metadata

title: QandA Generator
emoji: 💬
colorFrom: yellow
colorTo: purple
sdk: gradio
sdk_version: 5.0.1
app_file: app.py
pinned: false
license: apache-2.0

Paragraph-to-Question Generator (Auto Q&A for HF Dataset)

This Hugging Face Space is an interactive demo that generates question and answer pairs from paragraph-based data. It uses advanced NLP models to parse text, generate questions, and lets you update a dataset hosted on Hugging Face. Each saved Q&A entry is automatically timestamped with the current month and year.

Features

Extract Facts: Automatically break down your input text (separated by paragraphs) into facts.
Customizable Generation: Adjust parameters such as minimum/maximum token length, temperature, top-k, and top-p sampling to influence the question generation.
Editable Q&A JSON: Review and modify the generated Q&A JSON output before submitting.
Dataset Update: Save your generated Q&A entries (with additional timestamp information) to a remote dataset on the Hugging Face Hub (University_Inquiries_AI_Chatbot/dataset.json).

Setup Instructions

1. Hugging Face Secrets

Add your Hugging Face token as a secret in your Space. In your Space settings, add a secret: