# RAGFlow

> Open-source RAG engine for LLM apps with deep document parsing, multi-granularity chunking, hybrid retrieval integrating vector stores (e.g., Elasticsearch), and visual workflow builder.

- **URL:** https://ragflow.io/
- **Category:** RAG Frameworks & Pipelines
- **Tags:** Rag Pipeline, llm-rag, document-parsing
- **Updated:** 2026-04-23 13:22
- **Canonical page:** https://vectordb.ever.works/it/items/ragflow

## Details

## Overview

RAGFlow simplifies RAG deployment for LLM apps with end-to-end pipelines from parsing to grounded generation.

## Key RAG Features

- **Chunking**: Layout-aware (tables, images), adaptive granularity
- **Retrieval**: Semantic + keyword hybrid, multi-vector
- **Vector Store Integrations**: Elasticsearch, Infinity (native)
- **Reranking**: Multi-strategy fusion, citations

## Use Cases

- Complex doc analysis (PDFs, scans)
- RAG chat interfaces
- Enterprise knowledge bases

## Comparisons

| Aspect | LangChain | LlamaIndex | RAGFlow |
|--------|-----------|------------|---------|
| Parsing | Basic | Good | Advanced visual docs |
| UI/Workflow | Code-based | Index mgmt | Visual builder |
| Deployment | Flexible | Local/cloud | Self-hosted focus |

## Pricing

Free open-source (Apache 2.0).

---

_This Markdown mirror is generated by Ever Works for AI agents. The canonical HTML page is at https://vectordb.ever.works/it/items/ragflow._