mirror of
https://github.com/katanemo/plano.git
synced 2026-06-29 15:49:40 +02:00
deploy: e224cba3e3
This commit is contained in:
adilhafeez
parent
0898a9aa15
commit
c25ce33efc
68 changed files with 9799 additions and 4588 deletions
|
|
@ -7,17 +7,18 @@
|
|||
<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>Configuration Reference | Arch Docs v0.3.22</title>
|
||||
<meta content="Configuration Reference | Arch Docs v0.3.22" property="og:title"/>
|
||||
<meta content="Configuration Reference | Arch Docs v0.3.22" name="twitter:title"/>
|
||||
<title>Configuration Reference | Plano Docs v0.4</title>
|
||||
<meta content="Configuration Reference | Plano Docs v0.4" property="og:title"/>
|
||||
<meta content="Configuration Reference | 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/configuration_reference.html" rel="canonical"/>
|
||||
<link href="../_static/favicon.ico" rel="icon"/>
|
||||
<link href="../search.html" rel="search" title="Search"/>
|
||||
<link href="llms_txt.html" rel="next" title="llms.txt"/>
|
||||
<link href="deployment.html" rel="prev" title="Deployment"/>
|
||||
<script>
|
||||
<!-- Prevent Flash of wrong theme -->
|
||||
|
|
@ -38,7 +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>
|
||||
|
|
@ -55,7 +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>
|
||||
|
|
@ -74,40 +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>
|
||||
|
|
@ -117,27 +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"><a class="reference internal" href="deployment.html">Deployment</a></li>
|
||||
<li class="toctree-l1 current"><a class="current reference internal" href="#">Configuration Reference</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="llms_txt.html">llms.txt</a></li>
|
||||
</ul>
|
||||
</nav>
|
||||
</div>
|
||||
|
|
@ -152,7 +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>
|
||||
|
|
@ -162,111 +158,120 @@
|
|||
<div id="content" role="main">
|
||||
<section id="configuration-reference">
|
||||
<span id="id1"></span><h1>Configuration Reference<a @click.prevent="window.navigator.clipboard.writeText($el.href); $el.setAttribute('data-tooltip', 'Copied!'); setTimeout(() => $el.setAttribute('data-tooltip', 'Copy link to this element'), 2000)" aria-label="Copy link to this element" class="headerlink" data-tooltip="Copy link to this element" href="#configuration-reference"><svg height="1em" viewbox="0 0 24 24" width="1em" xmlns="http://www.w3.org/2000/svg"><path d="M3.9 12c0-1.71 1.39-3.1 3.1-3.1h4V7H7c-2.76 0-5 2.24-5 5s2.24 5 5 5h4v-1.9H7c-1.71 0-3.1-1.39-3.1-3.1zM8 13h8v-2H8v2zm9-6h-4v1.9h4c1.71 0 3.1 1.39 3.1 3.1s-1.39 3.1-3.1 3.1h-4V17h4c2.76 0 5-2.24 5-5s-2.24-5-5-5z"></path></svg></a></h1>
|
||||
<p>The following is a complete reference of the <code class="docutils literal notranslate"><span class="pre">arch_config.yml</span></code> that controls the behavior of a single instance of
|
||||
<p>The following is a complete reference of the <code class="docutils literal notranslate"><span class="pre">plano_config.yml</span></code> that controls the behavior of a single instance of
|
||||
the Arch gateway. This where you enable capabilities like routing to upstream LLm providers, defining prompt_targets
|
||||
where prompts get routed to, apply guardrails, and enable critical agent observability features.</p>
|
||||
<div class="literal-block-wrapper docutils container" id="id2">
|
||||
<div class="code-block-caption"><span class="caption-text"><a class="reference download internal" download="" href="../_downloads/ca9d3b7116524473d8adbde7cf15d167/arch_config_full_reference.yaml"><code class="xref download docutils literal notranslate"><span class="pre">Arch</span> <span class="pre">Configuration</span> <span class="pre">-</span> <span class="pre">Full</span> <span class="pre">Reference</span></code></a></span><a @click.prevent="window.navigator.clipboard.writeText($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><span id="line-3"><span class="linenos"> 3</span><span class="nt">listeners</span><span class="p">:</span>
|
||||
</span><span id="line-4"><span class="linenos"> 4</span><span class="w"> </span><span class="nt">ingress_traffic</span><span class="p">:</span>
|
||||
</span><span id="line-5"><span class="linenos"> 5</span><span class="w"> </span><span class="nt">address</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">0.0.0.0</span>
|
||||
</span><span id="line-6"><span class="linenos"> 6</span><span class="w"> </span><span class="nt">port</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">10000</span>
|
||||
</span><span id="line-7"><span class="linenos"> 7</span><span class="w"> </span><span class="nt">message_format</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">openai</span>
|
||||
</span><span id="line-8"><span class="linenos"> 8</span><span class="w"> </span><span class="nt">timeout</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">5s</span>
|
||||
</span><span id="line-9"><span class="linenos"> 9</span><span class="w"> </span><span class="nt">egress_traffic</span><span class="p">:</span>
|
||||
</span><span id="line-10"><span class="linenos"> 10</span><span class="w"> </span><span class="nt">address</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">0.0.0.0</span>
|
||||
</span><span id="line-11"><span class="linenos"> 11</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">12000</span>
|
||||
</span><span id="line-12"><span class="linenos"> 12</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">openai</span>
|
||||
</span><span id="line-13"><span class="linenos"> 13</span><span class="w"> </span><span class="nt">timeout</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">5s</span>
|
||||
</span><span id="line-14"><span class="linenos"> 14</span>
|
||||
</span><span id="line-15"><span class="linenos"> 15</span><span class="c1"># Arch creates a round-robin load balancing between different endpoints, managed via the cluster subsystem.</span>
|
||||
</span><span id="line-16"><span class="linenos"> 16</span><span class="nt">endpoints</span><span class="p">:</span>
|
||||
</span><span id="line-17"><span class="linenos"> 17</span><span class="w"> </span><span class="nt">app_server</span><span class="p">:</span>
|
||||
</span><span id="line-18"><span class="linenos"> 18</span><span class="w"> </span><span class="c1"># value could be ip address or a hostname with port</span>
|
||||
</span><span id="line-19"><span class="linenos"> 19</span><span class="w"> </span><span class="c1"># this could also be a list of endpoints for load balancing</span>
|
||||
</span><span id="line-20"><span class="linenos"> 20</span><span class="w"> </span><span class="c1"># for example endpoint: [ ip1:port, ip2:port ]</span>
|
||||
</span><span id="line-21"><span class="linenos"> 21</span><span class="w"> </span><span class="nt">endpoint</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">127.0.0.1:80</span>
|
||||
</span><span id="line-22"><span class="linenos"> 22</span><span class="w"> </span><span class="c1"># max time to wait for a connection to be established</span>
|
||||
</span><span id="line-23"><span class="linenos"> 23</span><span class="w"> </span><span class="nt">connect_timeout</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">0.005s</span>
|
||||
</span><span id="line-24"><span class="linenos"> 24</span>
|
||||
</span><span id="line-25"><span class="linenos"> 25</span><span class="w"> </span><span class="nt">mistral_local</span><span class="p">:</span>
|
||||
</span><span id="line-26"><span class="linenos"> 26</span><span class="w"> </span><span class="nt">endpoint</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">127.0.0.1:8001</span>
|
||||
</span><span id="line-27"><span class="linenos"> 27</span>
|
||||
</span><span id="line-28"><span class="linenos"> 28</span><span class="w"> </span><span class="nt">error_target</span><span class="p">:</span>
|
||||
</span><span id="line-29"><span class="linenos"> 29</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">error_target_1</span>
|
||||
</span><span id="line-30"><span class="linenos"> 30</span>
|
||||
</span><span id="line-31"><span class="linenos"> 31</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-32"><span class="linenos"> 32</span><span class="nt">llm_providers</span><span class="p">:</span>
|
||||
</span><span id="line-33"><span class="linenos"> 33</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/gpt-4o</span>
|
||||
</span><span id="line-34"><span class="linenos"> 34</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-35"><span class="linenos"> 35</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">openai/gpt-4o</span>
|
||||
</span><span id="line-36"><span class="linenos"> 36</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>
|
||||
<div class="code-block-caption"><span class="caption-text"><a class="reference download internal" download="" href="../_downloads/ca9d3b7116524473d8adbde7cf15d167/arch_config_full_reference.yaml"><code class="xref download docutils literal notranslate"><span class="pre">Plano</span> <span class="pre">Configuration</span> <span class="pre">-</span> <span class="pre">Full</span> <span class="pre">Reference</span></code></a></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="c1"># Arch Gateway configuration version</span>
|
||||
</span><span id="line-2"><span class="linenos"> 2</span><span class="nt">version</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">v0.3.0</span>
|
||||
</span><span id="line-3"><span class="linenos"> 3</span>
|
||||
</span><span id="line-4"><span class="linenos"> 4</span>
|
||||
</span><span id="line-5"><span class="linenos"> 5</span><span class="c1"># External HTTP agents - API type is controlled by request path (/v1/responses, /v1/messages, /v1/chat/completions)</span>
|
||||
</span><span id="line-6"><span class="linenos"> 6</span><span class="nt">agents</span><span class="p">:</span>
|
||||
</span><span id="line-7"><span class="linenos"> 7</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">id</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">weather_agent</span><span class="w"> </span><span class="c1"># Example agent for weather</span>
|
||||
</span><span id="line-8"><span class="linenos"> 8</span><span class="w"> </span><span class="nt">url</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">http://host.docker.internal:10510</span>
|
||||
</span><span id="line-9"><span class="linenos"> 9</span>
|
||||
</span><span id="line-10"><span class="linenos"> 10</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">id</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">flight_agent</span><span class="w"> </span><span class="c1"># Example agent for flights</span>
|
||||
</span><span id="line-11"><span class="linenos"> 11</span><span class="w"> </span><span class="nt">url</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">http://host.docker.internal:10520</span>
|
||||
</span><span id="line-12"><span class="linenos"> 12</span>
|
||||
</span><span id="line-13"><span class="linenos"> 13</span>
|
||||
