319 lines
No EOL
52 KiB
HTML
319 lines
No EOL
52 KiB
HTML
<!doctype html>
|
||
<html lang="en" dir="ltr" class="docs-wrapper plugin-docs plugin-id-default docs-version-current docs-doc-page docs-doc-id-get-started/docker" data-has-hydrated="false">
|
||
<head>
|
||
<meta charset="UTF-8">
|
||
<meta name="generator" content="Docusaurus v3.9.2">
|
||
<title data-rh="true">Deploy OpenRAG with self-managed services | OpenRAG</title><meta data-rh="true" name="viewport" content="width=device-width,initial-scale=1"><meta data-rh="true" name="robots" content="noindex, nofollow"><meta data-rh="true" name="twitter:card" content="summary_large_image"><meta data-rh="true" property="og:url" content="https://docs.openr.ag/docker"><meta data-rh="true" property="og:locale" content="en"><meta data-rh="true" name="docusaurus_locale" content="en"><meta data-rh="true" name="docsearch:language" content="en"><meta data-rh="true" name="docusaurus_version" content="current"><meta data-rh="true" name="docusaurus_tag" content="docs-default-current"><meta data-rh="true" name="docsearch:version" content="current"><meta data-rh="true" name="docsearch:docusaurus_tag" content="docs-default-current"><meta data-rh="true" property="og:title" content="Deploy OpenRAG with self-managed services | OpenRAG"><meta data-rh="true" name="description" content="To manage your own OpenRAG services, deploy OpenRAG with Docker or Podman."><meta data-rh="true" property="og:description" content="To manage your own OpenRAG services, deploy OpenRAG with Docker or Podman."><link data-rh="true" rel="icon" href="/img/favicon.ico"><link data-rh="true" rel="canonical" href="https://docs.openr.ag/docker"><link data-rh="true" rel="alternate" href="https://docs.openr.ag/docker" hreflang="en"><link data-rh="true" rel="alternate" href="https://docs.openr.ag/docker" hreflang="x-default"><script data-rh="true" type="application/ld+json">{"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Deploy self-managed services","item":"https://docs.openr.ag/docker"}]}</script><link rel="stylesheet" href="/assets/css/styles.66669ecc.css">
|
||
<script src="/assets/js/runtime~main.0ec053c5.js" defer="defer"></script>
|
||
<script src="/assets/js/main.b10c6137.js" defer="defer"></script>
|
||
</head>
|
||
<body class="navigation-with-keyboard">
|
||
<svg style="display: none;"><defs>
|
||
<symbol id="theme-svg-external-link" viewBox="0 0 24 24"><path fill="currentColor" d="M21 13v10h-21v-19h12v2h-10v15h17v-8h2zm3-12h-10.988l4.035 4-6.977 7.07 2.828 2.828 6.977-7.07 4.125 4.172v-11z"/></symbol>
|
||
</defs></svg>
|
||
<script>!function(){var t=function(){try{return new URLSearchParams(window.location.search).get("docusaurus-theme")}catch(t){}}()||function(){try{return window.localStorage.getItem("theme")}catch(t){}}();document.documentElement.setAttribute("data-theme",t||"light"),document.documentElement.setAttribute("data-theme-choice",t||"light")}(),function(){try{const c=new URLSearchParams(window.location.search).entries();for(var[t,e]of c)if(t.startsWith("docusaurus-data-")){var a=t.replace("docusaurus-data-","data-");document.documentElement.setAttribute(a,e)}}catch(t){}}()</script><div id="__docusaurus"><link rel="preload" as="image" href="/img/logo-openrag-light.svg"><link rel="preload" as="image" href="/img/logo-openrag-dark.svg"><div role="region" aria-label="Skip to main content"><a class="skipToContent_fXgn" href="#__docusaurus_skipToContent_fallback">Skip to main content</a></div><nav aria-label="Main" class="theme-layout-navbar navbar navbar--fixed-top"><div class="navbar__inner"><div class="theme-layout-navbar-left navbar__items"><button aria-label="Toggle navigation bar" aria-expanded="false" class="navbar__toggle clean-btn" type="button"><svg width="30" height="30" viewBox="0 0 30 30" aria-hidden="true"><path stroke="currentColor" stroke-linecap="round" stroke-miterlimit="10" stroke-width="2" d="M4 7h22M4 15h22M4 23h22"></path></svg></button><a class="navbar__brand" href="/"><div class="navbar__logo"><img src="/img/logo-openrag-light.svg" alt="OpenRAG Logo" class="themedComponent_mlkZ themedComponent--light_NVdE"><img src="/img/logo-openrag-dark.svg" alt="OpenRAG Logo" class="themedComponent_mlkZ themedComponent--dark_xIcU"></div></a></div><div class="theme-layout-navbar-right navbar__items navbar__items--right"><a href="https://github.com/langflow-ai/openrag" target="_blank" class="navbar__item navbar__link header-github-link" aria-label="GitHub repository"></a><div class="toggle_vylO colorModeToggle_DEke"><button class="clean-btn toggleButton_gllP toggleButtonDisabled_aARS" type="button" disabled="" title="system mode" aria-label="Switch between dark and light mode (currently system mode)"><svg viewBox="0 0 24 24" width="24" height="24" aria-hidden="true" class="toggleIcon_g3eP lightToggleIcon_pyhR"><path fill="currentColor" d="M12,9c1.65,0,3,1.35,3,3s-1.35,3-3,3s-3-1.35-3-3S10.35,9,12,9 M12,7c-2.76,0-5,2.24-5,5s2.24,5,5,5s5-2.24,5-5 S14.76,7,12,7L12,7z M2,13l2,0c0.55,0,1-0.45,1-1s-0.45-1-1-1l-2,0c-0.55,0-1,0.45-1,1S1.45,13,2,13z M20,13l2,0c0.55,0,1-0.45,1-1 s-0.45-1-1-1l-2,0c-0.55,0-1,0.45-1,1S19.45,13,20,13z M11,2v2c0,0.55,0.45,1,1,1s1-0.45,1-1V2c0-0.55-0.45-1-1-1S11,1.45,11,2z M11,20v2c0,0.55,0.45,1,1,1s1-0.45,1-1v-2c0-0.55-0.45-1-1-1C11.45,19,11,19.45,11,20z M5.99,4.58c-0.39-0.39-1.03-0.39-1.41,0 c-0.39,0.39-0.39,1.03,0,1.41l1.06,1.06c0.39,0.39,1.03,0.39,1.41,0s0.39-1.03,0-1.41L5.99,4.58z M18.36,16.95 c-0.39-0.39-1.03-0.39-1.41,0c-0.39,0.39-0.39,1.03,0,1.41l1.06,1.06c0.39,0.39,1.03,0.39,1.41,0c0.39-0.39,0.39-1.03,0-1.41 L18.36,16.95z M19.42,5.99c0.39-0.39,0.39-1.03,0-1.41c-0.39-0.39-1.03-0.39-1.41,0l-1.06,1.06c-0.39,0.39-0.39,1.03,0,1.41 s1.03,0.39,1.41,0L19.42,5.99z M7.05,18.36c0.39-0.39,0.39-1.03,0-1.41c-0.39-0.39-1.03-0.39-1.41,0l-1.06,1.06 c-0.39,0.39-0.39,1.03,0,1.41s1.03,0.39,1.41,0L7.05,18.36z"></path></svg><svg viewBox="0 0 24 24" width="24" height="24" aria-hidden="true" class="toggleIcon_g3eP darkToggleIcon_wfgR"><path fill="currentColor" d="M9.37,5.51C9.19,6.15,9.1,6.82,9.1,7.5c0,4.08,3.32,7.4,7.4,7.4c0.68,0,1.35-0.09,1.99-0.27C17.45,17.19,14.93,19,12,19 c-3.86,0-7-3.14-7-7C5,9.07,6.81,6.55,9.37,5.51z M12,3c-4.97,0-9,4.03-9,9s4.03,9,9,9s9-4.03,9-9c0-0.46-0.04-0.92-0.1-1.36 c-0.98,1.37-2.58,2.26-4.4,2.26c-2.98,0-5.4-2.42-5.4-5.4c0-1.81,0.89-3.42,2.26-4.4C12.92,3.04,12.46,3,12,3L12,3z"></path></svg><svg viewBox="0 0 24 24" width="24" height="24" aria-hidden="true" class="toggleIcon_g3eP systemToggleIcon_QzmC"><path fill="currentColor" d="m12 21c4.971 0 9-4.029 9-9s-4.029-9-9-9-9 4.029-9 9 4.029 9 9 9zm4.95-13.95c1.313 1.313 2.05 3.093 2.05 4.95s-0.738 3.637-2.05 4.95c-1.313 1.313-3.093 2.05-4.95 2.05v-14c1.857 0 3.637 0.737 4.95 2.05z"></path></svg></button></div><div class="navbarSearchContainer_Bca1"></div></div></div><div