kanshan/graphrag
1
0
Fork 0
mirror of https://github.com/microsoft/graphrag.git synced 2026-02-01 00:31:51 +08:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity
e4e63708b6
graphrag/config/yaml/index.html

1970 lines
62 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="prev" href="../init/">
<link rel="next" href="../models/">
<link rel="icon" href="../../assets/images/favicon.png">
<meta name="generator" content="mkdocs-1.6.1, mkdocs-material-9.6.15">
<title>Detailed Configuration - GraphRAG</title>
<link rel="stylesheet" href="../../assets/stylesheets/main.342714a4.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="#default-configuration-mode-using-yamljson" 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">
Detailed Configuration
</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="../../index/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 md-tabs__item--active">
<a href="../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="../../index/overview/" class="md-nav__link">
<span class="md-ellipsis">
Overview
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../index/default_dataflow/" class="md-nav__link">
<span class="md-ellipsis">
Dataflow
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../index/methods/" class="md-nav__link">
<span class="md-ellipsis">
Methods
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../index/inputs/" class="md-nav__link">
<span class="md-ellipsis">
Inputs
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../index/outputs/" class="md-nav__link">
<span class="md-ellipsis">
Outputs
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../index/byog/" class="md-nav__link">
<span class="md-ellipsis">
Custom Graphs
</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--active md-nav__item--section md-nav__item--nested">
<input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_5" checked>
<label class="md-nav__link" for="__nav_5" id="__nav_5_label" tabindex="">
<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="true">
<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="../overview/" class="md-nav__link">
<span class="md-ellipsis">
Overview
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../init/" class="md-nav__link">
<span class="md-ellipsis">
Init Command
</span>
</a>
</li>
<li class="md-nav__item md-nav__item--active">
<input class="md-nav__toggle md-toggle" type="checkbox" id="__toc">
<a href="./" class="md-nav__link md-nav__link--active">
<span class="md-ellipsis">
Detailed Configuration
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../models/" class="md-nav__link">
<span class="md-ellipsis">
Language Model Selection
</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">
</nav>
</div>
</div>
</div>
<div class="md-content" data-md-component="content">
<article class="md-content__inner md-typeset">
<h1 id="default-configuration-mode-using-yamljson">Default Configuration Mode (using YAML/JSON)</h1>
<p>The default configuration mode may be configured by using a <code>settings.yml</code> or <code>settings.json</code> file in the data project root. If a <code>.env</code> file is present along with this config file, then it will be loaded, and the environment variables defined therein will be available for token replacements in your configuration document using <code>${ENV_VAR}</code> syntax. We initialize with YML by default in <code>graphrag init</code> but you may use the equivalent JSON form if preferred.</p>
<p>Many of these config values have defaults. Rather than replicate them here, please refer to the <a href="https://github.com/microsoft/graphrag/blob/main/graphrag/config/defaults.py">constants in the code</a> directly.</p>
<p>For example:</p>
<div class="highlight"><pre><span></span><code><a id="__codelineno-0-1" name="__codelineno-0-1" href="#__codelineno-0-1"></a># .env
<a id="__codelineno-0-2" name="__codelineno-0-2" href="#__codelineno-0-2"></a>GRAPHRAG_API_KEY=some_api_key
<a id="__codelineno-0-3" name="__codelineno-0-3" href="#__codelineno-0-3"></a>
<a id="__codelineno-0-4" name="__codelineno-0-4" href="#__codelineno-0-4"></a># settings.yml
<a id="__codelineno-0-5" name="__codelineno-0-5" href="#__codelineno-0-5"></a>llm:
