LangChain overview for Node.js

LangChain.js provides a standardized framework for building LLM applications in TypeScript and Node.js, enabling developers to compose prompts, models, tools, and retrievers into reusable pipelines and agents. The framework introduces core concepts like Documents, Runnables, and LCEL (LangChain Expression Language) for chaining components, and offers high-level agent APIs such as createAgent for complex multi-step tasks.

LangChain.js https://docs.langchain.com/oss/javascript/langchain/overview is a framework for LLM applications in TypeScript and Node.js. It standardizes how you wire prompts, models, tools, document loaders, embeddings, and retrievers into reusable pipelines and agents. | Project | Role | |---|---| | createAgent , loaders, retrieversUse Deep Agents for complex multi-step tasks out of the box. Use LangChain's createAgent when you want a minimal harness you compose with middleware. Reach for LangGraph when you need custom stateful workflows, branching, or fine-grained control over the agent loop. Install the core packages first install guide https://docs.langchain.com/oss/javascript/langchain/install : npm i langchain @langchain/core @langchain/openai zod Provider-specific integrations live in separate packages: langchain - createAgent , tool , and high-level chain helpers zod - tool input schemas when defining tools with tool @langchain/core - prompts, output parsers, Runnable interface, LCEL @langchain/openai - ChatOpenAI , OpenAIEmbeddings @langchain/textsplitters - document chunking used in the For raw API access, see the Chat Completions https://sevic.dev/notes/chatgpt-api-nodejs/ and OpenAI Responses API https://sevic.dev/notes/llm-integration-openai-responses-api/ posts. For provider-agnostic text and agents, see the Vercel AI SDK https://sevic.dev/notes/llm-integration-vercel-ai-sdk/ and OpenAI Agents SDK https://sevic.dev/notes/ai-agents-openai-sdk/ posts. | Tool | Best for | |---|---| Raw openai package | Minimal calls, full control, least abstraction | | generateText , streaming, embeddings, tool loops createAgent , swappable vector storesReach for LangChain when RAG or multi-step LLM pipelines grow beyond a few manual API calls. langchain , @langchain/core , @langchain/openai , and zod installed OPENAI API KEY set in the environment Document - a chunk of text with optional metadata. Loaders produce Document instances; splitters break long sources into retrieval-friendly pieces. js import { Document } from '@langchain/core/documents'; const doc = new Document { pageContent: 'LangChain helps compose LLM pipelines.', metadata: { source: 'intro' } } ; Runnable - any component with .invoke , .stream , or .batch . Prompts, models, parsers, and composed chains are all Runnables. LCEL LangChain Expression Language - chain Runnables with .pipe . Data flows left to right: prompt → model → parser. The same .invoke , .stream , and .batch interface applies to every Runnable in the chain. js import { ChatPromptTemplate } from '@langchain/core/prompts'; import { StringOutputParser } from '@langchain/core/output parsers'; import { ChatOpenAI } from '@langchain/openai'; const prompt = ChatPromptTemplate.fromMessages 'system', 'Answer in one sentence.' , 'human', '{question}' ; const model = new ChatOpenAI { model: 'gpt-5.5' } ; const chain = prompt.pipe model .pipe new StringOutputParser ; const answer = await chain.invoke { question: 'What is LangChain?' } ; console.log answer ; Agents - LangChain's current high-level agent API is createAgent https://docs.langchain.com/oss/javascript/langchain/agents . Pass a model string or chat model, optional tools with zod schemas , and an optional checkpointer for conversation memory @langchain/langgraph : js import { createAgent } from 'langchain'; const agent = createAgent { model: 'gpt-5.5', tools: } ; const result = await agent.invoke { messages: { role: 'user', content: 'What is LangChain?' } } ; @langchain/langgraph thread id ; long-term memory via createAgent with tools and middleware; for production agents you may also prefer the LANGSMITH TRACING=true ; optional The same LCEL chain supports streaming and batch invocation: js for await const chunk of await chain.stream { question: 'What is LCEL?' } { process.stdout.write chunk ; } const answers = await chain.batch { question: 'What is a Runnable?' }, { question: 'What is a retriever?' } ; Runnable LCEL scripts for this post live in the langchain-overview-nodejs-demo folder. Get access via code demos https://sevic.dev/demos .