Update app.py

app.py

@@ -34,6 +34,7 @@ list_llm = ["mistralai/Mistral-7B-Instruct-v0.2", "mistralai/Mixtral-8x7B-Instru
 ]
 list_llm_simple = [os.path.basename(llm) for llm in list_llm]
 
+
 # Load PDF document and create doc splits
 def load_doc(list_file_path, chunk_size, chunk_overlap):
     # Processing for one document only
@@ -120,7 +121,7 @@ def initialize_llmchain(llm_model, temperature, max_tokens, top_k, vector_db, pr
             top_k = top_k,
         )
     elif llm_model == "microsoft/phi-2":
-        raise gr.Error("phi-2 model requires 'trust_remote_code=True', currently not supported by langchain HuggingFaceHub...")
+        # raise gr.Error("phi-2 model requires 'trust_remote_code=True', currently not supported by langchain HuggingFaceHub...")
         llm = HuggingFaceEndpoint(
             repo_id=llm_model, 
             # model_kwargs={"temperature": temperature, "max_new_tokens": max_tokens, "top_k": top_k, "trust_remote_code": True, "torch_dtype": "auto"}
@@ -267,12 +268,7 @@ def conversation(qa_chain, message, history):
     # return gr.update(value=""), new_history, response_sources[0], response_sources[1] 
     return qa_chain, gr.update(value=""), new_history, response_source1, response_source1_page, response_source2, response_source2_page, response_source3, response_source3_page
     
-def download_csv(chat_history):
-    df = pd.DataFrame(chat_history, columns=['User Message', 'Assistant Response', 'Rating'])
-    df.to_csv('conversation_history.csv', index=False)
-    return 'conversation_history.csv'
 
-    
 def upload_file(file_obj):
     list_file_path = []
     for idx, file in enumerate(file_obj):
@@ -290,16 +286,21 @@ def demo():
         collection_name = gr.State()
         
         gr.Markdown(
-        """<center><h2>PDF-based chatbot (powered by LangChain and open-source LLMs)</center></h2>
-        <h3>Ask any questions about your PDF documents, along with follow-ups</h3>
-        <b>Note:</b> This AI assistant performs retrieval-augmented generation from your PDF documents. \
-        When generating answers, it takes past questions into account (via conversational memory), and includes document references for clarity purposes.</i>
-        <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 an output.<br>
+        """<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 - Document pre-processing"):
+        
+        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):
@@ -310,15 +311,15 @@ def demo():
             with gr.Row():
                 db_progress = gr.Textbox(label="Vector database initialization", value="None")
             with gr.Row():
-                db_btn = gr.Button("Generate vector database...")
+                db_btn = gr.Button("Generate vector database")
             
-        with gr.Tab("Step 2 - QA chain initialization"):
+        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 = 0.0, 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)
                 with gr.Row():
@@ -326,14 +327,10 @@ def demo():
             with gr.Row():
                 llm_progress = gr.Textbox(value="None",label="QA chain initialization")
             with gr.Row():
-                qachain_btn = gr.Button("Initialize question-answering chain...")
+                qachain_btn = gr.Button("Initialize Question Answering chain")
 
-        with gr.Tab("Step 3 - Conversation with chatbot"):
+        with gr.Tab("Step 4 - Chatbot"):
             chatbot = gr.Chatbot(height=300)
-             # Add rating slider
-            with gr.Row():
-                rating_slider = gr.Slider(minimum=1, maximum=5, label="Rate the message:", interactive=True)
-
             with gr.Accordion("Advanced - Document references", open=False):
                 with gr.Row():
                     doc_source1 = gr.Textbox(label="Reference 1", lines=2, container=True, scale=20)
@@ -345,14 +342,11 @@ def demo():
                     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", container=True)
-            with gr.Row():
-                submit_btn = gr.Button("Submit")
-                clear_btn = gr.ClearButton([msg, chatbot])
-                
+                msg = gr.Textbox(placeholder="Type message (e.g. 'What is this document about?')", container=True)
             with gr.Row():
-                download_btn = gr.Button("Download Conversation History as CSV")
-
+                submit_btn = gr.Button("Submit message")
+                clear_btn = gr.ClearButton([msg, chatbot], value="Clear conversation")
+            
         # Preprocessing events
         #upload_btn.upload(upload_file, inputs=[upload_btn], outputs=[document])
         db_btn.click(initialize_database, \
@@ -365,25 +359,21 @@ def demo():
             outputs=[chatbot, doc_source1, source1_page, doc_source2, source2_page, doc_source3, source3_page], \
             queue=False)
 
-        # Conversation events
+        # Chatbot events
         msg.submit(conversation, \
-            inputs=[qa_chain, msg, chatbot, rating_slider], \
+            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, rating_slider], \
+            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)
-
-        # Add download button event
-        download_btn.click(download_csv, inputs=[chatbot], outputs=None)
-        
-    demo.queue().launch(debug=True)
+    demo.queue().launch(debug=True,share=True)
 
 
 if __name__ == "__main__":
-    demo()
+    demo()