This commit is contained in:
salmanap 2024-10-08 20:19:06 +00:00
parent f4b686c7fc
commit 3e881c6eec
28 changed files with 819 additions and 820 deletions

View file

@ -0,0 +1,244 @@
<!DOCTYPE html>
<html :class="{'dark': darkMode === 'dark' || (darkMode === 'system' &amp;&amp; window.matchMedia('(prefers-color-scheme: dark)').matches)}" class="scroll-smooth" data-content_root="../../" lang="en" x-data="{ darkMode: localStorage.getItem('darkMode') || localStorage.setItem('darkMode', 'system'), activeSection: '' }" x-init="$watch('darkMode', val =&gt; localStorage.setItem('darkMode', val))">
<head>
<meta content="width=device-width, initial-scale=1.0" name="viewport"/>
<meta charset="utf-8"/>
<meta content="white" media="(prefers-color-scheme: light)" name="theme-color"/>
<meta content="black" media="(prefers-color-scheme: dark)" name="theme-color"/>
<meta content="width=device-width, initial-scale=1" name="viewport"/>
<title>Error Target | Arch Docs v0.1</title>
<meta content="Error Target | Arch Docs v0.1" property="og:title"/>
<meta content="Error Target | Arch Docs v0.1" name="twitter:title"/>
<link href="../../_static/pygments.css?v=75ebff74" rel="stylesheet" type="text/css"/>
<link href="../../_static/theme.css?v=edd7d3d2" rel="stylesheet" type="text/css"/>
<link href="../../_static/_static/custom.css" rel="stylesheet" type="text/css"/>
<link href="../../_static/sphinx-design.min.css?v=95c83b7e" rel="stylesheet" type="text/css"/>
<link href="../../_static/awesome-sphinx-design.css?v=a54cf077" rel="stylesheet" type="text/css"/>
<link href="./docs/concepts/tech_overview/error_target.html" rel="canonical"/>
<link href="../../_static/favicon.ico" rel="icon"/>
<link href="../../search.html" rel="search" title="Search"/>
<link href="../llm_provider.html" rel="next" title="LLM Provider"/>
<link href="request_lifecycle.html" rel="prev" title="Request Lifecycle"/>
<script>
<!-- Prevent Flash of wrong theme -->
const userPreference = localStorage.getItem('darkMode');
let mode;
if (userPreference === 'dark' || window.matchMedia('(prefers-color-scheme: dark)').matches) {
mode = 'dark';
document.documentElement.classList.add('dark');
} else {
mode = 'light';
}
if (!userPreference) {localStorage.setItem('darkMode', mode)}
</script>
</head>
<body :class="{ 'overflow-hidden': showSidebar }" class="min-h-screen font-sans antialiased bg-background text-foreground" x-data="{ showSidebar: false, showScrollTop: false }">
<div @click.self="showSidebar = false" class="fixed inset-0 z-50 overflow-hidden bg-background/80 backdrop-blur-sm md:hidden" x-cloak="" x-show="showSidebar"></div><div class="relative flex flex-col min-h-screen" id="page"><a class="absolute top-0 left-0 z-[100] block bg-background p-4 text-xl transition -translate-x-full opacity-0 focus:translate-x-0 focus:opacity-100" href="#content">
Skip to content
</a><header class="sticky top-0 z-40 w-full border-b shadow-sm border-border supports-backdrop-blur:bg-background/60 bg-background/95 backdrop-blur"><div class="container flex items-center h-14">
<div class="hidden mr-4 md:flex">
<a class="flex items-center mr-6" href="../../index.html">
<img alt="Logo" class="mr-2 dark:invert" height="24" src="../../_static/favicon.ico" width="24"/><span class="hidden font-bold sm:inline-block text-clip whitespace-nowrap">Arch Docs v0.1</span>
</a></div><button @click="showSidebar = true" class="inline-flex items-center justify-center h-10 px-0 py-2 mr-2 text-base font-medium transition-colors rounded-md hover:text-accent-foreground hover:bg-transparent md:hidden" type="button">
<svg aria-hidden="true" fill="currentColor" height="24" viewbox="0 96 960 960" width="24" xmlns="http://www.w3.org/2000/svg">
<path d="M152.587 825.087q-19.152 0-32.326-13.174t-13.174-32.326q0-19.152 13.174-32.326t32.326-13.174h440q19.152 0 32.326 13.174t13.174 32.326q0 19.152-13.174 32.326t-32.326 13.174h-440Zm0-203.587q-19.152 0-32.326-13.174T107.087 576q0-19.152 13.174-32.326t32.326-13.174h320q19.152 0 32.326 13.174T518.087 576q0 19.152-13.174 32.326T472.587 621.5h-320Zm0-203.587q-19.152 0-32.326-13.174t-13.174-32.326q0-19.152 13.174-32.326t32.326-13.174h440q19.152 0 32.326 13.174t13.174 32.326q0 19.152-13.174 32.326t-32.326 13.174h-440ZM708.913 576l112.174 112.174q12.674 12.674 12.674 31.826t-12.674 31.826Q808.413 764.5 789.261 764.5t-31.826-12.674l-144-144Q600 594.391 600 576t13.435-31.826l144-144q12.674-12.674 31.826-12.674t31.826 12.674q12.674 12.674 12.674 31.826t-12.674 31.826L708.913 576Z"></path>
</svg>
<span class="sr-only">Toggle navigation menu</span>
</button>
<div class="flex items-center justify-between flex-1 space-x-2 sm:space-x-4 md:justify-end">
<div class="flex-1 w-full md:w-auto md:flex-none"><form @keydown.k.window.meta="$refs.search.focus()" action="../../search.html" class="relative flex items-center group" id="searchbox" method="get">
<input aria-label="Search the docs" class="inline-flex items-center font-medium transition-colors bg-transparent focus-visible:outline-none focus-visible:ring-2 focus-visible:ring-ring focus-visible:ring-offset-2 ring-offset-background border border-input hover:bg-accent focus:bg-accent hover:text-accent-foreground focus:text-accent-foreground hover:placeholder-accent-foreground py-2 px-4 relative h-9 w-full justify-start rounded-[0.5rem] text-sm text-muted-foreground sm:pr-12 md:w-40 lg:w-64" id="search-input" name="q" placeholder="Search ..." type="search" x-ref="search"/>
<kbd class="pointer-events-none absolute right-1.5 top-2 hidden h-5 select-none text-muted-foreground items-center gap-1 rounded border border-border bg-muted px-1.5 font-mono text-[10px] font-medium opacity-100 sm:flex group-hover:bg-accent group-hover:text-accent-foreground">
<span class="text-xs"></span>
K
</kbd>
</form>
</div>
<nav class="flex items-center space-x-1">
<a href="https://github.com/katanemo/arch" rel="noopener nofollow" title="Visit repository on GitHub">
<div class="inline-flex items-center justify-center px-0 text-sm font-medium transition-colors rounded-md disabled:opacity-50 disabled:pointer-events-none hover:bg-accent hover:text-accent-foreground h-9 w-9">
<svg fill="currentColor" height="26px" style="margin-top:-2px;display:inline" viewbox="0 0 45 44" xmlns="http://www.w3.org/2000/svg"><path clip-rule="evenodd" d="M22.477.927C10.485.927.76 10.65.76 22.647c0 9.596 6.223 17.736 14.853 20.608 1.087.2 1.483-.47 1.483-1.047 0-.516-.019-1.881-.03-3.693-6.04 1.312-7.315-2.912-7.315-2.912-.988-2.51-2.412-3.178-2.412-3.178-1.972-1.346.149-1.32.149-1.32 2.18.154 3.327 2.24 3.327 2.24 1.937 3.318 5.084 2.36 6.321 1.803.197-1.403.759-2.36 1.379-2.903-4.823-.548-9.894-2.412-9.894-10.734 0-2.37.847-4.31 2.236-5.828-.224-.55-.969-2.759.214-5.748 0 0 1.822-.584 5.972 2.226 1.732-.482 3.59-.722 5.437-.732 1.845.01 3.703.25 5.437.732 4.147-2.81 5.967-2.226 5.967-2.226 1.185 2.99.44 5.198.217 5.748 1.392 1.517 2.232 3.457 2.232 5.828 0 8.344-5.078 10.18-9.916 10.717.779.67 1.474 1.996 1.474 4.021 0 2.904-.027 5.247-.027 5.96 0 .58.392 1.256 1.493 1.044C37.981 40.375 44.2 32.24 44.2 22.647c0-11.996-9.726-21.72-21.722-21.72" fill="currentColor" fill-rule="evenodd"></path></svg>
</div>
</a>
<button @click="darkMode = darkMode === 'light' ? 'dark' : 'light'" aria-label="Color theme switcher" class="relative inline-flex items-center justify-center px-0 text-sm font-medium transition-colors rounded-md hover:bg-accent hover:text-accent-foreground h-9 w-9" type="button">
<svg class="absolute transition-all scale-100 rotate-0 dark:-rotate-90 dark:scale-0" fill="currentColor" height="24" viewbox="0 96 960 960" width="24" xmlns="http://www.w3.org/2000/svg">
<path d="M480 685q45.456 0 77.228-31.772Q589 621.456 589 576q0-45.456-31.772-77.228Q525.456 467 480 467q-45.456 0-77.228 31.772Q371 530.544 371 576q0 45.456 31.772 77.228Q434.544 685 480 685Zm0 91q-83 0-141.5-58.5T280 576q0-83 58.5-141.5T480 376q83 0 141.5 58.5T680 576q0 83-58.5 141.5T480 776ZM80 621.5q-19.152 0-32.326-13.174T34.5 576q0-19.152 13.174-32.326T80 530.5h80q19.152 0 32.326 13.174T205.5 576q0 19.152-13.174 32.326T160 621.5H80Zm720 0q-19.152 0-32.326-13.174T754.5 576q0-19.152 13.174-32.326T800 530.5h80q19.152 0 32.326 13.174T925.5 576q0 19.152-13.174 32.326T880 621.5h-80Zm-320-320q-19.152 0-32.326-13.174T434.5 256v-80q0-19.152 13.174-32.326T480 130.5q19.152 0 32.326 13.174T525.5 176v80q0 19.152-13.174 32.326T480 301.5Zm0 720q-19.152 0-32.326-13.17Q434.5 995.152 434.5 976v-80q0-19.152 13.174-32.326T480 850.5q19.152 0 32.326 13.174T525.5 896v80q0 19.152-13.174 32.33-13.174 13.17-32.326 13.17ZM222.174 382.065l-43-42Q165.5 327.391 166 308.239t13.174-33.065q13.435-13.674 32.587-13.674t32.065 13.674l42.239 43q12.674 13.435 12.555 31.706-.12 18.272-12.555 31.946-12.674 13.674-31.445 13.413-18.772-.261-32.446-13.174Zm494 494.761-42.239-43q-12.674-13.435-12.674-32.087t12.674-31.565Q686.609 756.5 705.38 757q18.772.5 32.446 13.174l43 41.761Q794.5 824.609 794 843.761t-13.174 33.065Q767.391 890.5 748.239 890.5t-32.065-13.674Zm-42-494.761Q660.5 369.391 661 350.62q.5-18.772 13.174-32.446l41.761-43Q728.609 261.5 747.761 262t33.065 13.174q13.674 13.435 13.674 32.587t-13.674 32.065l-43 42.239q-13.435 12.674-31.706 12.555-18.272-.12-31.946-12.555Zm-495 494.761Q165.5 863.391 165.5 844.239t13.674-32.065l43-42.239q13.435-12.674 32.087-12.674t31.565 12.674Q299.5 782.609 299 801.38q-.5 18.772-13.174 32.446l-41.761 43Q231.391 890.5 212.239 890t-33.065-13.174ZM480 576Z"></path>
</svg>
<svg class="absolute transition-all scale-0 rotate-90 dark:rotate-0 dark:scale-100" fill="currentColor" height="24" viewbox="0 96 960 960" width="24" xmlns="http://www.w3.org/2000/svg">
<path d="M480 936q-151 0-255.5-104.5T120 576q0-138 90-239.5T440 218q25-3 39 18t-1 44q-17 26-25.5 55t-8.5 61q0 90 63 153t153 63q31 0 61.5-9t54.5-25q21-14 43-1.5t19 39.5q-14 138-117.5 229T480 936Zm0-80q88 0 158-48.5T740 681q-20 5-40 8t-40 3q-123 0-209.5-86.5T364 396q0-20 3-40t8-40q-78 32-126.5 102T200 576q0 116 82 198t198 82Zm-10-270Z"></path>
</svg>
</button>
</nav>
</div>
</div>
</header>
<div class="flex-1"><div class="container flex-1 items-start md:grid md:grid-cols-[220px_minmax(0,1fr)] md:gap-6 lg:grid-cols-[240px_minmax(0,1fr)] lg:gap-10"><aside :aria-hidden="!showSidebar" :class="{ 'translate-x-0': showSidebar }" class="fixed inset-y-0 left-0 md:top-14 z-50 md:z-30 bg-background md:bg-transparent transition-all duration-100 -translate-x-full md:translate-x-0 ml-0 p-6 md:p-0 md:-ml-2 md:h-[calc(100vh-3.5rem)] w-5/6 md:w-full shrink-0 overflow-y-auto border-r border-border md:sticky" id="left-sidebar">
<a class="!justify-start text-sm md:!hidden bg-background" href="../../index.html">
<img alt="Logo" class="mr-2 dark:invert" height="16" src="../../_static/favicon.ico" width="16"/><span class="font-bold text-clip whitespace-nowrap">Arch Docs v0.1</span>
</a>
<div class="relative overflow-hidden md:overflow-auto my-4 md:my-0 h-[calc(100vh-8rem)] md:h-auto">
<div class="overflow-y-auto h-full w-full relative pr-6">
<script async="" src="https://www.googletagmanager.com/gtag/js?id=G-K2LXXSX6HB"></script>
<script>
window.dataLayer = window.dataLayer || [];
function gtag(){dataLayer.push(arguments);}
gtag('js', new Date());
gtag('config', 'G-K2LXXSX6HB');
</script>
<nav class="table w-full min-w-full my-6 lg:my-8">
<p class="caption" role="heading"><span class="caption-text">Get Started</span></p>
<ul>
<li class="toctree-l1"><a class="reference internal" href="../../get_started/overview.html">Overview</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../get_started/intro_to_arch.html">Intro to Arch</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../get_started/quickstart.html">Quickstart</a></li>
</ul>
<p class="caption" role="heading"><span class="caption-text">Concepts</span></p>
<ul class="current">
<li class="toctree-l1 current" x-data="{ expanded: $el.classList.contains('current') ? true : false }"><a :class="{ 'expanded' : expanded }" @click="expanded = !expanded" class="reference internal expandable" href="tech_overview.html">Tech Overview<button @click.prevent.stop="expanded = !expanded" type="button"><span class="sr-only"></span><svg fill="currentColor" height="18px" stroke="none" viewbox="0 0 24 24" width="18px" xmlns="http://www.w3.org/2000/svg"><path d="M10 6L8.59 7.41 13.17 12l-4.58 4.59L10 18l6-6z"></path></svg></button></a><ul class="current" x-show="expanded">
<li class="toctree-l2"><a class="reference internal" href="terminology.html">Terminology</a></li>
<li class="toctree-l2"><a class="reference internal" href="threading_model.html">Threading Model</a></li>
<li class="toctree-l2"><a class="reference internal" href="listener.html">Listener</a></li>
<li class="toctree-l2"><a class="reference internal" href="prompt.html">Prompts</a></li>
<li class="toctree-l2"><a class="reference internal" href="model_serving.html">Model Serving</a></li>
<li class="toctree-l2"><a class="reference internal" href="request_lifecycle.html">Request Lifecycle</a></li>
<li class="toctree-l2 current"><a class="current reference internal" href="#">Error Target</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="../llm_provider.html">LLM Provider</a></li>
<li class="toctree-l1"><a class="reference internal" href="../prompt_target.html">Prompt Target</a></li>
</ul>
<p class="caption" role="heading"><span class="caption-text">Guides</span></p>
<ul>
<li class="toctree-l1"><a class="reference internal" href="../../guides/prompt_guard.html">Prompt Guard</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../guides/function_calling.html">Function Calling</a></li>
