RAG-Anything

RAG / Q&A

HKUDS/RAG-Anything

24.0K2.8KPythonMIT

Reads PDFs, images, tables and formulas together, turning them into a searchable knowledge base for building multimodal question-answering apps.

🏷️ PDF Processing🏗️ Agent Building🔌 API Integration🏠 Local Runtime

RAG-Anything preview — Preview card generated by GitHub from the repository. Star counts on the card may lag behind the figures above.

Tool Info

Type🐙 Open Source

Stars24.0K

Forks2.8K

LanguagePython

LicenseMIT

Unlock the full analysis — free

You're reading the public preview of RAG-Anything. The AI-written pros & cons, use cases, setup guide and audience fit are free with an account — no credit card. Pro adds AI comparisons (50 per 30 days) and member daily & weekly reports.

Compare RAG-Anything with alternatives

See how it stacks up against other rag / q&a tools.

More Tools

ragflow

92.6K

RAGFlow is an open-source retrieval-augmented generation engine that enables large models to answer questions accurately based on your private documents.

headroom

77.2K

Automatically compress text before sending it to large models, saving a lot on token fees without changing answer quality.

open-notebook

40.4K

An open-source alternative to Notebook LM. Upload materials and let AI help you summarize, answer questions, and take notes.

LightRAG

40.3K

An open-source tool that lets AI answer questions based on your own documents and automatically organizes knowledge graphs.

PageIndex

39.4K

Turns long documents into a tree-like outline so AI can follow the structure and reason its way to answers, without vector search.