kanshan/graphrag
1
0
Fork 0
mirror of https://github.com/microsoft/graphrag.git synced 2026-01-14 09:07:20 +08:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity
22bb80fb50
graphrag/index/methods/index.html

1553 lines
35 KiB
HTML
Raw Blame History

<!doctype html>
<html lang="en" class="no-js">
<head>
<meta charset="utf-8">
<meta name="viewport" content="width=device-width,initial-scale=1">
<link rel="icon" href="../../assets/images/favicon.png">
<meta name="generator" content="mkdocs-1.6.1, mkdocs-material-9.6.7">
<title>Indexing Methods - GraphRAG</title>
<link rel="stylesheet" href="../../assets/stylesheets/main.8608ea7d.min.css">
<link rel="stylesheet" href="../../assets/stylesheets/palette.06af60db.min.css">
<script src="https://wcpstatic.microsoft.com/mscc/lib/v2/wcp-consent.js"></script>
<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin>
<link rel="stylesheet" href="https://fonts.googleapis.com/css?family=Roboto:300,300i,400,400i,700,700i%7CRoboto+Mono:400,400i,700,700i&display=fallback">
<style>:root{--md-text-font:"Roboto";--md-code-font:"Roboto Mono"}</style>
<link rel="stylesheet" href="../../stylesheets/extra.css">
<script>__md_scope=new URL("../..",location),__md_hash=e=>[...e].reduce(((e,_)=>(e<<5)-e+_.charCodeAt(0)),0),__md_get=(e,_=localStorage,t=__md_scope)=>JSON.parse(_.getItem(t.pathname+"."+e)),__md_set=(e,_,t=localStorage,a=__md_scope)=>{try{t.setItem(a.pathname+"."+e,JSON.stringify(_))}catch(e){}}</script>
</head>
<body dir="ltr" data-md-color-scheme="default" data-md-color-primary="indigo" data-md-color-accent="indigo">
<input class="md-toggle" data-md-toggle="drawer" type="checkbox" id="__drawer" autocomplete="off">
<input class="md-toggle" data-md-toggle="search" type="checkbox" id="__search" autocomplete="off">
<label class="md-overlay" for="__drawer"></label>
<div data-md-component="skip">
<a href="#indexing-methods" class="md-skip">
Skip to content
</a>
</div>
<div data-md-component="announce">
</div>
<header class="md-header" data-md-component="header">
<nav class="md-header__inner md-grid" aria-label="Header">
<a href="../.." title="GraphRAG" class="md-header__button md-logo" aria-label="GraphRAG" data-md-component="logo">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M19.375 8.5a3.25 3.25 0 1 1-3.163 4h-3a3.252 3.252 0 0 1-4.443 2.509L7.214 17.76a3.25 3.25 0 1 1-1.342-.674l1.672-2.957A3.24 3.24 0 0 1 6.75 12c0-.907.371-1.727.97-2.316L6.117 6.846A3.253 3.253 0 0 1 1.875 3.75a3.25 3.25 0 1 1 5.526 2.32l1.603 2.836A3.25 3.25 0 0 1 13.093 11h3.119a3.25 3.25 0 0 1 3.163-2.5M10 10.25a1.75 1.75 0 1 0-.001 3.499A1.75 1.75 0 0 0 10 10.25M5.125 2a1.75 1.75 0 1 0 0 3.5 1.75 1.75 0 0 0 0-3.5m12.5 9.75a1.75 1.75 0 1 0 3.5 0 1.75 1.75 0 0 0-3.5 0m-14.25 8.5a1.75 1.75 0 1 0 3.501-.001 1.75 1.75 0 0 0-3.501.001"/></svg>
</a>
<label class="md-header__button md-icon" for="__drawer">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M3 6h18v2H3zm0 5h18v2H3zm0 5h18v2H3z"/></svg>
</label>
<div class="md-header__title" data-md-component="header-title">
<div class="md-header__ellipsis">
<div class="md-header__topic">
<span class="md-ellipsis">
GraphRAG
</span>
</div>
<div class="md-header__topic" data-md-component="header-topic">
<span class="md-ellipsis">
Indexing Methods
</span>
</div>
</div>
</div>
<form class="md-header__option" data-md-component="palette">
<input class="md-option" data-md-color-media="" data-md-color-scheme="default" data-md-color-primary="indigo" data-md-color-accent="indigo" aria-label="Switch to dark mode" type="radio" name="__palette" id="__palette_0">
<label class="md-header__button md-icon" title="Switch to dark mode" for="__palette_1" hidden>
