mirror of
https://github.com/katanemo/plano.git
synced 2026-04-25 08:46:24 +02:00
424 lines
No EOL
62 KiB
HTML
Executable file
424 lines
No EOL
62 KiB
HTML
Executable file
<!DOCTYPE html>
|
||
|
||
<html :class="{'dark': darkMode === 'dark' || (darkMode === 'system' && 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 => 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>Agentic Apps | Arch Docs v0.1.7</title>
|
||
<meta content="Agentic Apps | Arch Docs v0.1.7" property="og:title"/>
|
||
<meta content="Agentic Apps | Arch Docs v0.1.7" name="twitter:title"/>
|
||
<link href="../_static/pygments.css?v=75ebff74" rel="stylesheet" type="text/css"/>
|
||
<link href="../_static/theme.css?v=42baaae4" 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=15e0fffa" rel="stylesheet" type="text/css"/>
|
||
<link href="./docs/build_with_arch/agent.html" rel="canonical"/>
|
||
<link href="../_static/favicon.ico" rel="icon"/>
|
||
<link href="../search.html" rel="search" title="Search"/>
|
||
<link href="rag.html" rel="next" title="RAG Apps"/>
|
||
<link href="../guides/observability/access_logging.html" rel="prev" title="Access Logging"/>
|
||
<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 v0.1.7</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 v0.1.7</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>
|
||
<li class="toctree-l1"><a class="reference internal" href="../get_started/quickstart.html#next-steps">Next Steps</a></li>
|
||
</ul>
|
||
<p class="caption" role="heading"><span class="caption-text">Concepts</span></p>
|
||
<ul>
|
||
<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="../concepts/tech_overview/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 x-show="expanded">
|
||
<li class="toctree-l2"><a class="reference internal" href="../concepts/tech_overview/terminology.html">Terminology</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../concepts/tech_overview/threading_model.html">Threading Model</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../concepts/tech_overview/listener.html">Listener</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../concepts/tech_overview/prompt.html">Prompts</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../concepts/tech_overview/model_serving.html">Model Serving</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../concepts/tech_overview/request_lifecycle.html">Request Lifecycle</a></li>
|
||
<li class="toctree-l2"><a class="reference internal" href="../concepts/tech_overview/error_target.html">Error Target</a></li>
|
||
</ul>
|
||
</li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../concepts/llm_provider.html">LLM Provider</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../concepts/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 class="current">
|
||
<li class="toctree-l1 current"><a class="current reference internal" href="#">Agentic Apps</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="rag.html">RAG Apps</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="multi_turn.html">Multi-Turn</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 v0.1.7</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><span aria-current="page" class="font-medium text-foreground overflow-hidden text-ellipsis whitespace-nowrap">Agentic Apps</span>
|
||
</nav>
|
||
<div id="content" role="main">
|
||
<section id="agentic-apps">
|
||
<span id="arch-agent-guide"></span><h1>Agentic Apps<a @click.prevent="window.navigator.clipboard.writeText($el.href); $el.setAttribute('data-tooltip', 'Copied!'); setTimeout(() => $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="#agentic-apps"><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 helps you build personalized agentic applications by calling application-specific (API) functions via user prompts.
