Update app.py

app.py

@@ -40,15 +40,16 @@ def data_ingestion_from_directory():
     index = VectorStoreIndex.from_documents(documents)
     index.storage_context.persist(persist_dir=PERSIST_DIR)
 
-def handle_query(message, history):
-    # Prepare the chat history for context
-    chat_history = [[msg["text"], ""] for msg in history]
-
-    # Prepare the chat prompt template
+def handle_query(query):
     chat_text_qa_msgs = [
         (
             "user",
-            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}"
+            """
+            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}
+            """
         )
     ]
     text_qa_template = ChatPromptTemplate.from_messages(chat_text_qa_msgs)
@@ -57,9 +58,14 @@ def handle_query(message, history):
     storage_context = StorageContext.from_defaults(persist_dir=PERSIST_DIR)
     index = load_index_from_storage(storage_context)
 
-    # Use the Llama index to generate a response
-    query_engine = index.as_query_engine(text_qa_template=text_qa_template, context_str="")
-    answer = query_engine.query(message)
+    # 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"
+
+    query_engine = index.as_query_engine(text_qa_template=text_qa_template, context_str=context_str)
+    answer = query_engine.query(query)
 
     if hasattr(answer, 'response'):
         response = answer.response
@@ -68,23 +74,19 @@ def handle_query(message, history):
     else:
         response = "Sorry, I couldn't find an answer."
 
-    # Update chat history with the current interaction
-    chat_history.append([message, response])
+    # Update current chat history
+    current_chat_history.append((query, response))
 
     return response
 
-
 # Example usage: Process PDF ingestion from directory
 print("Processing PDF ingestion from directory:", PDF_DIRECTORY)
 data_ingestion_from_directory()
 
-# Create the Gradio interface
-interface = gr.ChatInterface(
-    fn=handle_query,
-    examples=[{"text": "hello"}, {"text": "hola"}, {"text": "merhaba"}],
-    title="RedfernsTech Q&A Chatbot",
-    description="Ask me anything about the uploaded document."
-)
+# Define the function to handle predictions
+def predict(message):
+    response = handle_query(message)
+    return response
 
-# Launch the Gradio interface
-interface.launch()
+# Create the Gradio interface using ChatInterface
+gr.ChatInterface(predict).launch()