Mathis/llamactl
1
0
Fork 0
mirror of https://github.com/lordmathis/llamactl.git synced 2025-11-05 16:44:22 +00:00
Code Issues Packages Projects Releases Wiki Activity
Files
dc21ae7cf490a44af35508f2e779e4e17e35b1c4
llamactl/v0.11.2/quick-start/index.html

1079 lines
53 KiB
HTML
Raw Blame History

<!doctype html>
<html lang="en" class="no-js">
<head>
<meta charset="utf-8">
<meta name="viewport" content="width=device-width,initial-scale=1">
<meta name="description" content="User documentation for Llamatl - A management tool for Llama.cpp instances">
<meta name="author" content="Llamatl Team">
<link rel="canonical" href="https://llamactl.org/v0.11.2/quick-start/">
<link rel="prev" href="../installation/">
<link rel="next" href="../configuration/">
<link rel="icon" href="../assets/images/favicon.png">
<meta name="generator" content="mkdocs-1.6.1, mkdocs-material-9.6.22">
<title>Quick Start - Llamatl Documentation</title>
<link rel="stylesheet" href="../assets/stylesheets/main.84d31ad4.min.css">
<link rel="stylesheet" href="../assets/stylesheets/palette.06af60db.min.css">
<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin>
<link rel="stylesheet" href="https://fonts.googleapis.com/css?family=Roboto:300,300i,400,400i,700,700i%7CRoboto+Mono:400,400i,700,700i&display=fallback">
<style>:root{--md-text-font:"Roboto";--md-code-font:"Roboto Mono"}</style>
<link rel="stylesheet" href="../css/css-v1.1.3.css">
<script>__md_scope=new URL("..",location),__md_hash=e=>[...e].reduce(((e,_)=>(e<<5)-e+_.charCodeAt(0)),0),__md_get=(e,_=localStorage,t=__md_scope)=>JSON.parse(_.getItem(t.pathname+"."+e)),__md_set=(e,_,t=localStorage,a=__md_scope)=>{try{t.setItem(a.pathname+"."+e,JSON.stringify(_))}catch(e){}}</script>
</head>
<body dir="ltr" data-md-color-scheme="default" data-md-color-primary="indigo" data-md-color-accent="indigo">
<input class="md-toggle" data-md-toggle="drawer" type="checkbox" id="__drawer" autocomplete="off">
<input class="md-toggle" data-md-toggle="search" type="checkbox" id="__search" autocomplete="off">
<label class="md-overlay" for="__drawer"></label>
<div data-md-component="skip">
<a href="#quick-start" class="md-skip">
Skip to content
</a>
</div>
<div data-md-component="announce">
</div>
<div data-md-color-scheme="default" data-md-component="outdated" hidden>
</div>
<header class="md-header md-header--shadow md-header--lifted" data-md-component="header">
<nav class="md-header__inner md-grid" aria-label="Header">
<a href=".." title="Llamatl Documentation" class="md-header__button md-logo" aria-label="Llamatl Documentation" data-md-component="logo">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M12 8a3 3 0 0 0 3-3 3 3 0 0 0-3-3 3 3 0 0 0-3 3 3 3 0 0 0 3 3m0 3.54C9.64 9.35 6.5 8 3 8v11c3.5 0 6.64 1.35 9 3.54 2.36-2.19 5.5-3.54 9-3.54V8c-3.5 0-6.64 1.35-9 3.54"/></svg>
</a>
<label class="md-header__button md-icon" for="__drawer">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M3 6h18v2H3zm0 5h18v2H3zm0 5h18v2H3z"/></svg>
</label>
<div class="md-header__title" data-md-component="header-title">
<div class="md-header__ellipsis">
<div class="md-header__topic">
<span class="md-ellipsis">
Llamatl Documentation
</span>
</div>
<div class="md-header__topic" data-md-component="header-topic">
<span class="md-ellipsis">
Quick Start
</span>
</div>
</div>
</div>
<form class="md-header__option" data-md-component="palette">
<input class="md-option" data-md-color-media="" data-md-color-scheme="default" data-md-color-primary="indigo" data-md-color-accent="indigo" aria-label="Switch to dark mode" type="radio" name="__palette" id="__palette_0">
<label class="md-header__button md-icon" title="Switch to dark mode" for="__palette_1" hidden>
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M12 8a4 4 0 0 0-4 4 4 4 0 0 0 4 4 4 4 0 0 0 4-4 4 4 0 0 0-4-4m0 10a6 6 0 0 1-6-6 6 6 0 0 1 6-6 6 6 0 0 1 6 6 6 6 0 0 1-6 6m8-9.31V4h-4.69L12 .69 8.69 4H4v4.69L.69 12 4 15.31V20h4.69L12 23.31 15.31 20H20v-4.69L23.31 12z"/></svg>
</label>
<input class="md-option" data-md-color-media="" data-md-color-scheme="slate" data-md-color-primary="indigo" data-md-color-accent="indigo" aria-label="Switch to light mode" type="radio" name="__palette" id="__palette_1">
<label class="md-header__button md-icon" title="Switch to light mode" for="__palette_0" hidden>
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M12 18c-.89 0-1.74-.2-2.5-.55C11.56 16.5 13 14.42 13 12s-1.44-4.5-3.5-5.45C10.26 6.2 11.11 6 12 6a6 6 0 0 1 6 6 6 6 0 0 1-6 6m8-9.31V4h-4.69L12 .69 8.69 4H4v4.69L.69 12 4 15.31V20h4.69L12 23.31 15.31 20H20v-4.69L23.31 12z"/></svg>
</label>
</form>
<script>var palette=__md_get("__palette");if(palette&&palette.color){if("(prefers-color-scheme)"===palette.color.media){var media=matchMedia("(prefers-color-scheme: light)"),input=document.querySelector(media.matches?"[data-md-color-media='(prefers-color-scheme: light)']":"[data-md-color-media='(prefers-color-scheme: dark)']");palette.color.media=input.getAttribute("data-md-color-media"),palette.color.scheme=input.getAttribute("data-md-color-scheme"),palette.color.primary=input.getAttribute("data-md-color-primary"),palette.color.accent=input.getAttribute("data-md-color-accent")}for(var[key,value]of Object.entries(palette.color))document.body.setAttribute("data-md-color-"+key,value)}</script>
<label class="md-header__button md-icon" for="__search">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M9.5 3A6.5 6.5 0 0 1 16 9.5c0 1.61-.59 3.09-1.56 4.23l.27.27h.79l5 5-1.5 1.5-5-5v-.79l-.27-.27A6.52 6.52 0 0 1 9.5 16 6.5 6.5 0 0 1 3 9.5 6.5 6.5 0 0 1 9.5 3m0 2C7 5 5 7 5 9.5S7 14 9.5 14 14 12 14 9.5 12 5 9.5 5"/></svg>
</label>
<div class="md-search" data-md-component="search" role="dialog">
<label class="md-search__overlay" for="__search"></label>
<div class="md-search__inner" role="search">
<form class="md-search__form" name="search">
<input type="text" class="md-search__input" name="query" aria-label="Search" placeholder="Search" autocapitalize="off" autocorrect="off" autocomplete="off" spellcheck="false" data-md-component="search-query" required>
