..

app.py

@@ -385,25 +385,21 @@ def upload_file(file_obj):
     # initialize_database(file_path, progress)
     return list_file_path
 
+####################################
 
-
-
-
-
-###################################
 def demo():
     with gr.Blocks(theme="base") as demo:
         vector_db = gr.State()
         qa_chain = gr.State()
         collection_name = gr.State()
-        history = gr.State()
+        history = gr.State([])  # Initialize history as an empty list
         
         gr.Markdown(
         """<center><h2>PDF-based chatbot</center></h2>
         <h3>Ask any questions about your PDF documents</h3>""")
         gr.Markdown(
         """<b>Note:</b> This AI assistant, using Langchain and open-source LLMs, performs retrieval-augmented generation (RAG) from your PDF documents. \
-        The user interface explicitely shows multiple steps to help understand the RAG workflow. 
+        The user interface explicitly shows multiple steps to help understand the RAG workflow. 
         This chatbot takes past questions into account when generating answers (via conversational memory), and includes document references for clarity purposes.<br>
         <br><b>Warning:</b> This space uses the free CPU Basic hardware from Hugging Face. Some steps and LLM models used below (free inference endpoints) can take some time to generate a reply.
         """)
@@ -411,16 +407,15 @@ def demo():
         with gr.Tab("Step 1 - Upload PDF"):
             with gr.Row():
                 document = gr.Files(height=100, file_count="multiple", file_types=["pdf"], interactive=True, label="Upload your PDF documents (single or multiple)")
-                # upload_btn = gr.UploadButton("Loading document...", height=100, file_count="multiple", file_types=["pdf"], scale=1)
         
         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")
+                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="Chunk size", interactive=True)
+                    slider_chunk_size = gr.Slider(minimum=100, maximum=1000, value=600, step=20, label="Chunk size", info="Chunk size", interactive=True)
                 with gr.Row():
-                    slider_chunk_overlap = gr.Slider(minimum = 10, maximum = 200, value=40, step=10, label="Chunk overlap", info="Chunk overlap", interactive=True)
+                    slider_chunk_overlap = gr.Slider(minimum=10, maximum=200, value=40, step=10, label="Chunk overlap", info="Chunk overlap", interactive=True)
             with gr.Row():
                 db_progress = gr.Textbox(label="Vector database initialization", value="None")
             with gr.Row():
@@ -428,17 +423,16 @@ def demo():
             
         with gr.Tab("Step 3 - Initialize QA chain"):
             with gr.Row():
-                llm_btn = gr.Radio(list_llm_simple, \
-                    label="LLM models", value = list_llm_simple[0], type="index", info="Choose your LLM model")
+                llm_btn = gr.Radio(list_llm_simple, label="LLM models", value=list_llm_simple[0], type="index", info="Choose your LLM model")
             with gr.Accordion("Advanced options - LLM model", open=False):
                 with gr.Row():
-                    slider_temperature = gr.Slider(minimum = 0.01, maximum = 1.0, value=0.7, step=0.1, label="Temperature", info="Model temperature", interactive=True)
+                    slider_temperature = gr.Slider(minimum=0.01, maximum=1.0, value=0.7, step=0.1, label="Temperature", info="Model temperature", interactive=True)
                 with gr.Row():
-                    slider_maxtokens = gr.Slider(minimum = 224, maximum = 4096, value=1024, step=32, label="Max Tokens", info="Model max tokens", interactive=True)
+                    slider_maxtokens = gr.Slider(minimum=224, maximum=4096, value=1024, step=32, label="Max Tokens", info="Model max tokens", interactive=True)
                 with gr.Row():
-                    slider_topk = gr.Slider(minimum = 1, maximum = 10, value=3, step=1, label="top-k samples", info="Model top-k samples", interactive=True)
+                    slider_topk = gr.Slider(minimum=1, maximum=10, value=3, step=1, label="top-k samples", info="Model top-k samples", interactive=True)
             with gr.Row():
-                llm_progress = gr.Textbox(value="None",label="QA chain initialization")
+                llm_progress = gr.Textbox(value="None", label="QA chain initialization")
             with gr.Row():
                 qachain_btn = gr.Button("Initialize Question Answering chain")
 
@@ -462,42 +456,151 @@ def demo():
             with gr.Row("Metrics"):
                 metrics_output = gr.Textbox(lines=10, label="Evaluation Metrics")
 
-            
         # Preprocessing events
-        #upload_btn.upload(upload_file, inputs=[upload_btn], outputs=[document])
-        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)
+        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(interact, inputs=[gr.State(),qa_chain, msg, history], outputs=[
-        gr.State(), chatbot, history, response_source1, response_source1_page,
-        response_source2, response_source2_page, response_source3, response_source3_page,
-        None, None, None, metrics_output
-    ],queue=False)
+        msg.submit(interact, inputs=[qa_chain, msg, history], outputs=[
+            qa_chain, chatbot, history, doc_source1, source1_page,
+            doc_source2, source2_page, doc_source3, source3_page,
+            metrics_output
+        ])
 