<a id="__codelineno-0-6" name="__codelineno-0-6" href="#__codelineno-0-6"></a> api_key: ${GRAPHRAG_API_KEY}
</code></pre></div>
<h1 id="config-sections">Config Sections</h1>
<h2 id="language-model-setup">Language Model Setup</h2>
<h3 id="models">models</h3>
<p>This is a dict of model configurations. The dict key is used to reference this configuration elsewhere when a model instance is desired. In this way, you can specify as many different models as you need, and reference them differentially in the workflow steps.</p>
<p>For example:
<div class="highlight"><pre><span></span><code><a id="__codelineno-1-1" name="__codelineno-1-1" href="#__codelineno-1-1"></a>models:
<a id="__codelineno-1-2" name="__codelineno-1-2" href="#__codelineno-1-2"></a> default_chat_model:
<a id="__codelineno-1-3" name="__codelineno-1-3" href="#__codelineno-1-3"></a> api_key: ${GRAPHRAG_API_KEY}
<a id="__codelineno-1-4" name="__codelineno-1-4" href="#__codelineno-1-4"></a> type: openai_chat
<a id="__codelineno-1-5" name="__codelineno-1-5" href="#__codelineno-1-5"></a> model: gpt-4o
<a id="__codelineno-1-6" name="__codelineno-1-6" href="#__codelineno-1-6"></a> model_supports_json: true
<a id="__codelineno-1-7" name="__codelineno-1-7" href="#__codelineno-1-7"></a> default_embedding_model:
<a id="__codelineno-1-8" name="__codelineno-1-8" href="#__codelineno-1-8"></a> api_key: ${GRAPHRAG_API_KEY}
<a id="__codelineno-1-9" name="__codelineno-1-9" href="#__codelineno-1-9"></a> type: openai_embedding
<a id="__codelineno-1-10" name="__codelineno-1-10" href="#__codelineno-1-10"></a> model: text-embedding-ada-002
</code></pre></div></p>
<h4 id="fields">Fields</h4>
<ul>
<li><code>api_key</code> <strong>str</strong> - The OpenAI API key to use.</li>
<li><code>auth_type</code> <strong>api_key|azure_managed_identity</strong> - Indicate how you want to authenticate requests.</li>
<li><code>type</code> <strong>openai_chat|azure_openai_chat|openai_embedding|azure_openai_embedding|mock_chat|mock_embeddings</strong> - The type of LLM to use.</li>
<li><code>model</code> <strong>str</strong> - The model name.</li>
<li><code>encoding_model</code> <strong>str</strong> - The text encoding model to use. Default is to use the encoding model aligned with the language model (i.e., it is retrieved from tiktoken if unset).</li>
<li><code>api_base</code> <strong>str</strong> - The API base url to use.</li>
<li><code>api_version</code> <strong>str</strong> - The API version.</li>
<li><code>deployment_name</code> <strong>str</strong> - The deployment name to use (Azure).</li>
<li><code>organization</code> <strong>str</strong> - The client organization.</li>
<li><code>proxy</code> <strong>str</strong> - The proxy URL to use.</li>
<li><code>audience</code> <strong>str</strong> - (Azure OpenAI only) The URI of the target Azure resource/service for which a managed identity token is requested. Used if <code>api_key</code> is not defined. Default=<code>https://cognitiveservices.azure.com/.default</code></li>
<li><code>model_supports_json</code> <strong>bool</strong> - Whether the model supports JSON-mode output.</li>
<li><code>request_timeout</code> <strong>float</strong> - The per-request timeout.</li>
<li><code>tokens_per_minute</code> <strong>int</strong> - Set a leaky-bucket throttle on tokens-per-minute.</li>
<li><code>requests_per_minute</code> <strong>int</strong> - Set a leaky-bucket throttle on requests-per-minute.</li>
<li><code>retry_strategy</code> <strong>str</strong> - Retry strategy to use, "native" is the default and uses the strategy built into the OpenAI SDK. Other allowable values include "exponential_backoff", "random_wait", and "incremental_wait".</li>
<li><code>max_retries</code> <strong>int</strong> - The maximum number of retries to use.</li>
<li><code>max_retry_wait</code> <strong>float</strong> - The maximum backoff time.</li>
<li><code>concurrent_requests</code> <strong>int</strong> The number of open requests to allow at once.</li>
<li><code>async_mode</code> <strong>asyncio|threaded</strong> The async mode to use. Either <code>asyncio</code> or <code>threaded</code>.</li>
<li><code>responses</code> <strong>list[str]</strong> - If this model type is mock, this is a list of response strings to return.</li>
<li><code>n</code> <strong>int</strong> - The number of completions to generate.</li>
