yujunjun/graphrag
1
0
Fork 0
mirror of https://github.com/microsoft/graphrag.git synced 2025-09-17 20:24:20 +00:00
Code Issues Packages Projects Releases Wiki Activity
graphrag/posts/query/3-cli/index.html

352 lines
13 KiB
HTML
Raw Blame History

<!doctype html>
<html lang="en">
<head>
<meta charset="utf-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>Query CLI</title>
<link rel="stylesheet" href="https://cdn.jsdelivr.net/npm/bulma@0.9.4/css/bulma.min.css">
<link href="https://unpkg.com/prismjs@1.20.0/themes/prism-okaidia.css" rel="stylesheet">
<link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/Primer/19.1.1/tooltips.min.css" crossorigin="anonymous" referrerpolicy="no-referrer">
<style>
html {
padding: 0;
margin: 0;
}
body{
font-family: "Helvetica Neue", Helvetica, Arial, sans-serif;
padding: 0;
margin: 0;
}
footer{
width: 100%;
height: 32px;
font-size: 12px;
display: flex;
flex-direction: row;
justify-content: center;
gap: 18px;
align-items: center;
color: #5d5d5d;
background: #e9eaeb;
border-top: 1px solid #c4c5c6;
}
#cookiesManager{
cursor: pointer;
color: #485fc7;
}
.page-content {
display: flex;
flex-direction: row;
margin: 0;
padding: 0;
overflow: scroll;
padding: 0;
margin: 0;
}
header {
background-color: lightgrey;
height: 2%;
padding: 10px;
}
nav {
padding: 1em;
min-width: 200px;
}
main {
flex: 1;
padding: 0 5em 0 5em;
}
.logotitle {
font-size: 1.5em;
font-weight: bold;
margin: 5px;
}
.number {
all: unset;
}
.tag.token {
all: unset;
}
main ul {
list-style-type: disc;
padding-left: 30px;
margin-top: 10px;
}
h1 {
font-size: 2rem;
margin-top: 10px;
}
h2 {
font-size: 1.5rem;
margin-top: 10px;
font-weight: 500;
}
h3 {
font-size: 1rem;
margin-top: 10px;
font-weight: 500;
}
p {
margin-top: 10px;
}
/* Accessibility styling */
a {
color: #485fc7;
text-decoration: underline;
}
.menu-list a {
text-decoration: none;
}
.token.comment, .token.prolog, .token.doctype, .token.cdata {
color: #8093a5;
}
.token.property, .token.tag, .token.constant, .token.symbol, .token.deleted {
color: #ff36ab;
}
</style>
<script type="module" async="">import mermaid from "https://unpkg.com/mermaid@10/dist/mermaid.esm.min.mjs";document.addEventListener('DOMContentLoaded', mermaid.initialize({"loadOnSave":true}));</script>
<script>function showTooltip(o,e){o.trigger.className.includes("tooltipped")||(o.trigger.children[0].className="tooltipped tooltipped-s",o.trigger.children[0].ariaLabel=e)}window.addEventListener("load",()=>{var o=new ClipboardJS(".code-copy");o.on("success",o=>showTooltip(o,"Copied!")),o.on("error",o=>showTooltip(o,"Failed..."))});</script>
<script async="" src="https://cdn.jsdelivr.net/npm/clipboard@2.0.11/dist/clipboard.min.js"></script>
<script src="https://wcpstatic.microsoft.com/mscc/lib/v2/wcp-consent.js" type="text/javascript"></script>
<script>
function onConsentChanged(categoryPreferences) {
console.log("onConsentChanged", categoryPreferences);
}
var siteConsent
function initialize(){
var currentYear = new Date().getFullYear()
document.getElementById("copyright").innerHTML = `©️ ${currentYear} Microsoft`;
window.WcpConsent && WcpConsent.init("en-US", "cookie-banner", function (err, _siteConsent) {
if (!err) {
siteConsent = _siteConsent; //siteConsent is used to get the current consent
} else {
console.log("Error initializing WcpConsent: "+ err);
}
}, onConsentChanged, WcpConsent.themes.light);
}
addEventListener("DOMContentLoaded", initialize)
addEventListener("DOMContentLoaded", checkCookieManager)
function checkCookieManager(){
if(siteConsent.isConsentRequired){
document.getElementById("cookiesManager").style.display = 'block';
document.getElementById("divider").style.display = 'block';
}
else{
document.getElementById("cookiesManager").style.display = 'none';
document.getElementById("divider").style.display = 'none';
}
}
function manageConsent() {
if(siteConsent.isConsentRequired){
siteConsent.manageConsent();
}
}
</script>
</head>
<body>
<header>
<div id="cookie-banner"></div>
<a href="/"><span class="logotitle">GraphRAG</span></a>
</header>
<div class="page-content">
<!-- Sidebar -->
