deploy: 0bc7d57063
This commit is contained in:
aimurphy
parent
7c8450169a
commit
0fc850040b
32 changed files with 215 additions and 60 deletions
2
404.html
2
404.html
|
|
@ -4,7 +4,7 @@
|
|||
<meta charset="UTF-8">
|
||||
<meta name="generator" content="Docusaurus v3.9.2">
|
||||
<title data-rh="true">OpenRAG</title><meta data-rh="true" property="og:title" content="OpenRAG"><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/404.html"><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"><link data-rh="true" rel="icon" href="/img/favicon.ico"><link data-rh="true" rel="canonical" href="https://docs.openr.ag/404.html"><link data-rh="true" rel="alternate" href="https://docs.openr.ag/404.html" hreflang="en"><link data-rh="true" rel="alternate" href="https://docs.openr.ag/404.html" hreflang="x-default"><link rel="stylesheet" href="/assets/css/styles.66669ecc.css">
|
||||
<script src="/assets/js/runtime~main.732f6967.js" defer="defer"></script>
|
||||
<script src="/assets/js/runtime~main.28b5001d.js" defer="defer"></script>
|
||||
<script src="/assets/js/main.b10c6137.js" defer="defer"></script>
|
||||
</head>
|
||||
<body class="navigation-with-keyboard">
|
||||
|
|
|
|||
|
|
@ -4,7 +4,7 @@
|
|||
<meta charset="UTF-8">
|
||||
<meta name="generator" content="Docusaurus v3.9.2">
|
||||
<title data-rh="true">Use Langflow in OpenRAG | 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/agents"><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="Use Langflow in OpenRAG | OpenRAG"><meta data-rh="true" name="description" content="OpenRAG includes a built-in Langflow instance for creating and managing functional application workflows called flows."><meta data-rh="true" property="og:description" content="OpenRAG includes a built-in Langflow instance for creating and managing functional application workflows called flows."><link data-rh="true" rel="icon" href="/img/favicon.ico"><link data-rh="true" rel="canonical" href="https://docs.openr.ag/agents"><link data-rh="true" rel="alternate" href="https://docs.openr.ag/agents" hreflang="en"><link data-rh="true" rel="alternate" href="https://docs.openr.ag/agents" hreflang="x-default"><script data-rh="true" type="application/ld+json">{"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Flows","item":"https://docs.openr.ag/agents"}]}</script><link rel="stylesheet" href="/assets/css/styles.66669ecc.css">
|
||||
<script src="/assets/js/runtime~main.732f6967.js" defer="defer"></script>
|
||||
<script src="/assets/js/runtime~main.28b5001d.js" defer="defer"></script>
|
||||
<script src="/assets/js/main.b10c6137.js" defer="defer"></script>
|
||||
</head>
|
||||
<body class="navigation-with-keyboard">
|
||||
|
|
|
|||
File diff suppressed because one or more lines are too long
1
assets/js/441f609b.ae58055a.js
Normal file
1
assets/js/441f609b.ae58055a.js
Normal file
File diff suppressed because one or more lines are too long
1
assets/js/4ba45368.1fce6090.js
Normal file
1
assets/js/4ba45368.1fce6090.js
Normal file
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
1
assets/js/749371cc.774b6a0c.js
Normal file
1
assets/js/749371cc.774b6a0c.js
Normal file
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
1
assets/js/d0314b07.ebf2fdd5.js
Normal file
1
assets/js/d0314b07.ebf2fdd5.js
Normal file
File diff suppressed because one or more lines are too long
1
assets/js/eb5b356a.d35eda0a.js
Normal file
1
assets/js/eb5b356a.d35eda0a.js
Normal file
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
|
|
@ -4,7 +4,7 @@
|
|||
<meta charset="UTF-8">
|
||||
<meta name="generator" content="Docusaurus v3.9.2">
|
||||
<title data-rh="true">Chat in OpenRAG | 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/chat"><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="Chat in OpenRAG | OpenRAG"><meta data-rh="true" name="description" content="After you upload documents to your knowledge base, you can use the OpenRAG Chat feature to interact with your knowledge through natural language queries."><meta data-rh="true" property="og:description" content="After you upload documents to your knowledge base, you can use the OpenRAG Chat feature to interact with your knowledge through natural language queries."><link data-rh="true" rel="icon" href="/img/favicon.ico"><link data-rh="true" rel="canonical" href="https://docs.openr.ag/chat"><link data-rh="true" rel="alternate" href="https://docs.openr.ag/chat" hreflang="en"><link data-rh="true" rel="alternate" href="https://docs.openr.ag/chat" hreflang="x-default"><script data-rh="true" type="application/ld+json">{"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Chat","item":"https://docs.openr.ag/chat"}]}</script><link rel="stylesheet" href="/assets/css/styles.66669ecc.css">
|
||||
<script src="/assets/js/runtime~main.732f6967.js" defer="defer"></script>
|
||||
<script src="/assets/js/runtime~main.28b5001d.js" defer="defer"></script>
|
||||
<script src="/assets/js/main.b10c6137.js" defer="defer"></script>
|
||||
</head>
|
||||
<body class="navigation-with-keyboard">
|
||||
|
|
|
|||
|
|
@ -4,7 +4,7 @@
|
|||
<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.732f6967.js" defer="defer"></script>
|
||||
<script src="/assets/js/runtime~main.28b5001d.js" defer="defer"></script>
|
||||
<script src="/assets/js/main.b10c6137.js" defer="defer"></script>
|
||||
</head>
|
||||
<body class="navigation-with-keyboard">
|
||||
|
|
@ -40,11 +40,33 @@ 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=""><strong>OpenAI</strong>: Create an <a href="https://platform.openai.com/api-keys" target="_blank" rel="noopener noreferrer" class="">OpenAI API key</a>.</li>
|
||||
<li class=""><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.</li>
|
||||
<li class=""><strong>IBM watsonx.ai</strong>: Get your watsonx.ai API endpoint, IBM project ID, and IBM API key from your watsonx deployment.</li>
|
||||
<li class=""><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, and then get your Ollama server's base URL and the names of the models that you want to use.</li>
|
||||
<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="">
|
||||
|
|
@ -213,9 +235,22 @@ Verify that the credentials are valid and have access to the selected model, and
|
|||
<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=""><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>Ollama isn't installed with OpenRAG. You must install it separately if you want to use Ollama as a model provider.</p></div></div><p>Using Ollama as your language and embedding model provider offers greater flexibility and configuration options for hosting models, but it can be advanced for new users.
|
||||
The recommendations given here are a reasonable starting point for users with at least one GPU and experience running LLMs locally.</p><p>The OpenRAG team recommends the OpenAI <code>gpt-oss:20b</code> lanuage model and the <a href="https://ollama.com/library/nomic-embed-text" target="_blank" rel="noopener noreferrer" class=""><code>nomic-embed-text</code></a> embedding model.
|
||||
However, <code>gpt-oss:20b</code> uses 16GB of RAM, so consider using Ollama Cloud or running Ollama on a remote machine.</p><ol>
|
||||
</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>
|
||||
|
|
|
|||
|
|
@ -4,7 +4,7 @@
|
|||
<meta charset="UTF-8">
|
||||
<meta name="generator" content="Docusaurus v3.9.2">
|
||||
<title data-rh="true">What is OpenRAG? | 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/"><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="What is OpenRAG? | OpenRAG"><meta data-rh="true" name="description" content="OpenRAG is an open-source package for building agentic RAG systems that integrates with a wide range of orchestration tools, databases, and LLM providers."><meta data-rh="true" property="og:description" content="OpenRAG is an open-source package for building agentic RAG systems that integrates with a wide range of orchestration tools, databases, and LLM providers."><link data-rh="true" rel="icon" href="/img/favicon.ico"><link data-rh="true" rel="canonical" href="https://docs.openr.ag/"><link data-rh="true" rel="alternate" href="https://docs.openr.ag/" hreflang="en"><link data-rh="true" rel="alternate" href="https://docs.openr.ag/" hreflang="x-default"><script data-rh="true">function insertBanner(){var n=document.createElement("div");n.id="__docusaurus-base-url-issue-banner-container";n.innerHTML='\n<div id="__docusaurus-base-url-issue-banner" style="border: thick solid red; background-color: rgb(255, 230, 179); margin: 20px; padding: 20px; font-size: 20px;">\n <p style="font-weight: bold; font-size: 30px;">Your Docusaurus site did not load properly.</p>\n <p>A very common reason is a wrong site <a href="https://docusaurus.io/docs/docusaurus.config.js/#baseUrl" style="font-weight: bold;">baseUrl configuration</a>.</p>\n <p>Current configured baseUrl = <span style="font-weight: bold; color: red;">/</span> (default value)</p>\n <p>We suggest trying baseUrl = <span id="__docusaurus-base-url-issue-banner-suggestion-container" style="font-weight: bold; color: green;"></span></p>\n</div>\n',document.body.prepend(n);var e=document.getElementById("__docusaurus-base-url-issue-banner-suggestion-container"),s=window.location.pathname,o="/"===s.substr(-1)?s:s+"/";e.innerHTML=o}document.addEventListener("DOMContentLoaded",function(){void 0===window.docusaurus&&insertBanner()})</script><script data-rh="true" type="application/ld+json">{"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"About OpenRAG","item":"https://docs.openr.ag/"}]}</script><link rel="stylesheet" href="/assets/css/styles.66669ecc.css">
|
||||
<script src="/assets/js/runtime~main.732f6967.js" defer="defer"></script>
|
||||
<script src="/assets/js/runtime~main.28b5001d.js" defer="defer"></script>
|
||||
<script src="/assets/js/main.b10c6137.js" defer="defer"></script>
|
||||
</head>
|
||||
<body class="navigation-with-keyboard">
|
||||
|
|
|
|||
|
|
@ -4,7 +4,7 @@
|
|||
<meta charset="UTF-8">
|
||||
<meta name="generator" content="Docusaurus v3.9.2">
|
||||
<title data-rh="true">Ingest knowledge | 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/ingestion"><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="Ingest knowledge | OpenRAG"><meta data-rh="true" name="description" content="Upload documents to your OpenRAG OpenSearch instance to populate your knowledge base with unique content, such as your own company documents, research papers, or websites."><meta data-rh="true" property="og:description" content="Upload documents to your OpenRAG OpenSearch instance to populate your knowledge base with unique content, such as your own company documents, research papers, or websites."><link data-rh="true" rel="icon" href="/img/favicon.ico"><link data-rh="true" rel="canonical" href="https://docs.openr.ag/ingestion"><link data-rh="true" rel="alternate" href="https://docs.openr.ag/ingestion" hreflang="en"><link data-rh="true" rel="alternate" href="https://docs.openr.ag/ingestion" hreflang="x-default"><script data-rh="true" type="application/ld+json">{"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Ingest knowledge","item":"https://docs.openr.ag/ingestion"}]}</script><link rel="stylesheet" href="/assets/css/styles.66669ecc.css">
|
||||
<script src="/assets/js/runtime~main.732f6967.js" defer="defer"></script>
|
||||
<script src="/assets/js/runtime~main.28b5001d.js" defer="defer"></script>
|
||||
<script src="/assets/js/main.b10c6137.js" defer="defer"></script>
|
||||
</head>
|
||||
<body class="navigation-with-keyboard">
|
||||
|
|
|
|||
|
|
@ -4,7 +4,7 @@
|
|||
<meta charset="UTF-8">
|
||||
<meta name="generator" content="Docusaurus v3.9.2">
|
||||
<title data-rh="true">Select an installation method | 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/install-options"><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="Select an installation method | OpenRAG"><meta data-rh="true" name="description" content="The OpenRAG architecture is lightweight and container-based with a central OpenRAG backend that orchestrates the various services and external connectors."><meta data-rh="true" property="og:description" content="The OpenRAG architecture is lightweight and container-based with a central OpenRAG backend that orchestrates the various services and external connectors."><link data-rh="true" rel="icon" href="/img/favicon.ico"><link data-rh="true" rel="canonical" href="https://docs.openr.ag/install-options"><link data-rh="true" rel="alternate" href="https://docs.openr.ag/install-options" hreflang="en"><link data-rh="true" rel="alternate" href="https://docs.openr.ag/install-options" hreflang="x-default"><script data-rh="true" type="application/ld+json">{"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Select an installation method","item":"https://docs.openr.ag/install-options"}]}</script><link rel="stylesheet" href="/assets/css/styles.66669ecc.css">
|
||||
<script src="/assets/js/runtime~main.732f6967.js" defer="defer"></script>
|
||||
<script src="/assets/js/runtime~main.28b5001d.js" defer="defer"></script>
|
||||
<script src="/assets/js/main.b10c6137.js" defer="defer"></script>
|
||||
</head>
|
||||
<body class="navigation-with-keyboard">
|
||||
|
|
|
|||
|
|
@ -4,7 +4,7 @@
|
|||
<meta charset="UTF-8">
|
||||
<meta name="generator" content="Docusaurus v3.9.2">
|
||||
<title data-rh="true">Install OpenRAG in a Python project with uv | 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/install-uv"><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="Install OpenRAG in a Python project with uv | OpenRAG"><meta data-rh="true" name="description" content="Use uv to install OpenRAG as a managed or unmanaged dependency in a new or existing Python project."><meta data-rh="true" property="og:description" content="Use uv to install OpenRAG as a managed or unmanaged dependency in a new or existing Python project."><link data-rh="true" rel="icon" href="/img/favicon.ico"><link data-rh="true" rel="canonical" href="https://docs.openr.ag/install-uv"><link data-rh="true" rel="alternate" href="https://docs.openr.ag/install-uv" hreflang="en"><link data-rh="true" rel="alternate" href="https://docs.openr.ag/install-uv" hreflang="x-default"><script data-rh="true" type="application/ld+json">{"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Install OpenRAG with uv","item":"https://docs.openr.ag/install-uv"}]}</script><link rel="stylesheet" href="/assets/css/styles.66669ecc.css">
|
||||
<script src="/assets/js/runtime~main.732f6967.js" defer="defer"></script>
|
||||
<script src="/assets/js/runtime~main.28b5001d.js" defer="defer"></script>
|
||||
<script src="/assets/js/main.b10c6137.js" defer="defer"></script>
|
||||
</head>
|
||||
<body class="navigation-with-keyboard">
|
||||
|
|
@ -41,11 +41,33 @@ 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=""><strong>OpenAI</strong>: Create an <a href="https://platform.openai.com/api-keys" target="_blank" rel="noopener noreferrer" class="">OpenAI API key</a>.</li>
|
||||
<li class=""><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.</li>
|
||||
<li class=""><strong>IBM watsonx.ai</strong>: Get your watsonx.ai API endpoint, IBM project ID, and IBM API key from your watsonx deployment.</li>
|
||||
<li class=""><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, and then get your Ollama server's base URL and the names of the models that you want to use.</li>
|
||||
<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="">
|
||||
|
|
@ -319,9 +341,22 @@ Verify that the credentials are valid and have access to the selected model, and
|
|||
<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=""><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>Ollama isn't installed with OpenRAG. You must install it separately if you want to use Ollama as a model provider.</p></div></div><p>Using Ollama as your language and embedding model provider offers greater flexibility and configuration options for hosting models, but it can be advanced for new users.
|
||||
The recommendations given here are a reasonable starting point for users with at least one GPU and experience running LLMs locally.</p><p>The OpenRAG team recommends the OpenAI <code>gpt-oss:20b</code> lanuage model and the <a href="https://ollama.com/library/nomic-embed-text" target="_blank" rel="noopener noreferrer" class=""><code>nomic-embed-text</code></a> embedding model.
|
||||
However, <code>gpt-oss:20b</code> uses 16GB of RAM, so consider using Ollama Cloud or running Ollama on a remote machine.</p><ol>
|
||||
</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>
|
||||
|
|
|
|||
|
|
@ -4,7 +4,7 @@
|
|||
<meta charset="UTF-8">
|
||||
<meta name="generator" content="Docusaurus v3.9.2">
|
||||
<title data-rh="true">Invoke OpenRAG with uvx | 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/install-uvx"><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="Invoke OpenRAG with uvx | OpenRAG"><meta data-rh="true" name="description" content="Use uvx to invoke OpenRAG outside of a Python project or without modifying your project's dependencies."><meta data-rh="true" property="og:description" content="Use uvx to invoke OpenRAG outside of a Python project or without modifying your project's dependencies."><link data-rh="true" rel="icon" href="/img/favicon.ico"><link data-rh="true" rel="canonical" href="https://docs.openr.ag/install-uvx"><link data-rh="true" rel="alternate" href="https://docs.openr.ag/install-uvx" hreflang="en"><link data-rh="true" rel="alternate" href="https://docs.openr.ag/install-uvx" hreflang="x-default"><script data-rh="true" type="application/ld+json">{"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Invoke OpenRAG with uvx","item":"https://docs.openr.ag/install-uvx"}]}</script><link rel="stylesheet" href="/assets/css/styles.66669ecc.css">
|
||||
<script src="/assets/js/runtime~main.732f6967.js" defer="defer"></script>
|
||||
<script src="/assets/js/runtime~main.28b5001d.js" defer="defer"></script>
|
||||
<script src="/assets/js/main.b10c6137.js" defer="defer"></script>
|
||||
</head>
|
||||
<body class="navigation-with-keyboard">
|
||||
|
|
@ -43,11 +43,33 @@ 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=""><strong>OpenAI</strong>: Create an <a href="https://platform.openai.com/api-keys" target="_blank" rel="noopener noreferrer" class="">OpenAI API key</a>.</li>
|
||||
<li class=""><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.</li>
|
||||
<li class=""><strong>IBM watsonx.ai</strong>: Get your watsonx.ai API endpoint, IBM project ID, and IBM API key from your watsonx deployment.</li>
|
||||
<li class=""><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, and then get your Ollama server's base URL and the names of the models that you want to use.</li>
|
||||
<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="">
|
||||
|
|
@ -275,9 +297,22 @@ Verify that the credentials are valid and have access to the selected model, and
|
|||
<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=""><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>Ollama isn't installed with OpenRAG. You must install it separately if you want to use Ollama as a model provider.</p></div></div><p>Using Ollama as your language and embedding model provider offers greater flexibility and configuration options for hosting models, but it can be advanced for new users.
|
||||
The recommendations given here are a reasonable starting point for users with at least one GPU and experience running LLMs locally.</p><p>The OpenRAG team recommends the OpenAI <code>gpt-oss:20b</code> lanuage model and the <a href="https://ollama.com/library/nomic-embed-text" target="_blank" rel="noopener noreferrer" class=""><code>nomic-embed-text</code></a> embedding model.
|
||||
However, <code>gpt-oss:20b</code> uses 16GB of RAM, so consider using Ollama Cloud or running Ollama on a remote machine.</p><ol>
|
||||
</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>
|
||||
|
|
|
|||
|
|
@ -4,7 +4,7 @@
|
|||
<meta charset="UTF-8">
|
||||
<meta name="generator" content="Docusaurus v3.9.2">
|
||||
<title data-rh="true">Install OpenRAG on Microsoft Windows | 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/install-windows"><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="Install OpenRAG on Microsoft Windows | OpenRAG"><meta data-rh="true" name="description" content="If you're using Windows, you must install OpenRAG within the Windows Subsystem for Linux (WSL)."><meta data-rh="true" property="og:description" content="If you're using Windows, you must install OpenRAG within the Windows Subsystem for Linux (WSL)."><link data-rh="true" rel="icon" href="/img/favicon.ico"><link data-rh="true" rel="canonical" href="https://docs.openr.ag/install-windows"><link data-rh="true" rel="alternate" href="https://docs.openr.ag/install-windows" hreflang="en"><link data-rh="true" rel="alternate" href="https://docs.openr.ag/install-windows" hreflang="x-default"><script data-rh="true" type="application/ld+json">{"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Install OpenRAG on Windows","item":"https://docs.openr.ag/install-windows"}]}</script><link rel="stylesheet" href="/assets/css/styles.66669ecc.css">
|
||||
<script src="/assets/js/runtime~main.732f6967.js" defer="defer"></script>
|
||||
<script src="/assets/js/runtime~main.28b5001d.js" defer="defer"></script>
|
||||
<script src="/assets/js/main.b10c6137.js" defer="defer"></script>
|
||||
</head>
|
||||
<body class="navigation-with-keyboard">
|
||||
|
|
|
|||
|
|
@ -4,7 +4,7 @@
|
|||
<meta charset="UTF-8">
|
||||
<meta name="generator" content="Docusaurus v3.9.2">
|
||||
<title data-rh="true">Install OpenRAG with the automatic installer script | 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/install"><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="Install OpenRAG with the automatic installer script | OpenRAG"><meta data-rh="true" name="description" content="To quickly install and test OpenRAG's core features, try the quickstart."><meta data-rh="true" property="og:description" content="To quickly install and test OpenRAG's core features, try the quickstart."><link data-rh="true" rel="icon" href="/img/favicon.ico"><link data-rh="true" rel="canonical" href="https://docs.openr.ag/install"><link data-rh="true" rel="alternate" href="https://docs.openr.ag/install" hreflang="en"><link data-rh="true" rel="alternate" href="https://docs.openr.ag/install" hreflang="x-default"><script data-rh="true" type="application/ld+json">{"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Run the installer script","item":"https://docs.openr.ag/install"}]}</script><link rel="stylesheet" href="/assets/css/styles.66669ecc.css">
|
||||
<script src="/assets/js/runtime~main.732f6967.js" defer="defer"></script>
|
||||
<script src="/assets/js/runtime~main.28b5001d.js" defer="defer"></script>
|
||||
<script src="/assets/js/main.b10c6137.js" defer="defer"></script>
|
||||
</head>
|
||||
<body class="navigation-with-keyboard">
|
||||
|
|
@ -32,11 +32,33 @@ 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=""><strong>OpenAI</strong>: Create an <a href="https://platform.openai.com/api-keys" target="_blank" rel="noopener noreferrer" class="">OpenAI API key</a>.</li>
|
||||
<li class=""><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.</li>
|
||||
<li class=""><strong>IBM watsonx.ai</strong>: Get your watsonx.ai API endpoint, IBM project ID, and IBM API key from your watsonx deployment.</li>
|
||||
<li class=""><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, and then get your Ollama server's base URL and the names of the models that you want to use.</li>
|
||||
<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="">
|
||||
|
|
@ -266,9 +288,22 @@ Verify that the credentials are valid and have access to the selected model, and
|
|||
<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=""><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>Ollama isn't installed with OpenRAG. You must install it separately if you want to use Ollama as a model provider.</p></div></div><p>Using Ollama as your language and embedding model provider offers greater flexibility and configuration options for hosting models, but it can be advanced for new users.
|
||||
The recommendations given here are a reasonable starting point for users with at least one GPU and experience running LLMs locally.</p><p>The OpenRAG team recommends the OpenAI <code>gpt-oss:20b</code> lanuage model and the <a href="https://ollama.com/library/nomic-embed-text" target="_blank" rel="noopener noreferrer" class=""><code>nomic-embed-text</code></a> embedding model.
|
||||
However, <code>gpt-oss:20b</code> uses 16GB of RAM, so consider using Ollama Cloud or running Ollama on a remote machine.</p><ol>
|
||||
</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>
|
||||
|
|
|
|||
|
|
@ -4,7 +4,7 @@
|
|||
<meta charset="UTF-8">
|
||||
<meta name="generator" content="Docusaurus v3.9.2">
|
||||
<title data-rh="true">Filter knowledge | 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/knowledge-filters"><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="Filter knowledge | OpenRAG"><meta data-rh="true" name="description" content="OpenRAG's knowledge filters help you organize and manage your knowledge base by creating pre-defined views of your documents."><meta data-rh="true" property="og:description" content="OpenRAG's knowledge filters help you organize and manage your knowledge base by creating pre-defined views of your documents."><link data-rh="true" rel="icon" href="/img/favicon.ico"><link data-rh="true" rel="canonical" href="https://docs.openr.ag/knowledge-filters"><link data-rh="true" rel="alternate" href="https://docs.openr.ag/knowledge-filters" hreflang="en"><link data-rh="true" rel="alternate" href="https://docs.openr.ag/knowledge-filters" hreflang="x-default"><script data-rh="true" type="application/ld+json">{"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Filter knowledge","item":"https://docs.openr.ag/knowledge-filters"}]}</script><link rel="stylesheet" href="/assets/css/styles.66669ecc.css">
|
||||
<script src="/assets/js/runtime~main.732f6967.js" defer="defer"></script>
|
||||
<script src="/assets/js/runtime~main.28b5001d.js" defer="defer"></script>
|
||||
<script src="/assets/js/main.b10c6137.js" defer="defer"></script>
|
||||
</head>
|
||||
<body class="navigation-with-keyboard">
|
||||
|
|
|
|||
|
|
@ -4,7 +4,7 @@
|
|||
<meta charset="UTF-8">
|
||||
<meta name="generator" content="Docusaurus v3.9.2">
|
||||
<title data-rh="true">Configure knowledge | 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/knowledge"><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="Configure knowledge | OpenRAG"><meta data-rh="true" name="description" content="OpenRAG includes a built-in OpenSearch instance that serves as the underlying datastore for your knowledge (documents)."><meta data-rh="true" property="og:description" content="OpenRAG includes a built-in OpenSearch instance that serves as the underlying datastore for your knowledge (documents)."><link data-rh="true" rel="icon" href="/img/favicon.ico"><link data-rh="true" rel="canonical" href="https://docs.openr.ag/knowledge"><link data-rh="true" rel="alternate" href="https://docs.openr.ag/knowledge" hreflang="en"><link data-rh="true" rel="alternate" href="https://docs.openr.ag/knowledge" hreflang="x-default"><script data-rh="true" type="application/ld+json">{"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Configure knowledge","item":"https://docs.openr.ag/knowledge"}]}</script><link rel="stylesheet" href="/assets/css/styles.66669ecc.css">
|
||||
<script src="/assets/js/runtime~main.732f6967.js" defer="defer"></script>
|
||||
<script src="/assets/js/runtime~main.28b5001d.js" defer="defer"></script>
|
||||
<script src="/assets/js/main.b10c6137.js" defer="defer"></script>
|
||||
</head>
|
||||
<body class="navigation-with-keyboard">
|
||||
|
|
|
|||
|
|
@ -4,7 +4,7 @@
|
|||
<meta charset="UTF-8">
|
||||
<meta name="generator" content="Docusaurus v3.9.2">
|
||||
<title data-rh="true">Manage OpenRAG containers and 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/manage-services"><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="Manage OpenRAG containers and services | OpenRAG"><meta data-rh="true" name="description" content="Service management is an essential part of maintaining your OpenRAG deployment."><meta data-rh="true" property="og:description" content="Service management is an essential part of maintaining your OpenRAG deployment."><link data-rh="true" rel="icon" href="/img/favicon.ico"><link data-rh="true" rel="canonical" href="https://docs.openr.ag/manage-services"><link data-rh="true" rel="alternate" href="https://docs.openr.ag/manage-services" hreflang="en"><link data-rh="true" rel="alternate" href="https://docs.openr.ag/manage-services" hreflang="x-default"><script data-rh="true" type="application/ld+json">{"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Manage services","item":"https://docs.openr.ag/manage-services"}]}</script><link rel="stylesheet" href="/assets/css/styles.66669ecc.css">
|
||||
<script src="/assets/js/runtime~main.732f6967.js" defer="defer"></script>
|
||||
<script src="/assets/js/runtime~main.28b5001d.js" defer="defer"></script>
|
||||
<script src="/assets/js/main.b10c6137.js" defer="defer"></script>
|
||||
</head>
|
||||
<body class="navigation-with-keyboard">
|
||||
|
|
|
|||
|
|
@ -4,7 +4,7 @@
|
|||
<meta charset="UTF-8">
|
||||
<meta name="generator" content="Docusaurus v3.9.2">
|
||||
<title data-rh="true">Quickstart | 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/quickstart"><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="Quickstart | OpenRAG"><meta data-rh="true" name="description" content="Use this quickstart to install OpenRAG, and then try some of OpenRAG's core features."><meta data-rh="true" property="og:description" content="Use this quickstart to install OpenRAG, and then try some of OpenRAG's core features."><link data-rh="true" rel="icon" href="/img/favicon.ico"><link data-rh="true" rel="canonical" href="https://docs.openr.ag/quickstart"><link data-rh="true" rel="alternate" href="https://docs.openr.ag/quickstart" hreflang="en"><link data-rh="true" rel="alternate" href="https://docs.openr.ag/quickstart" hreflang="x-default"><script data-rh="true" type="application/ld+json">{"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Quickstart","item":"https://docs.openr.ag/quickstart"}]}</script><link rel="stylesheet" href="/assets/css/styles.66669ecc.css">
|
||||
<script src="/assets/js/runtime~main.732f6967.js" defer="defer"></script>
|
||||
<script src="/assets/js/runtime~main.28b5001d.js" defer="defer"></script>
|
||||
<script src="/assets/js/main.b10c6137.js" defer="defer"></script>
|
||||
</head>
|
||||
<body class="navigation-with-keyboard">
|
||||
|
|
|
|||
|
|
@ -4,7 +4,7 @@
|
|||
<meta charset="UTF-8">
|
||||
<meta name="generator" content="Docusaurus v3.9.2">
|
||||
<title data-rh="true">Environment variables | 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/reference/configuration"><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="Environment variables | OpenRAG"><meta data-rh="true" name="description" content="OpenRAG's .env file is the primary configuration file for OpenRAG."><meta data-rh="true" property="og:description" content="OpenRAG's .env file is the primary configuration file for OpenRAG."><link data-rh="true" rel="icon" href="/img/favicon.ico"><link data-rh="true" rel="canonical" href="https://docs.openr.ag/reference/configuration"><link data-rh="true" rel="alternate" href="https://docs.openr.ag/reference/configuration" hreflang="en"><link data-rh="true" rel="alternate" href="https://docs.openr.ag/reference/configuration" hreflang="x-default"><script data-rh="true" type="application/ld+json">{"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Environment variables","item":"https://docs.openr.ag/reference/configuration"}]}</script><link rel="stylesheet" href="/assets/css/styles.66669ecc.css">
|
||||
<script src="/assets/js/runtime~main.732f6967.js" defer="defer"></script>
|
||||
<script src="/assets/js/runtime~main.28b5001d.js" defer="defer"></script>
|
||||
<script src="/assets/js/main.b10c6137.js" defer="defer"></script>
|
||||
</head>
|
||||
<body class="navigation-with-keyboard">
|
||||
|
|
|
|||
|
|
@ -4,7 +4,7 @@
|
|||
<meta charset="UTF-8">
|
||||
<meta name="generator" content="Docusaurus v3.9.2">
|
||||
<title data-rh="true">Reinstall OpenRAG | 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/reinstall"><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="Reinstall OpenRAG | OpenRAG"><meta data-rh="true" name="description" content="You can reset your OpenRAG deployment to its initial state by recreating the containers and deleting accessory data, such as the .env file and ingested documents."><meta data-rh="true" property="og:description" content="You can reset your OpenRAG deployment to its initial state by recreating the containers and deleting accessory data, such as the .env file and ingested documents."><link data-rh="true" rel="icon" href="/img/favicon.ico"><link data-rh="true" rel="canonical" href="https://docs.openr.ag/reinstall"><link data-rh="true" rel="alternate" href="https://docs.openr.ag/reinstall" hreflang="en"><link data-rh="true" rel="alternate" href="https://docs.openr.ag/reinstall" hreflang="x-default"><script data-rh="true" type="application/ld+json">{"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Reinstall OpenRAG","item":"https://docs.openr.ag/reinstall"}]}</script><link rel="stylesheet" href="/assets/css/styles.66669ecc.css">
|
||||
<script src="/assets/js/runtime~main.732f6967.js" defer="defer"></script>
|
||||
<script src="/assets/js/runtime~main.28b5001d.js" defer="defer"></script>
|
||||
<script src="/assets/js/main.b10c6137.js" defer="defer"></script>
|
||||
</head>
|
||||
<body class="navigation-with-keyboard">
|
||||
|
|
|
|||
|
|
@ -4,7 +4,7 @@
|
|||
<meta charset="UTF-8">
|
||||
<meta name="generator" content="Docusaurus v3.9.2">
|
||||
<title data-rh="true">Troubleshoot OpenRAG | 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/support/troubleshoot"><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="Troubleshoot OpenRAG | OpenRAG"><meta data-rh="true" name="description" content="This page provides troubleshooting advice for issues you might encounter when using OpenRAG or contributing to OpenRAG."><meta data-rh="true" property="og:description" content="This page provides troubleshooting advice for issues you might encounter when using OpenRAG or contributing to OpenRAG."><link data-rh="true" rel="icon" href="/img/favicon.ico"><link data-rh="true" rel="canonical" href="https://docs.openr.ag/support/troubleshoot"><link data-rh="true" rel="alternate" href="https://docs.openr.ag/support/troubleshoot" hreflang="en"><link data-rh="true" rel="alternate" href="https://docs.openr.ag/support/troubleshoot" hreflang="x-default"><script data-rh="true" type="application/ld+json">{"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Troubleshoot OpenRAG","item":"https://docs.openr.ag/support/troubleshoot"}]}</script><link rel="stylesheet" href="/assets/css/styles.66669ecc.css">
|
||||
<script src="/assets/js/runtime~main.732f6967.js" defer="defer"></script>
|
||||
<script src="/assets/js/runtime~main.28b5001d.js" defer="defer"></script>
|
||||
<script src="/assets/js/main.b10c6137.js" defer="defer"></script>
|
||||
</head>
|
||||
<body class="navigation-with-keyboard">
|
||||
|
|
@ -101,7 +101,22 @@ This should automatically install <code>easyocr</code> because <code>easyocr</co
|
|||
</li>
|
||||
</ol>
|
||||
<h2 class="anchor anchorTargetStickyNavbar_Vzrq" id="document-ingestion-or-similarity-search-issues">Document ingestion or similarity search issues<a href="#document-ingestion-or-similarity-search-issues" class="hash-link" aria-label="Direct link to Document ingestion or similarity search issues" title="Direct link to Document ingestion or similarity search issues" translate="no"></a></h2>
|
||||
<p>See <a class="" href="/ingestion#troubleshoot-ingestion">Troubleshoot ingestion</a>.</p></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/support/troubleshoot.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="/reference/configuration"><div class="pagination-nav__sublabel">Previous</div><div class="pagination-nav__label">Environment variables</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="#opensearch-fails-to-start" class="table-of-contents__link toc-highlight">OpenSearch fails to start</a></li><li><a href="#openrag-fails-to-start-from-the-tui-with-operation-not-supported" class="table-of-contents__link toc-highlight">OpenRAG fails to start from the TUI with operation not supported</a></li><li><a href="#openrag-installation-fails-with-unable-to-get-local-issuer-certificate" class="table-of-contents__link toc-highlight">OpenRAG installation fails with unable to get local issuer certificate</a></li><li><a href="#langflow-connection-issues" class="table-of-contents__link toc-highlight">Langflow connection issues</a></li><li><a href="#container-out-of-memory-errors" class="table-of-contents__link toc-highlight">Container out of memory errors</a></li><li><a href="#memory-issue-with-podman-on-macos" class="table-of-contents__link toc-highlight">Memory issue with Podman on macOS</a></li><li><a href="#port-conflicts" class="table-of-contents__link toc-highlight">Port conflicts</a></li><li><a href="#ocr-ingestion-fails-easyocr-not-installed" class="table-of-contents__link toc-highlight">OCR ingestion fails (easyocr not installed)</a></li><li><a href="#langflow-container-already-exists-during-upgrade" class="table-of-contents__link toc-highlight">Upgrade fails due to Langflow container already exists</a></li><li><a href="#document-ingestion-or-similarity-search-issues" class="table-of-contents__link toc-highlight">Document ingestion or similarity search issues</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">
|
||||
<p>See <a class="" href="/ingestion#troubleshoot-ingestion">Troubleshoot ingestion</a>.</p>
|
||||
<h2 class="anchor anchorTargetStickyNavbar_Vzrq" id="ollama-model-issues">Ollama model issues<a href="#ollama-model-issues" class="hash-link" aria-label="Direct link to Ollama model issues" title="Direct link to Ollama model issues" translate="no"></a></h2>
|
||||
<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><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/support/troubleshoot.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="/reference/configuration"><div class="pagination-nav__sublabel">Previous</div><div class="pagination-nav__label">Environment variables</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="#opensearch-fails-to-start" class="table-of-contents__link toc-highlight">OpenSearch fails to start</a></li><li><a href="#openrag-fails-to-start-from-the-tui-with-operation-not-supported" class="table-of-contents__link toc-highlight">OpenRAG fails to start from the TUI with operation not supported</a></li><li><a href="#openrag-installation-fails-with-unable-to-get-local-issuer-certificate" class="table-of-contents__link toc-highlight">OpenRAG installation fails with unable to get local issuer certificate</a></li><li><a href="#langflow-connection-issues" class="table-of-contents__link toc-highlight">Langflow connection issues</a></li><li><a href="#container-out-of-memory-errors" class="table-of-contents__link toc-highlight">Container out of memory errors</a></li><li><a href="#memory-issue-with-podman-on-macos" class="table-of-contents__link toc-highlight">Memory issue with Podman on macOS</a></li><li><a href="#port-conflicts" class="table-of-contents__link toc-highlight">Port conflicts</a></li><li><a href="#ocr-ingestion-fails-easyocr-not-installed" class="table-of-contents__link toc-highlight">OCR ingestion fails (easyocr not installed)</a></li><li><a href="#langflow-container-already-exists-during-upgrade" class="table-of-contents__link toc-highlight">Upgrade fails due to Langflow container already exists</a></li><li><a href="#document-ingestion-or-similarity-search-issues" class="table-of-contents__link toc-highlight">Document ingestion or similarity search issues</a></li><li><a href="#ollama-model-issues" class="table-of-contents__link toc-highlight">Ollama model issues</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>
|
||||
|
|
|
|||
|
|
@ -4,7 +4,7 @@
|
|||
<meta charset="UTF-8">
|
||||
<meta name="generator" content="Docusaurus v3.9.2">
|
||||
<title data-rh="true">Use the TUI | 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/tui"><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="Use the TUI | OpenRAG"><meta data-rh="true" name="description" content="The OpenRAG Terminal User Interface (TUI) provides a simplified and guided experience for configuring, managing, and monitoring your OpenRAG deployment directly from the terminal."><meta data-rh="true" property="og:description" content="The OpenRAG Terminal User Interface (TUI) provides a simplified and guided experience for configuring, managing, and monitoring your OpenRAG deployment directly from the terminal."><link data-rh="true" rel="icon" href="/img/favicon.ico"><link data-rh="true" rel="canonical" href="https://docs.openr.ag/tui"><link data-rh="true" rel="alternate" href="https://docs.openr.ag/tui" hreflang="en"><link data-rh="true" rel="alternate" href="https://docs.openr.ag/tui" hreflang="x-default"><script data-rh="true" type="application/ld+json">{"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Use the TUI","item":"https://docs.openr.ag/tui"}]}</script><link rel="stylesheet" href="/assets/css/styles.66669ecc.css">
|
||||
<script src="/assets/js/runtime~main.732f6967.js" defer="defer"></script>
|
||||
<script src="/assets/js/runtime~main.28b5001d.js" defer="defer"></script>
|
||||
<script src="/assets/js/main.b10c6137.js" defer="defer"></script>
|
||||
</head>
|
||||
<body class="navigation-with-keyboard">
|
||||
|
|
|
|||
|
|
@ -4,7 +4,7 @@
|
|||
<meta charset="UTF-8">
|
||||
<meta name="generator" content="Docusaurus v3.9.2">
|
||||
<title data-rh="true">Remove OpenRAG | 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/uninstall"><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="Remove OpenRAG | OpenRAG"><meta data-rh="true" name="description" content="If you want to reset your OpenRAG containers without removing OpenRAG entirely, see Reset OpenRAG containers and Reinstall OpenRAG."><meta data-rh="true" property="og:description" content="If you want to reset your OpenRAG containers without removing OpenRAG entirely, see Reset OpenRAG containers and Reinstall OpenRAG."><link data-rh="true" rel="icon" href="/img/favicon.ico"><link data-rh="true" rel="canonical" href="https://docs.openr.ag/uninstall"><link data-rh="true" rel="alternate" href="https://docs.openr.ag/uninstall" hreflang="en"><link data-rh="true" rel="alternate" href="https://docs.openr.ag/uninstall" hreflang="x-default"><script data-rh="true" type="application/ld+json">{"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Remove OpenRAG","item":"https://docs.openr.ag/uninstall"}]}</script><link rel="stylesheet" href="/assets/css/styles.66669ecc.css">
|
||||
<script src="/assets/js/runtime~main.732f6967.js" defer="defer"></script>
|
||||
<script src="/assets/js/runtime~main.28b5001d.js" defer="defer"></script>
|
||||
<script src="/assets/js/main.b10c6137.js" defer="defer"></script>
|
||||
</head>
|
||||
<body class="navigation-with-keyboard">
|
||||
|
|
|
|||
|
|
@ -4,7 +4,7 @@
|
|||
<meta charset="UTF-8">
|
||||
<meta name="generator" content="Docusaurus v3.9.2">
|
||||
<title data-rh="true">Upgrade OpenRAG | 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/upgrade"><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="Upgrade OpenRAG | OpenRAG"><meta data-rh="true" name="description" content="Use these steps to upgrade your OpenRAG deployment to the latest version or a specific version."><meta data-rh="true" property="og:description" content="Use these steps to upgrade your OpenRAG deployment to the latest version or a specific version."><link data-rh="true" rel="icon" href="/img/favicon.ico"><link data-rh="true" rel="canonical" href="https://docs.openr.ag/upgrade"><link data-rh="true" rel="alternate" href="https://docs.openr.ag/upgrade" hreflang="en"><link data-rh="true" rel="alternate" href="https://docs.openr.ag/upgrade" hreflang="x-default"><script data-rh="true" type="application/ld+json">{"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Upgrade OpenRAG","item":"https://docs.openr.ag/upgrade"}]}</script><link rel="stylesheet" href="/assets/css/styles.66669ecc.css">
|
||||
<script src="/assets/js/runtime~main.732f6967.js" defer="defer"></script>
|
||||
<script src="/assets/js/runtime~main.28b5001d.js" defer="defer"></script>
|
||||
<script src="/assets/js/main.b10c6137.js" defer="defer"></script>
|
||||
</head>
|
||||
<body class="navigation-with-keyboard">
|
||||
|
|
|
|||
Loading…
Add table
Reference in a new issue