main_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

st.set_page_config(page_title="Converse com Resoluções do Bacen, powered by LlamaIndex", page_icon="🦙", layout="centered", initial_sidebar_state="auto", menu_items=None)

############### reduce top margin ################
st.markdown(
        """
<style>
    .css-1y4p8pa {
        padding-top: 0px;
    }
</style>
""",
        unsafe_allow_html=True,
    )

############### hidde hamburguer menu ################
st.markdown(""" <style>
#MainMenu {visibility: hidden;}
footer {visibility: hidden;}
</style> """, unsafe_allow_html=True)

openai.api_key = st.secrets.openai_key
st.header("Converse 💬 com as Resoluções 4.966 e 352 do Banco Central e outras relacionadas, powered by LlamaIndex 🦙")
st.info("Código disponível neste [repositório Github](https://github.com/mvpalheta/4966_LLM)", icon="💡")
         
if "messages" not in st.session_state.keys(): # Initialize the chat messages history
    st.session_state.messages = [
        {"role": "assistant", "content": "Me pergunte algo relacionado às Resoluções 4.966 e 352 do Banco Central!"}
    ]

@st.cache_resource(show_spinner=False, ttl="30min")
def load_data():
    with st.spinner(text="Loading and indexing the docs – 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))
        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)

if prompt := st.chat_input("Sua pergunta"): # 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("Pensando..."):
            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