<li class="toctree-l1" x-data="{ expanded: $el.classList.contains('current') ? true : false }"><a :class="{ 'expanded' : expanded }" @click="expanded = !expanded" class="reference internal expandable" href="../../guides/observability/observability.html">Observability<button @click.prevent.stop="expanded = !expanded" type="button"><span class="sr-only"></span><svg fill="currentColor" height="18px" stroke="none" viewbox="0 0 24 24" width="18px" xmlns="http://www.w3.org/2000/svg"><path d="M10 6L8.59 7.41 13.17 12l-4.58 4.59L10 18l6-6z"></path></svg></button></a><ul x-show="expanded">
<li class="toctree-l2"><a class="reference internal" href="../../guides/observability/tracing.html">Tracing</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../guides/observability/monitoring.html">Monitoring</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../guides/observability/access_logging.html">Access Logging</a></li>
</ul>
</li>
</ul>
<p class="caption" role="heading"><span class="caption-text">Build with Arch</span></p>
<ul>
<li class="toctree-l1"><a class="reference internal" href="../../build_with_arch/agent.html">Agentic Workflow</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../build_with_arch/rag.html">RAG Application</a></li>
</ul>
<p class="caption" role="heading"><span class="caption-text">Resources</span></p>
<ul>
<li class="toctree-l1"><a class="reference internal" href="../../resources/configuration_reference.html">Configuration Reference</a></li>
</ul>
</nav>
</div>
</div>
<button @click="showSidebar = false" class="absolute md:hidden right-4 top-4 rounded-sm opacity-70 transition-opacity hover:opacity-100" type="button">
<svg class="h-4 w-4" fill="currentColor" height="24" stroke="none" viewbox="0 96 960 960" width="24" xmlns="http://www.w3.org/2000/svg">
<path d="M480 632 284 828q-11 11-28 11t-28-11q-11-11-11-28t11-28l196-196-196-196q-11-11-11-28t11-28q11-11 28-11t28 11l196 196 196-196q11-11 28-11t28 11q11 11 11 28t-11 28L536 576l196 196q11 11 11 28t-11 28q-11 11-28 11t-28-11L480 632Z"></path>
</svg>
</button>
</aside>
<main class="relative py-6 lg:gap-10 lg:py-8 xl:grid xl:grid-cols-[1fr_300px]">
<div class="w-full min-w-0 mx-auto">
<nav aria-label="breadcrumbs" class="flex items-center mb-4 space-x-1 text-sm text-muted-foreground">
<a class="overflow-hidden text-ellipsis whitespace-nowrap hover:text-foreground" href="../../index.html">
<span class="hidden md:inline">Arch Docs v0.1</span>
<svg aria-label="Home" class="md:hidden" fill="currentColor" height="18" stroke="none" viewbox="0 96 960 960" width="18" xmlns="http://www.w3.org/2000/svg">
<path d="M240 856h120V616h240v240h120V496L480 316 240 496v360Zm-80 80V456l320-240 320 240v480H520V696h-80v240H160Zm320-350Z"></path>
</svg>
</a>
<div class="mr-1">/</div><a class="hover:text-foreground overflow-hidden text-ellipsis whitespace-nowrap" href="tech_overview.html">Tech Overview</a>
<div class="mr-1">/</div><span aria-current="page" class="font-medium text-foreground overflow-hidden text-ellipsis whitespace-nowrap">Error Target</span>
</nav>
<div id="content" role="main">
<section id="error-target">
<span id="id1"></span><h1>Error Target<a @click.prevent="window.navigator.clipboard.writeText($el.href); $el.setAttribute('data-tooltip', 'Copied!'); setTimeout(() =&gt; $el.setAttribute('data-tooltip', 'Copy link to this element'), 2000)" aria-label="Copy link to this element" class="headerlink" data-tooltip="Copy link to this element" href="#error-target"><svg height="1em" viewbox="0 0 24 24" width="1em" xmlns="http://www.w3.org/2000/svg"><path d="M3.9 12c0-1.71 1.39-3.1 3.1-3.1h4V7H7c-2.76 0-5 2.24-5 5s2.24 5 5 5h4v-1.9H7c-1.71 0-3.1-1.39-3.1-3.1zM8 13h8v-2H8v2zm9-6h-4v1.9h4c1.71 0 3.1 1.39 3.1 3.1s-1.39 3.1-3.1 3.1h-4V17h4c2.76 0 5-2.24 5-5s-2.24-5-5-5z"></path></svg></a></h1>
<p><strong>Error targets</strong> are designed to capture and manage specific issues or exceptions that occur during Archs function or systems execution.</p>
<p>These endpoints receive errors forwarded from Arch when issues arise, such as improper function/API calls, guardrail violations, or other processing errors.
The errors are communicated to the application via headers like <code class="docutils literal notranslate"><span class="pre">X-Arch-[ERROR-TYPE]</span></code>, enabling you to respond appropriately and handle errors gracefully.</p>
<section id="key-concepts">
<h2>Key Concepts<a @click.prevent="window.navigator.clipboard.writeText($el.href); $el.setAttribute('data-tooltip', 'Copied!'); setTimeout(() =&gt; $el.setAttribute('data-tooltip', 'Copy link to this element'), 2000)" aria-label="Copy link to this element" class="headerlink" data-tooltip="Copy link to this element" href="#key-concepts" x-intersect.margin.0%.0%.-70%.0%="activeSection = '#key-concepts'"><svg height="1em" viewbox="0 0 24 24" width="1em" xmlns="http://www.w3.org/2000/svg"><path d="M3.9 12c0-1.71 1.39-3.1 3.1-3.1h4V7H7c-2.76 0-5 2.24-5 5s2.24 5 5 5h4v-1.9H7c-1.71 0-3.1-1.39-3.1-3.1zM8 13h8v-2H8v2zm9-6h-4v1.9h4c1.71 0 3.1 1.39 3.1 3.1s-1.39 3.1-3.1 3.1h-4V17h4c2.76 0 5-2.24 5-5s-2.24-5-5-5z"></path></svg></a></h2>
<ul class="simple">
<li><p><strong>Error Type</strong>: Categorizes the nature of the error, such as “ValidationError” or “RuntimeError.” These error types help in identifying what kind of issue occurred and provide context for troubleshooting.</p></li>
<li><p><strong>Error Message</strong>: A clear, human-readable message describing the error. This should provide enough detail to inform users or developers of the root cause or required action.</p></li>
<li><p><strong>Target Prompt</strong>: The specific prompt or operation where the error occurred. Understanding where the error happened helps with debugging and pinpointing the source of the problem.</p></li>
<li><p><strong>Parameter-Specific Errors</strong>: Errors that arise due to invalid or missing parameters when invoking a function. These errors are critical for ensuring the correctness of inputs.</p></li>
</ul>
</section>
<section id="error-header-example">
<h2>Error Header Example<a @click.prevent="window.navigator.clipboard.writeText($el.href); $el.setAttribute('data-tooltip', 'Copied!'); setTimeout(() =&gt; $el.setAttribute('data-tooltip', 'Copy link to this element'), 2000)" aria-label="Copy link to this element" class="headerlink" data-tooltip="Copy link to this element" href="#error-header-example" x-intersect.margin.0%.0%.-70%.0%="activeSection = '#error-header-example'"><svg height="1em" viewbox="0 0 24 24" width="1em" xmlns="http://www.w3.org/2000/svg"><path d="M3.9 12c0-1.71 1.39-3.1 3.1-3.1h4V7H7c-2.76 0-5 2.24-5 5s2.24 5 5 5h4v-1.9H7c-1.71 0-3.1-1.39-3.1-3.1zM8 13h8v-2H8v2zm9-6h-4v1.9h4c1.71 0 3.1 1.39 3.1 3.1s-1.39 3.1-3.1 3.1h-4V17h4c2.76 0 5-2.24 5-5s-2.24-5-5-5z"></path></svg></a></h2>
<div class="literal-block-wrapper docutils container" id="id2">
<div class="code-block-caption"><span class="caption-text">Error Header Example</span><a @click.prevent="window.navigator.clipboard.writeText($el.href); $el.setAttribute('data-tooltip', 'Copied!'); setTimeout(() =&gt; $el.setAttribute('data-tooltip', 'Copy link to this element'), 2000)" aria-label="Copy link to this element" class="headerlink" data-tooltip="Copy link to this element" href="#id2"><svg height="1em" viewbox="0 0 24 24" width="1em" xmlns="http://www.w3.org/2000/svg"><path d="M3.9 12c0-1.71 1.39-3.1 3.1-3.1h4V7H7c-2.76 0-5 2.24-5 5s2.24 5 5 5h4v-1.9H7c-1.71 0-3.1-1.39-3.1-3.1zM8 13h8v-2H8v2zm9-6h-4v1.9h4c1.71 0 3.1 1.39 3.1 3.1s-1.39 3.1-3.1 3.1h-4V17h4c2.76 0 5-2.24 5-5s-2.24-5-5-5z"></path></svg></a></div>
<div class="highlight-bash notranslate"><div class="highlight"><pre><span></span><code><span id="line-1"><span class="w"> </span>HTTP/1.1<span class="w"> </span><span class="m">400</span><span class="w"> </span>Bad<span class="w"> </span>Request
</span><span id="line-2"><span class="w"> </span>X-Arch-Error-Type:<span class="w"> </span>FunctionValidationError
</span><span id="line-3"><span class="w"> </span>X-Arch-Error-Message:<span class="w"> </span>Tools<span class="w"> </span>call<span class="w"> </span>parsing<span class="w"> </span>failure
</span><span id="line-4"><span class="w"> </span>X-Arch-Target-Prompt:<span class="w"> </span>createUser
</span><span id="line-5"><span class="w"> </span>Content-Type:<span class="w"> </span>application/json
</span><span id="line-6">
</span><span id="line-7"><span class="w"> </span><span class="s2">"messages"</span>:<span class="w"> </span><span class="o">[</span>
</span><span id="line-8"><span class="w"> </span><span class="o">{</span>
</span><span id="line-9"><span class="w"> </span><span class="s2">"role"</span>:<span class="w"> </span><span class="s2">"user"</span>,
</span><span id="line-10"><span class="w"> </span><span class="s2">"content"</span>:<span class="w"> </span><span class="s2">"Please create a user with the following ID: 1234"</span>
</span><span id="line-11"><span class="w"> </span><span class="o">}</span>,
</span><span id="line-12"><span class="w"> </span><span class="o">{</span>
</span><span id="line-13"><span class="w"> </span><span class="s2">"role"</span>:<span class="w"> </span><span class="s2">"system"</span>,
</span><span id="line-14"><span class="w"> </span><span class="s2">"content"</span>:<span class="w"> </span><span class="s2">"Expected a string for 'user_id', but got an integer."</span>
</span><span id="line-15"><span class="w"> </span><span class="o">}</span>
</span><span id="line-16"><span class="w"> </span><span class="o">]</span>
</span></code></pre></div>
</div>
</div>
</section>
<section id="best-practices-and-tips">
<h2>Best Practices and Tips<a @click.prevent="window.navigator.clipboard.writeText($el.href); $el.setAttribute('data-tooltip', 'Copied!'); setTimeout(() =&gt; $el.setAttribute('data-tooltip', 'Copy link to this element'), 2000)" aria-label="Copy link to this element" class="headerlink" data-tooltip="Copy link to this element" href="#best-practices-and-tips" x-intersect.margin.0%.0%.-70%.0%="activeSection = '#best-practices-and-tips'"><svg height="1em" viewbox="0 0 24 24" width="1em" xmlns="http://www.w3.org/2000/svg"><path d="M3.9 12c0-1.71 1.39-3.1 3.1-3.1h4V7H7c-2.76 0-5 2.24-5 5s2.24 5 5 5h4v-1.9H7c-1.71 0-3.1-1.39-3.1-3.1zM8 13h8v-2H8v2zm9-6h-4v1.9h4c1.71 0 3.1 1.39 3.1 3.1s-1.39 3.1-3.1 3.1h-4V17h4c2.76 0 5-2.24 5-5s-2.24-5-5-5z"></path></svg></a></h2>
<ul class="simple">
<li><p><strong>Graceful Degradation</strong>: If an error occurs, fail gracefully by providing fallback logic or alternative flows when possible.</p></li>
<li><p><strong>Log Errors</strong>: Always log errors on the server side for later analysis.</p></li>
<li><p><strong>Client-Side Handling</strong>: Make sure the client can interpret error responses and provide meaningful feedback to the user. Clients should not display raw error codes or stack traces but rather handle them gracefully.</p></li>
</ul>
</section>
</section>
</div><div class="flex justify-between items-center pt-6 mt-12 border-t border-border gap-4">
<div class="mr-auto">
<a class="inline-flex items-center justify-center rounded-md text-sm font-medium transition-colors border border-input hover:bg-accent hover:text-accent-foreground py-2 px-4" href="request_lifecycle.html">
<svg class="mr-2 h-4 w-4" fill="none" height="24" stroke="currentColor" stroke-linecap="round" stroke-linejoin="round" stroke-width="2" viewbox="0 0 24 24" width="24" xmlns="http://www.w3.org/2000/svg">
<polyline points="15 18 9 12 15 6"></polyline>
</svg>
Request Lifecycle
</a>
</div>
<div class="ml-auto">
<a class="inline-flex items-center justify-center rounded-md text-sm font-medium transition-colors border border-input hover:bg-accent hover:text-accent-foreground py-2 px-4" href="../llm_provider.html">
LLM Provider
<svg class="ml-2 h-4 w-4" fill="none" height="24" stroke="currentColor" stroke-linecap="round" stroke-linejoin="round" stroke-width="2" viewbox="0 0 24 24" width="24" xmlns="http://www.w3.org/2000/svg">
<polyline points="9 18 15 12 9 6"></polyline>
</svg>
</a>
</div>
</div></div><aside class="hidden text-sm xl:block" id="right-sidebar">
<div class="sticky top-16 -mt-10 max-h-[calc(100vh-5rem)] overflow-y-auto pt-6 space-y-2"><p class="font-medium">On this page</p>
<ul>
<li><a :data-current="activeSection === '#key-concepts'" class="reference internal" href="#key-concepts">Key Concepts</a></li>
<li><a :data-current="activeSection === '#error-header-example'" class="reference internal" href="#error-header-example">Error Header Example</a></li>
<li><a :data-current="activeSection === '#best-practices-and-tips'" class="reference internal" href="#best-practices-and-tips">Best Practices and Tips</a></li>
</ul>
</div>
</aside>
</main>
</div>
</div><footer class="py-6 border-t border-border md:py-0">
<div class="container flex flex-col items-center justify-between gap-4 md:h-24 md:flex-row">
<div class="flex flex-col items-center gap-4 px-8 md:flex-row md:gap-2 md:px-0">
<p class="text-sm leading-loose text-center text-muted-foreground md:text-left">© 2024, Katanemo Labs, Inc Last updated: Oct 08, 2024. </p>
</div>
</div>
</footer>
</div>
<script src="../../_static/documentation_options.js?v=a0703c7e"></script>
<script src="../../_static/doctools.js?v=9a2dae69"></script>
<script src="../../_static/sphinx_highlight.js?v=dc90522c"></script>
<script defer="defer" src="../../_static/theme.js?v=1808ab49"></script>
<script src="../../_static/design-tabs.js?v=f930bc37"></script>
</body>
</html>