<li><code>max_tokens</code> <strong>int</strong> - The maximum number of output tokens. Not valid for o-series models.</li>
<li><code>temperature</code> <strong>float</strong> - The temperature to use. Not valid for o-series models.</li>
<li><code>top_p</code> <strong>float</strong> - The top-p value to use. Not valid for o-series models.</li>
<li><code>frequency_penalty</code> <strong>float</strong> - Frequency penalty for token generation. Not valid for o-series models.</li>
<li><code>presence_penalty</code> <strong>float</strong> - Frequency penalty for token generation. Not valid for o-series models.</li>
<li><code>max_completion_tokens</code> <strong>int</strong> - Max number of tokens to consume for chat completion. Must be large enough to include an unknown amount for "reasoning" by the model. o-series models only.</li>
<li><code>reasoning_effort</code> <strong>low|medium|high</strong> - Amount of "thought" for the model to expend reasoning about a response. o-series models only.</li>
</ul>
<h2 id="input-files-and-chunking">Input Files and Chunking</h2>
<h3 id="input">input</h3>
<p>Our pipeline can ingest .csv, .txt, or .json data from an input location. See the <a href="../../index/inputs/">inputs page</a> for more details and examples.</p>
<h4 id="fields_1">Fields</h4>
<ul>
<li><code>storage</code> <strong>StorageConfig</strong></li>
<li><code>type</code> <strong>file|blob|cosmosdb</strong> - The storage type to use. Default=<code>file</code></li>
<li><code>base_dir</code> <strong>str</strong> - The base directory to write output artifacts to, relative to the root.</li>
<li><code>connection_string</code> <strong>str</strong> - (blob/cosmosdb only) The Azure Storage connection string.</li>
<li><code>container_name</code> <strong>str</strong> - (blob/cosmosdb only) The Azure Storage container name.</li>
<li><code>storage_account_blob_url</code> <strong>str</strong> - (blob only) The storage account blob URL to use.</li>
<li><code>cosmosdb_account_blob_url</code> <strong>str</strong> - (cosmosdb only) The CosmosDB account blob URL to use.</li>
<li><code>file_type</code> <strong>text|csv|json</strong> - The type of input data to load. Default is <code>text</code></li>
<li><code>encoding</code> <strong>str</strong> - The encoding of the input file. Default is <code>utf-8</code></li>
<li><code>file_pattern</code> <strong>str</strong> - A regex to match input files. Default is <code>.*\.csv$</code>, <code>.*\.txt$</code>, or <code>.*\.json$</code> depending on the specified <code>file_type</code>, but you can customize it if needed.</li>
<li><code>file_filter</code> <strong>dict</strong> - Key/value pairs to filter. Default is None.</li>
<li><code>text_column</code> <strong>str</strong> - (CSV/JSON only) The text column name. If unset we expect a column named <code>text</code>.</li>
<li><code>title_column</code> <strong>str</strong> - (CSV/JSON only) The title column name, filename will be used if unset.</li>
<li><code>metadata</code> <strong>list[str]</strong> - (CSV/JSON only) The additional document attributes fields to keep.</li>
</ul>
<h3 id="chunks">chunks</h3>
<p>These settings configure how we parse documents into text chunks. This is necessary because very large documents may not fit into a single context window, and graph extraction accuracy can be modulated. Also note the <code>metadata</code> setting in the input document config, which will replicate document metadata into each chunk.</p>
<h4 id="fields_2">Fields</h4>
<ul>
<li><code>size</code> <strong>int</strong> - The max chunk size in tokens.</li>
<li><code>overlap</code> <strong>int</strong> - The chunk overlap in tokens.</li>
<li><code>group_by_columns</code> <strong>list[str]</strong> - Group documents by these fields before chunking.</li>
<li><code>strategy</code> <strong>str</strong>[tokens|sentences] - How to chunk the text. </li>
<li><code>encoding_model</code> <strong>str</strong> - The text encoding model to use for splitting on token boundaries.</li>
<li><code>prepend_metadata</code> <strong>bool</strong> - Determines if metadata values should be added at the beginning of each chunk. Default=<code>False</code>.</li>
