app.py

import gradio as gr
import numpy as np
import pandas as pd
from sklearn.metrics.pairwise import cosine_similarity

import os
import requests

url = 'https://huggingface.co/datasets/sheacon/song_lyrics/resolve/main/v2ga_w_embeddings.parquet'
response = requests.get(url, stream=True)

filename = os.path.join(os.getcwd(), url.split('/')[-1])
with open(filename, 'wb') as file:
    for chunk in response.iter_content(chunk_size=8192):
        if chunk:
            file.write(chunk)

print(f"File '{filename}' has been downloaded to the present working directory.")


pwd = os.getcwd()
print("Present Working Directory:", pwd)

contents = os.listdir(pwd)
print("Contents of the Directory:")
for item in contents:
    print(item)