View file

@ -18,7 +18,7 @@
<link href="./docs/concepts/tech_overview/listener.html" rel="canonical"/>
<link href="../../_static/favicon.ico" rel="icon"/>
<link href="../../search.html" rel="search" title="Search"/>
<link href="model_serving.html" rel="next" title="Model Serving"/>
<link href="prompt.html" rel="next" title="Prompts"/>
<link href="threading_model.html" rel="prev" title="Threading Model"/>
<script>
<!-- Prevent Flash of wrong theme -->
@ -101,9 +101,10 @@
<li class="toctree-l2"><a class="reference internal" href="terminology.html">Terminology</a></li>
<li class="toctree-l2"><a class="reference internal" href="threading_model.html">Threading Model</a></li>
<li class="toctree-l2 current"><a class="current reference internal" href="#">Listener</a></li>
<li class="toctree-l2"><a class="reference internal" href="prompt.html">Prompts</a></li>
<li class="toctree-l2"><a class="reference internal" href="model_serving.html">Model Serving</a></li>
<li class="toctree-l2"><a class="reference internal" href="prompt.html">Prompt</a></li>
<li class="toctree-l2"><a class="reference internal" href="request_lifecycle.html">Request Lifecycle</a></li>
<li class="toctree-l2"><a class="reference internal" href="error_target.html">Error Target</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="../llm_provider.html">LLM Provider</a></li>
@ -128,7 +129,6 @@
<p class="caption" role="heading"><span class="caption-text">Resources</span></p>
<ul>
<li class="toctree-l1"><a class="reference internal" href="../../resources/configuration_reference.html">Configuration Reference</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../resources/error_target.html">Error Targets</a></li>
</ul>
</nav>
</div>
@ -154,7 +154,7 @@
<div id="content" role="main">
<section id="listener">
<span id="arch-overview-listeners"></span><h1>Listener<a @click.prevent="window.navigator.clipboard.writeText($el.href); $el.setAttribute('data-tooltip', 'Copied!'); setTimeout(() =&gt; $el.setAttribute('data-tooltip', 'Copy link to this element'), 2000)" aria-label="Copy link to this element" class="headerlink" data-tooltip="Copy link to this element" href="#listener"><svg height="1em" viewbox="0 0 24 24" width="1em" xmlns="http://www.w3.org/2000/svg"><path d="M3.9 12c0-1.71 1.39-3.1 3.1-3.1h4V7H7c-2.76 0-5 2.24-5 5s2.24 5 5 5h4v-1.9H7c-1.71 0-3.1-1.39-3.1-3.1zM8 13h8v-2H8v2zm9-6h-4v1.9h4c1.71 0 3.1 1.39 3.1 3.1s-1.39 3.1-3.1 3.1h-4V17h4c2.76 0 5-2.24 5-5s-2.24-5-5-5z"></path></svg></a></h1>
<p>Listener is a top level primitive in Arch, which simplifies the configuration required to bind incoming
<p><strong>Listener</strong> is a top level primitive in Arch, which simplifies the configuration required to bind incoming
connections from downstream clients, and for egress connections to LLMs (hosted or API)</p>
<p>Arch builds on Envoys Listener subsystem to streamline connection managemet for developers. Arch minimizes
the complexity of Envoys listener setup by using best-practices and exposing only essential settings,
@ -165,33 +165,33 @@ simplification ensures that connections are secure, reliable, and optimized for
<p>Developers can configure Arch to accept connections from downstream clients. A downstream listener acts as the
primary entry point for incoming traffic, handling initial connection setup, including network filtering, gurdrails,
and additional network security checks. For more details on prompt security and safety,
see <a class="reference internal" href="prompt.html#arch-overview-prompt-handling"><span class="std std-ref">here</span></a></p>
see <a class="reference internal" href="prompt.html#arch-overview-prompt-handling"><span class="std std-ref">here</span></a>.</p>
</section>
<section id="upstream-egress">
<h2>Upstream (Egress)<a @click.prevent="window.navigator.clipboard.writeText($el.href); $el.setAttribute('data-tooltip', 'Copied!'); setTimeout(() =&gt; $el.setAttribute('data-tooltip', 'Copy link to this element'), 2000)" aria-label="Copy link to this element" class="headerlink" data-tooltip="Copy link to this element" href="#upstream-egress" x-intersect.margin.0%.0%.-70%.0%="activeSection = '#upstream-egress'"><svg height="1em" viewbox="0 0 24 24" width="1em" xmlns="http://www.w3.org/2000/svg"><path d="M3.9 12c0-1.71 1.39-3.1 3.1-3.1h4V7H7c-2.76 0-5 2.24-5 5s2.24 5 5 5h4v-1.9H7c-1.71 0-3.1-1.39-3.1-3.1zM8 13h8v-2H8v2zm9-6h-4v1.9h4c1.71 0 3.1 1.39 3.1 3.1s-1.39 3.1-3.1 3.1h-4V17h4c2.76 0 5-2.24 5-5s-2.24-5-5-5z"></path></svg></a></h2>
<p>Arch automatically configures a listener to route requests from your application to upstream LLM API providers (or hosts).
When you start Arch, it creates a listener for egress traffic based on the presence of the <code class="docutils literal notranslate"><span class="pre">llm_providers</span></code> configuration
section in the <code class="docutils literal notranslate"><span class="pre">prompt_config.yml</span></code> file. Arch binds itself to a local address such as <code class="docutils literal notranslate"><span class="pre">127.0.0.1:9000/v1</span></code> or a DNS-based
address like <code class="docutils literal notranslate"><span class="pre">arch.local:9000/v1</span></code> for outgoing traffic. For more details on LLM providers, read <a class="reference internal" href="../llm_provider.html#llm-provider"><span class="std std-ref">here</span></a></p>
When you start Arch, it creates a listener for egress traffic based on the presence of the <code class="docutils literal notranslate"><span class="pre">listener</span></code> configuration
section in the configuration file. Arch binds itself to a local address such as <code class="docutils literal notranslate"><span class="pre">127.0.0.1:9000/v1</span></code> or a DNS-based
address like <code class="docutils literal notranslate"><span class="pre">arch.local:9000/v1</span></code> for outgoing traffic. For more details on LLM providers, read <a class="reference internal" href="../llm_provider.html#llm-provider"><span class="std std-ref">here</span></a>.</p>
</section>
<section id="configure-listener">
<h2>Configure Listener<a @click.prevent="window.navigator.clipboard.writeText($el.href); $el.setAttribute('data-tooltip', 'Copied!'); setTimeout(() =&gt; $el.setAttribute('data-tooltip', 'Copy link to this element'), 2000)" aria-label="Copy link to this element" class="headerlink" data-tooltip="Copy link to this element" href="#configure-listener" x-intersect.margin.0%.0%.-70%.0%="activeSection = '#configure-listener'"><svg height="1em" viewbox="0 0 24 24" width="1em" xmlns="http://www.w3.org/2000/svg"><path d="M3.9 12c0-1.71 1.39-3.1 3.1-3.1h4V7H7c-2.76 0-5 2.24-5 5s2.24 5 5 5h4v-1.9H7c-1.71 0-3.1-1.39-3.1-3.1zM8 13h8v-2H8v2zm9-6h-4v1.9h4c1.71 0 3.1 1.39 3.1 3.1s-1.39 3.1-3.1 3.1h-4V17h4c2.76 0 5-2.24 5-5s-2.24-5-5-5z"></path></svg></a></h2>
<p>To configure a Downstream (Ingress) Listner, simply add the <code class="docutils literal notranslate"><span class="pre">listener</span></code> directive to your <code class="docutils literal notranslate"><span class="pre">prompt_config.yml</span></code> file:</p>
<p>To configure a Downstream (Ingress) Listner, simply add the <code class="docutils literal notranslate"><span class="pre">listener</span></code> directive to your configuration file:</p>
<div class="literal-block-wrapper docutils container" id="id1">
<div class="code-block-caption"><span class="caption-text">Example Configuration</span><a @click.prevent="window.navigator.clipboard.writeText($el.href); $el.setAttribute('data-tooltip', 'Copied!'); setTimeout(() =&gt; $el.setAttribute('data-tooltip', 'Copy link to this element'), 2000)" aria-label="Copy link to this element" class="headerlink" data-tooltip="Copy link to this element" href="#id1"><svg height="1em" viewbox="0 0 24 24" width="1em" xmlns="http://www.w3.org/2000/svg"><path d="M3.9 12c0-1.71 1.39-3.1 3.1-3.1h4V7H7c-2.76 0-5 2.24-5 5s2.24 5 5 5h4v-1.9H7c-1.71 0-3.1-1.39-3.1-3.1zM8 13h8v-2H8v2zm9-6h-4v1.9h4c1.71 0 3.1 1.39 3.1 3.1s-1.39 3.1-3.1 3.1h-4V17h4c2.76 0 5-2.24 5-5s-2.24-5-5-5z"></path></svg></a></div>
<div class="highlight-yaml notranslate"><div class="highlight"><pre><span></span><code><span id="line-1"><span class="linenos"> 1</span><span class="nt">version</span><span class="p">:</span><span class="w"> </span><span class="s">"0.1-beta"</span>
</span><span id="line-2"><mark><span class="linenos"> 2</span>
</mark></span><span id="line-3"><mark><span class="linenos"> 3</span><span class="nt">listener</span><span class="p">:</span>
<div class="highlight-yaml notranslate"><div class="highlight"><pre><span></span><code><span id="line-1"><span class="linenos"> 1</span><span class="nt">version</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">v0.1</span>
</span><span id="line-2"><span class="linenos"> 2</span>
</span><span id="line-3"><mark><span class="linenos"> 3</span><span class="nt">listener</span><span class="p">:</span>
</mark></span><span id="line-4"><mark><span class="linenos"> 4</span><span class="w"> </span><span class="nt">address</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">0.0.0.0</span><span class="w"> </span><span class="c1"># or 127.0.0.1</span>
</mark></span><span id="line-5"><mark><span class="linenos"> 5</span><span class="w"> </span><span class="nt">port</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">10000</span>
</mark></span><span id="line-6"><span class="linenos"> 6</span><span class="w"> </span><span class="c1"># Defines how Arch should parse the content from application/json or text/pain Content-type in the http request</span>
</span><span id="line-7"><span class="linenos"> 7</span><span class="w"> </span><span class="nt">message_format</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">huggingface</span>
</span><span id="line-8"><span class="linenos"> 8</span>
</mark></span><span id="line-6"><mark><span class="linenos"> 6</span><span class="w"> </span><span class="c1"># Defines how Arch should parse the content from application/json or text/pain Content-type in the http request</span>
</mark></span><span id="line-7"><mark><span class="linenos"> 7</span><span class="w"> </span><span class="nt">message_format</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">huggingface</span>
</mark></span><span id="line-8"><span class="linenos"> 8</span>
</span><span id="line-9"><span class="linenos"> 9</span><span class="c1"># Centralized way to manage LLMs, manage keys, retry logic, failover and limits in a central way</span>
</span><span id="line-10"><span class="linenos">10</span><span class="nt">llm_providers</span><span class="p">:</span>
</span><span id="line-11"><span class="linenos">11</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="s">"OpenAI"</span>
</span><span id="line-12"><span class="linenos">12</span><span class="w"> </span><span class="nt">provider</span><span class="p">:</span><span class="w"> </span><span class="s">"openai"</span>
</span><span id="line-13"><span class="linenos">13</span><span class="w"> </span><span class="nt">access_key</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">$OPENAI_API_KEY</span>
</span><span id="line-11"><span class="linenos">11</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">OpenAI</span>
</span><span id="line-12"><span class="linenos">12</span><span class="w"> </span><span class="nt">provider</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">openai</span>
</span><span id="line-13"><span class="linenos">13</span><span class="w"> </span><span class="nt">access_key</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">OPENAI_API_KEY</span>
</span><span id="line-14"><span class="linenos">14</span><span class="w"> </span><span class="nt">model</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">gpt-4o</span>
</span><span id="line-15"><span class="linenos">15</span><span class="w"> </span><span class="nt">default</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">true</span>
</span><span id="line-16"><span class="linenos">16</span><span class="w"> </span><span class="nt">stream</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">true</span>
@ -212,8 +212,8 @@ address like <code class="docutils literal notranslate"><span class="pre">arch.l
</a>
</div>
<div class="ml-auto">
<a class="inline-flex items-center justify-center rounded-md text-sm font-medium transition-colors border border-input hover:bg-accent hover:text-accent-foreground py-2 px-4" href="model_serving.html">
Model Serving
<a class="inline-flex items-center justify-center rounded-md text-sm font-medium transition-colors border border-input hover:bg-accent hover:text-accent-foreground py-2 px-4" href="prompt.html">
Prompts
<svg class="ml-2 h-4 w-4" fill="none" height="24" stroke="currentColor" stroke-linecap="round" stroke-linejoin="round" stroke-width="2" viewbox="0 0 24 24" width="24" xmlns="http://www.w3.org/2000/svg">
<polyline points="9 18 15 12 9 6"></polyline>
</svg>

View file

@ -18,8 +18,8 @@
<link href="./docs/concepts/tech_overview/model_serving.html" rel="canonical"/>
<link href="../../_static/favicon.ico" rel="icon"/>
<link href="../../search.html" rel="search" title="Search"/>
<link href="prompt.html" rel="next" title="Prompt"/>
<link href="listener.html" rel="prev" title="Listener"/>
<link href="request_lifecycle.html" rel="next" title="Request Lifecycle"/>
<link href="prompt.html" rel="prev" title="Prompts"/>
<script>
<!-- Prevent Flash of wrong theme -->
const userPreference = localStorage.getItem('darkMode');
@ -101,9 +101,10 @@
<li class="toctree-l2"><a class="reference internal" href="terminology.html">Terminology</a></li>
<li class="toctree-l2"><a class="reference internal" href="threading_model.html">Threading Model</a></li>
<li class="toctree-l2"><a class="reference internal" href="listener.html">Listener</a></li>
<li class="toctree-l2"><a class="reference internal" href="prompt.html">Prompts</a></li>
<li class="toctree-l2 current"><a class="current reference internal" href="#">Model Serving</a></li>
<li class="toctree-l2"><a class="reference internal" href="prompt.html">Prompt</a></li>
<li class="toctree-l2"><a class="reference internal" href="request_lifecycle.html">Request Lifecycle</a></li>
<li class="toctree-l2"><a class="reference internal" href="error_target.html">Error Target</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="../llm_provider.html">LLM Provider</a></li>
@ -128,7 +129,6 @@
<p class="caption" role="heading"><span class="caption-text">Resources</span></p>
<ul>
<li class="toctree-l1"><a class="reference internal" href="../../resources/configuration_reference.html">Configuration Reference</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../resources/error_target.html">Error Targets</a></li>
</ul>
</nav>
</div>
@ -153,15 +153,14 @@
</nav>
<div id="content" role="main">
<section id="model-serving">
<span id="arch-model-serving"></span><h1>Model Serving<a @click.prevent="window.navigator.clipboard.writeText($el.href); $el.setAttribute('data-tooltip', 'Copied!'); setTimeout(() =&gt; $el.setAttribute('data-tooltip', 'Copy link to this element'), 2000)" aria-label="Copy link to this element" class="headerlink" data-tooltip="Copy link to this element" href="#model-serving"><svg height="1em" viewbox="0 0 24 24" width="1em" xmlns="http://www.w3.org/2000/svg"><path d="M3.9 12c0-1.71 1.39-3.1 3.1-3.1h4V7H7c-2.76 0-5 2.24-5 5s2.24 5 5 5h4v-1.9H7c-1.71 0-3.1-1.39-3.1-3.1zM8 13h8v-2H8v2zm9-6h-4v1.9h4c1.71 0 3.1 1.39 3.1 3.1s-1.39 3.1-3.1 3.1h-4V17h4c2.76 0 5-2.24 5-5s-2.24-5-5-5z"></path></svg></a></h1>
<p>Arch is a set of <strong>two</strong> self-contained processes that are designed to run alongside your application
<span id="id1"></span><h1>Model Serving<a @click.prevent="window.navigator.clipboard.writeText($el.href); $el.setAttribute('data-tooltip', 'Copied!'); setTimeout(() =&gt; $el.setAttribute('data-tooltip', 'Copy link to this element'), 2000)" aria-label="Copy link to this element" class="headerlink" data-tooltip="Copy link to this element" href="#model-serving"><svg height="1em" viewbox="0 0 24 24" width="1em" xmlns="http://www.w3.org/2000/svg"><path d="M3.9 12c0-1.71 1.39-3.1 3.1-3.1h4V7H7c-2.76 0-5 2.24-5 5s2.24 5 5 5h4v-1.9H7c-1.71 0-3.1-1.39-3.1-3.1zM8 13h8v-2H8v2zm9-6h-4v1.9h4c1.71 0 3.1 1.39 3.1 3.1s-1.39 3.1-3.1 3.1h-4V17h4c2.76 0 5-2.24 5-5s-2.24-5-5-5z"></path></svg></a></h1>
<p>Arch is a set of <cite>two</cite> self-contained processes that are designed to run alongside your application
servers (or on a separate host connected via a network). The first process is designated to manage low-level
networking and HTTP related comcerns, and the other process is for <strong>model serving</strong>, which helps Arch make
networking and HTTP related comcerns, and the other process is for model serving, which helps Arch make
intelligent decisions about the incoming prompts. The model server is designed to call the purpose-built
LLMs in Arch.</p>
<a class="reference internal image-reference" href="../../_images/arch-system-architecture.jpg"><img alt="../../_images/arch-system-architecture.jpg" class="align-center" src="../../_images/arch-system-architecture.jpg" style="width: 50%;"/>
<a class="reference internal image-reference" href="../../_images/arch-system-architecture.jpg"><img alt="../../_images/arch-system-architecture.jpg" class="align-center" src="../../_images/arch-system-architecture.jpg" style="width: 40%;"/>
</a>
<hr class="docutils"/>
<p>Arch is designed to be deployed in your cloud VPC, on a on-premises host, and can work on devices that dont
have a GPU. Note, GPU devices are need for fast and cost-efficient use, so that Arch (model server, specifically)
can process prompts quickly and forward control back to the applicaton host. There are three modes in which Arch
@ -176,11 +175,11 @@ might not be available.</p>
</div>
</section>
<section id="local-serving-gpu-fast">
<h2>Local Serving (GPU- Fast)<a @click.prevent="window.navigator.clipboard.writeText($el.href); $el.setAttribute('data-tooltip', 'Copied!'); setTimeout(() =&gt; $el.setAttribute('data-tooltip', 'Copy link to this element'), 2000)" aria-label="Copy link to this element" class="headerlink" data-tooltip="Copy link to this element" href="#local-serving-gpu-fast" x-intersect.margin.0%.0%.-70%.0%="activeSection = '#local-serving-gpu-fast'"><svg height="1em" viewbox="0 0 24 24" width="1em" xmlns="http://www.w3.org/2000/svg"><path d="M3.9 12c0-1.71 1.39-3.1 3.1-3.1h4V7H7c-2.76 0-5 2.24-5 5s2.24 5 5 5h4v-1.9H7c-1.71 0-3.1-1.39-3.1-3.1zM8 13h8v-2H8v2zm9-6h-4v1.9h4c1.71 0 3.1 1.39 3.1 3.1s-1.39 3.1-3.1 3.1h-4V17h4c2.76 0 5-2.24 5-5s-2.24-5-5-5z"></path></svg></a></h2>
<h2>Local Serving (GPU - Fast)<a @click.prevent="window.navigator.clipboard.writeText($el.href); $el.setAttribute('data-tooltip', 'Copied!'); setTimeout(() =&gt; $el.setAttribute('data-tooltip', 'Copy link to this element'), 2000)" aria-label="Copy link to this element" class="headerlink" data-tooltip="Copy link to this element" href="#local-serving-gpu-fast" x-intersect.margin.0%.0%.-70%.0%="activeSection = '#local-serving-gpu-fast'"><svg height="1em" viewbox="0 0 24 24" width="1em" xmlns="http://www.w3.org/2000/svg"><path d="M3.9 12c0-1.71 1.39-3.1 3.1-3.1h4V7H7c-2.76 0-5 2.24-5 5s2.24 5 5 5h4v-1.9H7c-1.71 0-3.1-1.39-3.1-3.1zM8 13h8v-2H8v2zm9-6h-4v1.9h4c1.71 0 3.1 1.39 3.1 3.1s-1.39 3.1-3.1 3.1h-4V17h4c2.76 0 5-2.24 5-5s-2.24-5-5-5z"></path></svg></a></h2>
<p>The following bash commands enable you to configure the model server subsystem in Arch to run locally on the
machine and utilize the GPU available for fast inference across all model use cases, including function calling
guardails, etc.</p>
<div class="highlight-console notranslate"><div class="highlight"><pre><span></span><code><span id="line-1"><span class="gp">$ </span>archgw<span class="w"> </span>up<span class="w"> </span>--local
<div class="highlight-console notranslate"><div class="highlight"><pre><span></span><code><span id="line-1"><span class="gp">$ </span>archgw<span class="w"> </span>up<span class="w"> </span>--local-gpu
</span></code></pre></div>
</div>
</section>
@ -202,16 +201,16 @@ how to generate API keys for model serving</p>
</section>
</div><div class="flex justify-between items-center pt-6 mt-12 border-t border-border gap-4">
<div class="mr-auto">
<a class="inline-flex items-center justify-center rounded-md text-sm font-medium transition-colors border border-input hover:bg-accent hover:text-accent-foreground py-2 px-4" href="listener.html">
<a class="inline-flex items-center justify-center rounded-md text-sm font-medium transition-colors border border-input hover:bg-accent hover:text-accent-foreground py-2 px-4" href="prompt.html">
<svg class="mr-2 h-4 w-4" fill="none" height="24" stroke="currentColor" stroke-linecap="round" stroke-linejoin="round" stroke-width="2" viewbox="0 0 24 24" width="24" xmlns="http://www.w3.org/2000/svg">
<polyline points="15 18 9 12 15 6"></polyline>
</svg>
Listener
Prompts
</a>
</div>
<div class="ml-auto">
<a class="inline-flex items-center justify-center rounded-md text-sm font-medium transition-colors border border-input hover:bg-accent hover:text-accent-foreground py-2 px-4" href="prompt.html">
Prompt
<a class="inline-flex items-center justify-center rounded-md text-sm font-medium transition-colors border border-input hover:bg-accent hover:text-accent-foreground py-2 px-4" href="request_lifecycle.html">
Request Lifecycle
<svg class="ml-2 h-4 w-4" fill="none" height="24" stroke="currentColor" stroke-linecap="round" stroke-linejoin="round" stroke-width="2" viewbox="0 0 24 24" width="24" xmlns="http://www.w3.org/2000/svg">
<polyline points="9 18 15 12 9 6"></polyline>
</svg>
@ -221,7 +220,7 @@ how to generate API keys for model serving</p>
<div class="sticky top-16 -mt-10 max-h-[calc(100vh-5rem)] overflow-y-auto pt-6 space-y-2"><p class="font-medium">On this page</p>
<ul>
<li><a :data-current="activeSection === '#local-serving-cpu-moderate'" class="reference internal" href="#local-serving-cpu-moderate">Local Serving (CPU - Moderate)</a></li>
<li><a :data-current="activeSection === '#local-serving-gpu-fast'" class="reference internal" href="#local-serving-gpu-fast">Local Serving (GPU- Fast)</a></li>
<li><a :data-current="activeSection === '#local-serving-gpu-fast'" class="reference internal" href="#local-serving-gpu-fast">Local Serving (GPU - Fast)</a></li>
<li><a :data-current="activeSection === '#cloud-serving-gpu-blazing-fast'" class="reference internal" href="#cloud-serving-gpu-blazing-fast">Cloud Serving (GPU - Blazing Fast)</a></li>
</ul>
</div>