|
||
This involves any predefined functions or APIs you want to expose to users to perform tasks, gather information,
|
||
or manipulate data. This capability is generally referred to as <a class="reference internal" href="../guides/function_calling.html#function-calling"><span class="std std-ref">function calling</span></a>, where
|
||
you can support “agentic” apps tailored to specific use cases - from updating insurance claims to creating ad campaigns - via prompts.</p>
|
||
<p>Arch analyzes prompts, extracts critical information from prompts, engages in lightweight conversation with the user to
|
||
gather any missing parameters and makes API calls so that you can focus on writing business logic. Arch does this via its
|
||
purpose-built <a class="reference external" href="https://huggingface.co/collections/katanemo/arch-function-66f209a693ea8df14317ad68" rel="nofollow noopener">Arch-Function<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> -
|
||
the fastest (200ms p50 - 12x faser than GPT-4o) and cheapest (44x than GPT-4o) function calling LLM that matches or outperforms
|
||
frontier LLMs.</p>
|
||
<a class="reference internal image-reference" href="../_images/function-calling-flow.jpg"><img alt="../_images/function-calling-flow.jpg" class="align-center" src="../_images/function-calling-flow.jpg" style="width: 100%;"/>
|
||
</a>
|
||
<section id="single-function-call">
|
||
<h2>Single Function Call<a @click.prevent="window.navigator.clipboard.writeText($el.href); $el.setAttribute('data-tooltip', 'Copied!'); setTimeout(() => $el.setAttribute('data-tooltip', 'Copy link to this element'), 2000)" aria-label="Copy link to this element" class="headerlink" data-tooltip="Copy link to this element" href="#single-function-call" x-intersect.margin.0%.0%.-70%.0%="activeSection = '#single-function-call'"><svg height="1em" viewbox="0 0 24 24" width="1em" xmlns="http://www.w3.org/2000/svg"><path d="M3.9 12c0-1.71 1.39-3.1 3.1-3.1h4V7H7c-2.76 0-5 2.24-5 5s2.24 5 5 5h4v-1.9H7c-1.71 0-3.1-1.39-3.1-3.1zM8 13h8v-2H8v2zm9-6h-4v1.9h4c1.71 0 3.1 1.39 3.1 3.1s-1.39 3.1-3.1 3.1h-4V17h4c2.76 0 5-2.24 5-5s-2.24-5-5-5z"></path></svg></a></h2>
|
||
<p>In the most common scenario, users will request a single action via prompts, and Arch efficiently processes the
|
||
request by extracting relevant parameters, validating the input, and calling the designated function or API. Here
|
||
is how you would go about enabling this scenario with Arch:</p>
|
||
<section id="step-1-define-prompt-targets">
|
||
<h3>Step 1: Define Prompt Targets<a @click.prevent="window.navigator.clipboard.writeText($el.href); $el.setAttribute('data-tooltip', 'Copied!'); setTimeout(() => $el.setAttribute('data-tooltip', 'Copy link to this element'), 2000)" aria-label="Copy link to this element" class="headerlink" data-tooltip="Copy link to this element" href="#step-1-define-prompt-targets" x-intersect.margin.0%.0%.-70%.0%="activeSection = '#step-1-define-prompt-targets'"><svg height="1em" viewbox="0 0 24 24" width="1em" xmlns="http://www.w3.org/2000/svg"><path d="M3.9 12c0-1.71 1.39-3.1 3.1-3.1h4V7H7c-2.76 0-5 2.24-5 5s2.24 5 5 5h4v-1.9H7c-1.71 0-3.1-1.39-3.1-3.1zM8 13h8v-2H8v2zm9-6h-4v1.9h4c1.71 0 3.1 1.39 3.1 3.1s-1.39 3.1-3.1 3.1h-4V17h4c2.76 0 5-2.24 5-5s-2.24-5-5-5z"></path></svg></a></h3>
|
||
<div class="literal-block-wrapper docutils container" id="id2">
|
||
<div class="code-block-caption"><span class="caption-text">Prompt Target Example Configuration</span><a @click.prevent="window.navigator.clipboard.writeText($el.href); $el.setAttribute('data-tooltip', 'Copied!'); setTimeout(() => $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="l l-Scalar l-Scalar-Plain">v0.1</span>
|
||
</span><span id="line-2"><span class="linenos"> 2</span><span class="nt">listener</span><span class="p">:</span>
|
||
</span><span id="line-3"><span class="linenos"> 3</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">127.0.0.1</span>
|
||
</span><span id="line-4"><span class="linenos"> 4</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">8080</span><span class="w"> </span><span class="c1">#If you configure port 443, you'll need to update the listener with tls_certificates</span>
|
||
</span><span id="line-5"><span class="linenos"> 5</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-6"><span class="linenos"> 6</span>
|
||
</span><span id="line-7"><span class="linenos"> 7</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-8"><span class="linenos"> 8</span><span class="nt">llm_providers</span><span class="p">:</span>
|
||
