mirror of
https://github.com/microsoft/graphrag.git
synced 2025-09-18 12:44:23 +00:00
542 lines
34 KiB
HTML
542 lines
34 KiB
HTML
|
||
|
||
|
||
|
||
<!doctype html>
|
||
<html lang="en">
|
||
<head>
|
||
<meta charset="utf-8">
|
||
<meta name="viewport" content="width=device-width, initial-scale=1.0">
|
||
<title>Global Search Notebook</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)
|
||
|
||
function manageConsent() {
|
||
if(siteConsent.isConsentRequired){
|
||
siteConsent.manageConsent();
|
||
}
|
||
}
|
||
</script>
|
||
|
||
</head>
|
||
<body>
|
||
<header>
|
||
<div id="cookie-banner"></div>
|
||
<a href="/graphrag/"><span class="logotitle">GraphRAG</span></a>
|
||
</header>
|
||
<div class="page-content">
|
||
<!-- Sidebar -->
|
||
<aside class="menu">
|
||
<ul class="menu-list">
|
||
<li>
|
||
|
||
<a href="/graphrag/">Welcome</a>
|
||
|
||
</li>
|
||
|
||
<!-- Get Started Links -->
|
||
<li>
|
||
|
||
<a href="/graphrag/posts/get_started/">Get Started</a>
|
||
|
||
|
||
<a href="/graphrag/posts/developing/">Developing</a>
|
||
|
||
</li>
|
||
|
||
<!-- Indexing Links -->
|
||
<li>
|
||
|
||
<a href="/graphrag/posts/index/overview/">Indexing</a>
|
||
|
||
<ul><li>
|
||
<a href="/graphrag/posts/index/0-architecture/">Architecture</a>
|
||
</li><li>
|
||
<a href="/graphrag/posts/index/1-default_dataflow/">Dataflow</a>
|
||
</li><li>
|
||
<a href="/graphrag/posts/index/2-cli/">CLI</a>
|
||
</li><li>
|
||
<a href="/graphrag/posts/index/3-prompt_tuning/">Prompt Tuning</a>
|
||
</li><li>
|
||
|
||
<a href="/graphrag/posts/index/workflows/overview/">Workflows</a>
|
||
|
||
<ul hidden=""><li>
|
||
<a href="/graphrag/posts/index/workflows/create_base_documents/">create_base_documents</a>
|
||
</li><li>
|
||
<a href="/graphrag/posts/index/workflows/create_base_entity_graph/">create_base_entity_graph</a>
|
||
</li><li>
|
||
<a href="/graphrag/posts/index/workflows/create_base_extracted_entities/">create_base_extracted_entities</a>
|
||
</li><li>
|
||
<a href="/graphrag/posts/index/workflows/create_base_text_units/">create_base_text_units</a>
|
||
</li><li>
|
||
<a href="/graphrag/posts/index/workflows/create_final_communities/">create_final_communities</a>
|
||
</li><li>
|
||
<a href="/graphrag/posts/index/workflows/create_final_community_reports/">create_final_community_reports</a>
|
||
</li><li>
|
||
<a href="/graphrag/posts/index/workflows/create_final_covariates/">create_final_covariates</a>
|
||
</li><li>
|
||
<a href="/graphrag/posts/index/workflows/create_final_documents/">create_final_documents</a>
|
||
</li><li>
|
||
<a href="/graphrag/posts/index/workflows/create_final_entities/">create_final_entities</a>
|
||
</li><li>
|
||
<a href="/graphrag/posts/index/workflows/create_final_nodes/">create_final_nodes</a>
|
||
</li><li>
|
||
<a href="/graphrag/posts/index/workflows/create_final_relationships/">create_final_relationships</a>
|
||
</li><li>
|
||
<a href="/graphrag/posts/index/workflows/create_final_text_units/">create_final_text_units</a>
|
||
</li><li>
|
||
