mirror of
https://github.com/katanemo/plano.git
synced 2026-04-28 18:36:34 +02:00
deploy: e224cba3e3
This commit is contained in:
adilhafeez
parent
0898a9aa15
commit
c25ce33efc
68 changed files with 9799 additions and 4588 deletions
|
|
@ -7,19 +7,19 @@
|
|||
<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>Deployment | Arch Docs v0.3.22</title>
|
||||
<meta content="Deployment | Arch Docs v0.3.22" property="og:title"/>
|
||||
<meta content="Deployment | Arch Docs v0.3.22" name="twitter:title"/>
|
||||
<title>Deployment | Plano Docs v0.4</title>
|
||||
<meta content="Deployment | Plano Docs v0.4" property="og:title"/>
|
||||
<meta content="Deployment | Plano Docs v0.4" name="twitter:title"/>
|
||||
<link href="../_static/pygments.css?v=466e7b45" 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/css/custom.css?v=2929376a" rel="stylesheet" type="text/css"/>
|
||||
<link href="../_static/awesome-sphinx-design.css?v=15e0fffa" rel="stylesheet" type="text/css"/>
|
||||
<link href="./docs/resources/deployment.html" rel="canonical"/>
|
||||
<link href="../_static/favicon.ico" rel="icon"/>
|
||||
<link href="../search.html" rel="search" title="Search"/>
|
||||
<link href="configuration_reference.html" rel="next" title="Configuration Reference"/>
|
||||
<link href="../build_with_arch/multi_turn.html" rel="prev" title="Multi-Turn"/>
|
||||
<link href="tech_overview/threading_model.html" rel="prev" title="Threading Model"/>
|
||||
<script>
|
||||
<!-- Prevent Flash of wrong theme -->
|
||||
const userPreference = localStorage.getItem('darkMode');
|
||||
|
|
@ -39,7 +39,7 @@
|
|||
</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 v0.3.22</span>
|
||||
<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">Plano Docs v0.4</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>
|
||||
|
|
@ -56,7 +56,7 @@
|
|||
</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">
|
||||
<a href="https://github.com/katanemo/plano" 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>
|
||||
|
|
@ -75,40 +75,33 @@
|
|||
</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 v0.3.22</span>
|
||||
<img alt="Logo" class="mr-2 dark:invert" height="16" src="../_static/favicon.ico" width="16"/><span class="font-bold text-clip whitespace-nowrap">Plano Docs v0.4</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 async="" src="https://www.googletagmanager.com/gtag/js?id=G-EH2VW19FXE"></script>
|
||||
<script>
|
||||
window.dataLayer = window.dataLayer || [];
|
||||
function gtag(){dataLayer.push(arguments);}
|
||||
gtag('js', new Date());
|
||||
|
||||
gtag('config', 'G-K2LXXSX6HB');
|
||||
gtag('config', 'G-EH2VW19FXE');
|
||||
</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/intro_to_plano.html">Intro to Plano</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" x-data="{ expanded: $el.classList.contains('current') ? true : false }"><a :class="{ 'expanded' : expanded }" @click="expanded = !expanded" class="reference internal expandable" href="../concepts/llm_providers/llm_providers.html">LLM Providers<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-l1"><a class="reference internal" href="../concepts/listeners.html">Listeners</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../concepts/agents.html">Agents</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../concepts/filter_chain.html">Filter Chains</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="../concepts/llm_providers/llm_providers.html">Model (LLM) Providers<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/llm_providers/supported_providers.html">Supported Providers & Configuration</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../concepts/llm_providers/client_libraries.html">Client Libraries</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../concepts/llm_providers/model_aliases.html">Model Aliases</a></li>
|
||||
|
|
@ -118,27 +111,29 @@
|
|||
