# datawhalechina/all-in-rag

🔍大模型应用开发实战一：RAG 技术全栈指南，在线阅读地址：https://datawhalechina.github.io/all-in-rag/

Repository: https://github.com/datawhalechina/all-in-rag
Canonical: https://ross.abutalabs.com/products/all-in-rag
Homepage: https://datawhalechina.github.io/all-in-rag/
Language: Python
License Family: other
Topics: embedding, kimi-k2, langchain, llama-index, llm, milvus, multimodal, rag, ai, neo4j, python, deepseek
Last push: 2026-07-29T11:43:11+00:00

## Health v2 (maintenance only)
Score: 61/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 95, release rhythm 35, longevity 32
- inputs: {"age_days": 454, "days_push": 35, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 10622, forks 5260 (observed 2026-08-28T04:10:42.585272+00:00)

## What it is
An open-source Chinese-language tutorial (Datawhale) providing a full-stack guide to Retrieval-Augmented Generation (RAG) for LLM applications, from fundamentals to advanced practice. It includes hands-on examples using tools like LangChain, LlamaIndex, Milvus, and Neo4j, readable online.

## Use cases
- learn how to build RAG applications
- understand retrieval-augmented generation from basics to advanced
- find a hands-on RAG course with code examples
- learn to use LangChain and LlamaIndex for RAG
- build a knowledge base chatbot with vector databases
- study multimodal and graph RAG techniques

## When to choose
- you want a structured, free curriculum for learning RAG end to end
- you prefer learning by doing with Python code examples
- you want coverage of the modern RAG stack including Milvus, Neo4j, and multimodal RAG

## When to avoid
- you need a production-ready RAG framework or library rather than a tutorial
- you need software with a maintained license for redistribution
- you are looking for non-Chinese-language primary content (though an English README exists)

## Facets
- artifact type: learning-resource
- maturity: active
- function: rag, llm-inference, search-engine, nlp
- domain: large-language-models, tutorials, artificial-intelligence
- platform: python, cross-platform
- tags: rag, tutorial, open-course, langchain, llama-index, milvus, embeddings, vector-database, chinese, datawhale, retrieval-augmented-generation

## Member repositories
- datawhalechina/all-in-rag (main) score 61

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:42.585272+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:18:27.693999+00:00, confidence not recorded.
  - readme: https://github.com/datawhalechina/all-in-rag (fetched 2026-08-28T04:10:42.585272+00:00, sha fce446204c78)
  - homepage: https://datawhalechina.github.io/all-in-rag/ (fetched 2026-08-29T08:17:29.927509+00:00, sha f54409f5c0e0)
- Data as of 2026-08-30T08:39:29.467469+00:00.