zstar1003/ragflow-plus

Ragflow-Plus 是 Ragflow 的二次开发版本，使其更为简洁实用

What it solves

Ragflow-Plus is a specialized version of Ragflow designed for practical, industry-specific applications, particularly in Chinese language contexts. It addresses gaps in original Ragflow by adding administrative controls, improving document parsing, and enhancing the user interface for specific workflows like document writing.

How it works

The project is a secondary development of Ragflow, integrating several key enhancements:

  • Administrative Backend: Adds a management system for administrators to handle users, teams, configurations, and knowledge bases.
  • Parsing Improvements: Replaces the DeepDoc algorithm with MinerU to improve file parsing quality and add support for image parsing.
  • Multimodal Output: Enables the AI model to output images associated with the referenced text blocks during answers.
  • Interface Simplification: Restricts user permissions in the frontend to create a simpler, more focused user experience.
  • Document Mode: Introduces a new interaction experience specifically for document writing.

Who it’s for

Organizations and developers who need a more robust, administrative-ready RAG (Retrieval-Augmented Generation) system tailored for Chinese application scenarios.

Highlights

  • Enhanced Parsing: Uses MinerU for better document and image parsing.
  • Citations with Images: Supports outputting images linked to cited text blocks.
  • Management System: Dedicated backend for user, team, and configuration management.
  • Specialized Interaction: Includes a dedicated document writing mode.

Related

  • Project
    infiniflow/ragflow

    An open-source RAG engine that combines deep document understanding and agentic capabilities to create a high-fidelity context layer for LLMs using complex unstructured data.

  • Project
    langflow-ai/openrag

    An intelligent agent-powered document search platform that enables users to upload, process, and query documents through a chat interface using RAG.

  • Project
    DevYangJC/Argus

    Argus is an open‑source, enterprise‑grade RAG platform that ingests private documents, builds both vector and keyword indexes, and answers questions with a LLM that must cite real sources. It includes a Spring AI‑based ReactAgent for chat, hybrid retrieval with RRF fusion, multi‑level evidence scoring, role‑based security, and a Vue 3 front‑end.

  • Project
    rag-web-ui/rag-web-ui

    An intelligent dialogue system that allows users to build custom Q&A services by combining their own document knowledge bases with LLMs using Retrieval-Augmented Generation.

  • Project
    Farzad-R/LLM-Zero-to-Hundred

    A collection of LLM projects and tutorials covering RAG, agentic workflows, multimodal chatbots, and fine-tuning pipelines to move from basic to advanced AI application development.