role="presentation" class="navbar-sidebar__backdrop"></div></nav><div id="__docusaurus_skipToContent_fallback" class="theme-layout-main main-wrapper mainWrapper_z2l0"><div class="docsWrapper_hBAB"><button aria-label="Scroll back to top" class="clean-btn theme-back-to-top-button backToTopButton_sjWU" type="button"></button><div class="docRoot_UBD9"><aside class="theme-doc-sidebar-container docSidebarContainer_YfHR"><div class="sidebarViewport_aRkj"><div class="sidebar_njMd"><nav aria-label="Docs sidebar" class="menu thin-scrollbar menu_SIkG"><ul class="theme-doc-sidebar-menu menu__list"><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-1 menu__list-item"><a class="menu__link" href="/"><span title="About OpenRAG" class="linkLabel_WmDU">About OpenRAG</span></a></li><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-1 menu__list-item"><a class="menu__link" href="/quickstart"><span title="Quickstart" class="linkLabel_WmDU">Quickstart</span></a></li><li class="theme-doc-sidebar-item-category theme-doc-sidebar-item-category-level-1 menu__list-item"><div class="menu__list-item-collapsible"><a class="categoryLink_byQd menu__link menu__link--sublist menu__link--sublist-caret menu__link--active" role="button" aria-expanded="true" href="/install-options"><span title="Installation" class="categoryLinkLabel_W154">Installation</span></a></div><ul class="menu__list"><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-2 menu__list-item"><a class="menu__link" tabindex="0" href="/install-options"><span title="Select an installation method" class="linkLabel_WmDU">Select an installation method</span></a></li><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-2 menu__list-item"><a class="menu__link" tabindex="0" href="/install"><span title="Run the installer script" class="linkLabel_WmDU">Run the installer script</span></a></li><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-2 menu__list-item"><a class="menu__link" tabindex="0" href="/install-uv"><span title="Install OpenRAG with uv" class="linkLabel_WmDU">Install OpenRAG with uv</span></a></li><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-2 menu__list-item"><a class="menu__link" tabindex="0" href="/install-uvx"><span title="Invoke OpenRAG with uvx" class="linkLabel_WmDU">Invoke OpenRAG with uvx</span></a></li><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-2 menu__list-item"><a class="menu__link" tabindex="0" href="/install-windows"><span title="Install OpenRAG on Windows" class="linkLabel_WmDU">Install OpenRAG on Windows</span></a></li><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-2 menu__list-item"><a class="menu__link menu__link--active" aria-current="page" tabindex="0" href="/docker"><span title="Deploy self-managed services" class="linkLabel_WmDU">Deploy self-managed services</span></a></li><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-2 menu__list-item"><a class="menu__link" tabindex="0" href="/upgrade"><span title="Upgrade OpenRAG" class="linkLabel_WmDU">Upgrade OpenRAG</span></a></li><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-2 menu__list-item"><a class="menu__link" tabindex="0" href="/reinstall"><span title="Reinstall OpenRAG" class="linkLabel_WmDU">Reinstall OpenRAG</span></a></li><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-2 menu__list-item"><a class="menu__link" tabindex="0" href="/uninstall"><span title="Remove OpenRAG" class="linkLabel_WmDU">Remove OpenRAG</span></a></li></ul></li><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-1 menu__list-item"><a class="menu__link" href="/tui"><span title="Use the TUI" class="linkLabel_WmDU">Use the TUI</span></a></li><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-1 menu__list-item"><a class="menu__link" href="/manage-services"><span title="Manage services" class="linkLabel_WmDU">Manage services</span></a></li><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-1 menu__list-item"><a class="menu__link" href="/agents"><span title="Flows" class="linkLabel_WmDU">Flows</span></a></li><li class="theme-doc-sidebar-item-category theme-doc-sidebar-item-category-level-1 menu__list-item menu__list-item--collapsed"><div class="menu__list-item-collapsible"><a class="categoryLink_byQd menu__link menu__link--sublist menu__link--sublist-caret" role="button" aria-expanded="false" href="/knowledge"><span title="Knowledge" class="categoryLinkLabel_W154">Knowledge</span></a></div></li><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-1 menu__list-item"><a class="menu__link" href="/chat"><span title="Chat" class="linkLabel_WmDU">Chat</span></a></li><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-1 menu__list-item"><a class="menu__link" href="/reference/configuration"><span title="Environment variables" class="linkLabel_WmDU">Environment variables</span></a></li><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-1 menu__list-item"><a class="menu__link" href="/support/troubleshoot"><span title="Troubleshoot OpenRAG" class="linkLabel_WmDU">Troubleshoot OpenRAG</span></a></li></ul></nav></div></div></aside><main class="docMainContainer_TBSr"><div class="container padding-top--md padding-bottom--lg"><div class="row"><div class="col docItemCol_VOVn"><div class="docItemContainer_Djhp"><article><nav class="theme-doc-breadcrumbs breadcrumbsContainer_Z_bl" aria-label="Breadcrumbs"><ul class="breadcrumbs"><li class="breadcrumbs__item"><a aria-label="Home page" class="breadcrumbs__link" href="/"><svg viewBox="0 0 24 24" class="breadcrumbHomeIcon_YNFT"><path d="M10 19v-5h4v5c0 .55.45 1 1 1h3c.55 0 1-.45 1-1v-7h1.7c.46 0 .68-.57.33-.87L12.67 3.6c-.38-.34-.96-.34-1.34 0l-8.36 7.53c-.34.3-.13.87.33.87H5v7c0 .55.45 1 1 1h3c.55 0 1-.45 1-1z" fill="currentColor"></path></svg></a></li><li class="breadcrumbs__item"><span class="breadcrumbs__link">Installation</span></li><li class="breadcrumbs__item breadcrumbs__item--active"><span class="breadcrumbs__link">Deploy self-managed services</span></li></ul></nav><div class="tocCollapsible_ETCw theme-doc-toc-mobile tocMobile_ITEo"><button type="button" class="clean-btn tocCollapsibleButton_TO0P">On this page</button></div><div class="theme-doc-markdown markdown"><header><h1>Deploy OpenRAG with self-managed services</h1></header><p>To manage your own OpenRAG services, deploy OpenRAG with Docker or Podman.</p>
|
||
<p>Use this installation method if you don't want to <a class="" href="/tui">use the Terminal User Interface (TUI)</a>, or you need to run OpenRAG in an environment where using the TUI is unfeasible.</p>
|
||
<h2 class="anchor anchorTargetStickyNavbar_Vzrq" id="prerequisites">Prerequisites<a href="#prerequisites" class="hash-link" aria-label="Direct link to Prerequisites" title="Direct link to Prerequisites" translate="no"></a></h2>
|
||
<ul>
|
||
<li class="">For Microsoft Windows, you must use the Windows Subsystem for Linux (WSL).