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M12 8a4 4 0 0 0-4 4 4 4 0 0 0 4 4 4 4 0 0 0 4-4 4 4 0 0 0-4-4m0 10a6 6 0 0 1-6-6 6 6 0 0 1 6-6 6 6 0 0 1 6 6 6 6 0 0 1-6 6m8-9.31V4h-4.69L12 .69 8.69 4H4v4.69L.69 12 4 15.31V20h4.69L12 23.31 15.31 20H20v-4.69L23.31 12z"/></svg>
</label>
<input class="md-option" data-md-color-media="" data-md-color-scheme="slate" data-md-color-primary="indigo" data-md-color-accent="indigo" aria-label="Switch to light mode" type="radio" name="__palette" id="__palette_1">
<label class="md-header__button md-icon" title="Switch to light mode" for="__palette_0" hidden>
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M12 18c-.89 0-1.74-.2-2.5-.55C11.56 16.5 13 14.42 13 12s-1.44-4.5-3.5-5.45C10.26 6.2 11.11 6 12 6a6 6 0 0 1 6 6 6 6 0 0 1-6 6m8-9.31V4h-4.69L12 .69 8.69 4H4v4.69L.69 12 4 15.31V20h4.69L12 23.31 15.31 20H20v-4.69L23.31 12z"/></svg>
</label>
</form>
<script>var palette=__md_get("__palette");if(palette&&palette.color){if("(prefers-color-scheme)"===palette.color.media){var media=matchMedia("(prefers-color-scheme: light)"),input=document.querySelector(media.matches?"[data-md-color-media='(prefers-color-scheme: light)']":"[data-md-color-media='(prefers-color-scheme: dark)']");palette.color.media=input.getAttribute("data-md-color-media"),palette.color.scheme=input.getAttribute("data-md-color-scheme"),palette.color.primary=input.getAttribute("data-md-color-primary"),palette.color.accent=input.getAttribute("data-md-color-accent")}for(var[key,value]of Object.entries(palette.color))document.body.setAttribute("data-md-color-"+key,value)}</script>
<label class="md-header__button md-icon" for="__search">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M9.5 3A6.5 6.5 0 0 1 16 9.5c0 1.61-.59 3.09-1.56 4.23l.27.27h.79l5 5-1.5 1.5-5-5v-.79l-.27-.27A6.52 6.52 0 0 1 9.5 16 6.5 6.5 0 0 1 3 9.5 6.5 6.5 0 0 1 9.5 3m0 2C7 5 5 7 5 9.5S7 14 9.5 14 14 12 14 9.5 12 5 9.5 5"/></svg>
</label>
<div class="md-search" data-md-component="search" role="dialog">
<label class="md-search__overlay" for="__search"></label>
<div class="md-search__inner" role="search">
<form class="md-search__form" name="search">
<input type="text" class="md-search__input" name="query" aria-label="Search" placeholder="Search" autocapitalize="off" autocorrect="off" autocomplete="off" spellcheck="false" data-md-component="search-query" required>
<label class="md-search__icon md-icon" for="__search">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M9.5 3A6.5 6.5 0 0 1 16 9.5c0 1.61-.59 3.09-1.56 4.23l.27.27h.79l5 5-1.5 1.5-5-5v-.79l-.27-.27A6.52 6.52 0 0 1 9.5 16 6.5 6.5 0 0 1 3 9.5 6.5 6.5 0 0 1 9.5 3m0 2C7 5 5 7 5 9.5S7 14 9.5 14 14 12 14 9.5 12 5 9.5 5"/></svg>
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M20 11v2H8l5.5 5.5-1.42 1.42L4.16 12l7.92-7.92L13.5 5.5 8 11z"/></svg>
</label>
<nav class="md-search__options" aria-label="Search">
<button type="reset" class="md-search__icon md-icon" title="Clear" aria-label="Clear" tabindex="-1">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M19 6.41 17.59 5 12 10.59 6.41 5 5 6.41 10.59 12 5 17.59 6.41 19 12 13.41 17.59 19 19 17.59 13.41 12z"/></svg>
</button>
</nav>
</form>
<div class="md-search__output">
<div class="md-search__scrollwrap" tabindex="0" data-md-scrollfix>
<div class="md-search-result" data-md-component="search-result">
<div class="md-search-result__meta">
Initializing search
</div>
<ol class="md-search-result__list" role="presentation"></ol>
</div>
</div>
</div>
</div>
</div>
<div class="md-header__source">
<a href="https://github.com/microsoft/graphrag" title="Go to repository" class="md-source" data-md-component="source">
