RAGFlow is an open-source Retrieval-Augmented Generation engine that integrates agent capabilities for enhanced context management in LLM applications. It supports various data sources and offers features like template-based chunking and automated workflows.
Collecting history — the radar snapshots this repo daily. The trend line appears after 3 days of data (1 so far).
What it is
RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses RAG with Agent capabilities to create a superior context layer for LLMs. It offers a streamlined RAG workflow adaptable to enterprises of any scale.
How it works
RAGFlow utilizes a converged context engine and pre-built agent templates to transform complex data into high-fidelity, production-ready AI systems. It supports various data formats and sources, including Word, slides, Excel, images, and web pages.
Getting started
To get started with RAGFlow, you can try the cloud service at https://cloud.ragflow.io. For self-hosting, follow these steps:
- Ensure
vm.max_map_countis set to at least 262144:$ sysctl vm.max_map_count $ sudo sysctl -w vm.max_map_count=262144 - Clone the repository:
$ git clone https://github.com/infiniflow/ragflow.git - Start the server using Docker:
$ cd ragflow/docker $ docker compose -f docker-compose.yml up -d - Check server status:
$ docker logs -f docker-ragflow-cpu-1 - Access RAGFlow in your web browser at
http://IP_OF_YOUR_MACHINE. - Configure the LLM factory in
service_conf.yaml.template.
Recent releases
- v0.26.4 (2026-07-07): Adds a language-aware Snowball stemmer supporting 16 languages.
- v0.26.3 (2026-07-02): Introduces Google BigQuery as a data source connector.
- v0.26.2 (2026-06-29): Integrates WhatsApp and DingTal as chat channels.
- v0.26.1 (2026-06-17): Allows modification of model types in existing configurations.
Traction
- Stars: 84830
- Forks: 9906
- Open Issues: 2304
Caveats
- License: Apache-2.0
- Open Issues: 2304
- Age: Created on 2023-12-12, with the last push on 2026-07-11.