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/config/json_yaml/index.html

494 lines
19 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>Default Configuration Mode (using JSON/YAML)</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/">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>Default Configuration Mode (using JSON/YAML)</h1>
<p>The default configuration mode may be configured by using a <code>config.json</code> or <code>config.yml</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.</p>
<p>For example:</p>
<pre><code># .env
API_KEY=some_api_key
# config.json
{
&quot;llm&quot;: {
&quot;api_key&quot;: &quot;${API_KEY}&quot;
}
}
</code></pre>
<h1>Config Sections</h1>
<h2>input</h2>
<h3>Fields</h3>
<ul>
<li><code>type</code> <strong>file|blob</strong> - The input type to use. Default=<code>file</code></li>
<li><code>file_type</code> <strong>text|csv</strong> - The type of input data to load. Either <code>text</code> or <code>csv</code>. Default is <code>csv</code></li>
<li><code>file_encoding</code> <strong>str</strong> - The encoding of the input file. Default is <code>utf-8</code></li>
<li><code>file_pattern</code> <strong>str</strong> - A regex to match input files. Default is <code>.*\.csv$</code> if in csv mode and <code>.*\.txt$</code> if in text mode.</li>
<li><code>source_column</code> <strong>str</strong> - (CSV Mode Only) The source column name.</li>
<li><code>timestamp_column</code> <strong>str</strong> - (CSV Mode Only) The timestamp column name.</li>
<li><code>timestamp_format</code> <strong>str</strong> - (CSV Mode Only) The source format.</li>
<li><code>text_column</code> <strong>str</strong> - (CSV Mode Only) The text column name.</li>
<li><code>title_column</code> <strong>str</strong> - (CSV Mode Only) The title column name.</li>
<li><code>document_attribute_columns</code> <strong>list[str]</strong> - (CSV Mode Only) The additional document attributes to include.</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>base_dir</code> <strong>str</strong> - The base directory to read input from, relative to the root.</li>
<li><code>storage_account_blob_url</code> <strong>str</strong> - The storage account blob URL to use.</li>
</ul>
<h2>llm</h2>
<p>This is the base LLM configuration section. Other steps may override this configuration with their own LLM configuration.</p>
<h3>Fields</h3>
<ul>
<li><code>api_key</code> <strong>str</strong> - The OpenAI API key to use.</li>
<li><code>type</code> <strong>openai_chat|azure_openai_chat|openai_embedding|azure_openai_embedding</strong> - The type of LLM to use.</li>
<li><code>model</code> <strong>str</strong> - The model name.</li>
<li><code>max_tokens</code> <strong>int</strong> - The maximum number of output tokens.</li>
<li><code>request_timeout</code> <strong>float</strong> - The per-request timeout.</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>organization</code> <strong>str</strong> - The client organization.</li>
<li><code>proxy</code> <strong>str</strong> - The proxy URL to use.</li>
<li><code>cognitive_services_endpoint</code> <strong>str</strong> - The url endpoint for cognitive services.</li>
<li><code>deployment_name</code> <strong>str</strong> - The deployment name to use (Azure).</li>
<li><code>model_supports_json</code> <strong>bool</strong> - Whether the model supports JSON-mode output.</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>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>sleep_on_rate_limit_recommendation</code> <strong>bool</strong> - Whether to adhere to sleep recommendations (Azure).</li>
<li><code>concurrent_requests</code> <strong>int</strong> The number of open requests to allow at once.</li>
</ul>
<h2>parallelization</h2>
<h3>Fields</h3>
<ul>
<li><code>stagger</code> <strong>float</strong> - The threading stagger value.</li>
<li><code>num_threads</code> <strong>int</strong> - The maximum number of work threads.</li>
</ul>
<h2>async_mode</h2>
<p><strong>asyncio|threaded</strong> The async mode to use. Either <code>asyncio</code> or `threaded.</p>
<h2>embeddings</h2>
<h3>Fields</h3>
<ul>
<li><code>llm</code> (see LLM top-level config)</li>
<li><code>parallelization</code> (see Parallelization top-level config)</li>
<li><code>async_mode</code> (see Async Mode top-level config)</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 #-tokens.</li>
<li><code>target</code> <strong>required|all</strong> - Determines which set of embeddings to emit.</li>
<li><code>skip</code> <strong>list[str]</strong> - Which embeddings to skip.</li>
