348 lines
11 KiB
HTML
Raw Blame History

This file contains invisible Unicode characters

This file contains invisible Unicode characters that are indistinguishable to humans but may be processed differently by a computer. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

<!doctype html>
<html lang="en">
<head>
<meta charset="utf-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>Prompt Tuning⚙</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/" class="is-active" aria-current="page">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/">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>Prompt Tuning⚙</h1>
<p>The GraphRAG indexer, by default, will run with a handful of prompts that are designed to work well in the broad context of knowledge discovery.
However, it is quite common to want to tune the prompts to better suit your specific use case.
We provide a means for you to do this by allowing you to specify a custom prompt file, which will each use a series of token-replacements internally.</p>
<p>Each of these prompts may be overridden by writing a custom prompt file in plaintext. We use token-replacements in the form of <code>{token_name}</code>, and the descriptions for the available tokens can be found below.</p>
<h2>Entity/Relationship Extraction</h2>
<p><a href="http://github.com/microsoft/graphrag/blob/main/graphrag/index/graph/extractors/graph/prompts.py">Prompt Source</a></p>
<h3>Tokens (values provided by extractor)</h3>
<ul>
<li><strong>{input_text}</strong> - The input text to be processed.</li>
<li><strong>{entity_types}</strong> - A list of entity types</li>
<li><strong>{tuple_delimiter}</strong> - A delimiter for separating values within a tuple. A single tuple is used to represent an individual entity or relationship.</li>
<li><strong>{record_delimiter}</strong> - A delimiter for separating tuple instances.</li>
<li><strong>{completion_delimiter}</strong> - An indicator for when generation is complete.</li>
</ul>
<h2>Summarize Entity/Relationship Descriptions</h2>
<p><a href="http://github.com/microsoft/graphrag/blob/main/graphrag/index/graph/extractors/summarize/prompts.py">Prompt Source</a></p>
<h3>Tokens (values provided by extractor)</h3>
<ul>
<li><strong>{entity_name}</strong> - The name of the entity or the source/target pair of the relationship.</li>
<li><strong>{description_list}</strong> - A list of descriptions for the entity or relationship.</li>
</ul>
<h2>Claim Extraction</h2>
<p><a href="http://github.com/microsoft/graphrag/blob/main/graphrag/index/graph/extractors/claims/prompts.py">Prompt Source</a></p>
<h3>Tokens (values provided by extractor)</h3>
<ul>
<li><strong>{input_text}</strong> - The input text to be processed.</li>
<li><strong>{tuple_delimiter}</strong> - A delimiter for separating values within a tuple. A single tuple is used to represent an individual entity or relationship.</li>
<li><strong>{record_delimiter}</strong> - A delimiter for separating tuple instances.</li>
<li><strong>{completion_delimiter}</strong> - An indicator for when generation is complete.</li>
</ul>
<p>Note: there is additional paramater for the <code>Claim Description</code> that is used in claim extraction.
The default value is</p>
<p><code>&quot;Any claims or facts that could be relevant to information discovery.&quot;</code></p>
<p>See the <a href="/posts/config/overview/">configuration documentation</a> for details on how to change this.</p>
<h2>Generate Community Reports</h2>
<p><a href="http://github.com/microsoft/graphrag/blob/main/graphrag/index/graph/extractors/community_reports/prompts.py">Prompt Source</a></p>
<h3>Tokens (values provided by extractor)</h3>
<ul>
<li><strong>{input_text}</strong> - The input text to generate the report with. This will contain tables of entities and relationships.</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>