app.py

import gradio as gr
from datasets import load_dataset
import pandas as pd

# Load dataset
dataset = load_dataset('dell-research-harvard/newswire', split='train')

# Function to filter and match articles
def filter_nobel_articles(laureates_file):
    laureates_df = pd.read_csv(laureates_file.name)
    nobel_articles = dataset.filter(lambda example: 'nobel' in example['text'].lower())
    
    def contains_laureate(article_text):
        for _, row in laureates_df.iterrows():
            if row['first_name'] in article_text and row['last_name'] in article_text:
                return True
        return False
    
    filtered_articles = nobel_articles.filter(lambda example: contains_laureate(example['text']))
    return f"Found {len(filtered_articles)} articles mentioning Nobel laureates."

# Create Gradio interface
interface = gr.Interface(
    fn=filter_nobel_articles,
    inputs=gr.File(label="Upload Nobel Laureates CSV"),
    outputs="text"
)

interface.launch()