<div class="md-source__icon md-icon">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 448 512"><!--! Font Awesome Free 6.7.2 by @fontawesome - https://fontawesome.com License - https://fontawesome.com/license/free (Icons: CC BY 4.0, Fonts: SIL OFL 1.1, Code: MIT License) Copyright 2024 Fonticons, Inc.--><path d="M439.55 236.05 244 40.45a28.87 28.87 0 0 0-40.81 0l-40.66 40.63 51.52 51.52c27.06-9.14 52.68 16.77 43.39 43.68l49.66 49.66c34.23-11.8 61.18 31 35.47 56.69-26.49 26.49-70.21-2.87-56-37.34L240.22 199v121.85c25.3 12.54 22.26 41.85 9.08 55a34.34 34.34 0 0 1-48.55 0c-17.57-17.6-11.07-46.91 11.25-56v-123c-20.8-8.51-24.6-30.74-18.64-45L142.57 101 8.45 235.14a28.86 28.86 0 0 0 0 40.81l195.61 195.6a28.86 28.86 0 0 0 40.8 0l194.69-194.69a28.86 28.86 0 0 0 0-40.81"/></svg>
</div>
<div class="md-source__repository">
graphrag
</div>
</a>
</div>
</nav>
</header>
<div class="md-container" data-md-component="container">
<nav class="md-tabs" aria-label="Tabs" data-md-component="tabs">
<div class="md-grid">
<ul class="md-tabs__list">
<li class="md-tabs__item">
<a href="../.." class="md-tabs__link">
Home
</a>
</li>
<li class="md-tabs__item">
<a href="../overview/" class="md-tabs__link">
Indexing
</a>
</li>
<li class="md-tabs__item">
<a href="../../prompt_tuning/overview/" class="md-tabs__link">
Prompt Tuning
</a>
</li>
<li class="md-tabs__item">
<a href="../../query/overview/" class="md-tabs__link">
Query
</a>
</li>
<li class="md-tabs__item">
<a href="../../config/overview/" class="md-tabs__link">
Configuration
</a>
</li>
<li class="md-tabs__item">
<a href="../../cli/" class="md-tabs__link">
CLI
</a>
</li>
<li class="md-tabs__item">
<a href="../../blog_posts/" class="md-tabs__link">
Extras
</a>
</li>
</ul>
</div>
</nav>
<main class="md-main" data-md-component="main">
<div class="md-main__inner md-grid">
<div class="md-sidebar md-sidebar--primary" data-md-component="sidebar" data-md-type="navigation" >
<div class="md-sidebar__scrollwrap">
<div class="md-sidebar__inner">
<nav class="md-nav md-nav--primary md-nav--lifted" aria-label="Navigation" data-md-level="0">
<label class="md-nav__title" for="__drawer">
<a href="../.." title="GraphRAG" class="md-nav__button md-logo" aria-label="GraphRAG" data-md-component="logo">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M19.375 8.5a3.25 3.25 0 1 1-3.163 4h-3a3.252 3.252 0 0 1-4.443 2.509L7.214 17.76a3.25 3.25 0 1 1-1.342-.674l1.672-2.957A3.24 3.24 0 0 1 6.75 12c0-.907.371-1.727.97-2.316L6.117 6.846A3.253 3.253 0 0 1 1.875 3.75a3.25 3.25 0 1 1 5.526 2.32l1.603 2.836A3.25 3.25 0 0 1 13.093 11h3.119a3.25 3.25 0 0 1 3.163-2.5M10 10.25a1.75 1.75 0 1 0-.001 3.499A1.75 1.75 0 0 0 10 10.25M5.125 2a1.75 1.75 0 1 0 0 3.5 1.75 1.75 0 0 0 0-3.5m12.5 9.75a1.75 1.75 0 1 0 3.5 0 1.75 1.75 0 0 0-3.5 0m-14.25 8.5a1.75 1.75 0 1 0 3.501-.001 1.75 1.75 0 0 0-3.501.001"/></svg>
</a>
GraphRAG
</label>
<div class="md-nav__source">
<a href="https://github.com/microsoft/graphrag" title="Go to repository" class="md-source" data-md-component="source">
<div class="md-source__icon md-icon">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 448 512"><!--! Font Awesome Free 6.7.2 by @fontawesome - https://fontawesome.com License - https://fontawesome.com/license/free (Icons: CC BY 4.0, Fonts: SIL OFL 1.1, Code: MIT License) Copyright 2024 Fonticons, Inc.--><path d="M439.55 236.05 244 40.45a28.87 28.87 0 0 0-40.81 0l-40.66 40.63 51.52 51.52c27.06-9.14 52.68 16.77 43.39 43.68l49.66 49.66c34.23-11.8 61.18 31 35.47 56.69-26.49 26.49-70.21-2.87-56-37.34L240.22 199v121.85c25.3 12.54 22.26 41.85 9.08 55a34.34 34.34 0 0 1-48.55 0c-17.57-17.6-11.07-46.91 11.25-56v-123c-20.8-8.51-24.6-30.74-18.64-45L142.57 101 8.45 235.14a28.86 28.86 0 0 0 0 40.81l195.61 195.6a28.86 28.86 0 0 0 40.8 0l194.69-194.69a28.86 28.86 0 0 0 0-40.81"/></svg>
</div>
<div class="md-source__repository">
graphrag
</div>
</a>
</div>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item md-nav__item--nested">