<a href="/graphrag/posts/index/workflows/create_summarized_entities/">create_summarized_entities</a>
|
||
</li></ul>
|
||
</li>
|
||
|
||
<li>
|
||
|
||
<a href="/graphrag/posts/index/verbs/overview/">Verbs</a>
|
||
|
||
<ul hidden=""><li>
|
||
<a href="/graphrag/posts/index/verbs/aggregate/">aggregate</a>
|
||
</li><li>
|
||
<a href="/graphrag/posts/index/verbs/chunk/">chunk</a>
|
||
</li><li>
|
||
<a href="/graphrag/posts/index/verbs/cluster_graph/">cluster_graph</a>
|
||
</li><li>
|
||
<a href="/graphrag/posts/index/verbs/concat/">concat</a>
|
||
</li><li>
|
||
<a href="/graphrag/posts/index/verbs/create_graph/">create_graph</a>
|
||
</li><li>
|
||
<a href="/graphrag/posts/index/verbs/genid/">genid</a>
|
||
</li><li>
|
||
<a href="/graphrag/posts/index/verbs/layout_graph/">layout_graph</a>
|
||
</li><li>
|
||
<a href="/graphrag/posts/index/verbs/merge/">merge</a>
|
||
</li><li>
|
||
<a href="/graphrag/posts/index/verbs/merge_graphs/">merge_graphs</a>
|
||
</li><li>
|
||
<a href="/graphrag/posts/index/verbs/spread_json/">spread_json</a>
|
||
</li><li>
|
||
<a href="/graphrag/posts/index/verbs/text_replace/">text_replace</a>
|
||
</li><li>
|
||
<a href="/graphrag/posts/index/verbs/text_split/">text_split</a>
|
||
</li><li>
|
||
<a href="/graphrag/posts/index/verbs/unpack_graph/">unpack_graph</a>
|
||
</li><li>
|
||
<a href="/graphrag/posts/index/verbs/unzip/">unzip</a>
|
||
</li><li>
|
||
<a href="/graphrag/posts/index/verbs/zip/">zip</a>
|
||
</li></ul>
|
||
</li>
|
||
|
||
<li>
|
||
|
||
<a href="/graphrag/posts/config/overview/">Configuration</a>
|
||
|
||
<ul>
|
||
<li>
|
||
<a href="/graphrag/posts/config/env_vars">Using Env Vars</a>
|
||
</li>
|
||
<li>
|
||
<a href="/graphrag/posts/config/json_yaml">Using JSON or YAML</a>
|
||
</li>
|
||
<li>
|
||
<a href="/graphrag/posts/config/custom">Fully Custom</a>
|
||
</li>
|
||
</ul>
|
||
</li>
|
||
</ul>
|
||
</li>
|
||
|
||
|
||
<!-- Query Links -->
|
||
<li>
|
||
|
||
<a href="/graphrag/posts/query/overview/">Query</a>
|
||
|
||
<ul><li>
|
||
<a href="/graphrag/posts/query/0-global_search/">Global Search</a>
|
||
</li><li>
|
||
<a href="/graphrag/posts/query/1-local_search/">Local Search</a>
|
||
</li><li>
|
||
<a href="/graphrag/posts/query/2-question_generation/">Question Generation</a>
|
||
</li><li>
|
||
<a href="/graphrag/posts/query/3-cli/">CLI</a>
|
||
</li><li>
|
||
|
||
<a href="/graphrag/posts/query/notebooks/overview/">Notebooks</a>
|
||
|
||
<ul>
|
||
<li>
|
||
<a href="/graphrag/posts/query/notebooks/global_search_nb">Global Search</a>
|
||
</li>
|
||
<li>
|
||
<a href="/graphrag/posts/query/notebooks/local_search_nb">Local Search</a>
|
||
</li>
|
||
</ul>
|
||
</li>
|
||
</ul>
|
||
</li>
|
||
</ul>
|
||
</aside>
|
||
|
||
<!-- Main Content -->
|
||
<main>
|
||
<h1>Global Search Notebook</h1>
|
||
|
||
<div style="position: relative">
|
||
<pre class="language-python"><code id="code-0" class="language-python"><span class="token triple-quoted-string string">"""
|
||
Copyright (c) Microsoft Corporation. All rights reserved.
