From Java Dev to AI Engineer: Spring AI Fast Track

Descripción

Are you ready to build AI-powered Java applications with real-world use cases? This hands-on course will teach you how to integrate cutting-edge AI capabilities into your Spring Boot applications using the Spring AI 2.x framework and OpenAI. You’ll master everything from building your first chat-based app to using Retrieval-Augmented Generation (RAG), Tool Calling, Structured Output Conversion, MCP (Model Context Protocol), and even Speech-to-Text, Text-to-Speech, and Image Generation — all using Java and Spring Boot. From understanding how LLMs work to deploying production-ready AI features with observability, testing, and advisor-based safety, this course is packed with powerful demos, clean explanations, and practical techniques to bring intelligence to your backend. Whether you're a Java developer, Spring enthusiast, or backend engineer exploring Generative AI, this course will guide you step-by-step with best practices and battle-tested code. What You’ll Learn: Section 1: Welcome & Hello World with Spring AI • Understand the Spring AI framework and course roadmap • Build your first Spring Boot AI app using OpenAI • Deep dive into ChatModel and ChatClient APIs Section 2: Prompt Engineering & Structured Output • Use message roles, prompt templates, and stuffing techniques • Work with advisors to control AI behavior • Map AI responses to Java Beans, Lists, and Maps Section 3: Generative AI & LLM Fundamentals • Learn about tokens, embeddings, and how LLMs generate text • Understand attention, vocabulary, and model internals • Explore static vs positional embeddings and context windows Section 4: AI Memory with ChatHistory • Implement stateless-to-stateful conversations • Use MemoryAdvisors and Conversation IDs for per-user memory • Persist chat memory using JDBC and configure maxMessages Section 5: RAG – Retrieval-Augmented Generation • Set up a vector store (Qdrant) using Docker • Store and query document embeddings in Spring Boot • Use RetrievalAugmentationAdvisor to feed documents to AI Section 6: Tool Calling – Let AI Take Action • Enable tool invocation via LLMs • Build tools for real-time actions like querying time or database • Customize tool errors and return responses to users Section 7: Model Context Protocol (MCP) • Learn MCP architecture and communication patterns • Build MCP Clients and Servers using Spring AI • Integrate with GitHub’s MCP Server and explore STDIO transport • MCP concepts including Tool Filtering, Logging, Tool Progress, Sampling, Elicitation Section 8: Testing & Validating AI Outputs • Use RelevancyEvaluator and FactCheckingEvaluator • Test AI responses for correctness in dev and production • Add runtime safety checks with Spring Retry Section 9: Observability – Monitoring AI Operations • Enable Spring Boot Actuator metrics for AI • Set up Prometheus & Grafana dashboards • Trace AI behavior with OpenTelemetry and Jaeger Section 10: Speech & Image Generation • Convert voice to text with AI-powered transcription • Generate natural speech from text prompts • Turn prompts into images using the ImageModel Section 11 : Capstone Project - Building a Real-World AI Agent

Lo que aprenderás

• Build Spring Boot applications powered by Spring AI
• Integrate Spring AI app with OpenAI, Ollama, Docker Model Runner, and AWS Bedrock
• Use prompt templates and prompt stuffing techniques
• Convert AI text responses to Java Beans, Lists, and Maps
• Understand how LLMs work internally with tokens and embeddings
• Implement Retrieval-Augmented Generation (RAG) with Spring AI
• Implement memory in chat apps using Spring AI advisors
• Teach LLMs to call tools exposed by Java methods
• Build both MCP clients and servers with Spring AI
• From Testing to Production – Making AI Answers Safer with Evaluators
• Observability in Spring AI – Metrics, Monitoring & Tracing
• Transcription, Speech, and Image Generation using Spring AI

Requisitos

• Knowledge on Java, Spring Boot is mandatory