</span><span id="line-14"><span class="linenos"> 14</span><span class="c1"># MCP filters applied to requests/responses (e.g., input validation, query rewriting)</span>
|
||||
</span><span id="line-15"><span class="linenos"> 15</span><span class="nt">filters</span><span class="p">:</span>
|
||||
</span><span id="line-16"><span class="linenos"> 16</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">id</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">input_guards</span><span class="w"> </span><span class="c1"># Example filter for input validation</span>
|
||||
</span><span id="line-17"><span class="linenos"> 17</span><span class="w"> </span><span class="nt">url</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">http://host.docker.internal:10500</span>
|
||||
</span><span id="line-18"><span class="linenos"> 18</span><span class="w"> </span><span class="c1"># type: mcp (default)</span>
|
||||
</span><span id="line-19"><span class="linenos"> 19</span><span class="w"> </span><span class="c1"># transport: streamable-http (default)</span>
|
||||
</span><span id="line-20"><span class="linenos"> 20</span><span class="w"> </span><span class="c1"># tool: input_guards (default - same as filter id)</span>
|
||||
</span><span id="line-21"><span class="linenos"> 21</span>
|
||||
</span><span id="line-22"><span class="linenos"> 22</span>
|
||||
</span><span id="line-23"><span class="linenos"> 23</span><span class="c1"># LLM provider configurations with API keys and model routing</span>
|
||||
</span><span id="line-24"><span class="linenos"> 24</span><span class="nt">model_providers</span><span class="p">:</span>
|
||||
</span><span id="line-25"><span class="linenos"> 25</span><span class="w"> </span><span class="p p-Indicator">-</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">openai/gpt-4o</span>
|
||||
</span><span id="line-26"><span class="linenos"> 26</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-27"><span class="linenos"> 27</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-28"><span class="linenos"> 28</span>
|
||||
</span><span id="line-29"><span class="linenos"> 29</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">model</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">openai/gpt-4o-mini</span>
|
||||
</span><span id="line-30"><span class="linenos"> 30</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">$OPENAI_API_KEY</span>
|
||||
</span><span id="line-31"><span class="linenos"> 31</span>
|
||||
</span><span id="line-32"><span class="linenos"> 32</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">model</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">anthropic/claude-sonnet-4-0</span>
|
||||
</span><span id="line-33"><span class="linenos"> 33</span><span class="w"> </span><span class="nt">access_key</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">$ANTHROPIC_API_KEY</span>
|
||||
</span><span id="line-34"><span class="linenos"> 34</span>
|
||||
</span><span id="line-35"><span class="linenos"> 35</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">model</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">mistral/ministral-3b-latest</span>
|
||||
</span><span id="line-36"><span class="linenos"> 36</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">$MISTRAL_API_KEY</span>
|
||||
</span><span id="line-37"><span class="linenos"> 37</span>
|
||||
</span><span id="line-38"><span class="linenos"> 38</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">access_key</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">$MISTRAL_API_KEY</span>
|
||||
</span><span id="line-39"><span class="linenos"> 39</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">mistral/mistral-8x7b</span>
|
||||
</span><span id="line-40"><span class="linenos"> 40</span>
|
||||
</span><span id="line-41"><span class="linenos"> 41</span><span class="w"> </span><span class="p p-Indicator">-</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">mistral/mistral-7b-instruct</span>
|
||||
</span><span id="line-42"><span class="linenos"> 42</span><span class="w"> </span><span class="nt">base_url</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">http://mistral_local</span>
|
||||
</span><span id="line-38"><span class="linenos"> 38</span>
|
||||
</span><span id="line-39"><span class="linenos"> 39</span><span class="c1"># Model aliases - use friendly names instead of full provider model names</span>
|
||||
</span><span id="line-40"><span class="linenos"> 40</span><span class="nt">model_aliases</span><span class="p">:</span>
|
||||
</span><span id="line-41"><span class="linenos"> 41</span><span class="w"> </span><span class="nt">fast-llm</span><span class="p">:</span>
|
||||
</span><span id="line-42"><span class="linenos"> 42</span><span class="w"> </span><span class="nt">target</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">gpt-4o-mini</span>
|
||||
</span><span id="line-43"><span class="linenos"> 43</span>
|
||||
</span><span id="line-44"><span class="linenos"> 44</span><span class="c1"># Model aliases - friendly names that map to actual provider names</span>
|
||||
</span><span id="line-45"><span class="linenos"> 45</span><span class="nt">model_aliases</span><span class="p">:</span>
|
||||
</span><span id="line-46"><span class="linenos"> 46</span><span class="w"> </span><span class="c1"># Alias for summarization tasks -> fast/cheap model</span>
|
||||
</span><span id="line-47"><span class="linenos"> 47</span><span class="w"> </span><span class="nt">arch.summarize.v1</span><span class="p">:</span>
|
||||
</span><span id="line-48"><span class="linenos"> 48</span><span class="w"> </span><span class="nt">target</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">gpt-4o</span>
|
||||
</span><span id="line-49"><span class="linenos"> 49</span>
|
||||
</span><span id="line-50"><span class="linenos"> 50</span><span class="w"> </span><span class="c1"># Alias for general purpose tasks -> latest model</span>
|
||||
</span><span id="line-51"><span class="linenos"> 51</span><span class="w"> </span><span class="nt">arch.v1</span><span class="p">:</span>
|
||||
</span><span id="line-52"><span class="linenos"> 52</span><span class="w"> </span><span class="nt">target</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">mistral-8x7b</span>
|
||||
</span><span id="line-53"><span class="linenos"> 53</span>
|
||||
</span><span id="line-54"><span class="linenos"> 54</span><span class="c1"># provides a way to override default settings for the arch system</span>
|
||||
</span><span id="line-55"><span class="linenos"> 55</span><span class="nt">overrides</span><span class="p">:</span>
|
||||
</span><span id="line-56"><span class="linenos"> 56</span><span class="w"> </span><span class="c1"># By default Arch uses an NLI + embedding approach to match an incoming prompt to a prompt target.</span>
|
||||
</span><span id="line-57"><span class="linenos"> 57</span><span class="w"> </span><span class="c1"># The intent matching threshold is kept at 0.80, you can override this behavior if you would like</span>
|
||||
</span><span id="line-58"><span class="linenos"> 58</span><span class="w"> </span><span class="nt">prompt_target_intent_matching_threshold</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">0.60</span>
|
||||
</span><span id="line-59"><span class="linenos"> 59</span>
|
||||
</span><span id="line-60"><span class="linenos"> 60</span><span class="c1"># default system prompt used by all prompt targets</span>
|
||||
</span><span id="line-61"><span class="linenos"> 61</span><span class="nt">system_prompt</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">You are a network assistant that just offers facts; not advice on manufacturers or purchasing decisions.</span>
|
||||
</span><span id="line-62"><span class="linenos"> 62</span>
|
||||
</span><span id="line-63"><span class="linenos"> 63</span><span class="nt">prompt_guards</span><span class="p">:</span>
|
||||
</span><span id="line-64"><span class="linenos"> 64</span><span class="w"> </span><span class="nt">input_guards</span><span class="p">:</span>
|
||||
</span><span id="line-65"><span class="linenos"> 65</span><span class="w"> </span><span class="nt">jailbreak</span><span class="p">:</span>
|
||||
</span><span id="line-66"><span class="linenos"> 66</span><span class="w"> </span><span class="nt">on_exception</span><span class="p">:</span>
|
||||
</span><span id="line-67"><span class="linenos"> 67</span><span class="w"> </span><span class="nt">message</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">Looks like you're curious about my abilities, but I can only provide assistance within my programmed parameters.</span>
|
||||
</span><span id="line-68"><span class="linenos"> 68</span>
|
||||
</span><span id="line-69"><span class="linenos"> 69</span><span class="nt">prompt_targets</span><span class="p">:</span>
|
||||
</span><span id="line-70"><span class="linenos"> 70</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">information_extraction</span>
|
||||
</span><span id="line-71"><span class="linenos"> 71</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-72"><span class="linenos"> 72</span><span class="w"> </span><span class="nt">description</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">handel all scenarios that are question and answer in nature. Like summarization, information extraction, etc.</span>
|
||||
</span><span id="line-73"><span class="linenos"> 73</span><span class="w"> </span><span class="nt">endpoint</span><span class="p">:</span>
|
||||
</span><span id="line-74"><span class="linenos"> 74</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">app_server</span>
|
||||
</span><span id="line-75"><span class="linenos"> 75</span><span class="w"> </span><span class="nt">path</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">/agent/summary</span>
|
||||
</span><span id="line-76"><span class="linenos"> 76</span><span class="w"> </span><span class="nt">http_method</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">POST</span>
|
||||
</span><span id="line-77"><span class="linenos"> 77</span><span class="w"> </span><span class="c1"># Arch uses the default LLM and treats the response from the endpoint as the prompt to send to the LLM</span>
|
||||
</span><span id="line-78"><span class="linenos"> 78</span><span class="w"> </span><span class="nt">auto_llm_dispatch_on_response</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">true</span>
|
||||
</span><span id="line-79"><span class="linenos"> 79</span><span class="w"> </span><span class="c1"># override system prompt for this prompt target</span>
|
||||
</span><span id="line-80"><span class="linenos"> 80</span><span class="w"> </span><span class="nt">system_prompt</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">You are a helpful information extraction assistant. Use the information that is provided to you.</span>
|
||||
</span><span id="line-44"><span class="linenos"> 44</span><span class="w"> </span><span class="nt">smart-llm</span><span class="p">:</span>
|
||||
