Choose it for a similar, actively maintained notebook-style RAG tutorial using LangChain.
Everything you need to know to build your own RAG application
- 4.2k
- Jupyter Notebook
- NOASSERTION
RAG educational tutorials
Jupyter notebooks teaching retrieval-augmented generation (RAG) from scratch, covering indexing, retrieval, and generation basics.
Same problem, same approach. Swapping one for another is a config change, not a rewrite.
Choose it for a similar, actively maintained notebook-style RAG tutorial using LangChain.
Everything you need to know to build your own RAG application
Solves the same problem with a different architecture or at a different layer. Expect to rewrite the integration.
Choose it when you prefer a JavaScript/local-LLM implementation over Python notebooks.
Demystify RAG by building it from scratch. Local LLMs, no black boxes - real understanding of embeddings, vector search, retrieval, and context-augmented generation.
Choose it when you already understand RAG basics and want advanced technique notebooks.
This repository contains various advanced techniques for Retrieval-Augmented Generation (RAG) systems.
Choose it when you want to learn agentic RAG workflows with LangGraph instead of baseline RAG.
A modular Agentic RAG built with LangGraph — learn Retrieval-Augmented Generation Agents in minutes.
Choose it for a comprehensive set of advanced RAG technique notebooks.
This repository showcases various advanced techniques for Retrieval-Augmented Generation (RAG) systems. Each technique has a detailed notebook tutorial.
These projects were analysed and named rag-from-scratch among their alternatives. The relationship is not symmetric — how rag-from-scratch rates them is a separate judgement, made when rag-from-scratch is analysed in its own right.
calls rag-from-scratch “Teaches RAG by building components from scratch with low-level code, a different approach from the seed's framework-based full-stack path.”
🔍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/