</span><span id="line-9"><span class="linenos"> 9</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-10"><span class="linenos">10</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-11"><span class="linenos">11</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-12"><span class="linenos">12</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-3.5-turbo</span>
|
||
</span><span id="line-13"><span class="linenos">13</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-14"><span class="linenos">14</span>
|
||
</span><span id="line-15"><span class="linenos">15</span><span class="c1"># default system prompt used by all prompt targets</span>
|
||
</span><span id="line-16"><span class="linenos">16</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-17"><span class="linenos">17</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-18"><span class="linenos">18</span>
|
||
</span><span id="line-19"><mark><span class="linenos">19</span><span class="nt">prompt_targets</span><span class="p">:</span>
|
||
</mark></span><span id="line-20"><mark><span class="linenos">20</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">network_qa</span>
|
||
</mark></span><span id="line-21"><mark><span class="linenos">21</span><span class="w"> </span><span class="nt">endpoint</span><span class="p">:</span>
|
||
</mark></span><span id="line-22"><mark><span class="linenos">22</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-23"><mark><span class="linenos">23</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/network_summary</span>
|
||
</mark></span><span id="line-24"><mark><span class="linenos">24</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">Handle general Q/A related to networking.</span>
|
||
</mark></span><span id="line-25"><mark><span class="linenos">25</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>
|
||
</mark></span><span id="line-26"><mark><span class="linenos">26</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_devices</span>
|
||
</mark></span><span id="line-27"><mark><span class="linenos">27</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 specific devices or device groups</span>
|
||
</mark></span><span id="line-28"><mark><span class="linenos">28</span><span class="w"> </span><span class="nt">endpoint</span><span class="p">:</span>
|
||
</mark></span><span id="line-29"><mark><span class="linenos">29</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-30"><mark><span class="linenos">30</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/device_reboot</span>
|
||
</mark></span><span id="line-31"><mark><span class="linenos">31</span><span class="w"> </span><span class="nt">parameters</span><span class="p">:</span>
|
||
</mark></span><span id="line-32"><mark><span class="linenos">32</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_ids</span>
|
||
</mark></span><span id="line-33"><mark><span class="linenos">33</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">list</span>
|
||
</mark></span><span id="line-34"><mark><span class="linenos">34</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">A list of device identifiers (IDs) to reboot.</span>
|
||
</mark></span><span id="line-35"><mark><span class="linenos">35</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-36"><mark><span class="linenos">36</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_summary</span>
|
||
</mark></span><span id="line-37"><mark><span class="linenos">37</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">Retrieve statistics for specific devices within a time range</span>
|
||
</mark></span><span id="line-38"><mark><span class="linenos">38</span><span class="w"> </span><span class="nt">endpoint</span><span class="p">:</span>
|
||
</mark></span><span id="line-39"><mark><span class="linenos">39</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-40"><mark><span class="linenos">40</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/device_summary</span>
|
||
</mark></span><span id="line-41"><mark><span class="linenos">41</span><span class="w"> </span><span class="nt">parameters</span><span class="p">:</span>
|
||
</mark></span><span id="line-42"><mark><span class="linenos">42</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_ids</span>
|
||
</mark></span><span id="line-43"><mark><span class="linenos">43</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">list</span>
|
||
</mark></span><span id="line-44"><mark><span class="linenos">44</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">A list of device identifiers (IDs) to retrieve statistics for.</span>
|
||
</mark></span><span id="line-45"><mark><span class="linenos">45</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 class="w"> </span><span class="c1"># device_ids are required to get device statistics</span>
|
||
</mark></span><span id="line-46"><mark><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="l l-Scalar l-Scalar-Plain">time_range</span>
