# gabrielchua/RAGxplorer

Open-source tool to visualise your RAG 🔮

Repository: https://github.com/gabrielchua/RAGxplorer
Canonical: https://ross.abutalabs.com/products/ragxplorer
Language: Jupyter Notebook
License: MIT
License Family: permissive
Topics: llm, python, rag, streamlit, visualization, interactive
Last push: 2025-01-03T15:10:06+00:00

## Health v2 (maintenance only)
Score: 16/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 8, longevity 68
- inputs: {"age_days": 965, "days_push": 607, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1220, forks 112 (observed 2026-08-28T04:04:01.847336+00:00)

## What it is
RAGxplorer is a Python library and hosted Streamlit app for visualizing Retrieval Augmented Generation pipelines. It chunks PDFs, embeds them, and plots the chunks in an interactive space so you can see which documents are retrieved for a query.

## Use cases
- visualize rag retrieval results
- debug which chunks a query retrieves
- explore embeddings of pdf documents in 2d
- understand chunking and retrieval for a rag pipeline
- demo rag retrieval interactively in streamlit

## When to choose
- you want to inspect or explain how a RAG system retrieves chunks
- you need a quick interactive visualization of embeddings and retrieval
- you are teaching or learning how RAG retrieval works

## When to avoid
- you need a production RAG framework rather than a visualization tool
- your documents are not PDFs or simple text
- you need heavy customization of embedding or retrieval backends

## Facets
- artifact type: library
- maturity: active
- function: rag, data-visualization, machine-learning, pdf
- domain: large-language-models, data-visualization, machine-learning
- platform: python
- tags: streamlit, embeddings, chunking, jupyter-notebook, developer-tools, retrieval-augmented-generation, web

## Member repositories
- gabrielchua/RAGxplorer (main) score 16

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:01.847336+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:16:00.621222+00:00, confidence not recorded.
  - readme: https://github.com/gabrielchua/RAGxplorer (fetched 2026-08-28T04:04:01.847336+00:00, sha 8ae2cd53e507)
  - registry_pypi: https://pypi.org/pypi/ragxplorer/json (fetched 2026-08-29T12:24:36.919267+00:00, sha 362f24ee6e00)
- Data as of 2026-08-30T08:39:29.467469+00:00.