plano/llms/llms.html

655 lines
22 KiB
HTML
Raw Normal View History

<!DOCTYPE html>
<html lang="en" data-content_root="../" >
<head>
<meta charset="utf-8" />
<meta name="viewport" content="width=device-width, initial-scale=1.0" /><meta name="viewport" content="width=device-width, initial-scale=1" />
<title>LLMs &#8212; Arch 0.1-beta documentation</title>
<script data-cfasync="false">
document.documentElement.dataset.mode = localStorage.getItem("mode") || "";
document.documentElement.dataset.theme = localStorage.getItem("theme") || "";
</script>
<!-- Loaded before other Sphinx assets -->
<link href="../_static/styles/theme.css?digest=dfe6caa3a7d634c4db9b" rel="stylesheet" />
<link href="../_static/styles/bootstrap.css?digest=dfe6caa3a7d634c4db9b" rel="stylesheet" />
<link href="../_static/styles/pydata-sphinx-theme.css?digest=dfe6caa3a7d634c4db9b" rel="stylesheet" />
<link href="../_static/vendor/fontawesome/6.5.2/css/all.min.css?digest=dfe6caa3a7d634c4db9b" rel="stylesheet" />
<link rel="preload" as="font" type="font/woff2" crossorigin href="../_static/vendor/fontawesome/6.5.2/webfonts/fa-solid-900.woff2" />
<link rel="preload" as="font" type="font/woff2" crossorigin href="../_static/vendor/fontawesome/6.5.2/webfonts/fa-brands-400.woff2" />
<link rel="preload" as="font" type="font/woff2" crossorigin href="../_static/vendor/fontawesome/6.5.2/webfonts/fa-regular-400.woff2" />
<link rel="stylesheet" type="text/css" href="../_static/pygments.css?v=a746c00c" />
<link rel="stylesheet" type="text/css" href="../_static/styles/sphinx-book-theme.css?v=a3416100" />
<link rel="stylesheet" type="text/css" href="../_static/copybutton.css?v=76b2166b" />
<!-- Pre-loaded scripts that we'll load fully later -->
<link rel="preload" as="script" href="../_static/scripts/bootstrap.js?digest=dfe6caa3a7d634c4db9b" />
<link rel="preload" as="script" href="../_static/scripts/pydata-sphinx-theme.js?digest=dfe6caa3a7d634c4db9b" />
<script src="../_static/vendor/fontawesome/6.5.2/js/all.min.js?digest=dfe6caa3a7d634c4db9b"></script>
<script src="../_static/documentation_options.js?v=2742c0eb"></script>
<script src="../_static/doctools.js?v=9a2dae69"></script>
<script src="../_static/sphinx_highlight.js?v=dc90522c"></script>
<script src="../_static/clipboard.min.js?v=a7894cd8"></script>
<script src="../_static/copybutton.js?v=f281be69"></script>
<script src="../_static/scripts/sphinx-book-theme.js?v=887ef09a"></script>
<script>DOCUMENTATION_OPTIONS.pagename = 'llms/llms';</script>
<link rel="icon" href="../_static/favicon.ico"/>
<link rel="index" title="Index" href="../genindex.html" />
<link rel="search" title="Search" href="../search.html" />
<link rel="next" title="Configuration Reference" href="../configuration_reference.html" />
<link rel="prev" title="Access Logging" href="../observability/access_logs.html" />
<meta name="viewport" content="width=device-width, initial-scale=1"/>
<meta name="docsearch:language" content="en"/>
</head>
<body data-bs-spy="scroll" data-bs-target=".bd-toc-nav" data-offset="180" data-bs-root-margin="0px 0px -60%" data-default-mode="">
<div id="pst-skip-link" class="skip-link d-print-none"><a href="#main-content">Skip to main content</a></div>
<div id="pst-scroll-pixel-helper"></div>
<button type="button" class="btn rounded-pill" id="pst-back-to-top">
<i class="fa-solid fa-arrow-up"></i>Back to top</button>
<input type="checkbox"
class="sidebar-toggle"
id="pst-primary-sidebar-checkbox"/>
<label class="overlay overlay-primary" for="pst-primary-sidebar-checkbox"></label>
<input type="checkbox"
class="sidebar-toggle"
id="pst-secondary-sidebar-checkbox"/>
<label class="overlay overlay-secondary" for="pst-secondary-sidebar-checkbox"></label>
<div class="search-button__wrapper">
<div class="search-button__overlay"></div>
<div class="search-button__search-container">
<form class="bd-search d-flex align-items-center"
action="../search.html"
method="get">
<i class="fa-solid fa-magnifying-glass"></i>
<input type="search"
class="form-control"
name="q"
id="search-input"
placeholder="Search..."
