World Congress 2024 • Aug 20, 2024 • Session details

Building AI-Driven Spring Applications With Spring AI

Sandra Ahlgrimm , Timo Salm

Tired of AI vendor lock-in? Spring AI treats LLMs like swappable dependencies. Discover how to easily build RAG pipelines and map JSON strings to strongly-typed Java objects.

Pause
Mute Enter Fullscreen
#1 about 2 min

Session overview and setup for building AI applications

Introduction to the speakers and the agenda for building applications with Spring AI.

#2 about 2 min

Evolution from artificial intelligence to generative AI models

How the history of artificial intelligence progressed from early machine learning to modern deep learning and generative models.

#3 about 2 min

Comparing traditional machine learning with flexible foundation models

Why foundation models offer flexible, reusable alternatives to traditional machine learning bottlenecks.

#4 about 1 min

Understanding prompt tokenization in large language models

How large language models map subsets of characters into tokens to predict the most likely next word.

#5 about 2 min

Exploring common use cases for modern generative AI

Examples of applying AI to generate text, code, images, and domain-specific structured data.

#6 about 2 min

Why developers choose the Spring framework for enterprise APIs

How the Spring ecosystem prioritizes developer productivity and production readiness for the Java virtual machine.

#7 about 2 min

Core design principles and capabilities of Spring AI

How Spring AI abstracts model integrations and structured outputs while supporting advanced patterns like retrieval and multimodality.

#8 about 2 min

Demonstrating a local recipe finder powered by Ollama

A local demonstration using llama 3 and ollama to generate context-specific recipe results.

#9 about 5 min

Implementing a basic AI chat client in Spring

Configuring an AI chat client with prompt templates and mapping outputs directly to strongly typed JSON objects.

#10 about 4 min

Switching model vendors to Azure OpenAI using configurations

How abstractions in Spring AI allow swapping from a local model to Azure OpenAI without altering core business logic.

#11 about 5 min

Adapting foundation models with targeted context techniques

Why techniques like prompt engineering, function calling, and retrieval-augmented generation outperform basic foundational knowledge for business data.

#12 about 3 min

Implementing AI function calling for dynamic data lookup

Creating a function interface in Spring that allows the language model to query external APIs and mock services.

#13 about 2 min

Understanding vector databases and retrieval-augmented generation pipelines

How ETL pipelines process, split, and embed documents into a vector database for similarity searches.

#14 about 4 min

Integrating vector stores and RAG capabilities in Spring AI

Wiring up Redis vector stores and question-answer advisors to inject proprietary PDF data into the generation context.

Matching moments

54 sec

Overview of enterprise Java and generative AI

Timo Salm Timo Salm · World Congress 2025

4:24 min

Building intelligent interactions with the Spring AI framework

Timo Salm Timo Salm · World Congress 2025

3:36 min

Overview of generative AI and the presentation agenda

juarezjunior juarezjunior · World Congress 2024

3:13 min

Embedding generative AI in enterprise software platforms

Mike Butcher Mike Butcher +3 · World Congress 2024

1:48 min

Exploring AI integrations in modern agile development workflows

Markus Walker Markus Walker · World Congress 2023

2:00 min

Integrating AI throughout the extensive end-to-end development lifecycle

Hanna Hennig Hanna Hennig +3 · World Congress 2025