# parthsarthi03/raptor

The official implementation of RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval

Repository: https://github.com/parthsarthi03/raptor
Canonical: https://ross.abutalabs.com/products/parthsarthi03-raptor
Homepage: https://arxiv.org/abs/2401.18059
Language: Python
License: MIT
License Family: permissive
Topics: rag, retrieval, retrieval-augmented-generation, clustering, language-model, machine-learning, vector-database, agents, framework, llm
Last push: 2024-09-03T08:34:31+00:00

## Health v2 (maintenance only)
Score: 25/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 65
- inputs: {"age_days": 919, "days_push": 729, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1750, forks 234 (observed 2026-08-28T04:05:31.083212+00:00)

## What it is
The official Python implementation of RAPTOR (Recursive Abstractive Processing for Tree-Organized Retrieval), a retrieval-augmented generation method from an arXiv paper. It recursively embeds, clusters, and summarizes document chunks into a multi-level tree, then retrieves from that tree at query time to answer questions with context spanning different levels of abstraction.

## Use cases
- improve rag retrieval over long documents
- answer questions that require multi-step reasoning across a whole document
- build recursive hierarchical summaries of text for retrieval
- implement tree-organized retrieval in python
- get document-level context instead of short contiguous chunks
- question answering on benchmarks like QuALITY with GPT-4

## When to choose
- You need retrieval that captures holistic document context rather than isolated chunks
- You are doing long-document or multi-hop question answering where standard RAG underperforms
- You want a programmable RAG layer where you can swap in custom summarization, embedding, or QA models

## When to avoid
- You need a production RAG platform with ingestion pipelines, connectors, and UIs out of the box
- Your corpus is small or short documents where plain chunk retrieval already suffices and tree-building LLM costs are not justified
- You want a no-code turnkey search product rather than a library to integrate into your code

## Facets
- artifact type: library
- maturity: active
- function: rag, machine-learning, nlp, search-engine
- domain: artificial-intelligence, machine-learning, large-language-models
- platform: python
- tags: retrieval-augmented-generation, tree-structured-retrieval, recursive-summarization, hierarchical-clustering, question-answering, long-document-retrieval, research-paper-implementation, document-indexing, natural-language-processing, search

## Member repositories
- parthsarthi03/raptor (main) score 25

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:31.083212+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 2026-08-30T03:28:45.350708+00:00, confidence not recorded.
  - readme: https://github.com/parthsarthi03/raptor (fetched 2026-08-28T04:05:31.083212+00:00, sha 5aae6d8f3bb1)
  - homepage: https://arxiv.org/abs/2401.18059 (fetched 2026-08-29T11:06:37.393410+00:00, sha 986f3971f21f)
  - site_page: https://info.arxiv.org/about/donate.html (fetched 2026-08-29T11:06:37.396243+00:00, sha cca9c3a11c56)
  - site_page: https://info.arxiv.org/about/ourmembers.html (fetched 2026-08-29T11:06:37.399710+00:00, sha 47cbc55ff1de)
  - site_page: https://info.arxiv.org/about (fetched 2026-08-29T11:06:37.401612+00:00, sha a1f16f915a9a)
  - site_page: https://info.arxiv.org/labs/index.html (fetched 2026-08-29T11:06:37.398079+00:00, sha b14a8d05a0ec)
- Data as of 2026-08-30T08:39:29.467469+00:00.