deploy: c9b95c7c9f15441738c938bb27cca66eb86990e3

This commit is contained in:
salmanap 2024-10-06 18:14:10 +00:00
parent c901be3b22
commit fd31269b72
205 changed files with 20640 additions and 1 deletions

View file

@ -0,0 +1,465 @@
<!DOCTYPE html>
<html lang="en" data-content_root="../../" >
<head>
<meta charset="utf-8" />
<meta name="viewport" content="width=device-width, initial-scale=1.0" /><meta name="viewport" content="width=device-width, initial-scale=1" />
<title>Technical Architecture &#8212; Arch 0.1-beta documentation</title>
<script data-cfasync="false">
document.documentElement.dataset.mode = localStorage.getItem("mode") || "";
document.documentElement.dataset.theme = localStorage.getItem("theme") || "";
</script>
<!-- Loaded before other Sphinx assets -->
<link href="../../_static/styles/theme.css?digest=dfe6caa3a7d634c4db9b" rel="stylesheet" />
<link href="../../_static/styles/bootstrap.css?digest=dfe6caa3a7d634c4db9b" rel="stylesheet" />
<link href="../../_static/styles/pydata-sphinx-theme.css?digest=dfe6caa3a7d634c4db9b" rel="stylesheet" />
<link href="../../_static/vendor/fontawesome/6.5.2/css/all.min.css?digest=dfe6caa3a7d634c4db9b" rel="stylesheet" />
<link rel="preload" as="font" type="font/woff2" crossorigin href="../../_static/vendor/fontawesome/6.5.2/webfonts/fa-solid-900.woff2" />
<link rel="preload" as="font" type="font/woff2" crossorigin href="../../_static/vendor/fontawesome/6.5.2/webfonts/fa-brands-400.woff2" />
<link rel="preload" as="font" type="font/woff2" crossorigin href="../../_static/vendor/fontawesome/6.5.2/webfonts/fa-regular-400.woff2" />
<link rel="stylesheet" type="text/css" href="../../_static/pygments.css?v=a746c00c" />
<link rel="stylesheet" type="text/css" href="../../_static/styles/sphinx-book-theme.css?v=a3416100" />
<link rel="stylesheet" type="text/css" href="../../_static/copybutton.css?v=76b2166b" />
<!-- Pre-loaded scripts that we'll load fully later -->
<link rel="preload" as="script" href="../../_static/scripts/bootstrap.js?digest=dfe6caa3a7d634c4db9b" />
<link rel="preload" as="script" href="../../_static/scripts/pydata-sphinx-theme.js?digest=dfe6caa3a7d634c4db9b" />
<script src="../../_static/vendor/fontawesome/6.5.2/js/all.min.js?digest=dfe6caa3a7d634c4db9b"></script>
<script src="../../_static/documentation_options.js?v=2742c0eb"></script>
<script src="../../_static/doctools.js?v=9a2dae69"></script>
<script src="../../_static/sphinx_highlight.js?v=dc90522c"></script>
<script src="../../_static/clipboard.min.js?v=a7894cd8"></script>
<script src="../../_static/copybutton.js?v=f281be69"></script>
<script src="../../_static/scripts/sphinx-book-theme.js?v=887ef09a"></script>
<script>DOCUMENTATION_OPTIONS.pagename = 'intro/architecture/architecture';</script>
<link rel="icon" href="../../_static/favicon.ico"/>
<link rel="index" title="Index" href="../../genindex.html" />
<link rel="search" title="Search" href="../../search.html" />
<link rel="next" title="Terminology" href="intro/terminology.html" />
<link rel="prev" title="What is Arch" href="../what_is_arch.html" />
<meta name="viewport" content="width=device-width, initial-scale=1"/>
<meta name="docsearch:language" content="en"/>
</head>
<body data-bs-spy="scroll" data-bs-target=".bd-toc-nav" data-offset="180" data-bs-root-margin="0px 0px -60%" data-default-mode="">
<div id="pst-skip-link" class="skip-link d-print-none"><a href="#main-content">Skip to main content</a></div>
<div id="pst-scroll-pixel-helper"></div>
<button type="button" class="btn rounded-pill" id="pst-back-to-top">
<i class="fa-solid fa-arrow-up"></i>Back to top</button>
<input type="checkbox"
class="sidebar-toggle"
id="pst-primary-sidebar-checkbox"/>
<label class="overlay overlay-primary" for="pst-primary-sidebar-checkbox"></label>
<input type="checkbox"
class="sidebar-toggle"
id="pst-secondary-sidebar-checkbox"/>
<label class="overlay overlay-secondary" for="pst-secondary-sidebar-checkbox"></label>
<div class="search-button__wrapper">
<div class="search-button__overlay"></div>
<div class="search-button__search-container">
<form class="bd-search d-flex align-items-center"
action="../../search.html"
method="get">
<i class="fa-solid fa-magnifying-glass"></i>
<input type="search"
class="form-control"
name="q"
id="search-input"
placeholder="Search..."
aria-label="Search..."
autocomplete="off"
autocorrect="off"
autocapitalize="off"
spellcheck="false"/>
<span class="search-button__kbd-shortcut"><kbd class="kbd-shortcut__modifier">Ctrl</kbd>+<kbd>K</kbd></span>
</form></div>
</div>
<div class="pst-async-banner-revealer d-none">
<aside id="bd-header-version-warning" class="d-none d-print-none" aria-label="Version warning"></aside>
</div>
<header class="bd-header navbar navbar-expand-lg bd-navbar d-print-none">
</header>
<div class="bd-container">
<div class="bd-container__inner bd-page-width">
<div class="bd-sidebar-primary bd-sidebar">
<div class="sidebar-header-items sidebar-primary__section">
</div>
<div class="sidebar-primary-items__start sidebar-primary__section">
<div class="sidebar-primary-item">
<a class="navbar-brand logo" href="../../root.html">
<img src="../../_static/arch-nav-logo.png" class="logo__image only-light" alt="Arch 0.1-beta documentation - Home"/>
<script>document.write(`<img src="../../_static/arch-nav-logo.png" class="logo__image only-dark" alt="Arch 0.1-beta documentation - Home"/>`);</script>
</a></div>
<div class="sidebar-primary-item">
<script>
document.write(`
<button class="btn search-button-field search-button__button" title="Search" aria-label="Search" data-bs-placement="bottom" data-bs-toggle="tooltip">
<i class="fa-solid fa-magnifying-glass"></i>
<span class="search-button__default-text">Search</span>
<span class="search-button__kbd-shortcut"><kbd class="kbd-shortcut__modifier">Ctrl</kbd>+<kbd class="kbd-shortcut__modifier">K</kbd></span>
</button>
`);
</script></div>
<div class="sidebar-primary-item"><nav class="bd-links bd-docs-nav" aria-label="Main">
<div class="bd-toc-item navbar-nav active">
<ul class="current nav bd-sidenav">
<li class="toctree-l1 current active has-children"><a class="reference internal" href="../intro.html">Introduction</a><details open="open"><summary><span class="toctree-toggle" role="presentation"><i class="fa-solid fa-chevron-down"></i></span></summary><ul class="current">
<li class="toctree-l2"><a class="reference internal" href="../what_is_arch.html">What is Arch</a></li>
<li class="toctree-l2 current active has-children"><a class="current reference internal" href="#">Technical Architecture</a><details open="open"><summary><span class="toctree-toggle" role="presentation"><i class="fa-solid fa-chevron-down"></i></span></summary><ul>
<li class="toctree-l3"><a class="reference internal" href="intro/terminology.html">Terminology</a></li>
<li class="toctree-l3"><a class="reference internal" href="intro/threading_model.html">Threading model</a></li>
<li class="toctree-l3"><a class="reference internal" href="listeners/listeners.html">Listener</a></li>
<li class="toctree-l3"><a class="reference internal" href="prompt_processing/prompt_processing.html">Prompts</a></li>
<li class="toctree-l3"><a class="reference internal" href="listeners/llm_provider.html">LLM Provider</a></li>
<li class="toctree-l3"><a class="reference internal" href="model_serving/model_serving.html">Model Serving</a></li>
</ul>
</details></li>
<li class="toctree-l2"><a class="reference internal" href="../life_of_a_request.html">Life of a Request</a></li>
<li class="toctree-l2"><a class="reference internal" href="../getting_help.html">Getting help</a></li>
</ul>
</details></li>
<li class="toctree-l1"><a class="reference internal" href="../../getting_started/getting_started.html">Getting Started</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../getting_started/use_cases/rag.html">Retrieval-Augmented (RAG)</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../getting_started/use_cases/function_calling.html">Agentic (Text-to-Action) Apps</a></li>
<li class="toctree-l1 has-children"><a class="reference internal" href="../../observability/observability.html">Observability</a><details><summary><span class="toctree-toggle" role="presentation"><i class="fa-solid fa-chevron-down"></i></span></summary><ul>
<li class="toctree-l2"><a class="reference internal" href="../../observability/tracing.html">Tracing</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../observability/stats.html">Monitoring</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../observability/access_logs.html">Access Logging</a></li>
</ul>
</details></li>
<li class="toctree-l1"><a class="reference internal" href="../../llms/llms.html">LLMs</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../configuration_reference.html">Configuration Reference</a></li>
</ul>
</div>
</nav></div>
</div>
<div class="sidebar-primary-items__end sidebar-primary__section">
</div>
<div id="rtd-footer-container"></div>
</div>
<main id="main-content" class="bd-main" role="main">
<div class="sbt-scroll-pixel-helper"></div>
<div class="bd-content">
<div class="bd-article-container">
<div class="bd-header-article d-print-none">
<div class="header-article-items header-article__inner">
<div class="header-article-items__start">
<div class="header-article-item"><button class="sidebar-toggle primary-toggle btn btn-sm" title="Toggle primary sidebar" data-bs-placement="bottom" data-bs-toggle="tooltip">
<span class="fa-solid fa-bars"></span>
</button></div>
</div>
<div class="header-article-items__end">
<div class="header-article-item">
<div class="article-header-buttons">
<div class="dropdown dropdown-download-buttons">
<button class="btn dropdown-toggle" type="button" data-bs-toggle="dropdown" aria-expanded="false" aria-label="Download this page">
<i class="fas fa-download"></i>
</button>
<ul class="dropdown-menu">
<li><a href="../../_sources/intro/architecture/architecture.rst" target="_blank"
class="btn btn-sm btn-download-source-button dropdown-item"
title="Download source file"
data-bs-placement="left" data-bs-toggle="tooltip"
>
<span class="btn__icon-container">
<i class="fas fa-file"></i>
</span>
<span class="btn__text-container">.rst</span>
</a>
</li>
<li>
<button onclick="window.print()"
class="btn btn-sm btn-download-pdf-button dropdown-item"
title="Print to PDF"
data-bs-placement="left" data-bs-toggle="tooltip"
>
<span class="btn__icon-container">
<i class="fas fa-file-pdf"></i>
</span>
<span class="btn__text-container">.pdf</span>
</button>
</li>
</ul>
</div>
<button onclick="toggleFullScreen()"
class="btn btn-sm btn-fullscreen-button"
title="Fullscreen mode"
data-bs-placement="bottom" data-bs-toggle="tooltip"
>
<span class="btn__icon-container">
<i class="fas fa-expand"></i>
</span>
</button>
<script>
document.write(`
<button class="btn btn-sm nav-link pst-navbar-icon theme-switch-button" title="light/dark" aria-label="light/dark" data-bs-placement="bottom" data-bs-toggle="tooltip">
<i class="theme-switch fa-solid fa-sun fa-lg" data-mode="light"></i>
<i class="theme-switch fa-solid fa-moon fa-lg" data-mode="dark"></i>
<i class="theme-switch fa-solid fa-circle-half-stroke fa-lg" data-mode="auto"></i>
</button>
`);
</script>
<script>
document.write(`
<button class="btn btn-sm pst-navbar-icon search-button search-button__button" title="Search" aria-label="Search" data-bs-placement="bottom" data-bs-toggle="tooltip">
<i class="fa-solid fa-magnifying-glass fa-lg"></i>
</button>
`);
</script>
</div></div>
</div>
</div>
</div>
<div id="jb-print-docs-body" class="onlyprint">
<h1>Technical Architecture</h1>
<!-- Table of contents -->
<div id="print-main-content">
<div id="jb-print-toc">
</div>
</div>
</div>
<div id="searchbox"></div>
<article class="bd-article">
<section id="technical-architecture">
<h1>Technical Architecture<a class="headerlink" href="#technical-architecture" title="Link to this heading">#</a></h1>
<div class="toctree-wrapper compound">
<ul>
<li class="toctree-l1"><a class="reference internal" href="intro/terminology.html">Terminology</a></li>
<li class="toctree-l1"><a class="reference internal" href="intro/threading_model.html">Threading model</a></li>
<li class="toctree-l1"><a class="reference internal" href="listeners/listeners.html">Listener</a><ul>
<li class="toctree-l2"><a class="reference internal" href="listeners/listeners.html#downstream-ingress">Downstream (Ingress)</a></li>
<li class="toctree-l2"><a class="reference internal" href="listeners/listeners.html#upstream-egress">Upstream (Egress)</a></li>
<li class="toctree-l2"><a class="reference internal" href="listeners/listeners.html#configure-listener">Configure Listener</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="prompt_processing/prompt_processing.html">Prompts</a></li>
<li class="toctree-l1"><a class="reference internal" href="prompt_processing/prompt_processing.html#messages">Messages</a></li>
<li class="toctree-l1"><a class="reference internal" href="prompt_processing/prompt_processing.html#prompt-guardrails">Prompt Guardrails</a></li>
<li class="toctree-l1"><a class="reference internal" href="prompt_processing/prompt_processing.html#prompt-targets">Prompt Targets</a><ul>
<li class="toctree-l2"><a class="reference internal" href="prompt_processing/prompt_processing.html#intent-detection-and-prompt-matching">Intent Detection and Prompt Matching:</a></li>
<li class="toctree-l2"><a class="reference internal" href="prompt_processing/prompt_processing.html#agentic-apps-via-prompt-targets">Agentic Apps via Prompt Targets</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="prompt_processing/prompt_processing.html#prompting-llms">Prompting LLMs</a><ul>
<li class="toctree-l2"><a class="reference internal" href="prompt_processing/prompt_processing.html#example-using-the-arch-python-sdk">Example: Using the Arch Python SDK</a></li>
<li class="toctree-l2"><a class="reference internal" href="prompt_processing/prompt_processing.html#example-using-openai-client-with-arch-as-an-egress-gateway">Example: Using OpenAI Client with Arch as an Egress Gateway</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="listeners/llm_provider.html">LLM Provider</a></li>
<li class="toctree-l1"><a class="reference internal" href="listeners/llm_provider.html#example-using-the-arch-python-sdk">Example: Using the Arch Python SDK</a></li>
<li class="toctree-l1"><a class="reference internal" href="model_serving/model_serving.html">Model Serving</a><ul>
<li class="toctree-l2"><a class="reference internal" href="model_serving/model_serving.html#local-serving-cpu-moderate">Local Serving (CPU - Moderate)</a></li>
<li class="toctree-l2"><a class="reference internal" href="model_serving/model_serving.html#local-serving-gpu-fast">Local Serving (GPU- Fast)</a></li>
<li class="toctree-l2"><a class="reference internal" href="model_serving/model_serving.html#cloud-serving-gpu-blazing-fast">Cloud Serving (GPU - Blazing Fast)</a></li>
</ul>
</li>
</ul>
</div>
</section>
</article>
<footer class="prev-next-footer d-print-none">
<div class="prev-next-area">
<a class="left-prev"
href="../what_is_arch.html"
title="previous page">
<i class="fa-solid fa-angle-left"></i>
<div class="prev-next-info">
<p class="prev-next-subtitle">previous</p>
<p class="prev-next-title">What is Arch</p>
</div>
</a>
<a class="right-next"
href="intro/terminology.html"
title="next page">
<div class="prev-next-info">
<p class="prev-next-subtitle">next</p>
<p class="prev-next-title">Terminology</p>
</div>
<i class="fa-solid fa-angle-right"></i>
</a>
</div>
</footer>
</div>
</div>
<footer class="bd-footer-content">
<div class="bd-footer-content__inner container">
<div class="footer-item">
<p class="component-author">
By Katanemo Labs, Inc
</p>
</div>
<div class="footer-item">
<p class="copyright">
© Copyright 2024, Katanemo Labs, Inc.
<br/>
</p>
</div>
<div class="footer-item">
</div>
<div class="footer-item">
</div>
</div>
</footer>
</main>
</div>
</div>
<!-- Scripts loaded after <body> so the DOM is not blocked -->
<script src="../../_static/scripts/bootstrap.js?digest=dfe6caa3a7d634c4db9b"></script>
<script src="../../_static/scripts/pydata-sphinx-theme.js?digest=dfe6caa3a7d634c4db9b"></script>
<footer class="bd-footer">
</footer>
</body>
</html>