View file

@ -7,9 +7,9 @@
<meta content="white" media="(prefers-color-scheme: light)" name="theme-color"/>
<meta content="black" media="(prefers-color-scheme: dark)" name="theme-color"/>
<meta content="width=device-width, initial-scale=1" name="viewport"/>
<title>Prompt | Arch Docs v0.1</title>
<meta content="Prompt | Arch Docs v0.1" property="og:title"/>
<meta content="Prompt | Arch Docs v0.1" name="twitter:title"/>
<title>Prompts | Arch Docs v0.1</title>
<meta content="Prompts | Arch Docs v0.1" property="og:title"/>
<meta content="Prompts | Arch Docs v0.1" name="twitter:title"/>
<link href="../../_static/pygments.css?v=75ebff74" rel="stylesheet" type="text/css"/>
<link href="../../_static/theme.css?v=edd7d3d2" rel="stylesheet" type="text/css"/>
<link href="../../_static/_static/custom.css" rel="stylesheet" type="text/css"/>
@ -18,8 +18,8 @@
<link href="./docs/concepts/tech_overview/prompt.html" rel="canonical"/>
<link href="../../_static/favicon.ico" rel="icon"/>
<link href="../../search.html" rel="search" title="Search"/>
<link href="request_lifecycle.html" rel="next" title="Request Lifecycle"/>
<link href="model_serving.html" rel="prev" title="Model Serving"/>
<link href="model_serving.html" rel="next" title="Model Serving"/>
<link href="listener.html" rel="prev" title="Listener"/>
<script>
<!-- Prevent Flash of wrong theme -->
const userPreference = localStorage.getItem('darkMode');
@ -101,9 +101,10 @@
<li class="toctree-l2"><a class="reference internal" href="terminology.html">Terminology</a></li>
<li class="toctree-l2"><a class="reference internal" href="threading_model.html">Threading Model</a></li>
<li class="toctree-l2"><a class="reference internal" href="listener.html">Listener</a></li>
<li class="toctree-l2 current"><a class="current reference internal" href="#">Prompts</a></li>
<li class="toctree-l2"><a class="reference internal" href="model_serving.html">Model Serving</a></li>
<li class="toctree-l2 current"><a class="current reference internal" href="#">Prompt</a></li>
<li class="toctree-l2"><a class="reference internal" href="request_lifecycle.html">Request Lifecycle</a></li>
<li class="toctree-l2"><a class="reference internal" href="error_target.html">Error Target</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="../llm_provider.html">LLM Provider</a></li>
@ -128,7 +129,6 @@
<p class="caption" role="heading"><span class="caption-text">Resources</span></p>
<ul>
<li class="toctree-l1"><a class="reference internal" href="../../resources/configuration_reference.html">Configuration Reference</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../resources/error_target.html">Error Targets</a></li>
</ul>
</nav>
</div>
@ -149,20 +149,19 @@
</svg>
</a>
<div class="mr-1">/</div><a class="hover:text-foreground overflow-hidden text-ellipsis whitespace-nowrap" href="tech_overview.html">Tech Overview</a>
<div class="mr-1">/</div><span aria-current="page" class="font-medium text-foreground overflow-hidden text-ellipsis whitespace-nowrap">Prompt</span>
<div class="mr-1">/</div><span aria-current="page" class="font-medium text-foreground overflow-hidden text-ellipsis whitespace-nowrap">Prompts</span>
</nav>
<div id="content" role="main">
<section id="prompt">
<span id="arch-overview-prompt-handling"></span><h1>Prompt<a @click.prevent="window.navigator.clipboard.writeText($el.href); $el.setAttribute('data-tooltip', 'Copied!'); setTimeout(() =&gt; $el.setAttribute('data-tooltip', 'Copy link to this element'), 2000)" aria-label="Copy link to this element" class="headerlink" data-tooltip="Copy link to this element" href="#prompt"><svg height="1em" viewbox="0 0 24 24" width="1em" xmlns="http://www.w3.org/2000/svg"><path d="M3.9 12c0-1.71 1.39-3.1 3.1-3.1h4V7H7c-2.76 0-5 2.24-5 5s2.24 5 5 5h4v-1.9H7c-1.71 0-3.1-1.39-3.1-3.1zM8 13h8v-2H8v2zm9-6h-4v1.9h4c1.71 0 3.1 1.39 3.1 3.1s-1.39 3.1-3.1 3.1h-4V17h4c2.76 0 5-2.24 5-5s-2.24-5-5-5z"></path></svg></a></h1>
<section id="prompts">
<span id="arch-overview-prompt-handling"></span><h1>Prompts<a @click.prevent="window.navigator.clipboard.writeText($el.href); $el.setAttribute('data-tooltip', 'Copied!'); setTimeout(() =&gt; $el.setAttribute('data-tooltip', 'Copy link to this element'), 2000)" aria-label="Copy link to this element" class="headerlink" data-tooltip="Copy link to this element" href="#prompts"><svg height="1em" viewbox="0 0 24 24" width="1em" xmlns="http://www.w3.org/2000/svg"><path d="M3.9 12c0-1.71 1.39-3.1 3.1-3.1h4V7H7c-2.76 0-5 2.24-5 5s2.24 5 5 5h4v-1.9H7c-1.71 0-3.1-1.39-3.1-3.1zM8 13h8v-2H8v2zm9-6h-4v1.9h4c1.71 0 3.1 1.39 3.1 3.1s-1.39 3.1-3.1 3.1h-4V17h4c2.76 0 5-2.24 5-5s-2.24-5-5-5z"></path></svg></a></h1>
<p>Archs primary design point is to securely accept, process and handle prompts. To do that effectively,
Arch relies on Envoys HTTP <a class="reference external" href="https://www.envoyproxy.io/docs/envoy/v1.31.2/intro/arch_overview/http/http_connection_management" rel="nofollow noopener">connection management<svg fill="currentColor" height="1em" stroke="none" viewbox="0 96 960 960" width="1em" xmlns="http://www.w3.org/2000/svg"><path d="M188 868q-11-11-11-28t11-28l436-436H400q-17 0-28.5-11.5T360 336q0-17 11.5-28.5T400 296h320q17 0 28.5 11.5T760 336v320q0 17-11.5 28.5T720 696q-17 0-28.5-11.5T680 656V432L244 868q-11 11-28 11t-28-11Z"></path></svg></a>,
subsystem and its <strong>prompt handler</strong> subsystem engineered with purpose-built LLMs to
implement critical functionality on behalf of developers so that you can stay focused on business logic.</p>
<div class="admonition note">
<p class="admonition-title">Note</p>
<p>Archs <strong>prompt handler</strong> subsystem interacts with the <strong>model</strong> subsytem through Envoys cluster manager
system to ensure robust, resilient and fault-tolerant experience in managing incoming prompts. Read more
about the <a class="reference internal" href="model_serving.html#arch-model-serving"><span class="std std-ref">model subsystem</span></a> and how the LLMs are hosted in Arch.</p>
<p>Archs <strong>prompt handler</strong> subsystem interacts with the <strong>model subsytem</strong> through Envoys cluster manager system to ensure robust, resilient and fault-tolerant experience in managing incoming prompts.</p>
<div class="admonition seealso">
<p class="admonition-title">See also</p>
<p>Read more about the <a class="reference internal" href="model_serving.html#model-serving"><span class="std std-ref">model subsystem</span></a> and how the LLMs are hosted in Arch.</p>
</div>
<section id="messages">
<h2>Messages<a @click.prevent="window.navigator.clipboard.writeText($el.href); $el.setAttribute('data-tooltip', 'Copied!'); setTimeout(() =&gt; $el.setAttribute('data-tooltip', 'Copy link to this element'), 2000)" aria-label="Copy link to this element" class="headerlink" data-tooltip="Copy link to this element" href="#messages" x-intersect.margin.0%.0%.-70%.0%="activeSection = '#messages'"><svg height="1em" viewbox="0 0 24 24" width="1em" xmlns="http://www.w3.org/2000/svg"><path d="M3.9 12c0-1.71 1.39-3.1 3.1-3.1h4V7H7c-2.76 0-5 2.24-5 5s2.24 5 5 5h4v-1.9H7c-1.71 0-3.1-1.39-3.1-3.1zM8 13h8v-2H8v2zm9-6h-4v1.9h4c1.71 0 3.1 1.39 3.1 3.1s-1.39 3.1-3.1 3.1h-4V17h4c2.76 0 5-2.24 5-5s-2.24-5-5-5z"></path></svg></a></h2>
@ -176,15 +175,15 @@ containing two key-value pairs:</p>
</ul>
</div></blockquote>
</section>
<section id="prompt-guardrails">
<h2>Prompt Guardrails<a @click.prevent="window.navigator.clipboard.writeText($el.href); $el.setAttribute('data-tooltip', 'Copied!'); setTimeout(() =&gt; $el.setAttribute('data-tooltip', 'Copy link to this element'), 2000)" aria-label="Copy link to this element" class="headerlink" data-tooltip="Copy link to this element" href="#prompt-guardrails" x-intersect.margin.0%.0%.-70%.0%="activeSection = '#prompt-guardrails'"><svg height="1em" viewbox="0 0 24 24" width="1em" xmlns="http://www.w3.org/2000/svg"><path d="M3.9 12c0-1.71 1.39-3.1 3.1-3.1h4V7H7c-2.76 0-5 2.24-5 5s2.24 5 5 5h4v-1.9H7c-1.71 0-3.1-1.39-3.1-3.1zM8 13h8v-2H8v2zm9-6h-4v1.9h4c1.71 0 3.1 1.39 3.1 3.1s-1.39 3.1-3.1 3.1h-4V17h4c2.76 0 5-2.24 5-5s-2.24-5-5-5z"></path></svg></a></h2>
<section id="prompt-guard">
<h2>Prompt Guard<a @click.prevent="window.navigator.clipboard.writeText($el.href); $el.setAttribute('data-tooltip', 'Copied!'); setTimeout(() =&gt; $el.setAttribute('data-tooltip', 'Copy link to this element'), 2000)" aria-label="Copy link to this element" class="headerlink" data-tooltip="Copy link to this element" href="#prompt-guard" x-intersect.margin.0%.0%.-70%.0%="activeSection = '#prompt-guard'"><svg height="1em" viewbox="0 0 24 24" width="1em" xmlns="http://www.w3.org/2000/svg"><path d="M3.9 12c0-1.71 1.39-3.1 3.1-3.1h4V7H7c-2.76 0-5 2.24-5 5s2.24 5 5 5h4v-1.9H7c-1.71 0-3.1-1.39-3.1-3.1zM8 13h8v-2H8v2zm9-6h-4v1.9h4c1.71 0 3.1 1.39 3.1 3.1s-1.39 3.1-3.1 3.1h-4V17h4c2.76 0 5-2.24 5-5s-2.24-5-5-5z"></path></svg></a></h2>
<p>Arch is engineered with <a class="reference internal" href="../../guides/prompt_guard.html#prompt-guard"><span class="std std-ref">Arch-Guard</span></a>, an industry leading safety layer, powered by a
compact and high-performimg LLM that monitors incoming prompts to detect and reject jailbreak attempts -
ensuring that unauthorized or harmful behaviors are intercepted early in the process.</p>
<p>To add jailbreak guardrails, see example below:</p>
<div class="literal-block-wrapper docutils container" id="id1">
<div class="code-block-caption"><span class="caption-text">Example Configuration</span><a @click.prevent="window.navigator.clipboard.writeText($el.href); $el.setAttribute('data-tooltip', 'Copied!'); setTimeout(() =&gt; $el.setAttribute('data-tooltip', 'Copy link to this element'), 2000)" aria-label="Copy link to this element" class="headerlink" data-tooltip="Copy link to this element" href="#id1"><svg height="1em" viewbox="0 0 24 24" width="1em" xmlns="http://www.w3.org/2000/svg"><path d="M3.9 12c0-1.71 1.39-3.1 3.1-3.1h4V7H7c-2.76 0-5 2.24-5 5s2.24 5 5 5h4v-1.9H7c-1.71 0-3.1-1.39-3.1-3.1zM8 13h8v-2H8v2zm9-6h-4v1.9h4c1.71 0 3.1 1.39 3.1 3.1s-1.39 3.1-3.1 3.1h-4V17h4c2.76 0 5-2.24 5-5s-2.24-5-5-5z"></path></svg></a></div>
<div class="highlight-yaml notranslate"><div class="highlight"><pre><span></span><code><span id="line-1"><span class="linenos"> 1</span><span class="nt">version</span><span class="p">:</span><span class="w"> </span><span class="s">"0.1-beta"</span>
<div class="highlight-yaml notranslate"><div class="highlight"><pre><span></span><code><span id="line-1"><span class="linenos"> 1</span><span class="nt">version</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">v0.1</span>
</span><span id="line-2"><span class="linenos"> 2</span>
</span><span id="line-3"><span class="linenos"> 3</span><span class="nt">listener</span><span class="p">:</span>
</span><span id="line-4"><span class="linenos"> 4</span><span class="w"> </span><span class="nt">address</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">0.0.0.0</span><span class="w"> </span><span class="c1"># or 127.0.0.1</span>
@ -194,46 +193,27 @@ ensuring that unauthorized or harmful behaviors are intercepted early in the pro
</span><span id="line-8"><span class="linenos"> 8</span>
</span><span id="line-9"><span class="linenos"> 9</span><span class="c1"># Centralized way to manage LLMs, manage keys, retry logic, failover and limits in a central way</span>
</span><span id="line-10"><span class="linenos">10</span><span class="nt">llm_providers</span><span class="p">:</span>
</span><span id="line-11"><span class="linenos">11</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="s">"OpenAI"</span>
</span><span id="line-12"><span class="linenos">12</span><span class="w"> </span><span class="nt">provider</span><span class="p">:</span><span class="w"> </span><span class="s">"openai"</span>
</span><span id="line-13"><span class="linenos">13</span><span class="w"> </span><span class="nt">access_key</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">$OPENAI_API_KEY</span>
</span><span id="line-11"><span class="linenos">11</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">OpenAI</span>
</span><span id="line-12"><span class="linenos">12</span><span class="w"> </span><span class="nt">provider</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">openai</span>
</span><span id="line-13"><span class="linenos">13</span><span class="w"> </span><span class="nt">access_key</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">OPENAI_API_KEY</span>
</span><span id="line-14"><span class="linenos">14</span><span class="w"> </span><span class="nt">model</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">gpt-4o</span>
</span><span id="line-15"><span class="linenos">15</span><span class="w"> </span><span class="nt">default</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">true</span>
</span><span id="line-16"><span class="linenos">16</span><span class="w"> </span><span class="nt">stream</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">true</span>
</span><span id="line-17"><span class="linenos">17</span>
</span><span id="line-18"><span class="linenos">18</span><span class="c1"># default system prompt used by all prompt targets</span>
</span><span id="line-19"><span class="linenos">19</span><span class="nt">system_prompt</span><span class="p">:</span><span class="w"> </span><span class="p p-Indicator">|</span>
</span><span id="line-20"><span class="linenos">20</span><span class="w"> </span><span class="no">You are a network assistant that just offers facts; not advice on manufacturers or purchasing decisions.</span>
</span><span id="line-21"><span class="linenos">21</span>
</span><span id="line-22"><mark><span class="linenos">22</span><span class="nt">prompt_guards</span><span class="p">:</span>
</mark></span><span id="line-23"><mark><span class="linenos">23</span><span class="w"> </span><span class="nt">input_guards</span><span class="p">:</span>
</mark></span><span id="line-24"><mark><span class="linenos">24</span><span class="w"> </span><span class="nt">jailbreak</span><span class="p">:</span>
</mark></span><span id="line-25"><mark><span class="linenos">25</span><span class="w"> </span><span class="nt">on_exception</span><span class="p">:</span>
</mark></span><span id="line-26"><mark><span class="linenos">26</span><span class="w"> </span><span class="nt">message</span><span class="p">:</span><span class="w"> </span><span class="s">"Looks</span><span class="nv"> </span><span class="s">like</span><span class="nv"> </span><span class="s">you're</span><span class="nv"> </span><span class="s">curious</span><span class="nv"> </span><span class="s">about</span><span class="nv"> </span><span class="s">my</span><span class="nv"> </span><span class="s">abilities,</span><span class="nv"> </span><span class="s">but</span><span class="nv"> </span><span class="s">I</span><span class="nv"> </span><span class="s">can</span><span class="nv"> </span><span class="s">only</span><span class="nv"> </span><span class="s">provide</span><span class="nv"> </span><span class="s">assistance</span><span class="nv"> </span><span class="s">within</span><span class="nv"> </span><span class="s">my</span><span class="nv"> </span><span class="s">programmed</span><span class="nv"> </span><span class="s">parameters."</span>
</mark></span><span id="line-27"><span class="linenos">27</span>
</span><span id="line-28"><span class="linenos">28</span><span class="nt">prompt_targets</span><span class="p">:</span>
</span><span id="line-29"><span class="linenos">29</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="s">"reboot_network_device"</span>
</span><span id="line-30"><span class="linenos">30</span><span class="w"> </span><span class="nt">description</span><span class="p">:</span><span class="w"> </span><span class="s">"Helps</span><span class="nv"> </span><span class="s">network</span><span class="nv"> </span><span class="s">operators</span><span class="nv"> </span><span class="s">perform</span><span class="nv"> </span><span class="s">device</span><span class="nv"> </span><span class="s">operations</span><span class="nv"> </span><span class="s">like</span><span class="nv"> </span><span class="s">rebooting</span><span class="nv"> </span><span class="s">a</span><span class="nv"> </span><span class="s">device."</span>
</span><span id="line-31"><span class="linenos">31</span><span class="w"> </span><span class="nt">endpoint</span><span class="p">:</span>
</span><span id="line-32"><span class="linenos">32</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">app_server</span>
</span><span id="line-33"><span class="linenos">33</span><span class="w"> </span><span class="nt">path</span><span class="p">:</span><span class="w"> </span><span class="s">"/agent/action"</span>
</span><span id="line-34"><span class="linenos">34</span><span class="w"> </span><span class="nt">parameters</span><span class="p">:</span>