<aside class="menu">
<ul class="menu-list">
<li>
<a href="/">Welcome</a>
</li>
<!-- Get Started Links -->
<li>
<a href="/posts/get_started/">Get Started</a>
<a href="/posts/developing/">Developing</a>
</li>
<!-- Indexing Links -->
<li>
<a href="/posts/index/overview/">Indexing</a>
<ul><li>
<a href="/posts/index/0-architecture/">Architecture</a>
</li><li>
<a href="/posts/index/1-default_dataflow/">Dataflow</a>
</li><li>
<a href="/posts/index/2-cli/">CLI</a>
</li><li>
<a href="/posts/config/overview/">Configuration</a>
<ul>
<li>
<a href="/posts/config/env_vars">Using Env Vars</a>
</li>
<li>
<a href="/posts/config/json_yaml">Using JSON or YAML</a>
</li>
<li>
<a href="/posts/config/custom">Fully Custom</a>
</li>
<li>
<a href="/posts/config/template">Template</a>
</li>
</ul>
</li>
<li>
<a href="/posts/prompt_tuning/overview/">Prompt Tuning</a>
<ul>
<li>
<a href="/posts/prompt_tuning/auto_prompt_tuning/">Automatic Templating</a>
</li>
<li>
<a href="/posts/prompt_tuning/manual_prompt_tuning/">Manual Prompt Tuning</a>
</li>
</ul>
</li>
</ul>
</li>
<!-- Query Links -->
<li>
<a href="/posts/query/overview/">Query</a>
<ul><li>
<a href="/posts/query/1-local_search/">Local Search</a>
</li><li>
<a href="/posts/query/2-question_generation/">Question Generation</a>
</li><li>
<a href="/posts/query/0-global_search/">Global Search</a>
</li><li>
<a href="/posts/query/3-cli/" class="is-active" aria-current="page">CLI</a>
</li><li>
<a href="/posts/query/notebooks/overview/">Notebooks</a>
<ul>
<li>
<a href="/posts/query/notebooks/global_search_nb">Global Search</a>
</li>
<li>
<a href="/posts/query/notebooks/local_search_nb">Local Search</a>
</li>
</ul>
</li>
</ul>
</li>
</ul>
</aside>
<!-- Main Content -->
<main>
<h1>Query CLI</h1>
<p>The GraphRAG query CLI allows for no-code usage of the GraphRAG Query engine.</p>
<div style="position: relative">
<pre class="language-bash"><code id="code-3" class="language-bash">python <span class="token parameter variable">-m</span> graphrag.query <span class="token parameter variable">--data</span> <span class="token operator">&lt;</span>path-to-data<span class="token operator">></span> <span class="token parameter variable">--community_level</span> <span class="token operator">&lt;</span>comunit-level<span class="token operator">></span> <span class="token parameter variable">--response_type</span> <span class="token operator">&lt;</span>response-type<span class="token operator">></span> <span class="token parameter variable">--method</span> <span class="token operator">&lt;</span><span class="token string">"local"</span><span class="token operator">|</span><span class="token string">"global"</span><span class="token operator">></span> <span class="token operator">&lt;</span>query<span class="token operator">></span></code></pre>
<button class="code-copy " data-clipboard-target="#code-3" style="position: absolute; top: 7.5px; right: 6px; padding-top: 3px; cursor: pointer; outline: none; opacity: 0.8;" title="Copy">
<span style="display:inline-block;background:url(https://api.iconify.design/mdi/content-copy.svg) no-repeat center center / contain;width: 16px; height: 16px;" class=""></span>
</button>
</div>
<h2>CLI Arguments</h2>
<ul>
<li><code>--data &lt;path-to-data&gt;</code> - Folder containing the <code>.parquet</code> output files from running the Indexer.</li>
<li><code>--community_level &lt;community-level&gt;</code> - Community level in the Leiden community hierarchy from which we will load the community reports higher value means we use reports on smaller communities. Default: 2</li>
<li><code>--response_type &lt;response-type&gt;</code> - Free form text describing the response type and format, can be anything, e.g. <code>Multiple Paragraphs</code>, <code>Single Paragraph</code>, <code>Single Sentence</code>, <code>List of 3-7 Points</code>, <code>Single Page</code>, <code>Multi-Page Report</code>. Default: <code>Multiple Paragraphs</code>.</li>
<li><code>--method &lt;&quot;local&quot;|&quot;global&quot;&gt;</code> - Method to use to answer the query, one of local or global. For more information check <a href="overview.md">Overview</a></li>