aria-label="Search..."
autocomplete="off"
autocorrect="off"
autocapitalize="off"
spellcheck="false"/>
<span class="search-button__kbd-shortcut"><kbd class="kbd-shortcut__modifier">Ctrl</kbd>+<kbd>K</kbd></span>
</form></div>
</div>
<div class="pst-async-banner-revealer d-none">
<aside id="bd-header-version-warning" class="d-none d-print-none" aria-label="Version warning"></aside>
</div>
<header class="bd-header navbar navbar-expand-lg bd-navbar d-print-none">
</header>
<div class="bd-container">
<div class="bd-container__inner bd-page-width">
<div class="bd-sidebar-primary bd-sidebar">
<div class="sidebar-header-items sidebar-primary__section">
</div>
<div class="sidebar-primary-items__start sidebar-primary__section">
<div class="sidebar-primary-item">
<a class="navbar-brand logo" href="../root.html">
<img src="../_static/arch-nav-logo.png" class="logo__image only-light" alt="Arch 0.1-beta documentation - Home"/>
<script>document.write(`<img src="../_static/arch-nav-logo.png" class="logo__image only-dark" alt="Arch 0.1-beta documentation - Home"/>`);</script>
</a></div>
<div class="sidebar-primary-item">
<script>
document.write(`
<button class="btn search-button-field search-button__button" title="Search" aria-label="Search" data-bs-placement="bottom" data-bs-toggle="tooltip">
<i class="fa-solid fa-magnifying-glass"></i>
<span class="search-button__default-text">Search</span>
<span class="search-button__kbd-shortcut"><kbd class="kbd-shortcut__modifier">Ctrl</kbd>+<kbd class="kbd-shortcut__modifier">K</kbd></span>
</button>
`);
</script></div>
<div class="sidebar-primary-item"><nav class="bd-links bd-docs-nav" aria-label="Main">
<div class="bd-toc-item navbar-nav active">
<ul class="current nav bd-sidenav">
<li class="toctree-l1 has-children"><a class="reference internal" href="../intro/intro.html">Introduction</a><details><summary><span class="toctree-toggle" role="presentation"><i class="fa-solid fa-chevron-down"></i></span></summary><ul>
<li class="toctree-l2"><a class="reference internal" href="../intro/what_is_arch.html">What is Arch</a></li>
<li class="toctree-l2 has-children"><a class="reference internal" href="../intro/architecture/architecture.html">Technical Architecture</a><details><summary><span class="toctree-toggle" role="presentation"><i class="fa-solid fa-chevron-down"></i></span></summary><ul>
<li class="toctree-l3"><a class="reference internal" href="../intro/architecture/intro/terminology.html">Terminology</a></li>
<li class="toctree-l3"><a class="reference internal" href="../intro/architecture/intro/threading_model.html">Threading model</a></li>
<li class="toctree-l3"><a class="reference internal" href="../intro/architecture/listeners/listeners.html">Listener</a></li>
<li class="toctree-l3"><a class="reference internal" href="../intro/architecture/prompt_processing/prompt_processing.html">Prompts</a></li>
<li class="toctree-l3"><a class="reference internal" href="../intro/architecture/listeners/llm_provider.html">LLM Provider</a></li>
<li class="toctree-l3"><a class="reference internal" href="../intro/architecture/model_serving/model_serving.html">Model Serving</a></li>
</ul>
</details></li>
<li class="toctree-l2"><a class="reference internal" href="../intro/life_of_a_request.html">Life of a Request</a></li>
<li class="toctree-l2"><a class="reference internal" href="../intro/getting_help.html">Getting help</a></li>
</ul>
</details></li>
