{"id":434035,"date":"2024-10-01T03:00:09","date_gmt":"2024-10-01T03:00:09","guid":{"rendered":"http:\/\/savepearlharbor.com\/?p=434035"},"modified":"-0001-11-30T00:00:00","modified_gmt":"-0001-11-29T21:00:00","slug":"","status":"publish","type":"post","link":"https:\/\/savepearlharbor.com\/?p=434035","title":{"rendered":"<span>Run AI Locally: Llama 3.2 OpenWebUI Tutorial<\/span>"},"content":{"rendered":"<div><!--[--><!--]--><\/div>\n<div id=\"post-content-body\">\n<div>\n<div class=\"article-formatted-body article-formatted-body article-formatted-body_version-2\">\n<div xmlns=\"http:\/\/www.w3.org\/1999\/xhtml\">\n<p>Did you know you can run powerful AI models right on your computer? It&#8217;s true! Today, I will show you how easy it is to get started with Llama 3.2 and OpenWebUI. <\/p>\n<div class=\"tm-iframe_temp\" data-src=\"https:\/\/embedd.srv.habr.com\/iframe\/66fab09e28dfc09d9e93424f\" data-style=\"\" id=\"66fab09e28dfc09d9e93424f\" width=\"\"><\/div>\n<p><strong><em>Watch on YouTube: <\/em><\/strong><a href=\"https:\/\/youtu.be\/woUB_vhoML0?si=IvyCEnQLZ_w1jEaC\" rel=\"noopener noreferrer nofollow\"><em>Run AI On YOUR Computer<\/em><\/a><\/p>\n<h3>Running Llama 3.2 Locally: A Comprehensive Guide<\/h3>\n<h4>Introduction to Llama 3.2<\/h4>\n<p>Llama 3.2 is the latest iteration of Meta&#8217;s open-source language model, offering enhanced capabilities for text and image processing. It is designed to run efficiently on local devices, making it ideal for applications that require privacy and low latency. The model comes in various sizes, including 1B, 3B, and 11B parameters. In this tutorial, I&#8217;m going to use the 1B model, but you can download any you like.<\/p>\n<figure class=\"full-width\"><img loading=\"lazy\" decoding=\"async\" src=\"https:\/\/habrastorage.org\/r\/w1560\/getpro\/habr\/upload_files\/592\/65a\/7bb\/59265a7bb0912b9efe0205dc344bc16d.png\" alt=\"Introduction to Llama 3.2\" title=\"Introduction to Llama 3.2\" width=\"1077\" height=\"621\" data-src=\"https:\/\/habrastorage.org\/getpro\/habr\/upload_files\/592\/65a\/7bb\/59265a7bb0912b9efe0205dc344bc16d.png\"\/><\/p>\n<div><figcaption>Introduction to Llama 3.2<\/figcaption><\/div>\n<\/figure>\n<p><strong>Before setting up Llama 3.2 locally, ensure you have the following:<\/strong><\/p>\n<ul>\n<li>\n<p>A computer with Windows, macOS, or Linux. I&#8217;m going to use Linux (Ubuntu).<\/p>\n<\/li>\n<li>\n<p>Basic knowledge of using the terminal or command prompt.<\/p>\n<\/li>\n<\/ul>\n<h3>Step-by-Step Installation Guide<\/h3>\n<h4>Step 1: Install Docker<\/h4>\n<p>Docker is a tool that allows developers to package applications and their dependencies into a standardized unit called a\u00a0<em>container<\/em>, which can run consistently across different computing environments.\u00a0Unlike virtual machines, containers are lightweight and share the host system&#8217;s operating system, making them more efficient and faster to start.<\/p>\n<\/p>\n<figure class=\"full-width\"><img loading=\"lazy\" decoding=\"async\" src=\"https:\/\/habrastorage.org\/r\/w1560\/getpro\/habr\/upload_files\/0e2\/fa0\/e96\/0e2fa0e965a5e94d02e7bef37cc651bf.png\" alt=\"Docker\" title=\"Docker\" width=\"1366\" height=\"681\" data-src=\"https:\/\/habrastorage.org\/getpro\/habr\/upload_files\/0e2\/fa0\/e96\/0e2fa0e965a5e94d02e7bef37cc651bf.png\"\/><\/p>\n<div><figcaption>Docker<\/figcaption><\/div>\n<\/figure>\n<p>You can download the Docker Desktop application from the Docker website\u00a0<a href=\"https:\/\/www.docker.com\/\" rel=\"noopener noreferrer nofollow\">https:\/\/www.docker.com\/<\/a>\u00a0or via the terminal. Docker is available for Mac, Windows, and Linux.