Build context-augmented web apps using
LlamaIndex.TS

LlamaIndex.TS is the JS/TS version of LlamaIndex, the framework for building agentic generative AI applications connected to your data.

Designed for building web applications in

Next.js

Progressive

From the simplest to the most complex

LlamaIndex.TS is designed to be simple to get started, but powerful enough to build complex, agentic AI applications.

import { OpenAI } from "llamaindex";
const llm = new OpenAI();
const response = await llm.complete({ prompt: "How are you?" });

Agents

Build agentic RAG applications

Truly powerful retrieval-augmented generation applications use agentic techniques, and LlamaIndex.TS makes it easy to build them.

import { FunctionTool } from "llamaindex";
import { OpenAIAgent } from "@llamaindex/openai";
 
const interpreterTool = FunctionTool.from(...);
const systemPrompt = `...`;
 
const agent = new OpenAIAgent({
  llm,
  tools: [interpreterTool],
  systemPrompt,
});
 
await agent.chat('...');

Providers

LLMs, Data Loaders, Vector Stores and more!

LlamaIndex.TS has hundreds of integrations to connect to your data, index it, and query it with LLMs.

LLMs

Vector Stores

create-llama CLI

Build a RAG app with a single command

A command line tool to generate LlamaIndex apps, the easiest way to get started with LlamaIndex.

localhost:8080

 Terminal
npx create-llama@latest ┌ Create Llama│◇ What is your project named?│ my-app│◆ What app do you want to build?│ ● Agentic RAG│ ○ Data Scientist