</span><span id="line-45"><span class="linenos"> 45</span><span class="w"> </span><span class="nt">target</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">gpt-4o</span>
|
||||
</span><span id="line-46"><span class="linenos"> 46</span>
|
||||
</span><span id="line-47"><span class="linenos"> 47</span>
|
||||
</span><span id="line-48"><span class="linenos"> 48</span><span class="c1"># HTTP listeners - entry points for agent routing, prompt targets, and direct LLM access</span>
|
||||
</span><span id="line-49"><span class="linenos"> 49</span><span class="nt">listeners</span><span class="p">:</span>
|
||||
</span><span id="line-50"><span class="linenos"> 50</span><span class="w"> </span><span class="c1"># Agent listener for routing requests to multiple agents</span>
|
||||
</span><span id="line-51"><span class="linenos"> 51</span><span class="w"> </span><span class="p p-Indicator">-</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">agent</span>
|
||||
</span><span id="line-52"><span class="linenos"> 52</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">travel_booking_service</span>
|
||||
</span><span id="line-53"><span class="linenos"> 53</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">8001</span>
|
||||
</span><span id="line-54"><span class="linenos"> 54</span><span class="w"> </span><span class="nt">router</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">plano_orchestrator_v1</span>
|
||||
</span><span id="line-55"><span class="linenos"> 55</span><span class="w"> </span><span class="nt">address</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">0.0.0.0</span>
|
||||
</span><span id="line-56"><span class="linenos"> 56</span><span class="w"> </span><span class="nt">agents</span><span class="p">:</span>
|
||||
</span><span id="line-57"><span class="linenos"> 57</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">id</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">rag_agent</span>
|
||||
</span><span id="line-58"><span class="linenos"> 58</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">virtual assistant for retrieval augmented generation tasks</span>
|
||||
</span><span id="line-59"><span class="linenos"> 59</span><span class="w"> </span><span class="nt">filter_chain</span><span class="p">:</span>
|
||||
</span><span id="line-60"><span class="linenos"> 60</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">input_guards</span>
|
||||
</span><span id="line-61"><span class="linenos"> 61</span>
|
||||
</span><span id="line-62"><span class="linenos"> 62</span><span class="w"> </span><span class="c1"># Model listener for direct LLM access</span>
|
||||
</span><span id="line-63"><span class="linenos"> 63</span><span class="w"> </span><span class="p p-Indicator">-</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">model</span>
|
||||
</span><span id="line-64"><span class="linenos"> 64</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">model_1</span>
|
||||
</span><span id="line-65"><span class="linenos"> 65</span><span class="w"> </span><span class="nt">address</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">0.0.0.0</span>
|
||||
</span><span id="line-66"><span class="linenos"> 66</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">12000</span>
|
||||
</span><span id="line-67"><span class="linenos"> 67</span>
|
||||
</span><span id="line-68"><span class="linenos"> 68</span><span class="w"> </span><span class="c1"># Prompt listener for function calling (for prompt_targets)</span>
|
||||
</span><span id="line-69"><span class="linenos"> 69</span><span class="w"> </span><span class="p p-Indicator">-</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">prompt</span>
|
||||
</span><span id="line-70"><span class="linenos"> 70</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">prompt_function_listener</span>
|
||||
</span><span id="line-71"><span class="linenos"> 71</span><span class="w"> </span><span class="nt">address</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">0.0.0.0</span>
|
||||
</span><span id="line-72"><span class="linenos"> 72</span><span class="w"> </span><span class="nt">port</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">10000</span>
|
||||
</span><span id="line-73"><span class="linenos"> 73</span><span class="w"> </span><span class="c1"># This listener is used for prompt_targets and function calling</span>
|
||||
</span><span id="line-74"><span class="linenos"> 74</span>
|
||||
</span><span id="line-75"><span class="linenos"> 75</span>
|
||||
</span><span id="line-76"><span class="linenos"> 76</span><span class="c1"># Reusable service endpoints</span>
|
||||
</span><span id="line-77"><span class="linenos"> 77</span><span class="nt">endpoints</span><span class="p">:</span>
|
||||
</span><span id="line-78"><span class="linenos"> 78</span><span class="w"> </span><span class="nt">app_server</span><span class="p">:</span>
|
||||
</span><span id="line-79"><span class="linenos"> 79</span><span class="w"> </span><span class="nt">endpoint</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">127.0.0.1:80</span>
|
||||
</span><span id="line-80"><span class="linenos"> 80</span><span class="w"> </span><span class="nt">connect_timeout</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">0.005s</span>
|
||||
</span><span id="line-81"><span class="linenos"> 81</span>
|
||||
</span><span id="line-82"><span class="linenos"> 82</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">reboot_network_device</span>
|
||||
</span><span id="line-83"><span class="linenos"> 83</span><span class="w"> </span><span class="nt">description</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">Reboot a specific network device</span>
|
||||
</span><span id="line-84"><span class="linenos"> 84</span><span class="w"> </span><span class="nt">endpoint</span><span class="p">:</span>
|
||||
</span><span id="line-85"><span class="linenos"> 85</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">app_server</span>
|
||||
</span><span id="line-86"><span class="linenos"> 86</span><span class="w"> </span><span class="nt">path</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">/agent/action</span>
|
||||
</span><span id="line-87"><span class="linenos"> 87</span><span class="w"> </span><span class="nt">parameters</span><span class="p">:</span>
|
||||
</span><span id="line-88"><span class="linenos"> 88</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">device_id</span>
|
||||
</span><span id="line-89"><span class="linenos"> 89</span><span class="w"> </span><span class="nt">type</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">str</span>
|
||||
</span><span id="line-90"><span class="linenos"> 90</span><span class="w"> </span><span class="nt">description</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">Identifier of the network device to reboot.</span>
|
||||
</span><span id="line-91"><span class="linenos"> 91</span><span class="w"> </span><span class="nt">required</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">true</span>
|
||||
</span><span id="line-92"><span class="linenos"> 92</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">confirmation</span>
|
||||
</span><span id="line-93"><span class="linenos"> 93</span><span class="w"> </span><span class="nt">type</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">bool</span>
|
||||
</span><span id="line-94"><span class="linenos"> 94</span><span class="w"> </span><span class="nt">description</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">Confirmation flag to proceed with reboot.</span>
|
||||
</span><span id="line-95"><span class="linenos"> 95</span><span class="w"> </span><span class="nt">default</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">false</span>
|
||||
</span><span id="line-96"><span class="linenos"> 96</span><span class="w"> </span><span class="nt">enum</span><span class="p">:</span><span class="w"> </span><span class="p p-Indicator">[</span><span class="nv">true</span><span class="p p-Indicator">,</span><span class="w"> </span><span class="nv">false</span><span class="p p-Indicator">]</span>
|
||||
</span><span id="line-97"><span class="linenos"> 97</span>
|
||||
</span><span id="line-98"><span class="linenos"> 98</span><span class="nt">tracing</span><span class="p">:</span>
|
||||
</span><span id="line-99"><span class="linenos"> 99</span><span class="w"> </span><span class="c1"># sampling rate. Note by default Arch works on OpenTelemetry compatible tracing.</span>
|
||||
</span><span id="line-100"><span class="linenos">100</span><span class="w"> </span><span class="nt">sampling_rate</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">0.1</span>
|
||||
</span><span id="line-82"><span class="linenos"> 82</span><span class="w"> </span><span class="nt">mistral_local</span><span class="p">:</span>
|
||||
</span><span id="line-83"><span class="linenos"> 83</span><span class="w"> </span><span class="nt">endpoint</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">127.0.0.1:8001</span>
|
||||
</span><span id="line-84"><span class="linenos"> 84</span>
|
||||
</span><span id="line-85"><span class="linenos"> 85</span>
|
||||
</span><span id="line-86"><span class="linenos"> 86</span><span class="c1"># Prompt targets for function calling and API orchestration</span>
|
||||
</span><span id="line-87"><span class="linenos"> 87</span><span class="nt">prompt_targets</span><span class="p">:</span>
|
||||
</span><span id="line-88"><span class="linenos"> 88</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">get_current_weather</span>
|
||||
</span><span id="line-89"><span class="linenos"> 89</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">Get current weather at a location.</span>
|
||||
</span><span id="line-90"><span class="linenos"> 90</span><span class="w"> </span><span class="nt">parameters</span><span class="p">:</span>
|
||||
</span><span id="line-91"><span class="linenos"> 91</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">location</span>
|
||||
</span><span id="line-92"><span class="linenos"> 92</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">The location to get the weather for</span>
|
||||
</span><span id="line-93"><span class="linenos"> 93</span><span class="w"> </span><span class="nt">required</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">true</span>
|
||||
</span><span id="line-94"><span class="linenos"> 94</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">string</span>
|
||||
</span><span id="line-95"><span class="linenos"> 95</span><span class="w"> </span><span class="nt">format</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">City, State</span>
|
||||
</span><span id="line-96"><span class="linenos"> 96</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">days</span>
|
||||
</span><span id="line-97"><span class="linenos"> 97</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">the number of days for the request</span>
|
||||
</span><span id="line-98"><span class="linenos"> 98</span><span class="w"> </span><span class="nt">required</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">true</span>