View file

@ -0,0 +1,464 @@
<!DOCTYPE html>
<html lang="en" data-content_root="../../../" >
<head>
<meta charset="utf-8" />
<meta name="viewport" content="width=device-width, initial-scale=1.0" /><meta name="viewport" content="width=device-width, initial-scale=1" />
<title>Terminology &#8212; Arch 0.1-beta documentation</title>
<script data-cfasync="false">
document.documentElement.dataset.mode = localStorage.getItem("mode") || "";
document.documentElement.dataset.theme = localStorage.getItem("theme") || "";
</script>
<!-- Loaded before other Sphinx assets -->
<link href="../../../_static/styles/theme.css?digest=dfe6caa3a7d634c4db9b" rel="stylesheet" />
<link href="../../../_static/styles/bootstrap.css?digest=dfe6caa3a7d634c4db9b" rel="stylesheet" />
<link href="../../../_static/styles/pydata-sphinx-theme.css?digest=dfe6caa3a7d634c4db9b" rel="stylesheet" />
<link href="../../../_static/vendor/fontawesome/6.5.2/css/all.min.css?digest=dfe6caa3a7d634c4db9b" rel="stylesheet" />
<link rel="preload" as="font" type="font/woff2" crossorigin href="../../../_static/vendor/fontawesome/6.5.2/webfonts/fa-solid-900.woff2" />
<link rel="preload" as="font" type="font/woff2" crossorigin href="../../../_static/vendor/fontawesome/6.5.2/webfonts/fa-brands-400.woff2" />
<link rel="preload" as="font" type="font/woff2" crossorigin href="../../../_static/vendor/fontawesome/6.5.2/webfonts/fa-regular-400.woff2" />
<link rel="stylesheet" type="text/css" href="../../../_static/pygments.css?v=a746c00c" />
<link rel="stylesheet" type="text/css" href="../../../_static/styles/sphinx-book-theme.css?v=a3416100" />
<link rel="stylesheet" type="text/css" href="../../../_static/copybutton.css?v=76b2166b" />
<!-- Pre-loaded scripts that we'll load fully later -->
<link rel="preload" as="script" href="../../../_static/scripts/bootstrap.js?digest=dfe6caa3a7d634c4db9b" />
<link rel="preload" as="script" href="../../../_static/scripts/pydata-sphinx-theme.js?digest=dfe6caa3a7d634c4db9b" />
<script src="../../../_static/vendor/fontawesome/6.5.2/js/all.min.js?digest=dfe6caa3a7d634c4db9b"></script>
<script src="../../../_static/documentation_options.js?v=2742c0eb"></script>
<script src="../../../_static/doctools.js?v=9a2dae69"></script>
<script src="../../../_static/sphinx_highlight.js?v=dc90522c"></script>
<script src="../../../_static/clipboard.min.js?v=a7894cd8"></script>
<script src="../../../_static/copybutton.js?v=f281be69"></script>
<script src="../../../_static/scripts/sphinx-book-theme.js?v=887ef09a"></script>
<script>DOCUMENTATION_OPTIONS.pagename = 'intro/architecture/intro/terminology';</script>
<link rel="icon" href="../../../_static/favicon.ico"/>
<link rel="index" title="Index" href="../../../genindex.html" />
<link rel="search" title="Search" href="../../../search.html" />
<link rel="next" title="Threading model" href="threading_model.html" />
<link rel="prev" title="Technical Architecture" href="../architecture.html" />
<meta name="viewport" content="width=device-width, initial-scale=1"/>
<meta name="docsearch:language" content="en"/>
</head>
<body data-bs-spy="scroll" data-bs-target=".bd-toc-nav" data-offset="180" data-bs-root-margin="0px 0px -60%" data-default-mode="">
<div id="pst-skip-link" class="skip-link d-print-none"><a href="#main-content">Skip to main content</a></div>
<div id="pst-scroll-pixel-helper"></div>
<button type="button" class="btn rounded-pill" id="pst-back-to-top">
<i class="fa-solid fa-arrow-up"></i>Back to top</button>
<input type="checkbox"
class="sidebar-toggle"
id="pst-primary-sidebar-checkbox"/>
<label class="overlay overlay-primary" for="pst-primary-sidebar-checkbox"></label>
<input type="checkbox"
class="sidebar-toggle"
id="pst-secondary-sidebar-checkbox"/>
<label class="overlay overlay-secondary" for="pst-secondary-sidebar-checkbox"></label>
<div class="search-button__wrapper">
<div class="search-button__overlay"></div>
<div class="search-button__search-container">
<form class="bd-search d-flex align-items-center"
action="../../../search.html"
method="get">
<i class="fa-solid fa-magnifying-glass"></i>
<input type="search"
class="form-control"
name="q"
id="search-input"
placeholder="Search..."
aria-label="Search..."
autocomplete="off"
autocorrect="off"
autocapitalize="off"
spellcheck="false"/>
<span class="search-button__kbd-shortcut"><kbd class="kbd-shortcut__modifier">Ctrl</kbd>+<kbd>K</kbd></span>
</form></div>
</div>
<div class="pst-async-banner-revealer d-none">
<aside id="bd-header-version-warning" class="d-none d-print-none" aria-label="Version warning"></aside>
</div>
<header class="bd-header navbar navbar-expand-lg bd-navbar d-print-none">
</header>
<div class="bd-container">
<div class="bd-container__inner bd-page-width">
<div class="bd-sidebar-primary bd-sidebar">
<div class="sidebar-header-items sidebar-primary__section">
</div>
<div class="sidebar-primary-items__start sidebar-primary__section">
<div class="sidebar-primary-item">
<a class="navbar-brand logo" href="../../../root.html">
<img src="../../../_static/arch-nav-logo.png" class="logo__image only-light" alt="Arch 0.1-beta documentation - Home"/>
<script>document.write(`<img src="../../../_static/arch-nav-logo.png" class="logo__image only-dark" alt="Arch 0.1-beta documentation - Home"/>`);</script>
</a></div>
<div class="sidebar-primary-item">
<script>
document.write(`
<button class="btn search-button-field search-button__button" title="Search" aria-label="Search" data-bs-placement="bottom" data-bs-toggle="tooltip">
<i class="fa-solid fa-magnifying-glass"></i>
<span class="search-button__default-text">Search</span>
<span class="search-button__kbd-shortcut"><kbd class="kbd-shortcut__modifier">Ctrl</kbd>+<kbd class="kbd-shortcut__modifier">K</kbd></span>
</button>
`);
</script></div>
<div class="sidebar-primary-item"><nav class="bd-links bd-docs-nav" aria-label="Main">
<div class="bd-toc-item navbar-nav active">
<ul class="current nav bd-sidenav">
<li class="toctree-l1 current active has-children"><a class="reference internal" href="../../intro.html">Introduction</a><details open="open"><summary><span class="toctree-toggle" role="presentation"><i class="fa-solid fa-chevron-down"></i></span></summary><ul class="current">
<li class="toctree-l2"><a class="reference internal" href="../../what_is_arch.html">What is Arch</a></li>
<li class="toctree-l2 current active has-children"><a class="reference internal" href="../architecture.html">Technical Architecture</a><details open="open"><summary><span class="toctree-toggle" role="presentation"><i class="fa-solid fa-chevron-down"></i></span></summary><ul class="current">
<li class="toctree-l3 current active"><a class="current reference internal" href="#">Terminology</a></li>
<li class="toctree-l3"><a class="reference internal" href="threading_model.html">Threading model</a></li>
<li class="toctree-l3"><a class="reference internal" href="../listeners/listeners.html">Listener</a></li>
<li class="toctree-l3"><a class="reference internal" href="../prompt_processing/prompt_processing.html">Prompts</a></li>
<li class="toctree-l3"><a class="reference internal" href="../listeners/llm_provider.html">LLM Provider</a></li>
<li class="toctree-l3"><a class="reference internal" href="../model_serving/model_serving.html">Model Serving</a></li>
</ul>
</details></li>
<li class="toctree-l2"><a class="reference internal" href="../../life_of_a_request.html">Life of a Request</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../getting_help.html">Getting help</a></li>
</ul>
</details></li>
<li class="toctree-l1"><a class="reference internal" href="../../../getting_started/getting_started.html">Getting Started</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../getting_started/use_cases/rag.html">Retrieval-Augmented (RAG)</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../getting_started/use_cases/function_calling.html">Agentic (Text-to-Action) Apps</a></li>
<li class="toctree-l1 has-children"><a class="reference internal" href="../../../observability/observability.html">Observability</a><details><summary><span class="toctree-toggle" role="presentation"><i class="fa-solid fa-chevron-down"></i></span></summary><ul>
<li class="toctree-l2"><a class="reference internal" href="../../../observability/tracing.html">Tracing</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../observability/stats.html">Monitoring</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../observability/access_logs.html">Access Logging</a></li>
</ul>
</details></li>
<li class="toctree-l1"><a class="reference internal" href="../../../llms/llms.html">LLMs</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../configuration_reference.html">Configuration Reference</a></li>
</ul>
</div>
</nav></div>
</div>
<div class="sidebar-primary-items__end sidebar-primary__section">
</div>
<div id="rtd-footer-container"></div>
</div>
<main id="main-content" class="bd-main" role="main">
<div class="sbt-scroll-pixel-helper"></div>
<div class="bd-content">
<div class="bd-article-container">
<div class="bd-header-article d-print-none">
<div class="header-article-items header-article__inner">
<div class="header-article-items__start">
<div class="header-article-item"><button class="sidebar-toggle primary-toggle btn btn-sm" title="Toggle primary sidebar" data-bs-placement="bottom" data-bs-toggle="tooltip">
<span class="fa-solid fa-bars"></span>
</button></div>
</div>
<div class="header-article-items__end">
<div class="header-article-item">
<div class="article-header-buttons">
<div class="dropdown dropdown-download-buttons">
<button class="btn dropdown-toggle" type="button" data-bs-toggle="dropdown" aria-expanded="false" aria-label="Download this page">
<i class="fas fa-download"></i>
</button>
<ul class="dropdown-menu">
<li><a href="../../../_sources/intro/architecture/intro/terminology.rst" target="_blank"
class="btn btn-sm btn-download-source-button dropdown-item"
title="Download source file"
data-bs-placement="left" data-bs-toggle="tooltip"
>
<span class="btn__icon-container">
<i class="fas fa-file"></i>
</span>
<span class="btn__text-container">.rst</span>
</a>
</li>
<li>
<button onclick="window.print()"
class="btn btn-sm btn-download-pdf-button dropdown-item"
title="Print to PDF"
data-bs-placement="left" data-bs-toggle="tooltip"
>
<span class="btn__icon-container">
<i class="fas fa-file-pdf"></i>
</span>
<span class="btn__text-container">.pdf</span>
</button>
</li>
</ul>
</div>
<button onclick="toggleFullScreen()"
class="btn btn-sm btn-fullscreen-button"
title="Fullscreen mode"
data-bs-placement="bottom" data-bs-toggle="tooltip"
>
<span class="btn__icon-container">
<i class="fas fa-expand"></i>
</span>
</button>
<script>
document.write(`
<button class="btn btn-sm nav-link pst-navbar-icon theme-switch-button" title="light/dark" aria-label="light/dark" data-bs-placement="bottom" data-bs-toggle="tooltip">
<i class="theme-switch fa-solid fa-sun fa-lg" data-mode="light"></i>
<i class="theme-switch fa-solid fa-moon fa-lg" data-mode="dark"></i>
<i class="theme-switch fa-solid fa-circle-half-stroke fa-lg" data-mode="auto"></i>
</button>
`);
</script>
<script>
document.write(`
<button class="btn btn-sm pst-navbar-icon search-button search-button__button" title="Search" aria-label="Search" data-bs-placement="bottom" data-bs-toggle="tooltip">
<i class="fa-solid fa-magnifying-glass fa-lg"></i>
</button>
`);
</script>
</div></div>
</div>
</div>
</div>
<div id="jb-print-docs-body" class="onlyprint">
<h1>Terminology</h1>
<!-- Table of contents -->
<div id="print-main-content">
<div id="jb-print-toc">
</div>
</div>
</div>
<div id="searchbox"></div>
<article class="bd-article">
<section id="terminology">
<span id="arch-terminology"></span><h1>Terminology<a class="headerlink" href="#terminology" title="Link to this heading">#</a></h1>
<p>A few definitions before we dive into the main architecture documentation. Arch borrows from Envoys terminology
to keep things consistent in logs, traces and in code.</p>
<p><strong>Downstream(Ingress)</strong>: An downstream client (web application, etc.) connects to Arch, sends prompts, and receives responses.</p>
<p><strong>Upstream(Egress)</strong>: An upstream host that receives connections and prompts from Arch, and returns context or responses for a prompt</p>
<a class="reference internal image-reference" href="../../../_images/network-topology-ingress-egress.jpg"><img alt="../../../_images/network-topology-ingress-egress.jpg" class="align-center" src="../../../_images/network-topology-ingress-egress.jpg" style="width: 100%;" />
</a>
<p><strong>Listener</strong>: A listener is a named network location (e.g., port, address, path etc.) that Arch listens on to process prompts
before forwarding them to your application server endpoints. rch enables you to configure one listener for downstream connections
(like port 80, 443) and creates a separate internal listener for calls that initiate from your application code to LLMs.</p>
<div class="admonition note">
<p class="admonition-title">Note</p>
<p>When you start Arch, you specify a listener address/port that you want to bind downstream. But, Arch uses are predefined port
that you can use (<code class="docutils literal notranslate"><span class="pre">127.0.0.1:10000</span></code>) to proxy egress calls originating from your application to LLMs (API-based or hosted).
For more details, check out <a class="reference internal" href="../listeners/llm_provider.html#llm-providers"><span class="std std-ref">LLM providers</span></a></p>
</div>
<p><strong>Instance</strong>: An instance of the Arch gateway. When you start Arch it creates at most two processes. One to handle Layer 7
networking operations (auth, tls, observability, etc) and the second process to serve models that enable it to make smart
decisions on how to accept, handle and forward prompts. The second process is optional, as the model serving sevice could be
hosted on a different network (an API call). But these two processes are considered a single instance of Arch.</p>
<p><strong>Prompt Targets</strong>: Arch offers a primitive called <code class="docutils literal notranslate"><span class="pre">prompt_targets</span></code> to help separate business logic from undifferentiated
work in building generative AI apps. Prompt targets are endpoints that receive prompts that are processed by Arch.
For example, Arch enriches incoming prompts with metadata like knowing when a request is a follow-up or clarifying prompt
so that you can build faster, more accurate retrieval (RAG) apps. To support agentic apps, like scheduling travel plans or
sharing comments on a document - via prompts, Bolt uses its function calling abilities to extract critical information from
the incoming prompt (or a set of prompts) needed by a downstream backend API or function call before calling it directly.</p>
<p><strong>Error Targets</strong>: Error targets are those endpoints that receive forwarded errors from Arch when issues arise,
such as failing to properly call a function/API, detecting violations of guardrails, or encountering other processing errors.
These errors are communicated to the application via headers (X-Arch-[ERROR-TYPE]), allowing it to handle the errors gracefully
and take appropriate actions.</p>
<p><strong>Model Serving</strong>: Arch is a set of <strong>two</strong> self-contained processes that are designed to run alongside your application servers
(or on a separate hostconnected via a network).The <strong>model serving</strong> process helps Arch make intelligent decisions about the
incoming prompts. The model server is designed to call the (fast) purpose-built <a class="reference internal" href="../../../llms/llms.html#llms-in-arch"><span class="std std-ref">LLMs</span></a> in Arch.</p>
</section>
</article>
<footer class="prev-next-footer d-print-none">
<div class="prev-next-area">
<a class="left-prev"
href="../architecture.html"
title="previous page">
<i class="fa-solid fa-angle-left"></i>
<div class="prev-next-info">
<p class="prev-next-subtitle">previous</p>
<p class="prev-next-title">Technical Architecture</p>
</div>
</a>
<a class="right-next"
href="threading_model.html"
title="next page">
<div class="prev-next-info">
<p class="prev-next-subtitle">next</p>
<p class="prev-next-title">Threading model</p>
</div>
<i class="fa-solid fa-angle-right"></i>
</a>
</div>
</footer>
</div>
</div>
<footer class="bd-footer-content">
<div class="bd-footer-content__inner container">
<div class="footer-item">
<p class="component-author">
By Katanemo Labs, Inc
</p>
</div>
<div class="footer-item">
<p class="copyright">
© Copyright 2024, Katanemo Labs, Inc.
<br/>
</p>
</div>
<div class="footer-item">
</div>
<div class="footer-item">
</div>
</div>
</footer>
</main>
</div>
</div>
<!-- Scripts loaded after <body> so the DOM is not blocked -->
<script src="../../../_static/scripts/bootstrap.js?digest=dfe6caa3a7d634c4db9b"></script>
<script src="../../../_static/scripts/pydata-sphinx-theme.js?digest=dfe6caa3a7d634c4db9b"></script>
<footer class="bd-footer">
</footer>
</body>
</html>

