Udemyintermediateko

【한글자막】 랭체인 - LangChain 으로 LLM 기반 애플리케이션 개발하기

Learn LangChain & build generative AI apps fast! Hands-on Python (v0.3.0) experience with LLMs. Create real-world applications.

4.5(749)
3,745students
10h 19m
Certificate
Eden Marco
Eden MarcoBest Selling Instructor

Course Content

【한글자막】 랭체인 - LangChain 으로 LLM 기반 애플리케이션 개발하기 is an intermediate-level Udemy course taught by Eden Marco. It runs 10h 19m, is taught in Korean, and includes a certificate of completion. Learners rate it 4.5 out of 5 from 749 reviews, with 3,745 students enrolled. It is a paid course, last updated July 2025.

Master LangChain: Build Powerful LLM Applications with Python

Unlock the potential of Large Language Models (LLMs) and create cutting-edge applications with this comprehensive LangChain course. This course is a direct equivalent to the popular Udemy course "LangChain - Develop LLM powered applications with LangChain," but with the added benefit of professional Korean subtitles.

Who is this course for?

This course is designed for intermediate to advanced learners with a solid background in software engineering and proficiency in Python. You don't need to be a beginner; this course assumes you have existing programming knowledge. While the instructor uses PyCharm IDE, the course focuses on fundamental IDE functionalities like debugging and script execution, allowing you to use your preferred editor.

What you'll learn:

This hands-on course guides you through building real-world LLM applications from scratch. You'll gain practical skills and knowledge to develop advanced LLM solutions across various domains. We'll build three key applications:

  • Ice Breaker: Create a LangChain agent that generates personalized icebreakers by scraping information from the internet (LinkedIn, Twitter) based on a given name, and initiating conversations.
  • Documentation Helper: Build a chatbot that provides answers based on Python package documentation (and adaptable to other data sources). A streamlined version of ChatGPT code interpreter.
  • Prompt Engineering Fundamentals: Dive deep into prompt engineering techniques, including:
    • LLM & GenAI History: Understand the evolution of LLMs and Generative AI.
    • Prompting Strategies: Master techniques like few-shot prompting, chain-of-thought prompting, and ReAct prompting.
    • Chat Models & Open Source Models: Explore different chat models and open-source options.
    • Prompt Engineering Essentials: Learn about prompts, prompt templates, and LangChain's ub functionality.
    • Output Parsers: Utilize output parsers, including Pydantic output parsers.
    • Chains: Implement create_retrieval_chain and create_stuff_documents_chain.
    • Agents: Develop custom agents, Python agents, CSV agents, and agent routers.
    • OpenAI Functions & Tool Calling: Integrate OpenAI functions and implement tool calling.
    • Tools & Toolkits: Learn about various tools and toolkits for LLM applications.
    • Memory & Vector Stores: Utilize vector stores like Pinecone and FAISS.
    • RAG (Retrieval-Augmented Generation): Implement RAG for enhanced LLM performance.
    • Document Loaders & Text Splitters: Master document loading and text splitting techniques.
    • Streamlit (for UI): Build user interfaces with Streamlit.
    • LlamaIndex, LangSmith, LangGraph: Explore these powerful tools for LLM development.
    • FireCrawl, Cursor IDE, Cursor Composter, Cursor Chat: Discover advanced tools for web scraping and development.

Key Concepts Covered:

  • LangChain: A powerful framework for building LLM applications.
  • LLM + GenAI: Understanding the core concepts of Large Language Models and Generative AI.
  • Chat Models: Exploring different types of chat models.
  • Open Source Models: Leveraging open-source LLM models.
  • Prompt Engineering: Crafting effective prompts for optimal LLM performance.
  • Output Parsers: Structuring and parsing LLM outputs.
  • Chains: Creating complex workflows with LangChain chains.
  • Agents: Building autonomous agents that can interact with the world.
  • Tool Calling: Enabling agents to utilize external tools and APIs.
  • Memory: Implementing memory mechanisms for conversational agents.
  • Vector Stores: Storing and retrieving vector embeddings for semantic search.
  • RAG (Retrieval-Augmented Generation): Improving LLM accuracy with external knowledge.

Benefits of this Course:

  • Hands-on Learning: Apply concepts through practical projects.
  • Real-World Applications: Build powerful and efficient LLM applications.
  • Lifetime Access: Access the course materials anytime, anywhere.
  • Dedicated Support: Receive 1:1 assistance with your challenges.
  • Community Access: Join a dedicated Discord community of over 1000 learners.
  • Continuous Updates: Benefit from ongoing course updates at no extra cost.
  • Korean Subtitles: Enjoy professional Korean subtitles for enhanced understanding.

Important Note: The first project (

$ whoami — the devs behind tutorialsearch.io

Want AI in your product? Hire the team behind TutorialSearch.io

LLM features, RAG, agents and automation wired into a real product — built by the devs who shipped this site.