인프런 영문 브랜드 로고
인프런 영문 브랜드 로고
AI

/

Generative AI

RAG System Implemented with AI Agent (w. LangGraph)

Intelligent AI agent for search augmented generation (RAG) implemented with LangGraph! A hands-on tutorial that even beginners can easily follow, from theory to practice.

(5.0) 4 reviews

164 students

AI Agent
LangGraph
RAG
LLM
LangChain
Thumbnail

This course is prepared for Basic Learners.

What you will learn!

  • Design and implementation of AI agent structure using LangGraph

  • Applying AI Agents to RAG (Retrieval-Augmented Generation)

  • Expanding the capabilities of AI agents by implementing the Tool Calling function

  • Master the latest agent RAG architectures including Adaptive RAG, Self RAG, and Corrective RAG

For a powerful RAG system
Magic Tool AI Agent 🪄

Introduction page
Haute couture banner (32)

LLM excels at natural language processing and text generation, but it has limitations in self-coordinating complex workflows or making decisions. Beyond information retrieval, LLM needs the help of agents to evaluate results, modify queries, and select context-sensitive tools. Agents are a must-know technology for a smarter and more flexible RAG system .

AI Agents That Boost LLM Performance 🔧

✅ Choose the right tool for the situation

LLM helps you decide which tools to use for your situation. Depending on your request task, you can choose the appropriate tool, such as an API call, a database search, or an external search.

✅ Generate optimal search queries

When your question is unclear or complex, we help you refine or modify your query to get more accurate results. This allows LLM to generate optimal search queries.

✅ High quality answers

When multiple results are returned, we evaluate the most relevant information and select the best answer. This allows us to provide accurate information to users.

✅ Decision on follow-up work to improve results

If the results are insufficient or inaccurate, we run a feedback loop to determine whether further work is needed and either repeat the search or try a new approach.

Why use LangGraph? 🤔

LangGraph is a good tool for implementing complex workflows. While LangChain is suitable for processing relatively fixed flows, LangGraph is compatible with agents because it can flexibly process and manage complex tasks.

<Features of Langgraph>

  • Node-based management allows for easy handling of various states and conditions.

  • Manage complex workflows visually.

  • Combining agents into a lang graph allows you to effectively connect and execute various modules.


Features of this course

Screenshot 2024-10-11 115028

Step-by-step, practice-oriented learning

Immediately after explaining the theory, we proceed with related practical exercises to develop a solid understanding of the concept and the ability to apply it.

Screenshot 2024-10-11 115129

A curriculum that reflects the latest trends

We actively reflect the latest technologies and methodologies for agent-based RAG, providing knowledge that can be immediately applied in the field.

Please enter a title_-001 (12)
Screenshot 2024-10-11 114528

LangGraph Complete Guide

We explain the complex LangGraph step by step from the basics so that anyone can understand it, and we provide in-depth learning with various real-world examples.

Easy review with tutorial provided

We provide a WikiDocs textbook that summarizes the content on LangGraph and Agent RAG, so that you can continue studying and referencing after taking the course.

Learn about these things

Designing AI Agent Flows with LangGraph

Learn the core concepts of LangGraph: state graph, conditional edge, and feedback loop, and understand how to model the complex decision-making process of AI agents as graphs. You will also learn techniques that can be applied to various AI agent projects, such as Human-in-the-Loop, parallel execution, and subgraph.

Expanding AI Capabilities with Tool Calling

Master the Tool Calling technique that connects the capabilities of AI agents to the real world. Covers how to create and call LangChain's built-in tools, custom tools, etc. Learn how to integrate external APIs and various tools into your AI system.

Implementing an advanced agent-based RAG technique

Explore advanced techniques to take RAG system performance to the next level. Learn about the concepts and implementation techniques of Adaptive RAG, which operates dynamically depending on context, and Self RAG and Corrective RAG, which allow AI to evaluate and improve its own output.

Things to note before taking the class

Practice environment

  • Operating System and Version (OS): Lecture will be based on MacOS (Linux and Windows users can also practice)

  • Using a virtual environment: The lecture will proceed based on Poetry (conda, venv users can also practice)

  • Tools used: VS Code, OpenAI API, etc. LLM authentication key required (separate cost may apply)

  • PC Specs: Not applicable

  • LangGraph version: v0.2.34 applied

  • LangChain version: v0.3.1 applied

Learning Materials

Player Knowledge and Notes

  • People with basic knowledge of Python (those who can do basic programming)

  • [Free Lecture] LangChain Basics for Beginners (Required): https://inf.run/Fzfhs


  • If you have any questions or comments, please feel free to ask.

Linked lecture information

  • RAG Master: From Basics to Advanced Techniques (feat. LangChain)

  • From RAG implementation to performance evaluation -

    Practical AI Development Completed in 9 Hours

    • LangChain-based RAG system construction practice

    • Learn advanced RAG techniques

    • RAG System Performance Evaluation Methodology

    • LangChain's latest LCEL grammar and how to use Runnable


  • Link: https://inf.run/mdYe4

Recommended for
these people!

Who is this course right for?

  • For those who want to create their own intelligent AI agents beyond chatbots

  • Those who want to challenge themselves to develop practical AI solutions using RAG and LLM

  • Those who want to take the next step after attending a blockchain-based 'chatbot' or 'RAG' lecture

Need to know before starting?

  • Python

  • (Free Course) LangChain Basics for Beginners [Required]

  • (Paid Course) RAG Master: From Basics to Advanced Techniques [Recommended]

Hello
This is 판다스 스튜디오

Students

2,848

Reviews

168

Rating

4.8

Courses

6

안녕하세요. 저는 파이썬을 활용한 데이터 분석 및 인공지능 서비스 개발 실무를 하고 있습니다. 관심 있는 주제를 찾아서 공부하고 그 내용들을 많은 분들과 공유하기 위해 꾸준하게 책을 집필하고 인공지능 강의를 진행해 오고 있습니다.

 

[이력]

현) 핀테크 스타트업 CEO

전) 데이콘 CDO

전) 인덕대학교 컴퓨터소프트웨어학과 겸임교수

Kaggle Competitin Expert, 빅데이터 분석기사

 

[강의]

NCS 등록강사 (인공지능)

SBA 서울경제진흥원 새싹(SeSAC) 캠퍼스 SW 교육 ‘우수 파트너 선정’ (Python을 활용한 AI 모델 개발)

금융보안원, 한국전자정보통신산업진흥회, 한국디스플레이산업협회, 대구디지털산업진흥원 등 강의

서울대, 부산대, 경희대, 한국외대 등 국내 주요 대학 및 국내 기업체 교육 경험

  

[집필]

 

[유튜브] 판다스 스튜디오 : https://youtube.com/@pandas-data-studio?si=XoLVQzJ9mmdFJQHU

Curriculum

All

54 lectures ∙ (6hr 45min)

Lecture resources

are provided.

Published: 
Last updated: 

Reviews

Not enough reviews.
Become the author of a review that helps everyone!