<li><code>chunk_size_includes_metadata</code> <strong>bool</strong> - Specifies whether the chunk size calculation should include metadata tokens. Default=<code>False</code>.</li>
</ul>
<h2 id="outputs-and-storage">Outputs and Storage</h2>
<h3 id="output">output</h3>
<p>This section controls the storage mechanism used by the pipeline used for exporting output tables.</p>
<h4 id="fields_3">Fields</h4>
<ul>
<li><code>type</code> <strong>file|memory|blob|cosmosdb</strong> - The storage type to use. Default=<code>file</code></li>
<li><code>base_dir</code> <strong>str</strong> - The base directory to write output artifacts to, relative to the root.</li>
<li><code>connection_string</code> <strong>str</strong> - (blob/cosmosdb only) The Azure Storage connection string.</li>
<li><code>container_name</code> <strong>str</strong> - (blob/cosmosdb only) The Azure Storage container name.</li>
<li><code>storage_account_blob_url</code> <strong>str</strong> - (blob only) The storage account blob URL to use.</li>
<li><code>cosmosdb_account_blob_url</code> <strong>str</strong> - (cosmosdb only) The CosmosDB account blob URL to use.</li>
</ul>
<h3 id="update_index_output">update_index_output</h3>
<p>The section defines a secondary storage location for running incremental indexing, to preserve your original outputs.</p>
<h4 id="fields_4">Fields</h4>
<ul>
<li><code>type</code> <strong>file|memory|blob|cosmosdb</strong> - The storage type to use. Default=<code>file</code></li>
<li><code>base_dir</code> <strong>str</strong> - The base directory to write output artifacts to, relative to the root.</li>
<li><code>connection_string</code> <strong>str</strong> - (blob/cosmosdb only) The Azure Storage connection string.</li>
<li><code>container_name</code> <strong>str</strong> - (blob/cosmosdb only) The Azure Storage container name.</li>
<li><code>storage_account_blob_url</code> <strong>str</strong> - (blob only) The storage account blob URL to use.</li>
<li><code>cosmosdb_account_blob_url</code> <strong>str</strong> - (cosmosdb only) The CosmosDB account blob URL to use.</li>
</ul>
<h3 id="cache">cache</h3>
<p>This section controls the cache mechanism used by the pipeline. This is used to cache LLM invocation results for faster performance when re-running the indexing process.</p>
<h4 id="fields_5">Fields</h4>
<ul>
<li><code>type</code> <strong>file|memory|blob|cosmosdb</strong> - The storage type to use. Default=<code>file</code></li>
<li><code>base_dir</code> <strong>str</strong> - The base directory to write output artifacts to, relative to the root.</li>
<li><code>connection_string</code> <strong>str</strong> - (blob/cosmosdb only) The Azure Storage connection string.</li>
<li><code>container_name</code> <strong>str</strong> - (blob/cosmosdb only) The Azure Storage container name.</li>
<li><code>storage_account_blob_url</code> <strong>str</strong> - (blob only) The storage account blob URL to use.</li>
<li><code>cosmosdb_account_blob_url</code> <strong>str</strong> - (cosmosdb only) The CosmosDB account blob URL to use.</li>
</ul>
<h3 id="reporting">reporting</h3>
<p>This section controls the reporting mechanism used by the pipeline, for common events and error messages. The default is to write reports to a file in the output directory. However, you can also choose to write reports to an Azure Blob Storage container.</p>
<h4 id="fields_6">Fields</h4>
<ul>
<li><code>type</code> <strong>file|blob</strong> - The reporting type to use. Default=<code>file</code></li>
<li><code>base_dir</code> <strong>str</strong> - The base directory to write reports to, relative to the root.</li>
<li><code>connection_string</code> <strong>str</strong> - (blob only) The Azure Storage connection string.</li>
<li><code>container_name</code> <strong>str</strong> - (blob only) The Azure Storage container name.</li>
<li><code>storage_account_blob_url</code> <strong>str</strong> - The storage account blob URL to use.</li>
</ul>
<h3 id="vector_store">vector_store</h3>
<p>Where to put all vectors for the system. Configured for lancedb by default. This is a dict, with the key used to identify individual store parameters (e.g., for text embedding).</p>
<h4 id="fields_7">Fields</h4>
<ul>
<li><code>type</code> <strong>lancedb|azure_ai_search|cosmosdb</strong> - Type of vector store. Default=<code>lancedb</code></li>