View file

@ -0,0 +1,445 @@
<!DOCTYPE html>
<html lang="en" data-content_root="../../../" >
<head>
<meta charset="utf-8" />
<meta name="viewport" content="width=device-width, initial-scale=1.0" /><meta name="viewport" content="width=device-width, initial-scale=1" />
<title>Threading model &#8212; Arch 0.1-beta documentation</title>
<script data-cfasync="false">
document.documentElement.dataset.mode = localStorage.getItem("mode") || "";
document.documentElement.dataset.theme = localStorage.getItem("theme") || "";
</script>
<!-- Loaded before other Sphinx assets -->
<link href="../../../_static/styles/theme.css?digest=dfe6caa3a7d634c4db9b" rel="stylesheet" />
<link href="../../../_static/styles/bootstrap.css?digest=dfe6caa3a7d634c4db9b" rel="stylesheet" />
<link href="../../../_static/styles/pydata-sphinx-theme.css?digest=dfe6caa3a7d634c4db9b" rel="stylesheet" />
<link href="../../../_static/vendor/fontawesome/6.5.2/css/all.min.css?digest=dfe6caa3a7d634c4db9b" rel="stylesheet" />
<link rel="preload" as="font" type="font/woff2" crossorigin href="../../../_static/vendor/fontawesome/6.5.2/webfonts/fa-solid-900.woff2" />
<link rel="preload" as="font" type="font/woff2" crossorigin href="../../../_static/vendor/fontawesome/6.5.2/webfonts/fa-brands-400.woff2" />
<link rel="preload" as="font" type="font/woff2" crossorigin href="../../../_static/vendor/fontawesome/6.5.2/webfonts/fa-regular-400.woff2" />
<link rel="stylesheet" type="text/css" href="../../../_static/pygments.css?v=a746c00c" />
<link rel="stylesheet" type="text/css" href="../../../_static/styles/sphinx-book-theme.css?v=a3416100" />
<link rel="stylesheet" type="text/css" href="../../../_static/copybutton.css?v=76b2166b" />
<!-- Pre-loaded scripts that we'll load fully later -->
<link rel="preload" as="script" href="../../../_static/scripts/bootstrap.js?digest=dfe6caa3a7d634c4db9b" />
<link rel="preload" as="script" href="../../../_static/scripts/pydata-sphinx-theme.js?digest=dfe6caa3a7d634c4db9b" />
<script src="../../../_static/vendor/fontawesome/6.5.2/js/all.min.js?digest=dfe6caa3a7d634c4db9b"></script>
<script src="../../../_static/documentation_options.js?v=2742c0eb"></script>
<script src="../../../_static/doctools.js?v=9a2dae69"></script>
<script src="../../../_static/sphinx_highlight.js?v=dc90522c"></script>
<script src="../../../_static/clipboard.min.js?v=a7894cd8"></script>
<script src="../../../_static/copybutton.js?v=f281be69"></script>
<script src="../../../_static/scripts/sphinx-book-theme.js?v=887ef09a"></script>
<script>DOCUMENTATION_OPTIONS.pagename = 'intro/architecture/intro/threading_model';</script>
<link rel="icon" href="../../../_static/favicon.ico"/>
<link rel="index" title="Index" href="../../../genindex.html" />
<link rel="search" title="Search" href="../../../search.html" />
<link rel="next" title="Listener" href="../listeners/listeners.html" />
<link rel="prev" title="Terminology" href="terminology.html" />
<meta name="viewport" content="width=device-width, initial-scale=1"/>
<meta name="docsearch:language" content="en"/>
</head>
<body data-bs-spy="scroll" data-bs-target=".bd-toc-nav" data-offset="180" data-bs-root-margin="0px 0px -60%" data-default-mode="">
<div id="pst-skip-link" class="skip-link d-print-none"><a href="#main-content">Skip to main content</a></div>
<div id="pst-scroll-pixel-helper"></div>
<button type="button" class="btn rounded-pill" id="pst-back-to-top">
<i class="fa-solid fa-arrow-up"></i>Back to top</button>
<input type="checkbox"
class="sidebar-toggle"
id="pst-primary-sidebar-checkbox"/>
<label class="overlay overlay-primary" for="pst-primary-sidebar-checkbox"></label>
<input type="checkbox"
class="sidebar-toggle"
id="pst-secondary-sidebar-checkbox"/>
<label class="overlay overlay-secondary" for="pst-secondary-sidebar-checkbox"></label>
<div class="search-button__wrapper">
<div class="search-button__overlay"></div>
<div class="search-button__search-container">
<form class="bd-search d-flex align-items-center"
action="../../../search.html"
method="get">
<i class="fa-solid fa-magnifying-glass"></i>
<input type="search"
class="form-control"
name="q"
id="search-input"
placeholder="Search..."
aria-label="Search..."
autocomplete="off"
autocorrect="off"
autocapitalize="off"
spellcheck="false"/>
<span class="search-button__kbd-shortcut"><kbd class="kbd-shortcut__modifier">Ctrl</kbd>+<kbd>K</kbd></span>
</form></div>
</div>
<div class="pst-async-banner-revealer d-none">
<aside id="bd-header-version-warning" class="d-none d-print-none" aria-label="Version warning"></aside>
</div>
<header class="bd-header navbar navbar-expand-lg bd-navbar d-print-none">
</header>
<div class="bd-container">
<div class="bd-container__inner bd-page-width">
<div class="bd-sidebar-primary bd-sidebar">
<div class="sidebar-header-items sidebar-primary__section">
</div>
<div class="sidebar-primary-items__start sidebar-primary__section">
<div class="sidebar-primary-item">
<a class="navbar-brand logo" href="../../../root.html">
<img src="../../../_static/arch-nav-logo.png" class="logo__image only-light" alt="Arch 0.1-beta documentation - Home"/>
<script>document.write(`<img src="../../../_static/arch-nav-logo.png" class="logo__image only-dark" alt="Arch 0.1-beta documentation - Home"/>`);</script>
</a></div>
<div class="sidebar-primary-item">
<script>
document.write(`
<button class="btn search-button-field search-button__button" title="Search" aria-label="Search" data-bs-placement="bottom" data-bs-toggle="tooltip">
<i class="fa-solid fa-magnifying-glass"></i>
<span class="search-button__default-text">Search</span>
<span class="search-button__kbd-shortcut"><kbd class="kbd-shortcut__modifier">Ctrl</kbd>+<kbd class="kbd-shortcut__modifier">K</kbd></span>
</button>
`);
</script></div>
<div class="sidebar-primary-item"><nav class="bd-links bd-docs-nav" aria-label="Main">
<div class="bd-toc-item navbar-nav active">
<ul class="current nav bd-sidenav">
<li class="toctree-l1 current active has-children"><a class="reference internal" href="../../intro.html">Introduction</a><details open="open"><summary><span class="toctree-toggle" role="presentation"><i class="fa-solid fa-chevron-down"></i></span></summary><ul class="current">
<li class="toctree-l2"><a class="reference internal" href="../../what_is_arch.html">What is Arch</a></li>
<li class="toctree-l2 current active has-children"><a class="reference internal" href="../architecture.html">Technical Architecture</a><details open="open"><summary><span class="toctree-toggle" role="presentation"><i class="fa-solid fa-chevron-down"></i></span></summary><ul class="current">
<li class="toctree-l3"><a class="reference internal" href="terminology.html">Terminology</a></li>
<li class="toctree-l3 current active"><a class="current reference internal" href="#">Threading model</a></li>
<li class="toctree-l3"><a class="reference internal" href="../listeners/listeners.html">Listener</a></li>
<li class="toctree-l3"><a class="reference internal" href="../prompt_processing/prompt_processing.html">Prompts</a></li>
<li class="toctree-l3"><a class="reference internal" href="../listeners/llm_provider.html">LLM Provider</a></li>
<li class="toctree-l3"><a class="reference internal" href="../model_serving/model_serving.html">Model Serving</a></li>
</ul>
</details></li>
<li class="toctree-l2"><a class="reference internal" href="../../life_of_a_request.html">Life of a Request</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../getting_help.html">Getting help</a></li>
</ul>
</details></li>
<li class="toctree-l1"><a class="reference internal" href="../../../getting_started/getting_started.html">Getting Started</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../getting_started/use_cases/rag.html">Retrieval-Augmented (RAG)</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../getting_started/use_cases/function_calling.html">Agentic (Text-to-Action) Apps</a></li>
<li class="toctree-l1 has-children"><a class="reference internal" href="../../../observability/observability.html">Observability</a><details><summary><span class="toctree-toggle" role="presentation"><i class="fa-solid fa-chevron-down"></i></span></summary><ul>
<li class="toctree-l2"><a class="reference internal" href="../../../observability/tracing.html">Tracing</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../observability/stats.html">Monitoring</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../observability/access_logs.html">Access Logging</a></li>
</ul>
</details></li>
<li class="toctree-l1"><a class="reference internal" href="../../../llms/llms.html">LLMs</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../configuration_reference.html">Configuration Reference</a></li>
</ul>
</div>
</nav></div>
</div>
<div class="sidebar-primary-items__end sidebar-primary__section">
</div>
<div id="rtd-footer-container"></div>
</div>
<main id="main-content" class="bd-main" role="main">
<div class="sbt-scroll-pixel-helper"></div>
<div class="bd-content">
<div class="bd-article-container">
<div class="bd-header-article d-print-none">
<div class="header-article-items header-article__inner">
<div class="header-article-items__start">
<div class="header-article-item"><button class="sidebar-toggle primary-toggle btn btn-sm" title="Toggle primary sidebar" data-bs-placement="bottom" data-bs-toggle="tooltip">
<span class="fa-solid fa-bars"></span>
</button></div>
</div>
<div class="header-article-items__end">
<div class="header-article-item">
<div class="article-header-buttons">
<div class="dropdown dropdown-download-buttons">
<button class="btn dropdown-toggle" type="button" data-bs-toggle="dropdown" aria-expanded="false" aria-label="Download this page">
<i class="fas fa-download"></i>
</button>
<ul class="dropdown-menu">
<li><a href="../../../_sources/intro/architecture/intro/threading_model.rst" target="_blank"
class="btn btn-sm btn-download-source-button dropdown-item"
title="Download source file"
data-bs-placement="left" data-bs-toggle="tooltip"
>
<span class="btn__icon-container">
<i class="fas fa-file"></i>
</span>
<span class="btn__text-container">.rst</span>
</a>
</li>
<li>
<button onclick="window.print()"
class="btn btn-sm btn-download-pdf-button dropdown-item"
title="Print to PDF"
data-bs-placement="left" data-bs-toggle="tooltip"
>
<span class="btn__icon-container">
<i class="fas fa-file-pdf"></i>
</span>
<span class="btn__text-container">.pdf</span>
</button>
</li>
</ul>
</div>
<button onclick="toggleFullScreen()"
class="btn btn-sm btn-fullscreen-button"
title="Fullscreen mode"
data-bs-placement="bottom" data-bs-toggle="tooltip"
>
<span class="btn__icon-container">
<i class="fas fa-expand"></i>
</span>
</button>
<script>
document.write(`
<button class="btn btn-sm nav-link pst-navbar-icon theme-switch-button" title="light/dark" aria-label="light/dark" data-bs-placement="bottom" data-bs-toggle="tooltip">
<i class="theme-switch fa-solid fa-sun fa-lg" data-mode="light"></i>
<i class="theme-switch fa-solid fa-moon fa-lg" data-mode="dark"></i>
<i class="theme-switch fa-solid fa-circle-half-stroke fa-lg" data-mode="auto"></i>
</button>
`);
</script>
<script>
document.write(`
<button class="btn btn-sm pst-navbar-icon search-button search-button__button" title="Search" aria-label="Search" data-bs-placement="bottom" data-bs-toggle="tooltip">
<i class="fa-solid fa-magnifying-glass fa-lg"></i>
</button>
`);
</script>
</div></div>
</div>
</div>
</div>
<div id="jb-print-docs-body" class="onlyprint">
<h1>Threading model</h1>
<!-- Table of contents -->
<div id="print-main-content">
<div id="jb-print-toc">
</div>
</div>
</div>
<div id="searchbox"></div>
<article class="bd-article">
<section id="threading-model">
<span id="arch-overview-threading"></span><h1>Threading model<a class="headerlink" href="#threading-model" title="Link to this heading">#</a></h1>
<p>Arch builds on top of Envoys 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 Arch to be largely single threaded (embarrassingly parallel) with a small amount
of more complex code handling coordination between the worker threads.</p>
<p>Generally Arch is written to be 100% non-blocking.</p>
<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>
</article>
<footer class="prev-next-footer d-print-none">
<div class="prev-next-area">
<a class="left-prev"
href="terminology.html"
title="previous page">
<i class="fa-solid fa-angle-left"></i>
<div class="prev-next-info">
<p class="prev-next-subtitle">previous</p>
<p class="prev-next-title">Terminology</p>
</div>
</a>
<a class="right-next"
href="../listeners/listeners.html"
title="next page">
<div class="prev-next-info">
<p class="prev-next-subtitle">next</p>
<p class="prev-next-title">Listener</p>
</div>
<i class="fa-solid fa-angle-right"></i>
</a>
</div>
</footer>
</div>
</div>
<footer class="bd-footer-content">
<div class="bd-footer-content__inner container">
<div class="footer-item">
<p class="component-author">
By Katanemo Labs, Inc
</p>
</div>
<div class="footer-item">
<p class="copyright">
© Copyright 2024, Katanemo Labs, Inc.
<br/>
</p>
</div>
<div class="footer-item">
</div>
<div class="footer-item">
</div>
</div>
</footer>
</main>
</div>
</div>
<!-- Scripts loaded after <body> so the DOM is not blocked -->
<script src="../../../_static/scripts/bootstrap.js?digest=dfe6caa3a7d634c4db9b"></script>
<script src="../../../_static/scripts/pydata-sphinx-theme.js?digest=dfe6caa3a7d634c4db9b"></script>
<footer class="bd-footer">
</footer>
</body>
</html>