|
||
</mark></span><span id="line-47"><mark><span class="linenos">47</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">int</span>
|
||
</mark></span><span id="line-48"><mark><span class="linenos">48</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">Time range in days for which to gather device statistics. Defaults to 7.</span>
|
||
</mark></span><span id="line-49"><mark><span class="linenos">49</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">7</span>
|
||
</mark></span><span id="line-50"><span class="linenos">50</span>
|
||
</span><span id="line-51"><span class="linenos">51</span><span class="c1"># Arch creates a round-robin load balancing between different endpoints, managed via the cluster subsystem.</span>
|
||
</span><span id="line-52"><span class="linenos">52</span><span class="nt">endpoints</span><span class="p">:</span>
|
||
</span><span id="line-53"><span class="linenos">53</span><span class="w"> </span><span class="nt">app_server</span><span class="p">:</span>
|
||
</span><span id="line-54"><span class="linenos">54</span><span class="w"> </span><span class="c1"># value could be ip address or a hostname with port</span>
|
||
</span><span id="line-55"><span class="linenos">55</span><span class="w"> </span><span class="c1"># this could also be a list of endpoints for load balancing</span>
|
||
</span><span id="line-56"><span class="linenos">56</span><span class="w"> </span><span class="c1"># for example endpoint: [ ip1:port, ip2:port ]</span>
|
||
</span><span id="line-57"><span class="linenos">57</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">host.docker.internal:18083</span>
|
||
</span><span id="line-58"><span class="linenos">58</span><span class="w"> </span><span class="c1"># max time to wait for a connection to be established</span>
|
||
</span><span id="line-59"><span class="linenos">59</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>
|
||
</section>
|
||
<section id="step-2-process-request-parameters">
|
||
<h3>Step 2: Process Request Parameters<a @click.prevent="window.navigator.clipboard.writeText($el.href); $el.setAttribute('data-tooltip', 'Copied!'); setTimeout(() => $el.setAttribute('data-tooltip', 'Copy link to this element'), 2000)" aria-label="Copy link to this element" class="headerlink" data-tooltip="Copy link to this element" href="#step-2-process-request-parameters" x-intersect.margin.0%.0%.-70%.0%="activeSection = '#step-2-process-request-parameters'"><svg height="1em" viewbox="0 0 24 24" width="1em" xmlns="http://www.w3.org/2000/svg"><path d="M3.9 12c0-1.71 1.39-3.1 3.1-3.1h4V7H7c-2.76 0-5 2.24-5 5s2.24 5 5 5h4v-1.9H7c-1.71 0-3.1-1.39-3.1-3.1zM8 13h8v-2H8v2zm9-6h-4v1.9h4c1.71 0 3.1 1.39 3.1 3.1s-1.39 3.1-3.1 3.1h-4V17h4c2.76 0 5-2.24 5-5s-2.24-5-5-5z"></path></svg></a></h3>
|
||
<p>Once the prompt targets are configured as above, handling those parameters is</p>
|
||
<div class="literal-block-wrapper docutils container" id="id3">
|
||
<div class="code-block-caption"><span class="caption-text">Parameter handling with Flask</span><a @click.prevent="window.navigator.clipboard.writeText($el.href); $el.setAttribute('data-tooltip', 'Copied!'); setTimeout(() => $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="#id3"><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-python notranslate"><div class="highlight"><pre><span></span><code><span id="line-1"><span class="linenos"> 1</span><span class="kn">from</span> <span class="nn">flask</span> <span class="kn">import</span> <span class="n">Flask</span><span class="p">,</span> <span class="n">request</span><span class="p">,</span> <span class="n">jsonify</span>
|
||
</span><span id="line-2"><span class="linenos"> 2</span>
|
||
</span><span id="line-3"><span class="linenos"> 3</span><span class="n">app</span> <span class="o">=</span> <span class="n">Flask</span><span class="p">(</span><span class="vm">__name__</span><span class="p">)</span>
|
||
</span><span id="line-4"><span class="linenos"> 4</span>
|
||
</span><span id="line-5"><span class="linenos"> 5</span>
|
||
</span><span id="line-6"><span class="linenos"> 6</span><span class="nd">@app</span><span class="o">.</span><span class="n">route</span><span class="p">(</span><span class="s2">"/agent/device_summary"</span><span class="p">,</span> <span class="n">methods</span><span class="o">=</span><span class="p">[</span><span class="s2">"POST"</span><span class="p">])</span>
|
||
</span><span id="line-7"><span class="linenos"> 7</span><span class="k">def</span> <span class="nf">get_device_summary</span><span class="p">():</span>
|
||
</span><span id="line-8"><span class="linenos"> 8</span><span class="w"> </span><span class="sd">"""</span>
