?')", container=True)
-            with gr.Row():
-                submit_btn = gr.Button("Submit Query")
-                clear_btn = gr.ClearButton([msg, chatbot], value="Clear Conversation")
-            
-        # (Event handling and logic connections remain the same)
-        
+                submit_btn = gr.Button("Submit")
+                clear_btn = gr.Button("Clear Conversation")
+
+        # Preprocessing events
+        generate_db_btn.click(initialize_database, inputs=[document, slider_chunk_size, slider_chunk_overlap], outputs=[vector_db, collection_name, db_progress])
+        qachain_btn.click(
+            initialize_LLM, 
+            inputs=[llm_btn, slider_temperature, slider_maxtokens, slider_topk, vector_db], 
+            outputs=[qa_chain, llm_progress]
+        ).then(
+            lambda: [None, "", 0, "", 0, "", 0],
+            inputs=None,
+            outputs=[chatbot, doc_source1, source1_page, doc_source2, source2_page, doc_source3, source3_page],
+            queue=False
+        )
+
+        # Chatbot events
+        msg.submit(
+            conversation,
+            inputs=[qa_chain, msg, chatbot],
+            outputs=[qa_chain, msg, chatbot, doc_source1, source1_page, doc_source2, source2_page, doc_source3, source3_page],
+            queue=False
+        )
+        submit_btn.click(
+            conversation,
+            inputs=[qa_chain, msg, chatbot],
+            outputs=[qa_chain, msg, chatbot, doc_source1, source1_page, doc_source2, source2_page, doc_source3, source3_page],
+            queue=False
+        )
+        clear_btn.click(
+            lambda: [None, "", 0, "", 0, "", 0],
+            inputs=None,
+            outputs=[chatbot, doc_source1, source1_page, doc_source2, source2_page, doc_source3, source3_page],
+            queue=False
+        )
     demo.queue().launch(debug=True)
 
+
 if __name__ == "__main__":
     demo()
+