<\/p>\n<h4>How to Install Docker on Ubuntu<\/h4>\n<p>Download the package https:\/\/desktop.docker.com\/linux\/main\/amd64\/docker-desktop-amd64.deb<\/p>\n<p>Then use these commands:<\/p>\n<pre><code class=\"bash\">sudo apt-get update sudo apt-get install [path to the docker package].deb<\/code><\/pre>\n<p>More details: <a href=\"https:\/\/docs.docker.com\/desktop\/install\/linux\/ubuntu\/\" rel=\"noopener noreferrer nofollow\">https:\/\/docs.docker.com\/desktop\/install\/linux\/ubuntu\/<\/a><\/p>\n<h4>Step 2: Install Ollama<\/h4>\n<p>Ollama is essential for running large language models like Llama 3.2 locally. <\/p>\n<figure class=\"full-width\"><img loading=\"lazy\" decoding=\"async\" src=\"https:\/\/habrastorage.org\/r\/w1560\/getpro\/habr\/upload_files\/ba7\/ff2\/1ec\/ba7ff21ec0493b85b24f99d1f455778b.png\" alt=\"Install Ollama\" title=\"Install Ollama\" width=\"738\" height=\"428\" data-src=\"https:\/\/habrastorage.org\/getpro\/habr\/upload_files\/ba7\/ff2\/1ec\/ba7ff21ec0493b85b24f99d1f455778b.png\"\/><\/p>\n<div><figcaption>Install Ollama<\/figcaption><\/div>\n<\/figure>\n<p><strong>Follow these steps to install it:<\/strong><\/p>\n<ul>\n<li>\n<p>Visit the official <a href=\"https:\/\/ollama.com\/\" rel=\"noopener noreferrer nofollow\">Ollama website<\/a> and download the installer for your operating system.<\/p>\n<\/li>\n<li>\n<p>Run the installer and follow the on-screen instructions to complete the installation.<\/p>\n<\/li>\n<li>\n<p>Verify the installation by opening a terminal (or command prompt) and typing `ollama`. You should see a list of commands if installed correctly.<\/p>\n<\/li>\n<\/ul>\n<p>I&#8217;m going to use the terminal and this command:<\/p>\n<pre><code class=\"bash\">curl -fsSL https:\/\/ollama.com\/install.sh | sh<\/code><\/pre>\n<h4>Step 3: Download a New Llama 3.2 model from Ollama website<\/h4>\n<p>Once Ollama is set up, you can download Llama 3.2 models. All the available models you can find here <a href=\"https:\/\/ollama.com\/library\" rel=\"noopener noreferrer nofollow\">https:\/\/ollama.com\/library<\/a><\/p>\n<figure class=\"full-width\"><img loading=\"lazy\" decoding=\"async\" src=\"https:\/\/habrastorage.org\/r\/w1560\/getpro\/habr\/upload_files\/605\/f52\/f1b\/605f52f1beb320664b9c38943ea3406d.png\" alt=\": Download a New Llama 3.2\" title=\": Download a New Llama 3.2\" width=\"656\" height=\"329\" data-src=\"https:\/\/habrastorage.org\/getpro\/habr\/upload_files\/605\/f52\/f1b\/605f52f1beb320664b9c38943ea3406d.png\"\/><\/p>\n<div><figcaption>: Download a New Llama 3.2<\/figcaption><\/div>\n<\/figure>\n<p>Since I want to use 1B parameters model I&#8217;ll be using this command:<\/p>\n<pre><code class=\"bash\">ollama run llama3.2:1b<\/code><\/pre>\n<h4>Step 4: Install OpenWebUI with Default Configuration<\/h4>\n<p>OpenWebUI is a self-hosted, extensible web interface designed to interact entirely offline with large language models (LLMs). It offers a user-friendly experience similar to ChatGPT, supports integration with various LLMs, such as those compatible with OpenAI and Ollama, and provides features like markdown support, model management, and multi-user access.<\/p>\n<p>Go to <a href=\"https:\/\/docs.openwebui.com\/getting-started\/\" rel=\"noopener noreferrer nofollow\">https:\/\/docs.openwebui.com\/getting-started\/<\/a> and find the section Quick Start with Docker. Copy the code and then run it in the terminal.