app.py

import streamlit as st
from llama_index import VectorStoreIndex, ServiceContext, Document
from llama_index.llms import OpenAI
import openai
from llama_index import SimpleDirectoryReader
import os

st.set_page_config(page_title="HUD Audit Guide", page_icon="🍂", layout="centered", initial_sidebar_state="auto", menu_items=None)

test_key_print = os.environ['OPENAI_KEY']

openai.api_key = test_key_print
st.title("Ask the HUD Audit Guide 💬🤖")
st.info("Check out more info on the complete HUD Audit Guide at the official [website](https://www.hudoig.gov/library/single-audit-guidance/hud-consolidated-audit-guide)", icon="📃")
         
if "messages" not in st.session_state.keys(): # Initialize the chat messages history
    st.session_state.messages = [
        {"role": "assistant", "content": "Ask me a question about the HUD Audit Guide - Chapter 6 - Ginnie Mae Issuers of Mortgage-Backed Securities Audit Guidance!"}
    ]

@st.cache_resource(show_spinner=False)
def load_data():
    with st.spinner(text="Loading and indexing the HUD Audit Guide – hang tight! This should take 1-2 minutes."):
        reader = SimpleDirectoryReader(input_dir="./data", recursive=True)
        docs = reader.load_data()
        service_context = ServiceContext.from_defaults(llm=OpenAI(model="gpt-3.5-turbo", temperature=0.5, system_prompt="You are an expert on the HUD Audit Guide and your job is to answer technical questions. Assume that all questions are related to the HUD Audit Guide and Ginnie Mae Issuers. Keep your answers technical and based on facts – do not hallucinate features."))
        index = VectorStoreIndex.from_documents(docs, service_context=service_context)
        return index

index = load_data()
#chat_engine = index.as_chat_engine(chat_mode="condense_question", verbose=True, system_prompt="You are an expert on the Streamlit Python library and your job is to answer technical questions. Assume that all questions are related to the Streamlit Python library. Keep your answers technical and based on facts – do not hallucinate features.")
chat_engine = index.as_chat_engine(chat_mode="condense_question", verbose=True)

if prompt := st.chat_input("Your question"): # Prompt for user input and save to chat history
    st.session_state.messages.append({"role": "user", "content": prompt})

for message in st.session_state.messages: # Display the prior chat messages
    with st.chat_message(message["role"]):
        st.write(message["content"])

# If last message is not from assistant, generate a new response
if st.session_state.messages[-1]["role"] != "assistant":
    with st.chat_message("assistant"):
        with st.spinner("Thinking..."):
            response = chat_engine.chat(prompt)
            st.write(response.response)
            message = {"role": "assistant", "content": response.response}
            st.session_state.messages.append(message) # Add response to message history