David-Lolly/ViewRAG
图文并茂的 PDF RAG 系统：支持版式感知分块、图表深度理解与精准视觉溯源。 Multimodal PDF RAG: Features layout-aware chunking, visual chart understanding, and precise inline image citations.
This tool helps professionals working with PDFs to quickly get answers to their questions, even when the information is in images or tables. You input PDF documents and ask questions in natural language, and it provides accurate answers with inline images and precise citations to the original document pages. Anyone who regularly needs to extract information from complex PDFs, like researchers, analysts, or legal professionals, would find this valuable.
Use this if you need to understand and extract detailed information from PDFs, including content locked in images and tables, and require traceable, trustworthy answers.
Not ideal if your workflow involves only plain text documents or if you primarily need to summarize very short, simple texts without complex layouts.
Stars
21
Forks
4
Language
Python
License
MIT
Category
Last pushed
Feb 27, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/David-Lolly/ViewRAG"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
thiswillbeyourgithub/wdoc
Summarize and query from a lot of heterogeneous documents. Any LLM provider, any filetype,...
Arterning/DeepParseX
DeepParseX 是一个强大的多模态文档解析与知识管理平台，支持 PDF、Word、Excel、PPT、图片、视频、音频 等多种文件格式的智能解析，自动提取关键信息，并构建...
NoEdgeAI/pdfdeal
A python wrapper for the Doc2X API and comes with native texts processing (to improve PDF recall...
laxmimerit/RAGWire
Production-grade RAG toolkit — ingest PDFs, DOCX, XLSX into Qdrant with LLM metadata extraction,...
atpuxiner/docsloader
This is a documents loader. (文档解析加载器，rag文档解析，rag知识库构建)