all-in-rag and rag-guide
These are complementary educational resources that share the same tech stack (FastAPI + LangChain), with the former being a comprehensive theoretical guide and the latter being a practical hands-on handbook for implementing RAG applications end-to-end.
About all-in-rag
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/
This is a comprehensive guide for AI engineers and product developers to build advanced question-answering and knowledge retrieval systems using Large Language Models (LLMs). It takes you from understanding foundational RAG concepts to building production-ready applications, processing various data inputs, and producing highly accurate, contextually relevant answers. The guide targets individuals keen on developing smart information retrieval tools and interactive AI experiences.
About rag-guide
david-zlj/rag-guide
RAG 开发者的一站式手册。以 FastAPI + LangChain 为核心技术栈，助力学习者快速掌握从 0 到 1 搭建 RAG 应用的能力，轻松落地企业知识库等实际项目。
This guide helps developers learn how to build Retrieval-Augmented Generation (RAG) applications from scratch. It takes various data formats like PDFs, Word documents, and text files as input, processes them, and uses large language models to generate accurate answers or insights. Software engineers, AI/ML newcomers, and technical managers can use this to create applications like smart chatbots, enterprise knowledge bases, or academic research tools.
Scores updated daily from GitHub, PyPI, and npm data. How scores work