<label class="md-search__icon md-icon" for="__search">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M9.5 3A6.5 6.5 0 0 1 16 9.5c0 1.61-.59 3.09-1.56 4.23l.27.27h.79l5 5-1.5 1.5-5-5v-.79l-.27-.27A6.52 6.52 0 0 1 9.5 16 6.5 6.5 0 0 1 3 9.5 6.5 6.5 0 0 1 9.5 3m0 2C7 5 5 7 5 9.5S7 14 9.5 14 14 12 14 9.5 12 5 9.5 5"/></svg>
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M20 11v2H8l5.5 5.5-1.42 1.42L4.16 12l7.92-7.92L13.5 5.5 8 11z"/></svg>
</label>
<nav class="md-search__options" aria-label="Search">
<a href="javascript:void(0)" class="md-search__icon md-icon" title="Share" aria-label="Share" data-clipboard data-clipboard-text="" data-md-component="search-share" tabindex="-1">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M18 16.08c-.76 0-1.44.3-1.96.77L8.91 12.7c.05-.23.09-.46.09-.7s-.04-.47-.09-.7l7.05-4.11c.54.5 1.25.81 2.04.81a3 3 0 0 0 3-3 3 3 0 0 0-3-3 3 3 0 0 0-3 3c0 .24.04.47.09.7L8.04 9.81C7.5 9.31 6.79 9 6 9a3 3 0 0 0-3 3 3 3 0 0 0 3 3c.79 0 1.5-.31 2.04-.81l7.12 4.15c-.05.21-.08.43-.08.66 0 1.61 1.31 2.91 2.92 2.91s2.92-1.3 2.92-2.91A2.92 2.92 0 0 0 18 16.08"/></svg>
</a>
<button type="reset" class="md-search__icon md-icon" title="Clear" aria-label="Clear" tabindex="-1">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M19 6.41 17.59 5 12 10.59 6.41 5 5 6.41 10.59 12 5 17.59 6.41 19 12 13.41 17.59 19 19 17.59 13.41 12z"/></svg>
</button>
</nav>
</form>
<div class="md-search__output">
<div class="md-search__scrollwrap" tabindex="0" data-md-scrollfix>
<div class="md-search-result" data-md-component="search-result">
<div class="md-search-result__meta">
Initializing search
</div>
<ol class="md-search-result__list" role="presentation"></ol>
</div>
</div>
</div>
</div>
</div>
<div class="md-header__source">
<a href="https://github.com/lordmathis/llamactl" title="Go to repository" class="md-source" data-md-component="source">
<div class="md-source__icon md-icon">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 448 512"><!--! Font Awesome Free 7.1.0 by @fontawesome - https://fontawesome.com License - https://fontawesome.com/license/free (Icons: CC BY 4.0, Fonts: SIL OFL 1.1, Code: MIT License) Copyright 2025 Fonticons, Inc.--><path d="M439.6 236.1 244 40.5c-5.4-5.5-12.8-8.5-20.4-8.5s-15 3-20.4 8.4L162.5 81l51.5 51.5c27.1-9.1 52.7 16.8 43.4 43.7l49.7 49.7c34.2-11.8 61.2 31 35.5 56.7-26.5 26.5-70.2-2.9-56-37.3L240.3 199v121.9c25.3 12.5 22.3 41.8 9.1 55-6.4 6.4-15.2 10.1-24.3 10.1s-17.8-3.6-24.3-10.1c-17.6-17.6-11.1-46.9 11.2-56v-123c-20.8-8.5-24.6-30.7-18.6-45L142.6 101 8.5 235.1C3 240.6 0 247.9 0 255.5s3 15 8.5 20.4l195.6 195.7c5.4 5.4 12.7 8.4 20.4 8.4s15-3 20.4-8.4l194.7-194.7c5.4-5.4 8.4-12.8 8.4-20.4s-3-15-8.4-20.4"/></svg>
</div>
<div class="md-source__repository">
lordmathis/llamactl
</div>
</a>
</div>
</nav>
<nav class="md-tabs" aria-label="Tabs" data-md-component="tabs">
<div class="md-grid">
<ul class="md-tabs__list">
<li class="md-tabs__item">
<a href=".." class="md-tabs__link">
Home
</a>
</li>
<li class="md-tabs__item">
<a href="../installation/" class="md-tabs__link">
Installation
</a>
</li>
<li class="md-tabs__item md-tabs__item--active">
<a href="./" class="md-tabs__link">
Quick Start
</a>
</li>
<li class="md-tabs__item">
<a href="../configuration/" class="md-tabs__link">
Configuration
</a>
</li>
<li class="md-tabs__item">
<a href="../managing-instances/" class="md-tabs__link">
Managing Instances
</a>
</li>
<li class="md-tabs__item">
<a href="../api-reference/" class="md-tabs__link">
API Reference
</a>
</li>
<li class="md-tabs__item">
<a href="../troubleshooting/" class="md-tabs__link">
Troubleshooting
</a>
</li>
</ul>
</div>
</nav>
</header>
<div class="md-container" data-md-component="container">
<main class="md-main" data-md-component="main">
<div class="md-main__inner md-grid">
<div class="md-sidebar md-sidebar--primary" data-md-component="sidebar" data-md-type="navigation" >
<div class="md-sidebar__scrollwrap">
<div class="md-sidebar__inner">
<nav class="md-nav md-nav--primary md-nav--lifted md-nav--integrated" aria-label="Navigation" data-md-level="0">
<label class="md-nav__title" for="__drawer">
<a href=".." title="Llamatl Documentation" class="md-nav__button md-logo" aria-label="Llamatl Documentation" data-md-component="logo">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M12 8a3 3 0 0 0 3-3 3 3 0 0 0-3-3 3 3 0 0 0-3 3 3 3 0 0 0 3 3m0 3.54C9.64 9.35 6.5 8 3 8v11c3.5 0 6.64 1.35 9 3.54 2.36-2.19 5.5-3.54 9-3.54V8c-3.5 0-6.64 1.35-9 3.54"/></svg>
</a>
Llamatl Documentation
</label>
<div class="md-nav__source">
<a href="https://github.com/lordmathis/llamactl" title="Go to repository" class="md-source" data-md-component="source">
<div class="md-source__icon md-icon">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 448 512"><!--! Font Awesome Free 7.1.0 by @fontawesome - https://fontawesome.com License - https://fontawesome.com/license/free (Icons: CC BY 4.0, Fonts: SIL OFL 1.1, Code: MIT License) Copyright 2025 Fonticons, Inc.--><path d="M439.6 236.1 244 40.5c-5.4-5.5-12.8-8.5-20.4-8.5s-15 3-20.4 8.4L162.5 81l51.5 51.5c27.1-9.1 52.7 16.8 43.4 43.7l49.7 49.7c34.2-11.8 61.2 31 35.5 56.7-26.5 26.5-70.2-2.9-56-37.3L240.3 199v121.9c25.3 12.5 22.3 41.8 9.1 55-6.4 6.4-15.2 10.1-24.3 10.1s-17.8-3.6-24.3-10.1c-17.6-17.6-11.1-46.9 11.2-56v-123c-20.8-8.5-24.6-30.7-18.6-45L142.6 101 8.5 235.1C3 240.6 0 247.9 0 255.5s3 15 8.5 20.4l195.6 195.7c5.4 5.4 12.7 8.4 20.4 8.4s15-3 20.4-8.4l194.7-194.7c5.4-5.4 8.4-12.8 8.4-20.4s-3-15-8.4-20.4"/></svg>
</div>
<div class="md-source__repository">
lordmathis/llamactl
</div>
</a>
</div>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href=".." class="md-nav__link">
<span class="md-ellipsis">
Home
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../installation/" class="md-nav__link">
<span class="md-ellipsis">
Installation
</span>
</a>
</li>
<li class="md-nav__item md-nav__item--active">
<input class="md-nav__toggle md-toggle" type="checkbox" id="__toc">
<label class="md-nav__link md-nav__link--active" for="__toc">
<span class="md-ellipsis">
Quick Start
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<a href="./" class="md-nav__link md-nav__link--active">
<span class="md-ellipsis">
Quick Start
</span>
</a>
<nav class="md-nav md-nav--secondary" aria-label="Table of contents">