</span><span id="line-35"><span class="linenos">35</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="s">"device_id"</span>
</span><span id="line-36"><span class="linenos">36</span><span class="w"> </span><span class="c1"># additional type options include: int | float | bool | string | list | dict</span>
</span><span id="line-37"><span class="linenos">37</span><span class="w"> </span><span class="nt">type</span><span class="p">:</span><span class="w"> </span><span class="s">"string"</span>
</span><span id="line-38"><span class="linenos">38</span><span class="w"> </span><span class="nt">description</span><span class="p">:</span><span class="w"> </span><span class="s">"Identifier</span><span class="nv"> </span><span class="s">of</span><span class="nv"> </span><span class="s">the</span><span class="nv"> </span><span class="s">network</span><span class="nv"> </span><span class="s">device</span><span class="nv"> </span><span class="s">to</span><span class="nv"> </span><span class="s">reboot."</span>
</span><span id="line-39"><span class="linenos">39</span><span class="w"> </span><span class="nt">required</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">true</span>
</span><span id="line-40"><span class="linenos">40</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="s">"confirmation"</span>
</span><span id="line-41"><span class="linenos">41</span><span class="w"> </span><span class="nt">type</span><span class="p">:</span><span class="w"> </span><span class="s">"string"</span>
</span><span id="line-42"><span class="linenos">42</span><span class="w"> </span><span class="nt">description</span><span class="p">:</span><span class="w"> </span><span class="s">"Confirmation</span><span class="nv"> </span><span class="s">flag</span><span class="nv"> </span><span class="s">to</span><span class="nv"> </span><span class="s">proceed</span><span class="nv"> </span><span class="s">with</span><span class="nv"> </span><span class="s">reboot."</span>
</span><span id="line-43"><span class="linenos">43</span><span class="w"> </span><span class="nt">default</span><span class="p">:</span><span class="w"> </span><span class="s">"no"</span>
</span><span id="line-44"><span class="linenos">44</span><span class="w"> </span><span class="nt">enum</span><span class="p">:</span><span class="w"> </span><span class="p p-Indicator">[</span><span class="nv">yes</span><span class="p p-Indicator">,</span><span class="w"> </span><span class="nv">no</span><span class="p p-Indicator">]</span>
</span></code></pre></div>
</span><span id="line-19"><span class="linenos">19</span><span class="nt">system_prompt</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">You are a network assistant that just offers facts; not advice on manufacturers or purchasing decisions.</span>
</span><span id="line-20"><span class="linenos">20</span>
</span><span id="line-21"><mark><span class="linenos">21</span><span class="nt">prompt_guards</span><span class="p">:</span>
</mark></span><span id="line-22"><mark><span class="linenos">22</span><span class="w"> </span><span class="nt">input_guards</span><span class="p">:</span>
</mark></span><span id="line-23"><mark><span class="linenos">23</span><span class="w"> </span><span class="nt">jailbreak</span><span class="p">:</span>
</mark></span><span id="line-24"><mark><span class="linenos">24</span><span class="w"> </span><span class="nt">on_exception</span><span class="p">:</span>
</mark></span><span id="line-25"><mark><span class="linenos">25</span><span class="w"> </span><span class="nt">message</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">Looks like you're curious about my abilities, but I can only provide assistance within my programmed parameters.</span>
</mark></span></code></pre></div>
</div>
</div>
<div class="admonition note">
<p class="admonition-title">Note</p>
<p>As a roadmap item, Arch will expose the ability for developers to define custom guardrails via Arch-Guard-v2,
<p>As a roadmap item, Arch will expose the ability for developers to define custom guardrails via Arch-Guard,
and add support for additional safety checks defined by developers and hazardous categories like, violent crimes, privacy, hate,
etc. To offer feedback on our roadmap, please visit our <a class="reference external" href="https://github.com/orgs/katanemo/projects/1" rel="nofollow noopener">github page<svg fill="currentColor" height="1em" stroke="none" viewbox="0 96 960 960" width="1em" xmlns="http://www.w3.org/2000/svg"><path d="M188 868q-11-11-11-28t11-28l436-436H400q-17 0-28.5-11.5T360 336q0-17 11.5-28.5T400 296h320q17 0 28.5 11.5T760 336v320q0 17-11.5 28.5T720 696q-17 0-28.5-11.5T680 656V432L244 868q-11 11-28 11t-28-11Z"></path></svg></a></p>
</div>
@ -247,7 +227,7 @@ when a users intent has changed so that you can build faster, more accurate R
<p>Configuring <code class="docutils literal notranslate"><span class="pre">prompt_targets</span></code> is simple. See example below:</p>
<div class="literal-block-wrapper docutils container" id="id2">
<div class="code-block-caption"><span class="caption-text">Example Configuration</span><a @click.prevent="window.navigator.clipboard.writeText($el.href); $el.setAttribute('data-tooltip', 'Copied!'); setTimeout(() =&gt; $el.setAttribute('data-tooltip', 'Copy link to this element'), 2000)" aria-label="Copy link to this element" class="headerlink" data-tooltip="Copy link to this element" href="#id2"><svg height="1em" viewbox="0 0 24 24" width="1em" xmlns="http://www.w3.org/2000/svg"><path d="M3.9 12c0-1.71 1.39-3.1 3.1-3.1h4V7H7c-2.76 0-5 2.24-5 5s2.24 5 5 5h4v-1.9H7c-1.71 0-3.1-1.39-3.1-3.1zM8 13h8v-2H8v2zm9-6h-4v1.9h4c1.71 0 3.1 1.39 3.1 3.1s-1.39 3.1-3.1 3.1h-4V17h4c2.76 0 5-2.24 5-5s-2.24-5-5-5z"></path></svg></a></div>
<div class="highlight-yaml notranslate"><div class="highlight"><pre><span></span><code><span id="line-1"><span class="linenos"> 1</span><span class="nt">version</span><span class="p">:</span><span class="w"> </span><span class="s">"0.1-beta"</span>
<div class="highlight-yaml notranslate"><div class="highlight"><pre><span></span><code><span id="line-1"><span class="linenos"> 1</span><span class="nt">version</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">v0.1</span>
</span><span id="line-2"><span class="linenos"> 2</span>
</span><span id="line-3"><span class="linenos"> 3</span><span class="nt">listener</span><span class="p">:</span>
</span><span id="line-4"><span class="linenos"> 4</span><span class="w"> </span><span class="nt">address</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">0.0.0.0</span><span class="w"> </span><span class="c1"># or 127.0.0.1</span>
@ -257,70 +237,71 @@ when a users intent has changed so that you can build faster, more accurate R
</span><span id="line-8"><span class="linenos"> 8</span>
</span><span id="line-9"><span class="linenos"> 9</span><span class="c1"># Centralized way to manage LLMs, manage keys, retry logic, failover and limits in a central way</span>
</span><span id="line-10"><span class="linenos">10</span><span class="nt">llm_providers</span><span class="p">:</span>
</span><span id="line-11"><span class="linenos">11</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="s">"OpenAI"</span>
</span><span id="line-12"><span class="linenos">12</span><span class="w"> </span><span class="nt">provider</span><span class="p">:</span><span class="w"> </span><span class="s">"openai"</span>
</span><span id="line-13"><span class="linenos">13</span><span class="w"> </span><span class="nt">access_key</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">$OPENAI_API_KEY</span>
</span><span id="line-11"><span class="linenos">11</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">OpenAI</span>
</span><span id="line-12"><span class="linenos">12</span><span class="w"> </span><span class="nt">provider</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">openai</span>
</span><span id="line-13"><span class="linenos">13</span><span class="w"> </span><span class="nt">access_key</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">OPENAI_API_KEY</span>
</span><span id="line-14"><span class="linenos">14</span><span class="w"> </span><span class="nt">model</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">gpt-4o</span>
</span><span id="line-15"><span class="linenos">15</span><span class="w"> </span><span class="nt">default</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">true</span>
</span><span id="line-16"><span class="linenos">16</span><span class="w"> </span><span class="nt">stream</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">true</span>
</span><span id="line-17"><span class="linenos">17</span>
</span><span id="line-18"><span class="linenos">18</span><span class="c1"># default system prompt used by all prompt targets</span>
</span><span id="line-19"><span class="linenos">19</span><span class="nt">system_prompt</span><span class="p">:</span><span class="w"> </span><span class="p p-Indicator">|</span>
</span><span id="line-20"><span class="linenos">20</span><span class="w"> </span><span class="no">You are a network assistant that just offers facts; not advice on manufacturers or purchasing decisions.</span>
</span><span id="line-21"><span class="linenos">21</span>
</span><span id="line-22"><span class="linenos">22</span><span class="nt">prompt_guards</span><span class="p">:</span>
</span><span id="line-23"><span class="linenos">23</span><span class="w"> </span><span class="nt">input_guards</span><span class="p">:</span>
</span><span id="line-24"><span class="linenos">24</span><span class="w"> </span><span class="nt">jailbreak</span><span class="p">:</span>
</span><span id="line-25"><span class="linenos">25</span><span class="w"> </span><span class="nt">on_exception</span><span class="p">:</span>
</span><span id="line-26"><span class="linenos">26</span><span class="w"> </span><span class="nt">message</span><span class="p">:</span><span class="w"> </span><span class="s">"Looks</span><span class="nv"> </span><span class="s">like</span><span class="nv"> </span><span class="s">you're</span><span class="nv"> </span><span class="s">curious</span><span class="nv"> </span><span class="s">about</span><span class="nv"> </span><span class="s">my</span><span class="nv"> </span><span class="s">abilities,</span><span class="nv"> </span><span class="s">but</span><span class="nv"> </span><span class="s">I</span><span class="nv"> </span><span class="s">can</span><span class="nv"> </span><span class="s">only</span><span class="nv"> </span><span class="s">provide</span><span class="nv"> </span><span class="s">assistance</span><span class="nv"> </span><span class="s">within</span><span class="nv"> </span><span class="s">my</span><span class="nv"> </span><span class="s">programmed</span><span class="nv"> </span><span class="s">parameters."</span>
</span><span id="line-27"><span class="linenos">27</span>
</span><span id="line-28"><span class="linenos">28</span><span class="nt">prompt_targets</span><span class="p">:</span>
</span><span id="line-29"><mark><span class="linenos">29</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="s">"reboot_network_device"</span>
</mark></span><span id="line-30"><mark><span class="linenos">30</span><span class="w"> </span><span class="nt">description</span><span class="p">:</span><span class="w"> </span><span class="s">"Helps</span><span class="nv"> </span><span class="s">network</span><span class="nv"> </span><span class="s">operators</span><span class="nv"> </span><span class="s">perform</span><span class="nv"> </span><span class="s">device</span><span class="nv"> </span><span class="s">operations</span><span class="nv"> </span><span class="s">like</span><span class="nv"> </span><span class="s">rebooting</span><span class="nv"> </span><span class="s">a</span><span class="nv"> </span><span class="s">device."</span>
</mark></span><span id="line-31"><mark><span class="linenos">31</span><span class="w"> </span><span class="nt">endpoint</span><span class="p">:</span>
</mark></span><span id="line-32"><mark><span class="linenos">32</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">app_server</span>
</mark></span><span id="line-33"><mark><span class="linenos">33</span><span class="w"> </span><span class="nt">path</span><span class="p">:</span><span class="w"> </span><span class="s">"/agent/action"</span>
</mark></span><span id="line-34"><mark><span class="linenos">34</span><span class="w"> </span><span class="nt">parameters</span><span class="p">:</span>
</mark></span><span id="line-35"><mark><span class="linenos">35</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="s">"device_id"</span>
</mark></span><span id="line-36"><mark><span class="linenos">36</span><span class="w"> </span><span class="c1"># additional type options include: int | float | bool | string | list | dict</span>
</mark></span><span id="line-37"><mark><span class="linenos">37</span><span class="w"> </span><span class="nt">type</span><span class="p">:</span><span class="w"> </span><span class="s">"string"</span>
</mark></span><span id="line-38"><mark><span class="linenos">38</span><span class="w"> </span><span class="nt">description</span><span class="p">:</span><span class="w"> </span><span class="s">"Identifier</span><span class="nv"> </span><span class="s">of</span><span class="nv"> </span><span class="s">the</span><span class="nv"> </span><span class="s">network</span><span class="nv"> </span><span class="s">device</span><span class="nv"> </span><span class="s">to</span><span class="nv"> </span><span class="s">reboot."</span>
</mark></span><span id="line-39"><span class="linenos">39</span><span class="w"> </span><span class="nt">required</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">true</span>
</span><span id="line-40"><span class="linenos">40</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="s">"confirmation"</span>
</span><span id="line-41"><span class="linenos">41</span><span class="w"> </span><span class="nt">type</span><span class="p">:</span><span class="w"> </span><span class="s">"string"</span>
</span><span id="line-42"><span class="linenos">42</span><span class="w"> </span><span class="nt">description</span><span class="p">:</span><span class="w"> </span><span class="s">"Confirmation</span><span class="nv"> </span><span class="s">flag</span><span class="nv"> </span><span class="s">to</span><span class="nv"> </span><span class="s">proceed</span><span class="nv"> </span><span class="s">with</span><span class="nv"> </span><span class="s">reboot."</span>
</span><span id="line-43"><span class="linenos">43</span><span class="w"> </span><span class="nt">default</span><span class="p">:</span><span class="w"> </span><span class="s">"no"</span>
</span><span id="line-44"><span class="linenos">44</span><span class="w"> </span><span class="nt">enum</span><span class="p">:</span><span class="w"> </span><span class="p p-Indicator">[</span><span class="nv">yes</span><span class="p p-Indicator">,</span><span class="w"> </span><span class="nv">no</span><span class="p p-Indicator">]</span>
</span><span id="line-45"><span class="linenos">45</span>
</span><span id="line-46"><span class="linenos">46</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="s">"information_extraction"</span>
</span><span id="line-47"><span class="linenos">47</span><span class="w"> </span><span class="nt">default</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">true</span>
</span><span id="line-48"><span class="linenos">48</span><span class="w"> </span><span class="nt">description</span><span class="p">:</span><span class="w"> </span><span class="s">"This</span><span class="nv"> </span><span class="s">prompt</span><span class="nv"> </span><span class="s">handles</span><span class="nv"> </span><span class="s">all</span><span class="nv"> </span><span class="s">scenarios</span><span class="nv"> </span><span class="s">that</span><span class="nv"> </span><span class="s">are</span><span class="nv"> </span><span class="s">question</span><span class="nv"> </span><span class="s">and</span><span class="nv"> </span><span class="s">answer</span><span class="nv"> </span><span class="s">in</span><span class="nv"> </span><span class="s">nature.</span><span class="nv"> </span><span class="s">Like</span><span class="nv"> </span><span class="s">summarization,</span><span class="nv"> </span><span class="s">information</span><span class="nv"> </span><span class="s">extraction,</span><span class="nv"> </span><span class="s">etc."</span>
</span><span id="line-49"><span class="linenos">49</span><span class="w"> </span><span class="nt">endpoint</span><span class="p">:</span>
</span><span id="line-50"><span class="linenos">50</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">app_server</span>