|
||
"""</span></code></pre>
|
||
|
||
<button class="code-copy " data-clipboard-target="#code-0" 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>
|
||
|
||
<div style="position: relative">
|
||
<pre class="language-python"><code id="code-1" class="language-python"><span class="token keyword">import</span> os
|
||
<span class="token keyword">import</span> pandas <span class="token keyword">as</span> pd
|
||
<span class="token keyword">import</span> tiktoken
|
||
<span class="token keyword">from</span> graphrag<span class="token punctuation">.</span>query<span class="token punctuation">.</span>llm<span class="token punctuation">.</span>oai<span class="token punctuation">.</span>chat_openai <span class="token keyword">import</span> ChatOpenAI
|
||
<span class="token keyword">from</span> graphrag<span class="token punctuation">.</span>query<span class="token punctuation">.</span>llm<span class="token punctuation">.</span>oai<span class="token punctuation">.</span>typing <span class="token keyword">import</span> OpenaiApiType
|
||
<span class="token keyword">from</span> graphrag<span class="token punctuation">.</span>query<span class="token punctuation">.</span><span class="token builtin">input</span><span class="token punctuation">.</span>loaders<span class="token punctuation">.</span>dfs <span class="token keyword">import</span> read_community_reports
|
||
<span class="token keyword">from</span> graphrag<span class="token punctuation">.</span>query<span class="token punctuation">.</span>structured_search<span class="token punctuation">.</span>global_search<span class="token punctuation">.</span>search <span class="token keyword">import</span> GlobalSearch
|
||
<span class="token keyword">from</span> graphrag<span class="token punctuation">.</span>query<span class="token punctuation">.</span>structured_search<span class="token punctuation">.</span>global_search<span class="token punctuation">.</span>community_context <span class="token keyword">import</span> GlobalCommunityContext
|
||
|
||
<span class="token keyword">print</span><span class="token punctuation">(</span>os<span class="token punctuation">.</span>getcwd<span class="token punctuation">(</span><span class="token punctuation">)</span><span class="token punctuation">)</span></code></pre>
|
||
|
||
<button class="code-copy " data-clipboard-target="#code-1" 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>Global Search example</h2>
|
||
<p>Global search method generates answers by searching over all AI-generated community reports in a map-reduce fashion. This is a resource-intensive method, but often gives good responses for questions that require an understanding of the dataset as a whole (e.g. What are the most significant values of the herbs mentioned in this notebook?).</p>
|
||
<h3>LLM setup</h3>
|
||
|
||
<div style="position: relative">
|
||
<pre class="language-python"><code id="code-11" class="language-python">
|
||
api_key <span class="token operator">=</span> <span class="token string">"<api_key>"</span>
|
||
api_version <span class="token operator">=</span> <span class="token string">"api_version"</span>
|
||
llm_model <span class="token operator">=</span> <span class="token string">"model or deployment id"</span>
|
||
|
||
llm <span class="token operator">=</span> ChatOpenAI<span class="token punctuation">(</span>
|
||
api_key<span class="token operator">=</span>api_key<span class="token punctuation">,</span>
|
||
model<span class="token operator">=</span>llm_model<span class="token punctuation">,</span>
|
||
api_type<span class="token operator">=</span>OpenaiApiType<span class="token punctuation">.</span>OpenAI<span class="token punctuation">,</span> <span class="token comment"># OpenaiApiType.OpenAI or OpenaiApiType.AzureOpenAI</span>
|
||
api_version<span class="token operator">=</span>api_version<span class="token punctuation">,</span>
|
||
max_retries<span class="token operator">=</span><span class="token number">20</span>
|
||
<span class="token punctuation">)</span>
|
||
|
||
token_encoder <span class="token operator">=</span> tiktoken<span class="token punctuation">.</span>get_encoding<span class="token punctuation">(</span><span class="token string">"cl100k_base"</span><span class="token punctuation">)</span></code></pre>
|
||
|
||
<button class="code-copy " data-clipboard-target="#code-11" 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>
|
||
