app.py

import streamlit as st

from langchain.embeddings import HuggingFaceEmbeddings
from langchain.vectorstores import FAISS

sample_words = ['apple', 'orange', 'rose', 'chocolate', 'pen', 'school', 'book', 'computer']

#Define the HuggingFaceEmbeddings model
model_path = 'sentence-transformers/all-MiniLM-l6-v2'

embeddings = HuggingFaceEmbeddings(
    model_name= model_path,
    model_kwargs={'device':'cpu'},
    encode_kwargs={'normalize_embeddings': False}
)


db = FAISS.from_texts(sample_words, embeddings)

# UI 
st.header("Ask me a question, and I'll provide similar words!")

input_word = st.text_input("You: ", key= input)

if input_word:
    submit = st.button('Show me similar words')

    if submit:
        results = db.similarity_search(input_word)
        st.subheader("Top Words:")
        st.text(docs[0].page_content)
        st.text(docs[1].page_content)