Update app.py

app.py

@@ -9,7 +9,6 @@ from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder
 from langchain_core.messages import HumanMessage, AIMessage
 from langchain.memory import ConversationBufferMemory
 from langchain.document_loaders import PyPDFLoader
-from fuzzywuzzy import process
 
 # Set page config
 st.set_page_config(page_title="Tbank Assistant", layout="wide")
@@ -91,13 +90,13 @@ if "OPENAI_API_KEY" in os.environ:
 
         document_chain = create_stuff_documents_chain(chat, question_answering_prompt)
 
-        important_terms = ["Tbank", "Chairman", "CEO", "products", "services"]  # Add more terms as needed
+    
 
-        return retriever, document_chain, important_terms
+        return retriever, document_chain
 
     # Load components
     with st.spinner("Initializing Tbank Assistant..."):
-        retriever, document_chain, important_terms = initialize_components()
+        retriever, document_chain = initialize_components()
 
     # Initialize memory for each session
     if "memory" not in st.session_state:
@@ -115,11 +114,6 @@ if "OPENAI_API_KEY" in os.environ:
         with st.chat_message(message["role"]):
             st.markdown(message["content"])
 
-    def fuzzy_match(query, choices, threshold=80):
-        result = process.extractOne(query, choices)
-        if result and result[1] >= threshold:
-            return result[0]
-        return None
 
     # React to user input
     if prompt := st.chat_input("What would you like to know about Tbank?"):
@@ -131,10 +125,10 @@ if "OPENAI_API_KEY" in os.environ:
         with st.chat_message("assistant"):
             message_placeholder = st.empty()
 
-            # Fuzzy match important terms
-            matched_term = fuzzy_match(prompt.lower(), important_terms)
-            if matched_term:
-                prompt = f"{prompt} (Matched term: {matched_term})"
+            # # Fuzzy match important terms
+            # matched_term = fuzzy_match(prompt.lower(), important_terms)
+            # if matched_term:
+            #     prompt = f"{prompt} (Matched term: {matched_term})"
 
             # Retrieve relevant documents
             docs = retriever.get_relevant_documents(prompt)