</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/agent_routing.html">Agent Routing and Hand Off</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../guides/function_calling.html">Function Calling</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../guides/orchestration.html">Orchestration</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../guides/llm_router.html">LLM Routing</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 Apps</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../build_with_arch/rag.html">RAG Apps</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../build_with_arch/multi_turn.html">Multi-Turn</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../guides/prompt_guard.html">Guardrails</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../guides/state.html">Conversational State</a></li>
|
||||
</ul>
|
||||
<p class="caption" role="heading"><span class="caption-text">Resources</span></p>
|
||||
<ul class="current">
|
||||
<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="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="tech_overview/request_lifecycle.html">Request Lifecycle</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="tech_overview/model_serving.html">Bright Staff</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="tech_overview/threading_model.html">Threading Model</a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l1 current"><a class="current reference internal" href="#">Deployment</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="configuration_reference.html">Configuration Reference</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="llms_txt.html">llms.txt</a></li>
|
||||
</ul>
|
||||
</nav>
|
||||
</div>
|
||||
|
|
@ -153,7 +148,7 @@
|
|||
<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 v0.3.22</span>
|
||||
<span class="hidden md:inline">Plano Docs v0.4</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>
|
||||
|
|
@ -163,28 +158,28 @@
|
|||
<div id="content" role="main">
|
||||
<section id="deployment">
|
||||
<span id="id1"></span><h1>Deployment<a @click.prevent="window.navigator.clipboard.writeText($el.href); $el.setAttribute('data-tooltip', 'Copied!'); setTimeout(() => $el.setAttribute('data-tooltip', 'Copy link to this element'), 2000)" aria-label="Copy link to this element" class="headerlink" data-tooltip="Copy link to this element" href="#deployment"><svg height="1em" viewbox="0 0 24 24" width="1em" xmlns="http://www.w3.org/2000/svg"><path d="M3.9 12c0-1.71 1.39-3.1 3.1-3.1h4V7H7c-2.76 0-5 2.24-5 5s2.24 5 5 5h4v-1.9H7c-1.71 0-3.1-1.39-3.1-3.1zM8 13h8v-2H8v2zm9-6h-4v1.9h4c1.71 0 3.1 1.39 3.1 3.1s-1.39 3.1-3.1 3.1h-4V17h4c2.76 0 5-2.24 5-5s-2.24-5-5-5z"></path></svg></a></h1>
|
||||
<p>This guide shows how to deploy Arch directly using Docker without the archgw CLI, including basic runtime checks for routing and health monitoring.</p>
|
||||
<p>This guide shows how to deploy Plano directly using Docker without the <code class="docutils literal notranslate"><span class="pre">plano</span></code> CLI, including basic runtime checks for routing and health monitoring.</p>
|
||||
<section id="docker-deployment">
|
||||
<h2>Docker Deployment<a @click.prevent="window.navigator.clipboard.writeText($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="#docker-deployment" x-intersect.margin.0%.0%.-70%.0%="activeSection = '#docker-deployment'"><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>Below is a minimal, production-ready example showing how to deploy the Arch Docker image directly and run basic runtime checks. Adjust image names, tags, and the <code class="docutils literal notranslate"><span class="pre">arch_config.yaml</span></code> path to match your environment.</p>
|
||||
<p>Below is a minimal, production-ready example showing how to deploy the Plano Docker image directly and run basic runtime checks. Adjust image names, tags, and the <code class="docutils literal notranslate"><span class="pre">plano_config.yaml</span></code> path to match your environment.</p>
|
||||
<div class="admonition note">
|
||||
<p class="admonition-title">Note</p>
|
||||
<p>You will need to pass all required environment variables that are referenced in your <code class="docutils literal notranslate"><span class="pre">arch_config.yaml</span></code> file.</p>
|
||||
<p>You will need to pass all required environment variables that are referenced in your <code class="docutils literal notranslate"><span class="pre">plano_config.yaml</span></code> file.</p>
|
||||
</div>
|
||||
