app.py

import time
import datetime

import streamlit as st
from huggingface_hub import login
from transformers import pipeline

import os 

token = os.getenv("modelo")
login(token = token)

# question = "Name the planets in the solar system? A: "
# question = "Quais são os planetas do sistema solar?" 
# question = "Qual é o maior planeta do sistema solar?" 

before = datetime.datetime.now()

# =====================================================

import transformers
import torch

model_id = "meta-llama/Meta-Llama-3.1-8B-Instruct"

pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={"torch_dtype": torch.bfloat16},
    device_map="auto",
)


with st.container():
    st.write('\n\n')
    st.title('LLM-LANAChat\n\n')
    question = st.text_input("Chat", placeholder="E ai?")

    if question:
        messages = [
         # {"role": "system", "content": "You are a chatbot"},
        {"role": "user", "content": question}
        ]
        st.write('Gerando a saída...')
        outputs = pipeline(
          messages,
          max_new_tokens=256,
        )
        response = outputs[0]["generated_text"][-1]
        st.write('Saída gerada...')
    
    
    # =====================================================
    
        print('\n\n')
        st.write(response)


    after = datetime.datetime.now()
    current_time = (after - before) # .strftime("%H:%M:%S")
    print("\nTime Elapsed: ", current_time)
    st.write("\nTime Elapsed: ", current_time)