Edit Reading

Back to List

Basic Information

Title

Please enter a title.

URL

Please enter a valid URL.

Date

カテゴリID

画像ファイル名

単語数（空欄の場合は本文から自動計算）空欄の場合は本文から自動計算されます。本文が空欄の場合は既存の値が保持されます。

統計情報

現在の単語数: 246語

読了回数: 1回

作成日: 2025/10/17 12:11

更新日: 2025/12/08 00:06

本文

RAG-Anything: All-in-One RAG Framework
Published on Oct 14

Submitted by
Xubin Ren
on Oct 15
hkuds
Data Intelligence Lab@HKU

Authors:
Zirui Guo
,
Xubin Ren
,
Lingrui Xu
,
Jiahao Zhang
,
Chao Huang
Abstract

RAG-Anything is a unified framework that enhances multimodal knowledge retrieval by integrating cross-modal relationships and semantic matching, outperforming existing methods on complex benchmarks.
Retrieval-Augmented Generation (RAG) has emerged as a fundamental paradigm for expanding Large Language Models beyond their static training limitations. However, a critical misalignment exists between current RAG capabilities and real-world information environments. Modern knowledge repositories are inherently multimodal, containing rich combinations of textual content, visual elements, structured tables, and mathematical expressions. Yet existing RAG frameworks are limited to textual content, creating fundamental gaps when processing multimodal documents. We present RAG-Anything, a unified framework that enables comprehensive knowledge retrieval across all modalities. Our approach reconceptualizes multimodal content as interconnected knowledge entities rather than isolated data types. The framework introduces dual-graph construction to capture both cross-modal relationships and textual semantics within a unified representation. We develop cross-modal hybrid retrieval that combines structural knowledge navigation with semantic matching. This enables effective reasoning over heterogeneous content where relevant evidence spans multiple modalities. RAG-Anything demonstrates superior performance on challenging multimodal benchmarks, achieving significant improvements over state-of-the-art methods. Performance gains become particularly pronounced on long documents where traditional approaches fail. Our framework establishes a new paradigm for multimodal knowledge access, eliminating the architectural fragmentation that constrains current systems. Our framework is open-sourced at: https://github.com/HKUDS/RAG-Anything.

メモ

メモ・感想

キャンセル

Edit Reading

Basic Information

統計情報

本文

メモ

Send Report