LangChain.js Has a Free AI Framework: Build LLM-Powered Apps With Chains, Agents, and RAG in TypeScript

You want to build an AI app that searches your documents, calls APIs, and reasons through multi-step problems. The OpenAI SDK gives you chat completions. But chaining prompts, managing context windows, vectorizing documents, and building agent loops? That's on you.

LangChain.js gives you composable building blocks — chains, agents, retrievers, memory — for building complex AI applications.

Quick Start

npm install langchain @langchain/openai

Basic Chain

import { ChatOpenAI } from "@langchain/openai";
import { ChatPromptTemplate } from "@langchain/core/prompts";
import { StringOutputParser } from "@langchain/core/output_parsers";

const model = new ChatOpenAI({ modelName: "gpt-4-turbo" });

const prompt = ChatPromptTemplate.fromMessages([
  ["system", "You are a technical writer. Write concise explanations."],
  ["user", "Explain {topic} in 3 sentences for {audience}."],
]);

const chain = prompt.pipe(model).pipe(new StringOutputParser());

const result = await chain.invoke({
  topic: "WebSockets",
  audience: "junior developers",
});

RAG (Retrieval Augmented Generation)

import { RecursiveCharacterTextSplitter } from "langchain/text_splitter";
import { MemoryVectorStore } from "langchain/vectorstores/memory";
import { OpenAIEmbeddings } from "@langchain/openai";

// 1. Split documents into chunks
const splitter = new RecursiveCharacterTextSplitter({ chunkSize: 1000, chunkOverlap: 200 });
const docs = await splitter.createDocuments([myDocumentText]);

// 2. Create vector store
const vectorStore = await MemoryVectorStore.fromDocuments(docs, new OpenAIEmbeddings());

// 3. Create retriever
const retriever = vectorStore.asRetriever({ k: 4 });

// 4. Build RAG chain
import { createRetrievalChain } from "langchain/chains/retrieval";
import { createStuffDocumentsChain } from "langchain/chains/combine_documents";

const combineDocsChain = await createStuffDocumentsChain({
  llm: model,
  prompt: ChatPromptTemplate.fromMessages([
    ["system", "Answer based on the following context:\n{context}"],
    ["user", "{input}"],
  ]),
});

const ragChain = await createRetrievalChain({
  retriever,
  combineDocsChain,
});

const response = await ragChain.invoke({ input: "What does the refund policy say?" });

Agents — LLM Decides What Tools to Use

import { TavilySearchResults } from "@langchain/community/tools/tavily_search";
import { Calculator } from "@langchain/community/tools/calculator";
import { createReactAgent } from "@langchain/langgraph/prebuilt";

const tools = [new TavilySearchResults(), new Calculator()];

const agent = createReactAgent({ llm: model, tools });

const result = await agent.invoke({
  messages: [{ role: "user", content: "What's the population of Tokyo divided by the area in km²?" }],
});
// Agent: searches for Tokyo population, searches for area, calculates density

LangChain vs AI SDK vs Direct API

Feature	LangChain.js	AI SDK	Direct API
RAG	Built-in	Manual	Manual
Agents	Built-in	Tool calling	Manual
Memory	Built-in	Manual	Manual
Streaming	Yes	Yes	SSE
React hooks	No	Yes	No
Complexity	High	Low	Medium
Best for	Complex AI apps	Chat UIs	Simple calls

Choose LangChain for RAG, agents, and complex AI workflows. Choose AI SDK for streaming chat UIs.

Start here: js.langchain.com

---

Need custom data extraction, scraping, or automation? I build tools that collect and process data at scale — 78 actors on Apify Store and 265+ open-source repos. Email me: [e-mail] | My Apify Actors