<li><code>db_uri</code> <strong>str</strong> (only for lancedb) - The database uri. Default=<code>storage.base_dir/lancedb</code></li>
<li><code>url</code> <strong>str</strong> (only for AI Search) - AI Search endpoint</li>
<li><code>api_key</code> <strong>str</strong> (optional - only for AI Search) - The AI Search api key to use.</li>
<li><code>audience</code> <strong>str</strong> (only for AI Search) - Audience for managed identity token if managed identity authentication is used.</li>
<li><code>container_name</code> <strong>str</strong> - The name of a vector container. This stores all indexes (tables) for a given dataset ingest. Default=<code>default</code></li>
<li><code>database_name</code> <strong>str</strong> - (cosmosdb only) Name of the database.</li>
<li><code>overwrite</code> <strong>bool</strong> (only used at index creation time) - Overwrite collection if it exist. Default=<code>True</code></li>
</ul>
<h2 id="workflow-configurations">Workflow Configurations</h2>
<p>These settings control each individual workflow as they execute.</p>
<h3 id="workflows">workflows</h3>
<p><strong>list[str]</strong> - This is a list of workflow names to run, in order. GraphRAG has built-in pipelines to configure this, but you can run exactly and only what you want by specifying the list here. Useful if you have done part of the processing yourself.</p>
<h3 id="embed_text">embed_text</h3>
<p>By default, the GraphRAG indexer will only export embeddings required for our query methods. However, the model has embeddings defined for all plaintext fields, and these can be customized by setting the <code>target</code> and <code>names</code> fields.</p>
<p>Supported embeddings names are:</p>
<ul>
<li><code>text_unit.text</code></li>
<li><code>document.text</code></li>
<li><code>entity.title</code></li>
<li><code>entity.description</code></li>
<li><code>relationship.description</code></li>
<li><code>community.title</code></li>
<li><code>community.summary</code></li>
<li><code>community.full_content</code></li>
</ul>
<h4 id="fields_8">Fields</h4>
<ul>
<li><code>model_id</code> <strong>str</strong> - Name of the model definition to use for text embedding.</li>
<li><code>vector_store_id</code> <strong>str</strong> - Name of vector store definition to write to.</li>
<li><code>batch_size</code> <strong>int</strong> - The maximum batch size to use.</li>
<li><code>batch_max_tokens</code> <strong>int</strong> - The maximum batch # of tokens.</li>
<li><code>names</code> <strong>list[str]</strong> - List of the embeddings names to run (must be in supported list).</li>
</ul>
<h3 id="extract_graph">extract_graph</h3>
<p>Tune the language model-based graph extraction process.</p>
<h4 id="fields_9">Fields</h4>
<ul>
<li><code>model_id</code> <strong>str</strong> - Name of the model definition to use for API calls.</li>
<li><code>prompt</code> <strong>str</strong> - The prompt file to use.</li>
<li><code>entity_types</code> <strong>list[str]</strong> - The entity types to identify.</li>
<li><code>max_gleanings</code> <strong>int</strong> - The maximum number of gleaning cycles to use.</li>
</ul>
<h3 id="summarize_descriptions">summarize_descriptions</h3>
<h4 id="fields_10">Fields</h4>
<ul>
<li><code>model_id</code> <strong>str</strong> - Name of the model definition to use for API calls.</li>
<li><code>prompt</code> <strong>str</strong> - The prompt file to use.</li>
<li><code>max_length</code> <strong>int</strong> - The maximum number of output tokens per summarization.</li>
<li><code>max_input_length</code> <strong>int</strong> - The maximum number of tokens to collect for summarization (this will limit how many descriptions you send to be summarized for a given entity or relationship).</li>
</ul>
<h3 id="extract_graph_nlp">extract_graph_nlp</h3>
<p>Defines settings for NLP-based graph extraction methods.</p>
<h4 id="fields_11">Fields</h4>
<ul>
<li><code>normalize_edge_weights</code> <strong>bool</strong> - Whether to normalize the edge weights during graph construction. Default=<code>True</code>.</li>
<li><code>text_analyzer</code> <strong>dict</strong> - Parameters for the NLP model.</li>
<li>extractor_type <strong>regex_english|syntactic_parser|cfg</strong> - Default=<code>regex_english</code>.</li>
