ragflow

Free

RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs

Model APIsFreeFree tier

Outputs: text

Type

Open Source

Visit Website GitHub (78.5k stars)

About ragflow

RAGFlow is an open-source Retrieval-Augmented Generation (RAG) engine that combines RAG with agent capabilities to create a context layer for LLMs. It features a built-in ingestion pipeline to cleanse and process multi-format data (documents, images, web data) into rich semantic representations for superior retrieval. The system supports hybrid search combining vector search, BM25, and custom scoring with advanced re-ranking for accuracy. Users can build powerful agents visually by integrating RAG, tools, and Model Context Protocol (MCP) within workflows. Pre-built workflows demonstrate stock analysis, legal precedent analysis, and maintenance guidance. RAGFlow offers multiple deployment options including cloud, on-premises, and BYOC with dedicated support.

Key Features

Built-in ingestion pipeline for multi-format data (documents, images, data sources)

Semantic representation for superior retrieval accuracy

Hybrid search combining vector, BM25, and tensor search with re-ranking

Visual workflow builder for creating agents with RAG, tools, and MCP integration

Pre-built workflows for stock analysis, legal precedent analysis, and maintenance guidance

Multiple deployment options: cloud, on-premises, BYOC

Open-source and self-hosted

Pros & Cons

Pros

Open-source with self-hosted option for data control
Comprehensive data ingestion pipeline handles diverse formats
Hybrid search with re-ranking improves answer accuracy
Visual agent workflow builder enables complex automation without coding
Pre-built domain-specific workflows accelerate adoption
Scalable pricing from free to enterprise with dedicated support

Cons

Requires technical expertise for self-hosting and setup
Free tier has limited storage (0.1 GB) and credits (500/month)
API key not available in free tier
LLM dependency must be provided externally

Best For

Stock analysis and financial research with multi-agent orchestrationLegal precedent analysis with structured citation and reasoningMaintenance guidance by retrieving from internal manualsGeneral RAG-based question answering over documentsData consolidation and reporting from multiple sources

Alternatives to ragflow

AutoGPT

AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.

aider

aider is AI pair programming in your terminal

axolotl

Go ahead and axolotl questions

Chroma

Open-source embedding database

awesome-claude-code

A curated list of awesome skills, hooks, slash-commands, agent orchestrators, applications, and plugins for Claude Code by Anthropic

agents-course

This repository contains the Hugging Face Agents Course.

FAQ

What is RAGFlow?

RAGFlow is an open-source RAG engine that combines retrieval-augmented generation with agent capabilities, providing a context layer for LLMs.

What are the pricing plans?

RAGFlow offers Free, Starter ($29/month), Pro ($129/month), and Enterprise plans with custom pricing for on-premises or BYOC deployment.

Is RAGFlow open-source?

Yes, RAGFlow is open-source and available on GitHub.

What data formats are supported?

RAGFlow supports images, documents, and data sources through its ingestion pipeline, processing multi-format data into semantic representations.