app.py

import gradio as gr
import requests
import pandas as pd
from gradio_huggingfacehub_search import HuggingfaceHubSearch


def analyze_dataset(dataset: str) -> pd.DataFrame:
    yield f"Presidio scan results for {dataset}:", pd.DataFrame({"type": [], "text": [], "row_idx": [], "column_name": []})

iface = gr.Interface(
    fn=analyze_dataset,
    inputs=[
        HuggingfaceHubSearch(
            label="Hub Dataset ID",
            placeholder="Search for dataset id on Huggingface",
            search_type="dataset",
        ),
    ],
    outputs=[
        gr.Markdown(),
        gr.DataFrame(),
    ],
    title="Scan datasets using Presidio",
    description="The space takes an HF dataset name as an input, and returns the list of entities detected by Presidio in the first samples.",
)

with gr.Blocks() as demo:
    iface.render()

demo.launch()