<p>For <code class="docutils literal notranslate"><span class="pre">arch_config.yaml</span></code>, you can use any sample configuration defined earlier in the documentation. For example, you can try the <a class="reference internal" href="../guides/llm_router.html#llm-router"><span class="std std-ref">LLM Routing</span></a> sample config.</p>
|
||||
<p>For <code class="docutils literal notranslate"><span class="pre">plano_config.yaml</span></code>, you can use any sample configuration defined earlier in the documentation. For example, you can try the <a class="reference internal" href="../guides/llm_router.html#llm-router"><span class="std std-ref">LLM Routing</span></a> sample config.</p>
|
||||
<section id="docker-compose-setup">
|
||||
<h3>Docker Compose Setup<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="#docker-compose-setup" x-intersect.margin.0%.0%.-70%.0%="activeSection = '#docker-compose-setup'"><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>Create a <code class="docutils literal notranslate"><span class="pre">docker-compose.yml</span></code> file with the following configuration:</p>
|
||||
<div class="highlight-yaml notranslate"><div class="highlight"><pre><span></span><code><span id="line-1"><span class="c1"># docker-compose.yml</span>
|
||||
</span><span id="line-2"><span class="nt">services</span><span class="p">:</span>
|
||||
</span><span id="line-3"><span class="w"> </span><span class="nt">archgw</span><span class="p">:</span>
|
||||
</span><span id="line-4"><span class="w"> </span><span class="nt">image</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">katanemo/archgw:0.3.22</span>
|
||||
</span><span id="line-5"><span class="w"> </span><span class="nt">container_name</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">archgw</span>
|
||||
</span><span id="line-3"><span class="w"> </span><span class="nt">plano</span><span class="p">:</span>
|
||||
</span><span id="line-4"><span class="w"> </span><span class="nt">image</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">katanemo/plano:0.4.0</span>
|
||||
</span><span id="line-5"><span class="w"> </span><span class="nt">container_name</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">plano</span>
|
||||
</span><span id="line-6"><span class="w"> </span><span class="nt">ports</span><span class="p">:</span>
|
||||
</span><span id="line-7"><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="s">"10000:10000"</span><span class="w"> </span><span class="c1"># ingress (client -> arch)</span>
|
||||
</span><span id="line-8"><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="s">"12000:12000"</span><span class="w"> </span><span class="c1"># egress (arch -> upstream/llm proxy)</span>
|
||||
</span><span id="line-7"><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="s">"10000:10000"</span><span class="w"> </span><span class="c1"># ingress (client -> plano)</span>
|
||||
</span><span id="line-8"><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="s">"12000:12000"</span><span class="w"> </span><span class="c1"># egress (plano -> upstream/llm proxy)</span>
|
||||
</span><span id="line-9"><span class="w"> </span><span class="nt">volumes</span><span class="p">:</span>
|
||||
</span><span id="line-10"><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">./arch_config.yaml:/app/arch_config.yaml:ro</span>
|
||||
</span><span id="line-10"><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">./plano_config.yaml:/app/plano_config.yaml:ro</span>
|
||||
</span><span id="line-11"><span class="w"> </span><span class="nt">environment</span><span class="p">:</span>
|
||||
</span><span id="line-12"><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">OPENAI_API_KEY=${OPENAI_API_KEY:?error}</span>
|
||||
</span><span id="line-13"><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">ANTHROPIC_API_KEY=${ANTHROPIC_API_KEY:?error}</span>
|
||||
|
|
@ -193,14 +188,14 @@
|
|||
</section>
|
||||
<section id="starting-the-stack">
|
||||
<h3>Starting the Stack<a @click.prevent="window.navigator.clipboard.writeText($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="#starting-the-stack" x-intersect.margin.0%.0%.-70%.0%="activeSection = '#starting-the-stack'"><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>Start the services from the directory containing <code class="docutils literal notranslate"><span class="pre">docker-compose.yml</span></code> and <code class="docutils literal notranslate"><span class="pre">arch_config.yaml</span></code>:</p>