<\/p>\n<p>I&#8217;m going to run this code:<\/p>\n<pre><code class=\"bash\">docker run -d -p 3000:8080 --add-host=host.docker.internal:host-gateway -v ollama:\/root\/.ollama -v open-webui:\/app\/backend\/data --name open-webui --restart always ghcr.io\/open-webui\/open-webui:ollama<\/code><\/pre>\n<p>We will run a Docker command. It is used to run a containerized version of the OpenWebUI application.<\/p>\n<p>Once the installation is finished, open your browser and go to\u00a0<strong>http:\/\/0.0.0.0:3000\/.\u00a0<\/strong>If everything is okay, you will see the website. Create an account, and then you will see the welcome screen, which is similar to ChatGPT.<\/p>\n<figure class=\"full-width\"><img loading=\"lazy\" decoding=\"async\" src=\"https:\/\/habrastorage.org\/r\/w1560\/getpro\/habr\/upload_files\/097\/2b3\/2c5\/0972b32c5afcf358d330b0bfa843d448.png\" alt=\"Llama 3.2 in Browser\" title=\"Llama 3.2 in Browser\" width=\"1357\" height=\"700\" data-src=\"https:\/\/habrastorage.org\/getpro\/habr\/upload_files\/097\/2b3\/2c5\/0972b32c5afcf358d330b0bfa843d448.png\"\/><\/p>\n<div><figcaption>Llama 3.2 in Browser<\/figcaption><\/div>\n<\/figure>\n<h3>Troubleshooting Common Issue<\/h3>\n<h4>WebUI models not being pulled\/applied <\/h4>\n<p>Some of you could face an issue when the models are not available in the drop-down. To fix it follow these instructions:<\/p>\n<ol>\n<li>\n<p>Go to the settings at the bottom left corner.<\/p>\n<figure class=\"\"><img loading=\"lazy\" decoding=\"async\" src=\"https:\/\/habrastorage.org\/r\/w1560\/getpro\/habr\/upload_files\/c2c\/887\/4d3\/c2c8874d3a97e1811f9cdda95065de6c.png\" alt=\"Settings\" title=\"Settings\" width=\"431\" height=\"504\" data-src=\"https:\/\/habrastorage.org\/getpro\/habr\/upload_files\/c2c\/887\/4d3\/c2c8874d3a97e1811f9cdda95065de6c.png\"\/><\/p>\n<div><figcaption>Settings<\/figcaption><\/div>\n<\/figure>\n<\/li>\n<li>\n<p>Click on &#171;Admin Settings&#187;.<\/p>\n<figure class=\"full-width\"><img loading=\"lazy\" decoding=\"async\" src=\"https:\/\/habrastorage.org\/r\/w1560\/getpro\/habr\/upload_files\/31a\/380\/d21\/31a380d210e36607b1bc92ff52a0bd5a.png\" alt=\"Admin Settings\" title=\"Admin Settings\" width=\"1366\" height=\"681\" data-src=\"https:\/\/habrastorage.org\/getpro\/habr\/upload_files\/31a\/380\/d21\/31a380d210e36607b1bc92ff52a0bd5a.png\"\/><\/p>\n<div><figcaption>Admin Settings<\/figcaption><\/div>\n<\/figure>\n<\/li>\n<li>\n<p>Click on &#171;Models.&#187;<\/p>\n<figure class=\"full-width\"><img loading=\"lazy\" decoding=\"async\" src=\"https:\/\/habrastorage.org\/r\/w1560\/getpro\/habr\/upload_files\/ff7\/2df\/7e1\/ff72df7e17c42b50c2de68d71b859f7e.png\" alt=\"Models\" title=\"Models\" width=\"1366\" height=\"681\" data-src=\"https:\/\/habrastorage.org\/getpro\/habr\/upload_files\/ff7\/2df\/7e1\/ff72df7e17c42b50c2de68d71b859f7e.png\"\/><\/p>\n<div><figcaption>Models<\/figcaption><\/div>\n<\/figure>\n<\/li>\n<li>\n<p>In the input field, write the name of the model you would like to pull and click on the &#171;download&#187; icon.<\/p>\n<\/li>\n<\/ol>\n<figure class=\"full-width\"><img loading=\"lazy\" decoding=\"async\" src=\"https:\/\/habrastorage.org\/r\/w1560\/getpro\/habr\/upload_files\/d5a\/733\/0b3\/d5a7330b34d8c646504bb19f6a924c57.png\" alt=\"Pull the models\" title=\"Pull the models\" width=\"1366\" height=\"681\" data-src=\"https:\/\/habrastorage.org\/getpro\/habr\/upload_files\/d5a\/733\/0b3\/d5a7330b34d8c646504bb19f6a924c57.png\"\/><\/p>\n<div><figcaption>Pull the models<\/figcaption><\/div>\n<\/figure>\n<p>All the names you can find on <a href=\"https:\/\/ollama.com\/library\/llama3.2\" rel=\"noopener noreferrer nofollow\">https:\/\/ollama.com\/library\/llama3.2<\/a><\/p>\n<p>This should fix the issue.