import streamlit as st import pandas as pd import torch from transformers import pipeline #from transformers import TapasTokenizer, TapexTokenizer, BartForConditionalGeneration from transformers import AutoTokenizer, AutoModelForTableQuestionAnswering import datetime #df = pd.read_excel('discrepantes.xlsx', index_col='Unnamed: 0') df = pd.read_excel('discrepantes.xlsx') df.fillna(0, inplace=True) table_data = df.astype(str) print(table_data.head()) def response(user_question, table_data): a = datetime.datetime.now() model_name = "google/tapas-base-finetuned-wtq" model = AutoModelForTableQuestionAnswering.from_pretrained(model_name) tokenizer = AutoTokenizer.from_pretrained(model_name) # The query should be passed as a list encoding = tokenizer(table=table_data, queries=[user_question], padding=True, return_tensors="pt", truncation=True) # Experiment with generation parameters outputs = model.generate( **encoding, num_beams=5, # Beam search to generate more diverse responses top_k=50, # Top-k sampling for diversity top_p=0.95, # Nucleus sampling temperature=0.7, # Temperature scaling (if supported by the model) max_length=50, # Limit the length of the generated response early_stopping=True # Stop generation when an end token is generated ) ans = tokenizer.batch_decode(outputs, skip_special_tokens=True) query_result = { "Resposta": ans[0] } b = datetime.datetime.now() print(b - a) return query_result # Streamlit interface st.markdown("""