Llm App Patterns

This is a solid reference for building production LLM applications, covering the practical patterns you'll actually need. It walks through RAG pipelines with real chunking strategies and retrieval methods (semantic, hybrid, multi-query), plus agent architectures like ReAct and function calling with working code examples. The vector database comparison is helpful when you're choosing between Pinecone, Weaviate, ChromaDB, or pgvector. Use this when you're past the hello-world phase and need to understand how to structure a RAG system properly, decide between agent patterns, or set up retrieval that doesn't embarrass you in production. The code samples are Python-focused and look like they came from someone who's actually shipped this stuff.