app.py

from datasets import load_dataset
import streamlit as st


@st.cache()
def load_all_repository_names():
    list_of_repo_names = ["test"]
    #list_of_repo_names = load_dataset("bigcode/the-stack-paths", split="train")["repository_name"]
    return list_of_repo_names

st.title("Am I in The Stack?")
st.markdown("This tool lets you check if a repository under a given username is part of [The Stack dataset](https://huggingface.co/datasets/bigcode/the-stack).")
repo_names = load_all_repository_names()
n_repos = len(repo_names)

username = st.text_input("GitHub Username:")

st.markdown("_Note_: this Space is currently under construction.")