Description
转自 https://www.youtube.com/watch?v=MykcjWPJ6T4
本视频是"从零构建RAG流水线"系列的第二集（第一部分），由AI工程师Krishna主讲。在掌握了RAG基本概念之后，本课程正式进入实战编码阶段，重点讲解RAG的两大核心管道之一——数据摄入管道（Data Ingestion Pipeline）。课程以模块化编程思路为导向，从数据读取、文本分块（Chunking）、向量化（Embedding）到存入向量数据库（Vector DB）进行全流程讲解，代码由基础逐步演进为生产级别的结构，适合初学者跟随学习。
This is Episode 2 (Part 1) of the "Build RAG Pipeline From Scratch" series by AI engineer Krishna. Building on the conceptual foundation of RAG, this video dives into practical implementation, focusing on the Data Ingestion Pipeline — the first of two key RAG pipelines. It covers the full flow from loading raw data, chunking text, generating embeddings, to storing them in a vector database. The teaching philosophy emphasizes modular, production-ready code structure, making it easy for beginners to follow along and scale up.
原版视频：https://www.youtube.com/watch?v=MykcjWPJ6T4