강의

멘토링

로드맵

BEST
AI Development

/

AI Agent Development

Large Language Models LLM for Everyone Part 5 - Building Your Own AI Agent with LangGraph

AI Agent: A total integration of the latest AI technology! Implement various AI agents and learn to build your own AI agent using LangGraph.

(4.9) 31 reviews

313 learners

  • AISchool
ai활용
에이전트
LangGraph
AI Agent
LangChain
RAG
openAI API

Reviews from Early Learners

What you will learn!

  • How to Implement AI Agents Using LangGraph

  • Concept and Use Cases of AI Agents

  • Various AI Agent Architectures

  • Building my own AI Agent with LangGraph

  • How to build an advanced RAG system with LangGraph

AI Agent, a culmination of the latest AI technologies!
By implementing various AI agents, you will learn how to implement your own AI agent using LangGraph.

By creating various AI agents with LangGraph, you will gradually learn the components and various architectures required to implement AI agents.

  • Learn how to use the LangGraph library.

  • Learn how to implement your own AI agent using LangGraph.

Who is this course for?

Anyone who wants to create their own AI agent with LangGraph

Anyone who wants to learn various AI agent architectures to build a deep RAG system

Anyone who wants to develop a service using the latest LLM model

Player Course

👋 This course requires prior knowledge of Python, Natural Language Processing (NLP), LLM, and LangChain. Please take the following courses first, or acquire equivalent knowledge before taking this course.

Large Language Model for Everyone Part 2 - Building Your Own ChatGPT with LangChain

Q&A 💬

Q. What is an AI agent?

An AI agent is a software program that operates autonomously within a specific environment and performs tasks to achieve a given goal. This agent perceives its surroundings , makes decisions based on those decisions, takes actions , evaluates the results, learns, and evolves to make better decisions. An AI agent primarily consists of the following core components.


1. Environment

This refers to the external world with which the agent interacts. This can be a physical environment or a virtual environment within a software system. AI agents collect data from this environment and make decisions based on that data.


2. Sensors

AI agents gather information from their environment through sensors. For physical robots, these sensors can be hardware like cameras or microphones, while for software agents, they can gather information from APIs or databases.


3. Actuators

An agent is a tool or method used to influence its environment. For example, a robot can control mechanical devices like arms or wheels to take physical actions, while a software agent can execute code or manipulate data to produce results.


4. Goals

AI agents typically have one or more goals. These goals guide the agent to complete a specific task or reach a specific state in the environment. These goals can be explicitly stated or learned through techniques like reinforcement learning.


5. Action & Decision Making

AI agents analyze information received from the environment and make optimal decisions among possible actions to achieve a given goal. This can be a rule-based system or a complex algorithm such as reinforcement learning or deep neural networks.


6. Learning

Through learning, AI agents improve their performance over time. A prime example is using machine learning techniques to learn from past experiences to make better decisions. This allows the agent to quickly adapt to changes in the environment and improve its behavioral strategies.


Q. Is player knowledge required?

This lecture [Large Language Model for Everyone LLM Part 5 - Building Your Own AI Agent with LangGraph] covers how to build AI agents using the LangGraph library and LLM . Therefore, the lecture proceeds under the assumption that you have basic knowledge of Python, natural language processing, LLM, and LangChain. Therefore, if you lack prior knowledge, we recommend taking the preceding lecture [ Large Language Model for Everyone LLM (Large Language Model) Part 2 - Building Your Own ChatGPT with LangChain] first.

Recommended for
these people

Who is this course right for?

  • Deep Learning Research Job Aspirants

  • Person wishing to pursue AI/Deep Learning research

  • Those preparing for AI graduate school

  • Want to build your own AI agent with LangGraph.

  • For those wanting to build an advanced RAG system using LangGraph, beyond basic ones.

Need to know before starting?

  • Python experience

  • Pre-course [Large Language Model LLM(Large Language Model) for Everyone Part 2 - Creating My Own ChatGPT with LangChain] Course Experience

Hello
This is

9,083

Learners

668

Reviews

351

Answers

4.6

Rating

29

Courses

Curriculum

All

67 lectures ∙ (17hr 56min)

Course Materials:

Lecture resources
Published: 
Last updated: 

Reviews

All

31 reviews

4.9

31 reviews

  • songhunhan968882님의 프로필 이미지
    songhunhan968882

    Reviews 1

    Average Rating 5.0

    5

    38% enrolled

    Among the AI courses I've taken on various platforms like Inflearn and Fastcampus, this is the most satisfying. It's also the most relevant to my company's projects.

    • hsc650031님의 프로필 이미지
      hsc650031

      Reviews 1

      Average Rating 4.0

      4

      39% enrolled

      Everything else is fine. I think it would be good to also upload the post-release materials used in the presentation. Other than the post-release materials.

      • kwangchoon9989님의 프로필 이미지
        kwangchoon9989

        Reviews 1

        Average Rating 5.0

        5

        98% enrolled

        It was a beneficial lecture that provided practical help in advanced learning on building AI agents using LangGraph, allowing me to learn about the latest technologies and various use cases.

        • canflight0080096님의 프로필 이미지
          canflight0080096

          Reviews 7

          Average Rating 5.0

          5

          5% enrolled

          I believe there are very few courses that offer such a well-structured education in learning LLMs. Since the concepts are difficult, I think the order in which you acquire knowledge is important. Not only this lecture but also the "Natural Language Processing from Examples" class are all high quality, so I would like to actively recommend them to anyone reading this.

          • codenavi님의 프로필 이미지
            codenavi

            Reviews 1

            Average Rating 5.0

            5

            7% enrolled

            The lecture slides and Colab notebooks for practice made it easy to follow along. I was able to understand well because you explained only the necessary content. I liked the lecture style that focused on the core without any unnecessary details. I liked that I could immediately apply what I learned because of the practice-oriented structure. I hope there will be more lectures with this structure in the future!

            $59.40

            AISchool's other courses

            Check out other courses by the instructor!

            Similar courses

            Explore other courses in the same field!