<h3>Load community reports as context for global search</h3>
|
||
<ul>
|
||
<li>Load all community reports from <strong>create_final_community_reports</strong> table from the ire-indexing engine.</li>
|
||
</ul>
|
||
|
||
<div style="position: relative">
|
||
<pre class="language-python"><code id="code-22" class="language-python"><span class="token comment"># parquet files generated from indexing pipeline</span>
|
||
INPUT_DIR <span class="token operator">=</span> <span class="token string">"./data"</span>
|
||
COMMUNITY_REPORT_TABLE <span class="token operator">=</span> <span class="token string">"create_final_community_reports"</span>
|
||
ENTITY_TABLE <span class="token operator">=</span> <span class="token string">"create_final_nodes"</span>
|
||
|
||
<span class="token comment"># community level in the Leiden community hierarchy from which we will load the community reports</span>
|
||
<span class="token comment"># higher value means we use reports on smaller communities (and thus will have more reports to query aga</span>
|
||
COMMUNITY_LEVEL <span class="token operator">=</span> <span class="token number">2</span>
|
||
</code></pre>
|
||
|
||
<button class="code-copy " data-clipboard-target="#code-22" 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>
|
||
|
||
<div style="position: relative">
|
||
<pre class="language-python"><code id="code-23" class="language-python">
|
||
entity_df <span class="token operator">=</span> pd<span class="token punctuation">.</span>read_parquet<span class="token punctuation">(</span><span class="token string-interpolation"><span class="token string">f"</span><span class="token interpolation"><span class="token punctuation">{</span>INPUT_DIR<span class="token punctuation">}</span></span><span class="token string">/</span><span class="token interpolation"><span class="token punctuation">{</span>ENTITY_TABLE<span class="token punctuation">}</span></span><span class="token string">.parquet"</span></span><span class="token punctuation">)</span>
|
||
entity_df <span class="token operator">=</span> entity_df<span class="token punctuation">[</span><span class="token punctuation">(</span>entity_df<span class="token punctuation">.</span><span class="token builtin">type</span><span class="token operator">==</span><span class="token string">"entity"</span><span class="token punctuation">)</span> <span class="token operator">&</span> <span class="token punctuation">(</span>entity_df<span class="token punctuation">.</span>level<span class="token operator"><=</span><span class="token string">"level_{COMMUNITY_LEVEL}"</span><span class="token punctuation">)</span><span class="token punctuation">]</span>
|
||
entity_df<span class="token punctuation">[</span><span class="token string">"community"</span><span class="token punctuation">]</span> <span class="token operator">=</span> entity_df<span class="token punctuation">[</span><span class="token string">"community"</span><span class="token punctuation">]</span><span class="token punctuation">.</span>fillna<span class="token punctuation">(</span><span class="token operator">-</span><span class="token number">1</span><span class="token punctuation">)</span>
|
||
entity_df<span class="token punctuation">[</span><span class="token string">"community"</span><span class="token punctuation">]</span> <span class="token operator">=</span> entity_df<span class="token punctuation">[</span><span class="token string">"community"</span><span class="token punctuation">]</span><span class="token punctuation">.</span>astype<span class="token punctuation">(</span><span class="token builtin">int</span><span class="token punctuation">)</span>
|
||
|
||
entity_df <span class="token operator">=</span> entity_df<span class="token punctuation">.</span>groupby<span class="token punctuation">(</span><span class="token punctuation">[</span><span class="token string">"title"</span><span class="token punctuation">]</span><span class="token punctuation">)</span><span class="token punctuation">.</span>agg<span class="token punctuation">(</span><span class="token punctuation">{</span><span class="token string">"community"</span><span class="token punctuation">:</span> <span class="token string">"max"</span><span class="token punctuation">}</span><span class="token punctuation">)</span><span class="token punctuation">.</span>resetindex<span class="token punctuation">(</span><span class="token punctuation">)</span>
