LLM
3 items
Series Posts
Part 5: The Intelligent Layer — Azure AI & Machine Learning
CloudVault wants to add intelligent features to their platform. Marcus explores Azure AI Services (Vision, Language, Speech), Azure OpenAI for LLMs, and Azure Machine Learning. We integrate AI capabilities into a Java backend application and understand when to use pre-built APIs vs. custom models.
Part 8: "The Intelligent Agent" — Production RAG Architectures
Maya builds an AI shopping assistant. We move from naive retrieval to a production-grade Retrieval-Augmented Generation (RAG) system. We cover chunking strategies, hybrid search (combining vectors with metadata filters), and using Redis as conversational memory for LLMs.
Part 10: "Into the Deep End" — PyTorch, Concurrency and the AI Toolkit
Tensors, autograd and a hand-written PyTorch training loop. Then the questions a Java architect asks: the GIL, threads vs processes, asyncio for fanning out LLM calls, embeddings and semantic search, validated structured output, and how Python models reach JVM services.