Everything about AI Agent Development Learned by Building a Chatbot (FastAPI, RAG, Vector, LangChain, sLLM/Fine-tuning)
You will learn about RAG, VectorDB, LangChain, OpenAI, sLLM, and fine-tuning, which encompass the most important AI-related technologies at this time.
11 learners are taking this course
Level Beginner
Course period Unlimited
What you will gain after the course
Understanding the entire lifecycle of AI Agents, including planning, design, and development
Principles of Vector DB and Vector Similarity
Practical Application and Hands-on Experience with LangChain in RAG
Understanding and Practice of sLLM (llama) and Fine-tuning (lora)
By directly implementing a shopping mall customer center chatbot service, you will learn the most critical elements of current AI services, including RAG, Vector DB, LangChain, sLLM, and LoRA fine-tuning, through a real-world service workflow.
Backend
- - FastAPI
- - PostgreSQL
AI
- - RAG
- - LangChain
- - pgVector
- - OpenAI
sLLM &
Fine-tune
- - Ollama/Llama3.2
- - PEFT/LoRA
- - RunPod
- - Hugging Face
It doesn't just end with "making a single chatbot." We assume a real shopping mall customer center and design different processing paths depending on the nature of the question.
FastAPI + OpenAI
- Understand the FastAPI project structure
- OpenAI API integration and utilizing Tool Calling
RAG + LangChain
- Basics of RAG, principles of vectors and cosine similarity, embeddings and vector DBs
- Building a document loading/chunking/embedding/storage/retrieval (Retriever) pipeline with LangChain
RAG Optimization Strategies (Advanced)
- Reflecting follow-up question context through conversation history management (Window memory)
- Reduce token costs and optimize response latency with Semantic Caching (Redis Stack). If a question is similar, return a cached response without calling the LLM.
- Introduction to Hybrid Search (Dense + Sparse/BM25) concepts and Ranking Fusion (RRF)
sLLM + Fine-tuning
- Introducing local sLLMs because calling external commercial LLMs can be risky for sensitive information
- Run Llama models with Ollama and generate responses by calling them from the server via API
- Enhancing sLLM model accuracy with PEFT/LoRA fine-tuning
- Generating adapters and uploading merged models using Hugging Face
- Hands-on practice from training to uploading and testing in a RunPod GPU environment
sLLM
Fine-tuning
Recommended for
these people
Who is this course right for?
Planners, PMs, etc., who want to understand the latest AI trends from a technical perspective
An entry-level AI developer with absolutely no foundation in Vector DB, RAG, LangChain, sLLM, or fine-tuning.
Developers who are familiar with RAG and LangChain but need advanced AI agent strategies for search optimization, such as caching and token reduction.
Hello
This is bradkim
Inflearn Verified
Career Verified
3,677
Learners
399
Reviews
133
Answers
4.9
Rating
11
Courses
💪💪💪An expert with both practical and teaching experience 💪💪💪
Hello, I'm Seonguk Kim. I graduated from Yonsei University and have worked as a software engineer at major corporations and startups. Currently, I am working as a full-time instructor for corporate training and bootcamps. As an instructor with both practical and teaching experience, I will deliver essential knowledge in an easy-to-understand manner.
Profile : https://www.linkedin.com/in/seongukkim
Corporate training inquiries: ksg39412@naver.com
Curriculum
All
26 lectures ∙ (8hr 26min)
6. RAG Overview
11:00
8. Vector Similarity
09:45
9. Embedding
16:21
10. Vector DB
13:13
Reviews
bradkim's other courses
Check out other courses by the instructor!
Similar courses
Explore other courses in the same field!





![Just 1 hour! Creating 'My Own AI Senior Developer' to install on my computer (Antigravity Vibe Coding) [Source code provided]Course Thumbnail](https://cdn.inflearn.com/public/files/courses/340332/cover/ai/3/e87ee52b-1099-42db-a384-64ab8c725470.png?w=420)

