app.py

import streamlit as st
import pandas as pd
from sentence_transformers import SentenceTransformer, util
from datasets import load_dataset


@st.cache_resource
def load_model():
    return SentenceTransformer('sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2')

model = load_model()

secret_word = "нос"
secred_embedding = model.encode(secret_word)

if 'words' not in st.session_state:
    st.session_state['words'] = []

st.write('Try to guess a secret word by semantic similarity')

word = st.text_input("Input a word")

used_words = [w for w, s in st.session_state['words']]

if st.button("Guess") or word:
    if word not in used_words:
        word_embedding = model.encode(word)
        similarity = util.pytorch_cos_sim(secred_embedding, word_embedding).cpu().numpy()[0][0]
        st.session_state['words'].append((word, similarity))

words_df = pd.DataFrame(
    st.session_state['words'],
    columns=["word", "similarity"]
).sort_values(by=["similarity"], ascending=False)
st.dataframe(words_df)



@st.cache_data
def load_words_dataset():
    dataset = load_dataset("marksverdhei/wordnet-definitions-en-2021", split="train")
    return dataset["Word"]

all_words = load_words_dataset()
st.write(all_words)