Verified project record

datawhalechina/all-in-rag

A full-stack RAG tutorial that combines systematic theory with hands-on projects for building intelligent QA and knowledge retrieval systems. It covers data preparation, multimodal retrieval, and Graph RAG practices.

Project overview

Project type: RAG · AI Search · Data Processing
Use cases: Knowledge Q&A · Data Analysis
Deployment: Refer to project documentation
License: License pending

Best for

Developers, AI engineers, and researchers who want to progress from basic RAG concepts to advanced production applications.
Learners looking to understand multimodal embedding and text+image retrieval practices.

Key capabilities

Guides learners from basic concepts to advanced applications in a structured curriculum.
Teaches data loading from multiple formats and text chunking strategies.
Includes multimodal embedding and text+image retrieval practices.

Limitations and risks

Some sections, such as the multimodal embedding practice and chapter 10, are currently under optimization or planning.
GPU and minimum hardware requirements are not documented.

Getting started

Prepare a Python 3.12.7 environment and Docker. Follow the hands-on chapter tutorials to begin.

Evidence and sources

README: 本项目是一个面向大模型应用开发者的RAG（检索增强生成）技术全栈教程
README: 帮助开发者掌握基于大语言模型的RAG应用开发技能，构建生产级的智能问答和知识检索系统。
README: 现有的RAG教程往往零散且缺乏系统性，初学者难以形成完整的技术体系认知。
README: - [x] [数据加载](./docs/chapter2/04_data_load.md) - 多格式文档处理与加载
README: **第七章高级RAG架构（拓展部分）** [📖 查看章节](./docs/chapter7) - [x] [基于知识图谱的RAG](./docs/chapter7/20_kg_rag.md) **第八章项目实战一** [📖 查看章节](./docs/chapter8) - [x] [环境配置与项目架构](./docs/chapter8/01_env_a…

Reviewed at: 2026-07-18T03:40:40Z