import streamlit as st
import torch
from transformers import AutoTokenizer, AutoModel

# load the pre-trained model and tokenizer
tokenizer = AutoTokenizer.from_pretrained('sentence-transformers/distiluse-base-multilingual-cased-v1')
model = AutoModel.from_pretrained('sentence-transformers/distiluse-base-multilingual-cased-v1')

# set the app title
st.title("Brazilian Portuguese Sentence Similarity Checker")

# get the input sentences from the user
sentence1 = st.text_input("Enter the first sentence:")
sentence2 = st.text_input("Enter the second sentence:")

# check if both sentences are not empty
if sentence1 and sentence2:
    # tokenize the sentences and get their IDs
    input_ids = tokenizer.encode_plus(sentence1, sentence2, padding='max_length', truncation=True, return_tensors='pt')
    
    # pass the IDs through the model to get the embeddings
    with torch.no_grad():
        embeddings = model(input_ids['input_ids'], attention_mask=input_ids['attention_mask'])[0]
    
    # calculate the cosine similarity between the embeddings
    similarity = torch.nn.functional.cosine_similarity(embeddings[0], embeddings[1]).item()
    
    # display the predicted similarity to the user
    st.write("Similarity score between the sentences:", similarity)