{"id":1224,"date":"2026-09-03T14:31:18","date_gmt":"2026-09-03T14:31:18","guid":{"rendered":"https:\/\/www.techpolaju.com\/blog\/?p=1224"},"modified":"2026-09-03T14:31:21","modified_gmt":"2026-09-03T14:31:21","slug":"how-large-language-models-work","status":"publish","type":"post","link":"https:\/\/www.techpolaju.com\/blog\/ai\/how-large-language-models-work\/","title":{"rendered":"How Large Language Models Work: 7 Powerful Steps"},"content":{"rendered":"\n<p>How large language models work becomes much easier to understand when you break the process into a few simple steps.<\/p>\n\n\n\n<p>Tools such as ChatGPT and Microsoft Copilot may appear to understand normal human language, but underneath they are working with <strong>tokens, numbers, vectors, attention, and probabilities<\/strong>.<\/p>\n\n\n\n<figure class=\"wp-block-image size-large\"><img loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"576\" src=\"https:\/\/www.techpolaju.com\/blog\/wp-content\/uploads\/2026\/09\/complete-llm-process-1024x576.png\" alt=\"how large language models work\" class=\"wp-image-1231\" srcset=\"https:\/\/www.techpolaju.com\/blog\/wp-content\/uploads\/2026\/09\/complete-llm-process-1024x576.png 1024w, https:\/\/www.techpolaju.com\/blog\/wp-content\/uploads\/2026\/09\/complete-llm-process-300x169.png 300w, https:\/\/www.techpolaju.com\/blog\/wp-content\/uploads\/2026\/09\/complete-llm-process-768x432.png 768w, https:\/\/www.techpolaju.com\/blog\/wp-content\/uploads\/2026\/09\/complete-llm-process-1536x864.png 1536w, https:\/\/www.techpolaju.com\/blog\/wp-content\/uploads\/2026\/09\/complete-llm-process.png 1672w\" sizes=\"auto, (max-width: 1024px) 100vw, 1024px\" \/><\/figure>\n\n\n\n<p>The basic process is:<\/p>\n\n\n\n<p><strong>Text \u2192 Tokens \u2192 Token IDs \u2192 Embeddings \u2192 Attention \u2192 Prediction \u2192 Next Token<\/strong><\/p>\n\n\n\n<p>Let&#8217;s see how it works.<\/p>\n\n\n\n<div id=\"ez-toc-container\" class=\"ez-toc-v2_0_87 counter-hierarchy ez-toc-counter ez-toc-grey ez-toc-container-direction\">\n<div class=\"ez-toc-title-container\">\n<p class=\"ez-toc-title\" style=\"cursor:inherit\">Table of Contents<\/p>\n<span class=\"ez-toc-title-toggle\"><a href=\"#\" class=\"ez-toc-pull-right ez-toc-btn ez-toc-btn-xs ez-toc-btn-default ez-toc-toggle\" aria-label=\"Toggle Table of Content\"><span class=\"ez-toc-js-icon-con\"><span class=\"\"><span class=\"eztoc-hide\" style=\"display:none;\">Toggle<\/span><span class=\"ez-toc-icon-toggle-span\"><svg style=\"fill: #999;color:#999\" xmlns=\"http:\/\/www.w3.org\/2000\/svg\" class=\"list-377408\" width=\"20px\" height=\"20px\" viewBox=\"0 0 24 24\" fill=\"none\"><path d=\"M6 6H4v2h2V6zm14 0H8v2h12V6zM4 11h2v2H4v-2zm16 0H8v2h12v-2zM4 16h2v2H4v-2zm16 0H8v2h12v-2z\" fill=\"currentColor\"><\/path><\/svg><svg style=\"fill: #999;color:#999\" class=\"arrow-unsorted-368013\" xmlns=\"http:\/\/www.w3.org\/2000\/svg\" width=\"10px\" height=\"10px\" viewBox=\"0 0 24 24\" version=\"1.2\" baseProfile=\"tiny\"><path d=\"M18.2 9.3l-6.2-6.3-6.2 6.3c-.2.2-.3.4-.3.7s.1.5.3.7c.2.2.4.3.7.3h11c.3 0 .5-.1.7-.3.2-.2.3-.5.3-.7s-.1-.5-.3-.7zM5.8 14.7l6.2 6.3 6.2-6.3c.2-.2.3-.5.3-.7s-.1-.5-.3-.7c-.2-.2-.4-.3-.7-.3h-11c-.3 0-.5.1-.7.3-.2.2-.3.5-.3.7s.1.5.3.7z\"\/><\/svg><\/span><\/span><\/span><\/a><\/span><\/div>\n<nav><ul class='ez-toc-list ez-toc-list-level-1 ' ><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-1\" href=\"https:\/\/www.techpolaju.com\/blog\/ai\/how-large-language-models-work\/#Step_1_You_Give_the_LLM_a_Prompt\" >Step 1. You Give the LLM a Prompt<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-2\" href=\"https:\/\/www.techpolaju.com\/blog\/ai\/how-large-language-models-work\/#Step_2_Text_Is_Converted_Into_Tokens\" >Step 2. Text Is Converted Into Tokens<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-3\" href=\"https:\/\/www.techpolaju.com\/blog\/ai\/how-large-language-models-work\/#Step_3_Tokens_Get_Integer_IDs\" >Step 3. Tokens Get Integer IDs<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-4\" href=\"https:\/\/www.techpolaju.com\/blog\/ai\/how-large-language-models-work\/#Step_4_Token_IDs_Become_Embeddings\" >Step 4. Token IDs Become Embeddings<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-5\" href=\"https:\/\/www.techpolaju.com\/blog\/ai\/how-large-language-models-work\/#Step_5_Attention_Finds_Important_Relationships\" >Step 5. Attention Finds Important Relationships<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-6\" href=\"https:\/\/www.techpolaju.com\/blog\/ai\/how-large-language-models-work\/#Step_6_The_Model_Predicts_the_Next_Token\" >Step 6. The Model Predicts the Next Token<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-7\" href=\"https:\/\/www.techpolaju.com\/blog\/ai\/how-large-language-models-work\/#Step_7_The_Process_Repeats\" >Step 7. The Process Repeats<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-8\" href=\"https:\/\/www.techpolaju.com\/blog\/ai\/how-large-language-models-work\/#The_Complete_LLM_Process\" >The Complete LLM Process<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-9\" href=\"https:\/\/www.techpolaju.com\/blog\/ai\/how-large-language-models-work\/#Final_Thoughts\" >Final Thoughts<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-10\" href=\"https:\/\/www.techpolaju.com\/blog\/ai\/how-large-language-models-work\/#Further_Reading\" >Further Reading<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-11\" href=\"https:\/\/www.techpolaju.com\/blog\/ai\/how-large-language-models-work\/#AI_Tutorials\" >AI Tutorials<\/a><\/li><\/ul><\/nav><\/div>\n<h2 class=\"wp-block-heading\"><span class=\"ez-toc-section\" id=\"Step_1_You_Give_the_LLM_a_Prompt\"><\/span>Step 1. You Give the LLM a Prompt<span class=\"ez-toc-section-end\"><\/span><\/h2>\n\n\n\n<p>Everything starts with a prompt.<\/p>\n\n\n\n<p>For example:<\/p>\n\n\n\n<blockquote class=\"wp-block-quote is-layout-flow wp-block-quote-is-layout-flow\">\n<p>I heard a dog&#8230;<\/p>\n<\/blockquote>\n\n\n\n<p>The large language model tries to predict what should come next.<\/p>\n\n\n\n<p>Possible words might include:<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li>bark<\/li>\n\n\n\n<li>run<\/li>\n\n\n\n<li>sleep<\/li>\n\n\n\n<li>eat<\/li>\n<\/ul>\n\n\n\n<p>Because the words <strong>heard<\/strong> and <strong>dog<\/strong> strongly relate to a sound made by a dog, <strong>bark<\/strong> is likely to have a high probability.<\/p>\n\n\n\n<p>At its core, this next-token prediction is an important part of how large language models work.<\/p>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h2 class=\"wp-block-heading\"><span class=\"ez-toc-section\" id=\"Step_2_Text_Is_Converted_Into_Tokens\"><\/span>Step 2. Text Is Converted Into Tokens<span class=\"ez-toc-section-end\"><\/span><\/h2>\n\n\n\n<p>An AI model cannot directly perform neural-network calculations on normal text.