Practical learning repo

Learn AI engineering by building real projects, not just reading theory.

This repository walks from first LLM integrations to Spring AI apps, LangChain tooling, LangGraph workflows, MCP experiments, vector databases, RAG pipelines, and end-to-end products.

Open GitHub Repo Start the Journey

Learning journey

Follow the repo from core concepts to applied AI systems

Each numbered folder acts like a lesson milestone. Start at the beginning or jump to the topic you need most.

01

First AI code

Introductory Java demos and first interactions with model APIs.

 02

SDK exploration

OpenAI, Gemini, and Ollama examples at the SDK level.

 03

Embeddings and vectors

Embedding generation and vector representation basics.

 04

Spring AI basics

First Spring Boot integrations with AI model providers.

 05

LangChain foundations

Core chaining patterns and simple Python LLM workflows.

 06

Spring AI embeddings

Embedding workflows and a conversational UI example.

 07

Chat memory

Conversation memory and stateful LangChain demos.

 08

Vector databases

Spring AI with vector stores, retrieval, and tool examples.

 09

RAG with Spring AI

Retrieval-augmented generation using Spring Boot projects.

 10

RAG with LangChain

LangChain-based retrieval pipelines and study notes.

 11

Tool calling

Spring AI projects that call custom tools and utilities.

 12

LangChain tools

Tool-calling demos and project setup in Python.

 13

More tool orchestration

Additional tool-driven Python workflows and examples.

 14

MCP introduction

First MCP-oriented Spring AI demos and configuration patterns.

 15

MCP demo apps

MCP server and client examples using Spring Boot.

 15B

Custom MCP plus LangChain

Custom filesystem and MCP server experiments in Python.

 16

MCP with LangChain

Combined MCP and LangChain workflows and tooling.

 17

AI agents

LangChain agent examples and multi-tool workflows.

 18

LangGraph multi-agent flows

Workflow orchestration and agent collaboration patterns.

 19

Sequential workflows

Step-by-step execution graphs and guided task flows.

 20

Parallel workflows

Concurrent task execution and reporting examples.

 21

Java e-commerce AI project

Backend, frontend, and AI-assisted product workflows.

 22

Python e-commerce AI project

LangChain-based project evolution with full-stack pieces.

 23

Hugging Face and fine-tuning

Notebook-based experimentation with model tuning workflows.

Standout builds

Jump straight into the most complete projects

These projects are the best starting point if you want full application examples instead of smaller lesson snapshots.

My Personal Tutor

A Spring AI tutor app with chat, ingestion, memory, retrieval, and MariaDB-backed data handling.

SpringEcomAI

Spring Boot e-commerce backend with AI-powered search, chatbot capability, and image generation flow.

SpringEcomAI-LangChain

Python and LangChain variant of the e-commerce AI project for learners comparing stacks.

LANGGRAPH-DEMO

One folder with multiple LangGraph workflow examples, diagrams, and runnable scripts.

MCP Demo

A client-side MCP integration example for understanding how tool-enabled apps connect to MCP servers.

MCP Server

Server-side MCP implementation examples with practical tools like date, news, and stock helpers.

Setup basics

What you need before running the examples

This repo mixes Java, Python, and frontend projects, so use each folder as its own runnable unit.

Java and Spring Boot

Most Java projects include Maven wrappers, so you can run them from the project directory with:

mvnw.cmd spring-boot:run

Projects using Spring AI usually need `OPENAI_API_KEY` or another provider key set locally.

Python projects

Create a virtual environment inside the specific project folder, then install dependencies from `pyproject.toml`, `requirements.txt`, or `uv.lock`.

python -m venv .venv

Frontend apps

The frontend examples are mainly in `21_Project/e-com-Frontend` and `22_Project/e-com-Frontend`.

npm install && npm run dev

Databases and keys

Some examples expect MariaDB locally, and AI-powered demos require your own provider keys added to local env or config files.

Study guide

How to get the most from this repository

Start from module 01

If you are new to AI engineering, move in number order so each folder builds on the last one.

Use project READMEs

Several folders already contain local `README.md` files with project-specific setup notes.

Treat folders independently

Most folders are separate experiments or mini-projects rather than one shared application.

Learn by comparing stacks

The repo includes both Java and Python paths to similar AI patterns, which makes comparison easy.