강의

멘토링

커뮤니티

BEST
AI Development

/

AI Agent Development

graphRAG - Knowledge Graph-based RAG System Implementation with Neo4J (feat. LangChain)

Neo4J-based Knowledge Graph RAG System: Next-Generation Search Technology That Goes Beyond Simple Vector Search to Leverage Data Relationships Maximizing RAG Performance with the Power of Graph Databases!

(4.8) 32 reviews

286 learners

  • pdstudio
실습 중심
ai활용
RAG
LangChain
neo4j
LLM
DBMS/RDBMS

Reviews from Early Learners

What you will learn!

  • Methods for Building Knowledge Graphs Using Neo4J Graph Database

  • How to Apply Knowledge Graphs to RAG

  • Implementing a Graph-Based Search System by Integrating LangChain and Neo4J

  • Various search techniques (basic search, full-text search, vector search) utilization and integration

  • Text2Cypher Technique for Converting Natural Language Queries to Graph Queries

Building Powerful RAG Systems with Graph Databases 🪄

Traditional RAG systems rely on simple vector search, making it difficult to properly represent relationships between information. graphRAG utilizing graph databases structures complex relationships between data, enabling the generation of more accurate and contextually appropriate responses. Through structured knowledge representation and relationship-based search, you can achieve more accurate search results.

[Project 2] ETF Financial Product Recommendation - Knowledge Graph Implementation (Using Neo4J Browser)

Improving RAG Performance with Knowledge Graphs 🔧

Structured Knowledge Representation: Represents information as nodes and relationships to clarify connectivity between data and systematically structure complex knowledge.

Relationship-based search: Provides more accurate results through search based on semantic relationships, going beyond simple keyword matching or vector similarity.

Integrated Various Search Methods: Maximizes search performance by combining keyword-based full-text search and vector-based semantic search.

Scalable Knowledge Structure: You can easily add and connect new data and relationships, enabling the construction of a continuously expandable knowledge base.

  • Natural data modeling is possible through nodes and relationships.

  • Intuitive graph exploration is possible through the Cypher query language.

  • It supports powerful graph algorithms and vector indexing.

  • It provides various features for integrating with the LangChain framework.

[Implementing RAG using LangChain + Neo4J] https://neo4j.com/labs/genai-ecosystem/langchain/

Features of this course

Step-by-step learning focused on practical application

By combining theoretical explanations with immediate hands-on practice, you will develop a solid understanding of graph database and RAG integration concepts and build the ability to apply them effectively.

Learning Various Real-World Case Studies

You will learn how to build and search knowledge graphs across various domains using real data such as movie recommendations, news data, ETF financial products, and legal documents.

You'll learn this kind of content

Neo4J Graph Database Fundamentals

Learn from Neo4J AuraDB setup to the core concepts of graph databases including nodes, relationships, and properties. Acquire the fundamental knowledge needed for graph database utilization, including key syntax of the Cypher query language, path traversal, and aggregation functions.

Knowledge Graph Construction

Learn how to convert data from various domains including CSV structured data, news, ETF financial products, and legal documents into knowledge graphs. Study ontology design, constraint setting, and how to utilize LangChain tools for graph transformation.

Graph-based Search Technique Implementation

You will learn how to implement various graph-based search techniques including basic search, full-text search, vector search (semantic search), and Text2Cypher. You will also learn hybrid search methods for implementing enhanced RAG systems.

Pre-enrollment Reference Information

Practice Environment

  • Operating System and Version (OS): Lectures conducted based on MacOS (Linux and Windows users can also participate in hands-on practice)

  • Virtual environment usage: Using uv package manager (conda, poetry, venv users can also follow along)

  • Tools Used: VS Code, LLM API authentication key required (OpenAI/ Google Gemini) *Costs may apply

  • PC Specifications: Not applicable

  • Python 3.12 /

    langchain 0.3.23 / langchain-neo4j 0.3.0 / numpy 1.26.4

Learning Materials

  • Providing materials needed for practice (lecture notes, practice code, practice data)

  • Check the list of class notes and course materials downloads.

Prerequisites and Important Notes

  • Python basic programming skills

  • Understanding the Basic Concepts of LangChain

  • Graph database experience is not required (the course covers the basics)

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


Recommended for
these people

Who is this course right for?

  • Developers who want to improve the performance and accuracy of RAG systems

  • Those who want to effectively process data with complex relationships

  • Those who want to build structured knowledge search systems beyond simple vector search

  • Those who want to apply Knowledge Graphs to AI applications

Need to know before starting?

  • Python

  • LangChain

  • RAG

Hello
This is

14,264

Learners

554

Reviews

142

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

58 lectures ∙ (7hr 4min)

Course Materials:

Lecture resources
Published: 
Last updated: 

Reviews

All

32 reviews

4.8

32 reviews

  • 서강식님의 프로필 이미지
    서강식

    Reviews 3

    Average Rating 5.0

    5

    31% enrolled

    빨리 저의 db로 구현해보고 싶습니다

    • 판다스 스튜디오
      Instructor

      감사합니다.

  • jyuri001님의 프로필 이미지
    jyuri001

    Reviews 1

    Average Rating 5.0

    5

    31% enrolled

    • kmkang님의 프로필 이미지
      kmkang

      Reviews 6

      Average Rating 4.8

      5

      31% enrolled

      진심으로 감사합니다.

    • Hyuk Shin님의 프로필 이미지
      Hyuk Shin

      Reviews 5

      Average Rating 4.2

      5

      31% enrolled

      • JIYEON SUNG님의 프로필 이미지
        JIYEON SUNG

        Reviews 1

        Average Rating 5.0

        5

        100% enrolled

        vectorRAG를 사용해본 후에 graphRAG에 대해서도 배워보고 싶었는데 마침 강의가 나와서 듣게 되었습니다. 기초개념 설명부터 실제 데이터를 이용한 데이터 가공과 여러 방식의 쿼리 서치... Hybrid 방식의 RAG까지 친절한 실습 파일을 통해 따라가면서 익힐 수 있어서 유익했습니다! 실제 제가 구현하고 싶었던 것이 있었는데 해당 강의를 수강하고 나서 곧장 배운 지식을 이용해 시작해볼 수 있을 거 같네요. 강사님 톤이 차분하면서도 막힘 없이 흘러 가서 1.7배속으로 들었는데도 거슬리는 것 없이 귀에 잘 들어와서 강의를 금방 완강 할 수 있었습니다! 강의 재밌게 잘 들었습니다 강사님. 다음 강의도 기대하고 있겠습니다!

      $110.00

      pdstudio's other courses

      Check out other courses by the instructor!

      Similar courses

      Explore other courses in the same field!