<label class="md-nav__title" for="__toc">
<span class="md-nav__icon md-icon"></span>
Table of contents
</label>
<ul class="md-nav__list" data-md-component="toc" data-md-scrollfix>
<li class="md-nav__item">
<a href="#core-concepts" class="md-nav__link">
<span class="md-ellipsis">
Core Concepts
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#authentication" class="md-nav__link">
<span class="md-ellipsis">
Authentication
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#start-llamactl" class="md-nav__link">
<span class="md-ellipsis">
Start Llamactl
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#access-the-web-ui" class="md-nav__link">
<span class="md-ellipsis">
Access the Web UI
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#create-your-first-instance" class="md-nav__link">
<span class="md-ellipsis">
Create Your First Instance
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#start-your-instance" class="md-nav__link">
<span class="md-ellipsis">
Start Your Instance
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#example-configurations" class="md-nav__link">
<span class="md-ellipsis">
Example Configurations
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#docker-support" class="md-nav__link">
<span class="md-ellipsis">
Docker Support
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#using-the-api" class="md-nav__link">
<span class="md-ellipsis">
Using the API
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#openai-compatible-api" class="md-nav__link">
<span class="md-ellipsis">
OpenAI Compatible API
</span>
</a>
<nav class="md-nav" aria-label="OpenAI Compatible API">
<ul class="md-nav__list">
<li class="md-nav__item">
<a href="#chat-completions" class="md-nav__link">
<span class="md-ellipsis">
Chat Completions
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#using-with-python-openai-client" class="md-nav__link">
<span class="md-ellipsis">
Using with Python OpenAI Client
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#list-available-models" class="md-nav__link">
<span class="md-ellipsis">
List Available Models
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="#next-steps" class="md-nav__link">
<span class="md-ellipsis">
Next Steps
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="../configuration/" class="md-nav__link">
<span class="md-ellipsis">
Configuration
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../managing-instances/" class="md-nav__link">
<span class="md-ellipsis">
Managing Instances
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../api-reference/" class="md-nav__link">
<span class="md-ellipsis">
API Reference
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../troubleshooting/" class="md-nav__link">
<span class="md-ellipsis">
Troubleshooting
</span>
</a>
</li>
</ul>
</nav>
</div>
</div>
</div>
<div class="md-content" data-md-component="content">
<article class="md-content__inner md-typeset">
<h1 id="quick-start">Quick Start<a class="headerlink" href="#quick-start" title="Permanent link">&para;</a></h1>
<p>This guide will help you get Llamactl up and running in just a few minutes. </p>
<p><strong>Before you begin:</strong> Ensure you have at least one backend installed (llama.cpp, MLX, or vLLM). See the <a href="../installation/#prerequisites">Installation Guide</a> for backend setup. </p>
<h2 id="core-concepts">Core Concepts<a class="headerlink" href="#core-concepts" title="Permanent link">&para;</a></h2>
<p>Before you start, let's clarify a few key terms: </p>
<ul>
<li><strong>Instance</strong>: A running backend server that serves a specific model. Each instance has a unique name and runs independently. </li>
<li><strong>Backend</strong>: The inference engine that actually runs the model (llama.cpp, MLX, or vLLM). You need at least one backend installed before creating instances. </li>
<li><strong>Node</strong>: In multi-machine setups, a node represents one machine. Most users will just use the default "main" node for single-machine deployments. </li>
<li><strong>Proxy Architecture</strong>: Llamactl acts as a proxy in front of your instances. You make requests to llamactl (e.g., <code>http://localhost:8080/v1/chat/completions</code>), and it routes them to the appropriate backend instance. This means you don't need to track individual instance ports or endpoints. </li>
</ul>
<h2 id="authentication">Authentication<a class="headerlink" href="#authentication" title="Permanent link">&para;</a></h2>
<p>Llamactl uses two types of API keys: </p>
<ul>
<li><strong>Management API Key</strong>: Used to authenticate with the Llamactl management API (creating, starting, stopping instances). </li>
<li><strong>Inference API Key</strong>: Used to authenticate requests to the OpenAI-compatible endpoints (<code>/v1/chat/completions</code>, <code>/v1/completions</code>, etc.). </li>
</ul>
<p>By default, authentication is required. If you don't configure these keys in your configuration file, llamactl will auto-generate them and print them to the terminal on startup. You can also configure custom keys or disable authentication entirely in the <a href="../configuration/">Configuration</a> guide. </p>
<h2 id="start-llamactl">Start Llamactl<a class="headerlink" href="#start-llamactl" title="Permanent link">&para;</a></h2>
<p>Start the Llamactl server: </p>
<div class="highlight"><pre><span></span><code><a id="__codelineno-0-1" name="__codelineno-0-1" href="#__codelineno-0-1"></a>llamactl
</code></pre></div>
<div class="highlight"><pre><span></span><code><a id="__codelineno-1-1" name="__codelineno-1-1" href="#__codelineno-1-1"></a>━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
<a id="__codelineno-1-2" name="__codelineno-1-2" href="#__codelineno-1-2"></a>⚠️ MANAGEMENT AUTHENTICATION REQUIRED
<a id="__codelineno-1-3" name="__codelineno-1-3" href="#__codelineno-1-3"></a>━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
<a id="__codelineno-1-4" name="__codelineno-1-4" href="#__codelineno-1-4"></a>🔑 Generated Management API Key:
<a id="__codelineno-1-5" name="__codelineno-1-5" href="#__codelineno-1-5"></a>
<a id="__codelineno-1-6" name="__codelineno-1-6" href="#__codelineno-1-6"></a> sk-management-...
<a id="__codelineno-1-7" name="__codelineno-1-7" href="#__codelineno-1-7"></a>
<a id="__codelineno-1-8" name="__codelineno-1-8" href="#__codelineno-1-8"></a>━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
<a id="__codelineno-1-9" name="__codelineno-1-9" href="#__codelineno-1-9"></a>⚠️ INFERENCE AUTHENTICATION REQUIRED
<a id="__codelineno-1-10" name="__codelineno-1-10" href="#__codelineno-1-10"></a>━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
<a id="__codelineno-1-11" name="__codelineno-1-11" href="#__codelineno-1-11"></a>🔑 Generated Inference API Key:
<a id="__codelineno-1-12" name="__codelineno-1-12" href="#__codelineno-1-12"></a>
<a id="__codelineno-1-13" name="__codelineno-1-13" href="#__codelineno-1-13"></a> sk-inference-...
<a id="__codelineno-1-14" name="__codelineno-1-14" href="#__codelineno-1-14"></a>
<a id="__codelineno-1-15" name="__codelineno-1-15" href="#__codelineno-1-15"></a>━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
<a id="__codelineno-1-16" name="__codelineno-1-16" href="#__codelineno-1-16"></a>⚠️ IMPORTANT
<a id="__codelineno-1-17" name="__codelineno-1-17" href="#__codelineno-1-17"></a>━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
<a id="__codelineno-1-18" name="__codelineno-1-18" href="#__codelineno-1-18"></a>• These keys are auto-generated and will change on restart
<a id="__codelineno-1-19" name="__codelineno-1-19" href="#__codelineno-1-19"></a>• For production, add explicit keys to your configuration
<a id="__codelineno-1-20" name="__codelineno-1-20" href="#__codelineno-1-20"></a>• Copy these keys before they disappear from the terminal
<a id="__codelineno-1-21" name="__codelineno-1-21" href="#__codelineno-1-21"></a>━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
<a id="__codelineno-1-22" name="__codelineno-1-22" href="#__codelineno-1-22"></a>Llamactl server listening on 0.0.0.0:8080
</code></pre></div>
<p>Copy the <strong>Management</strong> and <strong>Inference</strong> API Keys from the terminal - you'll need them to access the web UI and make inference requests. </p>
<p>By default, Llamactl will start on <code>http://localhost:8080</code>. </p>
<h2 id="access-the-web-ui">Access the Web UI<a class="headerlink" href="#access-the-web-ui" title="Permanent link">&para;</a></h2>
<p>Open your web browser and navigate to: </p>
<div class="highlight"><pre><span></span><code><a id="__codelineno-2-1" name="__codelineno-2-1" href="#__codelineno-2-1"></a>http://localhost:8080
</code></pre></div>
<p>Login with the management API key from the terminal output. </p>
<p>You should see the Llamactl web interface. </p>
<h2 id="create-your-first-instance">Create Your First Instance<a class="headerlink" href="#create-your-first-instance" title="Permanent link">&para;</a></h2>
<ol>
<li>Click the "Add Instance" button </li>
<li>
<p>Fill in the instance configuration: </p>
<ul>
<li><strong>Name</strong>: Give your instance a descriptive name </li>
<li><strong>Node</strong>: Select which node to deploy the instance to (defaults to "main" for single-node setups) </li>
<li><strong>Backend Type</strong>: Choose from llama.cpp, MLX, or vLLM </li>
<li><strong>Model</strong>: Model path or huggingface repo </li>
<li><strong>Additional Options</strong>: Backend-specific parameters </li>
</ul>
<div class="admonition tip">
<p class="admonition-title">Auto-Assignment</p>
<p>Llamactl automatically assigns ports from the configured port range (default: 8000-9000) and generates API keys if authentication is enabled. You typically don't need to manually specify these values. </p>
</div>
<div class="admonition note">
<p class="admonition-title">Remote Node Deployment</p>
<p>If you have configured remote nodes in your configuration file, you can select which node to deploy the instance to. This allows you to distribute instances across multiple machines. See the <a href="../configuration/#remote-node-configuration">Configuration</a> guide for details on setting up remote nodes. </p>
</div>
</li>
<li>
<p>Click "Create Instance" </p>
</li>
</ol>
<h2 id="start-your-instance">Start Your Instance<a class="headerlink" href="#start-your-instance" title="Permanent link">&para;</a></h2>
<p>Once created, you can: </p>
<ul>
<li><strong>Start</strong> the instance by clicking the start button </li>
<li><strong>Monitor</strong> its status in real-time </li>
<li><strong>View logs</strong> by clicking the logs button </li>
<li><strong>Stop</strong> the instance when needed </li>
</ul>
<h2 id="example-configurations">Example Configurations<a class="headerlink" href="#example-configurations" title="Permanent link">&para;</a></h2>
<p>Here are basic example configurations for each backend: </p>
<p><strong>llama.cpp backend:</strong><br />
<div class="highlight"><pre><span></span><code><a id="__codelineno-3-1" name="__codelineno-3-1" href="#__codelineno-3-1"></a><span class="p">{</span>
<a id="__codelineno-3-2" name="__codelineno-3-2" href="#__codelineno-3-2"></a><span class="w"> </span><span class="nt">&quot;name&quot;</span><span class="p">:</span><span class="w"> </span><span class="s2">&quot;llama2-7b&quot;</span><span class="p">,</span>
<a id="__codelineno-3-3" name="__codelineno-3-3" href="#__codelineno-3-3"></a><span class="w"> </span><span class="nt">&quot;backend_type&quot;</span><span class="p">:</span><span class="w"> </span><span class="s2">&quot;llama_cpp&quot;</span><span class="p">,</span>
<a id="__codelineno-3-4" name="__codelineno-3-4" href="#__codelineno-3-4"></a><span class="w"> </span><span class="nt">&quot;backend_options&quot;</span><span class="p">:</span><span class="w"> </span><span class="p">{</span>
<a id="__codelineno-3-5" name="__codelineno-3-5" href="#__codelineno-3-5"></a><span class="w"> </span><span class="nt">&quot;model&quot;</span><span class="p">:</span><span class="w"> </span><span class="s2">&quot;/path/to/llama-2-7b-chat.gguf&quot;</span><span class="p">,</span>
<a id="__codelineno-3-6" name="__codelineno-3-6" href="#__codelineno-3-6"></a><span class="w"> </span><span class="nt">&quot;threads&quot;</span><span class="p">:</span><span class="w"> </span><span class="mi">4</span><span class="p">,</span>
<a id="__codelineno-3-7" name="__codelineno-3-7" href="#__codelineno-3-7"></a><span class="w"> </span><span class="nt">&quot;ctx_size&quot;</span><span class="p">:</span><span class="w"> </span><span class="mi">2048</span><span class="p">,</span>
<a id="__codelineno-3-8" name="__codelineno-3-8" href="#__codelineno-3-8"></a><span class="w"> </span><span class="nt">&quot;gpu_layers&quot;</span><span class="p">:</span><span class="w"> </span><span class="mi">32</span>
<a id="__codelineno-3-9" name="__codelineno-3-9" href="#__codelineno-3-9"></a><span class="w"> </span><span class="p">},</span>
<a id="__codelineno-3-10" name="__codelineno-3-10" href="#__codelineno-3-10"></a><span class="w"> </span><span class="nt">&quot;nodes&quot;</span><span class="p">:</span><span class="w"> </span><span class="p">[</span><span class="s2">&quot;main&quot;</span><span class="p">]</span>
<a id="__codelineno-3-11" name="__codelineno-3-11" href="#__codelineno-3-11"></a><span class="p">}</span>
</code></pre></div></p>
<p><strong>MLX backend (macOS only):</strong><br />
<div class="highlight"><pre><span></span><code><a id="__codelineno-4-1" name="__codelineno-4-1" href="#__codelineno-4-1"></a><span class="p">{</span>
<a id="__codelineno-4-2" name="__codelineno-4-2" href="#__codelineno-4-2"></a><span class="w"> </span><span class="nt">&quot;name&quot;</span><span class="p">:</span><span class="w"> </span><span class="s2">&quot;mistral-mlx&quot;</span><span class="p">,</span>
<a id="__codelineno-4-3" name="__codelineno-4-3" href="#__codelineno-4-3"></a><span class="w"> </span><span class="nt">&quot;backend_type&quot;</span><span class="p">:</span><span class="w"> </span><span class="s2">&quot;mlx_lm&quot;</span><span class="p">,</span>
<a id="__codelineno-4-4" name="__codelineno-4-4" href="#__codelineno-4-4"></a><span class="w"> </span><span class="nt">&quot;backend_options&quot;</span><span class="p">:</span><span class="w"> </span><span class="p">{</span>
<a id="__codelineno-4-5" name="__codelineno-4-5" href="#__codelineno-4-5"></a><span class="w"> </span><span class="nt">&quot;model&quot;</span><span class="p">:</span><span class="w"> </span><span class="s2">&quot;mlx-community/Mistral-7B-Instruct-v0.3-4bit&quot;</span><span class="p">,</span>
<a id="__codelineno-4-6" name="__codelineno-4-6" href="#__codelineno-4-6"></a><span class="w"> </span><span class="nt">&quot;temp&quot;</span><span class="p">:</span><span class="w"> </span><span class="mf">0.7</span><span class="p">,</span>
<a id="__codelineno-4-7" name="__codelineno-4-7" href="#__codelineno-4-7"></a><span class="w"> </span><span class="nt">&quot;max_tokens&quot;</span><span class="p">:</span><span class="w"> </span><span class="mi">2048</span>
<a id="__codelineno-4-8" name="__codelineno-4-8" href="#__codelineno-4-8"></a><span class="w"> </span><span class="p">},</span>
<a id="__codelineno-4-9" name="__codelineno-4-9" href="#__codelineno-4-9"></a><span class="w"> </span><span class="nt">&quot;nodes&quot;</span><span class="p">:</span><span class="w"> </span><span class="p">[</span><span class="s2">&quot;main&quot;</span><span class="p">]</span>
<a id="__codelineno-4-10" name="__codelineno-4-10" href="#__codelineno-4-10"></a><span class="p">}</span>
</code></pre></div></p>
<p><strong>vLLM backend:</strong><br />
<div class="highlight"><pre><span></span><code><a id="__codelineno-5-1" name="__codelineno-5-1" href="#__codelineno-5-1"></a><span class="p">{</span>
<a id="__codelineno-5-2" name="__codelineno-5-2" href="#__codelineno-5-2"></a><span class="w"> </span><span class="nt">&quot;name&quot;</span><span class="p">:</span><span class="w"> </span><span class="s2">&quot;dialogpt-vllm&quot;</span><span class="p">,</span>
<a id="__codelineno-5-3" name="__codelineno-5-3" href="#__codelineno-5-3"></a><span class="w"> </span><span class="nt">&quot;backend_type&quot;</span><span class="p">:</span><span class="w"> </span><span class="s2">&quot;vllm&quot;</span><span class="p">,</span>
<a id="__codelineno-5-4" name="__codelineno-5-4" href="#__codelineno-5-4"></a><span class="w"> </span><span class="nt">&quot;backend_options&quot;</span><span class="p">:</span><span class="w"> </span><span class="p">{</span>
<a id="__codelineno-5-5" name="__codelineno-5-5" href="#__codelineno-5-5"></a><span class="w"> </span><span class="nt">&quot;model&quot;</span><span class="p">:</span><span class="w"> </span><span class="s2">&quot;microsoft/DialoGPT-medium&quot;</span><span class="p">,</span>
<a id="__codelineno-5-6" name="__codelineno-5-6" href="#__codelineno-5-6"></a><span class="w"> </span><span class="nt">&quot;tensor_parallel_size&quot;</span><span class="p">:</span><span class="w"> </span><span class="mi">2</span><span class="p">,</span>
<a id="__codelineno-5-7" name="__codelineno-5-7" href="#__codelineno-5-7"></a><span class="w"> </span><span class="nt">&quot;gpu_memory_utilization&quot;</span><span class="p">:</span><span class="w"> </span><span class="mf">0.9</span>
<a id="__codelineno-5-8" name="__codelineno-5-8" href="#__codelineno-5-8"></a><span class="w"> </span><span class="p">},</span>
<a id="__codelineno-5-9" name="__codelineno-5-9" href="#__codelineno-5-9"></a><span class="w"> </span><span class="nt">&quot;nodes&quot;</span><span class="p">:</span><span class="w"> </span><span class="p">[</span><span class="s2">&quot;main&quot;</span><span class="p">]</span>
<a id="__codelineno-5-10" name="__codelineno-5-10" href="#__codelineno-5-10"></a><span class="p">}</span>
</code></pre></div></p>
<p><strong>Remote node deployment example:</strong><br />
<div class="highlight"><pre><span></span><code><a id="__codelineno-6-1" name="__codelineno-6-1" href="#__codelineno-6-1"></a><span class="p">{</span>
<a id="__codelineno-6-2" name="__codelineno-6-2" href="#__codelineno-6-2"></a><span class="w"> </span><span class="nt">&quot;name&quot;</span><span class="p">:</span><span class="w"> </span><span class="s2">&quot;distributed-model&quot;</span><span class="p">,</span>
<a id="__codelineno-6-3" name="__codelineno-6-3" href="#__codelineno-6-3"></a><span class="w"> </span><span class="nt">&quot;backend_type&quot;</span><span class="p">:</span><span class="w"> </span><span class="s2">&quot;llama_cpp&quot;</span><span class="p">,</span>
<a id="__codelineno-6-4" name="__codelineno-6-4" href="#__codelineno-6-4"></a><span class="w"> </span><span class="nt">&quot;backend_options&quot;</span><span class="p">:</span><span class="w"> </span><span class="p">{</span>
<a id="__codelineno-6-5" name="__codelineno-6-5" href="#__codelineno-6-5"></a><span class="w"> </span><span class="nt">&quot;model&quot;</span><span class="p">:</span><span class="w"> </span><span class="s2">&quot;/path/to/model.gguf&quot;</span><span class="p">,</span>
<a id="__codelineno-6-6" name="__codelineno-6-6" href="#__codelineno-6-6"></a><span class="w"> </span><span class="nt">&quot;gpu_layers&quot;</span><span class="p">:</span><span class="w"> </span><span class="mi">32</span>
<a id="__codelineno-6-7" name="__codelineno-6-7" href="#__codelineno-6-7"></a><span class="w"> </span><span class="p">},</span>
<a id="__codelineno-6-8" name="__codelineno-6-8" href="#__codelineno-6-8"></a><span class="w"> </span><span class="nt">&quot;nodes&quot;</span><span class="p">:</span><span class="w"> </span><span class="p">[</span><span class="s2">&quot;worker1&quot;</span><span class="p">]</span>
<a id="__codelineno-6-9" name="__codelineno-6-9" href="#__codelineno-6-9"></a><span class="p">}</span>
</code></pre></div></p>
<h2 id="docker-support">Docker Support<a class="headerlink" href="#docker-support" title="Permanent link">&para;</a></h2>
<p>Llamactl can run backends in Docker containers. To enable Docker for a backend, add a <code>docker</code> section to that backend in your YAML configuration file (e.g. <code>config.yaml</code>) as shown below: </p>
<div class="highlight"><pre><span></span><code><a id="__codelineno-7-1" name="__codelineno-7-1" href="#__codelineno-7-1"></a><span class="nt">backends</span><span class="p">:</span>
<a id="__codelineno-7-2" name="__codelineno-7-2" href="#__codelineno-7-2"></a><span class="w"> </span><span class="nt">vllm</span><span class="p">:</span>
<a id="__codelineno-7-3" name="__codelineno-7-3" href="#__codelineno-7-3"></a><span class="w"> </span><span class="nt">command</span><span class="p">:</span><span class="w"> </span><span class="s">&quot;vllm&quot;</span>
<a id="__codelineno-7-4" name="__codelineno-7-4" href="#__codelineno-7-4"></a><span class="w"> </span><span class="nt">args</span><span class="p">:</span><span class="w"> </span><span class="p p-Indicator">[</span><span class="s">&quot;serve&quot;</span><span class="p p-Indicator">]</span>
<a id="__codelineno-7-5" name="__codelineno-7-5" href="#__codelineno-7-5"></a><span class="w"> </span><span class="nt">docker</span><span class="p">:</span>
<a id="__codelineno-7-6" name="__codelineno-7-6" href="#__codelineno-7-6"></a><span class="w"> </span><span class="nt">enabled</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">true</span>
<a id="__codelineno-7-7" name="__codelineno-7-7" href="#__codelineno-7-7"></a><span class="w"> </span><span class="nt">image</span><span class="p">:</span><span class="w"> </span><span class="s">&quot;vllm/vllm-openai:latest&quot;</span>
<a id="__codelineno-7-8" name="__codelineno-7-8" href="#__codelineno-7-8"></a><span class="w"> </span><span class="nt">args</span><span class="p">:</span><span class="w"> </span><span class="p p-Indicator">[</span><span class="s">&quot;run&quot;</span><span class="p p-Indicator">,</span><span class="w"> </span><span class="s">&quot;--rm&quot;</span><span class="p p-Indicator">,</span><span class="w"> </span><span class="s">&quot;--network&quot;</span><span class="p p-Indicator">,</span><span class="w"> </span><span class="s">&quot;host&quot;</span><span class="p p-Indicator">,</span><span class="w"> </span><span class="s">&quot;--gpus&quot;</span><span class="p p-Indicator">,</span><span class="w"> </span><span class="s">&quot;all&quot;</span><span class="p p-Indicator">,</span><span class="w"> </span><span class="s">&quot;--shm-size&quot;</span><span class="p p-Indicator">,</span><span class="w"> </span><span class="s">&quot;1g&quot;</span><span class="p p-Indicator">]</span>
</code></pre></div>
<h2 id="using-the-api">Using the API<a class="headerlink" href="#using-the-api" title="Permanent link">&para;</a></h2>
<p>You can also manage instances via the REST API: </p>
<div class="highlight"><pre><span></span><code><a id="__codelineno-8-1" name="__codelineno-8-1" href="#__codelineno-8-1"></a><span class="c1"># List all instances</span>
<a id="__codelineno-8-2" name="__codelineno-8-2" href="#__codelineno-8-2"></a>curl<span class="w"> </span>http://localhost:8080/api/v1/instances
<a id="__codelineno-8-3" name="__codelineno-8-3" href="#__codelineno-8-3"></a>
<a id="__codelineno-8-4" name="__codelineno-8-4" href="#__codelineno-8-4"></a><span class="c1"># Create a new llama.cpp instance</span>
<a id="__codelineno-8-5" name="__codelineno-8-5" href="#__codelineno-8-5"></a>curl<span class="w"> </span>-X<span class="w"> </span>POST<span class="w"> </span>http://localhost:8080/api/v1/instances/my-model<span class="w"> </span><span class="se">\</span>
<a id="__codelineno-8-6" name="__codelineno-8-6" href="#__codelineno-8-6"></a><span class="w"> </span>-H<span class="w"> </span><span class="s2">&quot;Content-Type: application/json&quot;</span><span class="w"> </span><span class="se">\</span>
<a id="__codelineno-8-7" name="__codelineno-8-7" href="#__codelineno-8-7"></a><span class="w"> </span>-d<span class="w"> </span><span class="s1">&#39;{</span>
<a id="__codelineno-8-8" name="__codelineno-8-8" href="#__codelineno-8-8"></a><span class="s1"> &quot;backend_type&quot;: &quot;llama_cpp&quot;,</span>
<a id="__codelineno-8-9" name="__codelineno-8-9" href="#__codelineno-8-9"></a><span class="s1"> &quot;backend_options&quot;: {</span>
<a id="__codelineno-8-10" name="__codelineno-8-10" href="#__codelineno-8-10"></a><span class="s1"> &quot;model&quot;: &quot;/path/to/model.gguf&quot;</span>
<a id="__codelineno-8-11" name="__codelineno-8-11" href="#__codelineno-8-11"></a><span class="s1"> }</span>
<a id="__codelineno-8-12" name="__codelineno-8-12" href="#__codelineno-8-12"></a><span class="s1"> }&#39;</span>
<a id="__codelineno-8-13" name="__codelineno-8-13" href="#__codelineno-8-13"></a>
<a id="__codelineno-8-14" name="__codelineno-8-14" href="#__codelineno-8-14"></a><span class="c1"># Start an instance</span>
<a id="__codelineno-8-15" name="__codelineno-8-15" href="#__codelineno-8-15"></a>curl<span class="w"> </span>-X<span class="w"> </span>POST<span class="w"> </span>http://localhost:8080/api/v1/instances/my-model/start
</code></pre></div>
<h2 id="openai-compatible-api">OpenAI Compatible API<a class="headerlink" href="#openai-compatible-api" title="Permanent link">&para;</a></h2>
<p>Llamactl provides OpenAI-compatible endpoints, making it easy to integrate with existing OpenAI client libraries and tools. </p>
<h3 id="chat-completions">Chat Completions<a class="headerlink" href="#chat-completions" title="Permanent link">&para;</a></h3>
<p>Once you have an instance running, you can use it with the OpenAI-compatible chat completions endpoint: </p>
<div class="highlight"><pre><span></span><code><a id="__codelineno-9-1" name="__codelineno-9-1" href="#__codelineno-9-1"></a>curl<span class="w"> </span>-X<span class="w"> </span>POST<span class="w"> </span>http://localhost:8080/v1/chat/completions<span class="w"> </span><span class="se">\</span>
<a id="__codelineno-9-2" name="__codelineno-9-2" href="#__codelineno-9-2"></a><span class="w"> </span>-H<span class="w"> </span><span class="s2">&quot;Content-Type: application/json&quot;</span><span class="w"> </span><span class="se">\</span>
<a id="__codelineno-9-3" name="__codelineno-9-3" href="#__codelineno-9-3"></a><span class="w"> </span>-d<span class="w"> </span><span class="s1">&#39;{</span>
<a id="__codelineno-9-4" name="__codelineno-9-4" href="#__codelineno-9-4"></a><span class="s1"> &quot;model&quot;: &quot;my-model&quot;,</span>
<a id="__codelineno-9-5" name="__codelineno-9-5" href="#__codelineno-9-5"></a><span class="s1"> &quot;messages&quot;: [</span>
<a id="__codelineno-9-6" name="__codelineno-9-6" href="#__codelineno-9-6"></a><span class="s1"> {</span>
<a id="__codelineno-9-7" name="__codelineno-9-7" href="#__codelineno-9-7"></a><span class="s1"> &quot;role&quot;: &quot;user&quot;,</span>
<a id="__codelineno-9-8" name="__codelineno-9-8" href="#__codelineno-9-8"></a><span class="s1"> &quot;content&quot;: &quot;Hello! Can you help me write a Python function?&quot;</span>
<a id="__codelineno-9-9" name="__codelineno-9-9" href="#__codelineno-9-9"></a><span class="s1"> }</span>
<a id="__codelineno-9-10" name="__codelineno-9-10" href="#__codelineno-9-10"></a><span class="s1"> ],</span>
<a id="__codelineno-9-11" name="__codelineno-9-11" href="#__codelineno-9-11"></a><span class="s1"> &quot;max_tokens&quot;: 150,</span>
<a id="__codelineno-9-12" name="__codelineno-9-12" href="#__codelineno-9-12"></a><span class="s1"> &quot;temperature&quot;: 0.7</span>
<a id="__codelineno-9-13" name="__codelineno-9-13" href="#__codelineno-9-13"></a><span class="s1"> }&#39;</span>
</code></pre></div>
<h3 id="using-with-python-openai-client">Using with Python OpenAI Client<a class="headerlink" href="#using-with-python-openai-client" title="Permanent link">&para;</a></h3>
<p>You can also use the official OpenAI Python client: </p>
<div class="highlight"><pre><span></span><code><a id="__codelineno-10-1" name="__codelineno-10-1" href="#__codelineno-10-1"></a><span class="kn">from</span><span class="w"> </span><span class="nn">openai</span><span class="w"> </span><span class="kn">import</span> <span class="n">OpenAI</span>
<a id="__codelineno-10-2" name="__codelineno-10-2" href="#__codelineno-10-2"></a>
<a id="__codelineno-10-3" name="__codelineno-10-3" href="#__codelineno-10-3"></a><span class="c1"># Point the client to your Llamactl server</span>
<a id="__codelineno-10-4" name="__codelineno-10-4" href="#__codelineno-10-4"></a><span class="n">client</span> <span class="o">=</span> <span class="n">OpenAI</span><span class="p">(</span>
<a id="__codelineno-10-5" name="__codelineno-10-5" href="#__codelineno-10-5"></a> <span class="n">base_url</span><span class="o">=</span><span class="s2">&quot;http://localhost:8080/v1&quot;</span><span class="p">,</span>
<a id="__codelineno-10-6" name="__codelineno-10-6" href="#__codelineno-10-6"></a> <span class="n">api_key</span><span class="o">=</span><span class="s2">&quot;your-inference-api-key&quot;</span> <span class="c1"># Use the inference API key from terminal or config</span>
<a id="__codelineno-10-7" name="__codelineno-10-7" href="#__codelineno-10-7"></a><span class="p">)</span>
<a id="__codelineno-10-8" name="__codelineno-10-8" href="#__codelineno-10-8"></a>
<a id="__codelineno-10-9" name="__codelineno-10-9" href="#__codelineno-10-9"></a><span class="c1"># Create a chat completion</span>
<a id="__codelineno-10-10" name="__codelineno-10-10" href="#__codelineno-10-10"></a><span class="n">response</span> <span class="o">=</span> <span class="n">client</span><span class="o">.</span><span class="n">chat</span><span class="o">.</span><span class="n">completions</span><span class="o">.</span><span class="n">create</span><span class="p">(</span>
<a id="__codelineno-10-11" name="__codelineno-10-11" href="#__codelineno-10-11"></a> <span class="n">model</span><span class="o">=</span><span class="s2">&quot;my-model&quot;</span><span class="p">,</span> <span class="c1"># Use the name of your instance</span>
<a id="__codelineno-10-12" name="__codelineno-10-12" href="#__codelineno-10-12"></a> <span class="n">messages</span><span class="o">=</span><span class="p">[</span>
<a id="__codelineno-10-13" name="__codelineno-10-13" href="#__codelineno-10-13"></a> <span class="p">{</span><span class="s2">&quot;role&quot;</span><span class="p">:</span> <span class="s2">&quot;user&quot;</span><span class="p">,</span> <span class="s2">&quot;content&quot;</span><span class="p">:</span> <span class="s2">&quot;Explain quantum computing in simple terms&quot;</span><span class="p">}</span>
<a id="__codelineno-10-14" name="__codelineno-10-14" href="#__codelineno-10-14"></a> <span class="p">],</span>
<a id="__codelineno-10-15" name="__codelineno-10-15" href="#__codelineno-10-15"></a> <span class="n">max_tokens</span><span class="o">=</span><span class="mi">200</span><span class="p">,</span>
<a id="__codelineno-10-16" name="__codelineno-10-16" href="#__codelineno-10-16"></a> <span class="n">temperature</span><span class="o">=</span><span class="mf">0.7</span>
<a id="__codelineno-10-17" name="__codelineno-10-17" href="#__codelineno-10-17"></a><span class="p">)</span>
<a id="__codelineno-10-18" name="__codelineno-10-18" href="#__codelineno-10-18"></a>
<a id="__codelineno-10-19" name="__codelineno-10-19" href="#__codelineno-10-19"></a><span class="nb">print</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">message</span><span class="o">.</span><span class="n">content</span><span class="p">)</span>
</code></pre></div>
<div class="admonition note">
<p class="admonition-title">API Key</p>
<p>If you disabled authentication in your config, you can use any value for <code>api_key</code> (e.g., <code>"not-needed"</code>). Otherwise, use the inference API key shown in the terminal output on startup. </p>
</div>
<h3 id="list-available-models">List Available Models<a class="headerlink" href="#list-available-models" title="Permanent link">&para;</a></h3>
<p>Get a list of running instances (models) in OpenAI-compatible format: </p>
<div class="highlight"><pre><span></span><code><a id="__codelineno-11-1" name="__codelineno-11-1" href="#__codelineno-11-1"></a>curl<span class="w"> </span>http://localhost:8080/v1/models
</code></pre></div>
<h2 id="next-steps">Next Steps<a class="headerlink" href="#next-steps" title="Permanent link">&para;</a></h2>
<ul>
<li>Manage instances <a href="../managing-instances/">Managing Instances</a> </li>
<li>Explore the <a href="../api-reference/">API Reference</a> </li>
<li>Configure advanced settings in the <a href="../configuration/">Configuration</a> guide </li>
</ul>
<aside class="md-source-file">
<span class="md-source-file__fact">
<span class="md-icon" title="Last update">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M21 13.1c-.1 0-.3.1-.4.2l-1 1 2.1 2.1 1-1c.2-.2.2-.6 0-.8l-1.3-1.3c-.1-.1-.2-.2-.4-.2m-1.9 1.8-6.1 6V23h2.1l6.1-6.1zM12.5 7v5.2l4 2.4-1 1L11 13V7zM11 21.9c-5.1-.5-9-4.8-9-9.9C2 6.5 6.5 2 12 2c5.3 0 9.6 4.1 10 9.3-.3-.1-.6-.2-1-.2s-.7.1-1 .2C19.6 7.2 16.2 4 12 4c-4.4 0-8 3.6-8 8 0 4.1 3.1 7.5 7.1 7.9l-.1.2z"/></svg>
</span>
<span class="git-revision-date-localized-plugin git-revision-date-localized-plugin-date" title="October 26, 2025 16:19:53 UTC">October 26, 2025</span>
</span>
</aside>
</article>
</div>
<script>var target=document.getElementById(location.hash.slice(1));target&&target.name&&(target.checked=target.name.startsWith("__tabbed_"))</script>
</div>
<button type="button" class="md-top md-icon" data-md-component="top" hidden>
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M13 20h-2V8l-5.5 5.5-1.42-1.42L12 4.16l7.92 7.92-1.42 1.42L13 8z"/></svg>
Back to top
</button>
</main>
<footer class="md-footer">
<div class="md-footer-meta md-typeset">
<div class="md-footer-meta__inner md-grid">
<div class="md-copyright">
Made with
<a href="https://squidfunk.github.io/mkdocs-material/" target="_blank" rel="noopener">
Material for MkDocs
</a>
</div>
<div class="md-social">
<a href="https://github.com/lordmathis/llamactl" target="_blank" rel="noopener" title="github.com" class="md-social__link">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512"><!--! Font Awesome Free 7.1.0 by @fontawesome - https://fontawesome.com License - https://fontawesome.com/license/free (Icons: CC BY 4.0, Fonts: SIL OFL 1.1, Code: MIT License) Copyright 2025 Fonticons, Inc.--><path d="M173.9 397.4c0 2-2.3 3.6-5.2 3.6-3.3.3-5.6-1.3-5.6-3.6 0-2 2.3-3.6 5.2-3.6 3-.3 5.6 1.3 5.6 3.6m-31.1-4.5c-.7 2 1.3 4.3 4.3 4.9 2.6 1 5.6 0 6.2-2s-1.3-4.3-4.3-5.2c-2.6-.7-5.5.3-6.2 2.3m44.2-1.7c-2.9.7-4.9 2.6-4.6 4.9.3 2 2.9 3.3 5.9 2.6 2.9-.7 4.9-2.6 4.6-4.6-.3-1.9-3-3.2-5.9-2.9M252.8 8C114.1 8 8 113.3 8 252c0 110.9 69.8 205.8 169.5 239.2 12.8 2.3 17.3-5.6 17.3-12.1 0-6.2-.3-40.4-.3-61.4 0 0-70 15-84.7-29.8 0 0-11.4-29.1-27.8-36.6 0 0-22.9-15.7 1.6-15.4 0 0 24.9 2 38.6 25.8 21.9 38.6 58.6 27.5 72.9 20.9 2.3-16 8.8-27.1 16-33.7-55.9-6.2-112.3-14.3-112.3-110.5 0-27.5 7.6-41.3 23.6-58.9-2.6-6.5-11.1-33.3 2.6-67.9 20.9-6.5 69 27 69 27 20-5.6 41.5-8.5 62.8-8.5s42.8 2.9 62.8 8.5c0 0 48.1-33.6 69-27 13.7 34.7 5.2 61.4 2.6 67.9 16 17.7 25.8 31.5 25.8 58.9 0 96.5-58.9 104.2-114.8 110.5 9.2 7.9 17 22.9 17 46.4 0 33.7-.3 75.4-.3 83.6 0 6.5 4.6 14.4 17.3 12.1C436.2 457.8 504 362.9 504 252 504 113.3 391.5 8 252.8 8M105.2 352.9c-1.3 1-1 3.3.7 5.2 1.6 1.6 3.9 2.3 5.2 1 1.3-1 1-3.3-.7-5.2-1.6-1.6-3.9-2.3-5.2-1m-10.8-8.1c-.7 1.3.3 2.9 2.3 3.9 1.6 1 3.6.7 4.3-.7.7-1.3-.3-2.9-2.3-3.9-2-.6-3.6-.3-4.3.7m32.4 35.6c-1.6 1.3-1 4.3 1.3 6.2 2.3 2.3 5.2 2.6 6.5 1 1.3-1.3.7-4.3-1.3-6.2-2.2-2.3-5.2-2.6-6.5-1m-11.4-14.7c-1.6 1-1.6 3.6 0 5.9s4.3 3.3 5.6 2.3c1.6-1.3 1.6-3.9 0-6.2-1.4-2.3-4-3.3-5.6-2"/></svg>
</a>
</div>
</div>
</div>
</footer>
</div>
<div class="md-dialog" data-md-component="dialog">
<div class="md-dialog__inner md-typeset"></div>
</div>
<script id="__config" type="application/json">{"base": "..", "features": ["navigation.tabs", "navigation.tabs.sticky", "toc.integrate", "navigation.top", "search.highlight", "search.share", "content.code.copy"], "search": "../assets/javascripts/workers/search.973d3a69.min.js", "tags": null, "translations": {"clipboard.copied": "Copied to clipboard", "clipboard.copy": "Copy to clipboard", "search.result.more.one": "1 more on this page", "search.result.more.other": "# more on this page", "search.result.none": "No matching documents", "search.result.one": "1 matching document", "search.result.other": "# matching documents", "search.result.placeholder": "Type to start searching", "search.result.term.missing": "Missing", "select.version": "Select version"}, "version": {"default": "stable", "provider": "mike"}}</script>
<script src="../assets/javascripts/bundle.f55a23d4.min.js"></script>
</body>
</html>
Reference in New Issue View Git Blame Copy Permalink