</span><span id="line-51"><span class="linenos">51</span><span class="w"> </span><span class="nt">path</span><span class="p">:</span><span class="w"> </span><span class="s">"/agent/summary"</span>
</span><span id="line-52"><span class="linenos">52</span><span class="w"> </span><span class="c1"># Arch uses the default LLM and treats the response from the endpoint as the prompt to send to the LLM</span>
</span><span id="line-53"><span class="linenos">53</span><span class="w"> </span><span class="nt">auto_llm_dispatch_on_response</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">true</span>
</span><span id="line-54"><span class="linenos">54</span><span class="w"> </span><span class="c1"># override system prompt for this prompt target</span>
</span><span id="line-55"><span class="linenos">55</span><span class="w"> </span><span class="nt">system_prompt</span><span class="p">:</span><span class="w"> </span><span class="p p-Indicator">|</span>
</span><span id="line-56"><span class="linenos">56</span><span class="w"> </span><span class="no">You are a helpful information extraction assistant. Use the information that is provided to you.</span>
</span><span id="line-57"><span class="linenos">57</span>
</span><span id="line-58"><span class="linenos">58</span><span class="nt">error_target</span><span class="p">:</span>
</span><span id="line-59"><span class="linenos">59</span><span class="w"> </span><span class="nt">endpoint</span><span class="p">:</span>
</span><span id="line-60"><span class="linenos">60</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">error_target_1</span>
</span><span id="line-61"><span class="linenos">61</span><span class="w"> </span><span class="nt">path</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">/error</span>
</span><span id="line-62"><span class="linenos">62</span>
</span><span id="line-63"><span class="linenos">63</span><span class="c1"># Arch creates a round-robin load balancing between different endpoints, managed via the cluster subsystem.</span>
</span><span id="line-64"><span class="linenos">64</span><span class="nt">endpoints</span><span class="p">:</span>
</span><span id="line-65"><span class="linenos">65</span><span class="w"> </span><span class="nt">app_server</span><span class="p">:</span>
</span><span id="line-66"><span class="linenos">66</span><span class="w"> </span><span class="c1"># value could be ip address or a hostname with port</span>
</span><span id="line-67"><span class="linenos">67</span><span class="w"> </span><span class="c1"># this could also be a list of endpoints for load balancing</span>
</span><span id="line-68"><span class="linenos">68</span><span class="w"> </span><span class="c1"># for example endpoint: [ ip1:port, ip2:port ]</span>
</span><span id="line-69"><span class="linenos">69</span><span class="w"> </span><span class="nt">endpoint</span><span class="p">:</span><span class="w"> </span><span class="s">"127.0.0.1:80"</span>
</span><span id="line-70"><span class="linenos">70</span><span class="w"> </span><span class="c1"># max time to wait for a connection to be established</span>
</span><span id="line-71"><span class="linenos">71</span><span class="w"> </span><span class="nt">connect_timeout</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">0.005s</span>
</span><span id="line-19"><span class="linenos">19</span><span class="nt">system_prompt</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">You are a network assistant that just offers facts; not advice on manufacturers or purchasing decisions.</span>
</span><span id="line-20"><span class="linenos">20</span>
</span><span id="line-21"><span class="linenos">21</span><span class="nt">prompt_guards</span><span class="p">:</span>
</span><span id="line-22"><span class="linenos">22</span><span class="w"> </span><span class="nt">input_guards</span><span class="p">:</span>
</span><span id="line-23"><span class="linenos">23</span><span class="w"> </span><span class="nt">jailbreak</span><span class="p">:</span>
</span><span id="line-24"><span class="linenos">24</span><span class="w"> </span><span class="nt">on_exception</span><span class="p">:</span>
</span><span id="line-25"><span class="linenos">25</span><span class="w"> </span><span class="nt">message</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">Looks like you're curious about my abilities, but I can only provide assistance within my programmed parameters.</span>
</span><span id="line-26"><span class="linenos">26</span>
</span><span id="line-27"><span class="linenos">27</span><span class="nt">prompt_targets</span><span class="p">:</span>
</span><span id="line-28"><span class="linenos">28</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">information_extraction</span>
</span><span id="line-29"><span class="linenos">29</span><span class="w"> </span><span class="nt">default</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">true</span>
</span><span id="line-30"><span class="linenos">30</span><span class="w"> </span><span class="nt">description</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">handel all scenarios that are question and answer in nature. Like summarization, information extraction, etc.</span>
</span><span id="line-31"><span class="linenos">31</span><span class="w"> </span><span class="nt">endpoint</span><span class="p">:</span>
</span><span id="line-32"><span class="linenos">32</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">app_server</span>
</span><span id="line-33"><span class="linenos">33</span><span class="w"> </span><span class="nt">path</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">/agent/summary</span>
</span><span id="line-34"><span class="linenos">34</span><span class="w"> </span><span class="c1"># Arch uses the default LLM and treats the response from the endpoint as the prompt to send to the LLM</span>
</span><span id="line-35"><span class="linenos">35</span><span class="w"> </span><span class="nt">auto_llm_dispatch_on_response</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">true</span>
</span><span id="line-36"><span class="linenos">36</span><span class="w"> </span><span class="c1"># override system prompt for this prompt target</span>
</span><span id="line-37"><span class="linenos">37</span><span class="w"> </span><span class="nt">system_prompt</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">You are a helpful information extraction assistant. Use the information that is provided to you.</span>
</span><span id="line-38"><span class="linenos">38</span>
</span><span id="line-39"><mark><span class="linenos">39</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">reboot_network_device</span>
</mark></span><span id="line-40"><mark><span class="linenos">40</span><span class="w"> </span><span class="nt">description</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">Reboot a specific network device</span>
</mark></span><span id="line-41"><mark><span class="linenos">41</span><span class="w"> </span><span class="nt">endpoint</span><span class="p">:</span>
</mark></span><span id="line-42"><mark><span class="linenos">42</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">app_server</span>
</mark></span><span id="line-43"><mark><span class="linenos">43</span><span class="w"> </span><span class="nt">path</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">/agent/action</span>
</mark></span><span id="line-44"><mark><span class="linenos">44</span><span class="w"> </span><span class="nt">parameters</span><span class="p">:</span>
</mark></span><span id="line-45"><mark><span class="linenos">45</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">device_id</span>
</mark></span><span id="line-46"><mark><span class="linenos">46</span><span class="w"> </span><span class="nt">type</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">str</span>
</mark></span><span id="line-47"><mark><span class="linenos">47</span><span class="w"> </span><span class="nt">description</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">Identifier of the network device to reboot.</span>
</mark></span><span id="line-48"><mark><span class="linenos">48</span><span class="w"> </span><span class="nt">required</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">true</span>
</mark></span><span id="line-49"><mark><span class="linenos">49</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">confirmation</span>
</mark></span><span id="line-50"><mark><span class="linenos">50</span><span class="w"> </span><span class="nt">type</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">bool</span>
</mark></span><span id="line-51"><mark><span class="linenos">51</span><span class="w"> </span><span class="nt">description</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">Confirmation flag to proceed with reboot.</span>
</mark></span><span id="line-52"><mark><span class="linenos">52</span><span class="w"> </span><span class="nt">default</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">false</span>
</mark></span><span id="line-53"><mark><span class="linenos">53</span><span class="w"> </span><span class="nt">enum</span><span class="p">:</span><span class="w"> </span><span class="p p-Indicator">[</span><span class="nv">true</span><span class="p p-Indicator">,</span><span class="w"> </span><span class="nv">false</span><span class="p p-Indicator">]</span>
</mark></span><span id="line-54"><span class="linenos">54</span>
</span><span id="line-55"><span class="linenos">55</span><span class="nt">error_target</span><span class="p">:</span>
</span><span id="line-56"><span class="linenos">56</span><span class="w"> </span><span class="nt">endpoint</span><span class="p">:</span>
</span><span id="line-57"><span class="linenos">57</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">error_target_1</span>
</span><span id="line-58"><span class="linenos">58</span><span class="w"> </span><span class="nt">path</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">/error</span>
</span><span id="line-59"><span class="linenos">59</span>
</span><span id="line-60"><span class="linenos">60</span><span class="c1"># Arch creates a round-robin load balancing between different endpoints, managed via the cluster subsystem.</span>
</span><span id="line-61"><span class="linenos">61</span><span class="nt">endpoints</span><span class="p">:</span>
</span><span id="line-62"><span class="linenos">62</span><span class="w"> </span><span class="nt">app_server</span><span class="p">:</span>
</span><span id="line-63"><span class="linenos">63</span><span class="w"> </span><span class="c1"># value could be ip address or a hostname with port</span>
</span><span id="line-64"><span class="linenos">64</span><span class="w"> </span><span class="c1"># this could also be a list of endpoints for load balancing</span>
</span><span id="line-65"><span class="linenos">65</span><span class="w"> </span><span class="c1"># for example endpoint: [ ip1:port, ip2:port ]</span>
</span><span id="line-66"><span class="linenos">66</span><span class="w"> </span><span class="nt">endpoint</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">127.0.0.1:80</span>
</span><span id="line-67"><span class="linenos">67</span><span class="w"> </span><span class="c1"># max time to wait for a connection to be established</span>
</span><span id="line-68"><span class="linenos">68</span><span class="w"> </span><span class="nt">connect_timeout</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">0.005s</span>
</span></code></pre></div>
</div>
</div>
<div class="admonition seealso">
<p class="admonition-title">See also</p>
<p>Check <a class="reference internal" href="../prompt_target.html#prompt-target"><span class="std std-ref">Prompt Target</span></a> for more details!</p>
</div>
<section id="intent-detection-and-prompt-matching">
<h3>Intent Detection and Prompt Matching:<a @click.prevent="window.navigator.clipboard.writeText($el.href); $el.setAttribute('data-tooltip', 'Copied!'); setTimeout(() =&gt; $el.setAttribute('data-tooltip', 'Copy link to this element'), 2000)" aria-label="Copy link to this element" class="headerlink" data-tooltip="Copy link to this element" href="#intent-detection-and-prompt-matching" x-intersect.margin.0%.0%.-70%.0%="activeSection = '#intent-detection-and-prompt-matching'"><svg height="1em" viewbox="0 0 24 24" width="1em" xmlns="http://www.w3.org/2000/svg"><path d="M3.9 12c0-1.71 1.39-3.1 3.1-3.1h4V7H7c-2.76 0-5 2.24-5 5s2.24 5 5 5h4v-1.9H7c-1.71 0-3.1-1.39-3.1-3.1zM8 13h8v-2H8v2zm9-6h-4v1.9h4c1.71 0 3.1 1.39 3.1 3.1s-1.39 3.1-3.1 3.1h-4V17h4c2.76 0 5-2.24 5-5s-2.24-5-5-5z"></path></svg></a></h3>
<p>Arch uses fast Natural Language Inference (NLI) and embedding approaches to first detect the intent of each
@ -382,28 +363,24 @@ traffic, apply rate limits, and utilize a large set of traffic management capabi
</span><span id="line-14"><span class="nb">print</span><span class="p">(</span><span class="s2">"OpenAI Response:"</span><span class="p">,</span> <span class="n">response</span><span class="o">.</span><span class="n">choices</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span><span class="o">.</span><span class="n">text</span><span class="o">.</span><span class="n">strip</span><span class="p">())</span>
</span></code></pre></div>
</div>
<p>In these examples:</p>
<blockquote>
<div><p>The OpenAI client is used to send traffic directly through the Arch egress proxy to the LLM of your choice, such as OpenAI.
The OpenAI client is configured to route traffic via Arch by setting the proxy to 127.0.0.1:51001, assuming Arch is
running locally and bound to that address and port.</p>
</div></blockquote>
<p>This setup allows you to take advantage of Archs advanced traffic management features while interacting with LLM APIs like OpenAI.</p>
<p>In these examples, the OpenAI client is used to send traffic directly through the Arch egress proxy to the LLM of your choice, such as OpenAI.
The OpenAI client is configured to route traffic via Arch by setting the proxy to <code class="docutils literal notranslate"><span class="pre">127.0.0.1:51001</span></code>, assuming Arch is running locally and bound to that address and port.
This setup allows you to take advantage of Archs advanced traffic management features while interacting with LLM APIs like OpenAI.</p>
</section>
</section>
</section>
</div><div class="flex justify-between items-center pt-6 mt-12 border-t border-border gap-4">
<div class="mr-auto">
<a class="inline-flex items-center justify-center rounded-md text-sm font-medium transition-colors border border-input hover:bg-accent hover:text-accent-foreground py-2 px-4" href="model_serving.html">
<a class="inline-flex items-center justify-center rounded-md text-sm font-medium transition-colors border border-input hover:bg-accent hover:text-accent-foreground py-2 px-4" href="listener.html">
<svg class="mr-2 h-4 w-4" fill="none" height="24" stroke="currentColor" stroke-linecap="round" stroke-linejoin="round" stroke-width="2" viewbox="0 0 24 24" width="24" xmlns="http://www.w3.org/2000/svg">
<polyline points="15 18 9 12 15 6"></polyline>
</svg>
Model Serving
Listener
</a>
</div>
<div class="ml-auto">
<a class="inline-flex items-center justify-center rounded-md text-sm font-medium transition-colors border border-input hover:bg-accent hover:text-accent-foreground py-2 px-4" href="request_lifecycle.html">
Request Lifecycle
<a class="inline-flex items-center justify-center rounded-md text-sm font-medium transition-colors border border-input hover:bg-accent hover:text-accent-foreground py-2 px-4" href="model_serving.html">
Model Serving
<svg class="ml-2 h-4 w-4" fill="none" height="24" stroke="currentColor" stroke-linecap="round" stroke-linejoin="round" stroke-width="2" viewbox="0 0 24 24" width="24" xmlns="http://www.w3.org/2000/svg">
<polyline points="9 18 15 12 9 6"></polyline>
</svg>
@ -413,7 +390,7 @@ running locally and bound to that address and port.</p>
<div class="sticky top-16 -mt-10 max-h-[calc(100vh-5rem)] overflow-y-auto pt-6 space-y-2"><p class="font-medium">On this page</p>
<ul>
<li><a :data-current="activeSection === '#messages'" class="reference internal" href="#messages">Messages</a></li>
<li><a :data-current="activeSection === '#prompt-guardrails'" class="reference internal" href="#prompt-guardrails">Prompt Guardrails</a></li>
<li><a :data-current="activeSection === '#prompt-guard'" class="reference internal" href="#prompt-guard">Prompt Guard</a></li>
<li><a :data-current="activeSection === '#prompt-targets'" class="reference internal" href="#prompt-targets">Prompt Targets</a><ul>
<li><a :data-current="activeSection === '#intent-detection-and-prompt-matching'" class="reference internal" href="#intent-detection-and-prompt-matching">Intent Detection and Prompt Matching:</a></li>
<li><a :data-current="activeSection === '#agentic-apps-via-prompt-targets'" class="reference internal" href="#agentic-apps-via-prompt-targets">Agentic Apps via Prompt Targets</a></li>

