Runnable interface
The Runnable interface is a LangChain programming abstraction for components that accept input, perform processing, produce output, and support composition in workflows.
AI Agents and Applications
The Runnable interface is a common LangChain programming interface for components that can be invoked and composed in workflows.
- How it is used
- Provides a common contract for composing LangChain processing steps into LLM workflows.
- How deep it goes
- Defines the input-processing-output contract and demonstrates execution and composition methods, without detailing the interface’s internals.
- Examples
- Shows token-based text splitting through RunnableLambda and a RAG question routed through RunnablePassthrough.
- What you can do after
- Apply it via LangChain LCEL to assemble, invoke, and parallelize modular chains.
Read how AI Agents and Applications explains Runnable interface →
Build AI-Enhanced Web Apps
A runnable is a composable LangChain unit of work that accepts input, performs processing, and produces output, with support for invocation, batching, and streaming.
- How it is used
- Combines processing, prompts, models, and output parsing into reusable LangChain.js AI workflows.
- How deep it goes
- Defines the interface and demonstrates composition primitives and a JavaScript chain, but does not work through batching or streaming.
- Examples
- Demonstrates uppercase and vowel-count functions feeding a prompt, model, and StringOutputParser, with a `3 3` result.
- What you can do after
- Build it from scratch using RunnableLambda and RunnableSequence to compose custom JavaScript processing with a model-backed chain.
Read how Build AI-Enhanced Web Apps explains Runnable interface →
Related concepts
- pipelineused by · A pipeline is an ordered or coordinated sequence of connected processing stages or tasks that passes data, work, or results toward an outcome.
- LCELused by · LangChain Expression Language (LCEL) is a declarative composition language for connecting LangChain components into executable chains and workflows.
- RunnableLambdaimplemented by · RunnableLambda is a LangChain component that wraps a callable as a Runnable for execution within chains and workflows.
- LangChainused by · LangChain is an open-source software framework for building applications that compose language models with prompts, data sources, tools, and other components.
- LLM applicationuses · An LLM application is software whose functionality incorporates a large language model to perform tasks, process inputs, or produce outputs.
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.