|
||
</span><span id="line-9"><span class="linenos"> 9</span><span class="sd"> Endpoint to retrieve device statistics based on device IDs and an optional time range.</span>
|
||
</span><span id="line-10"><span class="linenos">10</span><span class="sd"> """</span>
|
||
</span><span id="line-11"><span class="linenos">11</span> <span class="n">data</span> <span class="o">=</span> <span class="n">request</span><span class="o">.</span><span class="n">get_json</span><span class="p">()</span>
|
||
</span><span id="line-12"><span class="linenos">12</span>
|
||
</span><span id="line-13"><span class="linenos">13</span> <span class="c1"># Validate 'device_ids' parameter</span>
|
||
</span><span id="line-14"><span class="linenos">14</span> <span class="n">device_ids</span> <span class="o">=</span> <span class="n">data</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s2">"device_ids"</span><span class="p">)</span>
|
||
</span><span id="line-15"><span class="linenos">15</span> <span class="k">if</span> <span class="ow">not</span> <span class="n">device_ids</span> <span class="ow">or</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">device_ids</span><span class="p">,</span> <span class="nb">list</span><span class="p">):</span>
|
||
</span><span id="line-16"><span class="linenos">16</span> <span class="k">return</span> <span class="p">(</span>
|
||
</span><span id="line-17"><span class="linenos">17</span> <span class="n">jsonify</span><span class="p">({</span><span class="s2">"error"</span><span class="p">:</span> <span class="s2">"'device_ids' parameter is required and must be a list"</span><span class="p">}),</span>
|
||
</span><span id="line-18"><span class="linenos">18</span> <span class="mi">400</span><span class="p">,</span>
|
||
</span><span id="line-19"><span class="linenos">19</span> <span class="p">)</span>
|
||
</span><span id="line-20"><span class="linenos">20</span>
|
||
</span><span id="line-21"><span class="linenos">21</span> <span class="c1"># Validate 'time_range' parameter (optional, defaults to 7)</span>
|
||
</span><span id="line-22"><span class="linenos">22</span> <span class="n">time_range</span> <span class="o">=</span> <span class="n">data</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s2">"time_range"</span><span class="p">,</span> <span class="mi">7</span><span class="p">)</span>
|
||
</span><span id="line-23"><span class="linenos">23</span> <span class="k">if</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">time_range</span><span class="p">,</span> <span class="nb">int</span><span class="p">):</span>
|
||
</span><span id="line-24"><span class="linenos">24</span> <span class="k">return</span> <span class="n">jsonify</span><span class="p">({</span><span class="s2">"error"</span><span class="p">:</span> <span class="s2">"'time_range' must be an integer"</span><span class="p">}),</span> <span class="mi">400</span>
|
||
</span><span id="line-25"><span class="linenos">25</span>
|
||
</span><span id="line-26"><span class="linenos">26</span> <span class="c1"># Simulate retrieving statistics for the given device IDs and time range</span>
|
||
</span><span id="line-27"><span class="linenos">27</span> <span class="c1"># In a real application, you would query your database or external service here</span>
|
||
</span><span id="line-28"><span class="linenos">28</span> <span class="n">statistics</span> <span class="o">=</span> <span class="p">[]</span>
|
||
</span><span id="line-29"><span class="linenos">29</span> <span class="k">for</span> <span class="n">device_id</span> <span class="ow">in</span> <span class="n">device_ids</span><span class="p">:</span>
|
||
</span><span id="line-30"><span class="linenos">30</span> <span class="c1"># Placeholder for actual data retrieval</span>
|
||
</span><span id="line-31"><span class="linenos">31</span> <span class="n">stats</span> <span class="o">=</span> <span class="p">{</span>
|
||
</span><span id="line-32"><span class="linenos">32</span> <span class="s2">"device_id"</span><span class="p">:</span> <span class="n">device_id</span><span class="p">,</span>
|
||
</span><span id="line-33"><span class="linenos">33</span> <span class="s2">"time_range"</span><span class="p">:</span> <span class="sa">f</span><span class="s2">"Last </span><span class="si">{</span><span class="n">time_range</span><span class="si">}</span><span class="s2"> days"</span><span class="p">,</span>
|
||
</span><span id="line-34"><span class="linenos">34</span> <span class="s2">"data"</span><span class="p">:</span> <span class="sa">f</span><span class="s2">"Statistics data for device </span><span class="si">{</span><span class="n">device_id</span><span class="si">}</span><span class="s2"> over the last </span><span class="si">{</span><span class="n">time_range</span><span class="si">}</span><span class="s2"> days."</span><span class="p">,</span>
