AI for Java Developers: Building Intelligent Applications

Overview of AI, ML, and LLMs for engineers

Where AI fits into modern Java architectures

AI terminology and core concepts

Setting up the Java + AI development environment

Calling OpenAI and Azure OpenAI APIs from Java

Handling streaming responses and tokens

Error handling, retries, and rate limits

Building a simple AI chatbot service

Introduction to the Spring AI framework

Configuring AI clients and models

Structured prompts and output parsing

Building AI-powered REST endpoints

Principles of effective prompt design

Few-shot and chain-of-thought prompting

Managing context windows and token limits

Testing and evaluating prompt quality

Introduction to ONNX Runtime for Java

Loading and running pre-trained models

Performance considerations on the JVM

Choosing between cloud and local inference

Concepts of embeddings and vector search

Integrating vector databases (e.g., Pinecone, Weaviate)

Building a RAG pipeline in Spring Boot

Improving accuracy with chunking strategies

Designing scalable AI microservices

Caching and reducing API costs

Asynchronous processing for AI workloads

Combining multiple AI services in one system

Securing API keys and sensitive data

Logging and monitoring AI usage

Handling hallucinations and output validation

Cost tracking and budget controls

Defining the capstone AI application

Implementing core AI features end-to-end

Testing, deployment, and demo preparation

Final project presentation and review