JAVA AI DEVELOPMENT
Spring AI
Build production-ready AI applications with Spring Boot, from core AI concepts and model providers through RAG, tools, MCP and enterprise architecture.
Spring AI Learning Path
Follow the sections in order to move from AI fundamentals to reliable, observable and maintainable Spring AI systems.
AI & LLM Concepts Glossary — Read This First
Review the AI and LLM concepts that Spring Boot developers need before starting with Spring AI.
Section 1 — Spring AI Architecture
Understand the core abstractions, modules and architecture that make up Spring AI.
Section 2 — Prompt API
Learn how Spring AI models prompts, messages, roles and generation options.
Section 3 — ChatClient
Build conversational AI requests with Spring AI's fluent ChatClient API.
Section 4 — ChatModel: Multi-Provider Integration
Connect Spring AI applications to multiple chat model providers through a common API.
Section 5 — Embeddings
Understand embeddings and use Spring AI to turn text into useful vector representations.
Section 6 — Vector Store
Store, index and search embeddings with Spring AI vector store abstractions.
Section 7 — RAG in Spring AI
Build retrieval-augmented generation workflows with Spring AI, documents and vector search.
Section 8 — Memory
Add conversational memory and manage chat history in Spring AI applications.
Section 9 — Tool Calling
Enable Spring AI models to call application tools and work with external capabilities.
Section 10 — MCP Integration
Connect Spring AI applications to Model Context Protocol tools and resources.
Section 11 — Structured Output
Generate typed, structured responses from AI models using Spring AI converters.
Section 12 — Streaming
Stream model responses incrementally to build responsive Spring AI experiences.
Section 13 — Observability
Observe, trace and measure Spring AI applications in production.
Section 14 — Testing
Test Spring AI prompts, model interactions and application behavior reliably.
Section 15 — Security
Design secure Spring AI applications with protected data, tools and model access.
Section 16 — Performance
Improve latency, throughput and resource use in Spring AI applications.
Section 17 — Enterprise Architecture
Apply Spring AI patterns to resilient, maintainable and production-ready enterprise systems.