Langchain

This is your go-to for building LLM applications that need more structure than raw API calls. It covers both LangChain's LCEL pipe syntax for composing chains and LangGraph for stateful agent workflows. The examples are practical: RAG pipelines with vector stores, structured output parsing with Pydantic models, and actual agent graphs with tools and conditional routing. The memory and streaming sections show you how to handle conversations and token-by-token responses. If you're wiring up retrieval systems or multi-step agents, this gets you past the boilerplate fast. LangSmith tracing integration is a nice touch for debugging complex chains.