DEDUPED Hot AI repos. Real use cases. What people build. Get the Monday 5

How to use Ragflow: what you can do with it

What is Ragflow? RAGFlow is an open-source Retrieval-Augmented Generation engine that fuses RAG with agent capabilities to build a context layer for LLMs. It offers deep document understanding of complex formats, template-based chunking you can inspect, Knowledge Compilation into Wikis, Graphs, Trees and Mind Maps, Agentic Retrieval with Low to Ultra thinking modes, and grounded answers with traceable citations, deployed with Docker or from source.

How do I use it? Clone the repo with git clone https://github.com/infiniflow/ragflow.git and enter the folder with cd ragflow/docker; then check out the release tag with git checkout v1.0.0-rc3; start the services with docker compose -f docker-compose.yml up -d. Full steps below.

Trended earlier

View repo on GitHub

Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer

What do you want to do?

3 use cases

  • Self-host a chat-with-your-documents engine

    Start RAGFlow with Docker Compose, connect your models and ask questions over your own files.

    View prompt
    Deploy infiniflow/ragflow on this server with Docker Compose at tag v1.0.0-rc3, wait until the healthz endpoint returns 200, and tell me the URL to open. List what I still need to configure on the model provider page.

  • See and fix how your documents are chunked

    Use RAGFlow's chunk visualization and templates so retrieval finds the right passages.

    View prompt
    In my infiniflow/ragflow instance, upload <document>, try two chunking templates, and compare how each splits <section>. Recommend the template that keeps <section> intact and explain why.

  • Answer multi-step questions with agentic retrieval

    Turn on Agentic Retrieval so the model breaks down a hard question, retrieves several times and checks evidence.

    View prompt
    In infiniflow/ragflow, enable Agentic Retrieval on dataset <name> and ask <question> at Medium and then High thinking mode. Compare the two answers and their citations and tell me which is better supported.

Quick start with Ragflow

  1. Check you have what it needs: Docker 24.0.0 or later and Docker Compose v2.26.1 or later; A starting machine of 4 CPU cores, 16 GB RAM and 50 GB free disk; An LLM, an embedding model and a reranker, added with their service address and API key after sign-in.
  2. Open infiniflow/ragflow on GitHub and read the README and license.
  3. Clone the repo with git clone https://github.com/infiniflow/ragflow.git and enter the folder with cd ragflow/docker
  4. Check out the release tag with git checkout v1.0.0-rc3
  5. Start the services with docker compose -f docker-compose.yml up -d
  6. Confirm it is ready with curl -f http://localhost/api/v1/system/healthz, and check logs with docker logs --tail 50 ragflow-cpu if it is not

These steps come from our top use case, Self-host a chat-with-your-documents engine, which also has a copy-paste agent prompt.

Use this in your AI agent

Ask your agent

Using the Deduped MCP, get the setup steps for infiniflow/ragflow

Add Deduped to Claude Code once

claude mcp add --transport http deduped https://dedupedai.com/mcp

Cursor, ChatGPT, others

Best AI repos for Research

About this repo

  • Who it is forTeams and builders who want a self-hosted question-answering system over their own documents, with citations they can check.
  • Why it is hot93k stars, talked about in 2 AI sources we track
  • LanguageGo
  • Sourcegithub.com/infiniflow/ragflow ยท Back to Hot repos

Requirements

  • Docker 24.0.0 or later and Docker Compose v2.26.1 or later
  • A starting machine of 4 CPU cores, 16 GB RAM and 50 GB free disk
  • An LLM, an embedding model and a reranker, added with their service address and API key after sign-in
  • If you use Elasticsearch, vm.max_map_count set to at least 262144

Add this badge to your README

Maintain Ragflow? Show readers where to find these use cases. Use cases on Deduped

Markdown 

[![Use cases on Deduped](https://dedupedai.com/badge/infiniflow/ragflow.svg)](https://dedupedai.com/use-cases/infiniflow-ragflow/?utm_source=github&utm_medium=badge&utm_campaign=infiniflow-ragflow)

HTML 

<a href="https://dedupedai.com/use-cases/infiniflow-ragflow/?utm_source=github&amp;utm_medium=badge&amp;utm_campaign=infiniflow-ragflow"><img src="https://dedupedai.com/badge/infiniflow/ragflow.svg" alt="Use cases on Deduped" height="20"></a>

A static image, no tracking script. About the badge

Questions about Ragflow

What is Ragflow?

RAGFlow is an open-source Retrieval-Augmented Generation engine that fuses RAG with agent capabilities to build a context layer for LLMs. It offers deep document understanding of complex formats, template-based chunking you can inspect, Knowledge Compilation into Wikis, Graphs, Trees and Mind Maps, Agentic Retrieval with Low to Ultra thinking modes, and grounded answers with traceable citations, deployed with Docker or from source. It is an open-source project on GitHub: https://github.com/infiniflow/ragflow.

How do I use Ragflow?

Clone the repo with git clone https://github.com/infiniflow/ragflow.git and enter the folder with cd ragflow/docker; then check out the release tag with git checkout v1.0.0-rc3; start the services with docker compose -f docker-compose.yml up -d. The use cases on this page give the full steps and a copy-paste agent prompt for each job.

Who is Ragflow for?

Teams and builders who want a self-hosted question-answering system over their own documents, with citations they can check.

What can I do with Ragflow?

3 use cases so far, for example: Self-host a chat-with-your-documents engine; See and fix how your documents are chunked; Answer multi-step questions with agentic retrieval. Each has steps and a copy-paste agent prompt.

What do I need to run Ragflow?

Docker 24.0.0 or later and Docker Compose v2.26.1 or later; A starting machine of 4 CPU cores, 16 GB RAM and 50 GB free disk; An LLM, an embedding model and a reranker, added with their service address and API key after sign-in; If you use Elasticsearch, vm.max_map_count set to at least 262144.

What are alternatives to Ragflow?

Other hot AI repos in Research: Sam2, Docling, LightRAG, Markitdown, MinerU.

Is Ragflow safe to run?

Deduped does not own, audit or vouch for it. Read the README and license, run it on your own systems first and review every command before you run it.