</ul>
<h2>Env Variables</h2>
<p>Required environment variables to execute:</p>
<ul>
<li><code>GRAPHRAG_API_KEY</code> - API Key for executing the model, will fallback to <code>OPENAI_API_KEY</code> if one is not provided.</li>
<li><code>GRAPHRAG_LLM_MODEL</code> - Model to use for Chat Completions.</li>
<li><code>GRAPHRAG_EMBEDDING_MODEL</code> - Model to use for Embeddings.</li>
</ul>
<p>You can further customize the execution by providing these environment variables:</p>
<ul>
<li><code>GRAPHRAG_LLM_API_BASE</code> - The API Base URL. Default: <code>None</code></li>
<li><code>GRAPHRAG_LLM_TYPE</code> - The LLM operation type. Either <code>openai_chat</code> or <code>azure_openai_chat</code>. Default: <code>openai_chat</code></li>
<li><code>GRAPHRAG_LLM_MAX_RETRIES</code> - The maximum number of retries to attempt when a request fails. Default: <code>20</code></li>
<li><code>GRAPHRAG_EMBEDDING_API_BASE</code> - The API Base URL. Default: <code>None</code></li>
<li><code>GRAPHRAG_EMBEDDING_TYPE</code> - The embedding client to use. Either <code>openai_embedding</code> or <code>azure_openai_embedding</code>. Default: <code>openai_embedding</code></li>
<li><code>GRAPHRAG_EMBEDDING_MAX_RETRIES</code> - The maximum number of retries to attempt when a request fails. Default: <code>20</code></li>
<li><code>GRAPHRAG_LOCAL_SEARCH_TEXT_UNIT_PROP</code> - Proportion of context window dedicated to related text units. Default: <code>0.5</code></li>
<li><code>GRAPHRAG_LOCAL_SEARCH_COMMUNITY_PROP</code> - Proportion of context window dedicated to community reports. Default: <code>0.1</code></li>
<li><code>GRAPHRAG_LOCAL_SEARCH_CONVERSATION_HISTORY_MAX_TURNS</code> - Maximum number of turns to include in the conversation history. Default: <code>5</code></li>
<li><code>GRAPHRAG_LOCAL_SEARCH_TOP_K_ENTITIES</code> - Number of related entities to retrieve from the entity description embedding store. Default: <code>10</code></li>
<li><code>GRAPHRAG_LOCAL_SEARCH_TOP_K_RELATIONSHIPS</code> - Control the number of out-of-network relationships to pull into the context window. Default: <code>10</code></li>
<li><code>GRAPHRAG_LOCAL_SEARCH_MAX_TOKENS</code> - Change this based on the token limit you have on your model (if you are using a model with 8k limit, a good setting could be 5000). Default: <code>12000</code></li>
<li><code>GRAPHRAG_LOCAL_SEARCH_LLM_MAX_TOKENS</code> - Change this based on the token limit you have on your model (if you are using a model with 8k limit, a good setting could be 1000=1500). Default: <code>2000</code></li>
<li><code>GRAPHRAG_GLOBAL_SEARCH_MAX_TOKENS</code> - Change this based on the token limit you have on your model (if you are using a model with 8k limit, a good setting could be 5000). Default: <code>12000</code></li>
<li><code>GRAPHRAG_GLOBAL_SEARCH_DATA_MAX_TOKENS</code> - Change this based on the token limit you have on your model (if you are using a model with 8k limit, a good setting could be 5000). Default: <code>12000</code></li>
<li><code>GRAPHRAG_GLOBAL_SEARCH_MAP_MAX_TOKENS</code> - Default: <code>500</code></li>
<li><code>GRAPHRAG_GLOBAL_SEARCH_REDUCE_MAX_TOKENS</code> - Change this based on the token limit you have on your model (if you are using a model with 8k limit, a good setting could be 1000-1500). Default: <code>2000</code></li>
<li><code>GRAPHRAG_GLOBAL_SEARCH_CONCURRENCY</code> - Default: <code>32</code></li>
</ul>
</main>
</div>
<footer>
<a href="https://go.microsoft.com/fwlink/?LinkId=521839">Privacy</a>
|
<a href="https://go.microsoft.com/fwlink/?LinkId=2259814">Consumer Health Privacy</a>
|
<span id="cookiesManager" onClick="manageConsent();">Cookies</span>
<span id="divider">|</span>
<a href="https://go.microsoft.com/fwlink/?LinkID=206977">Terms of Use</a>
|
<a href="https://www.microsoft.com/trademarks">Trademarks</a>
|
<a href="https://www.microsoft.com" id="copyright"></a>
|
<a href="https://github.com/microsoft/graphrag">GitHub</a>
</footer>
</body>
</html>
Reference in New Issue View Git Blame Copy Permalink