---
title: Paper Reader Assistant
emoji: 📚
colorFrom: blue
colorTo: green
sdk: gradio
sdk_version: "4.44.0"
app_file: app.py
pinned: false
---

# Paper Reader Assistant (Gradio on Hugging Face Spaces)

Features:
- Upload PDFs → extract text (PyMuPDF)
- Summarization (BART map-reduce)
- Keyword extraction (KeyBERT)
- RAG QA with FAISS + sentence-transformers + Flan-T5

## Quick Start
1. Create a new **Space** with SDK = **Gradio**.
2. Upload three files: `app.py`, `requirements.txt`, `README.md`.
3. Wait for auto-build to finish. Open the Space URL.

## Notes
- Works best on English scientific PDFs (text-based).  
- For scanned PDFs, run OCR first (not included).  
- All models run on CPU by default; enable GPU for faster inference.