View file

@ -18,8 +18,8 @@
<link href="./docs/concepts/tech_overview/request_lifecycle.html" rel="canonical"/>
<link href="../../_static/favicon.ico" rel="icon"/>
<link href="../../search.html" rel="search" title="Search"/>
<link href="../llm_provider.html" rel="next" title="LLM Provider"/>
<link href="prompt.html" rel="prev" title="Prompt"/>
<link href="error_target.html" rel="next" title="Error Target"/>
<link href="model_serving.html" rel="prev" title="Model Serving"/>
<script>
<!-- Prevent Flash of wrong theme -->
const userPreference = localStorage.getItem('darkMode');
@ -101,9 +101,10 @@
<li class="toctree-l2"><a class="reference internal" href="terminology.html">Terminology</a></li>
<li class="toctree-l2"><a class="reference internal" href="threading_model.html">Threading Model</a></li>
<li class="toctree-l2"><a class="reference internal" href="listener.html">Listener</a></li>
<li class="toctree-l2"><a class="reference internal" href="prompt.html">Prompts</a></li>
<li class="toctree-l2"><a class="reference internal" href="model_serving.html">Model Serving</a></li>
<li class="toctree-l2"><a class="reference internal" href="prompt.html">Prompt</a></li>
<li class="toctree-l2 current"><a class="current reference internal" href="#">Request Lifecycle</a></li>
<li class="toctree-l2"><a class="reference internal" href="error_target.html">Error Target</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="../llm_provider.html">LLM Provider</a></li>
@ -128,7 +129,6 @@
<p class="caption" role="heading"><span class="caption-text">Resources</span></p>
<ul>
<li class="toctree-l1"><a class="reference internal" href="../../resources/configuration_reference.html">Configuration Reference</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../resources/error_target.html">Error Targets</a></li>
</ul>
</nav>
</div>
@ -199,7 +199,7 @@ lifecycle. The downstream and upstream HTTP/2 codec lives here.</p></li>
forwarding prompts <code class="docutils literal notranslate"><span class="pre">prompt_targets</span></code> and establishes the lifecycle of any <strong>upstream</strong> connection to a
hosted endpoint that implements domain-specific business logic for incoming promots. This is where knowledge
of targets and endpoint health, load balancing and connection pooling exists.</p></li>
<li><p><a class="reference internal" href="model_serving.html#arch-model-serving"><span class="std std-ref">Model serving subsystem</span></a> which helps Arch make intelligent decisions about the
<li><p><a class="reference internal" href="model_serving.html#model-serving"><span class="std std-ref">Model serving subsystem</span></a> which helps Arch make intelligent decisions about the
incoming prompts. The model server is designed to call the purpose-built LLMs in Arch.</p></li>
</ul>
<p>The three subsystems are bridged with either the HTTP router filter, and the cluster manager subsystems of Envoy.</p>
@ -214,7 +214,7 @@ enables scaling to very high core count CPUs.</p>
<section id="configuration">
<h2>Configuration<a @click.prevent="window.navigator.clipboard.writeText($el.href); $el.setAttribute('data-tooltip', 'Copied!'); setTimeout(() =&gt; $el.setAttribute('data-tooltip', 'Copy link to this element'), 2000)" aria-label="Copy link to this element" class="headerlink" data-tooltip="Copy link to this element" href="#configuration" x-intersect.margin.0%.0%.-70%.0%="activeSection = '#configuration'"><svg height="1em" viewbox="0 0 24 24" width="1em" xmlns="http://www.w3.org/2000/svg"><path d="M3.9 12c0-1.71 1.39-3.1 3.1-3.1h4V7H7c-2.76 0-5 2.24-5 5s2.24 5 5 5h4v-1.9H7c-1.71 0-3.1-1.39-3.1-3.1zM8 13h8v-2H8v2zm9-6h-4v1.9h4c1.71 0 3.1 1.39 3.1 3.1s-1.39 3.1-3.1 3.1h-4V17h4c2.76 0 5-2.24 5-5s-2.24-5-5-5z"></path></svg></a></h2>
<p>Today, only support a static bootstrap configuration file for simplicity today:</p>
<div class="highlight-yaml notranslate"><div class="highlight"><pre><span></span><code><span id="line-1"><span class="nt">version</span><span class="p">:</span><span class="w"> </span><span class="s">"0.1-beta"</span>
<div class="highlight-yaml notranslate"><div class="highlight"><pre><span></span><code><span id="line-1"><span class="nt">version</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">v0.1</span>
</span><span id="line-2">
</span><span id="line-3"><span class="nt">listener</span><span class="p">:</span>
</span><span id="line-4"><span class="w"> </span><span class="nt">address</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">0.0.0.0</span><span class="w"> </span><span class="c1"># or 127.0.0.1</span>
@ -224,67 +224,64 @@ enables scaling to very high core count CPUs.</p>
</span><span id="line-8">
</span><span id="line-9"><span class="c1"># Centralized way to manage LLMs, manage keys, retry logic, failover and limits in a central way</span>
</span><span id="line-10"><span class="nt">llm_providers</span><span class="p">:</span>
</span><span id="line-11"><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="s">"OpenAI"</span>
</span><span id="line-12"><span class="w"> </span><span class="nt">provider</span><span class="p">:</span><span class="w"> </span><span class="s">"openai"</span>
</span><span id="line-13"><span class="w"> </span><span class="nt">access_key</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">$OPENAI_API_KEY</span>
</span><span id="line-11"><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">OpenAI</span>
</span><span id="line-12"><span class="w"> </span><span class="nt">provider</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">openai</span>
</span><span id="line-13"><span class="w"> </span><span class="nt">access_key</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">OPENAI_API_KEY</span>
</span><span id="line-14"><span class="w"> </span><span class="nt">model</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">gpt-4o</span>
</span><span id="line-15"><span class="w"> </span><span class="nt">default</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">true</span>
</span><span id="line-16"><span class="w"> </span><span class="nt">stream</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">true</span>
</span><span id="line-17">
</span><span id="line-18"><span class="c1"># default system prompt used by all prompt targets</span>
</span><span id="line-19"><span class="nt">system_prompt</span><span class="p">:</span><span class="w"> </span><span class="p p-Indicator">|</span>
</span><span id="line-20"><span class="w"> </span><span class="no">You are a network assistant that just offers facts; not advice on manufacturers or purchasing decisions.</span>
</span><span id="line-21">
</span><span id="line-22"><span class="nt">prompt_guards</span><span class="p">:</span>
</span><span id="line-23"><span class="w"> </span><span class="nt">input_guards</span><span class="p">:</span>
</span><span id="line-24"><span class="w"> </span><span class="nt">jailbreak</span><span class="p">:</span>
</span><span id="line-25"><span class="w"> </span><span class="nt">on_exception</span><span class="p">:</span>
</span><span id="line-26"><span class="w"> </span><span class="nt">message</span><span class="p">:</span><span class="w"> </span><span class="s">"Looks</span><span class="nv"> </span><span class="s">like</span><span class="nv"> </span><span class="s">you're</span><span class="nv"> </span><span class="s">curious</span><span class="nv"> </span><span class="s">about</span><span class="nv"> </span><span class="s">my</span><span class="nv"> </span><span class="s">abilities,</span><span class="nv"> </span><span class="s">but</span><span class="nv"> </span><span class="s">I</span><span class="nv"> </span><span class="s">can</span><span class="nv"> </span><span class="s">only</span><span class="nv"> </span><span class="s">provide</span><span class="nv"> </span><span class="s">assistance</span><span class="nv"> </span><span class="s">within</span><span class="nv"> </span><span class="s">my</span><span class="nv"> </span><span class="s">programmed</span><span class="nv"> </span><span class="s">parameters."</span>
</span><span id="line-27">
</span><span id="line-28"><span class="nt">prompt_targets</span><span class="p">:</span>
</span><span id="line-29"><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="s">"reboot_network_device"</span>
</span><span id="line-30"><span class="w"> </span><span class="nt">description</span><span class="p">:</span><span class="w"> </span><span class="s">"Helps</span><span class="nv"> </span><span class="s">network</span><span class="nv"> </span><span class="s">operators</span><span class="nv"> </span><span class="s">perform</span><span class="nv"> </span><span class="s">device</span><span class="nv"> </span><span class="s">operations</span><span class="nv"> </span><span class="s">like</span><span class="nv"> </span><span class="s">rebooting</span><span class="nv"> </span><span class="s">a</span><span class="nv"> </span><span class="s">device."</span>
</span><span id="line-19"><span class="nt">system_prompt</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">You are a network assistant that just offers facts; not advice on manufacturers or purchasing decisions.</span>
</span><span id="line-20">
</span><span id="line-21"><span class="nt">prompt_guards</span><span class="p">:</span>
</span><span id="line-22"><span class="w"> </span><span class="nt">input_guards</span><span class="p">:</span>
</span><span id="line-23"><span class="w"> </span><span class="nt">jailbreak</span><span class="p">:</span>
</span><span id="line-24"><span class="w"> </span><span class="nt">on_exception</span><span class="p">:</span>
</span><span id="line-25"><span class="w"> </span><span class="nt">message</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">Looks like you're curious about my abilities, but I can only provide assistance within my programmed parameters.</span>
</span><span id="line-26">
</span><span id="line-27"><span class="nt">prompt_targets</span><span class="p">:</span>
</span><span id="line-28"><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">information_extraction</span>
</span><span id="line-29"><span class="w"> </span><span class="nt">default</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">true</span>
</span><span id="line-30"><span class="w"> </span><span class="nt">description</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">handel all scenarios that are question and answer in nature. Like summarization, information extraction, etc.</span>
</span><span id="line-31"><span class="w"> </span><span class="nt">endpoint</span><span class="p">:</span>
</span><span id="line-32"><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">app_server</span>
</span><span id="line-33"><span class="w"> </span><span class="nt">path</span><span class="p">:</span><span class="w"> </span><span class="s">"/agent/action"</span>
</span><span id="line-34"><span class="w"> </span><span class="nt">parameters</span><span class="p">:</span>
</span><span id="line-35"><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="s">"device_id"</span>
</span><span id="line-36"><span class="w"> </span><span class="c1"># additional type options include: int | float | bool | string | list | dict</span>
</span><span id="line-37"><span class="w"> </span><span class="nt">type</span><span class="p">:</span><span class="w"> </span><span class="s">"string"</span>
</span><span id="line-38"><span class="w"> </span><span class="nt">description</span><span class="p">:</span><span class="w"> </span><span class="s">"Identifier</span><span class="nv"> </span><span class="s">of</span><span class="nv"> </span><span class="s">the</span><span class="nv"> </span><span class="s">network</span><span class="nv"> </span><span class="s">device</span><span class="nv"> </span><span class="s">to</span><span class="nv"> </span><span class="s">reboot."</span>
</span><span id="line-39"><span class="w"> </span><span class="nt">required</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">true</span>
</span><span id="line-40"><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="s">"confirmation"</span>
</span><span id="line-41"><span class="w"> </span><span class="nt">type</span><span class="p">:</span><span class="w"> </span><span class="s">"string"</span>
</span><span id="line-42"><span class="w"> </span><span class="nt">description</span><span class="p">:</span><span class="w"> </span><span class="s">"Confirmation</span><span class="nv"> </span><span class="s">flag</span><span class="nv"> </span><span class="s">to</span><span class="nv"> </span><span class="s">proceed</span><span class="nv"> </span><span class="s">with</span><span class="nv"> </span><span class="s">reboot."</span>
</span><span id="line-43"><span class="w"> </span><span class="nt">default</span><span class="p">:</span><span class="w"> </span><span class="s">"no"</span>
</span><span id="line-44"><span class="w"> </span><span class="nt">enum</span><span class="p">:</span><span class="w"> </span><span class="p p-Indicator">[</span><span class="nv">yes</span><span class="p p-Indicator">,</span><span class="w"> </span><span class="nv">no</span><span class="p p-Indicator">]</span>
</span><span id="line-45">
</span><span id="line-46"><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="s">"information_extraction"</span>
</span><span id="line-47"><span class="w"> </span><span class="nt">default</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">true</span>
</span><span id="line-48"><span class="w"> </span><span class="nt">description</span><span class="p">:</span><span class="w"> </span><span class="s">"This</span><span class="nv"> </span><span class="s">prompt</span><span class="nv"> </span><span class="s">handles</span><span class="nv"> </span><span class="s">all</span><span class="nv"> </span><span class="s">scenarios</span><span class="nv"> </span><span class="s">that</span><span class="nv"> </span><span class="s">are</span><span class="nv"> </span><span class="s">question</span><span class="nv"> </span><span class="s">and</span><span class="nv"> </span><span class="s">answer</span><span class="nv"> </span><span class="s">in</span><span class="nv"> </span><span class="s">nature.</span><span class="nv"> </span><span class="s">Like</span><span class="nv"> </span><span class="s">summarization,</span><span class="nv"> </span><span class="s">information</span><span class="nv"> </span><span class="s">extraction,</span><span class="nv"> </span><span class="s">etc."</span>
</span><span id="line-49"><span class="w"> </span><span class="nt">endpoint</span><span class="p">:</span>
</span><span id="line-50"><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">app_server</span>
</span><span id="line-51"><span class="w"> </span><span class="nt">path</span><span class="p">:</span><span class="w"> </span><span class="s">"/agent/summary"</span>
</span><span id="line-52"><span class="w"> </span><span class="c1"># Arch uses the default LLM and treats the response from the endpoint as the prompt to send to the LLM</span>
</span><span id="line-53"><span class="w"> </span><span class="nt">auto_llm_dispatch_on_response</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">true</span>
</span><span id="line-54"><span class="w"> </span><span class="c1"># override system prompt for this prompt target</span>
</span><span id="line-55"><span class="w"> </span><span class="nt">system_prompt</span><span class="p">:</span><span class="w"> </span><span class="p p-Indicator">|</span>
</span><span id="line-56"><span class="w"> </span><span class="no">You are a helpful information extraction assistant. Use the information that is provided to you.</span>
</span><span id="line-57">
</span><span id="line-58"><span class="nt">error_target</span><span class="p">:</span>
</span><span id="line-59"><span class="w"> </span><span class="nt">endpoint</span><span class="p">:</span>
</span><span id="line-60"><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">error_target_1</span>
</span><span id="line-61"><span class="w"> </span><span class="nt">path</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">/error</span>
</span><span id="line-62">
</span><span id="line-63"><span class="c1"># Arch creates a round-robin load balancing between different endpoints, managed via the cluster subsystem.</span>
</span><span id="line-64"><span class="nt">endpoints</span><span class="p">:</span>
</span><span id="line-65"><span class="w"> </span><span class="nt">app_server</span><span class="p">:</span>
</span><span id="line-66"><span class="w"> </span><span class="c1"># value could be ip address or a hostname with port</span>
</span><span id="line-67"><span class="w"> </span><span class="c1"># this could also be a list of endpoints for load balancing</span>
</span><span id="line-68"><span class="w"> </span><span class="c1"># for example endpoint: [ ip1:port, ip2:port ]</span>
</span><span id="line-69"><span class="w"> </span><span class="nt">endpoint</span><span class="p">:</span><span class="w"> </span><span class="s">"127.0.0.1:80"</span>
</span><span id="line-70"><span class="w"> </span><span class="c1"># max time to wait for a connection to be established</span>
</span><span id="line-71"><span class="w"> </span><span class="nt">connect_timeout</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">0.005s</span>
</span><span id="line-33"><span class="w"> </span><span class="nt">path</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">/agent/summary</span>
</span><span id="line-34"><span class="w"> </span><span class="c1"># Arch uses the default LLM and treats the response from the endpoint as the prompt to send to the LLM</span>
</span><span id="line-35"><span class="w"> </span><span class="nt">auto_llm_dispatch_on_response</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">true</span>
</span><span id="line-36"><span class="w"> </span><span class="c1"># override system prompt for this prompt target</span>
</span><span id="line-37"><span class="w"> </span><span class="nt">system_prompt</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">You are a helpful information extraction assistant. Use the information that is provided to you.</span>
</span><span id="line-38">
</span><span id="line-39"><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">reboot_network_device</span>
</span><span id="line-40"><span class="w"> </span><span class="nt">description</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">Reboot a specific network device</span>
</span><span id="line-41"><span class="w"> </span><span class="nt">endpoint</span><span class="p">:</span>
</span><span id="line-42"><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">app_server</span>
</span><span id="line-43"><span class="w"> </span><span class="nt">path</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">/agent/action</span>
</span><span id="line-44"><span class="w"> </span><span class="nt">parameters</span><span class="p">:</span>
</span><span id="line-45"><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">device_id</span>
</span><span id="line-46"><span class="w"> </span><span class="nt">type</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">str</span>
</span><span id="line-47"><span class="w"> </span><span class="nt">description</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">Identifier of the network device to reboot.</span>
</span><span id="line-48"><span class="w"> </span><span class="nt">required</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">true</span>
</span><span id="line-49"><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">confirmation</span>
</span><span id="line-50"><span class="w"> </span><span class="nt">type</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">bool</span>
</span><span id="line-51"><span class="w"> </span><span class="nt">description</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">Confirmation flag to proceed with reboot.</span>
</span><span id="line-52"><span class="w"> </span><span class="nt">default</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">false</span>
</span><span id="line-53"><span class="w"> </span><span class="nt">enum</span><span class="p">:</span><span class="w"> </span><span class="p p-Indicator">[</span><span class="nv">true</span><span class="p p-Indicator">,</span><span class="w"> </span><span class="nv">false</span><span class="p p-Indicator">]</span>
</span><span id="line-54">
</span><span id="line-55"><span class="nt">error_target</span><span class="p">:</span>
</span><span id="line-56"><span class="w"> </span><span class="nt">endpoint</span><span class="p">:</span>
</span><span id="line-57"><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">error_target_1</span>
</span><span id="line-58"><span class="w"> </span><span class="nt">path</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">/error</span>
</span><span id="line-59">
</span><span id="line-60"><span class="c1"># Arch creates a round-robin load balancing between different endpoints, managed via the cluster subsystem.</span>
</span><span id="line-61"><span class="nt">endpoints</span><span class="p">:</span>
</span><span id="line-62"><span class="w"> </span><span class="nt">app_server</span><span class="p">:</span>
</span><span id="line-63"><span class="w"> </span><span class="c1"># value could be ip address or a hostname with port</span>
</span><span id="line-64"><span class="w"> </span><span class="c1"># this could also be a list of endpoints for load balancing</span>
</span><span id="line-65"><span class="w"> </span><span class="c1"># for example endpoint: [ ip1:port, ip2:port ]</span>
</span><span id="line-66"><span class="w"> </span><span class="nt">endpoint</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">127.0.0.1:80</span>
</span><span id="line-67"><span class="w"> </span><span class="c1"># max time to wait for a connection to be established</span>
</span><span id="line-68"><span class="w"> </span><span class="nt">connect_timeout</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">0.005s</span>
</span></code></pre></div>
</div>
</section>
@ -374,16 +371,16 @@ processing request headers and then finalized by the HCM during post-request pro
</section>
</div><div class="flex justify-between items-center pt-6 mt-12 border-t border-border gap-4">
<div class="mr-auto">
<a class="inline-flex items-center justify-center rounded-md text-sm font-medium transition-colors border border-input hover:bg-accent hover:text-accent-foreground py-2 px-4" href="prompt.html">
<a class="inline-flex items-center justify-center rounded-md text-sm font-medium transition-colors border border-input hover:bg-accent hover:text-accent-foreground py-2 px-4" href="model_serving.html">
<svg class="mr-2 h-4 w-4" fill="none" height="24" stroke="currentColor" stroke-linecap="round" stroke-linejoin="round" stroke-width="2" viewbox="0 0 24 24" width="24" xmlns="http://www.w3.org/2000/svg">
<polyline points="15 18 9 12 15 6"></polyline>
</svg>
Prompt
Model Serving
</a>
</div>
<div class="ml-auto">
<a class="inline-flex items-center justify-center rounded-md text-sm font-medium transition-colors border border-input hover:bg-accent hover:text-accent-foreground py-2 px-4" href="../llm_provider.html">
LLM Provider
<a class="inline-flex items-center justify-center rounded-md text-sm font-medium transition-colors border border-input hover:bg-accent hover:text-accent-foreground py-2 px-4" href="error_target.html">
Error Target
<svg class="ml-2 h-4 w-4" fill="none" height="24" stroke="currentColor" stroke-linecap="round" stroke-linejoin="round" stroke-width="2" viewbox="0 0 24 24" width="24" xmlns="http://www.w3.org/2000/svg">
<polyline points="9 18 15 12 9 6"></polyline>
</svg>