<li>model_name <strong>str</strong> - Name of NLP model (for SpaCy-based models)</li>
<li>max_word_length <strong>int</strong> - Longest word to allow. Default=<code>15</code>.</li>
<li>word_delimiter <strong>str</strong> - Delimiter to split words. Default ' '.</li>
<li>include_named_entities <strong>bool</strong> - Whether to include named entities in noun phrases. Default=<code>True</code>.</li>
<li>exclude_nouns <strong>list[str] | None</strong> - List of nouns to exclude. If <code>None</code>, we use an internal stopword list.</li>
<li>exclude_entity_tags <strong>list[str]</strong> - List of entity tags to ignore.</li>
<li>exclude_pos_tags <strong>list[str]</strong> - List of part-of-speech tags to ignore.</li>
<li>noun_phrase_tags <strong>list[str]</strong> - List of noun phrase tags to ignore.</li>
<li>noun_phrase_grammars <strong>dict[str, str]</strong> - Noun phrase grammars for the model (cfg-only).</li>
</ul>
<h3 id="prune_graph">prune_graph</h3>
<p>Parameters for manual graph pruning. This can be used to optimize the modularity of your graph clusters, by removing overly-connected or rare nodes.</p>
<h4 id="fields_12">Fields</h4>
<ul>
<li>min_node_freq <strong>int</strong> - The minimum node frequency to allow.</li>
<li>max_node_freq_std <strong>float | None</strong> - The maximum standard deviation of node frequency to allow.</li>
<li>min_node_degree <strong>int</strong> - The minimum node degree to allow.</li>
<li>max_node_degree_std <strong>float | None</strong> - The maximum standard deviation of node degree to allow.</li>
<li>min_edge_weight_pct <strong>float</strong> - The minimum edge weight percentile to allow.</li>
<li>remove_ego_nodes <strong>bool</strong> - Remove ego nodes.</li>
<li>lcc_only <strong>bool</strong> - Only use largest connected component.</li>
</ul>
<h3 id="cluster_graph">cluster_graph</h3>
<p>These are the settings used for Leiden hierarchical clustering of the graph to create communities.</p>
<h4 id="fields_13">Fields</h4>
<ul>
<li><code>max_cluster_size</code> <strong>int</strong> - The maximum cluster size to export.</li>
<li><code>use_lcc</code> <strong>bool</strong> - Whether to only use the largest connected component.</li>
<li><code>seed</code> <strong>int</strong> - A randomization seed to provide if consistent run-to-run results are desired. We do provide a default in order to guarantee clustering stability.</li>
</ul>
<h3 id="extract_claims">extract_claims</h3>
<h4 id="fields_14">Fields</h4>
<ul>
<li><code>enabled</code> <strong>bool</strong> - Whether to enable claim extraction. Off by default, because claim prompts really need user tuning.</li>
<li><code>model_id</code> <strong>str</strong> - Name of the model definition to use for API calls.</li>
<li><code>prompt</code> <strong>str</strong> - The prompt file to use.</li>
<li><code>description</code> <strong>str</strong> - Describes the types of claims we want to extract.</li>
<li><code>max_gleanings</code> <strong>int</strong> - The maximum number of gleaning cycles to use.</li>
</ul>
<h3 id="community_reports">community_reports</h3>
<h4 id="fields_15">Fields</h4>
<ul>
<li><code>model_id</code> <strong>str</strong> - Name of the model definition to use for API calls.</li>
<li><code>prompt</code> <strong>str</strong> - The prompt file to use.</li>
<li><code>max_length</code> <strong>int</strong> - The maximum number of output tokens per report.</li>
<li><code>max_input_length</code> <strong>int</strong> - The maximum number of input tokens to use when generating reports.</li>
</ul>
<h3 id="embed_graph">embed_graph</h3>
<p>We use node2vec to embed the graph. This is primarily used for visualization, so it is not turned on by default.</p>
<h4 id="fields_16">Fields</h4>
<ul>
<li><code>enabled</code> <strong>bool</strong> - Whether to enable graph embeddings.</li>
<li><code>dimensions</code> <strong>int</strong> - Number of vector dimensions to produce.</li>
<li><code>num_walks</code> <strong>int</strong> - The node2vec number of walks.</li>
<li><code>walk_length</code> <strong>int</strong> - The node2vec walk length.</li>
<li><code>window_size</code> <strong>int</strong> - The node2vec window size.</li>
<li><code>iterations</code> <strong>int</strong> - The node2vec number of iterations.</li>
