Update app.py

app.py

@@ -1,34 +1,32 @@
 import os
 import streamlit as st
-from langchain_community.vectorstores import FAISS
-from langchain_huggingface import HuggingFaceEmbeddings
 import subprocess
 import openai
+from langchain_community.vectorstores import FAISS
+from langchain.embeddings import HuggingFaceEmbeddings
 from openai import OpenAI
 from langchain_openai import ChatOpenAI
-from io import BytesIO
 from typing import List, Dict
-from dotenv import load_dotenv
 # Load environment variables
 OPENAI_API_KEY = os.getenv("OPENAI_API")
 TOKEN=os.getenv('HF_TOKEN')
 subprocess.run(["huggingface-cli", "login", "--token", TOKEN, "--add-to-git-credential"])
 st.sidebar.title("Welcome to MBAL Chatbot")
 class PDFChatbot:
-    def __init__(self):
+   def __init__(self):
        self.azure_client = openai.OpenAI()
-       # Store conversation history
        self.conversation_history = []
+       self.pdf_content = ""
 
-    def get_relevant_context(self, user_question: str) -> List[str]:
+   def get_relevant_context(self, user_question: str) -> List[str]:
         """Split text into smaller chunks for better processing."""
         db = FAISS.load_local("mbal_faiss_db", embeddings=HuggingFaceEmbeddings(model_name='bkai-foundation-models/vietnamese-bi-encoder'), allow_dangerous_deserialization=True)
         relevant_chunks = db.similarity_search(user_question, k=3)
         relevant_chunks = [chunk.page_content for chunk in relevant_chunks]
         return "\n\n".join(relevant_chunks)
-    def chat_with_pdf(self, user_question: str, pdf_content: str) -> str:
+   def chat_with_pdf(self, user_question: str, pdf_content: str) -> str:
        """Generate response using Azure OpenAI based on PDF content and user question."""
-        try:
+       try:
            # Split PDF content into chunks
            # Get relevant context for the question
            relevant_context = self.get_relevant_context(user_question)
@@ -62,7 +60,7 @@ Please provide a helpful response based on the insurance document content above.
                messages.append(msg)
            # Get response from Azure OpenAI
            response = self.azure_client.chat.completions.create(
-               model="gpt-4o-mini",
+               model="gpt-4o-mini,
                messages=messages,
                max_tokens=1000,
                temperature=0.7
@@ -75,25 +73,46 @@ Please provide a helpful response based on the insurance document content above.
        except Exception as e:
            return f"Error generating response: {str(e)}"
 def main():
-    # st.set_page_config(page_title="Insurance PDF Chatbot", page_icon="🛡️", layout="wide")
-    st.title("🛡️ Insurance Policy Assistant")
-    st.markdown("Upload your insurance policy PDF and ask questions about your coverage, claims, deductibles, and more!")
-    # Initialize chatbot
-    if 'chatbot' not in st.session_state:
+   # st.set_page_config(page_title="Insurance PDF Chatbot", page_icon="🛡️", layout="wide")
+   st.title("🛡️ Insurance Policy Assistant")
+   st.markdown("Upload your insurance policy PDF and ask questions about your coverage, claims, deductibles, and more!")
+   # Initialize chatbot
+   if 'chatbot' not in st.session_state:
        st.session_state.chatbot = PDFChatbot()
        st.session_state.pdf_processed = False
        st.session_state.chat_history = []
-
+   # Sidebar for PDF upload and settings
+   with st.sidebar:
+       st.header("📁 Upload Insurance Document")
+       uploaded_file = st.file_uploader("Choose a PDF file", type="pdf")
+       if uploaded_file is not None:
+           if st.button("Process PDF"):
+               with st.spinner("Processing your insurance document..."):
+                   # Extract text from PDF
+                   text_content = st.session_state.chatbot.extract_text_from_pdf(uploaded_file)
+                   if text_content:
+                       st.session_state.chatbot.pdf_content = text_content
+                       st.session_state.pdf_processed = True
+                       st.success("Insurance document processed successfully!")
+                       # Show PDF summary
+                       st.subheader("Document Preview")
+                       st.text_area(
+                           "First 500 characters:",
+                           text_content[:500] + "..." if len(text_content) > 500 else text_content,
+                           height=100
+                       )
+                   else:
+                       st.error("Failed to process PDF")
        # Clear conversation
-       if st.button("Xóa lịch sử chat"):
+       if st.button("Xóa lịch sử"):
            st.session_state.chatbot.conversation_history = []
            st.session_state.chat_history = []
            st.rerun()
    # Main chat interface
-    if st.session_state.pdf_processed:
-        st.header("💬 Ask About Your Insurance Policy")
-        # Display chat history
-        for i, (question, answer) in enumerate(st.session_state.chat_history):
+   if st.session_state.pdf_processed:
+       st.header("💬 Ask About Your Insurance Policy")
+       # Display chat history
+       for i, (question, answer) in enumerate(st.session_state.chat_history):
            with st.container():
                st.markdown(f"**You:** {question}")
                st.markdown(f"**Insurance Assistant:** {answer}")
@@ -139,4 +158,4 @@ def main():
         """)
 
 if __name__ == "__main__":
-    main()
+   main()