<li class="toctree-l1"><a class="reference internal" href="../getting_started/getting_started.html">Getting Started</a></li>
<li class="toctree-l1"><a class="reference internal" href="../getting_started/use_cases/rag.html">Retrieval-Augmented (RAG)</a></li>
<li class="toctree-l1"><a class="reference internal" href="../getting_started/use_cases/function_calling.html">Agentic (Text-to-Action) Apps</a></li>
<li class="toctree-l1 has-children"><a class="reference internal" href="../observability/observability.html">Observability</a><details><summary><span class="toctree-toggle" role="presentation"><i class="fa-solid fa-chevron-down"></i></span></summary><ul>
<li class="toctree-l2"><a class="reference internal" href="../observability/tracing.html">Tracing</a></li>
<li class="toctree-l2"><a class="reference internal" href="../observability/stats.html">Monitoring</a></li>
<li class="toctree-l2"><a class="reference internal" href="../observability/access_logs.html">Access Logging</a></li>
</ul>
</details></li>
<li class="toctree-l1 current active"><a class="current reference internal" href="#">LLMs</a></li>
<li class="toctree-l1"><a class="reference internal" href="../configuration_reference.html">Configuration Reference</a></li>
</ul>
</div>
</nav></div>
</div>
<div class="sidebar-primary-items__end sidebar-primary__section">
</div>
<div id="rtd-footer-container"></div>
</div>
<main id="main-content" class="bd-main" role="main">
<div class="sbt-scroll-pixel-helper"></div>
<div class="bd-content">
<div class="bd-article-container">
<div class="bd-header-article d-print-none">
<div class="header-article-items header-article__inner">
<div class="header-article-items__start">
<div class="header-article-item"><button class="sidebar-toggle primary-toggle btn btn-sm" title="Toggle primary sidebar" data-bs-placement="bottom" data-bs-toggle="tooltip">
<span class="fa-solid fa-bars"></span>
</button></div>
</div>
<div class="header-article-items__end">
<div class="header-article-item">
<div class="article-header-buttons">
<div class="dropdown dropdown-download-buttons">
<button class="btn dropdown-toggle" type="button" data-bs-toggle="dropdown" aria-expanded="false" aria-label="Download this page">
<i class="fas fa-download"></i>
</button>
<ul class="dropdown-menu">
<li><a href="../_sources/llms/llms.rst" target="_blank"
class="btn btn-sm btn-download-source-button dropdown-item"
title="Download source file"
data-bs-placement="left" data-bs-toggle="tooltip"
>
<span class="btn__icon-container">
<i class="fas fa-file"></i>
</span>
<span class="btn__text-container">.rst</span>
</a>
</li>
<li>
<button onclick="window.print()"
class="btn btn-sm btn-download-pdf-button dropdown-item"
title="Print to PDF"
data-bs-placement="left" data-bs-toggle="tooltip"
>
<span class="btn__icon-container">
<i class="fas fa-file-pdf"></i>
</span>
<span class="btn__text-container">.pdf</span>
</button>
</li>
</ul>
</div>
<button onclick="toggleFullScreen()"
class="btn btn-sm btn-fullscreen-button"
title="Fullscreen mode"
data-bs-placement="bottom" data-bs-toggle="tooltip"
>
<span class="btn__icon-container">
<i class="fas fa-expand"></i>
</span>
</button>
<script>
document.write(`
<button class="btn btn-sm nav-link pst-navbar-icon theme-switch-button" title="light/dark" aria-label="light/dark" data-bs-placement="bottom" data-bs-toggle="tooltip">
<i class="theme-switch fa-solid fa-sun fa-lg" data-mode="light"></i>
<i class="theme-switch fa-solid fa-moon fa-lg" data-mode="dark"></i>
