Learn the core concepts of generative AI, including foundation models, large language models (LLMs), prompts, and the token-based prediction process.
Discover why frameworks are crucial for integrating AI, providing high-level abstractions for REST APIs, structured outputs, and easy model switching.
Get an overview of the Java AI ecosystem, comparing the key features and origins of LangChain4j, Spring AI, and Microsoft's Semantic Kernel.
See a practical implementation of an AI-powered recipe finder using LangChain4j, from low-level models to the high-level, declarative AI Service abstraction.
Explore how to build the same recipe finder application using Spring AI's fluent ChatClient API for a streamlined, builder-pattern approach to AI calls.
Understand common LLM limitations like context size and lack of custom knowledge, and learn about advanced patterns like RAG and tool calling to solve them.
Learn how to implement retrieval-augmented generation (RAG) and tool calling in LangChain4j using its built-in abstractions like the EmbeddingStoreIngester and @Tool annotation.
Discover how Spring AI handles advanced patterns by using the ChatClient's fluent API for tool registration and the Advisor concept for implementing RAG.
Get a glimpse into the future of autonomous AI agents and how the Model Context Protocol (MCP) aims to standardize interactions between different AI services.
32:14Timo Salm & Sandra Ahlgrimm
29:18Daniel Oh & Kevin Dubois
32:02Kevin Dubois
31:59Juarez Junior
25:17Scott Hanselman
35:16Ankit Patel
30:38Alex Soto
30:01Mario Fusco
Jobs that call for the skills explored in this talk.