<input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_1" >
<label class="md-nav__link" for="__nav_1" id="__nav_1_label" tabindex="0">
<span class="md-ellipsis">
Home
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="1" aria-labelledby="__nav_1_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_1">
<span class="md-nav__icon md-icon"></span>
Home
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../.." class="md-nav__link">
<span class="md-ellipsis">
Welcome
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../get_started/" class="md-nav__link">
<span class="md-ellipsis">
Getting Started
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../developing/" class="md-nav__link">
<span class="md-ellipsis">
Development Guide
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item md-nav__item--nested">
<input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_2" >
<label class="md-nav__link" for="__nav_2" id="__nav_2_label" tabindex="0">
<span class="md-ellipsis">
Indexing
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="1" aria-labelledby="__nav_2_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_2">
<span class="md-nav__icon md-icon"></span>
Indexing
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../overview/" class="md-nav__link">
<span class="md-ellipsis">
Overview
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../architecture/" class="md-nav__link">
<span class="md-ellipsis">
Architecture
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../default_dataflow/" class="md-nav__link">
<span class="md-ellipsis">
Dataflow
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../inputs/" class="md-nav__link">
<span class="md-ellipsis">
Inputs
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../outputs/" class="md-nav__link">
<span class="md-ellipsis">
Outputs
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item md-nav__item--nested">
<input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_3" >
<label class="md-nav__link" for="__nav_3" id="__nav_3_label" tabindex="0">
<span class="md-ellipsis">
Prompt Tuning
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="1" aria-labelledby="__nav_3_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_3">
<span class="md-nav__icon md-icon"></span>
Prompt Tuning
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../../prompt_tuning/overview/" class="md-nav__link">
<span class="md-ellipsis">
Overview
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../prompt_tuning/auto_prompt_tuning/" class="md-nav__link">
<span class="md-ellipsis">
Auto Tuning
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../prompt_tuning/manual_prompt_tuning/" class="md-nav__link">
<span class="md-ellipsis">
Manual Tuning
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item md-nav__item--nested">
<input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_4" >
<label class="md-nav__link" for="__nav_4" id="__nav_4_label" tabindex="0">
<span class="md-ellipsis">
Query
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="1" aria-labelledby="__nav_4_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_4">
<span class="md-nav__icon md-icon"></span>
Query
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../../query/overview/" class="md-nav__link">
<span class="md-ellipsis">
Overview
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../query/global_search/" class="md-nav__link">
<span class="md-ellipsis">
Global Search
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../query/local_search/" class="md-nav__link">
<span class="md-ellipsis">
Local Search
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../query/drift_search/" class="md-nav__link">
<span class="md-ellipsis">
DRIFT Search
