---
title: LightRAG Practical Guide
emoji: 📚
colorFrom: blue
colorTo: green
sdk: streamlit
sdk_version: 1.31.0
app_file: app.py
pinned: false
---

# LightRAG Practical Guide for Students

This Hugging Face Space is a practical implementation of the **LightRAG** framework using LangChain and Streamlit.

## Features
- **PDF Upload**: Load your own documents for analysis.
- **Configurable Parameters**: Adjust chunk size, overlap, and top-k retrieval.
- **Real-time Feedback**: View processing messages and retrieved text chunks.
- **Knowledge Graph**: Visualize the relationships between document chunks in a dedicated tab.
- **Local LLM**: Powered by `TinyLlama-1.1B-Chat` for efficient local inference.

## How to use
1. Upload a PDF file in the sidebar.
2. Wait for the indexing to finish (you'll see progress messages).
3. Ask questions in the "Q&A Interface" tab.
4. Explore the document structure in the "Knowledge Graph" tab.