Teach on Udemy

Turn what you know into an opportunity and reach millions around the world.

Learn More

Your cart is empty.

Keep shopping

Complete GenAI with Java & Spring AI: LLMs, RAG, AI Agents

Name: Complete GenAI with Java & Spring AI: LLMs, RAG, AI Agents
Rating: 4.4 (110 reviews)

Build production-ready Generative AI applications with Spring AI - LLM, RAG, AI agents, Chat memory, MCP, Observability

Bestseller

Role Play

Created byAli Gelenler, EA Algorithm

Last updated 5/2026

English

What you'll learn

Learn and implement GenAI applications using Java and Spring AI
Learn how to call remote Large Language Models using Open AI, Google Gemini and Hugging Face APIs
Learn how to call local Large Language Models using Ollama and Docker Model Runner
Learn and implement Spring AI advanced concepts: Streaming, Structured output, Chat options, Advisors, Prompt templates
Learn Prompt engineering best practices including zero/one/few shot, CoT, changing creativity(temperature), controlled variability(top-p,) limiting tokens
Learn Prompt hacking techniques and their mitigation strategies: Prompt injection, Jailbreaking, Prompt leaking and Advanced hacking techniques
Understand GenAI and LLM fundamentals: Tokenizers, Embeddings, Positional encoding, Transformer architecture, Token prediction and Softmax formula
Understand chat memory and implement with multiple backends using Spring AI: In-memory and Jdbc for short-term memory, Vector store for long-term memory
Learn and implement multimodality using text, image and sound conversion use cases
Understand LLM limitations and their possible mitigations
Learn and implement advanced RAG systems
Learn and implement AI Agent systems with autonomous and chained workflow agentic systems
Learn and implement Human-in-the-loop patter in AI Agent systems
Understand MCP (Model Context Protocol) and implement MCP server and MCP client applications using Spring AI
Understand and apply Observability to RAG and AI Agent systems using Spring Observability

Course content

15 sections • 135 lectures • 25h 51m total length

Course structure & Outline4:29
Build your first Spring AI app in 5 minutes3:40
Learning paths: How to navigate this course based on your goals2:46
What you will build: Basic use cases6:37
What you will build: Advanced use cases6:22
Setting up the environment5:35
Source code repository, presentations & diagrams0:11
How Spring AI can provide necessary functionality to GenAI applications
GenAI and Spring AI basics

Spring AI Introduction4:40
Setting up Open AI API Key4:41
Creating the first Spring AI application with ChatClient configuration12:25
Summarizer use case with Open AI API8:51
Exploring the ChatClient response types: Content vs ChatClientResponse8:00
Using in-place prompt template for secure and simplified Summarizer use case4:11
Using a Java Http Client to call Open AI API14:44
Using multiple AI models in Spring AI3:43
Java Doc comment generator use case with Google Gemini Vertex AI17:38
Introduction to Hugging Face3:31
Programming helper assistant use case with Hugging Face Qwen model - Part 115:36
Programming helper assistant use case with Hugging Face Qwen model - Part 217:53
Open Source Large Language Models6:58
Introduction to Ollama11:21
Email Drafting use case with Ollama and Mistral model16:54
Linkedin Post Generator use case with Docker Model Runner and Gemma3 model11:30
Using OpenWebUI for local LLMs6:36
Spring AI ChatClient and ChatModel implementation details16:34
Spring AI Advisor Architecture and Message Types implementation details12:23
How Spring AI enables calling remote and local Large Language Models
Understanding how to develop AI Assistants with Spring AI

Streaming response with Summarizer use case14:30
Spring AI response types2:42
Structured Output in Spring AI18:12
Chat Options Part-1: Model and Max Token properties14:02
Chat Options Part-2: Temperature property, LLM Non-determinism and randomness17:32
Chat Options Part-3: Top-p & Top-K for controlled randomness & stop sequences15:00
Advisor Architecture Details & Adding SimpleLoggerAdvisor to Summarizer use case11:02
Adding SafeGuardAdvisor to Summarizer use case7:39
Adding Custom Error Wrapping Advisor to Summarizer use case13:39
Adding Custom System Advisor to Summarizer use case8:41
Adding Custom Validation Advisor to Summarizer use case10:20
Advanced Spring AI concepts: streaming, structured output,chat options, advisors
Understanding advanced Spring AI concepts

Prompt Injection with Summarizer use case and Lakera Gandalf9:10
Jailbreaking with Summarizer use case using a Tool call10:09
Prompt leaking with Summarizer use case2:45
Advanced prompt hacking techniques: Context switching & Dictionary attack7:21
Prevention and Mitigation steps for Prompt hacking attacks14:04
Prompt Injection, Jailbreaking and Prompt Injection together with Mitigations
Understanding Prompt Hacking and Mitigation Strategies

Introduction to Chat Memory with Spring AI in-memory implementation18:22
Order Status Helper use case with in-memory chat memory implementation: Part-114:21
Order Status Helper use case with in-memory chat memory implementation: Part-210:07
Using Jdbc chat memory implementation for Order Status Helper use case15:43
Using Vector Store for long-term memory with PgVector: Part-113:45
Using Vector Store for long-term memory with PgVector: Part-213:44
Using Prompt Chat Memory Advisor & Recap of Chat Memory Advisors: Part-19:26
Using Prompt Chat Memory Advisor & Recap of Chat Memory Advisors: Part-28:39
Chat memory options: short-term vs long-term using Spring AI abstraction
Understanding Chat Memory in AI applications with Spring AI abstraction

Introduction to Multimodality in Spring AI5:18
Visual Compliance Checker: Image-to-Text use case with Open AI API10:45
Marketing Asset Generator: Text-to-Image use case with Open AI dall-e-3 model12:57
Smart Meeting Assistant: Speech-to-Text use case with whisper-1 & gpt-4o14:44
Ticket Status Provider on Voice: Text-to-Speech use case with tts-1 & gpt-4o15:29
Multimodality and Spring AI implementations
Understanding multimodality in AI applications

IT Support use case with In-Prompt Context (Prompt Stuffing)11:15
Introduction to RAG5:51
Employee Handbook use case with Simple Rag Flow - Ingestion pipeline: Part-114:21
Employee Handbook use case with Simple Rag Flow - Ingestion pipeline: Part-214:51
Employee Handbook use case with Simple Rag Flow - Retrieval pipeline: Part-19:42
Employee Handbook use case with Simple Rag Flow - Retrieval pipeline: Part-215:18
Tokenizer & Splitter 101: Part-116:17
Tokenizer & Splitter 101: Part-213:28
Embeddings 10111:26
Vector Databases 1014:29
Similarity (Semantic) Search 1015:09
Internal Q/A use case with Advanced RAG Flow: Dependency, Config and Input Files14:01
Adding Bean configurations for RetrievalAugmentationAdvisor and PgVectorStore12:46
Internal Q/A use case with Advanced RAG Flow - Ingestion Pipeline: Part-114:37
Internal Q/A use case with Advanced RAG Flow - Ingestion Pipeline: Part-214:47
Internal Q/A use case - Retrieval Pipeline with metadata filtering12:52
Internal Q/A use case - Adding Query transformer to Retrieval Pipeline15:05
Internal Q/A use case - Adding Neighbour Stitching to Retrieval Pipeline: Part-114:36
Internal Q/A use case - Adding Neighbour Stitching to Retrieval Pipeline: Part-215:25
Internal Q/A use case - Adding Citation Header to Retrieval Pipeline10:09
Internal Q/A use case - Adding Query Expander to Retrieval Pipeline14:09
Internal Q/A use case - Adding Reranker to Retrieval Pipeline: Part-116:54
Internal Q/A use case - Adding Reranker to Retrieval Pipeline: Part-218:22
Internal Q/A use case - Adding Update/Delete methods to Ingestion Pipeline20:15
Internal Q/A use case - Adding Pdf Watcher Service for dynamic RAG file updates18:54
Designing and implementing an advanced RAG ingestion and retrieval pipelines
Understanding how to design and implement an advanced RAG pipeline

Requirements

Basic to intermediate knowledge of Java
Familiarity with Spring Boot
Experience with backend development concepts
Basic familiarity with AI/LLM concepts

Description

Want to build real-world Generative AI (GenAI) applications with Java, Spring Boot, Spring AI, RAG and AI Agents—not just experiment with prompts?

This course will take you from fundamentals to production-ready AI systems, including RAG pipelines, AI agents, tool calling, chat memory, MCP, observability, prompt engineering, and prompt hacking.

Hi there! My name is Ali Gelenler. I'm here to help you learn GenAI using Java and Spring AI from fundamentals to real-world production ready AI architectures and systems with a practical approach.

Even if you are not a daily Java developer, this course can still help you understand how production-ready GenAI systems are designed and implemented in a structured backend environment.

In this course, you will focus on creating AI applications to go beyond AI generated code and implement over 20 use cases using Java and Spring AI together with various AI providers and models, such as Open AI, Google Gemini Vertex AI, Hugging Face, Ollama and Docker Model Runner. You will build AI applications and AI systems using LLMs (Large Language Models), integrate vector databases and embeddings, and design scalable backend architectures for Generative AI.

The course also includes production-ready Agentic AI design with tool calling, workflow design, chaining, decision control, human-in-the-loop steps, and MCP integration.

You will learn:

Building end-to-end GenAI systems in Java and Spring AI with advanced Spring AI concepts
Designing RAG pipelines with vector databases, embeddings, similarity search and semantic search using advanced ingestion and retrieval strategies such as query transformer, query expander, pre/post processors, re-ranker, metadata filtering and dynamic resource updates
Creating AI agents with tool/function calling using autonomous and chained workflow Agentic AI systems
Implementing Human-in-the-loop pattern in AI agents with checkpoint-based auto-progression with state machine
Implementing chat memory and long-term context with in-memory, jdbc and vector store backends using Spring AI advisors
Applying prompt engineering best practices and defend against prompt hacking techniques including prompt injection, jailbreaking and prompt leaking attacks
Using MCP (Model Context Protocol) for distributed AI systems, creating MCP Server and MCP client using Spring AI
Adding Observability (logs, traces, metrics) to AI applications
Learning Gen AI and LLM Fundamentals with Tokenizers, Embeddings, Positional encoding, Transformer architecture, Token prediction and Softmax formula
Mapping the Gen AI and LLM Fundamentals into practical solutions
Understanding LLM limitations and possible mitigations

You will implement 20+ real-world use cases, including:

AI-powered assistants: Summarizer, Java Doc generator, Programming helper, Email drafter, Post generator
Document Q&A systems with advanced RAG pipelines
Security review from architectural diagram AI agent system with multiple tools including Remote Mcp Server tool, Web tool, RAG tool and Diagram extract tool, implementing both autonomous and chained workflow agent systems with human approvals implementing human-in-the-loop pattern
Multimodal applications including Image-to-Text, Text-to-Image, Speech-to-Text and Text-to-Speech use cases
Order status helper with advanced chat memory strategies
Production-ready AI systems with monitoring and tracing

Technologies & tools you will use:

Java & Spring AI
Advanced Spring AI concepts: Streaming, Structured output, Chat options, Advisors, Prompt templates
OpenAI, Google Gemini (Vertex AI), Hugging Face APIs
Ollama & Docker Model Runner for local LLMs
Vector databases using PgVector
MCP (Model Context Protocol) with MCP Server and MCP Client implementations
Observability tools (Grafana, Prometheus, Otlp, Tempo, Jaeger, Loki and Promtail)

This is a practical and production-oriented course. You will not just generate code using AI tools—you will learn how to:

Design systems
Handle real-world limitations
Build scalable and maintainable AI applications

For more detailed information on the progress of this course, you can check the introductory video and free lessons, and if you decide to enroll in this course, you are always welcome to ask and discuss the concepts and implementation details on Q/A and messages sections. I will guide you from start to finish to help you successfully complete the course and gain as much knowledge and experience as possible from this course.

Support & updates

You can ask questions anytime in Q&A
The course will be continuously updated as Spring AI evolves
You’ll get guidance to fully understand and apply concepts

Remember! There is a 30-day full money-back guarantee for this course! So you can safely press the 'Buy this course' button with zero risk and join this learning journey with me.

Who this course is for:

Java / Spring Boot developers who want to integrate GenAI into real-world applications
Backend engineers looking to build production-ready AI applications with RAG pipelines and AI agent systems
Software engineers who want to move beyond AI-generated code and understand how GenAI systems actually work

Complete GenAI with Java & Spring AI: LLMs, RAG, AI Agents

What you'll learn

Explore related topics

Course content

Introduction8 lectures • 30min

Java & Spring AI: Basic GenAI Use Cases20 lectures • 3hr 18min

Advanced Spring AI Concepts12 lectures • 2hr 13min

Prompt Engineering4 lectures • 33min

Prompt Hacking6 lectures • 43min

GenAI and LLM Fundamentals8 lectures • 1hr 13min

Chat Memory9 lectures • 1hr 44min

Multimodality6 lectures • 59min

LLM Limitations & Mitigations3 lectures • 19min

RAG (Retrieval Augmented Generation)26 lectures • 5hr 35min

Requirements

Description

Who this course is for: