LangChain: Step by Step (9 Modules)
Models, structured output, tools, agents, memory, RAG, middleware, and production with LangChain v1.
9 lessons · about 76 minutes of reading
Log in to track your progress through this course.
Start lesson 1- 1
LangChain Module 1: Introduction, Setup, and Your First Model Call
Understand what LangChain v1 is, install it, set your API key, and make your first model call.
8 min read
- 2
LangChain Module 2: Chat Models, Messages, and Streaming
Work with the standard chat model interface: message formats, reading responses, streaming, and batching.
8 min read
- 3
LangChain Module 3: Structured Output with Pydantic
Get validated Python objects back from a model using with_structured_output and Pydantic schemas.
7 min read
- 4
LangChain Module 4: Tools and Your First Agent with create_agent
Define tools with @tool, build an agent with create_agent, and inspect the messages it produces.
9 min read
- 5
LangChain Module 5: Memory, Threads, and Long Conversations
Give an agent short-term memory with a checkpointer, separate conversations by thread, and keep history under control.
8 min read
- 6
LangChain Module 6: RAG Part 1, Loading, Splitting, and Embedding Documents
Build a searchable knowledge base: load documents, split them, embed them locally, and query a vector store.
9 min read
- 7
LangChain Module 7: RAG Part 2, Retrieval Agents and Two-Step Chains
Answer questions from your index two ways: a simple two-step flow, and an agent that decides when to retrieve.
9 min read
- 8
LangChain Module 8: Middleware, Limits, and Human Approval
Customize the agent loop with middleware: summarization, approval for risky tools, call limits, and your own hooks.
9 min read
- 9
LangChain Module 9: Observability, Testing, and Going to Production
Trace agent runs with LangSmith, test with a golden set, handle failures, and prepare a LangChain app for production.
9 min read