---
title: Document Question Answering
emoji: 📄
colorFrom: blue
colorTo: green
sdk: gradio
sdk_version: "5.38.0"
python_version: "3.11"
app_file: app.py
pinned: false
---

# Document Question Answering using Groq

A production-ready Retrieval-Augmented Generation (RAG) application built with:

- LangChain
- ChromaDB
- HuggingFace Embeddings
- Groq LLM
- Gradio

## Features

- Upload one or more PDF documents
- Semantic document retrieval
- Retrieval-Augmented Generation (RAG)
- Groq Llama 3.3 integration
- Source citations with page numbers
- Adjustable chunk size
- Adjustable chunk overlap
- Adjustable Top-K retrieval

## Deployment

1. Create a Hugging Face Space using the Gradio SDK.
2. Upload app.py, requirements.txt and this README.md.
3. Add a repository secret named GROQ_API_KEY.
4. Paste your Groq API key as the secret value.
5. Wait for the build to complete.

## Notes

This project is intended as an educational demonstration of a modern Document Question Answering workflow.