app.py

import streamlit as st
import pandas as pd
from transformers import BartForConditionalGeneration, TapexTokenizer, T5ForConditionalGeneration, T5Tokenizer
import datetime
import sentencepiece as spm

# File upload interface
uploaded_file = st.file_uploader("Upload a CSV or XLSX file", type=['csv', 'xlsx'])

if uploaded_file:
    # Load the file into a DataFrame
    if uploaded_file.name.endswith('.csv'):
        df = pd.read_csv(uploaded_file, quotechar='"', encoding='utf-8')
    elif uploaded_file.name.endswith('.xlsx'):
        df = pd.read_excel(uploaded_file)

    df.rename(columns={"ds": "datetime", "real": "monetary value", "Explicação": "explanation"}, inplace=True)
    df.sort_values(by=['datetime', 'monetary value'], ascending=False, inplace=True)
    df = df[df['monetary value'] >= 10000000.]
    df['monetary value'] = df['monetary value'].apply(lambda x: f"{x:.2f}")
    df = df.fillna('').astype(str)
    table_data = df

    # Display the uploaded table
    st.dataframe(table_data.head())

    # Load translation models
    pt_en_translator = T5ForConditionalGeneration.from_pretrained("unicamp-dl/translation-pt-en-t5")
    en_pt_translator = T5ForConditionalGeneration.from_pretrained("unicamp-dl/translation-en-pt-t5")
    tokenizer = T5Tokenizer.from_pretrained("unicamp-dl/translation-pt-en-t5")

    # Load TAPEX model
    tapex_model = BartForConditionalGeneration.from_pretrained("microsoft/tapex-large-finetuned-wtq")
    tapex_tokenizer = TapexTokenizer.from_pretrained("microsoft/tapex-large-finetuned-wtq")

    def translate(text, model, tokenizer, source_lang="pt", target_lang="en"):
        input_ids = tokenizer.encode(text, return_tensors="pt", add_special_tokens=True)
        outputs = model.generate(input_ids)
        translated_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
        return translated_text

    def response(user_question, table_data):
        # Traduz a pergunta para o inglês
        question_en = translate(user_question, pt_en_translator, tokenizer, source_lang="pt", target_lang="en")
        print(question_en)

        # Gera a resposta em inglês
        encoding = tapex_tokenizer(table=table_data, query=[question_en], padding=True, return_tensors="pt", truncation=True)
        outputs = tapex_model.generate(**encoding)
        response_en = tapex_tokenizer.batch_decode(outputs, skip_special_tokens=True)[0]
        print(response_en)

        # Traduz a resposta para o português
        response_pt = translate(response_en, en_pt_translator, tokenizer, source_lang="en", target_lang="pt")
        return response_pt

    # Streamlit interface

    st.markdown("""
    <div style='display: flex; align-items: center;'>
        <div style='width: 40px; height: 40px; background-color: green; border-radius: 50%; margin-right: 5px;'></div>
        <div style='width: 40px; height: 40px; background-color: red; border-radius: 50%; margin-right: 5px;'></div>
        <div style='width: 40px; height: 40px; background-color: yellow; border-radius: 50%; margin-right: 5px;'></div>
        <span style='font-size: 40px; font-weight: bold;'>Chatbot do Tesouro RS</span>
    </div>
    """, unsafe_allow_html=True)

    # Chat history
    if 'history' not in st.session_state:
        st.session_state['history'] = []

    # Input box for user question
    user_question = st.text_input("Escreva sua questão aqui:", "")

    if user_question:
        # Add human emoji when user asks a question
        st.session_state['history'].append(('👤', user_question))
        st.markdown(f"**👤 {user_question}**")
        
        # Generate the response
        bot_response = response(user_question, table_data)
        
        # Add robot emoji when generating response and align to the right
        st.session_state['history'].append(('🤖', bot_response))
        st.markdown(f"<div style='text-align: right'>**🤖 {bot_response}**</div>", unsafe_allow_html=True)

    # Clear history button
    if st.button("Limpar"):
        st.session_state['history'] = []

    # Display chat history
    for sender, message in st.session_state['history']:
        if sender == '👤':
            st.markdown(f"**👤 {message}**")
        elif sender == '🤖':
            st.markdown(f"<div style='text-align: right'>**🤖 {message}**</div>", unsafe_allow_html=True)
else:
    st.warning("Carregue um arquivo CSV ou XLSX para começar.")