ragflow
RAGFlow is an agent-native database: a Retrieval-Augmented Generation (RAG) engine that grew into context infrastructure.
What is ragflow?
RAGFlow is an agent-native database: a Retrieval-Augmented Generation (RAG) engine that grew into context infrastructure.
Overview of ragflow
What it is
RAGFlow is an open-source Retrieval-Augmented Generation (RAG) engine that combines RAG with Agent capabilities. It provides a context layer for LLMs, with a streamlined RAG workflow adaptable to enterprises of any scale. Powered by a converged context engine and pre-built agent templates, it enables developers to transform complex data into production-ready AI systems.
Key features
- Deep document understanding for knowledge extraction from unstructured data with complicated formats.
- Template-based chunking that is intelligent and explainable, with multiple template options.
- Knowledge Compilation: generates structured knowledge artifacts at document and dataset levels, including Wikis, Graphs, Trees, PageIndex, Mind Maps, Timelines, and Skills.
- Agentic Retrieval with multi-step retrieval and thinking modes (Low, Medium, High, Ultra) to control retrieval and reasoning depth.
- Grounded citations with reduced hallucinations, including visualization of text chunking and traceable references.
- Compatibility with heterogeneous data sources: Word, PowerPoint, Excel, TXT, images, PDFs, scanned copies, structured data, web pages, and more.
- Automated RAG workflow with configurable LLMs and embedding models, multiple recall paired with fused re-ranking, and intuitive APIs.
Use cases
- Enterprises of any scale needing a streamlined RAG workflow.
- Developers building production-ready AI systems that require high-fidelity context from complex data.
- Transforming unstructured data into structured knowledge artifacts for knowledge organization and reuse.
Getting started
Try the cloud service at https://cloud.ragflow.io. For local deployment using Docker: bash git clone https://github.com/infiniflow/ragflow.git cd ragflow/docker git checkout v1.0.0-rc1 docker compose -f docker-compose.yml up -d After startup, check server health: bash curl -f http://localhost/api/v1/system/healthz Open the web UI at http://IP_OF_YOUR_MACHINE (default port 80).
License and pricing
Licensed under Apache-2.0. Open source. No pricing information is stated.
Based on the project's public README and repository metadata.