<i class="theme-switch fa-solid fa-circle-half-stroke fa-lg" data-mode="auto"></i>
</button>
`);
</script>
<script>
document.write(`
<button class="btn btn-sm pst-navbar-icon search-button search-button__button" title="Search" aria-label="Search" data-bs-placement="bottom" data-bs-toggle="tooltip">
<i class="fa-solid fa-magnifying-glass fa-lg"></i>
</button>
`);
</script>
<button class="sidebar-toggle secondary-toggle btn btn-sm" title="Toggle secondary sidebar" data-bs-placement="bottom" data-bs-toggle="tooltip">
<span class="fa-solid fa-list"></span>
</button>
</div></div>
</div>
</div>
</div>
<div id="jb-print-docs-body" class="onlyprint">
<h1>LLMs</h1>
<!-- Table of contents -->
<div id="print-main-content">
<div id="jb-print-toc">
<div>
<h2> Contents </h2>
</div>
<nav aria-label="Page">
<ul class="visible nav section-nav flex-column">
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#arch-guard-v1">Arch-Guard-v1</a></li>
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#arch-fc">Arch-FC</a></li>
</ul>
</nav>
</div>
</div>
</div>
<div id="searchbox"></div>
<article class="bd-article">
<section id="llms">
<span id="llms-in-arch"></span><h1>LLMs<a class="headerlink" href="#llms" title="Link to this heading">#</a></h1>
<p>Arch utilizes purpose-built, industry leading, LLMs to handle the crufty and undifferentiated work around
accepting, handling and processing prompts. The following sections talk about some of the core models that
are built-in Arch.</p>
<section id="arch-guard-v1">
<h2>Arch-Guard-v1<a class="headerlink" href="#arch-guard-v1" title="Link to this heading">#</a></h2>
<p>LLM-powered applications are susceptible to prompt attacks, which are prompts intentionally designed to
subvert the developers intended behavior of the LLM. Arch-Guard-v1 is a classifier model trained on a large
corpus of attacks, capable of detecting explicitly malicious prompts (and toxicity).</p>
<p>The model is useful as a starting point for identifying and guardrailing against the most risky realistic
inputs to LLM-powered applications. Our goal in embedding Arch-Guard in the Arch gateway is to enable developers
to focus on their business logic and factor out security and safety outside application logic. Wth Arch-Guard-v1
developers can take to significantly reduce prompt attack risk while maintaining control over the user experience.</p>
<p>Below is our test results of the strength of our model as compared to Prompt-Guard from <a class="reference external" href="https://huggingface.co/meta-llama/Prompt-Guard-86M">Meta LLama</a>.</p>
<div class="pst-scrollable-table-container"><table class="table">
<colgroup>
<col style="width: 21.4%" />
<col style="width: 21.4%" />
<col style="width: 14.3%" />
<col style="width: 21.4%" />
<col style="width: 21.4%" />
</colgroup>
<thead>
<tr class="row-odd"><th class="head"><p>Dataset</p></th>
<th class="head"><p>Jailbreak (Yes/No)</p></th>
<th class="head"><p>Samples</p></th>
<th class="head"><p>Prompt-Guard Accuracy</p></th>
<th class="head"><p>Arch-Guard Accuracy</p></th>
</tr>
</thead>
<tbody>
<tr class="row-even"><td><p>casual_conversation</p></td>
<td><p>0</p></td>
<td><p>3725</p></td>
<td><p>1.00</p></td>
<td><p>1.00</p></td>
</tr>
<tr class="row-odd"><td><p>commonqa</p></td>
<td><p>0</p></td>
<td><p>9741</p></td>
<td><p>1.00</p></td>
<td><p>1.00</p></td>
</tr>
<tr class="row-even"><td><p>financeqa</p></td>
<td><p>0</p></td>
<td><p>1585</p></td>
<td><p>1.00</p></td>
<td><p>1.00</p></td>
</tr>