|
||
See <a class="" href="/install-windows">Install OpenRAG on Windows</a> before proceeding.</li>
|
||
</ul>
|
||
<ul>
|
||
<li class="">Install <a href="https://www.python.org/downloads/release/python-3100/" target="_blank" rel="noopener noreferrer" class="">Python</a> version 3.13 or later.</li>
|
||
</ul>
|
||
<ul>
|
||
<li class="">
|
||
<p>Install <a href="https://docs.astral.sh/uv/getting-started/installation/" target="_blank" rel="noopener noreferrer" class="">uv</a>.</p>
|
||
</li>
|
||
<li class="">
|
||
<p>Install <a href="https://podman.io/docs/installation" target="_blank" rel="noopener noreferrer" class="">Podman</a> (recommended) or <a href="https://docs.docker.com/get-docker/" target="_blank" rel="noopener noreferrer" class="">Docker</a>.</p>
|
||
</li>
|
||
<li class="">
|
||
<p>Install <a href="https://docs.podman.io/en/latest/markdown/podman-compose.1.html" target="_blank" rel="noopener noreferrer" class=""><code>podman-compose</code></a> or <a href="https://docs.docker.com/compose/install/" target="_blank" rel="noopener noreferrer" class="">Docker Compose</a>.
|
||
To use Docker Compose with Podman, you must alias Docker Compose commands to Podman commands.</p>
|
||
</li>
|
||
</ul>
|
||
<ul>
|
||
<li class="">
|
||
<p>Gather the credentials and connection details for your preferred model providers.
|
||
You must have access to at least one language model and one embedding model.
|
||
If a provider offers both types, you can use the same provider for both models.
|
||
If a provider offers only one type, you must select two providers.</p>
|
||
<ul>
|
||
<li class="">
|
||
<p><strong>OpenAI</strong>: Create an <a href="https://platform.openai.com/api-keys" target="_blank" rel="noopener noreferrer" class="">OpenAI API key</a>.</p>
|
||
</li>
|
||
<li class="">
|
||
<p><strong>Anthropic</strong>: Create an <a href="https://www.anthropic.com/docs/api/reference" target="_blank" rel="noopener noreferrer" class="">Anthropic API key</a>.
|
||
Anthropic provides language models only; you must select an additional provider for embeddings.</p>
|
||
</li>
|
||
<li class="">
|
||
<p><strong>IBM watsonx.ai</strong>: Get your watsonx.ai API endpoint, IBM project ID, and IBM API key from your watsonx deployment.</p>
|
||
</li>
|
||
<li class="">
|
||
<p><strong>Ollama</strong>: Deploy an <a href="https://docs.ollama.com/" target="_blank" rel="noopener noreferrer" class="">Ollama instance and models</a> locally, in the cloud, or on a remote server. Then, get your Ollama server's base URL and the names of the models that you want to use.</p>
|
||
<div class="theme-admonition theme-admonition-info admonition_xJq3 alert alert--info"><div class="admonitionHeading_Gvgb"><span class="admonitionIcon_Rf37"><svg viewBox="0 0 14 16"><path fill-rule="evenodd" d="M7 2.3c3.14 0 5.7 2.56 5.7 5.7s-2.56 5.7-5.7 5.7A5.71 5.71 0 0 1 1.3 8c0-3.14 2.56-5.7 5.7-5.7zM7 1C3.14 1 0 4.14 0 8s3.14 7 7 7 7-3.14 7-7-3.14-7-7-7zm1 3H6v5h2V4zm0 6H6v2h2v-2z"></path></svg></span>info</div><div class="admonitionContent_BuS1"><p>OpenRAG isn't guaranteed to be compatible with all models that are available through Ollama.
|
||
For example, some models might produce unexpected results, such as JSON-formatted output instead of natural language responses, and some models aren't appropriate for the types of tasks that OpenRAG performs, such as those that generate media.</p>
|
||
<p>The OpenRAG team recommends the following models when using Ollama as your model provider:</p>
|
||
<ul>
|
||
<li class="">
|
||
<p><strong>Language models</strong>: <code>gpt-oss:20b</code> or <code>mistral-nemo:12b</code>.</p>
|
||
<p>If you choose <code>gpt-oss:20b</code>, consider using Ollama Cloud or running Ollama on a remote machine because this model requires at least 16GB of RAM.</p>
|
||
</li>
|
||
<li class="">
|
||
<p><strong>Embedding models</strong>: <a href="https://ollama.com/library/nomic-embed-text" target="_blank" rel="noopener noreferrer" class=""><code>nomic-embed-text:latest</code></a>, <code>mxbai-embed-large:latest</code>, or <code>embeddinggemma:latest</code>.</p>
|
||
</li>
|
||
</ul>
|
||
<p>You can experiment with other models, but if you encounter issues that you are unable to resolve through other RAG best practices (like context filters and prompt engineering), try switching to one of the recommended models.