<\/p>\n\n\n\n<p>First, the text is broken into pieces called <strong>tokens<\/strong>.<\/p>\n\n\n\n<p>For example:<\/p>\n\n\n\n<p><strong>I heard a dog bark<\/strong><\/p>\n\n\n\n<p>might be simplified as:<\/p>\n\n\n\n<p><strong>I | heard | a | dog | bark<\/strong><\/p>\n\n\n\n<p>However, one token does not always equal one word.<\/p>\n\n\n\n<p>Tokens can also contain:<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li>parts of words<\/li>\n\n\n\n<li>punctuation<\/li>\n\n\n\n<li>numbers<\/li>\n\n\n\n<li>common character combinations<\/li>\n<\/ul>\n\n\n\n<p>For example, a long word might be split into several tokens.<\/p>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h2 class=\"wp-block-heading\"><span class=\"ez-toc-section\" id=\"Step_3_Tokens_Get_Integer_IDs\"><\/span>Step 3. Tokens Get Integer IDs<span class=\"ez-toc-section-end\"><\/span><\/h2>\n\n\n\n<p>Every token in the model&#8217;s vocabulary has an integer ID.<\/p>\n\n\n\n<p>A simplified example might be:<\/p>\n\n\n\n<figure class=\"wp-block-table\"><table class=\"has-fixed-layout\"><thead><tr><th>Token<\/th><th>ID<\/th><\/tr><\/thead><tbody><tr><td>I<\/td><td>1<\/td><\/tr><tr><td>heard<\/td><td>2<\/td><\/tr><tr><td>a<\/td><td>3<\/td><\/tr><tr><td>dog<\/td><td>4<\/td><\/tr><tr><td>bark<\/td><td>5<\/td><\/tr><\/tbody><\/table><\/figure>\n\n\n\n<p>If the token <strong>dog<\/strong> has ID <code>4<\/code>, the number <code>4<\/code> itself does not mean dog.<\/p>\n\n\n\n<p>It simply tells the model:<\/p>\n\n\n\n<blockquote class=\"wp-block-quote is-layout-flow wp-block-quote-is-layout-flow\">\n<p>Use token number 4 from the vocabulary.<\/p>\n<\/blockquote>\n\n\n\n<p>The token ID is therefore an identifier, not the actual meaning of the word.<\/p>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h2 class=\"wp-block-heading\"><span class=\"ez-toc-section\" id=\"Step_4_Token_IDs_Become_Embeddings\"><\/span>Step 4. Token IDs Become Embeddings<span class=\"ez-toc-section-end\"><\/span><\/h2>\n\n\n\n<p>The neural network needs more than integer IDs.<\/p>\n\n\n\n<p>Each token is converted into a numerical vector called an <strong>embedding<\/strong>.<\/p>\n\n\n\n<p>A very simplified example could be:<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>dog   \u2192 &#91;10, 3, 2]\npuppy \u2192 &#91;5, 3, 2]\ncat   \u2192 &#91;10, 3, 1]\n\ncar   \u2192 &#91;-2, -2, 1]\n<\/code><\/pre>\n\n\n\n<p>Real embeddings contain many more dimensions.<\/p>\n\n\n\n<p>These vectors allow the model to represent relationships mathematically.<\/p>\n\n\n\n<p>Because <strong>dog<\/strong>, <strong>puppy<\/strong>, and <strong>cat<\/strong> are often used in similar contexts, their vector representations can have similarities.<\/p>\n\n\n\n<p>This is one of the most important concepts for understanding how large language models work.<\/p>\n\n\n\n<p>Embeddings are also widely used in:<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li>semantic search<\/li>\n\n\n\n<li>Retrieval-Augmented Generation (RAG)<\/li>\n\n\n\n<li>AI knowledge bases<\/li>\n\n\n\n<li>recommendation systems<\/li>\n<\/ul>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h2 class=\"wp-block-heading\"><span class=\"ez-toc-section\" id=\"Step_5_Attention_Finds_Important_Relationships\"><\/span>Step 5. Attention Finds Important Relationships<span class=\"ez-toc-section-end\"><\/span><\/h2>\n\n\n\n<p>Next comes one of the most important parts of the Transformer architecture: <strong>attention<\/strong>.