|
||||
<p>Start the services from the directory containing <code class="docutils literal notranslate"><span class="pre">docker-compose.yml</span></code> and <code class="docutils literal notranslate"><span class="pre">plano_config.yaml</span></code>:</p>
|
||||
<div class="highlight-bash notranslate"><div class="highlight"><pre><span></span><code><span id="line-1"><span class="c1"># Set required environment variables and start services</span>
|
||||
</span><span id="line-2"><span class="nv">OPENAI_API_KEY</span><span class="o">=</span>xxx<span class="w"> </span><span class="nv">ANTHROPIC_API_KEY</span><span class="o">=</span>yyy<span class="w"> </span>docker<span class="w"> </span>compose<span class="w"> </span>up<span class="w"> </span>-d
|
||||
</span></code></pre></div>
|
||||
</div>
|
||||
<p>Check container health and logs:</p>
|
||||
<div class="highlight-bash notranslate"><div class="highlight"><pre><span></span><code><span id="line-1">docker<span class="w"> </span>compose<span class="w"> </span>ps
|
||||
</span><span id="line-2">docker<span class="w"> </span>compose<span class="w"> </span>logs<span class="w"> </span>-f<span class="w"> </span>archgw
|
||||
</span><span id="line-2">docker<span class="w"> </span>compose<span class="w"> </span>logs<span class="w"> </span>-f<span class="w"> </span>plano
|
||||
</span></code></pre></div>
|
||||
</div>
|
||||
</section>
|
||||
|
|
@ -211,14 +206,14 @@
|
|||
<section id="gateway-smoke-test">
|
||||
<h3>Gateway Smoke Test<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="#gateway-smoke-test" x-intersect.margin.0%.0%.-70%.0%="activeSection = '#gateway-smoke-test'"><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>Test the chat completion endpoint with automatic routing:</p>
|
||||
<div class="highlight-bash notranslate"><div class="highlight"><pre><span></span><code><span id="line-1"><span class="c1"># Request handled by the gateway. 'model: "none"' lets Arch decide routing</span>
|
||||
<div class="highlight-bash notranslate"><div class="highlight"><pre><span></span><code><span id="line-1"><span class="c1"># Request handled by the gateway. 'model: "none"' lets Plano decide routing</span>
|
||||
</span><span id="line-2">curl<span class="w"> </span>--header<span class="w"> </span><span class="s1">'Content-Type: application/json'</span><span class="w"> </span><span class="se">\</span>
|
||||
</span><span id="line-3"><span class="w"> </span>--data<span class="w"> </span><span class="s1">'{"messages":[{"role":"user","content":"tell me a joke"}], "model":"none"}'</span><span class="w"> </span><span class="se">\</span>
|
||||
</span><span id="line-4"><span class="w"> </span>http://localhost:12000/v1/chat/completions<span class="w"> </span><span class="p">|</span><span class="w"> </span>jq<span class="w"> </span>.model
|
||||
</span></code></pre></div>
|
||||
</div>
|
||||
<p>Expected output:</p>
|
||||
<div class="highlight-json notranslate"><div class="highlight"><pre><span></span><code><span id="line-1"><span class="s2">"gpt-4o-2024-08-06"</span>
|
||||
<div class="highlight-json notranslate"><div class="highlight"><pre><span></span><code><span id="line-1"><span class="s2">"gpt-5.2"</span>
|
||||
</span></code></pre></div>
|
||||
</div>
|
||||
</section>
|
||||
|
|
@ -226,12 +221,12 @@
|
|||
<h3>Model-Based Routing<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="#model-based-routing" x-intersect.margin.0%.0%.-70%.0%="activeSection = '#model-based-routing'"><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>Test explicit provider and model routing:</p>
|
||||
<div class="highlight-bash notranslate"><div class="highlight"><pre><span></span><code><span id="line-1">curl<span class="w"> </span>-s<span class="w"> </span>-H<span class="w"> </span><span class="s2">"Content-Type: application/json"</span><span class="w"> </span><span class="se">\</span>
|
||||
</span><span id="line-2"><span class="w"> </span>-d<span class="w"> </span><span class="s1">'{"messages":[{"role":"user","content":"Explain quantum computing"}], "model":"anthropic/claude-3-5-sonnet-20241022"}'</span><span class="w"> </span><span class="se">\</span>
|
||||