|
||
entity_df<span class="token punctuation">[</span><span class="token string">"community"</span><span class="token punctuation">]</span> <span class="token operator">=</span> entity_df<span class="token punctuation">[</span><span class="token string">"community"</span><span class="token punctuation">]</span><span class="token punctuation">.</span>astype<span class="token punctuation">(</span><span class="token builtin">str</span><span class="token punctuation">)</span>
|
||
filtered_community_df <span class="token operator">=</span> entity_df<span class="token punctuation">.</span>rename<span class="token punctuation">(</span>columns<span class="token operator">=</span><span class="token punctuation">{</span><span class="token string">"community"</span><span class="token punctuation">:</span> <span class="token string">"community_id"</span><span class="token punctuation">}</span><span class="token punctuation">)</span><span class="token punctuation">[</span><span class="token string">"community_id"</span><span class="token punctuation">]</span><span class="token punctuation">.</span>drop_duplicates<span class="token punctuation">(</span><span class="token punctuation">)</span>
|
||
|
||
report_df <span class="token operator">=</span> pd<span class="token punctuation">.</span>read_parquet<span class="token punctuation">(</span><span class="token string-interpolation"><span class="token string">f"</span><span class="token interpolation"><span class="token punctuation">{</span>INPUT_DIR<span class="token punctuation">}</span></span><span class="token string">/</span><span class="token interpolation"><span class="token punctuation">{</span>COMMUNITY_REPORT_TABLE<span class="token punctuation">}</span></span><span class="token string">.parquet"</span></span><span class="token punctuation">)</span>
|
||
report_df <span class="token operator">=</span> report_df<span class="token punctuation">[</span>report_df<span class="token punctuation">.</span>level <span class="token operator"><=</span> <span class="token string-interpolation"><span class="token string">f"level_</span><span class="token interpolation"><span class="token punctuation">{</span>COMMUNITY_LEVEL<span class="token punctuation">}</span></span><span class="token string">"</span></span><span class="token punctuation">]</span>
|
||
|
||
report_df<span class="token punctuation">[</span><span class="token string">"rank"</span><span class="token punctuation">]</span> <span class="token operator">=</span> report_df<span class="token punctuation">[</span><span class="token string">"rank"</span><span class="token punctuation">]</span><span class="token punctuation">.</span>astype<span class="token punctuation">(</span><span class="token builtin">int</span><span class="token punctuation">)</span>
|
||
|
||
report_df <span class="token operator">=</span> report_df<span class="token punctuation">.</span>merge<span class="token punctuation">(</span>filtered_community_df<span class="token punctuation">,</span> on<span class="token operator">=</span><span class="token string">"community_id"</span><span class="token punctuation">,</span> how<span class="token operator">=</span><span class="token string">"inner"</span><span class="token punctuation">)</span>
|
||
|
||
reports <span class="token operator">=</span> read_community_reports<span class="token punctuation">(</span>
|
||
df<span class="token operator">=</span>report_df<span class="token punctuation">,</span>
|
||
id_col<span class="token operator">=</span><span class="token string">"community_id"</span><span class="token punctuation">,</span>
|
||
short_id_col<span class="token operator">=</span><span class="token string">"community_id"</span><span class="token punctuation">,</span>
|
||
community_col<span class="token operator">=</span><span class="token string">"community_id"</span><span class="token punctuation">,</span>
|
||
title_col<span class="token operator">=</span><span class="token string">"title"</span><span class="token punctuation">,</span>
|
||
summary_col<span class="token operator">=</span><span class="token string">"summary"</span><span class="token punctuation">,</span>
|
||
content_col<span class="token operator">=</span><span class="token string">"full_content"</span><span class="token punctuation">,</span>
|
||
rank_col<span class="token operator">=</span><span class="token string">"rank"</span><span class="token punctuation">,</span>