View file

@ -0,0 +1,508 @@
<!DOCTYPE html>
<html lang="en" data-content_root="../../../" >
<head>
<meta charset="utf-8" />
<meta name="viewport" content="width=device-width, initial-scale=1.0" /><meta name="viewport" content="width=device-width, initial-scale=1" />
<title>Listener &#8212; Arch 0.1-beta documentation</title>
<script data-cfasync="false">
document.documentElement.dataset.mode = localStorage.getItem("mode") || "";
document.documentElement.dataset.theme = localStorage.getItem("theme") || "";
</script>
<!-- Loaded before other Sphinx assets -->
<link href="../../../_static/styles/theme.css?digest=dfe6caa3a7d634c4db9b" rel="stylesheet" />
<link href="../../../_static/styles/bootstrap.css?digest=dfe6caa3a7d634c4db9b" rel="stylesheet" />
<link href="../../../_static/styles/pydata-sphinx-theme.css?digest=dfe6caa3a7d634c4db9b" rel="stylesheet" />
<link href="../../../_static/vendor/fontawesome/6.5.2/css/all.min.css?digest=dfe6caa3a7d634c4db9b" rel="stylesheet" />
<link rel="preload" as="font" type="font/woff2" crossorigin href="../../../_static/vendor/fontawesome/6.5.2/webfonts/fa-solid-900.woff2" />
<link rel="preload" as="font" type="font/woff2" crossorigin href="../../../_static/vendor/fontawesome/6.5.2/webfonts/fa-brands-400.woff2" />
<link rel="preload" as="font" type="font/woff2" crossorigin href="../../../_static/vendor/fontawesome/6.5.2/webfonts/fa-regular-400.woff2" />
<link rel="stylesheet" type="text/css" href="../../../_static/pygments.css?v=a746c00c" />
<link rel="stylesheet" type="text/css" href="../../../_static/styles/sphinx-book-theme.css?v=a3416100" />
<link rel="stylesheet" type="text/css" href="../../../_static/copybutton.css?v=76b2166b" />
<!-- Pre-loaded scripts that we'll load fully later -->
<link rel="preload" as="script" href="../../../_static/scripts/bootstrap.js?digest=dfe6caa3a7d634c4db9b" />
<link rel="preload" as="script" href="../../../_static/scripts/pydata-sphinx-theme.js?digest=dfe6caa3a7d634c4db9b" />
<script src="../../../_static/vendor/fontawesome/6.5.2/js/all.min.js?digest=dfe6caa3a7d634c4db9b"></script>
<script src="../../../_static/documentation_options.js?v=2742c0eb"></script>
<script src="../../../_static/doctools.js?v=9a2dae69"></script>
<script src="../../../_static/sphinx_highlight.js?v=dc90522c"></script>
<script src="../../../_static/clipboard.min.js?v=a7894cd8"></script>
<script src="../../../_static/copybutton.js?v=f281be69"></script>
<script src="../../../_static/scripts/sphinx-book-theme.js?v=887ef09a"></script>
<script>DOCUMENTATION_OPTIONS.pagename = 'intro/architecture/listeners/listeners';</script>
<link rel="icon" href="../../../_static/favicon.ico"/>
<link rel="index" title="Index" href="../../../genindex.html" />
<link rel="search" title="Search" href="../../../search.html" />
<link rel="next" title="Prompts" href="../prompt_processing/prompt_processing.html" />
<link rel="prev" title="Threading model" href="../intro/threading_model.html" />
<meta name="viewport" content="width=device-width, initial-scale=1"/>
<meta name="docsearch:language" content="en"/>
</head>
<body data-bs-spy="scroll" data-bs-target=".bd-toc-nav" data-offset="180" data-bs-root-margin="0px 0px -60%" data-default-mode="">
<div id="pst-skip-link" class="skip-link d-print-none"><a href="#main-content">Skip to main content</a></div>
<div id="pst-scroll-pixel-helper"></div>
<button type="button" class="btn rounded-pill" id="pst-back-to-top">
<i class="fa-solid fa-arrow-up"></i>Back to top</button>
<input type="checkbox"
class="sidebar-toggle"
id="pst-primary-sidebar-checkbox"/>
<label class="overlay overlay-primary" for="pst-primary-sidebar-checkbox"></label>
<input type="checkbox"
class="sidebar-toggle"
id="pst-secondary-sidebar-checkbox"/>
<label class="overlay overlay-secondary" for="pst-secondary-sidebar-checkbox"></label>
<div class="search-button__wrapper">
<div class="search-button__overlay"></div>
<div class="search-button__search-container">
<form class="bd-search d-flex align-items-center"
action="../../../search.html"
method="get">
<i class="fa-solid fa-magnifying-glass"></i>
<input type="search"
class="form-control"
name="q"
id="search-input"
placeholder="Search..."
aria-label="Search..."
autocomplete="off"
autocorrect="off"
autocapitalize="off"
spellcheck="false"/>
<span class="search-button__kbd-shortcut"><kbd class="kbd-shortcut__modifier">Ctrl</kbd>+<kbd>K</kbd></span>
</form></div>
</div>
<div class="pst-async-banner-revealer d-none">
<aside id="bd-header-version-warning" class="d-none d-print-none" aria-label="Version warning"></aside>
</div>
<header class="bd-header navbar navbar-expand-lg bd-navbar d-print-none">
</header>
<div class="bd-container">
<div class="bd-container__inner bd-page-width">
<div class="bd-sidebar-primary bd-sidebar">
<div class="sidebar-header-items sidebar-primary__section">
</div>
<div class="sidebar-primary-items__start sidebar-primary__section">
<div class="sidebar-primary-item">
<a class="navbar-brand logo" href="../../../root.html">
<img src="../../../_static/arch-nav-logo.png" class="logo__image only-light" alt="Arch 0.1-beta documentation - Home"/>
<script>document.write(`<img src="../../../_static/arch-nav-logo.png" class="logo__image only-dark" alt="Arch 0.1-beta documentation - Home"/>`);</script>
</a></div>
<div class="sidebar-primary-item">
<script>
document.write(`
<button class="btn search-button-field search-button__button" title="Search" aria-label="Search" data-bs-placement="bottom" data-bs-toggle="tooltip">
<i class="fa-solid fa-magnifying-glass"></i>
<span class="search-button__default-text">Search</span>
<span class="search-button__kbd-shortcut"><kbd class="kbd-shortcut__modifier">Ctrl</kbd>+<kbd class="kbd-shortcut__modifier">K</kbd></span>
</button>
`);
</script></div>
<div class="sidebar-primary-item"><nav class="bd-links bd-docs-nav" aria-label="Main">
<div class="bd-toc-item navbar-nav active">
<ul class="current nav bd-sidenav">
<li class="toctree-l1 current active has-children"><a class="reference internal" href="../../intro.html">Introduction</a><details open="open"><summary><span class="toctree-toggle" role="presentation"><i class="fa-solid fa-chevron-down"></i></span></summary><ul class="current">
<li class="toctree-l2"><a class="reference internal" href="../../what_is_arch.html">What is Arch</a></li>
<li class="toctree-l2 current active has-children"><a class="reference internal" href="../architecture.html">Technical Architecture</a><details open="open"><summary><span class="toctree-toggle" role="presentation"><i class="fa-solid fa-chevron-down"></i></span></summary><ul class="current">
<li class="toctree-l3"><a class="reference internal" href="../intro/terminology.html">Terminology</a></li>
<li class="toctree-l3"><a class="reference internal" href="../intro/threading_model.html">Threading model</a></li>
<li class="toctree-l3 current active"><a class="current reference internal" href="#">Listener</a></li>
<li class="toctree-l3"><a class="reference internal" href="../prompt_processing/prompt_processing.html">Prompts</a></li>
<li class="toctree-l3"><a class="reference internal" href="llm_provider.html">LLM Provider</a></li>
<li class="toctree-l3"><a class="reference internal" href="../model_serving/model_serving.html">Model Serving</a></li>
</ul>
</details></li>
<li class="toctree-l2"><a class="reference internal" href="../../life_of_a_request.html">Life of a Request</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../getting_help.html">Getting help</a></li>
</ul>
</details></li>
<li class="toctree-l1"><a class="reference internal" href="../../../getting_started/getting_started.html">Getting Started</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../getting_started/use_cases/rag.html">Retrieval-Augmented (RAG)</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../getting_started/use_cases/function_calling.html">Agentic (Text-to-Action) Apps</a></li>
<li class="toctree-l1 has-children"><a class="reference internal" href="../../../observability/observability.html">Observability</a><details><summary><span class="toctree-toggle" role="presentation"><i class="fa-solid fa-chevron-down"></i></span></summary><ul>
<li class="toctree-l2"><a class="reference internal" href="../../../observability/tracing.html">Tracing</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../observability/stats.html">Monitoring</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../observability/access_logs.html">Access Logging</a></li>
</ul>
</details></li>
<li class="toctree-l1"><a class="reference internal" href="../../../llms/llms.html">LLMs</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../configuration_reference.html">Configuration Reference</a></li>
</ul>
</div>
</nav></div>
</div>
<div class="sidebar-primary-items__end sidebar-primary__section">
</div>
<div id="rtd-footer-container"></div>
</div>
<main id="main-content" class="bd-main" role="main">
<div class="sbt-scroll-pixel-helper"></div>
<div class="bd-content">
<div class="bd-article-container">
<div class="bd-header-article d-print-none">
<div class="header-article-items header-article__inner">
<div class="header-article-items__start">
<div class="header-article-item"><button class="sidebar-toggle primary-toggle btn btn-sm" title="Toggle primary sidebar" data-bs-placement="bottom" data-bs-toggle="tooltip">
<span class="fa-solid fa-bars"></span>
</button></div>
</div>
<div class="header-article-items__end">
<div class="header-article-item">
<div class="article-header-buttons">
<div class="dropdown dropdown-download-buttons">
<button class="btn dropdown-toggle" type="button" data-bs-toggle="dropdown" aria-expanded="false" aria-label="Download this page">
<i class="fas fa-download"></i>
</button>
<ul class="dropdown-menu">
<li><a href="../../../_sources/intro/architecture/listeners/listeners.rst" target="_blank"
class="btn btn-sm btn-download-source-button dropdown-item"
title="Download source file"
data-bs-placement="left" data-bs-toggle="tooltip"
>
<span class="btn__icon-container">
<i class="fas fa-file"></i>
</span>
<span class="btn__text-container">.rst</span>
</a>
</li>
<li>
<button onclick="window.print()"
class="btn btn-sm btn-download-pdf-button dropdown-item"
title="Print to PDF"
data-bs-placement="left" data-bs-toggle="tooltip"
>
<span class="btn__icon-container">
<i class="fas fa-file-pdf"></i>
</span>
<span class="btn__text-container">.pdf</span>
</button>
</li>
</ul>
</div>
<button onclick="toggleFullScreen()"
class="btn btn-sm btn-fullscreen-button"
title="Fullscreen mode"
data-bs-placement="bottom" data-bs-toggle="tooltip"
>
<span class="btn__icon-container">
<i class="fas fa-expand"></i>
</span>
</button>
<script>
document.write(`
<button class="btn btn-sm nav-link pst-navbar-icon theme-switch-button" title="light/dark" aria-label="light/dark" data-bs-placement="bottom" data-bs-toggle="tooltip">
<i class="theme-switch fa-solid fa-sun fa-lg" data-mode="light"></i>
<i class="theme-switch fa-solid fa-moon fa-lg" data-mode="dark"></i>
<i class="theme-switch fa-solid fa-circle-half-stroke fa-lg" data-mode="auto"></i>
</button>
`);
</script>
<script>
document.write(`
<button class="btn btn-sm pst-navbar-icon search-button search-button__button" title="Search" aria-label="Search" data-bs-placement="bottom" data-bs-toggle="tooltip">
<i class="fa-solid fa-magnifying-glass fa-lg"></i>
</button>
`);
</script>
<button class="sidebar-toggle secondary-toggle btn btn-sm" title="Toggle secondary sidebar" data-bs-placement="bottom" data-bs-toggle="tooltip">
<span class="fa-solid fa-list"></span>
</button>
</div></div>
</div>
</div>
</div>
<div id="jb-print-docs-body" class="onlyprint">
<h1>Listener</h1>
<!-- Table of contents -->
<div id="print-main-content">
<div id="jb-print-toc">
<div>
<h2> Contents </h2>
</div>
<nav aria-label="Page">
<ul class="visible nav section-nav flex-column">
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#downstream-ingress">Downstream (Ingress)</a></li>
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#upstream-egress">Upstream (Egress)</a></li>
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#configure-listener">Configure Listener</a></li>
</ul>
</nav>
</div>
</div>
</div>
<div id="searchbox"></div>
<article class="bd-article">
<section id="listener">
<span id="arch-overview-listeners"></span><h1>Listener<a class="headerlink" href="#listener" title="Link to this heading">#</a></h1>
<p>Listener is a top level primitive in Arch, which simplifies the configuration required to bind incoming
connections from downstream clients, and for egress connections to LLMs (hosted or API)</p>
<p>Arch builds on Envoys Listener subsystem to streamline connection managemet for developers. Arch minimizes
the complexity of Envoys listener setup by using best-practices and exposing only essential settings,
making it easier for developers to bind connections without deep knowledge of Envoys configuration model. This
simplification ensures that connections are secure, reliable, and optimized for performance.</p>
<section id="downstream-ingress">
<h2>Downstream (Ingress)<a class="headerlink" href="#downstream-ingress" title="Link to this heading">#</a></h2>
<p>Developers can configure Arch to accept connections from downstream clients. A downstream listener acts as the
primary entry point for incoming traffic, handling initial connection setup, including network filtering, gurdrails,
and additional network security checks. For more details on prompt security and safety,
see <a class="reference internal" href="../prompt_processing/prompt_processing.html#arch-overview-prompt-handling"><span class="std std-ref">here</span></a></p>
</section>
<section id="upstream-egress">
<h2>Upstream (Egress)<a class="headerlink" href="#upstream-egress" title="Link to this heading">#</a></h2>
<p>Arch automatically configures a listener to route requests from your application to upstream LLM API providers (or hosts).
When you start Arch, it creates a listener for egress traffic based on the presence of the <code class="docutils literal notranslate"><span class="pre">llm_providers</span></code> configuration
section in the <code class="docutils literal notranslate"><span class="pre">prompt_config.yml</span></code> file. Arch binds itself to a local address such as <code class="docutils literal notranslate"><span class="pre">127.0.0.1:9000/v1</span></code> or a DNS-based
address like <code class="docutils literal notranslate"><span class="pre">arch.local:9000/v1</span></code> for outgoing traffic. For more details on LLM providers, read <a class="reference internal" href="llm_provider.html#llm-providers"><span class="std std-ref">here</span></a></p>
</section>
<section id="configure-listener">
<h2>Configure Listener<a class="headerlink" href="#configure-listener" title="Link to this heading">#</a></h2>
<p>To configure a Downstream (Ingress) Listner, simply add the <code class="docutils literal notranslate"><span class="pre">listener</span></code> directive to your <code class="docutils literal notranslate"><span class="pre">prompt_config.yml</span></code> file:</p>
<div class="literal-block-wrapper docutils container" id="id1">
<div class="code-block-caption"><span class="caption-text"><a class="reference download internal" download="" href="../../../_downloads/a0b0970c8fa22d4fe861e8362965b77c/getting-started.yml"><code class="xref download docutils literal notranslate"><span class="pre">arch-getting-started.yml</span></code></a></span><a class="headerlink" href="#id1" title="Link to this code">#</a></div>
<div class="highlight-yaml notranslate"><div class="highlight"><pre><span></span><span class="linenos"> 1</span><span class="nt">version</span><span class="p">:</span><span class="w"> </span><span class="s">&quot;0.1-beta&quot;</span>
<span class="hll"><span class="linenos"> 2</span><span class="nt">listener</span><span class="p">:</span>
</span><span class="hll"><span class="linenos"> 3</span><span class="w"> </span><span class="nt">address</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">127.0.0.1 | 0.0.0.0</span>
</span><span class="hll"><span class="linenos"> 4</span><span class="w"> </span><span class="nt">port_value</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">8080</span><span class="w"> </span><span class="c1">#If you configure port 443, you&#39;ll need to update the listener with tls_certificates</span>
</span><span class="hll"><span class="linenos"> 5</span><span class="w"> </span><span class="nt">messages</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">tuple | hugging-face-messages-api</span>
</span><span class="linenos"> 6</span>
<span class="linenos"> 7</span><span class="nt">system_prompts</span><span class="p">:</span>
<span class="linenos"> 8</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">network_assistant</span>
<span class="linenos"> 9</span><span class="w"> </span><span class="nt">content</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 about the operational health of the network</span>
<span class="linenos">10</span>
<span class="linenos">11</span><span class="nt">llm_providers</span><span class="p">:</span>
<span class="linenos">12</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="s">&quot;OpenAI&quot;</span>
<span class="linenos">13</span><span class="w"> </span><span class="nt">access_key</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">$OPEN_AI_KEY</span>
<span class="linenos">14</span><span class="w"> </span><span class="nt">model</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">gpt-4o</span>
<span class="linenos">15</span><span class="w"> </span><span class="nt">default</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">true</span>
<span class="linenos">16</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="s">&quot;Mistral&quot;</span>
<span class="linenos">17</span><span class="w"> </span><span class="nt">access_key</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">$MISTRAL_KEY</span>
<span class="linenos">18</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">mixtral8-7B</span>
</pre></div>
</div>
</div>
</section>
</section>
</article>
<footer class="prev-next-footer d-print-none">
<div class="prev-next-area">
<a class="left-prev"
href="../intro/threading_model.html"
title="previous page">
<i class="fa-solid fa-angle-left"></i>
<div class="prev-next-info">
<p class="prev-next-subtitle">previous</p>
<p class="prev-next-title">Threading model</p>
</div>
</a>
<a class="right-next"
href="../prompt_processing/prompt_processing.html"
title="next page">
<div class="prev-next-info">
<p class="prev-next-subtitle">next</p>
<p class="prev-next-title">Prompts</p>
</div>
<i class="fa-solid fa-angle-right"></i>
</a>
</div>
</footer>
</div>
<div class="bd-sidebar-secondary bd-toc"><div class="sidebar-secondary-items sidebar-secondary__inner">
<div class="sidebar-secondary-item">
<div class="page-toc tocsection onthispage">
<i class="fa-solid fa-list"></i> Contents
</div>
<nav class="bd-toc-nav page-toc">
<ul class="visible nav section-nav flex-column">
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#downstream-ingress">Downstream (Ingress)</a></li>
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#upstream-egress">Upstream (Egress)</a></li>
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#configure-listener">Configure Listener</a></li>
</ul>
</nav></div>
</div></div>
</div>
<footer class="bd-footer-content">
<div class="bd-footer-content__inner container">
<div class="footer-item">
<p class="component-author">
By Katanemo Labs, Inc
</p>
</div>
<div class="footer-item">
<p class="copyright">
© Copyright 2024, Katanemo Labs, Inc.
<br/>
</p>
</div>
<div class="footer-item">
</div>
<div class="footer-item">
</div>
</div>
</footer>
</main>
</div>
</div>
<!-- Scripts loaded after <body> so the DOM is not blocked -->
<script src="../../../_static/scripts/bootstrap.js?digest=dfe6caa3a7d634c4db9b"></script>
<script src="../../../_static/scripts/pydata-sphinx-theme.js?digest=dfe6caa3a7d634c4db9b"></script>
<footer class="bd-footer">
</footer>
</body>
</html>

