Home Events Operating AI Systems with Spring AI

Operating AI Systems with Spring AI

Description

Operating AI Systems with Spring AI” is a focused course that takes developers from building AI applications to running them confidently in production. The course covers embeddings, vector databases, and RAG pipelines in depth, while placing strong emphasis on performance, cost management, reliability, and observability by equipping students with the skills to maintain and operate AI services under real-world conditions.

 

🕒 Duration: 6 hours

👥 Target Audience:

  • Roles: Backend Engineers, Software Architects, Technical Leads, Solution Architects
  • Seniority: Mid- to senior-level professionals
Webinar Content
Module 1: Operating AI Systems with Spring AI
 AI Systems in Production
  • Stateless vs stateful services
  • Request lifecycle
  • LLM & vector DB interactions
Embeddings: Concepts & Usage
  • What embeddings are
  • Generation
  • Storage/retrieval
  • Cost/performance basics
Vector Databases: Foundations
  • Vector search/indexing basics
  • Metadata filtering
  • Common stores
  • Integration with Spring AI
RAG with Embeddings
  • Using embeddings in RAG
  • Building simple RAG pipelines
  • Context assembly
  • Handling missing/irrelevant results
Performance, Cost & Safe Defaults
  • Context size vs latency
  • Caching embeddings/responses
  • Streaming vs non-streaming
  • LLM/vector DB unavailability
  • Predictable response design
Operations & Monitoring
  • AI service health metrics
  • Token/embedding usage
  • Latency monitoring
  • Vector database monitoring
  • Logging
  • Anomaly detection

 

Learning Objectives:

After attending this webinar participants will be able to:

  • Understand and manage the full request lifecycle of a production AI service, including interactions between LLMs and vector databases
  • Generate, store, and retrieve embeddings efficiently while balancing cost and performance
  • Set up and operate vector databases with filtering, indexing, and Spring AI integration
  • Build and tune RAG pipelines using embeddings, including handling edge cases like missing or irrelevant context
  • Apply caching, streaming, and context-size strategies to optimize latency and cost
  • Design AI services with safe, predictable defaults and graceful degradation under failure
  • Monitor AI system health through token usage, latency, vector DB metrics, and anomaly detection
Prerequisite Knowledge
  • Ideally, completion of “Building AI Systems with Spring AI” or equivalent hands-on experience with Spring AI
  • Familiarity with Spring Boot and REST service development
  • Basic understanding of LLMs, prompt engineering, and RAG concepts
  • Some exposure to Docker and cloud infrastructure is beneficial for deployment and operations topics
Tags:

Date

28 May 2026, 16:00-19:00

Cost

Free

Labels

AI-Native
Category

Organizer

Code.Hub
Email
[email protected]

Related Events