|
||||
</span><span id="line-99"><span class="linenos"> 99</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>
|
||||
</span><span id="line-100"><span class="linenos">100</span><span class="w"> </span><span class="nt">endpoint</span><span class="p">:</span>
|
||||
</span><span id="line-101"><span class="linenos">101</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">app_server</span>
|
||||
</span><span id="line-102"><span class="linenos">102</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">/weather</span>
|
||||
</span><span id="line-103"><span class="linenos">103</span><span class="w"> </span><span class="nt">http_method</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">POST</span>
|
||||
</span><span id="line-104"><span class="linenos">104</span>
|
||||
</span><span id="line-105"><span class="linenos">105</span>
|
||||
</span><span id="line-106"><span class="linenos">106</span><span class="c1"># OpenTelemetry tracing configuration</span>
|
||||
</span><span id="line-107"><span class="linenos">107</span><span class="nt">tracing</span><span class="p">:</span>
|
||||
</span><span id="line-108"><span class="linenos">108</span><span class="w"> </span><span class="c1"># Random sampling percentage (1-100)</span>
|
||||
</span><span id="line-109"><span class="linenos">109</span><span class="w"> </span><span class="nt">random_sampling</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">100</span>
|
||||
</span></code></pre></div>
|
||||
</div>
|
||||
</div>
|
||||
|
|
@ -280,18 +285,26 @@ where prompts get routed to, apply guardrails, and enable critical agent observa
|
|||
Deployment
|
||||
</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="llms_txt.html">
|
||||
llms.txt
|
||||
<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>
|
||||
</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">© 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>
|
||||
|
|
|
|||
|
|
@ -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>
|
||||
|
|
|
|||
189
resources/llms_txt.html
Executable file
189
resources/llms_txt.html
Executable file
|
|
@ -0,0 +1,189 @@
|
|||
<!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>llms.txt | Plano Docs v0.4</title>
|
||||
<meta content="llms.txt | Plano Docs v0.4" property="og:title"/>
|
||||
<meta content="llms.txt | 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/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/llms_txt.html" rel="canonical"/>
|
||||
<link href="../_static/favicon.ico" rel="icon"/>
|
||||
<link href="../search.html" rel="search" title="Search"/>
|
||||
<link href="configuration_reference.html" rel="prev" title="Configuration Reference"/>
|
||||
<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">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>
|
||||
</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/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>
|
||||
</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">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-EH2VW19FXE"></script>
|
||||
<script>
|
||||
window.dataLayer = window.dataLayer || [];
|
||||
function gtag(){dataLayer.push(arguments);}
|
||||
gtag('js', new Date());
|
||||
|
||||
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_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"><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>
|
||||
</ul>
|
||||
</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/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>
|
||||
<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"><a class="reference internal" href="deployment.html">Deployment</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="configuration_reference.html">Configuration Reference</a></li>
|
||||
<li class="toctree-l1 current"><a class="current reference internal" href="#">llms.txt</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">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>
|
||||
</a>
|
||||
<div class="mr-1">/</div><span aria-current="page" class="font-medium text-foreground overflow-hidden text-ellipsis whitespace-nowrap">llms.txt</span>
|
||||
</nav>
|
||||
<div id="content" role="main">
|
||||
<section id="llms-txt">
|
||||
<h1>llms.txt<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="#llms-txt"><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 project generates a single plaintext file containing the compiled text of all documentation pages, useful for large context models to reference Plano documentation.</p>
|
||||
<p>Open it here: <a class="reference external" href="../includes/llms.txt" rel="nofollow noopener">llms.txt<svg fill="currentColor" height="1em" stroke="none" viewbox="0 96 960 960" width="1em" xmlns="http://www.w3.org/2000/svg"><path d="M188 868q-11-11-11-28t11-28l436-436H400q-17 0-28.5-11.5T360 336q0-17 11.5-28.5T400 296h320q17 0 28.5 11.5T760 336v320q0 17-11.5 28.5T720 696q-17 0-28.5-11.5T680 656V432L244 868q-11 11-28 11t-28-11Z"></path></svg></a></p>
|
||||
</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="configuration_reference.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>
|
||||
Configuration Reference
|
||||
</a>
|
||||
</div>
|
||||
</div></div>
|
||||
</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">© 2025, Katanemo Labs, Inc Last updated: Dec 24, 2025. </p>
|
||||
</div>
|
||||
</div>
|
||||
</footer>
|
||||
</div>
|
||||
<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>
|
||||
<script src="../_static/design-tabs.js?v=f930bc37"></script>
|
||||
</body>
|
||||
</html>
|
||||
209
resources/tech_overview/model_serving.html
Executable file
209
resources/tech_overview/model_serving.html
Executable file
|
|
@ -0,0 +1,209 @@
|
|||
<!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>Bright Staff | Plano Docs v0.4</title>
|
||||
<meta content="Bright Staff | Plano Docs v0.4" property="og:title"/>
|
||||
<meta content="Bright Staff | 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/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/tech_overview/model_serving.html" rel="canonical"/>
|
||||
<link href="../../_static/favicon.ico" rel="icon"/>
|
||||
<link href="../../search.html" rel="search" title="Search"/>
|
||||
<link href="threading_model.html" rel="next" title="Threading Model"/>
|
||||
<link href="request_lifecycle.html" rel="prev" title="Request Lifecycle"/>
|
||||
<script>
|
||||
<!-- Prevent Flash of wrong theme -->
|
||||
const userPreference = localStorage.getItem('darkMode');
|
||||
let mode;
|
||||
if (userPreference === 'dark' || window.matchMedia('(prefers-color-scheme: dark)').matches) {
|
||||
mode = 'dark';
|
||||
document.documentElement.classList.add('dark');
|
||||
} else {
|
||||
mode = 'light';
|
||||
}
|
||||
if (!userPreference) {localStorage.setItem('darkMode', mode)}
|
||||
</script>
|
||||
</head>
|
||||
<body :class="{ 'overflow-hidden': showSidebar }" class="min-h-screen font-sans antialiased bg-background text-foreground" x-data="{ showSidebar: false, showScrollTop: false }">
|
||||
<div @click.self="showSidebar = false" class="fixed inset-0 z-50 overflow-hidden bg-background/80 backdrop-blur-sm md:hidden" x-cloak="" x-show="showSidebar"></div><div class="relative flex flex-col min-h-screen" id="page"><a class="absolute top-0 left-0 z-[100] block bg-background p-4 text-xl transition -translate-x-full opacity-0 focus:translate-x-0 focus:opacity-100" href="#content">
|
||||
Skip to content
|
||||
</a><header class="sticky top-0 z-40 w-full border-b shadow-sm border-border supports-backdrop-blur:bg-background/60 bg-background/95 backdrop-blur"><div class="container flex items-center h-14">
|
||||
<div class="hidden mr-4 md:flex">
|
||||
<a class="flex items-center mr-6" href="../../index.html">
|
||||
<img alt="Logo" class="mr-2 dark:invert" height="24" src="../../_static/favicon.ico" width="24"/><span class="hidden font-bold sm:inline-block text-clip whitespace-nowrap">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>
|
||||
</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/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>
|
||||
</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">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-EH2VW19FXE"></script>
|
||||
<script>
|
||||
window.dataLayer = window.dataLayer || [];
|
||||
function gtag(){dataLayer.push(arguments);}
|
||||
gtag('js', new Date());
|
||||
|
||||
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_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"><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>
|
||||
</ul>
|
||||
</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/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>
|
||||
<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 current" x-data="{ expanded: $el.classList.contains('current') ? true : false }"><a :class="{ 'expanded' : expanded }" @click="expanded = !expanded" class="reference internal expandable" href="tech_overview.html">Tech Overview<button @click.prevent.stop="expanded = !expanded" type="button"><span class="sr-only"></span><svg fill="currentColor" height="18px" stroke="none" viewbox="0 0 24 24" width="18px" xmlns="http://www.w3.org/2000/svg"><path d="M10 6L8.59 7.41 13.17 12l-4.58 4.59L10 18l6-6z"></path></svg></button></a><ul class="current" x-show="expanded">
|
||||
<li class="toctree-l2"><a class="reference internal" href="request_lifecycle.html">Request Lifecycle</a></li>
|
||||
<li class="toctree-l2 current"><a class="current reference internal" href="#">Bright Staff</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="threading_model.html">Threading Model</a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../deployment.html">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>
|
||||
</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">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>
|
||||
</a>
|
||||
<div class="mr-1">/</div><a class="hover:text-foreground overflow-hidden text-ellipsis whitespace-nowrap" href="tech_overview.html">Tech Overview</a>
|
||||
<div class="mr-1">/</div><span aria-current="page" class="font-medium text-foreground overflow-hidden text-ellipsis whitespace-nowrap">Bright Staff</span>
|
||||
</nav>
|
||||
<div id="content" role="main">
|
||||
<section id="bright-staff">
|
||||
<span id="id1"></span><h1>Bright Staff<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="#bright-staff"><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>Bright Staff is Plano’s memory-efficient, lightweight controller for agentic traffic. It sits inside the Plano
|
||||
data plane and makes real-time decisions about how prompts are handled, forwarded, and processed.</p>
|
||||
<p>Rather than running a separate “model server” subsystem, Plano relies on Envoy’s HTTP connection management
|
||||
and cluster subsystem to talk to different models and backends over HTTP(S). Bright Staff uses these primitives to:
|
||||
* Inspect prompts, conversation state, and metadata.
|
||||
* Decide which upstream model(s), tool backends, or APIs to call, and in what order.
|
||||
* Coordinate retries, fallbacks, and traffic splitting across providers and models.</p>
|
||||
<p>Plano is designed to run alongside your application servers in your cloud VPC, on-premises, or in local
|
||||
development. It does not require a GPU itself; GPUs live where your models are hosted (third-party APIs or your
|
||||
own deployments), and Plano reaches them via HTTP.</p>
|
||||
<a class="reference internal image-reference" href="../../_images/plano-system-architecture.png"><img alt="../../_images/plano-system-architecture.png" class="align-center" src="../../_images/plano-system-architecture.png" style="width: 40%;"/>
|
||||
</a>
|
||||
</section>
|
||||
</div><div class="flex justify-between items-center pt-6 mt-12 border-t border-border gap-4">
|
||||
<div class="mr-auto">
|
||||
<a class="inline-flex items-center justify-center rounded-md text-sm font-medium transition-colors border border-input hover:bg-accent hover:text-accent-foreground py-2 px-4" href="request_lifecycle.html">
|
||||
<svg class="mr-2 h-4 w-4" fill="none" height="24" stroke="currentColor" stroke-linecap="round" stroke-linejoin="round" stroke-width="2" viewbox="0 0 24 24" width="24" xmlns="http://www.w3.org/2000/svg">
|
||||
<polyline points="15 18 9 12 15 6"></polyline>
|
||||
</svg>
|
||||
Request Lifecycle
|
||||
</a>
|
||||
</div>
|
||||
<div class="ml-auto">
|
||||
<a class="inline-flex items-center justify-center rounded-md text-sm font-medium transition-colors border border-input hover:bg-accent hover:text-accent-foreground py-2 px-4" href="threading_model.html">
|
||||
Threading Model
|
||||
<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>
|
||||
</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">© 2025, Katanemo Labs, Inc Last updated: Dec 24, 2025. </p>
|
||||
</div>
|
||||
</div>
|
||||
</footer>
|
||||
</div>
|
||||
<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>
|
||||
<script src="../../_static/design-tabs.js?v=f930bc37"></script>
|
||||
</body>
|
||||
</html>
|
||||
386
resources/tech_overview/request_lifecycle.html
Executable file
386
resources/tech_overview/request_lifecycle.html
Executable file
|
|
@ -0,0 +1,386 @@
|
|||
<!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>Request Lifecycle | Plano Docs v0.4</title>
|
||||
<meta content="Request Lifecycle | Plano Docs v0.4" property="og:title"/>
|
||||
<meta content="Request Lifecycle | 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/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/tech_overview/request_lifecycle.html" rel="canonical"/>
|
||||
<link href="../../_static/favicon.ico" rel="icon"/>
|
||||
<link href="../../search.html" rel="search" title="Search"/>
|
||||
<link href="model_serving.html" rel="next" title="Bright Staff"/>
|
||||
<link href="tech_overview.html" rel="prev" title="Tech Overview"/>
|
||||
<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">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>
|
||||
</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/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>
|
||||
</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">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-EH2VW19FXE"></script>
|
||||
<script>
|
||||
window.dataLayer = window.dataLayer || [];
|
||||
function gtag(){dataLayer.push(arguments);}
|
||||
gtag('js', new Date());
|
||||
|
||||
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_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"><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>
|
||||
</ul>
|
||||
</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/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>
|
||||
<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 current" x-data="{ expanded: $el.classList.contains('current') ? true : false }"><a :class="{ 'expanded' : expanded }" @click="expanded = !expanded" class="reference internal expandable" href="tech_overview.html">Tech Overview<button @click.prevent.stop="expanded = !expanded" type="button"><span class="sr-only"></span><svg fill="currentColor" height="18px" stroke="none" viewbox="0 0 24 24" width="18px" xmlns="http://www.w3.org/2000/svg"><path d="M10 6L8.59 7.41 13.17 12l-4.58 4.59L10 18l6-6z"></path></svg></button></a><ul class="current" x-show="expanded">
|
||||
<li class="toctree-l2 current"><a class="current reference internal" href="#">Request Lifecycle</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="model_serving.html">Bright Staff</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="threading_model.html">Threading Model</a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../deployment.html">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>
|
||||
</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">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>
|
||||
</a>
|
||||
<div class="mr-1">/</div><a class="hover:text-foreground overflow-hidden text-ellipsis whitespace-nowrap" href="tech_overview.html">Tech Overview</a>
|
||||
<div class="mr-1">/</div><span aria-current="page" class="font-medium text-foreground overflow-hidden text-ellipsis whitespace-nowrap">Request Lifecycle</span>
|
||||
</nav>
|
||||
<div id="content" role="main">
|
||||
<section id="request-lifecycle">
|
||||
<span id="lifecycle-of-a-request"></span><h1>Request Lifecycle<a @click.prevent="window.navigator.clipboard.writeText($el.href); $el.setAttribute('data-tooltip', 'Copied!'); setTimeout(() => $el.setAttribute('data-tooltip', 'Copy link to this element'), 2000)" aria-label="Copy link to this element" class="headerlink" data-tooltip="Copy link to this element" href="#request-lifecycle"><svg height="1em" viewbox="0 0 24 24" width="1em" xmlns="http://www.w3.org/2000/svg"><path d="M3.9 12c0-1.71 1.39-3.1 3.1-3.1h4V7H7c-2.76 0-5 2.24-5 5s2.24 5 5 5h4v-1.9H7c-1.71 0-3.1-1.39-3.1-3.1zM8 13h8v-2H8v2zm9-6h-4v1.9h4c1.71 0 3.1 1.39 3.1 3.1s-1.39 3.1-3.1 3.1h-4V17h4c2.76 0 5-2.24 5-5s-2.24-5-5-5z"></path></svg></a></h1>
|
||||
<p>Below we describe the events in the lifecycle of a request passing through a Plano instance. We first
|
||||
describe how Plano fits into the request path and then the internal events that take place following
|
||||
the arrival of a request at Plano from downstream clients. We follow the request until the corresponding
|
||||
dispatch upstream and the response path.</p>
|
||||
<a class="reference internal image-reference" href="../../_images/network-topology-ingress-egress.png"><img alt="../../_images/network-topology-ingress-egress.png" class="align-center" src="../../_images/network-topology-ingress-egress.png" style="width: 100%;"/>
|
||||
</a>
|
||||
<section id="network-topology">
|
||||
<h2>Network topology<a @click.prevent="window.navigator.clipboard.writeText($el.href); $el.setAttribute('data-tooltip', 'Copied!'); setTimeout(() => $el.setAttribute('data-tooltip', 'Copy link to this element'), 2000)" aria-label="Copy link to this element" class="headerlink" data-tooltip="Copy link to this element" href="#network-topology" x-intersect.margin.0%.0%.-70%.0%="activeSection = '#network-topology'"><svg height="1em" viewbox="0 0 24 24" width="1em" xmlns="http://www.w3.org/2000/svg"><path d="M3.9 12c0-1.71 1.39-3.1 3.1-3.1h4V7H7c-2.76 0-5 2.24-5 5s2.24 5 5 5h4v-1.9H7c-1.71 0-3.1-1.39-3.1-3.1zM8 13h8v-2H8v2zm9-6h-4v1.9h4c1.71 0 3.1 1.39 3.1 3.1s-1.39 3.1-3.1 3.1h-4V17h4c2.76 0 5-2.24 5-5s-2.24-5-5-5z"></path></svg></a></h2>
|
||||
<p>How a request flows through the components in a network (including Plano) depends on the network’s topology.
|
||||
Plano can be used in a wide variety of networking topologies. We focus on the inner operations of Plano below,
|
||||
but briefly we address how Plano relates to the rest of the network in this section.</p>
|
||||
<ul class="simple">
|
||||
<li><p><strong>Downstream(Ingress)</strong> listeners take requests from upstream clients like a web UI or clients that forward
|
||||
prompts to you local application responses from the application flow back through Plano to the downstream.</p></li>
|
||||
<li><p><strong>Upstream(Egress)</strong> listeners take requests from the application and forward them to LLMs.</p></li>
|
||||
</ul>
|
||||
</section>
|
||||
<section id="high-level-architecture">
|
||||
<h2>High level architecture<a @click.prevent="window.navigator.clipboard.writeText($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="#high-level-architecture" x-intersect.margin.0%.0%.-70%.0%="activeSection = '#high-level-architecture'"><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>Plano is a set of <strong>two</strong> self-contained processes that are designed to run alongside your application servers
|
||||
(or on a separate server connected to your application servers via a network).</p>
|
||||
<p>The first process is designated to manage HTTP-level networking and connection management concerns (protocol management, request id generation, header sanitization, etc.), and the other process is a <strong>controller</strong>, which helps Plano make intelligent decisions about the incoming prompts. The controller hosts the purpose-built LLMs to manage several critical, but undifferentiated, prompt related tasks on behalf of developers.</p>
|
||||
<p>The request processing path in Plano has three main parts:</p>
|
||||
<ul class="simple">
|
||||
<li><p><a class="reference internal" href="../../concepts/listeners.html#plano-overview-listeners"><span class="std std-ref">Listener subsystem</span></a> which handles <strong>downstream</strong> and <strong>upstream</strong> request
|
||||
processing. It is responsible for managing the inbound(edge) and outbound(egress) request lifecycle. The downstream and upstream HTTP/2 codec lives here. This also includes the lifecycle of any <strong>upstream</strong> connection to an LLM provider or tool backend. The listenser subsystmem manages connection pools, load balancing, retries, and failover.</p></li>
|
||||
<li><p><a class="reference internal" href="model_serving.html#bright-staff"><span class="std std-ref">Bright Staff controller subsystem</span></a> is Plano’s memory-efficient, lightweight controller for agentic traffic. It sits inside the Plano data plane and makes real-time decisions about how prompts are handled, forwarded, and processed.</p></li>
|
||||
</ul>
|
||||
<p>These two subsystems are bridged with either the HTTP router filter, and the cluster manager subsystems of Envoy.</p>
|
||||
<p>Also, Plano utilizes <a class="reference external" href="https://blog.envoyproxy.io/envoy-threading-model-a8d44b922310" rel="nofollow noopener">Envoy event-based thread model<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>. A main thread is responsible for the server lifecycle, configuration processing, stats, etc. and some number of <a class="reference internal" href="threading_model.html#arch-overview-threading"><span class="std std-ref">worker threads</span></a> process requests. All threads operate around an event loop (<a class="reference external" href="https://libevent.org/" rel="nofollow noopener">libevent<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>) and any given downstream TCP connection will be handled by exactly one worker thread for its lifetime. Each worker thread maintains its own pool of TCP connections to upstream endpoints.</p>
|
||||
<p>Worker threads rarely share state and operate in a trivially parallel fashion. This threading model
|
||||
enables scaling to very high core count CPUs.</p>
|
||||
</section>
|
||||
<section id="request-flow-ingress">
|
||||
<h2>Request Flow (Ingress)<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="#request-flow-ingress" x-intersect.margin.0%.0%.-70%.0%="activeSection = '#request-flow-ingress'"><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>A brief outline of the lifecycle of a request and response using the example configuration above:</p>
|
||||
<ol class="arabic simple">
|
||||
<li><p><strong>TCP Connection Establishment</strong>:
|
||||
A TCP connection from downstream is accepted by an Plano listener running on a worker thread.
|
||||
The listener filter chain provides SNI and other pre-TLS information. The transport socket, typically TLS,
|
||||
decrypts incoming data for processing.</p></li>
|
||||
</ol>
|
||||
<ol class="arabic simple" start="3">
|
||||
<li><p><strong>Routing Decision (Agent vs Prompt Target)</strong>:
|
||||
The decrypted data stream is de-framed by the HTTP/2 codec in Plano’s HTTP connection manager. Plano performs
|
||||
intent matching (via the Bright Staff controller and prompt-handling logic) using the configured agents and
|
||||
<a class="reference internal" href="../../concepts/prompt_target.html#prompt-target"><span class="std std-ref">prompt targets</span></a>, determining whether this request should be handled by an agent workflow
|
||||
(with optional <a class="reference internal" href="../../concepts/filter_chain.html#filter-chain"><span class="std std-ref">Filter Chains</span></a>) or by a deterministic prompt target.</p></li>
|
||||
</ol>
|
||||
<p>4a. <strong>Agent Path: Orchestration and Filter Chains</strong></p>
|
||||
<blockquote>
|
||||
<div><p>If the request is routed to an <strong>agent</strong>, Plano executes any attached <a class="reference internal" href="../../concepts/filter_chain.html#filter-chain"><span class="std std-ref">Filter Chains</span></a> first. These filters can apply guardrails, rewrite prompts, or enrich context (for example, RAG retrieval) before the agent runs. Once filters complete, the Bright Staff controller orchestrates which downstream tools, APIs, or LLMs the agent should call and in what sequence.</p>
|
||||
<ul class="simple">
|
||||
<li><p>Plano may call one or more backend APIs or tools on behalf of the agent.</p></li>
|
||||
<li><p>If an endpoint cluster is identified, load balancing is performed, circuit breakers are checked, and the request is proxied to the appropriate upstream endpoint.</p></li>
|
||||
<li><p>If no specific endpoint is required, the prompt is sent to an upstream LLM using Plano’s model proxy for
|
||||
completion or summarization.</p></li>
|
||||
</ul>
|
||||
<p>For more on agent workflows and orchestration, see <a class="reference internal" href="../../concepts/prompt_target.html#prompt-target"><span class="std std-ref">Prompt Targets and Agents</span></a> and
|
||||
<a class="reference internal" href="../../concepts/filter_chain.html#filter-chain"><span class="std std-ref">Agent Filter Chains</span></a>.</p>
|
||||
</div></blockquote>
|
||||
<p>4b. <strong>Prompt Target Path: Deterministic Tool/API Calls</strong></p>
|
||||
<blockquote>
|
||||
<div><p>If the request is routed to a <strong>prompt target</strong>, Plano treats it as a deterministic, task-specific call.
|
||||
Plano engages its function-calling and parameter-gathering capabilities to extract the necessary details
|
||||
from the incoming prompt(s) and produce the structured inputs your backend expects.</p>
|
||||
<ul class="simple">
|
||||
<li><p><strong>Parameter Gathering</strong>: Plano extracts and validates parameters defined on the prompt target (for example,
|
||||
currency symbols, dates, or entity identifiers) so your backend does not need to parse natural language.</p></li>
|
||||
<li><p><strong>API Call Execution</strong>: Plano then routes the call to the configured backend endpoint. If an endpoint cluster is identified, load balancing and circuit-breaker checks are applied before proxying the request upstream.</p></li>
|
||||
</ul>
|
||||
<p>For more on how to design and configure prompt targets, see <a class="reference internal" href="../../concepts/prompt_target.html#prompt-target"><span class="std std-ref">Prompt Target</span></a>.</p>
|
||||
</div></blockquote>
|
||||
<ol class="arabic simple" start="5">
|
||||
<li><p><strong>Error Handling and Forwarding</strong>:
|
||||
Errors encountered during processing, such as failed function calls or guardrail detections, are forwarded to
|
||||
designated error targets. Error details are communicated through specific headers to the application:</p>
|
||||
<ul class="simple">
|
||||
<li><p><code class="docutils literal notranslate"><span class="pre">X-Function-Error-Code</span></code>: Code indicating the type of function call error.</p></li>
|
||||
<li><p><code class="docutils literal notranslate"><span class="pre">X-Prompt-Guard-Error-Code</span></code>: Code specifying violations detected by prompt guardrails.</p></li>
|
||||
<li><p>Additional headers carry messages and timestamps to aid in debugging and logging.</p></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li><p><strong>Response Handling</strong>:
|
||||
The upstream endpoint’s TLS transport socket encrypts the response, which is then proxied back downstream.
|
||||
Responses pass through HTTP filters in reverse order, ensuring any necessary processing or modification before final delivery.</p></li>
|
||||
</ol>
|
||||
</section>
|
||||
<section id="request-flow-egress">
|
||||
<h2>Request Flow (Egress)<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="#request-flow-egress" x-intersect.margin.0%.0%.-70%.0%="activeSection = '#request-flow-egress'"><svg height="1em" viewbox="0 0 24 24" width="1em" xmlns="http://www.w3.org/2000/svg"><path d="M3.9 12c0-1.71 1.39-3.1 3.1-3.1h4V7H7c-2.76 0-5 2.24-5 5s2.24 5 5 5h4v-1.9H7c-1.71 0-3.1-1.39-3.1-3.1zM8 13h8v-2H8v2zm9-6h-4v1.9h4c1.71 0 3.1 1.39 3.1 3.1s-1.39 3.1-3.1 3.1h-4V17h4c2.76 0 5-2.24 5-5s-2.24-5-5-5z"></path></svg></a></h2>
|
||||
<p>A brief outline of the lifecycle of a request and response in the context of egress traffic from an application to Large Language Models (LLMs) via Plano:</p>
|
||||
<ol class="arabic simple">
|
||||
<li><p><strong>HTTP Connection Establishment to LLM</strong>:
|
||||
Plano initiates an HTTP connection to the upstream LLM service. This connection is handled by Plano’s egress listener running on a worker thread. The connection typically uses a secure transport protocol such as HTTPS, ensuring the prompt data is encrypted before being sent to the LLM service.</p></li>
|
||||
<li><p><strong>Rate Limiting</strong>:
|
||||
Before sending the request to the LLM, Plano applies rate-limiting policies to ensure that the upstream LLM service is not overwhelmed by excessive traffic. Rate limits are enforced per client or service, ensuring fair usage and preventing accidental or malicious overload. If the rate limit is exceeded, Plano may return an appropriate HTTP error (e.g., 429 Too Many Requests) without sending the prompt to the LLM.</p></li>
|
||||
<li><p><strong>Seamless Request Transformation and Smart Routing</strong>:
|
||||
After rate limiting, Plano normalizes the outgoing request into a provider-agnostic shape and applies smart routing decisions using the configured <a class="reference internal" href="../../concepts/llm_providers/llm_providers.html#llm-providers"><span class="std std-ref">LLM Providers</span></a>. This includes translating client-specific conventions into a unified OpenAI-style contract, enriching or overriding parameters (for example, temperature or max tokens) based on policy, and choosing the best target model or provider using <a class="reference internal" href="../../concepts/llm_providers/llm_providers.html#llm-providers"><span class="std std-ref">model-based, alias-based, or preference-aligned routing</span></a>.</p></li>
|
||||
<li><p><strong>Load Balancing to (hosted) LLM Endpoints</strong>:
|
||||
After smart routing selects the target provider/model, Plano routes the prompt to the appropriate LLM endpoint.
|
||||
If multiple LLM provider instances are available, load balancing is performed to distribute traffic evenly
|
||||
across the instances. Plano checks the health of the LLM endpoints using circuit breakers and health checks,
|
||||
ensuring that the prompt is only routed to a healthy, responsive instance.</p></li>
|
||||
<li><p><strong>Response Reception and Forwarding</strong>:
|
||||
Once the LLM processes the prompt, Plano receives the response from the LLM service. The response is typically a generated text, completion, or summarization. Upon reception, Plano decrypts (if necessary) and handles the response, passing it through any egress processing pipeline defined by the application, such as logging or additional response filtering.</p></li>
|
||||
</ol>
|
||||
<section id="post-request-processing">
|
||||
<h3>Post-request processing<a @click.prevent="window.navigator.clipboard.writeText($el.href); $el.setAttribute('data-tooltip', 'Copied!'); setTimeout(() => $el.setAttribute('data-tooltip', 'Copy link to this element'), 2000)" aria-label="Copy link to this element" class="headerlink" data-tooltip="Copy link to this element" href="#post-request-processing" x-intersect.margin.0%.0%.-70%.0%="activeSection = '#post-request-processing'"><svg height="1em" viewbox="0 0 24 24" width="1em" xmlns="http://www.w3.org/2000/svg"><path d="M3.9 12c0-1.71 1.39-3.1 3.1-3.1h4V7H7c-2.76 0-5 2.24-5 5s2.24 5 5 5h4v-1.9H7c-1.71 0-3.1-1.39-3.1-3.1zM8 13h8v-2H8v2zm9-6h-4v1.9h4c1.71 0 3.1 1.39 3.1 3.1s-1.39 3.1-3.1 3.1h-4V17h4c2.76 0 5-2.24 5-5s-2.24-5-5-5z"></path></svg></a></h3>
|
||||
<p>Once a request completes, the stream is destroyed. The following also takes places:</p>
|
||||
<ul class="simple">
|
||||
<li><p>The post-request <a class="reference internal" href="../../guides/observability/monitoring.html#monitoring"><span class="std std-ref">monitoring</span></a> are updated (e.g. timing, active requests, upgrades, health checks).
|
||||
Some statistics are updated earlier however, during request processing. Stats are batched and written by the main
|
||||
thread periodically.</p></li>
|
||||
<li><p><a class="reference internal" href="../../guides/observability/access_logging.html#arch-access-logging"><span class="std std-ref">Access logs</span></a> are written to the access log</p></li>
|
||||
<li><p><a class="reference internal" href="../../guides/observability/tracing.html#arch-overview-tracing"><span class="std std-ref">Trace</span></a> spans are finalized. If our example request was traced, a
|
||||
trace span, describing the duration and details of the request would be created by the HCM when
|
||||
processing request headers and then finalized by the HCM during post-request processing.</p></li>
|
||||
</ul>
|
||||
</section>
|
||||
</section>
|
||||
<section id="configuration">
|
||||
<h2>Configuration<a @click.prevent="window.navigator.clipboard.writeText($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="#configuration" x-intersect.margin.0%.0%.-70%.0%="activeSection = '#configuration'"><svg height="1em" viewbox="0 0 24 24" width="1em" xmlns="http://www.w3.org/2000/svg"><path d="M3.9 12c0-1.71 1.39-3.1 3.1-3.1h4V7H7c-2.76 0-5 2.24-5 5s2.24 5 5 5h4v-1.9H7c-1.71 0-3.1-1.39-3.1-3.1zM8 13h8v-2H8v2zm9-6h-4v1.9h4c1.71 0 3.1 1.39 3.1 3.1s-1.39 3.1-3.1 3.1h-4V17h4c2.76 0 5-2.24 5-5s-2.24-5-5-5z"></path></svg></a></h2>
|
||||
<p>Today, only support a static bootstrap configuration file for simplicity today:</p>
|
||||
<div class="highlight-yaml notranslate"><div class="highlight"><pre><span></span><code><span id="line-1"><span class="nt">version</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">v0.2.0</span>
|
||||
</span><span id="line-2">
|
||||
</span><span id="line-3"><span class="nt">listeners</span><span class="p">:</span>
|
||||
</span><span id="line-4"><span class="w"> </span><span class="nt">ingress_traffic</span><span class="p">:</span>
|
||||
</span><span id="line-5"><span class="w"> </span><span class="nt">address</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">0.0.0.0</span>
|
||||
</span><span id="line-6"><span class="w"> </span><span class="nt">port</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">10000</span>
|
||||
</span><span id="line-7">
|
||||
</span><span id="line-8"><span class="c1"># Centralized way to manage LLMs, manage keys, retry logic, failover and limits in a central way</span>
|
||||
</span><span id="line-9"><span class="nt">model_providers</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="nt">access_key</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">$OPENAI_API_KEY</span>
|
||||
</span><span id="line-11"><span class="w"> </span><span class="nt">model</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">openai/gpt-4o</span>
|
||||
</span><span id="line-12"><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-13">
|
||||
</span><span id="line-14"><span class="nt">prompt_targets</span><span class="p">:</span>
|
||||
</span><span id="line-15"><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">information_extraction</span>
|
||||
</span><span id="line-16"><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-17"><span class="w"> </span><span class="nt">description</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">handel all scenarios that are question and answer in nature. Like summarization, information extraction, etc.</span>
|
||||
</span><span id="line-18"><span class="w"> </span><span class="nt">endpoint</span><span class="p">:</span>
|
||||
</span><span id="line-19"><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">app_server</span>
|
||||
</span><span id="line-20"><span class="w"> </span><span class="nt">path</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">/agent/summary</span>
|
||||
</span><span id="line-21"><span class="w"> </span><span class="c1"># Arch uses the default LLM and treats the response from the endpoint as the prompt to send to the LLM</span>
|
||||
</span><span id="line-22"><span class="w"> </span><span class="nt">auto_llm_dispatch_on_response</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">true</span>
|
||||
</span><span id="line-23"><span class="w"> </span><span class="c1"># override system prompt for this prompt target</span>
|
||||
</span><span id="line-24"><span class="w"> </span><span class="nt">system_prompt</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">You are a helpful information extraction assistant. Use the information that is provided to you.</span>
|
||||
</span><span id="line-25">
|
||||
</span><span id="line-26"><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">reboot_network_device</span>
|
||||
</span><span id="line-27"><span class="w"> </span><span class="nt">description</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">Reboot a specific network device</span>
|
||||
</span><span id="line-28"><span class="w"> </span><span class="nt">endpoint</span><span class="p">:</span>
|
||||
</span><span id="line-29"><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">app_server</span>
|
||||
</span><span id="line-30"><span class="w"> </span><span class="nt">path</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">/agent/action</span>
|
||||
</span><span id="line-31"><span class="w"> </span><span class="nt">parameters</span><span class="p">:</span>
|
||||
</span><span id="line-32"><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">device_id</span>
|
||||
</span><span id="line-33"><span class="w"> </span><span class="nt">type</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">str</span>
|
||||
</span><span id="line-34"><span class="w"> </span><span class="nt">description</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">Identifier of the network device to reboot.</span>
|
||||
</span><span id="line-35"><span class="w"> </span><span class="nt">required</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">true</span>
|
||||
</span><span id="line-36"><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">confirmation</span>
|
||||
</span><span id="line-37"><span class="w"> </span><span class="nt">type</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">bool</span>
|
||||
</span><span id="line-38"><span class="w"> </span><span class="nt">description</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">Confirmation flag to proceed with reboot.</span>
|
||||
</span><span id="line-39"><span class="w"> </span><span class="nt">default</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">false</span>
|
||||
</span><span id="line-40"><span class="w"> </span><span class="nt">enum</span><span class="p">:</span><span class="w"> </span><span class="p p-Indicator">[</span><span class="nv">true</span><span class="p p-Indicator">,</span><span class="w"> </span><span class="nv">false</span><span class="p p-Indicator">]</span>
|
||||
</span><span id="line-41">
|
||||
</span><span id="line-42"><span class="c1"># Arch creates a round-robin load balancing between different endpoints, managed via the cluster subsystem.</span>
|
||||
</span><span id="line-43"><span class="nt">endpoints</span><span class="p">:</span>
|
||||
</span><span id="line-44"><span class="w"> </span><span class="nt">app_server</span><span class="p">:</span>
|
||||
</span><span id="line-45"><span class="w"> </span><span class="c1"># value could be ip address or a hostname with port</span>
|
||||
</span><span id="line-46"><span class="w"> </span><span class="c1"># this could also be a list of endpoints for load balancing</span>
|
||||
</span><span id="line-47"><span class="w"> </span><span class="c1"># for example endpoint: [ ip1:port, ip2:port ]</span>
|
||||
</span><span id="line-48"><span class="w"> </span><span class="nt">endpoint</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">127.0.0.1:80</span>
|
||||
</span><span id="line-49"><span class="w"> </span><span class="c1"># max time to wait for a connection to be established</span>
|
||||
</span><span id="line-50"><span class="w"> </span><span class="nt">connect_timeout</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">0.005s</span>
|
||||
</span></code></pre></div>
|
||||
</div>
|
||||
</section>
|
||||
</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="tech_overview.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>
|
||||
Tech Overview
|
||||
</a>
|
||||
</div>
|
||||
<div class="ml-auto">
|
||||
<a class="inline-flex items-center justify-center rounded-md text-sm font-medium transition-colors border border-input hover:bg-accent hover:text-accent-foreground py-2 px-4" href="model_serving.html">
|
||||
Bright Staff
|
||||
<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 === '#network-topology'" class="reference internal" href="#network-topology">Network topology</a></li>
|
||||
<li><a :data-current="activeSection === '#high-level-architecture'" class="reference internal" href="#high-level-architecture">High level architecture</a></li>
|
||||
<li><a :data-current="activeSection === '#request-flow-ingress'" class="reference internal" href="#request-flow-ingress">Request Flow (Ingress)</a></li>
|
||||
<li><a :data-current="activeSection === '#request-flow-egress'" class="reference internal" href="#request-flow-egress">Request Flow (Egress)</a><ul>
|
||||
<li><a :data-current="activeSection === '#post-request-processing'" class="reference internal" href="#post-request-processing">Post-request processing</a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li><a :data-current="activeSection === '#configuration'" class="reference internal" href="#configuration">Configuration</a></li>
|
||||
</ul>
|
||||
</div>
|
||||
</aside>
|
||||
</main>
|
||||
</div>
|
||||
</div><footer class="py-6 border-t border-border md:py-0">
|
||||
<div class="container flex flex-col items-center justify-between gap-4 md:h-24 md:flex-row">
|
||||
<div class="flex flex-col items-center gap-4 px-8 md:flex-row md:gap-2 md:px-0">
|
||||
<p class="text-sm leading-loose text-center text-muted-foreground md:text-left">© 2025, Katanemo Labs, Inc Last updated: Dec 24, 2025. </p>
|
||||
</div>
|
||||
</div>
|
||||
</footer>
|
||||
</div>
|
||||
<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>
|
||||
<script src="../../_static/design-tabs.js?v=f930bc37"></script>
|
||||
</body>
|
||||
</html>
|
||||
210
resources/tech_overview/tech_overview.html
Executable file
210
resources/tech_overview/tech_overview.html
Executable file
|
|
@ -0,0 +1,210 @@
|
|||
<!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>Tech Overview | Plano Docs v0.4</title>
|
||||
<meta content="Tech Overview | Plano Docs v0.4" property="og:title"/>
|
||||
<meta content="Tech Overview | 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/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/tech_overview/tech_overview.html" rel="canonical"/>
|
||||
<link href="../../_static/favicon.ico" rel="icon"/>
|
||||
<link href="../../search.html" rel="search" title="Search"/>
|
||||
<link href="request_lifecycle.html" rel="next" title="Request Lifecycle"/>
|
||||
<link href="../../guides/state.html" rel="prev" title="Conversational State"/>
|
||||
<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">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>
|
||||
</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/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>
|
||||
</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">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-EH2VW19FXE"></script>
|
||||
<script>
|
||||
window.dataLayer = window.dataLayer || [];
|
||||
function gtag(){dataLayer.push(arguments);}
|
||||
gtag('js', new Date());
|
||||
|
||||
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_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"><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>
|
||||
</ul>
|
||||
</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/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>
|
||||
<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 current" x-data="{ expanded: $el.classList.contains('current') ? true : false }"><a :class="{ 'expanded' : expanded }" @click="expanded = !expanded" class="current reference internal expandable" href="#">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="request_lifecycle.html">Request Lifecycle</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="model_serving.html">Bright Staff</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="threading_model.html">Threading Model</a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../deployment.html">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>
|
||||
</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">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>
|
||||
</a>
|
||||
<div class="mr-1">/</div><span aria-current="page" class="font-medium text-foreground overflow-hidden text-ellipsis whitespace-nowrap">Tech Overview</span>
|
||||
</nav>
|
||||
<div id="content" role="main">
|
||||
<section id="tech-overview">
|
||||
<span id="id1"></span><h1>Tech Overview<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="#tech-overview"><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>
|
||||
<div class="toctree-wrapper compound">
|
||||
<ul>
|
||||
<li class="toctree-l1"><a class="reference internal" href="request_lifecycle.html">Request Lifecycle</a><ul>
|
||||
<li class="toctree-l2"><a class="reference internal" href="request_lifecycle.html#network-topology">Network topology</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="request_lifecycle.html#high-level-architecture">High level architecture</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="request_lifecycle.html#request-flow-ingress">Request Flow (Ingress)</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="request_lifecycle.html#request-flow-egress">Request Flow (Egress)</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="request_lifecycle.html#configuration">Configuration</a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="model_serving.html">Bright Staff</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="threading_model.html">Threading Model</a></li>
|
||||
</ul>
|
||||
</div>
|
||||
</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/state.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>
|
||||
Conversational State
|
||||
</a>
|
||||
</div>
|
||||
<div class="ml-auto">
|
||||
<a class="inline-flex items-center justify-center rounded-md text-sm font-medium transition-colors border border-input hover:bg-accent hover:text-accent-foreground py-2 px-4" href="request_lifecycle.html">
|
||||
Request Lifecycle
|
||||
<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>
|
||||
</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">© 2025, Katanemo Labs, Inc Last updated: Dec 24, 2025. </p>
|
||||
</div>
|
||||
</div>
|
||||
</footer>
|
||||
</div>
|
||||
<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>
|
||||
<script src="../../_static/design-tabs.js?v=f930bc37"></script>
|
||||
</body>
|
||||
</html>
|
||||
210
resources/tech_overview/threading_model.html
Executable file
210
resources/tech_overview/threading_model.html
Executable file
|
|
@ -0,0 +1,210 @@
|
|||
<!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>Threading Model | Plano Docs v0.4</title>
|
||||
<meta content="Threading Model | Plano Docs v0.4" property="og:title"/>
|
||||
<meta content="Threading Model | 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/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/tech_overview/threading_model.html" rel="canonical"/>
|
||||
<link href="../../_static/favicon.ico" rel="icon"/>
|
||||
<link href="../../search.html" rel="search" title="Search"/>
|
||||
<link href="../deployment.html" rel="next" title="Deployment"/>
|
||||
<link href="model_serving.html" rel="prev" title="Bright Staff"/>
|
||||
<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">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>
|
||||
</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/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>
|
||||
</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">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-EH2VW19FXE"></script>
|
||||
<script>
|
||||
window.dataLayer = window.dataLayer || [];
|
||||
function gtag(){dataLayer.push(arguments);}
|
||||
gtag('js', new Date());
|
||||
|
||||
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_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"><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>
|
||||
</ul>
|
||||
</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/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>
|
||||
<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 current" x-data="{ expanded: $el.classList.contains('current') ? true : false }"><a :class="{ 'expanded' : expanded }" @click="expanded = !expanded" class="reference internal expandable" href="tech_overview.html">Tech Overview<button @click.prevent.stop="expanded = !expanded" type="button"><span class="sr-only"></span><svg fill="currentColor" height="18px" stroke="none" viewbox="0 0 24 24" width="18px" xmlns="http://www.w3.org/2000/svg"><path d="M10 6L8.59 7.41 13.17 12l-4.58 4.59L10 18l6-6z"></path></svg></button></a><ul class="current" x-show="expanded">
|
||||
<li class="toctree-l2"><a class="reference internal" href="request_lifecycle.html">Request Lifecycle</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="model_serving.html">Bright Staff</a></li>
|
||||
<li class="toctree-l2 current"><a class="current reference internal" href="#">Threading Model</a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../deployment.html">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>
|
||||
</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">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>
|
||||
</a>
|
||||
<div class="mr-1">/</div><a class="hover:text-foreground overflow-hidden text-ellipsis whitespace-nowrap" href="tech_overview.html">Tech Overview</a>
|
||||
<div class="mr-1">/</div><span aria-current="page" class="font-medium text-foreground overflow-hidden text-ellipsis whitespace-nowrap">Threading Model</span>
|
||||
</nav>
|
||||
<div id="content" role="main">
|
||||
<section id="threading-model">
|
||||
<span id="arch-overview-threading"></span><h1>Threading Model<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="#threading-model"><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>Plano builds on top of Envoy’s single process with multiple threads architecture.</p>
|
||||
<p>A single <em>primary</em> thread controls various sporadic coordination tasks while some number of <em>worker</em>
|
||||
threads perform filtering, and forwarding.</p>
|
||||
<p>Once a connection is accepted, the connection spends the rest of its lifetime bound to a single worker
|
||||
thread. All the functionality around prompt handling from a downstream client is handled in a separate worker thread.
|
||||
This allows the majority of Plano to be largely single threaded (embarrassingly parallel) with a small amount
|
||||
of more complex code handling coordination between the worker threads.</p>
|
||||
<p>Generally, Plano is written to be 100% non-blocking.</p>
|
||||
<div class="admonition tip">
|
||||
<p class="admonition-title">Tip</p>
|
||||
<p>For most workloads we recommend configuring the number of worker threads to be equal to the number of
|
||||
hardware threads on the machine.</p>
|
||||
</div>
|
||||
</section>
|
||||
</div><div class="flex justify-between items-center pt-6 mt-12 border-t border-border gap-4">
|
||||
<div class="mr-auto">
|
||||
<a class="inline-flex items-center justify-center rounded-md text-sm font-medium transition-colors border border-input hover:bg-accent hover:text-accent-foreground py-2 px-4" href="model_serving.html">
|
||||
<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>
|
||||
Bright Staff
|
||||
</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="../deployment.html">
|
||||
Deployment
|
||||
<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>
|
||||
</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">© 2025, Katanemo Labs, Inc Last updated: Dec 24, 2025. </p>
|
||||
</div>
|
||||
</div>
|
||||
</footer>
|
||||
</div>
|
||||
<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>
|
||||
<script src="../../_static/design-tabs.js?v=f930bc37"></script>
|
||||
</body>
|
||||
</html>
|
||||
Loading…
Add table
Add a link
Reference in a new issue