Update app.py

app.py

@@ -13,6 +13,10 @@ from langchain_community.llms import HuggingFaceEndpoint
 list_llm = ["meta-llama/Meta-Llama-3-8B-Instruct", "mistralai/Mistral-7B-Instruct-v0.2"]  
 list_llm_simple = [os.path.basename(llm) for llm in list_llm]
 
+# Simulated user credentials (replace with a secure method in production)
+VALID_USERNAME = "admin"
+VALID_PASSWORD = "password123"
+
 # Load and split PDF document
 def load_doc(list_file_path):
     loaders = [PyPDFLoader(x) for x in list_file_path]
@@ -45,8 +49,8 @@ def initialize_llmchain(llm_model, temperature, max_tokens, top_k, vector_db, pr
             temperature=temperature,
             max_new_tokens=max_tokens,
             top_k=top_k,
-            timeout=120,  # Aumentado para 120 segundos
-            max_retries=3  # Tenta até 3 vezes
+            timeout=120,
+            max_retries=3
         )
     else:
         llm = HuggingFaceEndpoint(
@@ -85,8 +89,6 @@ def format_chat_history(message, chat_history):
 
 def conversation(qa_chain, message, history, language):
     formatted_chat_history = format_chat_history(message, history)
-    
-    # Ajustar o prompt com instrução de idioma
     if language == "Português":
         prompt = f"Responda em português: {message}"
     else:
@@ -118,45 +120,78 @@ def conversation(qa_chain, message, history, language):
     new_history = history + [(message, response_answer)]
     return qa_chain, gr.update(value=""), new_history, response_source1, response_source1_page, response_source2, response_source2_page, response_source3, response_source3_page
 
