microsoft/LangChain4j-for-Beginners

microsoft/LangChain4j-for-Beginners

Description: A course for AI applications with LangChain4j from simple chat to AI agents.

Language: Java

License: MIT

Stars: 369

Forks: 142

Open issues: 0

Created: 2025-10-24T12:34:24Z

Pushed: 2026-06-06T18:49:25Z

Default branch: main

Fork: no

Archived: no

README:

LangChain4j for Beginners

A course for building AI applications with LangChain4j and Azure OpenAI GPT-5.2, from basic chat to AI agents.

🌐 Multi-Language Support

Supported via GitHub Action (Automated & Always Up-to-Date)

[Arabic](./translations/ar/README.md) | [Bengali](./translations/bn/README.md) | [Bulgarian](./translations/bg/README.md) | [Burmese (Myanmar)](./translations/my/README.md) | [Chinese (Simplified)](./translations/zh-CN/README.md) | [Chinese (Traditional, Hong Kong)](./translations/zh-HK/README.md) | [Chinese (Traditional, Macau)](./translations/zh-MO/README.md) | [Chinese (Traditional, Taiwan)](./translations/zh-TW/README.md) | [Croatian](./translations/hr/README.md) | [Czech](./translations/cs/README.md) | [Danish](./translations/da/README.md) | [Dutch](./translations/nl/README.md) | [Estonian](./translations/et/README.md) | [Finnish](./translations/fi/README.md) | [French](./translations/fr/README.md) | [German](./translations/de/README.md) | [Greek](./translations/el/README.md) | [Hebrew](./translations/he/README.md) | [Hindi](./translations/hi/README.md) | [Hungarian](./translations/hu/README.md) | [Indonesian](./translations/id/README.md) | [Italian](./translations/it/README.md) | [Japanese](./translations/ja/README.md) | [Kannada](./translations/kn/README.md) | [Khmer](./translations/km/README.md) | [Korean](./translations/ko/README.md) | [Lithuanian](./translations/lt/README.md) | [Malay](./translations/ms/README.md) | [Malayalam](./translations/ml/README.md) | [Marathi](./translations/mr/README.md) | [Nepali](./translations/ne/README.md) | [Nigerian Pidgin](./translations/pcm/README.md) | [Norwegian](./translations/no/README.md) | [Persian (Farsi)](./translations/fa/README.md) | [Polish](./translations/pl/README.md) | [Portuguese (Brazil)](./translations/pt-BR/README.md) | [Portuguese (Portugal)](./translations/pt-PT/README.md) | [Punjabi (Gurmukhi)](./translations/pa/README.md) | [Romanian](./translations/ro/README.md) | [Russian](./translations/ru/README.md) | [Serbian (Cyrillic)](./translations/sr/README.md) | [Slovak](./translations/sk/README.md) | [Slovenian](./translations/sl/README.md) | [Spanish](./translations/es/README.md) | [Swahili](./translations/sw/README.md) | [Swedish](./translations/sv/README.md) | [Tagalog (Filipino)](./translations/tl/README.md) | [Tamil](./translations/ta/README.md) | [Telugu](./translations/te/README.md) | [Thai](./translations/th/README.md) | [Turkish](./translations/tr/README.md) | [Ukrainian](./translations/uk/README.md) | [Urdu](./translations/ur/README.md) | [Vietnamese](./translations/vi/README.md)

> Prefer to Clone Locally? > > This repository includes 50+ language translations which significantly increases the download size. To clone without translations, use sparse checkout: > > Bash / macOS / Linux: > ``bash > git clone --filter=blob:none --sparse https://github.com/microsoft/LangChain4j-for-Beginners.git > cd LangChain4j-for-Beginners > git sparse-checkout set --no-cone '/*' '!translations' '!translated_images' > > > **CMD (Windows):** > cmd > git clone --filter=blob:none --sparse https://github.com/microsoft/LangChain4j-for-Beginners.git > cd LangChain4j-for-Beginners > git sparse-checkout set --no-cone "/*" "!translations" "!translated_images" > `` > > This gives you everything you need to complete the course with a much faster download.

Table of Contents

1. [Quick Start](00-quick-start/README.md) - Get started with LangChain4j 2. [Introduction](01-introduction/README.md) - Learn the fundamentals of LangChain4j 3. [Prompt Engineering](02-prompt-engineering/README.md) - Master effective prompt design 4. [RAG (Retrieval-Augmented Generation)](03-rag/README.md) - Build intelligent knowledge-based systems 5. [Tools](04-tools/README.md) - Integrate external tools and simple assistants 6. [MCP (Model Context Protocol)](05-mcp/README.md) - Work with the Model Context Protocol (MCP) and Agentic modules

Video Walkthroughs

Each module has a companion live session where we walk through the concepts and code step by step.

| Module | Video | |--------|-------| | 01 - Introduction | Getting Started with LangChain4j | | 02 - Prompt Engineering | Prompt Engineering with LangChain4j | | 03 - RAG | RAG with LangChain4j | | 04 - Tools & 05 - MCP | AI Agents with Tools and MCP |

---

Learning Path

New to LangChain4j? Check out the [Glossary](docs/GLOSSARY.md) for definitions of key terms and concepts.

> Quick Start

1. Fork this repository to your GitHub account 2. Click Code → Codespaces tab → ... → New with options... 3. Use the defaults – this will select the Development container created for this course 4. Click Create codespace 5. Wait 5-10 minutes for the environment to be ready 6. Jump straight to [Quick Start](./00-quick-start/README.md) to get started!

After completing the modules, explore the [Testing Guide](docs/TESTING.md) to see LangChain4j testing concepts in action.

> Note: This training uses both GitHub Models and Azure OpenAI. The [Quick Start](00-quick-start/README.md) module uses GitHub Models (no Azure subscription required), while modules 1-5 use Azure OpenAI. Get started with a FREE Azure account if you don't have one.

Learning with GitHub Copilot

To quickly start coding, open this project in a GitHub Codespace or your local IDE with the provided devcontainer. The devcontainer used in this course comes pre-configured with GitHub Copilot for AI paired programming.

Each code example includes suggested questions you can ask GitHub Copilot to deepen your understanding. Look for the 💡/🤖 prompts in:

• Java file headers - Questions specific to each example
• Module READMEs - Exploration prompts after code examples

How to use: Open any code file and ask Copilot the suggested questions. It has full context of the codebase and can explain, extend, and suggest alternatives.…