View file

@ -101,9 +101,10 @@
<li class="toctree-l2"><a class="reference internal" href="terminology.html">Terminology</a></li>
<li class="toctree-l2"><a class="reference internal" href="threading_model.html">Threading Model</a></li>
<li class="toctree-l2"><a class="reference internal" href="listener.html">Listener</a></li>
<li class="toctree-l2"><a class="reference internal" href="prompt.html">Prompts</a></li>
<li class="toctree-l2"><a class="reference internal" href="model_serving.html">Model Serving</a></li>
<li class="toctree-l2"><a class="reference internal" href="prompt.html">Prompt</a></li>
<li class="toctree-l2"><a class="reference internal" href="request_lifecycle.html">Request Lifecycle</a></li>
<li class="toctree-l2"><a class="reference internal" href="error_target.html">Error Target</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="../llm_provider.html">LLM Provider</a></li>
@ -128,7 +129,6 @@
<p class="caption" role="heading"><span class="caption-text">Resources</span></p>
<ul>
<li class="toctree-l1"><a class="reference internal" href="../../resources/configuration_reference.html">Configuration Reference</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../resources/error_target.html">Error Targets</a></li>
</ul>
</nav>
</div>
@ -163,19 +163,19 @@
<li class="toctree-l2"><a class="reference internal" href="listener.html#configure-listener">Configure Listener</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="model_serving.html">Model Serving</a><ul>
<li class="toctree-l2"><a class="reference internal" href="model_serving.html#local-serving-cpu-moderate">Local Serving (CPU - Moderate)</a></li>
<li class="toctree-l2"><a class="reference internal" href="model_serving.html#local-serving-gpu-fast">Local Serving (GPU- Fast)</a></li>
<li class="toctree-l2"><a class="reference internal" href="model_serving.html#cloud-serving-gpu-blazing-fast">Cloud Serving (GPU - Blazing Fast)</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="prompt.html">Prompt</a><ul>
<li class="toctree-l1"><a class="reference internal" href="prompt.html">Prompts</a><ul>
<li class="toctree-l2"><a class="reference internal" href="prompt.html#messages">Messages</a></li>
<li class="toctree-l2"><a class="reference internal" href="prompt.html#prompt-guardrails">Prompt Guardrails</a></li>
<li class="toctree-l2"><a class="reference internal" href="prompt.html#prompt-guard">Prompt Guard</a></li>
<li class="toctree-l2"><a class="reference internal" href="prompt.html#prompt-targets">Prompt Targets</a></li>
<li class="toctree-l2"><a class="reference internal" href="prompt.html#prompting-llms">Prompting LLMs</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="model_serving.html">Model Serving</a><ul>
<li class="toctree-l2"><a class="reference internal" href="model_serving.html#local-serving-cpu-moderate">Local Serving (CPU - Moderate)</a></li>
<li class="toctree-l2"><a class="reference internal" href="model_serving.html#local-serving-gpu-fast">Local Serving (GPU - Fast)</a></li>
<li class="toctree-l2"><a class="reference internal" href="model_serving.html#cloud-serving-gpu-blazing-fast">Cloud Serving (GPU - Blazing Fast)</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="request_lifecycle.html">Request Lifecycle</a><ul>
<li class="toctree-l2"><a class="reference internal" href="request_lifecycle.html#terminology">Terminology</a></li>
<li class="toctree-l2"><a class="reference internal" href="request_lifecycle.html#network-topology">Network topology</a></li>
@ -186,6 +186,12 @@
<li class="toctree-l2"><a class="reference internal" href="request_lifecycle.html#id1">Overview</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="error_target.html">Error Target</a><ul>
<li class="toctree-l2"><a class="reference internal" href="error_target.html#key-concepts">Key Concepts</a></li>
<li class="toctree-l2"><a class="reference internal" href="error_target.html#error-header-example">Error Header Example</a></li>
<li class="toctree-l2"><a class="reference internal" href="error_target.html#best-practices-and-tips">Best Practices and Tips</a></li>
</ul>
</li>
</ul>
</div>
</section>

View file

@ -101,9 +101,10 @@
<li class="toctree-l2 current"><a class="current reference internal" href="#">Terminology</a></li>
<li class="toctree-l2"><a class="reference internal" href="threading_model.html">Threading Model</a></li>
<li class="toctree-l2"><a class="reference internal" href="listener.html">Listener</a></li>
<li class="toctree-l2"><a class="reference internal" href="prompt.html">Prompts</a></li>
<li class="toctree-l2"><a class="reference internal" href="model_serving.html">Model Serving</a></li>
<li class="toctree-l2"><a class="reference internal" href="prompt.html">Prompt</a></li>
<li class="toctree-l2"><a class="reference internal" href="request_lifecycle.html">Request Lifecycle</a></li>
<li class="toctree-l2"><a class="reference internal" href="error_target.html">Error Target</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="../llm_provider.html">LLM Provider</a></li>
@ -128,7 +129,6 @@
<p class="caption" role="heading"><span class="caption-text">Resources</span></p>
<ul>
<li class="toctree-l1"><a class="reference internal" href="../../resources/configuration_reference.html">Configuration Reference</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../resources/error_target.html">Error Targets</a></li>
</ul>
</nav>
</div>
@ -160,31 +160,31 @@ to keep things consistent in logs, traces and in code.</p>
<p><strong>Upstream(Egress)</strong>: An upstream host that receives connections and prompts from Arch, and returns context or responses for a prompt</p>
<a class="reference internal image-reference" href="../../_images/network-topology-ingress-egress.jpg"><img alt="../../_images/network-topology-ingress-egress.jpg" class="align-center" src="../../_images/network-topology-ingress-egress.jpg" style="width: 100%;"/>
</a>
<p><strong>Listener</strong>: A listener is a named network location (e.g., port, address, path etc.) that Arch listens on to process prompts
<p><strong>Listener</strong>: A <a class="reference internal" href="listener.html#arch-overview-listeners"><span class="std std-ref">listener</span></a> is a named network location (e.g., port, address, path etc.) that Arch listens on to process prompts
before forwarding them to your application server endpoints. rch enables you to configure one listener for downstream connections
(like port 80, 443) and creates a separate internal listener for calls that initiate from your application code to LLMs.</p>
<div class="admonition note">
<p class="admonition-title">Note</p>
<p>When you start Arch, you specify a listener address/port that you want to bind downstream. But, Arch uses are predefined port
that you can use (<code class="docutils literal notranslate"><span class="pre">127.0.0.1:10000</span></code>) to proxy egress calls originating from your application to LLMs (API-based or hosted).
For more details, check out <a class="reference internal" href="../llm_provider.html#llm-provider"><span class="std std-ref">LLM providers</span></a></p>
For more details, check out <a class="reference internal" href="../llm_provider.html#llm-provider"><span class="std std-ref">LLM provider</span></a>.</p>
</div>
<p><strong>Instance</strong>: An instance of the Arch gateway. When you start Arch it creates at most two processes. One to handle Layer 7
networking operations (auth, tls, observability, etc) and the second process to serve models that enable it to make smart
decisions on how to accept, handle and forward prompts. The second process is optional, as the model serving sevice could be
hosted on a different network (an API call). But these two processes are considered a single instance of Arch.</p>
<p><strong>Prompt Targets</strong>: Arch offers a primitive called <code class="docutils literal notranslate"><span class="pre">prompt_targets</span></code> to help separate business logic from undifferentiated
<p><strong>Prompt Target</strong>: Arch offers a primitive called <a class="reference internal" href="../prompt_target.html#prompt-target"><span class="std std-ref">prompt_target</span></a> to help separate business logic from undifferentiated
work in building generative AI apps. Prompt targets are endpoints that receive prompts that are processed by Arch.
For example, Arch enriches incoming prompts with metadata like knowing when a request is a follow-up or clarifying prompt
so that you can build faster, more accurate retrieval (RAG) apps. To support agentic apps, like scheduling travel plans or
sharing comments on a document - via prompts, Bolt uses its function calling abilities to extract critical information from
the incoming prompt (or a set of prompts) needed by a downstream backend API or function call before calling it directly.</p>
<p><strong>Error Targets</strong>: Error targets are those endpoints that receive forwarded errors from Arch when issues arise,
<p><strong>Error Target</strong>: <a class="reference internal" href="error_target.html#error-target"><span class="std std-ref">Error targets</span></a> are those endpoints that receive forwarded errors from Arch when issues arise,
such as failing to properly call a function/API, detecting violations of guardrails, or encountering other processing errors.
These errors are communicated to the application via headers (X-Arch-[ERROR-TYPE]), allowing it to handle the errors gracefully
These errors are communicated to the application via headers <code class="docutils literal notranslate"><span class="pre">X-Arch-[ERROR-TYPE]</span></code>, allowing it to handle the errors gracefully
and take appropriate actions.</p>
<p><strong>Model Serving</strong>: Arch is a set of <strong>two</strong> self-contained processes that are designed to run alongside your application servers
(or on a separate hostconnected via a network).The <strong>model serving</strong> process helps Arch make intelligent decisions about the
<p><strong>Model Serving</strong>: Arch is a set of <cite>two</cite> self-contained processes that are designed to run alongside your application servers
(or on a separate hostconnected via a network).The <a class="reference internal" href="model_serving.html#model-serving"><span class="std std-ref">model serving</span></a> process helps Arch make intelligent decisions about the
incoming prompts. The model server is designed to call the (fast) purpose-built LLMs in Arch.</p>
</section>
</div><div class="flex justify-between items-center pt-6 mt-12 border-t border-border gap-4">

View file

@ -101,9 +101,10 @@
<li class="toctree-l2"><a class="reference internal" href="terminology.html">Terminology</a></li>
<li class="toctree-l2 current"><a class="current reference internal" href="#">Threading Model</a></li>
<li class="toctree-l2"><a class="reference internal" href="listener.html">Listener</a></li>
<li class="toctree-l2"><a class="reference internal" href="prompt.html">Prompts</a></li>
<li class="toctree-l2"><a class="reference internal" href="model_serving.html">Model Serving</a></li>
<li class="toctree-l2"><a class="reference internal" href="prompt.html">Prompt</a></li>
<li class="toctree-l2"><a class="reference internal" href="request_lifecycle.html">Request Lifecycle</a></li>
<li class="toctree-l2"><a class="reference internal" href="error_target.html">Error Target</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="../llm_provider.html">LLM Provider</a></li>
@ -128,7 +129,6 @@
<p class="caption" role="heading"><span class="caption-text">Resources</span></p>
<ul>
<li class="toctree-l1"><a class="reference internal" href="../../resources/configuration_reference.html">Configuration Reference</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../resources/error_target.html">Error Targets</a></li>
</ul>
</nav>
</div>
@ -161,7 +161,7 @@ threads perform filtering, and forwarding.</p>
thread. All the functionality around prompt handling from a downstream client is handled in a separate worker thread.
This allows the majority of Arch to be largely single threaded (embarrassingly parallel) with a small amount
of more complex code handling coordination between the worker threads.</p>
<p>Generally Arch is written to be 100% non-blocking.</p>
<p>Generally, Arch is written to be 100% non-blocking.</p>
<div class="admonition tip">
<p class="admonition-title">Tip</p>
<p>For most workloads we recommend configuring the number of worker threads to be equal to the number of