<li><code>random_seed</code> <strong>int</strong> - The node2vec random seed.</li>
<li><code>strategy</code> <strong>dict</strong> - Fully override the embed graph strategy.</li>
</ul>
<h3 id="umap">umap</h3>
<p>Indicates whether we should run UMAP dimensionality reduction. This is used to provide an x/y coordinate to each graph node, suitable for visualization. If this is not enabled, nodes will receive a 0/0 x/y coordinate. If this is enabled, you <em>must</em> enable graph embedding as well.</p>
<h4 id="fields_17">Fields</h4>
<ul>
<li><code>enabled</code> <strong>bool</strong> - Whether to enable UMAP layouts.</li>
</ul>
<h3 id="snapshots">snapshots</h3>
<h4 id="fields_18">Fields</h4>
<ul>
<li><code>embeddings</code> <strong>bool</strong> - Export embeddings snapshots to parquet.</li>
<li><code>graphml</code> <strong>bool</strong> - Export graph snapshots to GraphML.</li>
</ul>
<h2 id="query">Query</h2>
<h3 id="local_search">local_search</h3>
<h4 id="fields_19">Fields</h4>
<ul>
<li><code>chat_model_id</code> <strong>str</strong> - Name of the model definition to use for Chat Completion calls.</li>
<li><code>embedding_model_id</code> <strong>str</strong> - Name of the model definition to use for Embedding calls.</li>
<li><code>prompt</code> <strong>str</strong> - The prompt file to use.</li>
<li><code>text_unit_prop</code> <strong>float</strong> - The text unit proportion. </li>
<li><code>community_prop</code> <strong>float</strong> - The community proportion.</li>
<li><code>conversation_history_max_turns</code> <strong>int</strong> - The conversation history maximum turns.</li>
<li><code>top_k_entities</code> <strong>int</strong> - The top k mapped entities.</li>
<li><code>top_k_relationships</code> <strong>int</strong> - The top k mapped relations.</li>
<li><code>max_context_tokens</code> <strong>int</strong> - The maximum tokens to use building the request context.</li>
</ul>
<h3 id="global_search">global_search</h3>
<h4 id="fields_20">Fields</h4>
<ul>
<li><code>chat_model_id</code> <strong>str</strong> - Name of the model definition to use for Chat Completion calls.</li>
<li><code>map_prompt</code> <strong>str</strong> - The mapper prompt file to use.</li>
<li><code>reduce_prompt</code> <strong>str</strong> - The reducer prompt file to use.</li>
<li><code>knowledge_prompt</code> <strong>str</strong> - The knowledge prompt file to use.</li>
<li><code>map_prompt</code> <strong>str | None</strong> - The global search mapper prompt to use.</li>
<li><code>reduce_prompt</code> <strong>str | None</strong> - The global search reducer to use.</li>
<li><code>knowledge_prompt</code> <strong>str | None</strong> - The global search general prompt to use.</li>
<li><code>max_context_tokens</code> <strong>int</strong> - The maximum context size to create, in tokens.</li>
<li><code>data_max_tokens</code> <strong>int</strong> - The maximum tokens to use constructing the final response from the reduces responses.</li>
<li><code>map_max_length</code> <strong>int</strong> - The maximum length to request for map responses, in words.</li>
<li><code>reduce_max_length</code> <strong>int</strong> - The maximum length to request for reduce responses, in words.</li>
<li><code>dynamic_search_threshold</code> <strong>int</strong> - Rating threshold in include a community report.</li>
<li><code>dynamic_search_keep_parent</code> <strong>bool</strong> - Keep parent community if any of the child communities are relevant.</li>
<li><code>dynamic_search_num_repeats</code> <strong>int</strong> - Number of times to rate the same community report.</li>
<li><code>dynamic_search_use_summary</code> <strong>bool</strong> - Use community summary instead of full_context.</li>
<li><code>dynamic_search_max_level</code> <strong>int</strong> - The maximum level of community hierarchy to consider if none of the processed communities are relevant.</li>
</ul>
<h3 id="drift_search">drift_search</h3>
<h4 id="fields_21">Fields</h4>
<ul>
<li><code>chat_model_id</code> <strong>str</strong> - Name of the model definition to use for Chat Completion calls.</li>
<li><code>embedding_model_id</code> <strong>str</strong> - Name of the model definition to use for Embedding calls.</li>
