Update app.py

app.py

@@ -1,15 +1,16 @@
 import streamlit as st
-from langchain_openai import ChatOpenAI, OpenAIEmbeddings
+from langchain_openai import ChatOpenAI
 import os
 import dotenv
+from langchain_community.document_loaders import WebBaseLoader
 from langchain_text_splitters import RecursiveCharacterTextSplitter
 from langchain_chroma import Chroma
+from langchain_openai import OpenAIEmbeddings
 from langchain.chains.combine_documents import create_stuff_documents_chain
 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")
@@ -32,6 +33,7 @@ if "OPENAI_API_KEY" in os.environ:
         dotenv.load_dotenv()
         chat = ChatOpenAI(model="gpt-3.5-turbo-1106", temperature=0.2)
 
+        #loader1 = WebBaseLoader("https://www.tbankltd.com/")
         loader1 = PyPDFLoader("Tbank resources.pdf")
         loader2 = PyPDFLoader("International Banking Services.pdf")
         data1 = loader1.load()
@@ -39,7 +41,6 @@ if "OPENAI_API_KEY" in os.environ:
         data = data1 + data2
         text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
         all_splits = text_splitter.split_documents(data)
-        
         embeddings = OpenAIEmbeddings(model="text-embedding-ada-002")
         vectorstore = Chroma.from_documents(documents=all_splits, embedding=embeddings)
         retriever = vectorstore.as_retriever(search_kwargs={"k": 6, "score_threshold": 0.5})
@@ -63,10 +64,11 @@ if "OPENAI_API_KEY" in os.environ:
         12. Regularly refer to the provided PDFs for accurate, up-to-date information about Tbank's products and services.
         13. Check for the basic Grammar and Spellings and understand if the spellings or grammar is slightly incorrect.
         14. Understand the user query with different angle, analyze properly, check through the possible answers and then give the answer.
-        15. Be forgiving of minor spelling mistakes and grammatical errors in user queries. Try to understand the intent behind the question.
-        16. Maintain context from previous messages in the conversation. If a user asks about a person or topic mentioned earlier, refer back to that information.
-        17. If a user asks about a person using only a name or title, try to identify who they're referring to based on previous context or your knowledge base.
-        18. When answering questions about specific people, provide their full name and title if available.
+        14. Be forgiving of minor spelling mistakes and grammatical errors in user queries. Try to understand the intent behind the question.
+        15. Maintain context from previous messages in the conversation. If a user asks about a person or topic mentioned earlier, refer back to that information.
+        16. If a user asks about a person using only a name or title, try to identify who they're referring to based on previous context or your knowledge base.
+        17. When answering questions about specific people, provide their full name and title if available.
+
         
         Your primary goal is to assist users with information directly related to Tbank, using only the website content and provided PDF documents. Avoid speculation and stick strictly to the provided information.
 
@@ -91,13 +93,14 @@ 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
+        important_terms = ["Tbank", "Chairman", "CEO", "products", "services"]
 
         return retriever, document_chain, important_terms
 
+
     # 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:
@@ -130,31 +133,31 @@ if "OPENAI_API_KEY" in os.environ:
 
         with st.chat_message("assistant"):
             message_placeholder = st.empty()
-
-            try:
-                # 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)
-
-                # Include previous messages for context
-                previous_messages = st.session_state.messages[-5:]  # Last 5 messages
-
-                # Generate response
-                response = document_chain.invoke(
-                    {
-                        "context": docs,
-                        "chat_history": st.session_state.memory.load_memory_variables({})["chat_history"],
-                        "messages": [HumanMessage(content=msg["content"]) for msg in previous_messages] + [HumanMessage(content=prompt)],
-                    }
-                )
-
-                full_response = response
-                message_placeholder.markdown(full_response)
-
+            
+            # 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)
+
+            # Include previous messages for context
+            previous_messages = st.session_state.messages[-5:]  # Last 5 messages
+
+           # Generate response
+            response = document_chain.invoke(
+                {
+                    "context": docs,
+                    "chat_history": st.session_state.memory.load_memory_variables({})["chat_history"],
+                    "messages": [HumanMessage(content=msg["content"]) for msg in previous_messages] + [HumanMessage(content=prompt)],
+                }
+            )
+
+            # The response is already a string, so we can use it directly
+            full_response = response
+            message_placeholder.markdown(full_response)
 
         # Add assistant response to chat history
         st.session_state.messages.append({"role": "assistant", "content": full_response})