<\/p>\n<h3>Conclusion<\/h3>\n<p>Running Llama 3.2 locally provides significant advantages regarding privacy and control over AI applications. But to have a smooth experience, you would need a powerful computer. \ud83d\ude42<\/p>\n<p>If you like this tutorial, please follow me on\u00a0<a href=\"https:\/\/www.youtube.com\/@proflead\/videos?sub_confirmation=1\" rel=\"noopener noreferrer nofollow\">YouTube<\/a>, join my\u00a0<a href=\"https:\/\/t.me\/profleaddev\" rel=\"noopener noreferrer nofollow\">Telegram<\/a>, or support me on\u00a0<a href=\"https:\/\/www.patreon.com\/proflead\" rel=\"noopener noreferrer nofollow\">Patreon<\/a>.<\/p>\n<p>Thanks! \ud83d\ude42<\/p>\n<\/div>\n<\/div>\n<\/div>\n<p><!----><!----><\/div>\n<p><!----><!----><br \/> \u0441\u0441\u044b\u043b\u043a\u0430 \u043d\u0430 \u043e\u0440\u0438\u0433\u0438\u043d\u0430\u043b \u0441\u0442\u0430\u0442\u044c\u0438 <a href=\"https:\/\/habr.com\/ru\/articles\/847166\/\"> https:\/\/habr.com\/ru\/articles\/847166\/<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"<div><!--[--><!--]--><\/div>\n<div id=\"post-content-body\">\n<div>\n<div class=\"article-formatted-body article-formatted-body article-formatted-body_version-2\">\n<div xmlns=\"http:\/\/www.w3.org\/1999\/xhtml\">\n<p>Did you know you can run powerful AI models right on your computer? It&#8217;s true! Today, I will show you how easy it is to get started with Llama 3.2 and OpenWebUI. <\/p>\n<div class=\"tm-iframe_temp\" data-src=\"https:\/\/embedd.srv.habr.com\/iframe\/66fab09e28dfc09d9e93424f\" data-style=\"\" id=\"66fab09e28dfc09d9e93424f\" width=\"\"><\/div>\n<p><strong><em>Watch on YouTube: <\/em><\/strong><a href=\"https:\/\/youtu.be\/woUB_vhoML0?si=IvyCEnQLZ_w1jEaC\" rel=\"noopener noreferrer nofollow\"><em>Run AI On YOUR Computer<\/em><\/a><\/p>\n<h3>Running Llama 3.2 Locally: A Comprehensive Guide<\/h3>\n<h4>Introduction to Llama 3.2<\/h4>\n<p>Llama 3.2 is the latest iteration of Meta&#8217;s open-source language model, offering enhanced capabilities for text and image processing. It is designed to run efficiently on local devices, making it ideal for applications that require privacy and low latency. The model comes in various sizes, including 1B, 3B, and 11B parameters. In this tutorial, I&#8217;m going to use the 1B model, but you can download any you like.<\/p>\n<figure class=\"full-width\">\n<div><figcaption>Introduction to Llama 3.2<\/figcaption><\/div>\n<\/figure>\n<p><strong>Before setting up Llama 3.2 locally, ensure you have the following:<\/strong><\/p>\n<ul>\n<li>\n<p>A computer with Windows, macOS, or Linux. I&#8217;m going to use Linux (Ubuntu).<\/p>\n<\/li>\n<li>\n<p>Basic knowledge of using the terminal or command prompt.<\/p>\n<\/li>\n<\/ul>\n<h3>Step-by-Step Installation Guide<\/h3>\n<h4>Step 1: Install Docker<\/h4>\n<p>Docker is a tool that allows developers to package applications and their dependencies into a standardized unit called a\u00a0<em>container<\/em>, which can run consistently across different computing environments.\u00a0Unlike virtual machines, containers are lightweight and share the host system&#8217;s operating system, making them more efficient and faster to start.