|
||
summary_embedding_col<span class="token operator">=</span><span class="token boolean">None</span><span class="token punctuation">,</span>
|
||
content_embedding_col<span class="token operator">=</span><span class="token boolean">None</span><span class="token punctuation">,</span>
|
||
<span class="token punctuation">)</span>
|
||
|
||
<span class="token keyword">print</span><span class="token punctuation">(</span><span class="token string-interpolation"><span class="token string">f'Report records: </span><span class="token interpolation"><span class="token punctuation">{</span><span class="token builtin">len</span><span class="token punctuation">(</span>report_df<span class="token punctuation">)</span><span class="token punctuation">}</span></span><span class="token string">'</span></span><span class="token punctuation">)</span>
|
||
report_df<span class="token punctuation">.</span>head<span class="token punctuation">(</span><span class="token punctuation">)</span></code></pre>
|
||
|
||
<button class="code-copy " data-clipboard-target="#code-23" 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>
|
||
<h4>Build global context based on community reports</h4>
|
||
|
||
<div style="position: relative">
|
||
<pre class="language-python"><code id="code-27" class="language-python">context_builder <span class="token operator">=</span> GlobalCommunityContext<span class="token punctuation">(</span>
|
||
community_reports<span class="token operator">=</span>reports<span class="token punctuation">,</span>
|
||
token_encoder<span class="token operator">=</span>token_encoder
|
||
<span class="token punctuation">)</span></code></pre>
|
||
|
||
<button class="code-copy " data-clipboard-target="#code-27" 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>
|
||
<h4>Perform global search</h4>
|
||
|
||
<div style="position: relative">
|
||
<pre class="language-python"><code id="code-31" class="language-python">context_builder_params <span class="token operator">=</span> <span class="token punctuation">{</span>
|
||
<span class="token string">"use_community_summary"</span><span class="token punctuation">:</span> <span class="token boolean">False</span><span class="token punctuation">,</span> <span class="token comment"># False means using full community reports. True means using community short summaries.</span>
|
||
<span class="token string">"shuffle_data"</span><span class="token punctuation">:</span> <span class="token boolean">True</span><span class="token punctuation">,</span>
|
||
<span class="token string">"include_community_rank"</span><span class="token punctuation">:</span> <span class="token boolean">True</span><span class="token punctuation">,</span>
|
||
<span class="token string">"min_community_rank"</span><span class="token punctuation">:</span> <span class="token number">0</span><span class="token punctuation">,</span>
|
||
<span class="token string">"max_tokens"</span><span class="token punctuation">:</span> <span class="token number">16000</span><span class="token punctuation">,</span> <span class="token comment"># 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)</span>
|
||
<span class="token string">"context_name"</span><span class="token punctuation">:</span> <span class="token string">"Reports"</span><span class="token punctuation">,</span>
|
||
<span class="token punctuation">}</span>
|
||
|
||
map_llm_params <span class="token operator">=</span> <span class="token punctuation">{</span>
|
||
<span class="token string">"max_tokens"</span><span class="token punctuation">:</span> <span class="token number">500</span><span class="token punctuation">,</span>
|
||
<span class="token string">"temperature"</span><span class="token punctuation">:</span> <span class="token number">0.0</span><span class="token punctuation">,</span>
|
||
<span class="token punctuation">}</span>
|
||
|
||
reduce_llm_params <span class="token operator">=</span> <span class="token punctuation">{</span>
|
||
<span class="token string">"max_tokens"</span><span class="token punctuation">:</span> <span class="token number">2000</span><span class="token punctuation">,</span> <span class="token comment"># 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)</span>
|
||
<span class="token string">"temperature"</span><span class="token punctuation">:</span> <span class="token number">0.0</span><span class="token punctuation">,</span>
