README.md

---
title: PDF Q&A Tutor (Groq Powered)
emoji: 📘
colorFrom: indigo
colorTo: blue
sdk: gradio
sdk_version: 5.44.1
app_file: app.py
pinned: false
---

# 📘 PDF Q&A Tutor

Upload a PDF research paper and ask questions about it!  
This Space uses:

- **SentenceTransformers** for embeddings
- **FAISS** for vector search
- **Groq API** for fast, low-latency LLM inference (e.g. `qwen/qwen3-32b` or `llama3-70b`)

## 🔑 Setup

1. Go to your Space’s **Settings → Repository secrets**.
2. Add your Groq API key as:
GROQ_API_KEY = your_api_key_here

## 🚀 Usage

1. Upload a PDF paper.
2. Ask questions in the chatbox.
3. The system retrieves relevant chunks from the PDF and asks Groq’s LLM to explain in simple terms.

## 🧩 Models
- Embeddings: `intfloat/e5-base-v2`
- Vector DB: FAISS
- LLM (via Groq API): `qwen/qwen3-32b` (default, can be swapped for `llama3-70b`)

---