<\/p>\n<\/p>\n<figure class=\"full-width\">\n<div><figcaption>Docker<\/figcaption><\/div>\n<\/figure>\n<p>You can download the Docker Desktop application from the Docker website\u00a0<a href=\"https:\/\/www.docker.com\/\" rel=\"noopener noreferrer nofollow\">https:\/\/www.docker.com\/<\/a>\u00a0or via the terminal. Docker is available for Mac, Windows, and Linux.<\/p>\n<h4>How to Install Docker on Ubuntu<\/h4>\n<p>Download the package https:\/\/desktop.docker.com\/linux\/main\/amd64\/docker-desktop-amd64.deb<\/p>\n<p>Then use these commands:<\/p>\n<pre><code class=\"bash\">sudo apt-get update sudo apt-get install [path to the docker package].deb<\/code><\/pre>\n<p>More details: <a href=\"https:\/\/docs.docker.com\/desktop\/install\/linux\/ubuntu\/\" rel=\"noopener noreferrer nofollow\">https:\/\/docs.docker.com\/desktop\/install\/linux\/ubuntu\/<\/a><\/p>\n<h4>Step 2: Install Ollama<\/h4>\n<p>Ollama is essential for running large language models like Llama 3.2 locally. <\/p>\n<figure class=\"full-width\">\n<div><figcaption>Install Ollama<\/figcaption><\/div>\n<\/figure>\n<p><strong>Follow these steps to install it:<\/strong><\/p>\n<ul>\n<li>\n<p>Visit the official <a href=\"https:\/\/ollama.com\/\" rel=\"noopener noreferrer nofollow\">Ollama website<\/a> and download the installer for your operating system.<\/p>\n<\/li>\n<li>\n<p>Run the installer and follow the on-screen instructions to complete the installation.<\/p>\n<\/li>\n<li>\n<p>Verify the installation by opening a terminal (or command prompt) and typing `ollama`. You should see a list of commands if installed correctly.<\/p>\n<\/li>\n<\/ul>\n<p>I&#8217;m going to use the terminal and this command:<\/p>\n<pre><code class=\"bash\">curl -fsSL https:\/\/ollama.com\/install.sh | sh<\/code><\/pre>\n<h4>Step 3: Download a New Llama 3.2 model from Ollama website<\/h4>\n<p>Once Ollama is set up, you can download Llama 3.2 models. All the available models you can find here <a href=\"https:\/\/ollama.com\/library\" rel=\"noopener noreferrer nofollow\">https:\/\/ollama.com\/library<\/a><\/p>\n<figure class=\"full-width\">\n<div><figcaption>: Download a New Llama 3.2<\/figcaption><\/div>\n<\/figure>\n<p>Since I want to use 1B parameters model I&#8217;ll be using this command:<\/p>\n<pre><code class=\"bash\">ollama run llama3.2:1b<\/code><\/pre>\n<h4>Step 4: Install OpenWebUI with Default Configuration<\/h4>\n<p>OpenWebUI is a self-hosted, extensible web interface designed to interact entirely offline with large language models (LLMs). It offers a user-friendly experience similar to ChatGPT, supports integration with various LLMs, such as those compatible with OpenAI and Ollama, and provides features like markdown support, model management, and multi-user access.<\/p>\n<p>Go to <a href=\"https:\/\/docs.openwebui.com\/getting-started\/\" rel=\"noopener noreferrer nofollow\">https:\/\/docs.openwebui.com\/getting-started\/<\/a> and find the section Quick Start with Docker. Copy the code and then run it in the terminal.<\/p>\n<p>I&#8217;m going to run this code:<\/p>\n<pre><code class=\"bash\">docker run -d -p 3000:8080 --add-host=host.docker.internal:host-gateway -v ollama:\/root\/.ollama -v open-webui:\/app\/backend\/data --name open-webui --restart always ghcr.io\/open-webui\/open-webui:ollama<\/code><\/pre>\n<p>We will run a Docker command. It is used to run a containerized version of the OpenWebUI application.<\/p>\n<p>Once the installation is finished, open your browser and go to\u00a0<strong>http:\/\/0.0.0.0:3000\/.