https://github.com/gabrielchua/ragxplorer

Open-source tool to visualise your RAG 🔮
https://github.com/gabrielchua/ragxplorer

interactive llm python rag streamlit visualization

Last synced: 10 months ago
JSON representation

Open-source tool to visualise your RAG 🔮

• Host: GitHub
• URL: https://github.com/gabrielchua/ragxplorer
• Owner: gabrielchua
• License: mit
• Created: 2024-01-11T15:31:36.000Z (about 2 years ago)
• Default Branch: main
• Last Pushed: 2025-01-03T15:10:06.000Z (about 1 year ago)
• Last Synced: 2025-04-12T05:58:36.823Z (10 months ago)
• Topics: interactive, llm, python, rag, streamlit, visualization
• Language: Jupyter Notebook
• Homepage:
• Size: 1.07 MB
• Stars: 1,120
• Watchers: 10
• Forks: 101
• Open Issues: 7
• Metadata Files:
  • Readme: README.md
  • Contributing: .github/CONTRIBUTING.md
  • License: LICENSE
  • Code of conduct: .github/CODE_OF_CONDUCT.md
  • Citation: CITATION.cff

Awesome Lists containing this project

README

          
# RAGxplorer 🦙🦺

[![PyPI version](https://img.shields.io/pypi/v/ragxplorer.svg)](https://pypi.org/project/ragxplorer/)

[![Streamlit App](https://static.streamlit.io/badges/streamlit_badge_black_white.svg)](https://ragxplorer.streamlit.app/)



RAGxplorer is a tool to build Retrieval Augmented Generation (RAG) visualisations.

# Quick Start ⚡

**Installation**

```bash

pip install ragxplorer

```

**Usage**

```python

from ragxplorer import RAGxplorer

client = RAGxplorer(embedding_model="thenlper/gte-large")

client.load_pdf("presentation.pdf", verbose=True)

client.visualize_query("What are the top revenue drivers for Microsoft?")

```

A quickstart Jupyter notebook tutorial on how to use `ragxplorer` can be found at 

Or as a Colab notebook:



  



# Streamlit Demo 🔎

The demo can be found here: 



View the project [here](https://github.com/gabrielchua/RAGxplorer-demo)

# Contributing 👋

Contributions to RAGxplorer are welcome. Please read our [contributing guidelines (WIP)](.github/CONTRIBUTING.md) for details.

# License 👀

This project is licensed under the MIT license - see the [LICENSE](LICENSE) for details.

# Acknowledgments 💙

- DeepLearning.AI and Chroma for the inspiration and code labs in their [Advanced Retrival](https://www.deeplearning.ai/short-courses/advanced-retrieval-for-ai/) course.

- The Streamlit community for the support and resources.