인프런 영문 브랜드 로고
인프런 영문 브랜드 로고
BEST
AI

/

Generative AI

LLM Application Development Using RAG (feat. LangChain)

Learn RAG from Silicon Valley GenAI Hackathon Winners. Packed with industry know-how.

(5.0) 56 reviews

832 students

LLM
RAG
LangChain
vector-database
openAI API
Thumbnail

This course is prepared for Basic Learners.

What you will learn!

  • LangChain

  • Large Language Model

  • Vector Database

  • Retrieval Augmented Generation(RAG)


RAG from Silicon Valley GenAI Hackathon Winner

  • Data Preprocessing and Efficient Retrieval : Learn the data preprocessing techniques required for RAG construction and how to maximize retrieval efficiency by leveraging keywords.

  • How to Write Efficient Prompts : With the improved performance of LLM, you can now write prompts in Korean and get good results. Learn how to write Korean prompts using LangChain's PromptTemplate.

  • LLM Performance Evaluation and Service Optimization : Learn how to systematically measure and optimize model performance, reliability, and accuracy through LLM evaluation after service deployment.

RAG? Augmented Search Generation?

RAG is a technology that improves the performance of large-scale language models (LLMs) through Retrieval Augmented Generation . LLMs have excellent language understanding and generation capabilities by learning massive text data, but they have limitations such as bias and factual errors. RAG can complement these limitations and improve accuracy and reliability through real-time information retrieval.

Features of this course

📌 Contains know-how learned through hands-on experience developing/distributing/operating LLM applications in the field.

📌 10% theory, 90% practice. Only essential theories are lightly explained and all lectures are conducted through live coding.

📌 I did not intentionally edit the errors. You can learn how to debug while developing LLM services.

📌 100% resolution of lecture questions! Through Q&A, we will solve difficulties encountered in lecture content or in the field together.

I recommend this to these people

I don't know where to start.
I want to create a service using LLM, where do I start?
Developers/development teams who are at a loss as to what to do

What is RAG?
Are you curious about what RAG is and why it is important? Anyone who wants to understand the latest technology and use it to develop their own AI applications.

What more can I do?
LLM Application in development
Hallucination problem
Developers/development teams that need to resolve

After class

  • Data Preprocessing and Keyword Utilization : You can learn the data preprocessing techniques required for RAG composition and how to maximize search efficiency by utilizing keywords.

  • Model Performance Evaluation : Through LLM evaluation, you will learn how to systematically measure and optimize the performance, reliability, and accuracy of your models. You will learn how to improve the quality of your models through evaluation results.

  • Deploying and Maintaining Services : Learn how to deploy and maintain applications using tools like Streamlit, and gain hands-on, practical skills.

  • Solving the Hallucination Problem : Learn techniques to minimize the inaccurate information generated by LLM models and provide more reliable information.

  • Understand and apply the latest AI technologies : Understand the latest AI technologies such as RAG and use them to develop your own AI applications.

Learn about these things.

LLM Answer Streaming

While LLM generates the answer, the user continues to
If you are looking at a loading screen, it will feel like the service is slow. Streaming improves the user experience.
Learn how to improve

Provide a source for your answer

Hallucination is the most problematic issue in LLM services.
How to improve the reliability of answers by providing the source of the answer to the user while generating the answer.
Learn

LLM Evaluation using LangSmith

The Knowledge Base also changes during service operation.
You will also need to modify the prompts each time you update.
Developers can't test them one by one.
Learn how to verify model accuracy using LangSmith to ensure stable service operation.

LangChain Expression Language (LCEL)

Did you know that LangChain can be used to connect various chains? Using LCEL syntax
Learn how to implement and connect chains that perform various functions.

Vector Database (Chroma, Pinecone)

Using LangChain, Chroma, Pinecone,
Learn how to store data using the same Vector Database and retrieve related documents through similarity search.

Who created this course



Things to note before taking the class

Practice environment

  • The lecture explains based on MacOS.

    • If Python runs on Windows or Linux, you can follow along.


Learning Materials

  • Source Code GitHub Repository (Jupyter Notebook, Streamlit)

  • GitBook for additional explanations

Player Knowledge and Notes

  • Python Basic Grammar

  • Anyone who has ever used ChatGPT will easily understand it.

  • I think this will be most helpful to those who are having difficulties developing an LLM application.

Recommended for
these people!

Who is this course right for?

  • Developers who want to create an LLM service

  • Developer with experience developing LLM applications

  • Developers having trouble configuring RAG

Need to know before starting?

  • Python

Hello
This is jasonkang14

Students

2,362

Reviews

133

Rating

5.0

Courses

6

Curriculum

All

25 lectures ∙ (3hr 28min)

Lecture resources

are provided.

Published: 
Last updated: 

Reviews

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