<\/p>\n\n\n\n<p>Consider:<\/p>\n\n\n\n<blockquote class=\"wp-block-quote is-layout-flow wp-block-quote-is-layout-flow\">\n<p>I heard a dog bark.<\/p>\n<\/blockquote>\n\n\n\n<p>When processing <strong>bark<\/strong>, not every previous word is equally important.<\/p>\n\n\n\n<p>The words:<\/p>\n\n\n\n<p><strong>heard<\/strong><\/p>\n\n\n\n<p>and:<\/p>\n\n\n\n<p><strong>dog<\/strong><\/p>\n\n\n\n<p>provide much stronger clues than words such as:<\/p>\n\n\n\n<p><strong>I<\/strong><\/p>\n\n\n\n<p>or:<\/p>\n\n\n\n<p><strong>a<\/strong><\/p>\n\n\n\n<p>Attention helps the model mathematically determine which tokens are most relevant to other tokens.<\/p>\n\n\n\n<p>Modern Transformers use <strong>multi-head attention<\/strong>, which allows the model to examine different relationships at the same time.<\/p>\n\n\n\n<p>This helps the model build a richer understanding of the context.<\/p>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h2 class=\"wp-block-heading\"><span class=\"ez-toc-section\" id=\"Step_6_The_Model_Predicts_the_Next_Token\"><\/span>Step 6. The Model Predicts the Next Token<span class=\"ez-toc-section-end\"><\/span><\/h2>\n\n\n\n<p>After processing the context, the model calculates probabilities for possible next tokens.<\/p>\n\n\n\n<p>For:<\/p>\n\n\n\n<blockquote class=\"wp-block-quote is-layout-flow wp-block-quote-is-layout-flow\">\n<p>I heard a dog&#8230;<\/p>\n<\/blockquote>\n\n\n\n<p>a simplified result might look like:<\/p>\n\n\n\n<figure class=\"wp-block-table\"><table class=\"has-fixed-layout\"><thead><tr><th>Token<\/th><th>Probability<\/th><\/tr><\/thead><tbody><tr><td>bark<\/td><td>60%<\/td><\/tr><tr><td>run<\/td><td>15%<\/td><\/tr><tr><td>growl<\/td><td>10%<\/td><\/tr><tr><td>jump<\/td><td>5%<\/td><\/tr><tr><td>others<\/td><td>10%<\/td><\/tr><\/tbody><\/table><\/figure>\n\n\n\n<p>The model then selects a token based on these probabilities and its generation settings.<\/p>\n\n\n\n<p>Suppose it selects:<\/p>\n\n\n\n<p><strong>bark<\/strong><\/p>\n\n\n\n<p>The sequence becomes:<\/p>\n\n\n\n<blockquote class=\"wp-block-quote is-layout-flow wp-block-quote-is-layout-flow\">\n<p>I heard a dog bark<\/p>\n<\/blockquote>\n\n\n\n<p>The model now runs the process again.<\/p>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h2 class=\"wp-block-heading\"><span class=\"ez-toc-section\" id=\"Step_7_The_Process_Repeats\"><\/span>Step 7. The Process Repeats<span class=\"ez-toc-section-end\"><\/span><\/h2>\n\n\n\n<p>This is the final key to understanding how large language models work.<\/p>\n\n\n\n<p>The LLM normally does not create an entire paragraph in one step.<\/p>\n\n\n\n<p>It generates text token by token.<\/p>\n\n\n\n<p>For example:<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>I heard a dog\n        \u2193\nbark\n        \u2193\nI heard a dog bark\n        \u2193\nloudly\n        \u2193\nI heard a dog bark loudly\n        \u2193\nat\n        \u2193\nI heard a dog bark loudly at...\n<\/code><\/pre>\n\n\n\n<p>This process repeats very quickly until the response is complete.