+        submit_btn.click(interact, 
+                         inputs=[qa_chain, msg, history], 
+                         outputs=[qa_chain, chatbot, history, doc_source1, source1_page, doc_source2, source2_page, doc_source3, source3_page, metrics_output])
 
-        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)
+        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()
+
+
+
+
+
+###################################
+# def demo():
+#     with gr.Blocks(theme="base") as demo:
+#         vector_db = gr.State()
+#         qa_chain = gr.State()
+#         collection_name = gr.State()
+#         history = gr.State()
         
+#         gr.Markdown(
+#         """<center><h2>PDF-based chatbot</center></h2>
+#         <h3>Ask any questions about your PDF documents</h3>""")
+#         gr.Markdown(
+#         """<b>Note:</b> This AI assistant, using Langchain and open-source LLMs, performs retrieval-augmented generation (RAG) from your PDF documents. \
+#         The user interface explicitely shows multiple steps to help understand the RAG workflow. 
+#         This chatbot takes past questions into account when generating answers (via conversational memory), and includes document references for clarity purposes.<br>
+#         <br><b>Warning:</b> This space uses the free CPU Basic hardware from Hugging Face. Some steps and LLM models used below (free inference endpoints) can take some time to generate a reply.
+#         """)
+        
+#         with gr.Tab("Step 1 - Upload PDF"):
+#             with gr.Row():
+#                 document = gr.Files(height=100, file_count="multiple", file_types=["pdf"], interactive=True, label="Upload your PDF documents (single or multiple)")
+#                 # upload_btn = gr.UploadButton("Loading document...", height=100, file_count="multiple", file_types=["pdf"], scale=1)
+        
+#         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="Chunk size", interactive=True)
+        #         with gr.Row():
+        #             slider_chunk_overlap = gr.Slider(minimum = 10, maximum = 200, value=40, step=10, label="Chunk overlap", info="Chunk overlap", interactive=True)
+        #     with gr.Row():
+        #         db_progress = gr.Textbox(label="Vector database initialization", value="None")
+        #     with gr.Row():
+        #         db_btn = gr.Button("Generate vector database")
+            
+        # with gr.Tab("Step 3 - Initialize QA chain"):
+        #     with gr.Row():
+        #         llm_btn = gr.Radio(list_llm_simple, \
+        #             label="LLM models", value = list_llm_simple[0], type="index", info="Choose your LLM model")
+        #     with gr.Accordion("Advanced options - LLM model", open=False):
+        #         with gr.Row():
+        #             slider_temperature = gr.Slider(minimum = 0.01, maximum = 1.0, value=0.7, step=0.1, label="Temperature", info="Model temperature", interactive=True)
+        #         with gr.Row():
+        #             slider_maxtokens = gr.Slider(minimum = 224, maximum = 4096, value=1024, step=32, label="Max Tokens", info="Model max tokens", interactive=True)
+        #         with gr.Row():
+        #             slider_topk = gr.Slider(minimum = 1, maximum = 10, value=3, step=1, label="top-k samples", info="Model top-k samples", interactive=True)
+        #     with gr.Row():
+        #         llm_progress = gr.Textbox(value="None",label="QA chain initialization")
+        #     with gr.Row():
+        #         qachain_btn = gr.Button("Initialize Question Answering chain")
+
+        # with gr.Tab("Step 4 - Chatbot"):
+        #     chatbot = gr.Chatbot(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)
+        #         with gr.Row():
+        #             doc_source2 = gr.Textbox(label="Reference 2", lines=2, container=True, scale=20)
+        #             source2_page = gr.Number(label="Page", scale=1)
+        #         with gr.Row():
+        #             doc_source3 = gr.Textbox(label="Reference 3", lines=2, container=True, scale=20)
+        #             source3_page = gr.Number(label="Page", scale=1)
+        #     with gr.Row():
+        #         msg = gr.Textbox(placeholder="Type message (e.g. 'What is this document about?')", container=True)
+        #     with gr.Row():
+        #         submit_btn = gr.Button("Submit message")
+        #         clear_btn = gr.ClearButton([msg, chatbot], value="Clear conversation")
+        #     with gr.Row("Metrics"):
+        #         metrics_output = gr.Textbox(lines=10, label="Evaluation Metrics")
 
+            
+        # # Preprocessing events
+        # #upload_btn.upload(upload_file, inputs=[upload_btn], outputs=[document])
+        # 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)
 
-    demo.queue().launch(debug=True)
+        # Chatbot events
+    #     msg.submit(interact, inputs=[gr.State(),qa_chain, msg, history], outputs=[
+    #     gr.State(), chatbot, history, response_source1, response_source1_page,
+    #     response_source2, response_source2_page, response_source3, response_source3_page,
+    #     None, None, None, metrics_output
+    # ],queue=False)
 
 
-if __name__ == "__main__":
-    demo()
+    #     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()