import os
import streamlit as st
from dotenv import load_dotenv
from AI_Risk_app import retrieval_augmented_qa_chain  # Importing the RAG chain

# Load the .env file
import streamlit as st
import openai

# Get OpenAI API key from Streamlit secrets
#openai.api_key = st.secrets["OPENAI_API_KEY"]

# Load environment variables
load_dotenv()

# Load environment variables from a .env file

openai_api_key = os.getenv('OPENAI_API_KEY')
# Set up the Streamlit interface
st.title("AI Risk Advisory QA")

# Get the user query
user_query = st.text_input("Ask your question:")

# Button to trigger the RAG process
if st.button("Get Answer"):
    if user_query:
        # Pass user query through RAG chain
        result = retrieval_augmented_qa_chain.invoke({"question": user_query})

        # Extract response content from RAG result
        response_content = result["response"].content

        # Display the response content in the Streamlit app
        st.write("**Answer:**")
        st.write(response_content)
    else:
        st.write("Please enter a question.")