🦜Generative AI

LangChain, LangGraph and LangSmith: full course guide

Master the full LangChain ecosystem — build production chains, stateful agentic workflows with LangGraph, and debug and evaluate with LangSmith. One course, every tool.

113 pages5 modules36 topics

Intermediate · read it in your browser with Skiiling Pro.

📝 Evaluation25 Q🎙️ Mock Interview
Beta

Loading the reader…

What is inside this guide

01LangChain Foundations

  • LangChain architecture and core abstractions
  • Chat models, LLMs, and model I/O
  • Prompt templates and few-shot prompting
  • Output parsers: JSON, Pydantic, structured
  • Building your first LCEL chain
  • Runnable interface and chaining patterns

02Memory, Tools & Retrieval

  • Conversation memory types: buffer, summary, window
  • Document loaders and text splitters
  • Embeddings and vector store retrievers
  • Retrieval-augmented generation (RAG) with LangChain
  • Tool calling and custom tools
  • Agents: ReAct, OpenAI Functions, XML agent

03LangGraph — Stateful Agents

  • Why LangGraph: limitations of linear chains
  • Graphs, nodes, and edges fundamentals
  • State management and shared state schema
  • Conditional edges and branching logic
  • Cyclic graphs and agent loop patterns
  • Human-in-the-loop with interrupt and resume
  • Parallel node execution and subgraphs
  • Building a multi-step research agent with LangGraph

04LangSmith — Debug & Evaluate

  • LangSmith setup and project tracing
  • Reading and interpreting trace trees
  • Comparing runs: A/B testing prompts
  • Creating evaluation datasets from traces
  • Automated evaluators: criteria, embedding distance
  • Feedback loops and human annotation
  • Monitoring production chains for regressions
  • Cost and latency dashboards

05LangServe, Hub & Production

  • LangServe: serving chains as FastAPI endpoints
  • Streaming responses with LangServe
  • LangChain Hub: finding and versioning prompts
  • Caching: in-memory and Redis-backed
  • Fallback chains for reliability
  • Rate limiting and retry strategies
  • Secrets management and environment config
  • Capstone: production RAG API with tracing and eval

How to read it

The reader above opens the complete guide in your browser. The contents panel on the left is built from the guide's own bookmarks, so every module and topic is one click away. You can search the full text, zoom, and highlight passages in four colours; highlights and your reading position are remembered on this device.

Reading the guides is part of Skiiling Pro, the one web subscription that also unlocks Role Prep and Practical Labs and Skill Plans. The syllabus above is free to browse. See pricing.