Home

Welcome to the home page! Everything you need is right here!

High-Level Concepts

Learn the basic fundamentals. So easy a caveman can do it!

Installation and Setup

UNDER CONSTRUCTION! Check back soon!

How to read these docs

Easy as pie! Just click the links!

Starter Examples

Get started with some rad examples.

Starter Tutorial (Using OpenAI)

Step-by-step guide using the power of OpenAI. Totally Tubular!

Starter Tutorial (Using Local LLMs)

Build agents the way you want! Check it out!

Discover LlamaIndex Video Series

Learn by watching! Don't be a zero, be a hero!

Frequently Asked Questions (FAQ)

Got questions? We got answers!

Starter Tools

Get your toolkit ready!

Learn

Learn to build amazing things!

Using LLMs

How to do stuff.

Building agents

Build agents like a pro!

Using existing tools

Use existing tools for RAD results!

Maintaining state

Stay in the loop, homey.

Streaming output and events

Get the stream!

Human in the loop

Talk to humans!

Multi-agent workflows

Multiple agents working together!

Building Workflows

Be a master builder!

A basic workflow

Learn the workflow!

Branches and loops

Branch out and loop!

Maintaining state

State! State! State!

Streaming events

Get with the stream!

Concurrent execution

Do things together!

Subclassing workflows

Classy.

Nested workflows

Workflow-ception!

Observability

Observe!

Unbound syntax

Syntax!

Building a RAG pipeline

Pipeline power!

Loading & Ingestion

Load it up!

Loading Data (Ingestion)

Load that data!

LlamaHub

Llama Hub.

Loading from LlamaCloud

LlamaCloud!

Indexing & Embedding

Make it index!

Storing

Storing is important!

Querying

Query time!

Structured Data Extraction

Structure it up!

Using Structured LLMs

Use that LLM!

Structured Prediction

Get that prediction!

Lower-level extraction

Low level!

Tracing and Debugging

Debug time!

Evaluating

Evaluate!

Evaluating

Get those metrics!

Cost Analysis

Track those costs!

Usage Pattern

Usage pattern!

Putting it all Together

Put it all together!

Full-stack web application

Make a web app!

A Guide to Building a Full-Stack Web App with LLamaIndex

Make the magic!

A Guide to Building a Full-Stack LlamaIndex Web App with Delphic

Delphic!

Q&A Patterns

Q & A!

A Guide to Extracting Terms and Definitions

Terms and defs.

Chatbots

Chatbots!

How to Build a Chatbot

Build it up!

Structured data

Structured data!

Use Cases

The most USEFUL cases!

Prompting

Prompt them to win!

Question-Answering (RAG)

QA!

Chatbots

Chatbots!

Structured Data Extraction

Extraction!

Agents

Agents!

Multi-Modal Applications

So many modes!

Fine-Tuning

Tune it!

Examples

Do it!

Agents

Agents!

How to Build a Chatbot

Build the bot!

GPT Builder Demo

GPT Demo.

FunctionAgent / AgentWorkflow Basic Introduction

Learn about Agents!

Multi-Agent Research Workflow with AgentWorkflow

Multi Agent!

Agent Workflow + Research Assistant using AgentQL

AgentQL!

Function Calling Anthropic Agent

Anthropic Agent!

Function Calling AWS Bedrock Converse Agent

AWS Bedrock!

Prebuilt CodeAct Agent w/ LlamaIndex

CodeAct!

Creating a CodeAct Agent From Scratch

Build your own!

Chat Memory Buffer

Chat buffer!

Simple Composable Memory

Simple memory!

Chat Summary Memory Buffer

Chat summary!

Vector Memory

Vector memory!

Function Calling Mistral Agent

Mistral Agent!

Multi-Document Agents (V1)

Multi document!

Function Calling NVIDIA Agent

NVIDIA agent!

Document Research Assistant for Blog Creation

Research!

Sub Question Query Engine powered by NVIDIA NIMs

NVIDIA NIMs!

Context-Augmented Function Calling Agent

Context!

OpenAI Agent Workarounds for Lengthy Tool Descriptions

OpenAI!

OpenAI Agent + Query Engine Experimental Cookbook

Query Engine!

Retrieval-Augmented Agents

Retrieval!

Agent with Query Engine Tools

Tools!

ReAct Agent - A Simple Intro with Calculator Tools

ReAct!

ReAct Agent with Query Engine (RAG) Tools

More ReAct!

Controlling Agent Reasoning Loop with Return Direct Tools

Control!

Chat Engines

CHat engines!

Chat Engine - Best Mode

Best Mode.

Chat Engine - Condense Plus Context Mode

Condense.

Chat Engine - Condense Question Mode

Question!

Chat Engine - Context Mode

Context!

Chat Engine - OpenAI Agent Mode

OpenAI Agent!

Chat Engine with a Personality ✨

Personality!

Chat Engine - ReAct Agent Mode

ReAct!

Chat Engine - Simple Mode REPL

Simple Mode!

Cookbooks

Cookbooks!

GraphRAG Implementation with LlamaIndex

GraphRAG!

GraphRAG Implementation with LlamaIndex - V2

V2!

AirtrainAI Cookbook

Airtrain!

Anthropic Haiku Cookbook

Generate your own 90s page here!