\u00a0<\/strong>If everything is okay, you will see the website. Create an account, and then you will see the welcome screen, which is similar to ChatGPT.<\/p>\n<figure class=\"full-width\">\n<div><figcaption>Llama 3.2 in Browser<\/figcaption><\/div>\n<\/figure>\n<h3>Troubleshooting Common Issue<\/h3>\n<h4>WebUI models not being pulled\/applied <\/h4>\n<p>Some of you could face an issue when the models are not available in the drop-down. To fix it follow these instructions:<\/p>\n<ol>\n<li>\n<p>Go to the settings at the bottom left corner.<\/p>\n<figure class=\"\">\n<div><figcaption>Settings<\/figcaption><\/div>\n<\/figure>\n<\/li>\n<li>\n<p>Click on &#171;Admin Settings&#187;.<\/p>\n<figure class=\"full-width\">\n<div><figcaption>Admin Settings<\/figcaption><\/div>\n<\/figure>\n<\/li>\n<li>\n<p>Click on &#171;Models.&#187;<\/p>\n<figure class=\"full-width\">\n<div><figcaption>Models<\/figcaption><\/div>\n<\/figure>\n<\/li>\n<li>\n<p>In the input field, write the name of the model you would like to pull and click on the &#171;download&#187; icon.<\/p>\n<\/li>\n<\/ol>\n<figure class=\"full-width\">\n<div><figcaption>Pull the models<\/figcaption><\/div>\n<\/figure>\n<p>All the names you can find on <a href=\"https:\/\/ollama.com\/library\/llama3.2\" rel=\"noopener noreferrer nofollow\">https:\/\/ollama.com\/library\/llama3.2<\/a><\/p>\n<p>This should fix the issue.<\/p>\n<h3>Conclusion<\/h3>\n<p>Running Llama 3.2 locally provides significant advantages regarding privacy and control over AI applications. But to have a smooth experience, you would need a powerful computer. \ud83d\ude42<\/p>\n<p>If you like this tutorial, please follow me on\u00a0<a href=\"https:\/\/www.youtube.com\/@proflead\/videos?sub_confirmation=1\" rel=\"noopener noreferrer nofollow\">YouTube<\/a>, join my\u00a0<a href=\"https:\/\/t.me\/profleaddev\" rel=\"noopener noreferrer nofollow\">Telegram<\/a>, or support me on\u00a0<a href=\"https:\/\/www.patreon.com\/proflead\" rel=\"noopener noreferrer nofollow\">Patreon<\/a>.<\/p>\n<p>Thanks! \ud83d\ude42<\/p>\n<\/div>\n<\/div>\n<\/div>\n<p><!----><!----><\/div>\n<p><!----><!----><br \/> \u0441\u0441\u044b\u043b\u043a\u0430 \u043d\u0430 \u043e\u0440\u0438\u0433\u0438\u043d\u0430\u043b \u0441\u0442\u0430\u0442\u044c\u0438 <a href=\"https:\/\/habr.com\/ru\/articles\/847166\/\"> https:\/\/habr.com\/ru\/articles\/847166\/<\/a><br \/><\/br><\/br><\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[],"tags":[],"class_list":["post-434035","post","type-post","status-publish","format-standard","hentry"],"_links":{"self":[{"href":"https:\/\/savepearlharbor.com\/index.php?rest_route=\/wp\/v2\/posts\/434035","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/savepearlharbor.com\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/savepearlharbor.com\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/savepearlharbor.com\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/savepearlharbor.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=434035"}],"version-history":[{"count":0,"href":"https:\/\/savepearlharbor.com\/index.php?rest_route=\/wp\/v2\/posts\/434035\/revisions"}],"wp:attachment":[{"href":"https:\/\/savepearlharbor.com\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=434035"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/savepearlharbor.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=434035"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/savepearlharbor.com\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=434035"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}