# HKUDS/RAG-Anything

"RAG-Anything: All-in-One RAG Framework"

Repository: https://github.com/HKUDS/RAG-Anything
Canonical: https://ross.abutalabs.com/products/rag-anything
Homepage: http://arxiv.org/abs/2510.12323
Language: Python
License: MIT
License Family: permissive
Topics: multi-modal-rag, retrieval-augmented-generation
Last push: 2026-08-20T11:39:08+00:00

## Health v2 (maintenance only)
Score: 80/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 98, release rhythm 84, longevity 32
- inputs: {"age_days": 453, "days_push": 13, "days_rel": 104, "gap_med": 7.0, "n_releases_24m": 19}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 23081, forks 2673 (observed 2026-08-28T04:11:34.386102+00:00)

## What it is
RAG-Anything is an all-in-one Python framework for multimodal Retrieval-Augmented Generation, built on LightRAG. It treats text, images, tables, and equations in documents as interconnected knowledge entities and uses dual-graph construction with cross-modal hybrid retrieval to answer queries over heterogeneous content.

## Use cases
- build a RAG pipeline over multimodal documents with images and tables
- query PDFs containing figures, tables, and equations with an LLM
- index long documents for retrieval-augmented question answering
- extract and search knowledge across text and visual content
- add multimodal retrieval to a chatbot or knowledge base
- run graph-based RAG over research papers or reports

## When to choose
- your documents mix text with images, tables, and math expressions
- you want a ready-made multimodal RAG framework based on LightRAG
- traditional text-only RAG fails on long or visually rich documents

## When to avoid
- you only need simple text-only RAG with minimal dependencies
- you need a fully managed hosted RAG service rather than a Python framework
- your project is not Python-based

## Facets
- artifact type: framework
- maturity: active
- function: rag, llm-inference, parser, search-engine, machine-learning
- domain: large-language-models, artificial-intelligence, pdf
- platform: python, cross-platform
- tags: multimodal-rag, knowledge-graph, document-parsing, lightrag, dual-graph-retrieval, retrieval-augmented-generation, natural-language-processing

## Member repositories
- HKUDS/RAG-Anything (main) score 80

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:34.386102+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 2026-08-29T16:56:48.208210+00:00, confidence not recorded.
  - readme: https://github.com/HKUDS/RAG-Anything (fetched 2026-08-28T04:11:34.386102+00:00, sha 933ecd023cf4)
  - homepage: http://arxiv.org/abs/2510.12323 (fetched 2026-08-29T07:54:48.168890+00:00, sha a3d08ce0c2a9)
  - site_page: https://info.arxiv.org/about/donate.html (fetched 2026-08-29T07:54:48.172692+00:00, sha cca9c3a11c56)
  - site_page: https://info.arxiv.org/about/ourmembers.html (fetched 2026-08-29T07:54:48.176152+00:00, sha 47cbc55ff1de)
  - site_page: https://info.arxiv.org/about (fetched 2026-08-29T07:54:48.178032+00:00, sha a1f16f915a9a)
  - site_page: https://info.arxiv.org/labs/index.html (fetched 2026-08-29T07:54:48.174479+00:00, sha b14a8d05a0ec)
- Data as of 2026-08-30T08:39:29.467469+00:00.