LLM / GenAI Patterns Architectures and Use Cases with Java

Learn how to...

Goals

• Enterprise "AI" Integration
• LLM evaluation and testing
• Building a practical enterprise AI application
• Advanced LangChain4j features
• SIMD and / vs. GPU acceleration
• model embeddings and vector stores
• Direct LLM integration and inference with Java 21+
• Prompt engineering techniques
• Direct vendor LLM API access
• tools and functions
• building AI agents vs. AI as a service
• RAG vs. large context windows
• AWS Bedrock
• Integrating with external tools and APIs
• Cloud and on-premise deployment options
• Monitoring and maintaining AI systems
• Future trends in AI and potential impacts on Java development
• LangChain4j, MicroProfile, Jakarta EE, Quarkus LLM integrations
• model training with Java
• Fine Tuning and Model Distillation
• cost driven architectures
• model routers, agentic systems and subagents
• accelerated Java with tornadoVM
• CI/CD
• ...(TBD)

I will ... workshop a GIT-repository with all intermediate steps and a deployable application.

For local model inference (fully optional) you will need a fastest possible machine. For all other use cases a typical development machine is sufficient.

Feel free to contact me / register via email: workshops[-AT-]adam-bien.com

To register for both workshops, just mention it in the comment section.

Registration