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../query/question_generation/" class="md-nav__link">
<span class="md-ellipsis">
Question Generation
</span>
</a>
</li>
<li class="md-nav__item md-nav__item--nested">
<input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_4_6" >
<label class="md-nav__link" for="__nav_4_6" id="__nav_4_6_label" tabindex="0">
<span class="md-ellipsis">
Notebooks
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="2" aria-labelledby="__nav_4_6_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_4_6">
<span class="md-nav__icon md-icon"></span>
Notebooks
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../../query/notebooks/overview/" class="md-nav__link">
<span class="md-ellipsis">
Overview
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../examples_notebooks/global_search/" class="md-nav__link">
<span class="md-ellipsis">
Global Search
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../examples_notebooks/local_search/" class="md-nav__link">
<span class="md-ellipsis">
Local Search
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../examples_notebooks/drift_search/" class="md-nav__link">
<span class="md-ellipsis">
DRIFT Search
</span>
</a>
</li>
</ul>
</nav>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item md-nav__item--nested">
<input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_5" >
<label class="md-nav__link" for="__nav_5" id="__nav_5_label" tabindex="0">
<span class="md-ellipsis">
Configuration
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="1" aria-labelledby="__nav_5_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_5">
<span class="md-nav__icon md-icon"></span>
Configuration
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../../config/overview/" class="md-nav__link">
<span class="md-ellipsis">
Overview
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../config/init/" class="md-nav__link">
<span class="md-ellipsis">
Init Command
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../config/yaml/" class="md-nav__link">
<span class="md-ellipsis">
Using YAML
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../config/env_vars/" class="md-nav__link">
<span class="md-ellipsis">
Using Env Vars
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="../../cli/" class="md-nav__link">
<span class="md-ellipsis">
CLI
</span>
</a>
</li>
<li class="md-nav__item md-nav__item--nested">
<input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_7" >
<label class="md-nav__link" for="__nav_7" id="__nav_7_label" tabindex="0">
<span class="md-ellipsis">
Extras
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="1" aria-labelledby="__nav_7_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_7">
<span class="md-nav__icon md-icon"></span>
Extras
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../../blog_posts/" class="md-nav__link">
<span class="md-ellipsis">
Microsoft Research Blog
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../visualization_guide/" class="md-nav__link">
<span class="md-ellipsis">
Visualization Guide
</span>
</a>
</li>
<li class="md-nav__item md-nav__item--nested">
<input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_7_3" >
<label class="md-nav__link" for="__nav_7_3" id="__nav_7_3_label" tabindex="0">
<span class="md-ellipsis">
Operation Dulce
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="2" aria-labelledby="__nav_7_3_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_7_3">
<span class="md-nav__icon md-icon"></span>
Operation Dulce
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../../data/operation_dulce/ABOUT/" class="md-nav__link">
<span class="md-ellipsis">
About
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../data/operation_dulce/Operation%20Dulce%20v2%201%201/" class="md-nav__link">