+# Login function
+def check_login(username, password):
+    if username == VALID_USERNAME and password == VALID_PASSWORD:
+        return True, "Login successful! Access the chatbot below."
+    else:
+        return False, "Invalid username or password. Please try again."
+
+# Main demo with login
 def demo():
     with gr.Blocks(theme=gr.themes.Default(primary_hue="red", secondary_hue="pink", neutral_hue="sky")) as demo:
+        # State variables
         vector_db = gr.State()
         qa_chain = gr.State()
-        gr.HTML("<center><h1>RAG PDF Chatbot</h1></center>")
-        gr.Markdown("""<b>Query your PDF documents!</b> This AI agent is designed to perform retrieval augmented generation (RAG) on PDF documents. \
-        <b>Please do not upload confidential documents.</b>""")
-        
-        with gr.Row():
-            with gr.Column(scale=86):
-                gr.Markdown("<b>Step 1 - Upload PDF documents and Initialize RAG pipeline</b>")
-                document = gr.Files(height=300, file_count="multiple", file_types=["pdf"], interactive=True, label="Upload PDF documents")
-                db_btn = gr.Button("Create vector database")
-                db_progress = gr.Textbox(value="Not initialized", show_label=False)
-                gr.Markdown("<b>Select Large Language Model (LLM) and input parameters</b>")
-                llm_btn = gr.Radio(list_llm_simple, label="Available LLMs", value=list_llm_simple[0], type="index")
-                with gr.Accordion("LLM input parameters", open=False):
-                    slider_temperature = gr.Slider(minimum=0.01, maximum=1.0, value=0.5, step=0.1, label="Temperature", interactive=True)
-                    slider_maxtokens = gr.Slider(minimum=128, maximum=9192, value=4096, step=128, label="Max New Tokens", interactive=True)
-                    slider_topk = gr.Slider(minimum=1, maximum=10, value=3, step=1, label="top-k", interactive=True)
-                qachain_btn = gr.Button("Initialize Question Answering Chatbot")
-                llm_progress = gr.Textbox(value="Not initialized", show_label=False)
-
-            with gr.Column(scale=200):
-                gr.Markdown("<b>Step 2 - Chat with your Document</b>")
-                language_selector = gr.Radio(["English", "Português"], label="Select Language", value="English")
-                chatbot = gr.Chatbot(height=505)
-                with gr.Accordion("Relevant context from the source document", open=False):
-                    doc_source1 = gr.Textbox(label="Reference 1", lines=2, container=True, scale=20)
-                    source1_page = gr.Number(label="Page", scale=1)
-                    doc_source2 = gr.Textbox(label="Reference 2", lines=2, container=True, scale=20)
-                    source2_page = gr.Number(label="Page", scale=1)
-                    doc_source3 = gr.Textbox(label="Reference 3", lines=2, container=True, scale=20)
-                    source3_page = gr.Number(label="Page", scale=1)
-                msg = gr.Textbox(placeholder="Ask a question", container=True)
-                submit_btn = gr.Button("Submit")
-                clear_btn = gr.ClearButton([msg, chatbot], value="Clear")
-
-        # Preprocessing events
+        logged_in = gr.State(value=False)
+
+        # Login interface
+        with gr.Column(visible=True) as login_col:
+            gr.HTML("<center><h1>RAG PDF Chatbot - Login</h1></center>")
+            username = gr.Textbox(label="Username", placeholder="Enter username")
+            password = gr.Textbox(label="Password", type="password", placeholder="Enter password")
+            login_btn = gr.Button("Login")
+            login_message = gr.Textbox(value="Please log in to access the chatbot.", show_label=False)
+
+        # Chatbot interface (hidden until login)
+        with gr.Column(visible=False) as chatbot_col:
+            gr.HTML("<center><h1>RAG PDF Chatbot</h1></center>")
+            gr.Markdown("""<b>Query your PDF documents!</b> This AI agent is designed to perform retrieval augmented generation (RAG) on PDF documents. \
+            <b>Please do not upload confidential documents.</b>""")
+            
+            with gr.Row():
+                with gr.Column(scale=86):
+                    gr.Markdown("<b>Step 1 - Upload PDF documents and Initialize RAG pipeline</b>")
+                    document = gr.Files(height=300, file_count="multiple", file_types=["pdf"], interactive=True, label="Upload PDF documents")
+                    db_btn = gr.Button("Create vector database")
+                    db_progress = gr.Textbox(value="Not initialized", show_label=False)
+                    gr.Markdown("<b>Select Large Language Model (LLM) and input parameters</b>")
+                    llm_btn = gr.Radio(list_llm_simple, label="Available LLMs", value=list_llm_simple[0], type="index")
+                    with gr.Accordion("LLM input parameters", open=False):
+                        slider_temperature = gr.Slider(minimum=0.01, maximum=1.0, value=0.5, step=0.1, label="Temperature", interactive=True)
+                        slider_maxtokens = gr.Slider(minimum=128, maximum=9192, value=4096, step=128, label="Max New Tokens", interactive=True)
+                        slider_topk = gr.Slider(minimum=1, maximum=10, value=3, step=1, label="top-k", interactive=True)
+                    qachain_btn = gr.Button("Initialize Question Answering Chatbot")
+                    llm_progress = gr.Textbox(value="Not initialized", show_label=False)
+
+                with gr.Column(scale=200):
+                    gr.Markdown("<b>Step 2 - Chat with your Document</b>")
+                    language_selector = gr.Radio(["English", "Português"], label="Select Language", value="English")
+                    chatbot = gr.Chatbot(height=505)
+                    with gr.Accordion("Relevant context from the source document", open=False):
+                        doc_source1 = gr.Textbox(label="Reference 1", lines=2, container=True, scale=20)
+                        source1_page = gr.Number(label="Page", scale=1)
+                        doc_source2 = gr.Textbox(label="Reference 2", lines=2, container=True, scale=20)
+                        source2_page = gr.Number(label="Page", scale=1)
+                        doc_source3 = gr.Textbox(label="Reference 3", lines=2, container=True, scale=20)
+                        source3_page = gr.Number(label="Page", scale=1)
+                    msg = gr.Textbox(placeholder="Ask a question", container=True)
+                    submit_btn = gr.Button("Submit")
+                    clear_btn = gr.ClearButton([msg, chatbot], value="Clear")
+
+        # Login event
+        login_btn.click(
+            fn=check_login,
+            inputs=[username, password],
+            outputs=[logged_in, login_message]
+        ).then(
+            fn=lambda logged: (gr.update(visible=not logged), gr.update(visible=logged)),
+            inputs=[logged_in],
+            outputs=[login_col, chatbot_col],
+            queue=False
+        )
+
+        # Preprocessing events (only accessible after login)
         db_btn.click(initialize_database, inputs=[document], outputs=[vector_db, 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