<tr class="row-odd"><td><p>instruction</p></td>
<td><p>0</p></td>
<td><p>5000</p></td>
<td><p>1.00</p></td>
<td><p>1.00</p></td>
</tr>
<tr class="row-even"><td><p>jailbreak_behavior_benign</p></td>
<td><p>0</p></td>
<td><p>100</p></td>
<td><p>0.10</p></td>
<td><p>0.20</p></td>
</tr>
<tr class="row-odd"><td><p>jailbreak_behavior_harmful</p></td>
<td><p>1</p></td>
<td><p>100</p></td>
<td><p>0.30</p></td>
<td><p>0.52</p></td>
</tr>
<tr class="row-even"><td><p>jailbreak_judge</p></td>
<td><p>1</p></td>
<td><p>300</p></td>
<td><p>0.33</p></td>
<td><p>0.49</p></td>
</tr>
<tr class="row-odd"><td><p>jailbreak_prompts</p></td>
<td><p>1</p></td>
<td><p>79</p></td>
<td><p>0.99</p></td>
<td><p>1.00</p></td>
</tr>
<tr class="row-even"><td><p>jailbreak_tweet</p></td>
<td><p>1</p></td>
<td><p>1282</p></td>
<td><p>0.16</p></td>
<td><p>0.35</p></td>
</tr>
<tr class="row-odd"><td><p>jailbreak_v</p></td>
<td><p>1</p></td>
<td><p>20000</p></td>
<td><p>0.90</p></td>
<td><p>0.93</p></td>
</tr>
<tr class="row-even"><td><p>jailbreak_vigil</p></td>
<td><p>1</p></td>
<td><p>104</p></td>
<td><p>1.00</p></td>
<td><p>1.00</p></td>
</tr>
<tr class="row-odd"><td><p>mental_health</p></td>
<td><p>0</p></td>
<td><p>3512</p></td>
<td><p>1.00</p></td>
<td><p>1.00</p></td>
</tr>
<tr class="row-even"><td><p>telecom</p></td>
<td><p>0</p></td>
<td><p>4000</p></td>
<td><p>1.00</p></td>
<td><p>1.00</p></td>
</tr>
<tr class="row-odd"><td><p>truthqa</p></td>
<td><p>0</p></td>
<td><p>817</p></td>
<td><p>1.00</p></td>
<td><p>0.98</p></td>
</tr>
<tr class="row-even"><td><p>weather</p></td>
<td><p>0</p></td>
<td><p>3121</p></td>
<td><p>1.00</p></td>
<td><p>1.00</p></td>
</tr>
</tbody>
</table>
</div>
<div class="pst-scrollable-table-container"><table class="table">
<colgroup>
<col style="width: 42.9%" />
<col style="width: 57.1%" />
</colgroup>
<thead>
<tr class="row-odd"><th class="head"><p>Statistics</p></th>
<th class="head"><p>Overall performance</p></th>
</tr>
</thead>
<tbody>
<tr class="row-even"><td><p>Overall Accuracy</p></td>
<td><p>0.93568 (Prompt-Guard), 0.95267 (Arch-Guard)</p></td>
</tr>
<tr class="row-odd"><td><p>True positives rate (TPR)</p></td>
<td><p>0.8468 (Prompt-Guard), 0.8887 (Arch-Guard)</p></td>
</tr>
<tr class="row-even"><td><p>True negative rate (TNR)</p></td>
<td><p>0.9972 (Prompt-Guard), 0.9970 (Arch-Guard)</p></td>
</tr>
<tr class="row-odd"><td><p>False positive rate (FPR)</p></td>
<td><p>0.0028 (Prompt-Guard), 0.0030 (Arch-Guard)</p></td>
</tr>
<tr class="row-even"><td><p>False negative rate (FNR)</p></td>
<td><p>0.1532 (Prompt-Guard), 0.1113 (Arch-Guard)</p></td>
</tr>
</tbody>
</table>
</div>
<div class="pst-scrollable-table-container"><table class="table">
<colgroup>
<col style="width: 42.9%" />
<col style="width: 57.1%" />
</colgroup>
<thead>
<tr class="row-odd"><th class="head"><p>Metrics</p></th>
<th class="head"><p>Values</p></th>
</tr>
</thead>
<tbody>
<tr class="row-even"><td><p>AUC</p></td>
<td><p>0.857 (Prompt-Guard), 0.880 (Arch-Guard)</p></td>
</tr>
<tr class="row-odd"><td><p>Precision</p></td>
<td><p>0.715 (Prompt-Guard), 0.761 (Arch-Guard)</p></td>
</tr>
<tr class="row-even"><td><p>Recall</p></td>
<td><p>0.999 (Prompt-Guard), 0.999 (Arch-Guard)</p></td>
</tr>
</tbody>
</table>
</div>
</section>
<section id="arch-fc">
<h2>Arch-FC<a class="headerlink" href="#arch-fc" title="Link to this heading">#</a></h2>
<p>Arch-FC is a lean, powerful and cost-effective agentic model designed for function calling scenarios.
