Skip to main content

A open-source tool to to visualise your RAG documents 🔮.

Project description

RAGxplorer 🦙🦺

PyPI version Streamlit App

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

Quick Start ⚡

Installation

pip install ragxplorer

Usage

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 https://github.com/gabrielchua/RAGxplorer/blob/main/tutorials/quickstart.ipynb

Or as a Colab notebook:

Open In Colab

Streamlit Demo 🔎

The demo can be found here: https://ragxplorer.streamlit.app/

View the project here

Contributing 👋

Contributions to RAGxplorer are welcome. Please read our contributing guidelines (WIP) for details.

License 👀

This project is licensed under the MIT license - see the LICENSE for details.

Acknowledgments 💙

  • DeepLearning.AI and Chroma for the inspiration and code labs in their Advanced Retrival course.
  • The Streamlit community for the support and resources.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distributions

No source distribution files available for this release.See tutorial on generating distribution archives.

Built Distribution

ragxplorer-0.1.10-py3-none-any.whl (11.2 kB view details)

Uploaded Python 3

File details

Details for the file ragxplorer-0.1.10-py3-none-any.whl.

File metadata

  • Download URL: ragxplorer-0.1.10-py3-none-any.whl
  • Upload date:
  • Size: 11.2 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.11.5

File hashes

Hashes for ragxplorer-0.1.10-py3-none-any.whl
Algorithm Hash digest
SHA256 467ea49d10c60e7b9821ee2dd674691850b27dd28ea3d61d752cba4b55e3764d
MD5 7c5fb14fa9bc74bfcb7f46dc90e4dedb
BLAKE2b-256 0858c1540e5b6de0e12846aab64feb5f97bd9a05cb9a325e531f0e6387790bd8

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page