liveBook · Manning

LCEL

LangChain Expression Language (LCEL) is a declarative composition language for connecting LangChain components into executable chains and workflows.

How 2 Manning books explain it

AI Agents and Applications

LCEL is LangChain's composition language for building modular and expressive large-language-model pipelines.

How it is used
Connects reusable components into summarization, web-research, and retrieval-chatbot workflows.
How deep it goes
Works through pipe composition, input mapping, parsing, sub-chains, and parallel execution; introduces fallbacks and tracing without detailing their implementation.
Examples
Uses a question-to-instructions chain, text-chunking function, parallel web-research chains, and a chatbot with memory.
What you can do after
Build it from scratch with LCEL by composing and testing modular chains, then combining them into a research summarization workflow.

Read how AI Agents and Applications explains LCEL →

Build AI-Enhanced Web Apps

LangChain Expression Language (LCEL) is a declarative syntax for composing LangChain functions into executable chains and workflows.

How it is used
Orchestrates readable, reusable linear AI workflows from existing LangChain Runnables.
How deep it goes
Defines core primitives and execution behavior, then stops short of loops, conditional logic, and stateful agent architecture.
Examples
Demonstrates uppercase transformation, vowel counting, prompt formatting, ChatOpenAI invocation, and string output parsing.
What you can do after
Build linear chains with JavaScript functions, prompts, language models, parsers, batching, streaming, and Runnable composition.

Read how Build AI-Enhanced Web Apps explains LCEL →

Related concepts

These guides are generated from the text of Manning books by Manning's knowledge graph and link to the sections they draw on. The full books are available on liveBook and at manning.com.