<li><code>prompt</code> <strong>str</strong> - The prompt file to use.</li>
<li><code>reduce_prompt</code> <strong>str</strong> - The reducer prompt file to use.</li>
<li><code>data_max_tokens</code> <strong>int</strong> - The data llm maximum tokens.</li>
<li><code>reduce_max_tokens</code> <strong>int</strong> - The maximum tokens for the reduce phase. Only use if a non-o-series model.</li>
<li><code>reduce_max_completion_tokens</code> <strong>int</strong> - The maximum tokens for the reduce phase. Only use for o-series models.</li>
<li><code>concurrency</code> <strong>int</strong> - The number of concurrent requests.</li>
<li><code>drift_k_followups</code> <strong>int</strong> - The number of top global results to retrieve.</li>
<li><code>primer_folds</code> <strong>int</strong> - The number of folds for search priming.</li>
<li><code>primer_llm_max_tokens</code> <strong>int</strong> - The maximum number of tokens for the LLM in primer.</li>
<li><code>n_depth</code> <strong>int</strong> - The number of drift search steps to take.</li>
<li><code>local_search_text_unit_prop</code> <strong>float</strong> - The proportion of search dedicated to text units.</li>
<li><code>local_search_community_prop</code> <strong>float</strong> - The proportion of search dedicated to community properties.</li>
<li><code>local_search_top_k_mapped_entities</code> <strong>int</strong> - The number of top K entities to map during local search.</li>
<li><code>local_search_top_k_relationships</code> <strong>int</strong> - The number of top K relationships to map during local search.</li>
<li><code>local_search_max_data_tokens</code> <strong>int</strong> - The maximum context size in tokens for local search.</li>
<li><code>local_search_temperature</code> <strong>float</strong> - The temperature to use for token generation in local search.</li>
<li><code>local_search_top_p</code> <strong>float</strong> - The top-p value to use for token generation in local search.</li>
<li><code>local_search_n</code> <strong>int</strong> - The number of completions to generate in local search.</li>
<li><code>local_search_llm_max_gen_tokens</code> <strong>int</strong> - The maximum number of generated tokens for the LLM in local search. Only use if a non-o-series model.</li>
<li><code>local_search_llm_max_gen_completion_tokens</code> <strong>int</strong> - The maximum number of generated tokens for the LLM in local search. Only use for o-series models.</li>
</ul>
<h3 id="basic_search">basic_search</h3>
<h4 id="fields_22">Fields</h4>
<ul>
<li><code>chat_model_id</code> <strong>str</strong> - Name of the model definition to use for Chat Completion calls.</li>
<li><code>embedding_model_id</code> <strong>str</strong> - Name of the model definition to use for Embedding calls.</li>
<li><code>prompt</code> <strong>str</strong> - The prompt file to use.</li>
<li><code>k</code> <strong>int | None</strong> - Number of text units to retrieve from the vector store for context building.</li>
</ul>
</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">
<nav class="md-footer__inner md-grid" aria-label="Footer" >
<a href="../init/" class="md-footer__link md-footer__link--prev" aria-label="Previous: Init Command">
<div class="md-footer__button md-icon">
<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>
</div>
<div class="md-footer__title">
<span class="md-footer__direction">
Previous
</span>
<div class="md-ellipsis">
Init Command
</div>
</div>
</a>
<a href="../models/" class="md-footer__link md-footer__link--next" aria-label="Next: Language Model Selection">
<div class="md-footer__title">
<span class="md-footer__direction">
Next
</span>
<div class="md-ellipsis">
Language Model Selection
</div>
</div>
<div class="md-footer__button md-icon">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M4 11v2h12l-5.5 5.5 1.42 1.42L19.84 12l-7.92-7.92L10.5 5.5 16 11z"/></svg>
</div>
</a>
</nav>
<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.d50fe291.min.js", "tags": null, "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"}, "version": null}</script>
<script src="../../assets/javascripts/bundle.56ea9cef.min.js"></script>
<script src="../../scripts/create_cookie_banner.js"></script>
</body>
</html>
Reference in New Issue View Git Blame Copy Permalink