You can run Arch-FC locally, or use the cloud-hosted version for as little as $0.05/M token (100x cheaper
than GPT-4o), with a p50 latency of 200ms (5x faster than GPT-4o), while meeting frontier model performance.</p>
<div class="admonition note">
<p class="admonition-title">Note</p>
<p>Function calling helps you personalize the GenAI experience by calling application-specific operations via
prompts. This involves any predefined functions or APIs you want to expose to perform tasks, gather
information, or manipulate data - via prompts.</p>
<p>You can get started with function calling simply by configuring a prompt target with a name, description
and set of parameters needed by a specific backend function or a hosted API. The name, and description helps
Arch-FC match a user prompt to a function or API that can process it.</p>
</div>
<p>By using Arch-FC, Arch enables you to easily build agentic workflows tailored to domain-specific use cases -
from updating insurance claims to creating ad campaigns. Arch-FC analyzes prompts, extracts critical information
from prompts, engages in lightweight conversations with the user to gather any missing parameters need before
handling control back to Arch to make the API call to your hosted backend. Arch-FC handles the muck of information
extraction so that you can focus on the business logic of your application.</p>
</section>
</section>
</article>
<footer class="prev-next-footer d-print-none">
<div class="prev-next-area">
<a class="left-prev"
href="../observability/access_logs.html"
title="previous page">
<i class="fa-solid fa-angle-left"></i>
<div class="prev-next-info">
<p class="prev-next-subtitle">previous</p>
<p class="prev-next-title">Access Logging</p>
</div>
</a>
<a class="right-next"
href="../configuration_reference.html"
title="next page">
<div class="prev-next-info">
<p class="prev-next-subtitle">next</p>
<p class="prev-next-title">Configuration Reference</p>
</div>
<i class="fa-solid fa-angle-right"></i>
</a>
</div>
</footer>
</div>
<div class="bd-sidebar-secondary bd-toc"><div class="sidebar-secondary-items sidebar-secondary__inner">
<div class="sidebar-secondary-item">
<div class="page-toc tocsection onthispage">
<i class="fa-solid fa-list"></i> Contents
</div>
<nav class="bd-toc-nav page-toc">
<ul class="visible nav section-nav flex-column">
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#arch-guard-v1">Arch-Guard-v1</a></li>
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#arch-fc">Arch-FC</a></li>
</ul>
</nav></div>
</div></div>
</div>
<footer class="bd-footer-content">
<div class="bd-footer-content__inner container">
<div class="footer-item">
<p class="component-author">
By Katanemo Labs, Inc
</p>
</div>
<div class="footer-item">
<p class="copyright">
© Copyright 2024, Katanemo Labs, Inc.
<br/>
</p>
</div>
<div class="footer-item">
</div>
<div class="footer-item">
</div>
</div>
</footer>
</main>
</div>
</div>
<!-- Scripts loaded after <body> so the DOM is not blocked -->
<script src="../_static/scripts/bootstrap.js?digest=dfe6caa3a7d634c4db9b"></script>
<script src="../_static/scripts/pydata-sphinx-theme.js?digest=dfe6caa3a7d634c4db9b"></script>
<footer class="bd-footer">
</footer>
</body>
</html>