<span class="md-ellipsis">
Document
</span>
</a>
</li>
</ul>
</nav>
</li>
</ul>
</nav>
</li>
</ul>
</nav>
</div>
</div>
</div>
<div class="md-sidebar md-sidebar--secondary" data-md-component="sidebar" data-md-type="toc" >
<div class="md-sidebar__scrollwrap">
<div class="md-sidebar__inner">
<nav class="md-nav md-nav--secondary" aria-label="Table of contents">
<label class="md-nav__title" for="__toc">
<span class="md-nav__icon md-icon"></span>
Table of contents
</label>
<ul class="md-nav__list" data-md-component="toc" data-md-scrollfix>
<li class="md-nav__item">
<a href="#standard-graphrag" class="md-nav__link">
<span class="md-ellipsis">
Standard GraphRAG
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#fastgraphrag" class="md-nav__link">
<span class="md-ellipsis">
FastGraphRAG
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#choosing-a-method" class="md-nav__link">
<span class="md-ellipsis">
Choosing a Method
</span>
</a>
</li>
</ul>
</nav>
</div>
</div>
</div>
<div class="md-content" data-md-component="content">
<article class="md-content__inner md-typeset">
<h1 id="indexing-methods">Indexing Methods</h1>
<p>GraphRAG is a platform for our research into RAG indexing methods that produce optimal context window content for language models. We have a standard indexing pipeline that uses a language model to extract the graph that our memory model is based upon. We may introduce additional indexing methods from time to time. This page documents those options.</p>
<h2 id="standard-graphrag">Standard GraphRAG</h2>
<p>This is the method described in the original <a href="https://www.microsoft.com/en-us/research/blog/graphrag-unlocking-llm-discovery-on-narrative-private-data/">blog post</a>. Standard uses a language model for all reasoning tasks:</p>
<ul>
<li>entity extraction: LLM is prompted to extract named entities and provide a description from each text unit.</li>
<li>relationship extraction: LLM is prompted to describe the relationship between each pair of entities in each text unit.</li>
<li>entity summarization: LLM is prompted to combine the descriptions for every instance of an entity found across the text units into a single summary.</li>
<li>relationship summarization: LLM is prompted to combine the descriptions for every instance of a relationship found across the text units into a single summary.</li>
<li>claim extraction (optiona): LLM is prompted to extract and describe claims from each text unit.</li>
<li>community report generation: entity and relationship descriptions (and optionally claims) for each community are collected and used to prompt the LLM to generate a summary report.</li>
</ul>
<p><code>graphrag index --method standard</code>. This is the default method, so the method param can actual be omitted.</p>
<h2 id="fastgraphrag">FastGraphRAG</h2>
<p>FastGraphRAG is a method that substitutes some of the language model reasoning for traditional natural language processing (NLP) methods. This is a hybrid technique that we developed as a faster and cheaper indexing alternative:</p>
<ul>
<li>entity extraction: entities are noun phrases extracted using NLP libraries such as NLTK and spaCy. There is no description; the source text unit is used for this.</li>
<li>relationship extraction: relationships are defined as text unit co-occurrence between entity pairs. There is no description.</li>
<li>entity summarization: not necessary.</li>
<li>relationship summarization: not necessary.</li>
<li>claim extraction (optiona): unused.</li>
<li>community report generation: The direct text unit content containing each entity noun phrase is collected and used to prompt the LLM to generate a summary report.</li>
</ul>
<p><code>graphrag index --method fast</code></p>
