강의

멘토링

로드맵

Inflearn brand logo image
BEST
AI Development

/

AI Agent Development

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

This lecture covers RAG (Retrieval-Augmented Generation) system fundamentals and implementation using LangChain. Participants will understand RAG's core principles and learn to build and evaluate systems using LangChain.

(5.0) 42 reviews

523 learners

  • pdstudio
이론 실습 모두
AI검색
RAG
LangChain
LLM
Chatbot
Python

Reviews from Early Learners

What you will learn!

  • Building a RAG System using LangChain

  • Mastering Effective Search and Generation Techniques

  • RAG System Performance Evaluation Methods

  • LangChain's LCEL grammar and Runnable usage

From RAG implementation to performance evaluation
Practical AI Development in 9 Hours

Advances in AI technology have increased the usability of RAG systems, but the process of learning and implementing them remains challenging. I, too, faced many challenges when first learning RAG, and that experience inspired me to plan this course.

The course focuses on building a working system based on step-by-step exercises. It covers not only basic implementations but also advanced techniques for improving search quality and performance evaluation, providing practical knowledge that can be applied directly to real-world projects.

Five months after launch
1590+ people took the course
Created the LLM series lectures
RAG lecture by knowledge sharer

Python & Langchain
Free basic lectures provided
Python Basics Course
Langchain Basics Course

For building a RAG system
Abundant learning materials
31 pages of summary material and
6 source code files

Lecture Points 💫

Building the foundation for RAG implementation

Simply following the code has its limitations. You need to understand the principles behind when and why you use each component . This course covers the fundamental concepts of RAG, its main components, and LCEL syntax , laying the foundation for implementing RAG . We also offer a free beginner-friendly course on Python and Langchain.

Improve RAG implementation capabilities with the latest modules and techniques

The RAG process consists of [document loading → text segmentation → embedding → vector storage → search → prompt → LLM → final result]. This lecture introduces various cutting-edge modules and techniques applicable to each process . In particular, you can experience advanced search techniques such as hybrid search, re-rank, and context compression to improve search performance.

10 Performance Evaluations for RAG Improvement

To enhance the RAG system, "evaluation and improvement" is essential. This lecture introduces five information retrieval methods to evaluate RAG's search performance. It also covers five response evaluation methods for RAG, including quantitative indicator-based evaluation methods and LLM-based evaluation methods.

Easy and clear explanations proven by numerous reviews

Many students have proven this

The course reviews are for courses opened by knowledge sharers as of September 24th.

Learn about these things

Understanding the basic concepts of RAG and LangChain

Understand the operating principles of the RAG system, learn LangChain's structure, and learn LCEL syntax. This will prepare you for a practical environment and provide fundamental knowledge that can be applied to various AI projects.

Hands-on : Installing LangChain, setting up the environment, and configuring a basic RAG pipeline.

Practice data processing and text segmentation techniques

You can handle various data formats (PDF, JSON, Web, etc.) and learn effective text segmentation techniques to efficiently manage large-scale data.

Hands-on training : Practice with various document loaders such as PyPDFLoader and CSVLoader, and apply text segmentation strategies (recursive segmentation, regular expression utilization, semantic segmentation).

Utilizing Embedding Models and Vector Storage

You can maximize RAG search performance by leveraging embedding models to convert text data into vectors and store them in a vector storage.

Hands-on training : Creating and searching Chroma and FAISS vector repositories, utilizing OpenAI, Huggingface, and Ollama embedding models.

RAG Search Performance Evaluation and Optimization

Evaluate RAG search performance using various information retrieval evaluation metrics and acquire optimization techniques that can be applied to actual projects.

Practical training : Search performance testing and evaluation (quantitative evaluation such as hit rate and MRR), optimization methods (query expansion, re-rank, context compression)

Generating and evaluating answers using LLM

You can generate answers for the RAG system using various LLMs and evaluate the quality of the answers using the LangChain evaluation tool.

Practice content : LLM integration practice, response evaluation using LangChain evaluation tool

Implementing a RAG-based chatbot using Gradio

Using Gradio, you can build RAG-based chatbot interfaces that interact with users and design real-time search and answer generation systems.

Hands-on : Implementing a RAG chatbot using Gradio, stream-based output, and adding chat history.

Things to note before taking the course

Practice environment

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

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

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

  • PC specifications: Not applicable

  • LangChain version: v0.2.16 applied

Learning Materials

  • Providing materials required for practice (lecture notes, practice code)

  • (For beginners) Reference material provided on Wikidocs: https://wikidocs.net/book/14473

Player Knowledge and Precautions

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

  • LangChain Basics for Beginners (Free Course): https://inf.run/Fzfhs


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

Linked lecture information

  • RAG system implemented with AI agents (w. LangGraph)

  • An intelligent AI agent for augmented search generation (RAG) implemented with LangGraph.


    • Design and Implementation of an AI Agent Structure Using LangGraph

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

    • Expanding the capabilities of AI agents by implementing tool calling functionality.

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

  • Link: https://inf.run/hTwjC

Recommended for
these people

Who is this course right for?

  • Those interested in RAG systems using LLM

  • Those wanting to start AI projects with LangChain

  • Those interested in learning RAG search and generation performance evaluation methods

Need to know before starting?

  • Python

  • LangChain Basics for Beginners (Lecture)

Hello
This is

13,691

Learners

479

Reviews

132

Answers

4.8

Rating

7

Courses

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

79 lectures ∙ (8hr 42min)

Course Materials:

Lecture resources
Published: 
Last updated: 

Reviews

All

42 reviews

5.0

42 reviews

  • hanjin1.choi님의 프로필 이미지
    hanjin1.choi

    Reviews 1

    Average Rating 5.0

    5

    30% enrolled

    • 박지웅님의 프로필 이미지
      박지웅

      Reviews 1

      Average Rating 5.0

      5

      61% enrolled

      • 서성호님의 프로필 이미지
        서성호

        Reviews 1

        Average Rating 5.0

        5

        100% enrolled

        다소 난이도 있는 강의이지만 상세한 예제를 이용해 이해하기 쉬운 교육이었습니다.

        • 판다스 스튜디오
          Instructor

          정말 감사합니다! 😊 더 좋은 강의를 준비해서 뵙겠습니다! 🌟

      • 박진영님의 프로필 이미지
        박진영

        Reviews 5

        Average Rating 5.0

        5

        30% enrolled

        • 정윤구님의 프로필 이미지
          정윤구

          Reviews 2

          Average Rating 5.0

          5

          30% enrolled

          $93.50

          pdstudio's other courses

          Check out other courses by the instructor!

          Similar courses

          Explore other courses in the same field!