|
||
</span><span id="line-35"><span class="linenos">35</span> <span class="p">}</span>
|
||
</span><span id="line-36"><span class="linenos">36</span> <span class="n">statistics</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">stats</span><span class="p">)</span>
|
||
</span><span id="line-37"><span class="linenos">37</span>
|
||
</span><span id="line-38"><span class="linenos">38</span> <span class="n">response</span> <span class="o">=</span> <span class="p">{</span><span class="s2">"statistics"</span><span class="p">:</span> <span class="n">statistics</span><span class="p">}</span>
|
||
</span><span id="line-39"><span class="linenos">39</span>
|
||
</span><span id="line-40"><span class="linenos">40</span> <span class="k">return</span> <span class="n">jsonify</span><span class="p">(</span><span class="n">response</span><span class="p">),</span> <span class="mi">200</span>
|
||
</span><span id="line-41"><span class="linenos">41</span>
|
||
</span><span id="line-42"><span class="linenos">42</span>
|
||
</span><span id="line-43"><span class="linenos">43</span><span class="k">if</span> <span class="vm">__name__</span> <span class="o">==</span> <span class="s2">"__main__"</span><span class="p">:</span>
|
||
</span><span id="line-44"><span class="linenos">44</span> <span class="n">app</span><span class="o">.</span><span class="n">run</span><span class="p">(</span><span class="n">debug</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
|
||
</span></code></pre></div>
|
||
</div>
|
||
</div>
|
||
</section>
|
||
</section>
|
||
<section id="parallel-multiple-function-calling">
|
||
<h2>Parallel & Multiple Function Calling<a @click.prevent="window.navigator.clipboard.writeText($el.href); $el.setAttribute('data-tooltip', 'Copied!'); setTimeout(() => $el.setAttribute('data-tooltip', 'Copy link to this element'), 2000)" aria-label="Copy link to this element" class="headerlink" data-tooltip="Copy link to this element" href="#parallel-multiple-function-calling" x-intersect.margin.0%.0%.-70%.0%="activeSection = '#parallel-multiple-function-calling'"><svg height="1em" viewbox="0 0 24 24" width="1em" xmlns="http://www.w3.org/2000/svg"><path d="M3.9 12c0-1.71 1.39-3.1 3.1-3.1h4V7H7c-2.76 0-5 2.24-5 5s2.24 5 5 5h4v-1.9H7c-1.71 0-3.1-1.39-3.1-3.1zM8 13h8v-2H8v2zm9-6h-4v1.9h4c1.71 0 3.1 1.39 3.1 3.1s-1.39 3.1-3.1 3.1h-4V17h4c2.76 0 5-2.24 5-5s-2.24-5-5-5z"></path></svg></a></h2>
|
||
<p>In more complex use cases, users may request multiple actions or need multiple APIs/functions to be called
|
||
simultaneously or sequentially. With Arch, you can handle these scenarios efficiently using parallel or multiple
|
||
function calling. This allows your application to engage in a broader range of interactions, such as updating
|
||
different datasets, triggering events across systems, or collecting results from multiple services in one prompt.</p>
|
||
<p>Arch-FC1B is built to manage these parallel tasks efficiently, ensuring low latency and high throughput, even
|
||
when multiple functions are invoked. It provides two mechanisms to handle these cases:</p>
|
||
<section id="id1">
|
||
<h3>Step 1: Define Prompt Targets<a @click.prevent="window.navigator.clipboard.writeText($el.href); $el.setAttribute('data-tooltip', 'Copied!'); setTimeout(() => $el.setAttribute('data-tooltip', 'Copy link to this element'), 2000)" aria-label="Copy link to this element" class="headerlink" data-tooltip="Copy link to this element" href="#id1" x-intersect.margin.0%.0%.-70%.0%="activeSection = '#id1'"><svg height="1em" viewbox="0 0 24 24" width="1em" xmlns="http://www.w3.org/2000/svg"><path d="M3.9 12c0-1.71 1.39-3.1 3.1-3.1h4V7H7c-2.76 0-5 2.24-5 5s2.24 5 5 5h4v-1.9H7c-1.71 0-3.1-1.39-3.1-3.1zM8 13h8v-2H8v2zm9-6h-4v1.9h4c1.71 0 3.1 1.39 3.1 3.1s-1.39 3.1-3.1 3.1h-4V17h4c2.76 0 5-2.24 5-5s-2.24-5-5-5z"></path></svg></a></h3>
|
||
<p>When enabling multiple function calling, define the prompt targets in a way that supports multiple functions or
|
||
API calls based on the user’s prompt. These targets can be triggered in parallel or sequentially, depending on
|
||
the user’s intent.</p>
|
||
<p>Example of Multiple Prompt Targets in YAML:</p>
|
||
<div class="literal-block-wrapper docutils container" id="id4">
|
||
<div class="code-block-caption"><span class="caption-text">Prompt Target Example Configuration</span><a @click.prevent="window.navigator.clipboard.writeText($el.href); $el.setAttribute('data-tooltip', 'Copied!'); setTimeout(() => $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="#id4"><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="l l-Scalar l-Scalar-Plain">v0.1</span>