<p>FastGraphRAG has a handful of NLP <a href="https://microsoft.github.io/graphrag/config/yaml/#extract_graph_nlp">options built in</a>. By default we use NLTK + regular expressions for the noun phrase extraction, which is very fast but primarily suitable for English. We have built in two additional methods using spaCy: semantic parsing and CFG. We use the <code>en_core_web_md</code> model by default for spaCy, but note that you can reference any <a href="https://spacy.io/models/">supported model</a> that you have installed. </p>
<p>Note that we also generally configure the text chunking to produce much smaller chunks (50-100 tokens). This results in a better co-occurrence graph.</p>
<p>⚠️ Note on SpaCy models:</p>
<p>This package requires SpaCy models to function correctly. If the required model is not installed, the package will automatically download and install it the first time it is used.</p>
<p>You can install it manually by running <code>python -m spacy download &lt;model_name&gt;</code>, for example <code>python -m spacy download en_core_web_md</code>.</p>
<h2 id="choosing-a-method">Choosing a Method</h2>
<p>Standard GraphRAG provides a rich description of real-world entities and relationships, but is more expensive that FastGraphRAG. We estimate graph extraction to constitute roughly 75% of indexing cost. FastGraphRAG is therefore much cheaper, but the tradeoff is that the extracted graph is less directly relevant for use outside of GraphRAG, and the graph tends to be quite a bit noisier. If high fidelity entities and graph exploration are important to your use case, we recommend staying with traditional GraphRAG. If your use case is primarily aimed at summary questions using global search, FastGraphRAG is a reasonable and cheaper alternative.</p>
</article>
</div>
<script>var target=document.getElementById(location.hash.slice(1));target&&target.name&&(target.checked=target.name.startsWith("__tabbed_"))</script>
</div>
</main>
<footer class="md-footer">
<div class="md-footer-meta md-typeset">
<div class="md-footer-meta__inner md-grid">
<div class="md-copyright">
<div class="md-copyright__highlight">
&copy; 2025 Microsoft&nbsp;|&nbsp; <a href="https://go.microsoft.com/fwlink/?LinkId=521839">Privacy</a>&nbsp;|&nbsp; <a href="https://go.microsoft.com/fwlink/?LinkId=2259814">Consumer Heath Privacy</a>&nbsp;|&nbsp; <a onclick="window.manageConsent();">Cookies</a>&nbsp;|&nbsp; <a href="https://go.microsoft.com/fwlink/?LinkID=206977">Terms of Use</a>&nbsp;|&nbsp; <a href="https://www.microsoft.com/trademarks">Trademarks</a>
</div>
Made with
<a href="https://squidfunk.github.io/mkdocs-material/" target="_blank" rel="noopener">
Material for MkDocs
</a>
</div>
</div>
</div>
</footer>
</div>
<div class="md-dialog" data-md-component="dialog">
<div class="md-dialog__inner md-typeset"></div>
</div>
<script id="__config" type="application/json">{"base": "../..", "features": ["content.code.copy", "content.code.select", "navigation.footer", "navigation.tabs"], "search": "../../assets/javascripts/workers/search.f8cc74c7.min.js", "translations": {"clipboard.copied": "Copied to clipboard", "clipboard.copy": "Copy to clipboard", "search.result.more.one": "1 more on this page", "search.result.more.other": "# more on this page", "search.result.none": "No matching documents", "search.result.one": "1 matching document", "search.result.other": "# matching documents", "search.result.placeholder": "Type to start searching", "search.result.term.missing": "Missing", "select.version": "Select version"}}</script>
<script src="../../assets/javascripts/bundle.c8b220af.min.js"></script>
<script src="../../scripts/create_cookie_banner.js"></script>
</body>
</html>
Reference in New Issue View Git Blame Copy Permalink