LightningRAG

# LightningRAG

English | [简体中文](./README_zh.md)

[GitHub](https://github.com/LightningRAG/LightningRAG): https://github.com/LightningRAG/LightningRAG

## 1. Basic Introduction

### 1.1 Project introduction

> **LightningRAG** is built around **RAG**: **knowledge bases** (ingest, parse, chunk, vector retrieval), pluggable **LLMs, embeddings, vector stores, and rerankers**, and **Agent orchestration** on a canvas (retrieval, LLM, tools, control flow)—with optional **webhook channel connectors** (Feishu, DingTalk, Slack, etc.). It ships as a **[Vue](https://vuejs.org) + [Gin](https://gin-gonic.com)** full-stack starter with JWT, dynamic routes/menus, Casbin, a form builder, and code generation.

~~[Online Demo](https://demo.LightningRAG.com): https://demo.LightningRAG.com~~

~~username：admin~~

~~password：123456~~

*Public preview is not deployed yet; remove the strikethrough and turn the demo link back on when the server is ready.*

## 2. Features

- **Knowledge bases & RAG**: Ingest documents, parse and chunk, embed into pluggable vector stores; hybrid / multi-path retrieval (vector, keyword, PageIndex, and related retriever types); conversation and streaming chat APIs with optional **`references`**; pluggable **LLMs, embeddings, rerankers**, and **`rag:`** defaults in `config.yaml` (Section 3 below; [`server/rag/README.md`](server/rag/README.md)).
- **Agent orchestration**: Visual canvas flows with nodes such as Begin, Retrieval, LLM, Message, and **Agent** (with tools) for multi-step and branching automation; extensible **tool registry** for RAG chat ([`server/rag/tools/README.md`](server/rag/tools/README.md)).
- **Channel connectors (optional)**: Bind published agents to **webhook** endpoints for Feishu, DingTalk, WeChat, Slack, Teams, and other platforms (Section 3.5 below; [`docs/THIRD_PARTY_CHANNEL_CONNECTORS.md`](docs/THIRD_PARTY_CHANNEL_CONNECTORS.md)).
- Authority management: Authority management based on `jwt` and `casbin`. 
- File upload and download: imp