|
||
</span><span id="line-2"><span class="linenos"> 2</span><span class="nt">listener</span><span class="p">:</span>
|
||
</span><span id="line-3"><span class="linenos"> 3</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">127.0.0.1</span>
|
||
</span><span id="line-4"><span class="linenos"> 4</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">8080</span><span class="w"> </span><span class="c1">#If you configure port 443, you'll need to update the listener with tls_certificates</span>
|
||
</span><span id="line-5"><span class="linenos"> 5</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-6"><span class="linenos"> 6</span>
|
||
</span><span id="line-7"><span class="linenos"> 7</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-8"><span class="linenos"> 8</span><span class="nt">llm_providers</span><span class="p">:</span>
|
||
</span><span id="line-9"><span class="linenos"> 9</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-10"><span class="linenos">10</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-11"><span class="linenos">11</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-12"><span class="linenos">12</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-3.5-turbo</span>
|
||
</span><span id="line-13"><span class="linenos">13</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-14"><span class="linenos">14</span>
|
||
</span><span id="line-15"><span class="linenos">15</span><span class="c1"># default system prompt used by all prompt targets</span>
|
||
</span><span id="line-16"><span class="linenos">16</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-17"><span class="linenos">17</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-18"><span class="linenos">18</span>
|
||
</span><span id="line-19"><mark><span class="linenos">19</span><span class="nt">prompt_targets</span><span class="p">:</span>
|
||
</mark></span><span id="line-20"><mark><span class="linenos">20</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">network_qa</span>
|
||
</mark></span><span id="line-21"><mark><span class="linenos">21</span><span class="w"> </span><span class="nt">endpoint</span><span class="p">:</span>
|
||
</mark></span><span id="line-22"><mark><span class="linenos">22</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-23"><mark><span class="linenos">23</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/network_summary</span>
|
||
</mark></span><span id="line-24"><mark><span class="linenos">24</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">Handle general Q/A related to networking.</span>
|
||
</mark></span><span id="line-25"><mark><span class="linenos">25</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>
|
||
</mark></span><span id="line-26"><mark><span class="linenos">26</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_devices</span>
|
||
</mark></span><span id="line-27"><mark><span class="linenos">27</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 specific devices or device groups</span>
|
||
</mark></span><span id="line-28"><mark><span class="linenos">28</span><span class="w"> </span><span class="nt">endpoint</span><span class="p">:</span>
|
||
</mark></span><span id="line-29"><mark><span class="linenos">29</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-30"><mark><span class="linenos">30</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/device_reboot</span>
|
||
</mark></span><span id="line-31"><mark><span class="linenos">31</span><span class="w"> </span><span class="nt">parameters</span><span class="p">:</span>
|
||
</mark></span><span id="line-32"><mark><span class="linenos">32</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_ids</span>
|
||
</mark></span><span id="line-33"><mark><span class="linenos">33</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">list</span>
|
||
</mark></span><span id="line-34"><mark><span class="linenos">34</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">A list of device identifiers (IDs) to reboot.</span>
|
||
</mark></span><span id="line-35"><mark><span class="linenos">35</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-36"><mark><span class="linenos">36</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_summary</span>
|
||
</mark></span><span id="line-37"><mark><span class="linenos">37</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">Retrieve statistics for specific devices within a time range</span>
|
||
</mark></span><span id="line-38"><mark><span class="linenos">38</span><span class="w"> </span><span class="nt">endpoint</span><span class="p">:</span>
|
||
