Library/raptorForked

parthsarthi03/raptor

raptor

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

View on GitHub↗Upstream parthsarthi03/raptor↗

Builder

parthsarthi03

parthsarthi03 • individual

Stars

1,633

Using upstream star count

Forks

216

Using upstream fork count

Open Issues

Activity Score

0/100

0 commits in 30d

Created

Feb 27, 2024

Project creation date

README Summary

RAPTOR is a retrieval system that builds tree structures from documents by recursively clustering and summarizing text chunks at multiple levels of abstraction. It enables more effective retrieval-augmented generation by allowing queries to match against both specific details and high-level summaries organized in a hierarchical tree structure.

AI Dev Skills

Unmapped

Retrieval-Augmented GenerationDocument ClusteringRecursive Text SummarizationHierarchical Information RetrievalTree-based Data StructuresEmbedding-based Similarity SearchMulti-level Text Abstraction

Taxonomy

AI Trends

Compound AI Systems Advanced RAG Architectures Hierarchical Knowledge Representation

Deployment Context

Self-hosted Cloud API

Modalities

Text

Skill Areas

Retrieval-Augmented Generation Document Clustering Recursive Text Summarization Hierarchical Information Retrieval Tree-based Data Structures Embedding-based Similarity Search Multi-level Text Abstraction

Use Cases

Long Document Question Answering Multi-document Information Synthesis Hierarchical Document Search Academic Paper Analysis Legal Document Retrieval

Recent Activity

Updated 1 years ago

7 Days

30 Days

90 Days

Quality

research

Quality: medium
Maturity: research

PM Skills

Developer Platform

Languages

Python100.0%

Timeline

Project created: Feb 27, 2024
Forked: Mar 29, 2026
Your last push: 1 years ago
Upstream last push: 1 years ago
Tracked since: Sep 3, 2024

Similar Repos

pgvector cosine similarity · $0

Loading…