<li><code>strategy</code> <strong>dict</strong> - Fully override the text-embedding strategy.</li>
</ul>
<h2>chunks</h2>
<h3>Fields</h3>
<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 fields before chunking.</li>
<li><code>strategy</code> <strong>dict</strong> - Fully override the chunking strategy.</li>
</ul>
<h2>cache</h2>
<h3>Fields</h3>
<ul>
<li><code>type</code> <strong>file|memory|none|blob</strong> - The cache type to use. Default=<code>file</code></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>base_dir</code> <strong>str</strong> - The base directory to write cache to, relative to the root.</li>
<li><code>storage_account_blob_url</code> <strong>str</strong> - The storage account blob URL to use.</li>
</ul>
<h2>storage</h2>
<h3>Fields</h3>
<ul>
<li><code>type</code> <strong>file|memory|blob</strong> - The storage type to use. Default=<code>file</code></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>base_dir</code> <strong>str</strong> - The base directory to write reports to, relative to the root.</li>
<li><code>storage_account_blob_url</code> <strong>str</strong> - The storage account blob URL to use.</li>
</ul>
<h2>reporting</h2>
<h3>Fields</h3>
<ul>
<li><code>type</code> <strong>file|console|blob</strong> - The reporting type to use. Default=<code>file</code></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>base_dir</code> <strong>str</strong> - The base directory to write reports to, relative to the root.</li>
<li><code>storage_account_blob_url</code> <strong>str</strong> - The storage account blob URL to use.</li>
</ul>
<h2>entity_extraction</h2>
<h3>Fields</h3>
<ul>
<li><code>llm</code> (see LLM top-level config)</li>
<li><code>parallelization</code> (see Parallelization top-level config)</li>
<li><code>async_mode</code> (see Async Mode top-level config)</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>
<li><code>strategy</code> <strong>dict</strong> - Fully override the entity extraction strategy.</li>
</ul>
<h2>summarize_descriptions</h2>
<h3>Fields</h3>
<ul>
<li><code>llm</code> (see LLM top-level config)</li>
<li><code>parallelization</code> (see Parallelization top-level config)</li>
<li><code>async_mode</code> (see Async Mode top-level config)</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>strategy</code> <strong>dict</strong> - Fully override the summarize description strategy.</li>
</ul>
<h2>claim_extraction</h2>
<h3>Fields</h3>
<ul>
<li><code>enabled</code> <strong>bool</strong> - Whether to enable claim extraction. default=False</li>
<li><code>llm</code> (see LLM top-level config)</li>
<li><code>parallelization</code> (see Parallelization top-level config)</li>
<li><code>async_mode</code> (see Async Mode top-level config)</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>
<li><code>strategy</code> <strong>dict</strong> - Fully override the claim extraction strategy.</li>
</ul>
<h2>community_reports</h2>
<h3>Fields</h3>
<ul>
<li><code>llm</code> (see LLM top-level config)</li>
<li><code>parallelization</code> (see Parallelization top-level config)</li>
<li><code>async_mode</code> (see Async Mode top-level config)</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>
<li><code>strategy</code> <strong>dict</strong> - Fully override the community reports strategy.</li>
</ul>
<h2>cluster_graph</h2>
<h3>Fields</h3>
<ul>
<li><code>max_cluster_size</code> <strong>int</strong> - The maximum cluster size to emit.</li>
<li><code>strategy</code> <strong>dict</strong> - Fully override the cluster_graph strategy.</li>
</ul>
<h2>embed_graph</h2>
<h3>Fields</h3>
<ul>
<li><code>enabled</code> <strong>bool</strong> - Whether to enable graph embeddings.</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>
<h2>umap</h2>
<h3>Fields</h3>
<ul>
<li><code>enabled</code> <strong>bool</strong> - Whether to enable UMAP layouts.</li>
</ul>
<h2>snapshots</h2>
<h3>Fields</h3>
<ul>
<li><code>graphml</code> <strong>bool</strong> - Emit graphml snapshots.</li>
<li><code>raw_entities</code> <strong>bool</strong> - Emit raw entity snapshots.</li>
<li><code>top_level_nodes</code> <strong>bool</strong> - Emit top-level-node snapshots.</li>
</ul>
<h2>encoding_model</h2>
<p><strong>str</strong> - The text encoding model to use. Default is <code>cl100k_base</code>.</p>
<h2>skip_workflows</h2>
<p><strong>list[str]</strong> - Which workflow names to skip.</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>
<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