</mark></span><span id="line-39"><mark><span class="linenos">39</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-40"><mark><span class="linenos">40</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/device_summary</span>
|
||
</mark></span><span id="line-41"><mark><span class="linenos">41</span><span class="w"> </span><span class="nt">parameters</span><span class="p">:</span>
|
||
</mark></span><span id="line-42"><mark><span class="linenos">42</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_ids</span>
|
||
</mark></span><span id="line-43"><mark><span class="linenos">43</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">list</span>
|
||
</mark></span><span id="line-44"><mark><span class="linenos">44</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">A list of device identifiers (IDs) to retrieve statistics for.</span>
|
||
</mark></span><span id="line-45"><mark><span class="linenos">45</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 class="w"> </span><span class="c1"># device_ids are required to get device statistics</span>
|
||
</mark></span><span id="line-46"><mark><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="l l-Scalar l-Scalar-Plain">time_range</span>
|
||
</mark></span><span id="line-47"><mark><span class="linenos">47</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">int</span>
|
||
</mark></span><span id="line-48"><mark><span class="linenos">48</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">Time range in days for which to gather device statistics. Defaults to 7.</span>
|
||
</mark></span><span id="line-49"><mark><span class="linenos">49</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">7</span>
|
||
</mark></span><span id="line-50"><span class="linenos">50</span>
|
||
</span><span id="line-51"><span class="linenos">51</span><span class="c1"># Arch creates a round-robin load balancing between different endpoints, managed via the cluster subsystem.</span>
|
||
</span><span id="line-52"><span class="linenos">52</span><span class="nt">endpoints</span><span class="p">:</span>
|
||
</span><span id="line-53"><span class="linenos">53</span><span class="w"> </span><span class="nt">app_server</span><span class="p">:</span>
|
||
</span><span id="line-54"><span class="linenos">54</span><span class="w"> </span><span class="c1"># value could be ip address or a hostname with port</span>
|
||
</span><span id="line-55"><span class="linenos">55</span><span class="w"> </span><span class="c1"># this could also be a list of endpoints for load balancing</span>
|
||
</span><span id="line-56"><span class="linenos">56</span><span class="w"> </span><span class="c1"># for example endpoint: [ ip1:port, ip2:port ]</span>
|
||
</span><span id="line-57"><span class="linenos">57</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">host.docker.internal:18083</span>
|
||
</span><span id="line-58"><span class="linenos">58</span><span class="w"> </span><span class="c1"># max time to wait for a connection to be established</span>
|
||
</span><span id="line-59"><span class="linenos">59</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>
|
||
</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="../guides/observability/access_logging.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>
|
||
Access Logging
|
||
</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="rag.html">
|
||
RAG Apps
|
||
<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 === '#single-function-call'" class="reference internal" href="#single-function-call">Single Function Call</a><ul>
|
||
<li><a :data-current="activeSection === '#step-1-define-prompt-targets'" class="reference internal" href="#step-1-define-prompt-targets">Step 1: Define Prompt Targets</a></li>
|
||
<li><a :data-current="activeSection === '#step-2-process-request-parameters'" class="reference internal" href="#step-2-process-request-parameters">Step 2: Process Request Parameters</a></li>
|
||
</ul>
|
||
</li>
|
||
<li><a :data-current="activeSection === '#parallel-multiple-function-calling'" class="reference internal" href="#parallel-multiple-function-calling">Parallel & Multiple Function Calling</a><ul>
|
||
<li><a :data-current="activeSection === '#id1'" class="reference internal" href="#id1">Step 1: Define Prompt Targets</a></li>
|
||
</ul>
|
||
</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: Dec 21, 2024. </p>
|
||
</div>
|
||
</div>
|
||
</footer>
|
||
</div>
|
||
<script src="../_static/documentation_options.js?v=d94a9a28"></script>
|
||
<script src="../_static/doctools.js?v=9bcbadda"></script>
|
||
<script src="../_static/sphinx_highlight.js?v=dc90522c"></script>
|
||
<script defer="defer" src="../_static/theme.js?v=073f68d9"></script>
|
||
<script src="../_static/design-tabs.js?v=f930bc37"></script>
|
||
</body>
|
||
</html> |