|
||
You can submit an <a href="https://github.com/langflow-ai/openrag/issues" target="_blank" rel="noopener noreferrer" class="">OpenRAG GitHub issue</a> to request support for specific models.</p></div></div>
|
||
</li>
|
||
</ul>
|
||
</li>
|
||
<li class="">
|
||
<p>Optional: Install GPU support with an NVIDIA GPU, <a href="https://docs.nvidia.com/cuda/" target="_blank" rel="noopener noreferrer" class="">CUDA</a> support, and compatible NVIDIA drivers on the OpenRAG host machine. If you don't have GPU capabilities, OpenRAG provides an alternate CPU-only deployment.</p>
|
||
</li>
|
||
</ul>
|
||
<h2 class="anchor anchorTargetStickyNavbar_Vzrq" id="setup">Prepare your deployment<a href="#setup" class="hash-link" aria-label="Direct link to Prepare your deployment" title="Direct link to Prepare your deployment" translate="no"></a></h2>
|
||
<ol>
|
||
<li class="">
|
||
<p>Clone the OpenRAG repository:</p>
|
||
<div class="language-bash codeBlockContainer_Ckt0 theme-code-block" style="--prism-color:#393A34;--prism-background-color:#f6f8fa"><div class="codeBlockContent_QJqH"><pre tabindex="0" class="prism-code language-bash codeBlock_bY9V thin-scrollbar" style="color:#393A34;background-color:#f6f8fa"><code class="codeBlockLines_e6Vv"><span class="token-line" style="color:#393A34"><span class="token function" style="color:#d73a49">git</span><span class="token plain"> clone https://github.com/langflow-ai/openrag.git</span><br></span></code></pre></div></div>
|
||
</li>
|
||
<li class="">
|
||
<p>Change to the root of the cloned repository:</p>
|
||
<div class="language-bash codeBlockContainer_Ckt0 theme-code-block" style="--prism-color:#393A34;--prism-background-color:#f6f8fa"><div class="codeBlockContent_QJqH"><pre tabindex="0" class="prism-code language-bash codeBlock_bY9V thin-scrollbar" style="color:#393A34;background-color:#f6f8fa"><code class="codeBlockLines_e6Vv"><span class="token-line" style="color:#393A34"><span class="token builtin class-name">cd</span><span class="token plain"> openrag</span><br></span></code></pre></div></div>
|
||
</li>
|
||
<li class="">
|
||
<p>Install dependencies:</p>
|
||
<div class="language-bash codeBlockContainer_Ckt0 theme-code-block" style="--prism-color:#393A34;--prism-background-color:#f6f8fa"><div class="codeBlockContent_QJqH"><pre tabindex="0" class="prism-code language-bash codeBlock_bY9V thin-scrollbar" style="color:#393A34;background-color:#f6f8fa"><code class="codeBlockLines_e6Vv"><span class="token-line" style="color:#393A34"><span class="token plain">uv </span><span class="token function" style="color:#d73a49">sync</span><br></span></code></pre></div></div>
|
||
</li>
|
||
<li class="">
|
||
<p>Create a <code>.env</code> file at the root of the cloned repository.</p>
|
||
<p>You can create an empty file or copy the repository's <a href="https://github.com/langflow-ai/openrag/blob/main/.env.example" target="_blank" rel="noopener noreferrer" class=""><code>.env.example</code></a> file.
|
||
The example file contains some of the <a class="" href="/reference/configuration">OpenRAG environment variables</a> to get you started with configuring your deployment.</p>
|
||
<div class="language-bash codeBlockContainer_Ckt0 theme-code-block" style="--prism-color:#393A34;--prism-background-color:#f6f8fa"><div class="codeBlockContent_QJqH"><pre tabindex="0" class="prism-code language-bash codeBlock_bY9V thin-scrollbar" style="color:#393A34;background-color:#f6f8fa"><code class="codeBlockLines_e6Vv"><span class="token-line" style="color:#393A34"><span class="token function" style="color:#d73a49">cp</span><span class="token plain"> .env.example .env</span><br></span></code></pre></div></div>
|
||
</li>
|
||
<li class="">
|
||
<p>Edit the <code>.env</code> file to configure your deployment using <a class="" href="/reference/configuration">OpenRAG environment variables</a>.
|
||
The OpenRAG Docker Compose files pull values from your <code>.env</code> file to configure the OpenRAG containers.
|
||
The following variables are required or recommended:</p>
|
||
<ul>
|
||
<li class="">
|
||
<p><strong><code>OPENSEARCH_PASSWORD</code> (Required)</strong>: Sets the OpenSearch administrator password. It must adhere to the <a href="https://docs.opensearch.org/latest/security/configuration/demo-configuration/#setting-up-a-custom-admin-password" target="_blank" rel="noopener noreferrer" class="">OpenSearch password complexity requirements</a>.</p>
|
||
</li>
|
||
<li class="">
|
||
<p><strong><code>LANGFLOW_SUPERUSER</code></strong>: The username for the Langflow administrator user. If <code>LANGFLOW_SUPERUSER</code> isn't set, then the default value is <code>admin</code>.</p>
|
||
</li>
|
||
<li class="">
|
||
<p><strong><code>LANGFLOW_SUPERUSER_PASSWORD</code> (Strongly recommended)</strong>: Sets the Langflow administrator password, and determines the Langflow server's default authentication mode. If <code>LANGFLOW_SUPERUSER_PASSWORD</code> isn't set, then the Langflow server starts without authentication enabled. For more information, see <a class="" href="/reference/configuration#langflow-settings">Langflow settings</a>.</p>
|
||
</li>
|
||
<li class="">
|
||
<p><strong><code>LANGFLOW_SECRET_KEY</code> (Strongly recommended)</strong>: A secret encryption key for internal Langflow operations. It is recommended to <a href="https://docs.langflow.org/api-keys-and-authentication#langflow-secret-key" target="_blank" rel="noopener noreferrer" class="">generate your own Langflow secret key</a>. If <code>LANGFLOW_SECRET_KEY</code> isn't set, then Langflow generates a secret key automatically.</p>
|
||
</li>
|
||
<li class="">
|
||
<p><strong>Model provider credentials</strong>: Provide credentials for your preferred model providers. If none of these are set in the <code>.env</code> file, you must configure at least one provider during the <a href="#application-onboarding" class="">application onboarding process</a>.</p>
|
||
<ul>
|
||
<li class=""><code>OPENAI_API_KEY</code></li>
|
||
<li class=""><code>ANTHROPIC_API_KEY</code></li>
|
||
<li class=""><code>OLLAMA_ENDPOINT</code></li>
|
||
<li class=""><code>WATSONX_API_KEY</code></li>
|
||
<li class=""><code>WATSONX_ENDPOINT</code></li>
|
||
<li class=""><code>WATSONX_PROJECT_ID</code></li>
|
||
</ul>
|
||
</li>
|
||
<li class="">
|
||
<p><strong>OAuth provider credentials</strong>: To upload documents from external storage, such as Google Drive, set the required OAuth credentials for the connectors that you want to use. You can <a class="" href="/ingestion#oauth-ingestion">manage OAuth credentials</a> later, but it is recommended to configure them during initial set up so you don't have to rebuild the containers.</p>
|
||
<ul>
|
||
<li class=""><strong>Amazon</strong>: Provide your AWS Access Key ID and AWS Secret Access Key with access to your S3 instance. For more information, see the AWS documentation on <a href="https://docs.aws.amazon.com/singlesignon/latest/userguide/manage-your-applications.html" target="_blank" rel="noopener noreferrer" class="">Configuring access to AWS applications</a>.</li>
|
||
<li class=""><strong>Google</strong>: Provide your Google OAuth Client ID and Google OAuth Client Secret. You can generate these in the <a href="https://console.cloud.google.com/apis/credentials" target="_blank" rel="noopener noreferrer" class="">Google Cloud Console</a>. For more information, see the <a href="https://developers.google.com/identity/protocols/oauth2" target="_blank" rel="noopener noreferrer" class="">Google OAuth client documentation</a>.</li>
|
||
<li class=""><strong>Microsoft</strong>: For the Microsoft OAuth Client ID and Microsoft OAuth Client Secret, provide <a href="https://learn.microsoft.com/en-us/onedrive/developer/rest-api/getting-started/app-registration?view=odsp-graph-online" target="_blank" rel="noopener noreferrer" class="">Azure application registration credentials for SharePoint and OneDrive</a>. For more information, see the <a href="https://learn.microsoft.com/en-us/onedrive/developer/rest-api/getting-started/graph-oauth" target="_blank" rel="noopener noreferrer" class="">Microsoft Graph OAuth client documentation</a>.</li>
|
||
</ul>
|
||
</li>
|
||
</ul>
|
||
<p>For more information and variables, see <a class="" href="/reference/configuration">OpenRAG environment variables</a>.</p>
|
||
</li>
|
||
</ol>
|
||
<h2 class="anchor anchorTargetStickyNavbar_Vzrq" id="start-services">Start services<a href="#start-services" class="hash-link" aria-label="Direct link to Start services" title="Direct link to Start services" translate="no"></a></h2>
|
||
<ol>
|
||
<li class="">
|
||
<p>Start <code>docling serve</code> on port 5001 on the host machine:</p>
|
||
<div class="language-bash codeBlockContainer_Ckt0 theme-code-block" style="--prism-color:#393A34;--prism-background-color:#f6f8fa"><div class="codeBlockContent_QJqH"><pre tabindex="0" class="prism-code language-bash codeBlock_bY9V thin-scrollbar" style="color:#393A34;background-color:#f6f8fa"><code class="codeBlockLines_e6Vv"><span class="token-line" style="color:#393A34"><span class="token plain">uv run python scripts/docling_ctl.py start </span><span class="token parameter variable" style="color:#36acaa">--port</span><span class="token plain"> </span><span class="token number" style="color:#36acaa">5001</span><br></span></code></pre></div></div>
|
||
<p>Docling cannot run inside a Docker container due to system-level dependencies, so you must manage it as a separate service on the host machine.
|
||
For more information, see <a class="" href="/manage-services#start-native-services">Stop, start, and inspect native services</a>.</p>
|
||
<p>This port is required to deploy OpenRAG successfully; don't use a different port.
|
||
Additionally, this enables the <a href="https://opensource.apple.com/projects/mlx/" target="_blank" rel="noopener noreferrer" class="">MLX framework</a> for accelerated performance on Apple Silicon Mac machines.</p>
|
||
</li>
|
||
<li class="">
|
||
<p>Confirm <code>docling serve</code> is running.</p>
|
||
<div class="language-bash codeBlockContainer_Ckt0 theme-code-block" style="--prism-color:#393A34;--prism-background-color:#f6f8fa"><div class="codeBlockContent_QJqH"><pre tabindex="0" class="prism-code language-bash codeBlock_bY9V thin-scrollbar" style="color:#393A34;background-color:#f6f8fa"><code class="codeBlockLines_e6Vv"><span class="token-line" style="color:#393A34"><span class="token plain">uv run python scripts/docling_ctl.py status</span><br></span></code></pre></div></div>
|
||
<p>If <code>docling serve</code> is running, the output includes the status, address, and process ID (PID):</p>
|
||
<div class="language-bash codeBlockContainer_Ckt0 theme-code-block" style="--prism-color:#393A34;--prism-background-color:#f6f8fa"><div class="codeBlockContent_QJqH"><pre tabindex="0" class="prism-code language-bash codeBlock_bY9V thin-scrollbar" style="color:#393A34;background-color:#f6f8fa"><code class="codeBlockLines_e6Vv"><span class="token-line" style="color:#393A34"><span class="token plain">Status: running</span><br></span><span class="token-line" style="color:#393A34"><span class="token plain">Endpoint: http://127.0.0.1:5001</span><br></span><span class="token-line" style="color:#393A34"><span class="token plain">Docs: http://127.0.0.1:5001/docs</span><br></span><span class="token-line" style="color:#393A34"><span class="token plain">PID: </span><span class="token number" style="color:#36acaa">27746</span><br></span></code></pre></div></div>
|
||
</li>
|
||
<li class="">
|
||
<p>Deploy the OpenRAG containers locally using the appropriate Docker Compose file for your environment.
|
||
Both files deploy the same services.</p>
|
||
<ul>
|
||
<li class="">
|
||
<p><a href="https://github.com/langflow-ai/openrag/blob/main/docker-compose.yml" target="_blank" rel="noopener noreferrer" class=""><code>docker-compose.yml</code></a>: If your host machine has an NVIDIA GPU with CUDA support and compatible NVIDIA drivers, you can use this file to deploy OpenRAG with accelerated processing.</p>
|
||
<div class="language-bash codeBlockContainer_Ckt0 theme-code-block" style="--prism-color:#393A34;--prism-background-color:#f6f8fa"><div class="codeBlockTitle_OeMC">Docker</div><div class="codeBlockContent_QJqH"><pre tabindex="0" class="prism-code language-bash codeBlock_bY9V thin-scrollbar" style="color:#393A34;background-color:#f6f8fa"><code class="codeBlockLines_e6Vv"><span class="token-line" style="color:#393A34"><span class="token function" style="color:#d73a49">docker</span><span class="token plain"> compose build</span><br></span><span class="token-line" style="color:#393A34"><span class="token plain"></span><span class="token function" style="color:#d73a49">docker</span><span class="token plain"> compose up </span><span class="token parameter variable" style="color:#36acaa">-d</span><br></span></code></pre></div></div>
|
||
<div class="language-bash codeBlockContainer_Ckt0 theme-code-block" style="--prism-color:#393A34;--prism-background-color:#f6f8fa"><div class="codeBlockTitle_OeMC">Podman</div><div class="codeBlockContent_QJqH"><pre tabindex="0" class="prism-code language-bash codeBlock_bY9V thin-scrollbar" style="color:#393A34;background-color:#f6f8fa"><code class="codeBlockLines_e6Vv"><span class="token-line" style="color:#393A34"><span class="token function" style="color:#d73a49">podman</span><span class="token plain"> compose build</span><br></span><span class="token-line" style="color:#393A34"><span class="token plain"></span><span class="token function" style="color:#d73a49">podman</span><span class="token plain"> compose up </span><span class="token parameter variable" style="color:#36acaa">-d</span><br></span></code></pre></div></div>
|
||
</li>
|
||
<li class="">
|
||
<p><a href="https://github.com/langflow-ai/openrag/blob/main/docker-compose-cpu.yml" target="_blank" rel="noopener noreferrer" class=""><code>docker-compose-cpu.yml</code></a>: If your host machine doesn't have NVIDIA GPU support, use this file for a CPU-only OpenRAG deployment.</p>
|
||
<div class="language-bash codeBlockContainer_Ckt0 theme-code-block" style="--prism-color:#393A34;--prism-background-color:#f6f8fa"><div class="codeBlockTitle_OeMC">Docker</div><div class="codeBlockContent_QJqH"><pre tabindex="0" class="prism-code language-bash codeBlock_bY9V thin-scrollbar" style="color:#393A34;background-color:#f6f8fa"><code class="codeBlockLines_e6Vv"><span class="token-line" style="color:#393A34"><span class="token function" style="color:#d73a49">docker</span><span class="token plain"> compose </span><span class="token parameter variable" style="color:#36acaa">-f</span><span class="token plain"> docker-compose-cpu.yml up </span><span class="token parameter variable" style="color:#36acaa">-d</span><br></span></code></pre></div></div>
|
||
<div class="language-bash codeBlockContainer_Ckt0 theme-code-block" style="--prism-color:#393A34;--prism-background-color:#f6f8fa"><div class="codeBlockTitle_OeMC">Podman</div><div class="codeBlockContent_QJqH"><pre tabindex="0" class="prism-code language-bash codeBlock_bY9V thin-scrollbar" style="color:#393A34;background-color:#f6f8fa"><code class="codeBlockLines_e6Vv"><span class="token-line" style="color:#393A34"><span class="token function" style="color:#d73a49">podman</span><span class="token plain"> compose </span><span class="token parameter variable" style="color:#36acaa">-f</span><span class="token plain"> docker-compose-cpu.yml up </span><span class="token parameter variable" style="color:#36acaa">-d</span><br></span></code></pre></div></div>
|
||
</li>
|
||
</ul>
|
||
</li>
|
||
<li class="">
|
||
<p>Wait for the OpenRAG containers to start, and then confirm that all containers are running:</p>
|
||
<div class="language-bash codeBlockContainer_Ckt0 theme-code-block" style="--prism-color:#393A34;--prism-background-color:#f6f8fa"><div class="codeBlockTitle_OeMC">Docker</div><div class="codeBlockContent_QJqH"><pre tabindex="0" class="prism-code language-bash codeBlock_bY9V thin-scrollbar" style="color:#393A34;background-color:#f6f8fa"><code class="codeBlockLines_e6Vv"><span class="token-line" style="color:#393A34"><span class="token function" style="color:#d73a49">docker</span><span class="token plain"> compose </span><span class="token function" style="color:#d73a49">ps</span><br></span></code></pre></div></div>
|
||
<div class="language-bash codeBlockContainer_Ckt0 theme-code-block" style="--prism-color:#393A34;--prism-background-color:#f6f8fa"><div class="codeBlockTitle_OeMC">Podman</div><div class="codeBlockContent_QJqH"><pre tabindex="0" class="prism-code language-bash codeBlock_bY9V thin-scrollbar" style="color:#393A34;background-color:#f6f8fa"><code class="codeBlockLines_e6Vv"><span class="token-line" style="color:#393A34"><span class="token function" style="color:#d73a49">podman</span><span class="token plain"> compose </span><span class="token function" style="color:#d73a49">ps</span><br></span></code></pre></div></div>
|
||
<p>The OpenRAG Docker Compose files deploy the following containers:</p>
|
||
<table><thead><tr><th>Container Name</th><th>Default address</th><th>Purpose</th></tr></thead><tbody><tr><td>OpenRAG Backend</td><td><a href="http://localhost:8000" target="_blank" rel="noopener noreferrer" class="">http://localhost:8000</a></td><td>FastAPI server and core functionality.</td></tr><tr><td>OpenRAG Frontend</td><td><a href="http://localhost:3000" target="_blank" rel="noopener noreferrer" class="">http://localhost:3000</a></td><td>React web interface for user interaction.</td></tr><tr><td>Langflow</td><td><a href="http://localhost:7860" target="_blank" rel="noopener noreferrer" class="">http://localhost:7860</a></td><td><a class="" href="/agents">AI workflow engine</a>.</td></tr><tr><td>OpenSearch</td><td><a href="http://localhost:9200" target="_blank" rel="noopener noreferrer" class="">http://localhost:9200</a></td><td>Datastore for <a class="" href="/knowledge">knowledge</a>.</td></tr><tr><td>OpenSearch Dashboards</td><td><a href="http://localhost:5601" target="_blank" rel="noopener noreferrer" class="">http://localhost:5601</a></td><td>OpenSearch database administration interface.</td></tr></tbody></table>
|
||
<p>When the containers are running, you can access your OpenRAG services at their addresses.</p>
|
||
</li>
|
||
<li class="">
|
||
<p>Access the OpenRAG frontend at <code>http://localhost:3000</code>, and then continue with the <a href="#application-onboarding" class="">application onboarding process</a>.</p>
|
||
</li>
|
||
</ol>
|
||
<h2 class="anchor anchorTargetStickyNavbar_Vzrq" id="application-onboarding">Complete the application onboarding process<a href="#application-onboarding" class="hash-link" aria-label="Direct link to Complete the application onboarding process" title="Direct link to Complete the application onboarding process" translate="no"></a></h2>
|
||
<p>The first time you start the OpenRAG application, you must complete the application onboarding process to select language and embedding models that are essential for OpenRAG features like the <a class="" href="/chat"><strong>Chat</strong></a>.</p>
|
||
<p>Some of these variables, such as the embedding models, can be changed seamlessly after onboarding.
|
||
Others are immutable and require you to destroy and recreate the OpenRAG containers.
|
||
For more information, see the <a class="" href="/reference/configuration">OpenRAG environment variables reference</a>.</p>
|
||
<p>You can use different providers for your language model and embedding model, such as Anthropic for the language model and OpenAI for the embedding model.
|
||
Additionally, you can set multiple embedding models.</p>
|
||
<p>You only need to complete onboarding for your preferred providers.</p>
|
||
<div class="theme-tabs-container tabs-container tabList__CuJ"><ul role="tablist" aria-orientation="horizontal" class="tabs"><li role="tab" tabindex="0" aria-selected="true" class="tabs__item tabItem_LNqP tabs__item--active">Anthropic</li><li role="tab" tabindex="-1" aria-selected="false" class="tabs__item tabItem_LNqP">IBM watsonx.ai</li><li role="tab" tabindex="-1" aria-selected="false" class="tabs__item tabItem_LNqP">Ollama</li><li role="tab" tabindex="-1" aria-selected="false" class="tabs__item tabItem_LNqP">OpenAI (default)</li></ul><div class="margin-top--md"><div role="tabpanel" class="tabItem_Ymn6"><div class="theme-admonition theme-admonition-info admonition_xJq3 alert alert--info"><div class="admonitionHeading_Gvgb"><span class="admonitionIcon_Rf37"><svg viewBox="0 0 14 16"><path fill-rule="evenodd" d="M7 2.3c3.14 0 5.7 2.56 5.7 5.7s-2.56 5.7-5.7 5.7A5.71 5.71 0 0 1 1.3 8c0-3.14 2.56-5.7 5.7-5.7zM7 1C3.14 1 0 4.14 0 8s3.14 7 7 7 7-3.14 7-7-3.14-7-7-7zm1 3H6v5h2V4zm0 6H6v2h2v-2z"></path></svg></span>info</div><div class="admonitionContent_BuS1"><p>Anthropic doesn't provide embedding models. If you select Anthropic for your language model, you must select a different provider for the embedding model.</p></div></div><ol>
|
||
<li class="">
|
||
<p>Enter your Anthropic API key, or enable <strong>Get API key from environment variable</strong> to pull the key from your <a class="" href="/reference/configuration">OpenRAG <code>.env</code> file</a>.</p>
|
||
<p>If you set <code>ANTHROPIC_API_KEY</code> in your OpenRAG <code>.env</code> file, this value can be populated automatically.</p>
|
||
</li>
|
||
<li class="">
|
||
<p>Under <strong>Advanced settings</strong>, select the language model that you want to use.</p>
|
||
</li>
|
||
<li class="">
|
||
<p>Click <strong>Complete</strong>.</p>
|
||
</li>
|
||
<li class="">
|
||
<p>Select a provider for embeddings, provide the required information, and then select the embedding model you want to use.
|
||
For information about another provider's credentials and settings, see the instructions for that provider.</p>
|
||
</li>
|
||
<li class="">
|
||
<p>Click <strong>Complete</strong>.</p>
|
||
<p>After you configure the embedding model, OpenRAG uses your credentials and models to ingest some <a class="" href="/knowledge#default-documents">initial documents</a>. This tests the connection, and it allows you to ask OpenRAG about itself in the <a class="" href="/chat"><strong>Chat</strong></a>.
|
||
If there is a problem with the model configuration, an error occurs and you are redirected back to the application onboarding screen.
|
||
Verify that the credential is valid and has access to the selected model, and then click <strong>Complete</strong> to retry ingestion.</p>
|
||
</li>
|
||
<li class="">
|
||
<p>Continue through the overview slides for a brief introduction to OpenRAG, or click <svg xmlns="http://www.w3.org/2000/svg" width="24" height="24" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-arrow-right" aria-hidden="true"><path d="M5 12h14"></path><path d="m12 5 7 7-7 7"></path></svg> <strong>Skip overview</strong>.
|
||
The overview demonstrates some basic functionality that is covered in the <a class="" href="/quickstart#chat-with-documents">quickstart</a> and in other parts of the OpenRAG documentation.</p>
|
||
</li>
|
||
</ol></div><div role="tabpanel" class="tabItem_Ymn6" hidden=""><ol>
|
||
<li class="">
|
||
<p>Use the values from your IBM watsonx deployment for the <strong>watsonx.ai API Endpoint</strong>, <strong>IBM Project ID</strong>, and <strong>IBM API key</strong> fields.</p>
|
||
<p>If you set <code>WATSONX_API_KEY</code>, <code>WATSONX_API_URL</code>, or <code>WATSONX_PROJECT_ID</code> in your <a class="" href="/reference/configuration">OpenRAG <code>.env</code> file</a>, these values can be populated automatically.</p>
|
||
</li>
|
||
<li class="">
|
||
<p>Under <strong>Advanced settings</strong>, select the language model that you want to use.</p>
|
||
</li>
|
||
<li class="">
|
||
<p>Click <strong>Complete</strong>.</p>
|
||
</li>
|
||
<li class="">
|
||
<p>Select a provider for embeddings, provide the required information, and then select the embedding model you want to use.
|
||
For information about another provider's credentials and settings, see the instructions for that provider.</p>
|
||
</li>
|
||
<li class="">
|
||
<p>Click <strong>Complete</strong>.</p>
|
||
<p>After you configure the embedding model, OpenRAG uses your credentials and models to ingest some <a class="" href="/knowledge#default-documents">initial documents</a>. This tests the connection, and it allows you to ask OpenRAG about itself in the <a class="" href="/chat"><strong>Chat</strong></a>.
|
||
If there is a problem with the model configuration, an error occurs and you are redirected back to the application onboarding screen.
|
||
Verify that the credentials are valid and have access to the selected model, and then click <strong>Complete</strong> to retry ingestion.</p>
|
||
</li>
|
||
<li class="">
|
||
<p>Continue through the overview slides for a brief introduction to OpenRAG, or click <svg xmlns="http://www.w3.org/2000/svg" width="24" height="24" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-arrow-right" aria-hidden="true"><path d="M5 12h14"></path><path d="m12 5 7 7-7 7"></path></svg> <strong>Skip overview</strong>.
|
||
The overview demonstrates some basic functionality that is covered in the <a class="" href="/quickstart#chat-with-documents">quickstart</a> and in other parts of the OpenRAG documentation.</p>
|
||
</li>
|
||
</ol></div><div role="tabpanel" class="tabItem_Ymn6" hidden=""><p>Using Ollama as your language and embedding model provider offers greater flexibility and configuration options for hosting models.
|
||
However, it requires additional setup because Ollama isn't included with OpenRAG.
|
||
You must deploy Ollama separately if you want to use Ollama as a model provider.</p><div class="theme-admonition theme-admonition-info admonition_xJq3 alert alert--info"><div class="admonitionHeading_Gvgb"><span class="admonitionIcon_Rf37"><svg viewBox="0 0 14 16"><path fill-rule="evenodd" d="M7 2.3c3.14 0 5.7 2.56 5.7 5.7s-2.56 5.7-5.7 5.7A5.71 5.71 0 0 1 1.3 8c0-3.14 2.56-5.7 5.7-5.7zM7 1C3.14 1 0 4.14 0 8s3.14 7 7 7 7-3.14 7-7-3.14-7-7-7zm1 3H6v5h2V4zm0 6H6v2h2v-2z"></path></svg></span>info</div><div class="admonitionContent_BuS1"><p>OpenRAG isn't guaranteed to be compatible with all models that are available through Ollama.
|
||
For example, some models might produce unexpected results, such as JSON-formatted output instead of natural language responses, and some models aren't appropriate for the types of tasks that OpenRAG performs, such as those that generate media.</p>
|
||
<p>The OpenRAG team recommends the following models when using Ollama as your model provider:</p>
|
||
<ul>
|
||
<li class="">
|
||
<p><strong>Language models</strong>: <code>gpt-oss:20b</code> or <code>mistral-nemo:12b</code>.</p>
|
||
<p>If you choose <code>gpt-oss:20b</code>, consider using Ollama Cloud or running Ollama on a remote machine because this model requires at least 16GB of RAM.</p>
|
||
</li>
|
||
<li class="">
|
||
<p><strong>Embedding models</strong>: <a href="https://ollama.com/library/nomic-embed-text" target="_blank" rel="noopener noreferrer" class=""><code>nomic-embed-text:latest</code></a>, <code>mxbai-embed-large:latest</code>, or <code>embeddinggemma:latest</code>.</p>
|
||
</li>
|
||
</ul>
|
||
<p>You can experiment with other models, but if you encounter issues that you are unable to resolve through other RAG best practices (like context filters and prompt engineering), try switching to one of the recommended models.
|
||
You can submit an <a href="https://github.com/langflow-ai/openrag/issues" target="_blank" rel="noopener noreferrer" class="">OpenRAG GitHub issue</a> to request support for specific models.</p></div></div><ol>
|
||
<li class="">
|
||
<p><a href="https://docs.ollama.com/" target="_blank" rel="noopener noreferrer" class="">Install Ollama locally or on a remote server</a>, or <a href="https://docs.ollama.com/cloud" target="_blank" rel="noopener noreferrer" class="">run models in Ollama Cloud</a>.</p>
|
||
<p>If you are running a remote server, it must be accessible from your OpenRAG deployment.</p>
|
||
</li>
|
||
<li class="">
|
||
<p>In OpenRAG onboarding, connect to your Ollama server:</p>
|
||
<ul>
|
||
<li class=""><strong>Local Ollama server</strong>: Enter your Ollama server's base URL and port. The default Ollama server address is <code>http://localhost:11434</code>.</li>
|
||
<li class=""><strong>Ollama Cloud</strong>: Because Ollama Cloud models run at the same address as a local Ollama server and automatically offload to Ollama's cloud service, you can use the same base URL and port as you would for a local Ollama server. The default address is <code>http://localhost:11434</code>.</li>
|
||
<li class=""><strong>Remote server</strong>: Enter your remote Ollama server's base URL and port, such as <code>http://your-remote-server:11434</code>.</li>
|
||
</ul>
|
||
<p>If the connection succeeds, OpenRAG populates the model lists with the server's available models.</p>
|
||
</li>
|
||
<li class="">
|
||
<p>Select the model that your Ollama server is running.</p>
|
||
<p>Language model and embedding model selections are independent.
|
||
You can use the same or different servers for each model.</p>
|
||
<p>To use different providers for each model, you must configure both providers, and select the relevant model for each provider.</p>
|
||
</li>
|
||
<li class="">
|
||
<p>Click <strong>Complete</strong>.</p>
|
||
<p>After you configure the embedding model, OpenRAG uses the address and models to ingest some <a class="" href="/knowledge#default-documents">initial documents</a>. This tests the connection, and it allows you to ask OpenRAG about itself in the <a class="" href="/chat"><strong>Chat</strong></a>.
|
||
If there is a problem with the model configuration, an error occurs and you are redirected back to the application onboarding screen.
|
||
Verify that the server address is valid, and that the selected model is running on the server.
|
||
Then, click <strong>Complete</strong> to retry ingestion.</p>
|
||
</li>
|
||
<li class="">
|
||
<p>Continue through the overview slides for a brief introduction to OpenRAG, or click <svg xmlns="http://www.w3.org/2000/svg" width="24" height="24" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-arrow-right" aria-hidden="true"><path d="M5 12h14"></path><path d="m12 5 7 7-7 7"></path></svg> <strong>Skip overview</strong>.
|
||
The overview demonstrates some basic functionality that is covered in the <a class="" href="/quickstart#chat-with-documents">quickstart</a> and in other parts of the OpenRAG documentation.</p>
|
||
</li>
|
||
</ol></div><div role="tabpanel" class="tabItem_Ymn6" hidden=""><ol>
|
||
<li class="">
|
||
<p>Enter your OpenAI API key, or enable <strong>Get API key from environment variable</strong> to pull the key from your <a class="" href="/reference/configuration">OpenRAG <code>.env</code> file</a>.</p>
|
||
<p>If you set <code>OPENAI_API_KEY</code> in your OpenRAG <code>.env</code> file, this value can be populated automatically.</p>
|
||
</li>
|
||
<li class="">
|
||
<p>Under <strong>Advanced settings</strong>, select the language model that you want to use.</p>
|
||
</li>
|
||
<li class="">
|
||
<p>Click <strong>Complete</strong>.</p>
|
||
</li>
|
||
<li class="">
|
||
<p>Select a provider for embeddings, provide the required information, and then select the embedding model you want to use.
|
||
For information about another provider's credentials and settings, see the instructions for that provider.</p>
|
||
</li>
|
||
<li class="">
|
||
<p>Click <strong>Complete</strong>.</p>
|
||
<p>After you configure the embedding model, OpenRAG uses your credentials and models to ingest some <a class="" href="/knowledge#default-documents">initial documents</a>. This tests the connection, and it allows you to ask OpenRAG about itself in the <a class="" href="/chat"><strong>Chat</strong></a>.
|
||
If there is a problem with the model configuration, an error occurs and you are redirected back to the application onboarding screen.
|
||
Verify that the credential is valid and has access to the selected model, and then click <strong>Complete</strong> to retry ingestion.</p>
|
||
</li>
|
||
<li class="">
|
||
<p>Continue through the overview slides for a brief introduction to OpenRAG, or click <svg xmlns="http://www.w3.org/2000/svg" width="24" height="24" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-arrow-right" aria-hidden="true"><path d="M5 12h14"></path><path d="m12 5 7 7-7 7"></path></svg> <strong>Skip overview</strong>.
|
||
The overview demonstrates some basic functionality that is covered in the <a class="" href="/quickstart#chat-with-documents">quickstart</a> and in other parts of the OpenRAG documentation.</p>
|
||
</li>
|
||
</ol></div></div></div>
|
||
<h2 class="anchor anchorTargetStickyNavbar_Vzrq" id="next-steps">Next steps<a href="#next-steps" class="hash-link" aria-label="Direct link to Next steps" title="Direct link to Next steps" translate="no"></a></h2>
|
||
<ul>
|
||
<li class="">Try some of OpenRAG's core features in the <a class="" href="/quickstart#chat-with-documents">quickstart</a>.</li>
|
||
<li class="">Learn how to <a class="" href="/manage-services">manage OpenRAG services</a>.</li>
|
||
<li class=""><a class="" href="/ingestion">Upload documents</a>, and then use the <a class="" href="/chat"><strong>Chat</strong></a> to explore your data.</li>
|
||
</ul></div><footer class="theme-doc-footer docusaurus-mt-lg"><div class="row margin-top--sm theme-doc-footer-edit-meta-row"><div class="col noPrint_WFHX"><a href="https://github.com/openrag/openrag/tree/main/docs/docs/get-started/docker.mdx" target="_blank" rel="noopener noreferrer" class="theme-edit-this-page"><svg fill="currentColor" height="20" width="20" viewBox="0 0 40 40" class="iconEdit_Z9Sw" aria-hidden="true"><g><path d="m34.5 11.7l-3 3.1-6.3-6.3 3.1-3q0.5-0.5 1.2-0.5t1.1 0.5l3.9 3.9q0.5 0.4 0.5 1.1t-0.5 1.2z m-29.5 17.1l18.4-18.5 6.3 6.3-18.4 18.4h-6.3v-6.2z"></path></g></svg>Edit this page</a></div><div class="col lastUpdated_JAkA"></div></div></footer></article><nav class="docusaurus-mt-lg pagination-nav" aria-label="Docs pages"><a class="pagination-nav__link pagination-nav__link--prev" href="/install-windows"><div class="pagination-nav__sublabel">Previous</div><div class="pagination-nav__label">Install OpenRAG on Windows</div></a><a class="pagination-nav__link pagination-nav__link--next" href="/upgrade"><div class="pagination-nav__sublabel">Next</div><div class="pagination-nav__label">Upgrade OpenRAG</div></a></nav></div></div><div class="col col--3"><div class="tableOfContents_bqdL thin-scrollbar theme-doc-toc-desktop"><ul class="table-of-contents table-of-contents__left-border"><li><a href="#prerequisites" class="table-of-contents__link toc-highlight">Prerequisites</a></li><li><a href="#setup" class="table-of-contents__link toc-highlight">Prepare your deployment</a></li><li><a href="#start-services" class="table-of-contents__link toc-highlight">Start services</a></li><li><a href="#application-onboarding" class="table-of-contents__link toc-highlight">Complete the application onboarding process</a></li><li><a href="#next-steps" class="table-of-contents__link toc-highlight">Next steps</a></li></ul></div></div></div></div></main></div></div></div><footer class="theme-layout-footer footer"><div class="container container-fluid"><div class="row footer__links"><div class="theme-layout-footer-column col footer__col"><div class="footer__title"></div><ul class="footer__items clean-list"><li class="footer__item"><div class="footer-links">
|
||
<span>© 2025 OpenRAG</span>
|
||
</div></li></ul></div></div></div></footer></div>
|
||
</body>
|
||
</html> |