</span><span id="line-2"><span class="w"> </span>-d<span class="w"> </span><span class="s1">'{"messages":[{"role":"user","content":"Explain quantum computing"}], "model":"anthropic/claude-sonnet-4-5"}'</span><span class="w"> </span><span class="se">\</span>
|
||||
</span><span id="line-3"><span class="w"> </span>http://localhost:12000/v1/chat/completions<span class="w"> </span><span class="p">|</span><span class="w"> </span>jq<span class="w"> </span>.model
|
||||
</span></code></pre></div>
|
||||
</div>
|
||||
<p>Expected output:</p>
|
||||
<div class="highlight-json notranslate"><div class="highlight"><pre><span></span><code><span id="line-1"><span class="s2">"claude-3-5-sonnet-20241022"</span>
|
||||
<div class="highlight-json notranslate"><div class="highlight"><pre><span></span><code><span id="line-1"><span class="s2">"claude-sonnet-4-5"</span>
|
||||
</span></code></pre></div>
|
||||
</div>
|
||||
</section>
|
||||
|
|
@ -241,18 +236,18 @@
|
|||
<section id="common-issues-and-solutions">
|
||||
<h3>Common Issues and Solutions<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="#common-issues-and-solutions" x-intersect.margin.0%.0%.-70%.0%="activeSection = '#common-issues-and-solutions'"><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>
|
||||
<dl class="simple">
|
||||
<dt><strong>Environment Variables</strong></dt><dd><p>Ensure all environment variables (<code class="docutils literal notranslate"><span class="pre">OPENAI_API_KEY</span></code>, <code class="docutils literal notranslate"><span class="pre">ANTHROPIC_API_KEY</span></code>, etc.) used by <code class="docutils literal notranslate"><span class="pre">arch_config.yaml</span></code> are set before starting services.</p>
|
||||
<dt><strong>Environment Variables</strong></dt><dd><p>Ensure all environment variables (<code class="docutils literal notranslate"><span class="pre">OPENAI_API_KEY</span></code>, <code class="docutils literal notranslate"><span class="pre">ANTHROPIC_API_KEY</span></code>, etc.) used by <code class="docutils literal notranslate"><span class="pre">plano_config.yaml</span></code> are set before starting services.</p>
|
||||
</dd>
|
||||
<dt><strong>TLS/Connection Errors</strong></dt><dd><p>If you encounter TLS or connection errors to upstream providers:</p>
|
||||
<ul class="simple">
|
||||
<li><p>Check DNS resolution</p></li>
|
||||
<li><p>Verify proxy settings</p></li>
|
||||
<li><p>Confirm correct protocol and port in your <code class="docutils literal notranslate"><span class="pre">arch_config</span></code> endpoints</p></li>
|
||||
<li><p>Confirm correct protocol and port in your <code class="docutils literal notranslate"><span class="pre">plano_config</span></code> endpoints</p></li>
|
||||
</ul>
|
||||
</dd>
|
||||
<dt><strong>Verbose Logging</strong></dt><dd><p>To enable more detailed logs for debugging:</p>
|
||||
<ul class="simple">
|
||||
<li><p>Run archgw with a higher component log level</p></li>
|
||||
<li><p>Run plano with a higher component log level</p></li>
|
||||
<li><p>See the <a class="reference internal" href="../guides/observability/observability.html#observability"><span class="std std-ref">Observability</span></a> guide for logging and monitoring details</p></li>
|
||||
<li><p>Rebuild the image if required with updated log configuration</p></li>
|
||||
</ul>
|
||||
|
|
@ -265,11 +260,11 @@
|
|||
</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="../build_with_arch/multi_turn.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="tech_overview/threading_model.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>
|
||||
Multi-Turn
|
||||
Threading Model
|
||||
</a>
|
||||
</div>
|
||||
<div class="ml-auto">
|
||||
|
|
@ -305,12 +300,12 @@
|
|||
</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">© 2025, Katanemo Labs, Inc Last updated: Dec 23, 2025. </p>
|
||||
<p class="text-sm leading-loose text-center text-muted-foreground md:text-left">© 2025, Katanemo Labs, Inc Last updated: Dec 24, 2025. </p>
|
||||
</div>
|
||||
</div>
|
||||
</footer>
|
||||
</div>
|
||||
<script src="../_static/documentation_options.js?v=3bad885e"></script>
|
||||
<script src="../_static/documentation_options.js?v=8cf1ab6b"></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>
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue