From Java Dev to AI Engineer: Spring AI Fast Track

Spring AI – Say Hello to AI in Spring Boot
1 Course Introduction
2 What is Spring AI Framework
3 Hello World Spring AI app with OpenAI – Part 1
4 Hello World Spring AI app with OpenAI – Part 2
5 Deep dive on ChatModel and ChatClient
6 Building a Hello World App with Spring AI and Ollama
7 Building a Hello World App with Spring AI and Docker
8 Building a Hello World App with Spring AI and AWS Bedrock – Part 1
9 Building a Hello World App with Spring AI and AWS Bedrock – Part 2
10 Working with Multiple Chat Models in Spring AI

Spring AI Essentials – Prompts, Advisors, and Structured Responses
11 Understanding Message Roles in LLMs – Theory
12 Understanding Message Roles in LLMs – Demo
13 What Are Defaults in Spring AI
14 Using Prompt Templates in Spring AI
15 Using Prompt Stuffing technique
16 Why Prompt Stuffing Isn’t Meant for Big Data
17 Understanding Advisors in Spring AI Workflows
18 Spring AI Built-in Advisors – Plug and Play Intelligence
19 Custom Advisors in Spring AI – Make the AI Work Your Way
20 Understanding ChatOptions in Spring AI
21 Configuring ChatOptions in Spring AI
22 Spring AI ChatClient – Response Types Explained
23 Streaming AI Responses in Real-Time using stream() Method
24 From Text to Types – Mastering Structured Output in Spring AI
25 From AI Text to Java Objects – Spring AI Structured Output Demo
26 Using Bean, List, and Map Output Converters in Spring AI
27 Mapping AI Response to ListPOJO using ParameterizedTypeReference

Foundations of Generative AI and LLMs
28 Tracing the Roots – How We Reached Generative AI
29 Meet the Gen AI Family – AI, ML, DL, and Beyond
30 Funny memes of AI
31 Types of Generative AI Models
32 Introduction to Large Language Models – The Text Experts
33 Core job of an LLM – Guessing next word
34 The concept of Tokens & Token IDs in LLM
35 Inside an LLM’s Dictionary – Understanding Model Vocabulary
36 Embeddings & Vectors – A way to represent meaning
37 How Embedding Vectors calculated
38 What are Static Embeddings
39 Positional Embeddings – How AI Understands Word Order
40 The Magic of Attention – How AI Understands Context

Teaching LLMs to Remember – The Power of Chat Memory in Spring AI
41 LLMs Don’t Remember You – The Stateless Nature of AI Models
42 LLMs Forget Everything — ChatMemory to the Rescue!
43 Making ChatClient ‘Remember’ – Spring AI’s Memory Advisors
44 From Stateless to Stateful – Spring AI Memory in Action
45 Per-User Memory in LLMs – Thanks to CONVERSATION_ID!
46 Chat Memory That Lasts – Spring AI with JDBC-Based Persistence
47 Using maxMessages to Limit Chat History in Spring AI
48 Avoiding Token Overload – Use maxMessages with Context Window size in Mind

The Art of Talking to Documents – RAG Unleashed
49 From Prompt Stuffing to RAG – A Better Way to Feed LLMs
50 Understanding the RAG flow
51 Meet the Vector Database – Storing Meaning, Not Just Data
52 Setting Up Qdrant Vector Store with Spring Boot Using Docker Compose
53 Demo of RAG using random text data – Part 1
54 Demo of RAG using random text data – Part 2
55 Demo of RAG using random text data – Part 3
56 Let’s talk to documents using RAG
57 Breaking Down Big Documents – The Art of Chunking for LLMs
58 RAG Made Easy – RetrievalAugmentationAdvisor in Action
59 RAG flow with Web Search – Part 1
60 RAG flow with Web Search – Part 2
61 Advanced RAG with Pre-Retrieval
62 Advanced RAG with Post-Retrieval
63 Who calculates the embedding values of the documents

Tool Calling in Action – Giving LLMs the Power to Do Things
64 Introduction to Tool Calling in AI
65 LLMs vs Reality – The Time Question They Can’t Answer
66 Tool Calling in Action – Teaching LLMs to Tell the Time
67 How the Tools get called by LLM internally
68 Letting LLMs Talk to Databases – A Tool Calling Demo – Part 1
69 Letting LLMs Talk to Databases – A Tool Calling Demo – Part 2
70 Letting LLMs Talk to Databases – A Tool Calling Demo – Part 3
71 Bypass the Model – Returning Tool Results Directly to the User
72 Graceful Failure – Customizing Tool Error Responses in Spring AI
73 Generative AI’s Journey – From Static Chat to Dynamic Intelligence

Mastering Model Context Protocol (MCP)
74 The Missing Link in AI Apps – Understanding the Need for MCP
75 Inside MCP – Understanding the Architecture of Model Context Protocol
76 Behind the Scenes of MCP Communication – Built-in Transport Logic
77 Building an MCP Client with Spring AI
78 Demo of MCP Client and MCP Server integration
79 Meet the MCP Inspector – The X-Ray Tool of MCP Server
80 Demo of integration with GitHub MCP Server
81 Building an MCP Server using STDIO – Part 1
82 Building an MCP Server using STDIO – Part 2
83 Building an MCP Server using remote invocation

From Testing to Production – Making AI Answers Safer with Evaluators
84 Testing the Untestable – Evaluating LLM Responses with Spring AI
85 Building Trustworthy AI with RelevancyEvaluator and FactCheckingEvaluator
86 RelevancyEvaluator Demo – Ensuring LLMs Stay on Topic
87 FactCheckingEvaluator in Action – Catching AI Hallucinations
88 Using Spring AI Evaluator in a RAG Scenario
89 Catching Bad LLM Answers in Production with Runtime Checks
90 Runtime Validation with Spring AI Evaluator and Spring Retry

Observability in Spring AI – Metrics, Monitoring & Tracing
91 Introduction to monitoring AI Operations
92 Enabling Metrics in Spring AI with Spring Boot Actuator – Part 1
93 Enabling Metrics in Spring AI with Spring Boot Actuator – Part 2
94 Enabling Prometheus Monitoring in Spring AI – Part 1
95 Enabling Prometheus Monitoring in Spring AI – Part 2
96 Setting Up Grafana Dashboard for Spring AI Metrics
97 Tracing AI Operations using OTLP & Jaeger – Part 1
98 Tracing AI Operations using OTLP & Jaeger – Part 2

Transcription, Speech, and Image Generation using Spring AI
99 From Voice to Text – Using Spring AI for Transcription – Part 1
100 From Voice to Text – Using Spring AI for Transcription – Part 2
101 From Text to Speech – Generating Voices with SpeechModel
102 From Prompt to Picture – Image Generation with ImageModel

Thank You & Congratulations
103 Thank You & Congratulations