View file

@ -0,0 +1,523 @@
<!DOCTYPE html>
<html lang="en" data-content_root="../../../" >
<head>
<meta charset="utf-8" />
<meta name="viewport" content="width=device-width, initial-scale=1.0" /><meta name="viewport" content="width=device-width, initial-scale=1" />
<title>LLM Provider &#8212; Arch 0.1-beta documentation</title>
<script data-cfasync="false">
document.documentElement.dataset.mode = localStorage.getItem("mode") || "";
document.documentElement.dataset.theme = localStorage.getItem("theme") || "";
</script>
<!-- Loaded before other Sphinx assets -->
<link href="../../../_static/styles/theme.css?digest=dfe6caa3a7d634c4db9b" rel="stylesheet" />
<link href="../../../_static/styles/bootstrap.css?digest=dfe6caa3a7d634c4db9b" rel="stylesheet" />
<link href="../../../_static/styles/pydata-sphinx-theme.css?digest=dfe6caa3a7d634c4db9b" rel="stylesheet" />
<link href="../../../_static/vendor/fontawesome/6.5.2/css/all.min.css?digest=dfe6caa3a7d634c4db9b" rel="stylesheet" />
<link rel="preload" as="font" type="font/woff2" crossorigin href="../../../_static/vendor/fontawesome/6.5.2/webfonts/fa-solid-900.woff2" />
<link rel="preload" as="font" type="font/woff2" crossorigin href="../../../_static/vendor/fontawesome/6.5.2/webfonts/fa-brands-400.woff2" />
<link rel="preload" as="font" type="font/woff2" crossorigin href="../../../_static/vendor/fontawesome/6.5.2/webfonts/fa-regular-400.woff2" />
<link rel="stylesheet" type="text/css" href="../../../_static/pygments.css?v=a746c00c" />
<link rel="stylesheet" type="text/css" href="../../../_static/styles/sphinx-book-theme.css?v=a3416100" />
<link rel="stylesheet" type="text/css" href="../../../_static/copybutton.css?v=76b2166b" />
<!-- Pre-loaded scripts that we'll load fully later -->
<link rel="preload" as="script" href="../../../_static/scripts/bootstrap.js?digest=dfe6caa3a7d634c4db9b" />
<link rel="preload" as="script" href="../../../_static/scripts/pydata-sphinx-theme.js?digest=dfe6caa3a7d634c4db9b" />
<script src="../../../_static/vendor/fontawesome/6.5.2/js/all.min.js?digest=dfe6caa3a7d634c4db9b"></script>
<script src="../../../_static/documentation_options.js?v=2742c0eb"></script>
<script src="../../../_static/doctools.js?v=9a2dae69"></script>
<script src="../../../_static/sphinx_highlight.js?v=dc90522c"></script>
<script src="../../../_static/clipboard.min.js?v=a7894cd8"></script>
<script src="../../../_static/copybutton.js?v=f281be69"></script>
<script src="../../../_static/scripts/sphinx-book-theme.js?v=887ef09a"></script>
<script>DOCUMENTATION_OPTIONS.pagename = 'intro/architecture/listeners/llm_provider';</script>
<link rel="icon" href="../../../_static/favicon.ico"/>
<link rel="index" title="Index" href="../../../genindex.html" />
<link rel="search" title="Search" href="../../../search.html" />
<link rel="next" title="Model Serving" href="../model_serving/model_serving.html" />
<link rel="prev" title="Prompts" href="../prompt_processing/prompt_processing.html" />
<meta name="viewport" content="width=device-width, initial-scale=1"/>
<meta name="docsearch:language" content="en"/>
</head>
<body data-bs-spy="scroll" data-bs-target=".bd-toc-nav" data-offset="180" data-bs-root-margin="0px 0px -60%" data-default-mode="">
<div id="pst-skip-link" class="skip-link d-print-none"><a href="#main-content">Skip to main content</a></div>
<div id="pst-scroll-pixel-helper"></div>
<button type="button" class="btn rounded-pill" id="pst-back-to-top">
<i class="fa-solid fa-arrow-up"></i>Back to top</button>
<input type="checkbox"
class="sidebar-toggle"
id="pst-primary-sidebar-checkbox"/>
<label class="overlay overlay-primary" for="pst-primary-sidebar-checkbox"></label>
<input type="checkbox"
class="sidebar-toggle"
id="pst-secondary-sidebar-checkbox"/>
<label class="overlay overlay-secondary" for="pst-secondary-sidebar-checkbox"></label>
<div class="search-button__wrapper">
<div class="search-button__overlay"></div>
<div class="search-button__search-container">
<form class="bd-search d-flex align-items-center"
action="../../../search.html"
method="get">
<i class="fa-solid fa-magnifying-glass"></i>
<input type="search"
class="form-control"
name="q"
id="search-input"
placeholder="Search..."
aria-label="Search..."
autocomplete="off"
autocorrect="off"
autocapitalize="off"
spellcheck="false"/>
<span class="search-button__kbd-shortcut"><kbd class="kbd-shortcut__modifier">Ctrl</kbd>+<kbd>K</kbd></span>
</form></div>
</div>
<div class="pst-async-banner-revealer d-none">
<aside id="bd-header-version-warning" class="d-none d-print-none" aria-label="Version warning"></aside>
</div>
<header class="bd-header navbar navbar-expand-lg bd-navbar d-print-none">
</header>
<div class="bd-container">
<div class="bd-container__inner bd-page-width">
<div class="bd-sidebar-primary bd-sidebar">
<div class="sidebar-header-items sidebar-primary__section">
</div>
<div class="sidebar-primary-items__start sidebar-primary__section">
<div class="sidebar-primary-item">
<a class="navbar-brand logo" href="../../../root.html">
<img src="../../../_static/arch-nav-logo.png" class="logo__image only-light" alt="Arch 0.1-beta documentation - Home"/>
<script>document.write(`<img src="../../../_static/arch-nav-logo.png" class="logo__image only-dark" alt="Arch 0.1-beta documentation - Home"/>`);</script>
</a></div>
<div class="sidebar-primary-item">
<script>
document.write(`
<button class="btn search-button-field search-button__button" title="Search" aria-label="Search" data-bs-placement="bottom" data-bs-toggle="tooltip">
<i class="fa-solid fa-magnifying-glass"></i>
<span class="search-button__default-text">Search</span>
<span class="search-button__kbd-shortcut"><kbd class="kbd-shortcut__modifier">Ctrl</kbd>+<kbd class="kbd-shortcut__modifier">K</kbd></span>
</button>
`);
</script></div>
<div class="sidebar-primary-item"><nav class="bd-links bd-docs-nav" aria-label="Main">
<div class="bd-toc-item navbar-nav active">
<ul class="current nav bd-sidenav">
<li class="toctree-l1 current active has-children"><a class="reference internal" href="../../intro.html">Introduction</a><details open="open"><summary><span class="toctree-toggle" role="presentation"><i class="fa-solid fa-chevron-down"></i></span></summary><ul class="current">
<li class="toctree-l2"><a class="reference internal" href="../../what_is_arch.html">What is Arch</a></li>
<li class="toctree-l2 current active has-children"><a class="reference internal" href="../architecture.html">Technical Architecture</a><details open="open"><summary><span class="toctree-toggle" role="presentation"><i class="fa-solid fa-chevron-down"></i></span></summary><ul class="current">
<li class="toctree-l3"><a class="reference internal" href="../intro/terminology.html">Terminology</a></li>
<li class="toctree-l3"><a class="reference internal" href="../intro/threading_model.html">Threading model</a></li>
<li class="toctree-l3"><a class="reference internal" href="listeners.html">Listener</a></li>
<li class="toctree-l3"><a class="reference internal" href="../prompt_processing/prompt_processing.html">Prompts</a></li>
<li class="toctree-l3 current active"><a class="current reference internal" href="#">LLM Provider</a></li>
<li class="toctree-l3"><a class="reference internal" href="../model_serving/model_serving.html">Model Serving</a></li>
</ul>
</details></li>
<li class="toctree-l2"><a class="reference internal" href="../../life_of_a_request.html">Life of a Request</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../getting_help.html">Getting help</a></li>
</ul>
</details></li>
<li class="toctree-l1"><a class="reference internal" href="../../../getting_started/getting_started.html">Getting Started</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../getting_started/use_cases/rag.html">Retrieval-Augmented (RAG)</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../getting_started/use_cases/function_calling.html">Agentic (Text-to-Action) Apps</a></li>
<li class="toctree-l1 has-children"><a class="reference internal" href="../../../observability/observability.html">Observability</a><details><summary><span class="toctree-toggle" role="presentation"><i class="fa-solid fa-chevron-down"></i></span></summary><ul>
<li class="toctree-l2"><a class="reference internal" href="../../../observability/tracing.html">Tracing</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../observability/stats.html">Monitoring</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../observability/access_logs.html">Access Logging</a></li>
</ul>
</details></li>
<li class="toctree-l1"><a class="reference internal" href="../../../llms/llms.html">LLMs</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../configuration_reference.html">Configuration Reference</a></li>
</ul>
</div>
</nav></div>
</div>
<div class="sidebar-primary-items__end sidebar-primary__section">
</div>
<div id="rtd-footer-container"></div>
</div>
<main id="main-content" class="bd-main" role="main">
<div class="sbt-scroll-pixel-helper"></div>
<div class="bd-content">
<div class="bd-article-container">
<div class="bd-header-article d-print-none">
<div class="header-article-items header-article__inner">
<div class="header-article-items__start">
<div class="header-article-item"><button class="sidebar-toggle primary-toggle btn btn-sm" title="Toggle primary sidebar" data-bs-placement="bottom" data-bs-toggle="tooltip">
<span class="fa-solid fa-bars"></span>
</button></div>
</div>
<div class="header-article-items__end">
<div class="header-article-item">
<div class="article-header-buttons">
<div class="dropdown dropdown-download-buttons">
<button class="btn dropdown-toggle" type="button" data-bs-toggle="dropdown" aria-expanded="false" aria-label="Download this page">
<i class="fas fa-download"></i>
</button>
<ul class="dropdown-menu">
<li><a href="../../../_sources/intro/architecture/listeners/llm_provider.rst" target="_blank"
class="btn btn-sm btn-download-source-button dropdown-item"
title="Download source file"
data-bs-placement="left" data-bs-toggle="tooltip"
>
<span class="btn__icon-container">
<i class="fas fa-file"></i>
</span>
<span class="btn__text-container">.rst</span>
</a>
</li>
<li>
<button onclick="window.print()"
class="btn btn-sm btn-download-pdf-button dropdown-item"
title="Print to PDF"
data-bs-placement="left" data-bs-toggle="tooltip"
>
<span class="btn__icon-container">
<i class="fas fa-file-pdf"></i>
</span>
<span class="btn__text-container">.pdf</span>
</button>
</li>
</ul>
</div>
<button onclick="toggleFullScreen()"
class="btn btn-sm btn-fullscreen-button"
title="Fullscreen mode"
data-bs-placement="bottom" data-bs-toggle="tooltip"
>
<span class="btn__icon-container">
<i class="fas fa-expand"></i>
</span>
</button>
<script>
document.write(`
<button class="btn btn-sm nav-link pst-navbar-icon theme-switch-button" title="light/dark" aria-label="light/dark" data-bs-placement="bottom" data-bs-toggle="tooltip">
<i class="theme-switch fa-solid fa-sun fa-lg" data-mode="light"></i>
<i class="theme-switch fa-solid fa-moon fa-lg" data-mode="dark"></i>
<i class="theme-switch fa-solid fa-circle-half-stroke fa-lg" data-mode="auto"></i>
</button>
`);
</script>
<script>
document.write(`
<button class="btn btn-sm pst-navbar-icon search-button search-button__button" title="Search" aria-label="Search" data-bs-placement="bottom" data-bs-toggle="tooltip">
<i class="fa-solid fa-magnifying-glass fa-lg"></i>
</button>
`);
</script>
<button class="sidebar-toggle secondary-toggle btn btn-sm" title="Toggle secondary sidebar" data-bs-placement="bottom" data-bs-toggle="tooltip">
<span class="fa-solid fa-list"></span>
</button>
</div></div>
</div>
</div>
</div>
<div id="jb-print-docs-body" class="onlyprint">
<h1>LLM Provider</h1>
<!-- Table of contents -->
<div id="print-main-content">
<div id="jb-print-toc">
<div>
<h2> Contents </h2>
</div>
<nav aria-label="Page">
<ul class="visible nav section-nav flex-column">
<li class="toc-h1 nav-item toc-entry"><a class="reference internal nav-link" href="#">LLM Provider</a></li>
<li class="toc-h1 nav-item toc-entry"><a class="reference internal nav-link" href="#example-using-the-arch-python-sdk">Example: Using the Arch Python SDK</a></li>
</ul>
</nav>
</div>
</div>
</div>
<div id="searchbox"></div>
<article class="bd-article">
<section id="llm-provider">
<span id="llm-providers"></span><h1>LLM Provider<a class="headerlink" href="#llm-provider" title="Link to this heading">#</a></h1>
<p><code class="docutils literal notranslate"><span class="pre">llm_provider</span></code> is a top-level primitive in Arch, helping developers centrally define, secure, observe,
and manage the usage of of their LLMs. Arch builds on Envoys reliable <a class="reference external" href="https://www.envoyproxy.io/docs/envoy/v1.31.2/intro/arch_overview/upstream/cluster_manager">cluster subsystem</a>
to manage egress traffic to LLMs, which includes intelligent routing, retry and fail-over mechanisms,
ensuring high availability and fault tolerance. This abstraction also enables developers to seamlessly switching between LLM providers or upgrade LLM versions, simplifying the integration and scaling of LLMs across
applications.</p>
<p>Below is an example of how you can configure <code class="docutils literal notranslate"><span class="pre">llm_providers</span></code> with an instance of an Arch gateway.</p>
<div class="literal-block-wrapper docutils container" id="id1">
<div class="code-block-caption"><span class="caption-text"><a class="reference download internal" download="" href="../../../_downloads/a0b0970c8fa22d4fe861e8362965b77c/getting-started.yml"><code class="xref download docutils literal notranslate"><span class="pre">arch-getting-started.yml</span></code></a></span><a class="headerlink" href="#id1" title="Link to this code">#</a></div>
<div class="highlight-yaml notranslate"><div class="highlight"><pre><span></span><span class="linenos"> 1</span><span class="nt">version</span><span class="p">:</span><span class="w"> </span><span class="s">&quot;0.1-beta&quot;</span>
<span class="linenos"> 2</span><span class="nt">listener</span><span class="p">:</span>
<span class="linenos"> 3</span><span class="w"> </span><span class="nt">address</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">127.0.0.1 | 0.0.0.0</span>
<span class="linenos"> 4</span><span class="w"> </span><span class="nt">port_value</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">8080</span><span class="w"> </span><span class="c1">#If you configure port 443, you&#39;ll need to update the listener with tls_certificates</span>
<span class="linenos"> 5</span><span class="w"> </span><span class="nt">messages</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">tuple | hugging-face-messages-api</span>
<span class="linenos"> 6</span>
<span class="linenos"> 7</span><span class="nt">system_prompts</span><span class="p">:</span>
<span class="linenos"> 8</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">network_assistant</span>
<span class="linenos"> 9</span><span class="w"> </span><span class="nt">content</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 about the operational health of the network</span>
<span class="linenos">10</span>
<span class="hll"><span class="linenos">11</span><span class="nt">llm_providers</span><span class="p">:</span>
</span><span class="hll"><span class="linenos">12</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="s">&quot;OpenAI&quot;</span>
</span><span class="hll"><span class="linenos">13</span><span class="w"> </span><span class="nt">access_key</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">$OPEN_AI_KEY</span>
</span><span class="hll"><span class="linenos">14</span><span class="w"> </span><span class="nt">model</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">gpt-4o</span>
</span><span class="hll"><span class="linenos">15</span><span class="w"> </span><span class="nt">default</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">true</span>
</span><span class="hll"><span class="linenos">16</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="s">&quot;Mistral&quot;</span>
</span><span class="hll"><span class="linenos">17</span><span class="w"> </span><span class="nt">access_key</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">$MISTRAL_KEY</span>
</span><span class="hll"><span class="linenos">18</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">mixtral8-7B</span>
</span><span class="linenos">19</span>
<span class="linenos">20</span><span class="nt">prompt_endpoints</span><span class="p">:</span>
</pre></div>
</div>
</div>
<div class="admonition note">
<p class="admonition-title">Note</p>
<p>When you start Arch, it creates a listener port for egress traffic based on the presence of <code class="docutils literal notranslate"><span class="pre">llm_providers</span></code>
configuration section in the <code class="docutils literal notranslate"><span class="pre">prompt_config.yml</span></code> file. Arch binds itself to a local address such as
<code class="docutils literal notranslate"><span class="pre">127.0.0.1:9000/v1</span></code> or a DNS-based address like <code class="docutils literal notranslate"><span class="pre">arch.local:9000/v1</span></code> for egress traffic.</p>
</div>
<p>Arch also offers vendor-agnostic SDKs and libraries to make LLM calls to API-based LLM providers (like OpenAI,
Anthropic, Mistral, Cohere, etc.) and supports calls to OSS LLMs that are hosted on your infrastructure. Arch
abstracts the complexities of integrating with different LLM providers, providing a unified interface for making
calls, handling retries, managing rate limits, and ensuring seamless integration with cloud-based and on-premise
LLMs. Simply configure the details of the LLMs your application will use, and Arch offers a unified interface to
make outbound LLM calls.</p>
</section>
<section id="example-using-the-arch-python-sdk">
<h1>Example: Using the Arch Python SDK<a class="headerlink" href="#example-using-the-arch-python-sdk" title="Link to this heading">#</a></h1>
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="kn">from</span> <span class="nn">arch_client</span> <span class="kn">import</span> <span class="n">ArchClient</span>
<span class="c1"># Initialize the Arch client</span>
<span class="n">client</span> <span class="o">=</span> <span class="n">ArchClient</span><span class="p">(</span><span class="n">base_url</span><span class="o">=</span><span class="s2">&quot;http://127.0.0.1:9000/v1&quot;</span><span class="p">)</span>
<span class="c1"># Define your LLM provider and prompt</span>
<span class="n">model_id</span> <span class="o">=</span> <span class="s2">&quot;openai&quot;</span>
<span class="n">prompt</span> <span class="o">=</span> <span class="s2">&quot;What is the capital of France?&quot;</span>
<span class="c1"># Send the prompt to the LLM through Arch</span>
<span class="n">response</span> <span class="o">=</span> <span class="n">client</span><span class="o">.</span><span class="n">completions</span><span class="o">.</span><span class="n">create</span><span class="p">(</span><span class="n">llm_provider</span><span class="o">=</span><span class="n">llm_provider</span><span class="p">,</span> <span class="n">prompt</span><span class="o">=</span><span class="n">prompt</span><span class="p">)</span>
<span class="c1"># Print the response</span>
<span class="nb">print</span><span class="p">(</span><span class="s2">&quot;LLM Response:&quot;</span><span class="p">,</span> <span class="n">response</span><span class="p">)</span>
</pre></div>
</div>
</section>
</article>
<footer class="prev-next-footer d-print-none">
<div class="prev-next-area">
<a class="left-prev"
href="../prompt_processing/prompt_processing.html"
title="previous page">
<i class="fa-solid fa-angle-left"></i>
<div class="prev-next-info">
<p class="prev-next-subtitle">previous</p>
<p class="prev-next-title">Prompts</p>
</div>
</a>
<a class="right-next"
href="../model_serving/model_serving.html"
title="next page">
<div class="prev-next-info">
<p class="prev-next-subtitle">next</p>
<p class="prev-next-title">Model Serving</p>
</div>
<i class="fa-solid fa-angle-right"></i>
</a>
</div>
</footer>
</div>
<div class="bd-sidebar-secondary bd-toc"><div class="sidebar-secondary-items sidebar-secondary__inner">
<div class="sidebar-secondary-item">
<div class="page-toc tocsection onthispage">
<i class="fa-solid fa-list"></i> Contents
</div>
<nav class="bd-toc-nav page-toc">
<ul class="visible nav section-nav flex-column">
<li class="toc-h1 nav-item toc-entry"><a class="reference internal nav-link" href="#">LLM Provider</a></li>
<li class="toc-h1 nav-item toc-entry"><a class="reference internal nav-link" href="#example-using-the-arch-python-sdk">Example: Using the Arch Python SDK</a></li>
</ul>
</nav></div>
</div></div>
</div>
<footer class="bd-footer-content">
<div class="bd-footer-content__inner container">
<div class="footer-item">
<p class="component-author">
By Katanemo Labs, Inc
</p>
</div>
<div class="footer-item">
<p class="copyright">
© Copyright 2024, Katanemo Labs, Inc.
<br/>
</p>
</div>
<div class="footer-item">
</div>
<div class="footer-item">
</div>
</div>
</footer>
</main>
</div>
</div>
<!-- Scripts loaded after <body> so the DOM is not blocked -->
<script src="../../../_static/scripts/bootstrap.js?digest=dfe6caa3a7d634c4db9b"></script>
<script src="../../../_static/scripts/pydata-sphinx-theme.js?digest=dfe6caa3a7d634c4db9b"></script>
<footer class="bd-footer">
</footer>
</body>
</html>

View file

@ -0,0 +1,506 @@
<!DOCTYPE html>
<html lang="en" data-content_root="../../../" >
<head>
<meta charset="utf-8" />
<meta name="viewport" content="width=device-width, initial-scale=1.0" /><meta name="viewport" content="width=device-width, initial-scale=1" />
<title>Model Serving &#8212; Arch 0.1-beta documentation</title>
<script data-cfasync="false">
document.documentElement.dataset.mode = localStorage.getItem("mode") || "";
document.documentElement.dataset.theme = localStorage.getItem("theme") || "";
</script>
<!-- Loaded before other Sphinx assets -->
<link href="../../../_static/styles/theme.css?digest=dfe6caa3a7d634c4db9b" rel="stylesheet" />
<link href="../../../_static/styles/bootstrap.css?digest=dfe6caa3a7d634c4db9b" rel="stylesheet" />
<link href="../../../_static/styles/pydata-sphinx-theme.css?digest=dfe6caa3a7d634c4db9b" rel="stylesheet" />
<link href="../../../_static/vendor/fontawesome/6.5.2/css/all.min.css?digest=dfe6caa3a7d634c4db9b" rel="stylesheet" />
<link rel="preload" as="font" type="font/woff2" crossorigin href="../../../_static/vendor/fontawesome/6.5.2/webfonts/fa-solid-900.woff2" />
<link rel="preload" as="font" type="font/woff2" crossorigin href="../../../_static/vendor/fontawesome/6.5.2/webfonts/fa-brands-400.woff2" />
<link rel="preload" as="font" type="font/woff2" crossorigin href="../../../_static/vendor/fontawesome/6.5.2/webfonts/fa-regular-400.woff2" />
<link rel="stylesheet" type="text/css" href="../../../_static/pygments.css?v=a746c00c" />
<link rel="stylesheet" type="text/css" href="../../../_static/styles/sphinx-book-theme.css?v=a3416100" />
<link rel="stylesheet" type="text/css" href="../../../_static/copybutton.css?v=76b2166b" />
<!-- Pre-loaded scripts that we'll load fully later -->
<link rel="preload" as="script" href="../../../_static/scripts/bootstrap.js?digest=dfe6caa3a7d634c4db9b" />
<link rel="preload" as="script" href="../../../_static/scripts/pydata-sphinx-theme.js?digest=dfe6caa3a7d634c4db9b" />
<script src="../../../_static/vendor/fontawesome/6.5.2/js/all.min.js?digest=dfe6caa3a7d634c4db9b"></script>
<script src="../../../_static/documentation_options.js?v=2742c0eb"></script>
<script src="../../../_static/doctools.js?v=9a2dae69"></script>
<script src="../../../_static/sphinx_highlight.js?v=dc90522c"></script>
<script src="../../../_static/clipboard.min.js?v=a7894cd8"></script>
<script src="../../../_static/copybutton.js?v=f281be69"></script>
<script src="../../../_static/scripts/sphinx-book-theme.js?v=887ef09a"></script>
<script>DOCUMENTATION_OPTIONS.pagename = 'intro/architecture/model_serving/model_serving';</script>
<link rel="icon" href="../../../_static/favicon.ico"/>
<link rel="index" title="Index" href="../../../genindex.html" />
<link rel="search" title="Search" href="../../../search.html" />
<link rel="next" title="Life of a Request" href="../../life_of_a_request.html" />
<link rel="prev" title="LLM Provider" href="../listeners/llm_provider.html" />
<meta name="viewport" content="width=device-width, initial-scale=1"/>
<meta name="docsearch:language" content="en"/>
</head>
<body data-bs-spy="scroll" data-bs-target=".bd-toc-nav" data-offset="180" data-bs-root-margin="0px 0px -60%" data-default-mode="">
<div id="pst-skip-link" class="skip-link d-print-none"><a href="#main-content">Skip to main content</a></div>
<div id="pst-scroll-pixel-helper"></div>
<button type="button" class="btn rounded-pill" id="pst-back-to-top">
<i class="fa-solid fa-arrow-up"></i>Back to top</button>
<input type="checkbox"
class="sidebar-toggle"
id="pst-primary-sidebar-checkbox"/>
<label class="overlay overlay-primary" for="pst-primary-sidebar-checkbox"></label>
<input type="checkbox"
class="sidebar-toggle"
id="pst-secondary-sidebar-checkbox"/>
<label class="overlay overlay-secondary" for="pst-secondary-sidebar-checkbox"></label>
<div class="search-button__wrapper">
<div class="search-button__overlay"></div>
<div class="search-button__search-container">
<form class="bd-search d-flex align-items-center"
action="../../../search.html"
method="get">
<i class="fa-solid fa-magnifying-glass"></i>
<input type="search"
class="form-control"
name="q"
id="search-input"
placeholder="Search..."
aria-label="Search..."
autocomplete="off"
autocorrect="off"
autocapitalize="off"
spellcheck="false"/>
<span class="search-button__kbd-shortcut"><kbd class="kbd-shortcut__modifier">Ctrl</kbd>+<kbd>K</kbd></span>
</form></div>
</div>
<div class="pst-async-banner-revealer d-none">
<aside id="bd-header-version-warning" class="d-none d-print-none" aria-label="Version warning"></aside>
</div>
<header class="bd-header navbar navbar-expand-lg bd-navbar d-print-none">
</header>
<div class="bd-container">
<div class="bd-container__inner bd-page-width">
<div class="bd-sidebar-primary bd-sidebar">
<div class="sidebar-header-items sidebar-primary__section">
</div>
<div class="sidebar-primary-items__start sidebar-primary__section">
<div class="sidebar-primary-item">
<a class="navbar-brand logo" href="../../../root.html">
<img src="../../../_static/arch-nav-logo.png" class="logo__image only-light" alt="Arch 0.1-beta documentation - Home"/>
<script>document.write(`<img src="../../../_static/arch-nav-logo.png" class="logo__image only-dark" alt="Arch 0.1-beta documentation - Home"/>`);</script>
</a></div>
<div class="sidebar-primary-item">
<script>
document.write(`
<button class="btn search-button-field search-button__button" title="Search" aria-label="Search" data-bs-placement="bottom" data-bs-toggle="tooltip">
<i class="fa-solid fa-magnifying-glass"></i>
<span class="search-button__default-text">Search</span>
<span class="search-button__kbd-shortcut"><kbd class="kbd-shortcut__modifier">Ctrl</kbd>+<kbd class="kbd-shortcut__modifier">K</kbd></span>
</button>
`);
</script></div>
<div class="sidebar-primary-item"><nav class="bd-links bd-docs-nav" aria-label="Main">
<div class="bd-toc-item navbar-nav active">
<ul class="current nav bd-sidenav">
<li class="toctree-l1 current active has-children"><a class="reference internal" href="../../intro.html">Introduction</a><details open="open"><summary><span class="toctree-toggle" role="presentation"><i class="fa-solid fa-chevron-down"></i></span></summary><ul class="current">
<li class="toctree-l2"><a class="reference internal" href="../../what_is_arch.html">What is Arch</a></li>
<li class="toctree-l2 current active has-children"><a class="reference internal" href="../architecture.html">Technical Architecture</a><details open="open"><summary><span class="toctree-toggle" role="presentation"><i class="fa-solid fa-chevron-down"></i></span></summary><ul class="current">
<li class="toctree-l3"><a class="reference internal" href="../intro/terminology.html">Terminology</a></li>
<li class="toctree-l3"><a class="reference internal" href="../intro/threading_model.html">Threading model</a></li>
<li class="toctree-l3"><a class="reference internal" href="../listeners/listeners.html">Listener</a></li>
<li class="toctree-l3"><a class="reference internal" href="../prompt_processing/prompt_processing.html">Prompts</a></li>
<li class="toctree-l3"><a class="reference internal" href="../listeners/llm_provider.html">LLM Provider</a></li>
<li class="toctree-l3 current active"><a class="current reference internal" href="#">Model Serving</a></li>
</ul>
</details></li>
<li class="toctree-l2"><a class="reference internal" href="../../life_of_a_request.html">Life of a Request</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../getting_help.html">Getting help</a></li>
</ul>
</details></li>
<li class="toctree-l1"><a class="reference internal" href="../../../getting_started/getting_started.html">Getting Started</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../getting_started/use_cases/rag.html">Retrieval-Augmented (RAG)</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../getting_started/use_cases/function_calling.html">Agentic (Text-to-Action) Apps</a></li>
<li class="toctree-l1 has-children"><a class="reference internal" href="../../../observability/observability.html">Observability</a><details><summary><span class="toctree-toggle" role="presentation"><i class="fa-solid fa-chevron-down"></i></span></summary><ul>
<li class="toctree-l2"><a class="reference internal" href="../../../observability/tracing.html">Tracing</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../observability/stats.html">Monitoring</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../observability/access_logs.html">Access Logging</a></li>
</ul>
</details></li>
<li class="toctree-l1"><a class="reference internal" href="../../../llms/llms.html">LLMs</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../configuration_reference.html">Configuration Reference</a></li>
</ul>
</div>
</nav></div>
</div>
<div class="sidebar-primary-items__end sidebar-primary__section">
</div>
<div id="rtd-footer-container"></div>
</div>
<main id="main-content" class="bd-main" role="main">
<div class="sbt-scroll-pixel-helper"></div>
<div class="bd-content">
<div class="bd-article-container">
<div class="bd-header-article d-print-none">
<div class="header-article-items header-article__inner">
<div class="header-article-items__start">
<div class="header-article-item"><button class="sidebar-toggle primary-toggle btn btn-sm" title="Toggle primary sidebar" data-bs-placement="bottom" data-bs-toggle="tooltip">
<span class="fa-solid fa-bars"></span>
</button></div>
</div>
<div class="header-article-items__end">
<div class="header-article-item">
<div class="article-header-buttons">
<div class="dropdown dropdown-download-buttons">
<button class="btn dropdown-toggle" type="button" data-bs-toggle="dropdown" aria-expanded="false" aria-label="Download this page">
<i class="fas fa-download"></i>
</button>
<ul class="dropdown-menu">
<li><a href="../../../_sources/intro/architecture/model_serving/model_serving.rst" target="_blank"
class="btn btn-sm btn-download-source-button dropdown-item"
title="Download source file"
data-bs-placement="left" data-bs-toggle="tooltip"
>
<span class="btn__icon-container">
<i class="fas fa-file"></i>
</span>
<span class="btn__text-container">.rst</span>
</a>
</li>
<li>
<button onclick="window.print()"
class="btn btn-sm btn-download-pdf-button dropdown-item"
title="Print to PDF"
data-bs-placement="left" data-bs-toggle="tooltip"
>
<span class="btn__icon-container">
<i class="fas fa-file-pdf"></i>
</span>
<span class="btn__text-container">.pdf</span>
</button>
</li>
</ul>
</div>
<button onclick="toggleFullScreen()"
class="btn btn-sm btn-fullscreen-button"
title="Fullscreen mode"
data-bs-placement="bottom" data-bs-toggle="tooltip"
>
<span class="btn__icon-container">
<i class="fas fa-expand"></i>
</span>
</button>
<script>
document.write(`
<button class="btn btn-sm nav-link pst-navbar-icon theme-switch-button" title="light/dark" aria-label="light/dark" data-bs-placement="bottom" data-bs-toggle="tooltip">
<i class="theme-switch fa-solid fa-sun fa-lg" data-mode="light"></i>
<i class="theme-switch fa-solid fa-moon fa-lg" data-mode="dark"></i>
<i class="theme-switch fa-solid fa-circle-half-stroke fa-lg" data-mode="auto"></i>
</button>
`);
</script>
<script>
document.write(`
<button class="btn btn-sm pst-navbar-icon search-button search-button__button" title="Search" aria-label="Search" data-bs-placement="bottom" data-bs-toggle="tooltip">
<i class="fa-solid fa-magnifying-glass fa-lg"></i>
</button>
`);
</script>
<button class="sidebar-toggle secondary-toggle btn btn-sm" title="Toggle secondary sidebar" data-bs-placement="bottom" data-bs-toggle="tooltip">
<span class="fa-solid fa-list"></span>
</button>
</div></div>
</div>
</div>
</div>
<div id="jb-print-docs-body" class="onlyprint">
<h1>Model Serving</h1>
<!-- Table of contents -->
<div id="print-main-content">
<div id="jb-print-toc">
<div>
<h2> Contents </h2>
</div>
<nav aria-label="Page">
<ul class="visible nav section-nav flex-column">
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#local-serving-cpu-moderate">Local Serving (CPU - Moderate)</a></li>
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#local-serving-gpu-fast">Local Serving (GPU- Fast)</a></li>
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#cloud-serving-gpu-blazing-fast">Cloud Serving (GPU - Blazing Fast)</a></li>
</ul>
</nav>
</div>
</div>
</div>
<div id="searchbox"></div>
<article class="bd-article">
<section id="model-serving">
<span id="arch-model-serving"></span><h1>Model Serving<a class="headerlink" href="#model-serving" title="Link to this heading">#</a></h1>
<p>Arch is a set of <strong>two</strong> self-contained processes that are designed to run alongside your application
servers (or on a separate host connected via a network). The first process is designated to manage low-level
networking and HTTP related comcerns, and the other process is for <strong>model serving</strong>, which helps Arch make
intelligent decisions about the incoming prompts. The model server is designed to call the purpose-built
<a class="reference internal" href="../../../llms/llms.html#llms-in-arch"><span class="std std-ref">LLMs</span></a> in Arch.</p>
<a class="reference internal image-reference" href="../../../_images/arch-system-architecture.jpg"><img alt="../../../_images/arch-system-architecture.jpg" class="align-center" src="../../../_images/arch-system-architecture.jpg" style="width: 50%;" />
</a>
<hr class="docutils" />
<p>Arch is designed to be deployed in your cloud VPC, on a on-premises host, and can work on devices that dont
have a GPU. Note, GPU devices are need for fast and cost-efficient use, so that Arch (model server, specifically)
can process prompts quickly and forward control back to the applicaton host. There are three modes in which Arch
can be configured to run its <strong>model server</strong> subsystem:</p>
<section id="local-serving-cpu-moderate">
<h2>Local Serving (CPU - Moderate)<a class="headerlink" href="#local-serving-cpu-moderate" title="Link to this heading">#</a></h2>
<p>The following bash commands enable you to configure the model server subsystem in Arch to run local on device
and only use CPU devices. This will be the slowest option but can be useful in dev/test scenarios where GPUs
might not be available.</p>
<div class="highlight-bash notranslate"><div class="highlight"><pre><span></span>archgw<span class="w"> </span>up<span class="w"> </span>--local<span class="w"> </span>-cpu
</pre></div>
</div>
</section>
<section id="local-serving-gpu-fast">
<h2>Local Serving (GPU- Fast)<a class="headerlink" href="#local-serving-gpu-fast" title="Link to this heading">#</a></h2>
<p>The following bash commands enable you to configure the model server subsystem in Arch to run locally on the
machine and utilize the GPU available for fast inference across all model use cases, including function calling
guardails, etc.</p>
<div class="highlight-bash notranslate"><div class="highlight"><pre><span></span>archgw<span class="w"> </span>up<span class="w"> </span>--local
</pre></div>
</div>
</section>
<section id="cloud-serving-gpu-blazing-fast">
<h2>Cloud Serving (GPU - Blazing Fast)<a class="headerlink" href="#cloud-serving-gpu-blazing-fast" title="Link to this heading">#</a></h2>
<p>The command below instructs Arch to intelligently use GPUs locally for fast intent detection, but default to
cloud serving for function calling and guardails scenarios to dramatically improve the speed and overall performance
of your applications.</p>
<div class="highlight-bash notranslate"><div class="highlight"><pre><span></span>archgw<span class="w"> </span>up
</pre></div>
</div>
<div class="admonition note">
<p class="admonition-title">Note</p>
<p>Archs model serving in the cloud is priced at $0.05M/token (156x cheaper than GPT-4o) with averlage latency
of 200ms (10x faster than GPT-4o). Please refer to our <a class="reference internal" href="../../../getting_started/getting_started.html#getting-started"><span class="std std-ref">getting started guide</span></a> to know
how to generate API keys for model serving</p>
</div>
</section>
</section>
</article>
<footer class="prev-next-footer d-print-none">
<div class="prev-next-area">
<a class="left-prev"
href="../listeners/llm_provider.html"
title="previous page">
<i class="fa-solid fa-angle-left"></i>
<div class="prev-next-info">
<p class="prev-next-subtitle">previous</p>
<p class="prev-next-title">LLM Provider</p>
</div>
</a>
<a class="right-next"
href="../../life_of_a_request.html"
title="next page">
<div class="prev-next-info">
<p class="prev-next-subtitle">next</p>
<p class="prev-next-title">Life of a Request</p>
</div>
<i class="fa-solid fa-angle-right"></i>
</a>
</div>
</footer>
</div>
<div class="bd-sidebar-secondary bd-toc"><div class="sidebar-secondary-items sidebar-secondary__inner">
<div class="sidebar-secondary-item">
<div class="page-toc tocsection onthispage">
<i class="fa-solid fa-list"></i> Contents
</div>
<nav class="bd-toc-nav page-toc">
<ul class="visible nav section-nav flex-column">
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#local-serving-cpu-moderate">Local Serving (CPU - Moderate)</a></li>
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#local-serving-gpu-fast">Local Serving (GPU- Fast)</a></li>
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#cloud-serving-gpu-blazing-fast">Cloud Serving (GPU - Blazing Fast)</a></li>
</ul>
</nav></div>
</div></div>
</div>
<footer class="bd-footer-content">
<div class="bd-footer-content__inner container">
<div class="footer-item">
<p class="component-author">
By Katanemo Labs, Inc
</p>
</div>
<div class="footer-item">
<p class="copyright">
© Copyright 2024, Katanemo Labs, Inc.
<br/>
</p>
</div>
<div class="footer-item">
</div>
<div class="footer-item">
</div>
</div>
</footer>
</main>
</div>
</div>
<!-- Scripts loaded after <body> so the DOM is not blocked -->
<script src="../../../_static/scripts/bootstrap.js?digest=dfe6caa3a7d634c4db9b"></script>
<script src="../../../_static/scripts/pydata-sphinx-theme.js?digest=dfe6caa3a7d634c4db9b"></script>
<footer class="bd-footer">
</footer>
</body>
</html>

View file

@ -0,0 +1,707 @@
<!DOCTYPE html>
<html lang="en" data-content_root="../../../" >
<head>
<meta charset="utf-8" />
<meta name="viewport" content="width=device-width, initial-scale=1.0" /><meta name="viewport" content="width=device-width, initial-scale=1" />
<title>Prompts &#8212; Arch 0.1-beta documentation</title>
<script data-cfasync="false">
document.documentElement.dataset.mode = localStorage.getItem("mode") || "";
document.documentElement.dataset.theme = localStorage.getItem("theme") || "";
</script>
<!-- Loaded before other Sphinx assets -->
<link href="../../../_static/styles/theme.css?digest=dfe6caa3a7d634c4db9b" rel="stylesheet" />
<link href="../../../_static/styles/bootstrap.css?digest=dfe6caa3a7d634c4db9b" rel="stylesheet" />
<link href="../../../_static/styles/pydata-sphinx-theme.css?digest=dfe6caa3a7d634c4db9b" rel="stylesheet" />
<link href="../../../_static/vendor/fontawesome/6.5.2/css/all.min.css?digest=dfe6caa3a7d634c4db9b" rel="stylesheet" />
<link rel="preload" as="font" type="font/woff2" crossorigin href="../../../_static/vendor/fontawesome/6.5.2/webfonts/fa-solid-900.woff2" />
<link rel="preload" as="font" type="font/woff2" crossorigin href="../../../_static/vendor/fontawesome/6.5.2/webfonts/fa-brands-400.woff2" />
<link rel="preload" as="font" type="font/woff2" crossorigin href="../../../_static/vendor/fontawesome/6.5.2/webfonts/fa-regular-400.woff2" />
<link rel="stylesheet" type="text/css" href="../../../_static/pygments.css?v=a746c00c" />
<link rel="stylesheet" type="text/css" href="../../../_static/styles/sphinx-book-theme.css?v=a3416100" />
<link rel="stylesheet" type="text/css" href="../../../_static/copybutton.css?v=76b2166b" />
<!-- Pre-loaded scripts that we'll load fully later -->
<link rel="preload" as="script" href="../../../_static/scripts/bootstrap.js?digest=dfe6caa3a7d634c4db9b" />
<link rel="preload" as="script" href="../../../_static/scripts/pydata-sphinx-theme.js?digest=dfe6caa3a7d634c4db9b" />
<script src="../../../_static/vendor/fontawesome/6.5.2/js/all.min.js?digest=dfe6caa3a7d634c4db9b"></script>
<script src="../../../_static/documentation_options.js?v=2742c0eb"></script>
<script src="../../../_static/doctools.js?v=9a2dae69"></script>
<script src="../../../_static/sphinx_highlight.js?v=dc90522c"></script>
<script src="../../../_static/clipboard.min.js?v=a7894cd8"></script>
<script src="../../../_static/copybutton.js?v=f281be69"></script>
<script src="../../../_static/scripts/sphinx-book-theme.js?v=887ef09a"></script>
<script>DOCUMENTATION_OPTIONS.pagename = 'intro/architecture/prompt_processing/prompt_processing';</script>
<link rel="icon" href="../../../_static/favicon.ico"/>
<link rel="index" title="Index" href="../../../genindex.html" />
<link rel="search" title="Search" href="../../../search.html" />
<link rel="next" title="LLM Provider" href="../listeners/llm_provider.html" />
<link rel="prev" title="Listener" href="../listeners/listeners.html" />
<meta name="viewport" content="width=device-width, initial-scale=1"/>
<meta name="docsearch:language" content="en"/>
</head>
<body data-bs-spy="scroll" data-bs-target=".bd-toc-nav" data-offset="180" data-bs-root-margin="0px 0px -60%" data-default-mode="">
<div id="pst-skip-link" class="skip-link d-print-none"><a href="#main-content">Skip to main content</a></div>
<div id="pst-scroll-pixel-helper"></div>
<button type="button" class="btn rounded-pill" id="pst-back-to-top">
<i class="fa-solid fa-arrow-up"></i>Back to top</button>
<input type="checkbox"
class="sidebar-toggle"
id="pst-primary-sidebar-checkbox"/>
<label class="overlay overlay-primary" for="pst-primary-sidebar-checkbox"></label>
<input type="checkbox"
class="sidebar-toggle"
id="pst-secondary-sidebar-checkbox"/>
<label class="overlay overlay-secondary" for="pst-secondary-sidebar-checkbox"></label>
<div class="search-button__wrapper">
<div class="search-button__overlay"></div>
<div class="search-button__search-container">
<form class="bd-search d-flex align-items-center"
action="../../../search.html"
method="get">
<i class="fa-solid fa-magnifying-glass"></i>
<input type="search"
class="form-control"
name="q"
id="search-input"
placeholder="Search..."
aria-label="Search..."
autocomplete="off"
autocorrect="off"
autocapitalize="off"
spellcheck="false"/>
<span class="search-button__kbd-shortcut"><kbd class="kbd-shortcut__modifier">Ctrl</kbd>+<kbd>K</kbd></span>
</form></div>
</div>
<div class="pst-async-banner-revealer d-none">
<aside id="bd-header-version-warning" class="d-none d-print-none" aria-label="Version warning"></aside>
</div>
<header class="bd-header navbar navbar-expand-lg bd-navbar d-print-none">
</header>
<div class="bd-container">
<div class="bd-container__inner bd-page-width">
<div class="bd-sidebar-primary bd-sidebar">
<div class="sidebar-header-items sidebar-primary__section">
</div>
<div class="sidebar-primary-items__start sidebar-primary__section">
<div class="sidebar-primary-item">
<a class="navbar-brand logo" href="../../../root.html">
<img src="../../../_static/arch-nav-logo.png" class="logo__image only-light" alt="Arch 0.1-beta documentation - Home"/>
<script>document.write(`<img src="../../../_static/arch-nav-logo.png" class="logo__image only-dark" alt="Arch 0.1-beta documentation - Home"/>`);</script>
</a></div>
<div class="sidebar-primary-item">
<script>
document.write(`
<button class="btn search-button-field search-button__button" title="Search" aria-label="Search" data-bs-placement="bottom" data-bs-toggle="tooltip">
<i class="fa-solid fa-magnifying-glass"></i>
<span class="search-button__default-text">Search</span>
<span class="search-button__kbd-shortcut"><kbd class="kbd-shortcut__modifier">Ctrl</kbd>+<kbd class="kbd-shortcut__modifier">K</kbd></span>
</button>
`);
</script></div>
<div class="sidebar-primary-item"><nav class="bd-links bd-docs-nav" aria-label="Main">
<div class="bd-toc-item navbar-nav active">
<ul class="current nav bd-sidenav">
<li class="toctree-l1 current active has-children"><a class="reference internal" href="../../intro.html">Introduction</a><details open="open"><summary><span class="toctree-toggle" role="presentation"><i class="fa-solid fa-chevron-down"></i></span></summary><ul class="current">
<li class="toctree-l2"><a class="reference internal" href="../../what_is_arch.html">What is Arch</a></li>
<li class="toctree-l2 current active has-children"><a class="reference internal" href="../architecture.html">Technical Architecture</a><details open="open"><summary><span class="toctree-toggle" role="presentation"><i class="fa-solid fa-chevron-down"></i></span></summary><ul class="current">
<li class="toctree-l3"><a class="reference internal" href="../intro/terminology.html">Terminology</a></li>
<li class="toctree-l3"><a class="reference internal" href="../intro/threading_model.html">Threading model</a></li>
<li class="toctree-l3"><a class="reference internal" href="../listeners/listeners.html">Listener</a></li>
<li class="toctree-l3 current active"><a class="current reference internal" href="#">Prompts</a></li>
<li class="toctree-l3"><a class="reference internal" href="../listeners/llm_provider.html">LLM Provider</a></li>
<li class="toctree-l3"><a class="reference internal" href="../model_serving/model_serving.html">Model Serving</a></li>
</ul>
</details></li>
<li class="toctree-l2"><a class="reference internal" href="../../life_of_a_request.html">Life of a Request</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../getting_help.html">Getting help</a></li>
</ul>
</details></li>
<li class="toctree-l1"><a class="reference internal" href="../../../getting_started/getting_started.html">Getting Started</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../getting_started/use_cases/rag.html">Retrieval-Augmented (RAG)</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../getting_started/use_cases/function_calling.html">Agentic (Text-to-Action) Apps</a></li>
<li class="toctree-l1 has-children"><a class="reference internal" href="../../../observability/observability.html">Observability</a><details><summary><span class="toctree-toggle" role="presentation"><i class="fa-solid fa-chevron-down"></i></span></summary><ul>
<li class="toctree-l2"><a class="reference internal" href="../../../observability/tracing.html">Tracing</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../observability/stats.html">Monitoring</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../observability/access_logs.html">Access Logging</a></li>
</ul>
</details></li>
<li class="toctree-l1"><a class="reference internal" href="../../../llms/llms.html">LLMs</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../configuration_reference.html">Configuration Reference</a></li>
</ul>
</div>
</nav></div>
</div>
<div class="sidebar-primary-items__end sidebar-primary__section">
</div>
<div id="rtd-footer-container"></div>
</div>
<main id="main-content" class="bd-main" role="main">
<div class="sbt-scroll-pixel-helper"></div>
<div class="bd-content">
<div class="bd-article-container">
<div class="bd-header-article d-print-none">
<div class="header-article-items header-article__inner">
<div class="header-article-items__start">
<div class="header-article-item"><button class="sidebar-toggle primary-toggle btn btn-sm" title="Toggle primary sidebar" data-bs-placement="bottom" data-bs-toggle="tooltip">
<span class="fa-solid fa-bars"></span>
</button></div>
</div>
<div class="header-article-items__end">
<div class="header-article-item">
<div class="article-header-buttons">
<div class="dropdown dropdown-download-buttons">
<button class="btn dropdown-toggle" type="button" data-bs-toggle="dropdown" aria-expanded="false" aria-label="Download this page">
<i class="fas fa-download"></i>
</button>
<ul class="dropdown-menu">
<li><a href="../../../_sources/intro/architecture/prompt_processing/prompt_processing.rst" target="_blank"
class="btn btn-sm btn-download-source-button dropdown-item"
title="Download source file"
data-bs-placement="left" data-bs-toggle="tooltip"
>
<span class="btn__icon-container">
<i class="fas fa-file"></i>
</span>
<span class="btn__text-container">.rst</span>
</a>
</li>
<li>
<button onclick="window.print()"
class="btn btn-sm btn-download-pdf-button dropdown-item"
title="Print to PDF"
data-bs-placement="left" data-bs-toggle="tooltip"
>
<span class="btn__icon-container">
<i class="fas fa-file-pdf"></i>
</span>
<span class="btn__text-container">.pdf</span>
</button>
</li>
</ul>
</div>
<button onclick="toggleFullScreen()"
class="btn btn-sm btn-fullscreen-button"
title="Fullscreen mode"
data-bs-placement="bottom" data-bs-toggle="tooltip"
>
<span class="btn__icon-container">
<i class="fas fa-expand"></i>
</span>
</button>
<script>
document.write(`
<button class="btn btn-sm nav-link pst-navbar-icon theme-switch-button" title="light/dark" aria-label="light/dark" data-bs-placement="bottom" data-bs-toggle="tooltip">
<i class="theme-switch fa-solid fa-sun fa-lg" data-mode="light"></i>
<i class="theme-switch fa-solid fa-moon fa-lg" data-mode="dark"></i>
<i class="theme-switch fa-solid fa-circle-half-stroke fa-lg" data-mode="auto"></i>
</button>
`);
</script>
<script>
document.write(`
<button class="btn btn-sm pst-navbar-icon search-button search-button__button" title="Search" aria-label="Search" data-bs-placement="bottom" data-bs-toggle="tooltip">
<i class="fa-solid fa-magnifying-glass fa-lg"></i>
</button>
`);
</script>
<button class="sidebar-toggle secondary-toggle btn btn-sm" title="Toggle secondary sidebar" data-bs-placement="bottom" data-bs-toggle="tooltip">
<span class="fa-solid fa-list"></span>
</button>
</div></div>
</div>
</div>
</div>
<div id="jb-print-docs-body" class="onlyprint">
<h1>Prompts</h1>
<!-- Table of contents -->
<div id="print-main-content">
<div id="jb-print-toc">
<div>
<h2> Contents </h2>
</div>
<nav aria-label="Page">
<ul class="visible nav section-nav flex-column">
<li class="toc-h1 nav-item toc-entry"><a class="reference internal nav-link" href="#">Prompts</a></li>
<li class="toc-h1 nav-item toc-entry"><a class="reference internal nav-link" href="#messages">Messages</a></li>
<li class="toc-h1 nav-item toc-entry"><a class="reference internal nav-link" href="#prompt-guardrails">Prompt Guardrails</a></li>
<li class="toc-h1 nav-item toc-entry"><a class="reference internal nav-link" href="#prompt-targets">Prompt Targets</a><ul class="visible nav section-nav flex-column">
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#intent-detection-and-prompt-matching">Intent Detection and Prompt Matching:</a></li>
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#agentic-apps-via-prompt-targets">Agentic Apps via Prompt Targets</a></li>
</ul>
</li>
<li class="toc-h1 nav-item toc-entry"><a class="reference internal nav-link" href="#prompting-llms">Prompting LLMs</a><ul class="visible nav section-nav flex-column">
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#example-using-the-arch-python-sdk">Example: Using the Arch Python SDK</a></li>
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#example-using-openai-client-with-arch-as-an-egress-gateway">Example: Using OpenAI Client with Arch as an Egress Gateway</a></li>
</ul>
</li>
</ul>
</nav>
</div>
</div>
</div>
<div id="searchbox"></div>
<article class="bd-article">
<section id="prompts">
<span id="arch-overview-prompt-handling"></span><h1>Prompts<a class="headerlink" href="#prompts" title="Link to this heading">#</a></h1>
<p>Archs primary design point is to securely accept, process and handle prompts. To do that effectively,
Arch relies on Envoys HTTP <a class="reference external" href="https://www.envoyproxy.io/docs/envoy/v1.31.2/intro/arch_overview/http/http_connection_management">connection management</a>,
subsystem and its <strong>prompt handler</strong> subsystem engineered with purpose-built <a class="reference internal" href="../../../llms/llms.html#llms-in-arch"><span class="std std-ref">LLMs</span></a> to
implement critical functionality on behalf of developers so that you can stay focused on business logic.</p>
<div class="admonition note">
<p class="admonition-title">Note</p>
<p>Archs <strong>prompt handler</strong> subsystem interacts with the <strong>model</strong> subsytem through Envoys cluster manager
system to ensure robust, resilient and fault-tolerant experience in managing incoming prompts. Read more
about the <a class="reference internal" href="../model_serving/model_serving.html#arch-model-serving"><span class="std std-ref">model subsystem</span></a> and how the LLMs are hosted in Arch.</p>
</div>
</section>
<section id="messages">
<h1>Messages<a class="headerlink" href="#messages" title="Link to this heading">#</a></h1>
<p>Arch accepts messages directly from the body of the HTTP request in a format that follows the <a class="reference external" href="https://huggingface.co/docs/text-generation-inference/en/messages_api">Hugging Face Messages API</a>.
This design allows developers to pass a list of messages, where each message is represented as a dictionary
containing two key-value pairs:</p>
<blockquote>
<div><ul class="simple">
<li><p><strong>Role</strong>: Defines the role of the message sender, such as “user” or “assistant”.</p></li>
<li><p><strong>Content</strong>: Contains the actual text of the message.</p></li>
</ul>
</div></blockquote>
</section>
<section id="prompt-guardrails">
<h1>Prompt Guardrails<a class="headerlink" href="#prompt-guardrails" title="Link to this heading">#</a></h1>
<p>Arch is engineered with <a class="reference internal" href="../../../llms/llms.html#llms-in-arch"><span class="std std-ref">Arch-Guard</span></a>, an industry leading safety layer, powered by a
compact and high-performimg LLM that monitors incoming prompts to detect and reject jailbreak attempts -
ensuring that unauthorized or harmful behaviors are intercepted early in the process.</p>
<p>To add jailbreak guardrails, see example below:</p>
<div class="literal-block-wrapper docutils container" id="id1">
<div class="code-block-caption"><span class="caption-text"><a class="reference download internal" download="" href="../../../_downloads/a0b0970c8fa22d4fe861e8362965b77c/getting-started.yml"><code class="xref download docutils literal notranslate"><span class="pre">arch-getting-started.yml</span></code></a></span><a class="headerlink" href="#id1" title="Link to this code">#</a></div>
<div class="highlight-yaml notranslate"><div class="highlight"><pre><span></span><span class="linenos"> 1</span><span class="nt">version</span><span class="p">:</span><span class="w"> </span><span class="s">&quot;0.1-beta&quot;</span>
<span class="linenos"> 2</span><span class="nt">listener</span><span class="p">:</span>
<span class="linenos"> 3</span><span class="w"> </span><span class="nt">address</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">127.0.0.1 | 0.0.0.0</span>
<span class="linenos"> 4</span><span class="w"> </span><span class="nt">port_value</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">8080</span><span class="w"> </span><span class="c1">#If you configure port 443, you&#39;ll need to update the listener with tls_certificates</span>
<span class="linenos"> 5</span><span class="w"> </span><span class="nt">messages</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">tuple | hugging-face-messages-api</span>
<span class="linenos"> 6</span>
<span class="linenos"> 7</span><span class="nt">system_prompts</span><span class="p">:</span>
<span class="linenos"> 8</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">network_assistant</span>
<span class="linenos"> 9</span><span class="w"> </span><span class="nt">content</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 about the operational health of the network</span>
<span class="linenos">10</span>
<span class="linenos">11</span><span class="nt">llm_providers</span><span class="p">:</span>
<span class="linenos">12</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="s">&quot;OpenAI&quot;</span>
<span class="linenos">13</span><span class="w"> </span><span class="nt">access_key</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">$OPEN_AI_KEY</span>
<span class="linenos">14</span><span class="w"> </span><span class="nt">model</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">gpt-4o</span>
<span class="linenos">15</span><span class="w"> </span><span class="nt">default</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">true</span>
<span class="linenos">16</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="s">&quot;Mistral&quot;</span>
<span class="linenos">17</span><span class="w"> </span><span class="nt">access_key</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">$MISTRAL_KEY</span>
<span class="linenos">18</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">mixtral8-7B</span>
<span class="linenos">19</span>
<span class="linenos">20</span><span class="nt">prompt_endpoints</span><span class="p">:</span>
<span class="linenos">21</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="s">&quot;http://127.0.0.2&quot;</span>
<span class="linenos">22</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="s">&quot;http://127.0.0.1&quot;</span>
<span class="linenos">23</span>
<span class="hll"><span class="linenos">24</span><span class="nt">prompt_guards</span><span class="p">:</span>
</span><span class="hll"><span class="linenos">25</span><span class="w"> </span><span class="nt">input-guard</span><span class="p">:</span>
</span><span class="hll"><span class="linenos">26</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="c1">#jailbreak</span>
</span><span class="hll"><span class="linenos">27</span><span class="w"> </span><span class="nt">on-exception-message</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">Looks like you are curious about my abilities. But I can only</span>
</span><span class="linenos">28</span>
<span class="linenos">29</span><span class="nt">prompt_targets</span><span class="p">:</span>
<span class="linenos">30</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 class="linenos">31</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">RAG</span>
<span class="linenos">32</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">this prompt handles all information extractions scenarios</span>
<span class="linenos">33</span><span class="w"> </span><span class="nt">path</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">/agent/summary</span>
<span class="linenos">34</span>
<span class="linenos">35</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">reboot_network_device</span>
<span class="linenos">36</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 class="linenos">37</span><span class="w"> </span><span class="nt">description</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">used to help network operators with perform device operations like rebooting a device.</span>
<span class="linenos">38</span><span class="w"> </span><span class="nt">parameters</span><span class="p">:</span>
<span class="linenos">39</span><span class="nt">error_target</span><span class="p">:</span><span class="w"> </span><span class="c1">#handle errors from Bolt or upstream LLMs</span>
<span class="linenos">40</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">“error_handler”</span>
<span class="linenos">41</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">/errors</span>
</pre></div>
</div>
</div>
<div class="admonition note">
<p class="admonition-title">Note</p>
<p>As a roadmap item, Arch will expose the ability for developers to define custom guardrails via Arch-Guard-v2,
and add support for additional safety checks defined by developers and hazardous categories like, violent crimes, privacy, hate,
etc. To offer feedback on our roadmap, please visit our <a class="reference external" href="https://github.com/orgs/katanemo/projects/1">github page</a></p>
</div>
</section>
<section id="prompt-targets">
<h1>Prompt Targets<a class="headerlink" href="#prompt-targets" title="Link to this heading">#</a></h1>
<p>Once a prompt passes any configured guardrail checks, Arch processes the contents of the incoming conversation
and identifies where to forwad the conversation to via its essential <code class="docutils literal notranslate"><span class="pre">prompt_targets</span></code> primitve. Prompt targets
are endpoints that receive prompts that are processed by Arch. For example, Arch enriches incoming prompts with
metadata like knowing when a users intent has changed so that you can build faster, more accurate RAG apps.</p>
<p>Configuring <code class="docutils literal notranslate"><span class="pre">prompt_targets</span></code> is simple. See example below:</p>
<div class="literal-block-wrapper docutils container" id="id2">
<div class="code-block-caption"><span class="caption-text"><a class="reference download internal" download="" href="../../../_downloads/a0b0970c8fa22d4fe861e8362965b77c/getting-started.yml"><code class="xref download docutils literal notranslate"><span class="pre">arch-getting-started.yml</span></code></a></span><a class="headerlink" href="#id2" title="Link to this code">#</a></div>
<div class="highlight-yaml notranslate"><div class="highlight"><pre><span></span><span class="linenos"> 1</span><span class="nt">version</span><span class="p">:</span><span class="w"> </span><span class="s">&quot;0.1-beta&quot;</span>
<span class="linenos"> 2</span><span class="nt">listener</span><span class="p">:</span>
<span class="linenos"> 3</span><span class="w"> </span><span class="nt">address</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">127.0.0.1 | 0.0.0.0</span>
<span class="linenos"> 4</span><span class="w"> </span><span class="nt">port_value</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">8080</span><span class="w"> </span><span class="c1">#If you configure port 443, you&#39;ll need to update the listener with tls_certificates</span>
<span class="linenos"> 5</span><span class="w"> </span><span class="nt">messages</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">tuple | hugging-face-messages-api</span>
<span class="linenos"> 6</span>
<span class="linenos"> 7</span><span class="nt">system_prompts</span><span class="p">:</span>
<span class="linenos"> 8</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">network_assistant</span>
<span class="linenos"> 9</span><span class="w"> </span><span class="nt">content</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 about the operational health of the network</span>
<span class="linenos">10</span>
<span class="linenos">11</span><span class="nt">llm_providers</span><span class="p">:</span>
<span class="linenos">12</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="s">&quot;OpenAI&quot;</span>
<span class="linenos">13</span><span class="w"> </span><span class="nt">access_key</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">$OPEN_AI_KEY</span>
<span class="linenos">14</span><span class="w"> </span><span class="nt">model</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">gpt-4o</span>
<span class="linenos">15</span><span class="w"> </span><span class="nt">default</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">true</span>
<span class="linenos">16</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="s">&quot;Mistral&quot;</span>
<span class="linenos">17</span><span class="w"> </span><span class="nt">access_key</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">$MISTRAL_KEY</span>
<span class="linenos">18</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">mixtral8-7B</span>
<span class="linenos">19</span>
<span class="linenos">20</span><span class="nt">prompt_endpoints</span><span class="p">:</span>
<span class="linenos">21</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="s">&quot;http://127.0.0.2&quot;</span>
<span class="linenos">22</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="s">&quot;http://127.0.0.1&quot;</span>
<span class="linenos">23</span>
<span class="linenos">24</span><span class="nt">prompt_guards</span><span class="p">:</span>
<span class="linenos">25</span><span class="w"> </span><span class="nt">input-guard</span><span class="p">:</span>
<span class="linenos">26</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="c1">#jailbreak</span>
<span class="linenos">27</span><span class="w"> </span><span class="nt">on-exception-message</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">Looks like you are curious about my abilities. But I can only</span>
<span class="linenos">28</span>
<span class="hll"><span class="linenos">29</span><span class="nt">prompt_targets</span><span class="p">:</span>
</span><span class="hll"><span class="linenos">30</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 class="hll"><span class="linenos">31</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">RAG</span>
</span><span class="hll"><span class="linenos">32</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">this prompt handles all information extractions scenarios</span>
</span><span class="hll"><span class="linenos">33</span><span class="w"> </span><span class="nt">path</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">/agent/summary</span>
</span><span class="hll"><span class="linenos">34</span>
</span><span class="hll"><span class="linenos">35</span><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">reboot_network_device</span>
</span><span class="hll"><span class="linenos">36</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 class="hll"><span class="linenos">37</span><span class="w"> </span><span class="nt">description</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">used to help network operators with perform device operations like rebooting a device.</span>
</span><span class="hll"><span class="linenos">38</span><span class="w"> </span><span class="nt">parameters</span><span class="p">:</span>
</span><span class="linenos">39</span><span class="nt">error_target</span><span class="p">:</span><span class="w"> </span><span class="c1">#handle errors from Bolt or upstream LLMs</span>
<span class="linenos">40</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">“error_handler”</span>
<span class="linenos">41</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">/errors</span>
</pre></div>
</div>
</div>
<section id="intent-detection-and-prompt-matching">
<h2>Intent Detection and Prompt Matching:<a class="headerlink" href="#intent-detection-and-prompt-matching" title="Link to this heading">#</a></h2>
<p>Arch uses fast Natural Language Inference (NLI) and embedding approaches to first detect the intent of each
incoming prompt. This intent detection phase analyzes the prompts content and matches it against predefined
prompt targets, ensuring that each prompt is forwarded to the most appropriate endpoint. Archs intent
detection framework considers both the name and description of each prompt target, and uses a composite matching
score between an NLI and cosine similarity to enchance accuracy in forwarding decisions.</p>
<ul class="simple">
<li><p><strong>Embeddings</strong>: By embedding the prompt and comparing it to known target vectors, Arch effectively identifies
the closest match, ensuring that the prompt is handled by the correct downstream service.</p></li>
<li><p><strong>NLI</strong>: NLI techniques further refine the matching process by evaluating the semantic alignment between the
prompt and potential targets.</p></li>
</ul>
</section>
<section id="agentic-apps-via-prompt-targets">
<h2>Agentic Apps via Prompt Targets<a class="headerlink" href="#agentic-apps-via-prompt-targets" title="Link to this heading">#</a></h2>
<p>To support agentic apps, like scheduling travel plans or sharing comments on a document - via prompts, Arch uses
its function calling abilities to extract critical information from the incoming prompt (or a set of prompts)
needed by a downstream backend API or function call before calling it directly. For more details on how you can
build agentic applications using Arch, see our full guide <a class="reference internal" href="../../../getting_started/use_cases/function_calling.html#arch-function-calling-agentic-guide"><span class="std std-ref">here</span></a>:</p>
<div class="admonition note">
<p class="admonition-title">Note</p>
<p>Arch <a class="reference internal" href="../../../llms/llms.html#llms-in-arch"><span class="std std-ref">Arch-FC</span></a> is the dedicated agentic model engineered in Arch to extract information from
a (set of) prompts and executes necessary backend API calls. This allows for efficient handling of agentic tasks,
such as scheduling data retrieval, by dynamically interacting with backend services. Arch-FC is a flagship 1.3
billion parameter model that matches performance with frontier models like Claude Sonnet 3.5 ang GPT-4, while
being 100x cheaper ($0.05M/token hosted) and 10x faster (p50 latencies of 200ms).</p>
</div>
</section>
</section>
<section id="prompting-llms">
<h1>Prompting LLMs<a class="headerlink" href="#prompting-llms" title="Link to this heading">#</a></h1>
<p>Arch is a single piece of software that is designed to manage both ingress and egress prompt traffic, drawing its
distributed proxy nature from the robust <a class="reference external" href="https://envoyproxy.io">Envoy</a>. This makes it extremely efficient and capable
of handling upstream connections to LLMs. If your application is originating code to an API-based LLM, simply use
Archs Python or JavaScript client SDK to send traffic to the desired LLM of choice. By sending traffic through Arch,
you can propagate traces, manage and monitor traffic, apply rate limits, and utilize a large set of traffic management
capabilities in a central place.</p>
<div class="admonition attention">
<p class="admonition-title">Attention</p>
<p>When you start Arch, it automatically creates a listener port for egress calls to upstream LLMs. This is based on the
<code class="docutils literal notranslate"><span class="pre">llm_providers</span></code> configuration section in the <code class="docutils literal notranslate"><span class="pre">prompt_config.yml</span></code> file. Arch binds itself to a local address such as
127.0.0.1:9000/v1 or a DNS-based address like arch.local:9000/v1 for outgoing traffic.</p>
</div>
<section id="example-using-the-arch-python-sdk">
<h2>Example: Using the Arch Python SDK<a class="headerlink" href="#example-using-the-arch-python-sdk" title="Link to this heading">#</a></h2>
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="kn">from</span> <span class="nn">arch_client</span> <span class="kn">import</span> <span class="n">ArchClient</span>
<span class="c1"># Initialize the Arch client</span>
<span class="n">client</span> <span class="o">=</span> <span class="n">ArchClient</span><span class="p">(</span><span class="n">base_url</span><span class="o">=</span><span class="s2">&quot;http://127.0.0.1:9000/v1&quot;</span><span class="p">)</span>
<span class="c1"># Define your LLM provider and prompt</span>
<span class="n">model_id</span> <span class="o">=</span> <span class="s2">&quot;openai&quot;</span>
<span class="n">prompt</span> <span class="o">=</span> <span class="s2">&quot;What is the capital of France?&quot;</span>
<span class="c1"># Send the prompt to the LLM through Arch</span>
<span class="n">response</span> <span class="o">=</span> <span class="n">client</span><span class="o">.</span><span class="n">completions</span><span class="o">.</span><span class="n">create</span><span class="p">(</span><span class="n">llm_provider</span><span class="o">=</span><span class="n">llm_provider</span><span class="p">,</span> <span class="n">prompt</span><span class="o">=</span><span class="n">prompt</span><span class="p">)</span>
<span class="c1"># Print the response</span>
<span class="nb">print</span><span class="p">(</span><span class="s2">&quot;LLM Response:&quot;</span><span class="p">,</span> <span class="n">response</span><span class="p">)</span>
</pre></div>
</div>
</section>
<section id="example-using-openai-client-with-arch-as-an-egress-gateway">
<h2>Example: Using OpenAI Client with Arch as an Egress Gateway<a class="headerlink" href="#example-using-openai-client-with-arch-as-an-egress-gateway" title="Link to this heading">#</a></h2>
<div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="kn">import</span> <span class="nn">openai</span>
<span class="c1"># Set the OpenAI API base URL to the Arch gateway endpoint</span>
<span class="n">openai</span><span class="o">.</span><span class="n">api_base</span> <span class="o">=</span> <span class="s2">&quot;http://127.0.0.1:9000/v1&quot;</span>
<span class="c1"># No need to set openai.api_key since it&#39;s configured in Arch&#39;s gateway</span>
<span class="c1"># Use the OpenAI client as usual</span>
<span class="n">response</span> <span class="o">=</span> <span class="n">openai</span><span class="o">.</span><span class="n">Completion</span><span class="o">.</span><span class="n">create</span><span class="p">(</span>
<span class="n">model</span><span class="o">=</span><span class="s2">&quot;text-davinci-003&quot;</span><span class="p">,</span>
<span class="n">prompt</span><span class="o">=</span><span class="s2">&quot;What is the capital of France?&quot;</span>
<span class="p">)</span>
<span class="nb">print</span><span class="p">(</span><span class="s2">&quot;OpenAI Response:&quot;</span><span class="p">,</span> <span class="n">response</span><span class="o">.</span><span class="n">choices</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span><span class="o">.</span><span class="n">text</span><span class="o">.</span><span class="n">strip</span><span class="p">())</span>
</pre></div>
</div>
<p>In these examples:</p>
<blockquote>
<div><p>The ArchClient is used to send traffic directly through the Arch egress proxy to the LLM of your choice, such as OpenAI.
The OpenAI client is configured to route traffic via Arch by setting the proxy to 127.0.0.1:9000, assuming Arch is
running locally and bound to that address and port.</p>
</div></blockquote>
<p>This setup allows you to take advantage of Archs advanced traffic management features while interacting with LLM APIs like OpenAI.</p>
</section>
</section>
</article>
<footer class="prev-next-footer d-print-none">
<div class="prev-next-area">
<a class="left-prev"
href="../listeners/listeners.html"
title="previous page">
<i class="fa-solid fa-angle-left"></i>
<div class="prev-next-info">
<p class="prev-next-subtitle">previous</p>
<p class="prev-next-title">Listener</p>
</div>
</a>
<a class="right-next"
href="../listeners/llm_provider.html"
title="next page">
<div class="prev-next-info">
<p class="prev-next-subtitle">next</p>
<p class="prev-next-title">LLM Provider</p>
</div>
<i class="fa-solid fa-angle-right"></i>
</a>
</div>
</footer>
</div>
<div class="bd-sidebar-secondary bd-toc"><div class="sidebar-secondary-items sidebar-secondary__inner">
<div class="sidebar-secondary-item">
<div class="page-toc tocsection onthispage">
<i class="fa-solid fa-list"></i> Contents
</div>
<nav class="bd-toc-nav page-toc">
<ul class="visible nav section-nav flex-column">
<li class="toc-h1 nav-item toc-entry"><a class="reference internal nav-link" href="#">Prompts</a></li>
<li class="toc-h1 nav-item toc-entry"><a class="reference internal nav-link" href="#messages">Messages</a></li>
<li class="toc-h1 nav-item toc-entry"><a class="reference internal nav-link" href="#prompt-guardrails">Prompt Guardrails</a></li>
<li class="toc-h1 nav-item toc-entry"><a class="reference internal nav-link" href="#prompt-targets">Prompt Targets</a><ul class="visible nav section-nav flex-column">
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#intent-detection-and-prompt-matching">Intent Detection and Prompt Matching:</a></li>
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#agentic-apps-via-prompt-targets">Agentic Apps via Prompt Targets</a></li>
</ul>
</li>
<li class="toc-h1 nav-item toc-entry"><a class="reference internal nav-link" href="#prompting-llms">Prompting LLMs</a><ul class="visible nav section-nav flex-column">
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#example-using-the-arch-python-sdk">Example: Using the Arch Python SDK</a></li>
<li class="toc-h2 nav-item toc-entry"><a class="reference internal nav-link" href="#example-using-openai-client-with-arch-as-an-egress-gateway">Example: Using OpenAI Client with Arch as an Egress Gateway</a></li>
</ul>
</li>
</ul>
</nav></div>
</div></div>
</div>
<footer class="bd-footer-content">
<div class="bd-footer-content__inner container">
<div class="footer-item">
<p class="component-author">
By Katanemo Labs, Inc
</p>
</div>
<div class="footer-item">
<p class="copyright">
© Copyright 2024, Katanemo Labs, Inc.
<br/>
</p>
</div>
<div class="footer-item">
</div>
<div class="footer-item">
</div>
</div>
</footer>
</main>
</div>
</div>
<!-- Scripts loaded after <body> so the DOM is not blocked -->
<script src="../../../_static/scripts/bootstrap.js?digest=dfe6caa3a7d634c4db9b"></script>
<script src="../../../_static/scripts/pydata-sphinx-theme.js?digest=dfe6caa3a7d634c4db9b"></script>
<footer class="bd-footer">
</footer>
</body>
</html>