Repolode
Submit
infiniflow

infiniflow/ragflow

Open-source RAG engine that pairs retrieval-augmented generation with agent capabilities to provide a context layer for LLM applications.

View on GitHubWebsite
Stars
92,517
Forks
11,047
Open issues
1,346
Last commit
6 hours ago

What is it?

RAGFlow is an open-source retrieval-augmented generation engine. It ingests documents from many formats, parses and chunks them with configurable templates, and indexes the results so that LLM applications can answer questions grounded in that material with traceable citations.

Beyond basic RAG, it adds agentic retrieval, where the model breaks down complex questions, runs multiple retrieval rounds and checks evidence, plus a Knowledge Compilation step that turns documents and datasets into wikis, graphs, trees, mind maps and other structured artifacts. Chunks can be reviewed and edited by hand before they are used.

RAGFlow provides a web UI, a set of APIs for integration, and Docker-based deployment, with support for configurable LLM, embedding and reranker models. It can also be run from source for development.

Key features

  • 01Deep document parsing for Word, PowerPoint, Excel, PDF, scanned files, images and web pages.
  • 02Template-based chunking with visual preview and manual intervention.
  • 03Agentic retrieval with Low, Medium, High and Ultra thinking modes.
  • 04Knowledge Compilation into wikis, graphs, trees, mind maps and timelines.
  • 05Traceable citations to support grounded answers.
  • 06Configurable LLM, embedding and reranker models with multi-recall and fused re-ranking.

Use cases

  • Building an internal question-answering assistant over company documents and manuals.
  • Creating a knowledge base from scanned or mixed-format files with citation support.
  • Connecting enterprise data sources such as cloud storage or BigQuery for ongoing synchronization.
  • Integrating retrieval-based answers into existing applications through its APIs.

Quick start

  1. 1

    Clone the repository

    git clone https://github.com/infiniflow/ragflow.git
  2. 2

    Enter the Docker deployment directory

    cd ragflow/docker
  3. 3

    Start the RAGFlow services with Docker Compose

    docker compose -f docker-compose.yml up -d
  4. 4

    Check that the server is ready using the health endpoint, then open the Web UI in your browser

    curl -f http://localhost/api/v1/system/healthz

Things to know

  • The README recommends at least 4 CPU cores, 16 GB RAM and 50 GB of disk space.
  • macOS is not currently supported for Docker deployment, according to the README.
  • The latest release is a release candidate (1.0.0-rc1), so it may still change.
  • After startup you must add your own LLM, embedding and reranker models with API keys.

Topics

#rag#retrieval-augmented-generation#llm#agents#document-parsing#knowledge-base#vector-search#docker#agent-harness#agentic-ai

FAQ

What is ragflow?
Open-source RAG engine that pairs retrieval-augmented generation with agent capabilities to provide a context layer for LLM applications. RAGFlow is an open-source retrieval-augmented generation engine. It ingests documents from many formats, parses and chunks them with configurable templates, and indexes the results so that LLM applications can answer questions grounded in that material with traceable citations.
Is ragflow free to use? What license does it have?
ragflow is open source under the Apache-2.0 license. Check the license terms before using it in commercial products.
Is ragflow still maintained?
Actively maintained. The last commit to ragflow was on Oct 20, 2026.
What can I use ragflow for?
Building an internal question-answering assistant over company documents and manuals. Creating a knowledge base from scanned or mixed-format files with citation support. Connecting enterprise data sources such as cloud storage or BigQuery for ongoing synchronization. Integrating retrieval-based answers into existing applications through its APIs.
How do I install ragflow?
Clone the repository: git clone https://github.com/infiniflow/ragflow.git Enter the Docker deployment directory: cd ragflow/docker Start the RAGFlow services with Docker Compose: docker compose -f docker-compose.yml up -d Check that the server is ready using the health endpoint, then open the Web UI in your browser: curl -f http://localhost/api/v1/system/healthz
Where can I get ragflow?
The source code and installation instructions are on GitHub: https://github.com/infiniflow/ragflow

Summary generated by AI from the project's README. GitHub stats refresh daily.

Related projects