Update app.py

app.py

@@ -40,16 +40,17 @@ def data_ingestion_from_directory():
     index = VectorStoreIndex.from_documents(documents)
     index.storage_context.persist(persist_dir=PERSIST_DIR)
 
-def handle_query(query):
+def handle_query(message, chat_history):
+    # Prepare the chat history for context
+    context_str = ""
+    for user_message, bot_response in chat_history:
+        context_str += f"User asked: '{user_message}'\nBot answered: '{bot_response}'\n"
+
+    # Prepare the chat prompt template
     chat_text_qa_msgs = [
         (
             "user",
-            """
-            You are now the RedFerns Tech chatbot. Your aim is to provide answers to the user based on the conversation flow only.
-            {context_str}
-            Question:
-            {query_str}
-            """
+            f"You are now the RedFerns Tech chatbot. Your aim is to provide answers to the user based on the conversation flow only.\n\nQuestion:\n{message}"
         )
     ]
     text_qa_template = ChatPromptTemplate.from_messages(chat_text_qa_msgs)
@@ -58,14 +59,9 @@ def handle_query(query):
     storage_context = StorageContext.from_defaults(persist_dir=PERSIST_DIR)
     index = load_index_from_storage(storage_context)
 
-    # Use chat history to enhance response
-    context_str = ""
-    for past_query, response in reversed(current_chat_history):
-        if past_query.strip():
-            context_str += f"User asked: '{past_query}'\nBot answered: '{response}'\n"
-
+    # Use the Llama index to generate a response
     query_engine = index.as_query_engine(text_qa_template=text_qa_template, context_str=context_str)
-    answer = query_engine.query(query)
+    answer = query_engine.query(message)
 
     if hasattr(answer, 'response'):
         response = answer.response
@@ -74,8 +70,8 @@ def handle_query(query):
     else:
         response = "Sorry, I couldn't find an answer."
 
-    # Update current chat history
-    current_chat_history.append((query, response))
+    # Update chat history with the current interaction
+    chat_history.append([message, response])
 
     return response
 
@@ -83,27 +79,13 @@ def handle_query(query):
 print("Processing PDF ingestion from directory:", PDF_DIRECTORY)
 data_ingestion_from_directory()
 
-# Define the input and output components for the Gradio interface
-input_component = gr.Textbox(
-    show_label=False,
-    placeholder="Ask me anything about the document..."
-)
-
-output_component = gr.Textbox()
-
-# Function to handle queries
-def chatbot_handler(query):
-    response = handle_query(query)
-    return response
-
 # Create the Gradio interface
 interface = gr.ChatInterface(
-    fn=chatbot_handler,
-    inputs=input_component,
-    outputs=output_component,
+    fn=handle_query,
+    inputs=gr.Textbox(label="Ask me anything about the document...", placeholder="Type your question here."),
     title="RedfernsTech Q&A Chatbot",
     description="Ask me anything about the uploaded document."
 )
 
 # Launch the Gradio interface
-interface.launch(share=True)
+interface.launch()