📚

RAG Full-Stack Development

This course is for developers with some AI and programming background, focusing on the principles, system composition, security considerations, and implementation of Retrieval-Augmented Generation (RAG). You will systematically learn the working mechanism of LLM and RAG, and master the complete E2E project construction method, including key modules such as index construction, query optimization, and permission control. The course adopts a combination of theory and practice to help you develop the ability to independently develop and deploy enterprise-level intelligent question-answering systems.

Syllabus

📦 Appendix

📋 LangChain official documentation

📋 LCEL usage guide

📋 Practical manual for vector databases (pgvector, FAISS, etc.)

📋 Sample project address

📋 Recommended GitHub repositories

📋 Collection of commonly used component libraries and templates

Day 1: RAG Theory and Core Process

Systematic Understanding from Concept to Technical Architecture

🔍

📚 Today's Content

•

1.1 RAG Overview

What is RAG? (What)

Why is RAG needed? (Why)

Analysis of typical application scenarios

Introduce the overall technical architecture of RAG in combination with LangChain/LangGraph

•

1.2 Two-Stage Workflow of RAG

Overview of the core working mechanism of the RAG system

Analysis of the two-stage collaborative mode

📥 Indexing Stage

• Document loading and chunking - LangChain / LCEL's loading and chunking capabilities

• Vectorization and Embedding models - selection of mainstream open source and commercial embedding models

• Vector database access - integration of vector storage solutions such as pgvector, FAISS, etc.

🔎 Retrieving Stage

• Retrieval technology principles: vector retrieval, similarity ranking

• Prompt template design and integration of upstream and downstream links

• Advanced retrieval strategies: Hybrid Search, Reranking

• Retrieval link construction in LangChain/LangGraph

•

1.4 Tool Practice Demonstration

Use LangChain/LCEL to demonstrate the complete RAG process: document loading → Embedding → retrieval

Operate a vector database (taking pgvector as an example)

💡 Learning Objectives

✓ In-depth understanding of the working principle and value of the RAG system
✓ Master the complete document processing and vectorization process
✓ Proficient in using mainstream vector databases and retrieval components
✓ Possess the ability to design the architecture of a RAG system

📦 Appendix

📋LangChain official documentation

📋LCEL usage guide

📋Practical manual for vector databases (pgvector, FAISS, etc.)

📋Sample project address

📋Recommended GitHub repositories

📋Collection of commonly used component libraries and templates

RAG Full-Stack Development

Syllabus

Day 1: RAG Theory and Core Process

Day 2: RAG Practice and Optimization

📦 Appendix

Day 1: RAG Theory and Core Process

📚 Today's Content

1.1 RAG Overview

1.2 Two-Stage Workflow of RAG

📥 Indexing Stage

🔎 Retrieving Stage

1.4 Tool Practice Demonstration

💡 Learning Objectives

Day 2: RAG Practice and Optimization

📚 Today's Content

2.1 Practice Preparation

2.2 Experiment 1: Indexing Pipeline Implementation

2.3 Experiment 2: Retrieving Pipeline Implementation

2.4 Experiment 3: Query Optimization and Enhancement

2.5 Experiment 4: Permission Control and Security Design

2.6 Summary and Q&A

💡 Learning Objectives

📦 Appendix