RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval

Repositoryparthsarthi03/raptorResearch

RAPTOR provides the official Python implementation of a tree-based RAG framework that recursively clusters and summarises documents, improving retrieval quality across large texts.

Key points

  1. Constructs recursive tree structures from texts to provide retrieval at multiple levels of abstraction.
  2. Addresses limitations of traditional RAG systems when handling holistic queries across long documents.
  3. Requires Python 3.8+ and uses OpenAI models by default, with interfaces to extend or swap underlying models.
  4. Supports saving and loading indexed tree structures to disk.

Why it matters

Conventional vector retrieval often struggles with questions requiring high-level context across an entire corpus. RAPTOR's hierarchical approach aggregates information across multiple levels of abstraction to address this limitation.

Analysis

The project serves as the official reference implementation for the research paper (arXiv:2401.18059). Released under the MIT license with over 1,700 GitHub stars, it provides a solid foundation for research and advanced RAG experiments, although parts of the advanced documentation remain marked as in-progress.

Mentioned links

Summary generated by AI (Gemini 3.8 Flash, 27 September 2026). It may contain errors – the original source is authoritative.

Related entries

Similar in content, found by the AI search.

  • Repository:OSU-NLP-Group/HippoRAG

    HippoRAG 2: Neurobiologically Inspired Memory Framework for LLMs

    HippoRAG (now in version 2) is an open-source memory framework for LLMs developed by the OSU NLP Group, combining knowledge graphs and Personalized PageRank to mimic human long-term memory across external documents.

    4kstarsPython

    AI & LLMs· Research

  • Repository:OpenSPG/KAG

    OpenSPG/KAG: Logic-Form Guided Reasoning and Retrieval Beyond Standard RAG

    KAG (Knowledge Augmented Generation) is an open-source framework combining LLMs with the OpenSPG engine. It aims to address the limitations of vector similarity in standard RAG and noise in OpenIE-based GraphRAG for domain-specific applications.

    9kstarsPython

    AI & LLMs· Tool

  • Repository:HuskyInSalt/CRAG

    CRAG: Corrective Retrieval Augmented Generation for Robust LLM Outputs

    CRAG (Corrective Retrieval Augmented Generation) is an open-source research framework designed to improve RAG reliability. It evaluates the quality of retrieved context using a lightweight evaluator and triggers corrective actions, such as web searches or text filtering, when confidence is low.

    469starsPython

    AI & LLMs· Research

  • Link:docling.ai

    Docling: Open-Source Document Intelligence for AI and RAG

    Docling is an open-source tool hosted by LF AI & Data that converts complex documents like PDFs, Office files, and images into structured data for AI applications. It operates locally and fully offline, preserves layouts and table structures, and provides interfaces for Python, CLI, REST APIs, and MCP.

    AI & LLMs· Tool

  • Repository:docling-project/docling

    Docling: Document Parsing for Generative AI

    Docling is an open-source Python tool designed to parse documents across multiple formats—such as PDF, office files, audio, and HTML—to prepare them for generative AI workflows.

    66kstarsPython

    AI & LLMs· Tool

Back to the knowledge base

Let's talk about your project

Get in touch

Locations

  • Mattersburg
    Johann Nepomuk Bergerstraße 7/2/14
    7210 Mattersburg, Austria
  • Vienna
    Ungargasse 64-66/3/404
    1030 Wien, Austria

Parts of this content were created with the assistance of AI.