24,594
stars
2,881
forks
116
watchers
295
prs
172
issues
24
releases
README
🚀 RAG-Anything: All-in-One RAG Framework
---
🎉 News
- [X] [2026.06]🎯📢 🎉 LightRAG enables multimodal RAG through native integration of RAG-Anything.
- [X] [2025.10]🎯📢 🚀 We have released the technical report of RAG-Anything. Access it now to explore our latest research findings.
- [X] [2025.08]🎯📢 🔍 RAG-Anything now features VLM-Enhanced Query mode! When documents include images, the system seamlessly integrates them into VLM for advanced multimodal analysis, combining visual and textual context for deeper insights.
- [X] [2025.07]🎯📢 RAG-Anything now features a context configuration module, enabling intelligent integration of relevant contextual information to enhance multimodal content processing.
- [X] [2025.07]🎯📢 🚀 RAG-Anything now supports multimodal query capabilities, enabling enhanced RAG with seamless processing of text, images, tables, and equations.
- [X] [2025.07]🎯📢 🎉 RAG-Anything has reached 1k🌟 stars on GitHub! Thank you for your incredible support and valuable contributions to the project.
---
🌟 System Overview
Next-Generation Multimodal Intelligence
Modern documents increasingly contain diverse multimodal content—text, images, tables, equations, charts, and multimedia—that traditional text-focused RAG systems cannot effectively process. RAG-Anything addresses this challenge as a comprehensive All-in-One Multimodal Document Processing RAG system built on LightRAG.
As a unified solution, RAG-Anything eliminates the need for multiple specialized tools. It provides seamless processing and querying across all content modalities within a single integrated framework. Unlike conventional RAG approaches that struggle with non-textual elements, our all-in-one system delivers comprehensive multimodal retrieval capabilities.
Users can query documents containing interleaved text, visual diagrams, structured tables, and mathematical formulations through one cohesive interface. This consolidated approach makes RAG-Anything particularly valuable for academic research, technical documentation, financial reports, and enterprise knowledge management where rich, mixed-content documents demand a unified processing framework.
🎯 Key Features
- 🔄 End-to-End Multimodal Pipeline - Complete workflow from document ingestion and parsing to intelligent multimodal query answering
- 📄 Universal Document Support - Seamless processing of PDFs, Office documents, images, and diverse file formats
- 🧠 Specialized Content Analysis - Dedicated processors for images, tables, mathematical equations, and heterogeneous content types
- 🔗 Multimodal Knowledge Graph - Automatic entity extraction and cross-modal relationship discovery for enhanced understanding
- ⚡ Adaptive Processing Modes - Flexible MinerU-based parsing or direct multimodal content injection workflows
- 📋 Direct Content LiTop issues
#70[Question]:Image is not analyzed properly10 comments · 2025-07-29#49[Question]: Not able to Process documents, Document Processing stuck9 comments · 2025-07-09#235[Question]:Consultation on the 63.4% accuracy on DocBench8 comments · 2026-04-02#69[Question]: raganything_example.py 改写为ollama下的模型时出现的问题7 comments · 2025-07-29#146[Question]:能够支持本地模型了吗6 comments · 2025-10-24#50[Question]:ImportError: cannot import name 'LightRAG' from 'lightrag' (unknown location)5 comments · 2025-07-10#48[Question]: Is it normal for documents to take a while to process?5 comments · 2025-07-08#26[Question]: How to Customize the Prompt for Knowledge Graph Generation in RAGAnything?5 comments · 2025-07-02
Discussions
#492Chopper: a small open model that cuts only the needed sentences out of retrieved text0 comments · 2026-11-16#378A hard dollar limit on one RAG-Anything ingestion job (text + vision calls)0 comments · 2026-10-03#245File Metadata and Filtering2 comments · 2026-04-19#229Example code but using ollama2 comments · 2026-03-23#194Are there any plans to integrate RAG-Anything into LightRAG server?0 comments · 2026-02-08#193Need a help!!!! Why I always get this connection problem1 comments · 2026-01-23#192Feature Discussion: Audio Transcription Support1 comments · 2026-01-20#179加载已有的RAG库时报错。0 comments · 2025-12-23
Latest release
v1.4.4 v1.4.4 2026-10-28MinerU compatibility RAG-Anything now requires MinerU =3.4.1,<4 on Python 3.10–3.13. MinerU 4 replaced the CLI used by this integration. The parser now rejects incompatible versions at initialization and includes the actual command output and repair advice in errors (449). On Python 3.14, install RAG-Anything with Docling and select parser="docling", or use Python 3.13 for MinerU. MinerU 3.x cannot be installed on Python 3.14, so this release excludes that dependency there. The configured parser is checked at initialization, including operations that insert pre-parsed content. For existing