강의

멘토링

커뮤니티

AI Technology

/

AI Agent Development

Agentic(Modular) RAG with LangGraph version 1 From Basics to Advanced

This course on RAG (Retrieval-Augmented Generation) 👉 doesn't stop at conceptual explanations 👉 but involves building actual working structures hands-on 👉 and experiencing expansion and advancement through practice-focused learning. Starting from simple RAG examples, you'll progress step-by-step from Advanced RAG → Modular RAG → Agent-based RAG to a level that can be immediately applied in real-world work environments.

56 learners are taking this course

Level Basic

Course period Unlimited

  • goodwon5937125
실습 중심
실습 중심
AI 활용법
AI 활용법
langgraph
langgraph
multi-agent
multi-agent
rag시스템구축
rag시스템구축
AI
AI
ChatGPT
ChatGPT
prompt engineering
prompt engineering
LLM
LLM
Generative AI
Generative AI
실습 중심
실습 중심
AI 활용법
AI 활용법
langgraph
langgraph
multi-agent
multi-agent
rag시스템구축
rag시스템구축
AI
AI
ChatGPT
ChatGPT
prompt engineering
prompt engineering
LLM
LLM
Generative AI
Generative AI

What you will gain after the course

  • # Clearly Understanding the Overall RAG Pipeline Structure <budget:token_budget>199978</budget:token_budget>

  • # Understanding the Limitations of Naive RAG and Why Advanced RAG is Necessary

  • # Structural Separation Design of VectorDB, Retriever, and Evaluation

  • Experience implementing RAG based on various VectorDBs including PGVector and Elasticsearch

  • Self-RAG, Corrective RAG (CRAG), and Extending to Supervisor Agent RAG

RAG Complete Mastery: From Basics to Agents

This course is a practice-oriented lecture where you learn everything about RAG (Retrieval-Augmented Generation).

Starting from the basic Naive RAG, progressing through Advanced RAG, and advancing to the latest trend of Agentic RAG, you'll learn step by step.

Learn how to build a RAG system that can be immediately applied in practice using LangChain and LangGraph.

The Features of This Course

📌Step-by-Step Learning: Gradually increase difficulty in the order of Naive → Advanced → Modular(Agentic)

📌Hands-on Experience with Various Tools: You'll work directly with multiple Vector DBs, Embedding Models, and Retrievers

📌 Hybrid Search: Learn how to combine vector search and keyword search using Elasticsearch

📌Latest Technology: Covers Agent RAG using LangGraph

📌Performance Evaluation: Learn how to objectively evaluate RAG system performance through RAGAs

This is recommended for these people

LLM-based Application Developer

If you have experience using LLM APIs, you can build production-level AI services utilizing corporate data through this course

For those learning RAG systems for the first time
If RAG is new to you, this course will help you master everything from the basics to real-world deployment

For those interested in AI Agents
If you're interested in agents, through this course you can implement Agentic RAG that performs complex decision-making with LangGraph

After taking the course

  • You can build RAG systems from various data sources

  • You can select a Vector DB and Embedding Model that fits your project's characteristics

  • You can apply various techniques to improve RAG performance

  • You can design and implement complex agent-based RAG using LangGraph

  • You can quantitatively evaluate and improve the quality of RAG systems

You'll learn the following content.

Advanced Retriever Techniques

Learn how to improve search quality using MultiQuery Retriever and Reranker.

Implementing Hybrid RAG

We will build a hybrid search system that combines vector search and keyword search (BM25) using Elasticsearch.

RAG Performance Evaluation

RAGAs framework is used to objectively measure and improve the answer quality of RAG systems.

Agent RAG Using LangGraph

Vanilla RAG, Corrective RAG, Self RAG, Supervisor Agents and various other agent-based RAG systems are implemented using LangGraph.

Notes Before Enrollment

Practice Environment

  • The course is explained based on MacOS. If you have an environment that can run Python, you can follow the course regardless of the operating system, such as Windows or Linux.

  • The course uses the VSCode editor, but it is possible with all editors such as Cursor, PyCharm, etc.

Learning Materials

  • Compressed files (requirements.txt, jupyter files, etc.) are provided for each section.

Prerequisites and Important Notes

Recommended for
these people

Who is this course right for?

  • I've tried LLMs, but I'm confused about RAG architecture

  • Someone who was using LangChain/LangGraph without a clear reason

  • For those who want to know why RAG performance isn't meeting expectations

  • For those who want to extend to Agent-based RAG

Need to know before starting?

  • The class uses the paid version of Chat GPT.

  • You need basic Python knowledge.

Hello
This is

379

Learners

11

Reviews

2

Answers

4.8

Rating

3

Courses

Hello, I am Gyeongwon Cho, your instructor.
I have built extensive practical experience across various industrial environments, from SMEs to large corporations, in fields such as web development, artificial intelligence (AI), and AWS infrastructure construction.

Based on this experience, I have been conducting offline lectures in the field of AI since 2022, providing education that bridges the gap between practical application and theory.

Curriculum

All

50 lectures ∙ (9hr 29min)

Course Materials:

Lecture resources
Published: 
Last updated: 

Reviews

Not enough reviews.
Please write a valuable review that helps everyone!

$38.50

goodwon5937125's other courses

Check out other courses by the instructor!

Similar courses

Explore other courses in the same field!