|
||
<span class="token punctuation">}</span></code></pre>
|
||
|
||
<button class="code-copy " data-clipboard-target="#code-31" 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>
|
||
|
||
<div style="position: relative">
|
||
<pre class="language-python"><code id="code-32" class="language-python">search_engine <span class="token operator">=</span> GlobalSearch<span class="token punctuation">(</span>
|
||
llm<span class="token operator">=</span>llm<span class="token punctuation">,</span>
|
||
context_builder<span class="token operator">=</span>context_builder<span class="token punctuation">,</span>
|
||
token_encoder<span class="token operator">=</span>token_encoder<span class="token punctuation">,</span>
|
||
max_data_tokens <span class="token operator">=</span> <span class="token number">16000</span><span class="token punctuation">,</span> <span class="token comment"># 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)</span>
|
||
map_llm_params<span class="token operator">=</span>map_llm_params<span class="token punctuation">,</span>
|
||
reduce_llm_params<span class="token operator">=</span>reduce_llm_params<span class="token punctuation">,</span>
|
||
context_builder_params<span class="token operator">=</span>context_builder_params<span class="token punctuation">,</span>
|
||
concurrent_coroutines<span class="token operator">=</span><span class="token number">32</span><span class="token punctuation">,</span>
|
||
response_type<span class="token operator">=</span><span class="token string">"multiple paragraphs"</span> <span class="token comment"># free form text describing the response type and format, can be anything, e.g. prioritized list, single paragraph, multiple paragraphs, multiple-page report</span>
|
||
<span class="token punctuation">)</span></code></pre>
|
||
|
||
<button class="code-copy " data-clipboard-target="#code-32" 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>
|
||
|
||
<div style="position: relative">
|
||
<pre class="language-python"><code id="code-33" class="language-python">result <span class="token operator">=</span> <span class="token keyword">await</span> search_engine<span class="token punctuation">.</span>asearch<span class="token punctuation">(</span><span class="token string">'How reliable are medicinal herbs?'</span><span class="token punctuation">)</span>
|
||
|
||
<span class="token keyword">print</span><span class="token punctuation">(</span>result<span class="token punctuation">.</span>response<span class="token punctuation">)</span></code></pre>
|
||
|
||
<button class="code-copy " data-clipboard-target="#code-33" 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>
|
||
|
||
<div style="position: relative">
|
||
<pre class="language-python"><code id="code-34" class="language-python"><span class="token comment"># inspect the data used to build the context for the LLM responses</span>
|
||
result<span class="token punctuation">.</span>context_data<span class="token punctuation">[</span><span class="token string">"reports"</span><span class="token punctuation">]</span></code></pre>
|
||
|
||
<button class="code-copy " data-clipboard-target="#code-34" 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>
|
||
|
||
<div style="position: relative">
|
||
<pre class="language-python"><code id="code-35" class="language-python"><span class="token comment"># inspect number of LLM calls and tokens</span>
|
||
<span class="token keyword">print</span><span class="token punctuation">(</span><span class="token string-interpolation"><span class="token string">f'LLM calls: </span><span class="token interpolation"><span class="token punctuation">{</span>result<span class="token punctuation">.</span>llm_calls<span class="token punctuation">}</span></span><span class="token string">. LLM tokens: </span><span class="token interpolation"><span class="token punctuation">{</span>result<span class="token punctuation">.</span>prompt_tokens<span class="token punctuation">}</span></span><span class="token string">'</span></span><span class="token punctuation">)</span></code></pre>
|
||
|
||
<button class="code-copy " data-clipboard-target="#code-35" 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>
|
||
<p>LLM calls: 13. LLM tokens: 184660</p>
|
||
|
||
</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>
|
||
|
|
||
<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> |