<\/p>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h2 class=\"wp-block-heading\"><span class=\"ez-toc-section\" id=\"The_Complete_LLM_Process\"><\/span>The Complete LLM Process<span class=\"ez-toc-section-end\"><\/span><\/h2>\n\n\n\n<p>The complete journey looks like this:<\/p>\n\n\n\n<p><strong>Human Text \u2192 Tokens \u2192 Token IDs \u2192 Embeddings \u2192 Transformer + Attention \u2192 Next-Token Probabilities \u2192 Select Token \u2192 Add Token \u2192 Repeat<\/strong><\/p>\n\n\n\n<p>That is the core idea behind how large language models work.<\/p>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity\"\/>\n\n\n\n<h2 class=\"wp-block-heading\"><span class=\"ez-toc-section\" id=\"Final_Thoughts\"><\/span>Final Thoughts<span class=\"ez-toc-section-end\"><\/span><\/h2>\n\n\n\n<p>Understanding how large language models work does not require advanced mathematics.<\/p>\n\n\n\n<p>Remember these seven ideas:<\/p>\n\n\n\n<p><strong>Prompt \u2192 Tokens \u2192 IDs \u2192 Embeddings \u2192 Attention \u2192 Prediction \u2192 Repeat<\/strong><\/p>\n\n\n\n<p>Once you understand this process, other AI concepts become much easier to understand.<\/p>\n\n\n\n<p>For example:<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>Tokens<\/strong> help explain context windows and API costs.<\/li>\n\n\n\n<li><strong>Embeddings<\/strong> help explain semantic search and RAG.<\/li>\n\n\n\n<li><strong>Attention<\/strong> helps explain how an LLM uses context.<\/li>\n\n\n\n<li><strong>Next-token prediction<\/strong> helps explain both AI-generated text and hallucinations.<\/li>\n<\/ul>\n\n\n\n<p>This same foundation helps you better understand technologies such as ChatGPT, Microsoft Copilot, Copilot Studio, Azure AI, AI agents, and modern generative AI applications.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\"><span class=\"ez-toc-section\" id=\"Further_Reading\"><\/span>Further Reading<span class=\"ez-toc-section-end\"><\/span><\/h2>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>Attention Is All You Need \u2014 Original Transformer Paper<\/strong><br>The original 2017 research paper that introduced the Transformer architecture. Best for readers who want the mathematical and architectural details behind attention.<br><a href=\"https:\/\/arxiv.org\/abs\/1706.03762?utm_source=chatgpt.com\" target=\"_blank\" rel=\"noreferrer noopener\">Read the paper on arXiv<\/a><\/li>\n\n\n\n<li><strong>Hugging Face LLM Course \u2014 How Transformers Work<\/strong><br>A much more approachable deep dive into Transformers, attention, encoder\/decoder architectures, tokenization, and modern LLM concepts.<br><a href=\"https:\/\/huggingface.co\/learn\/llm-course\/chapter1\/4?utm_source=chatgpt.com\" target=\"_blank\" rel=\"noreferrer noopener\">Read the Hugging Face LLM Course<\/a><\/li>\n<\/ul>\n\n\n\n<h2 class=\"wp-block-heading\"><span class=\"ez-toc-section\" id=\"AI_Tutorials\"><\/span>AI Tutorials<span class=\"ez-toc-section-end\"><\/span><\/h2>\n\n\n\n<ul class=\"wp-block-list\">\n<li><a href=\"https:\/\/www.techpolaju.com\/blog\/copilot\/copilot-studio-ai-agent\/\">Copilot Studio AI Agent: A Beginner\u2019s Guide in 7 Easy Steps<\/a><a href=\"https:\/\/www.techpolaju.com\/blog\/power-automate\/teams-quiz-bot-tutorial-2026\/\"><\/a><\/li>\n\n\n\n<li><a href=\"https:\/\/www.techpolaju.com\/blog\/power-automate\/ai-draft-reply-flow\/\">Master Power Automate AI Draft Reply Flow in 7 Steps for Effortless Email Replies<\/a><\/li>\n<\/ul>\n","protected":false},"excerpt":{"rendered":"<p>How large language models work becomes much easier to understand when you break the process into a few simple steps. Tools such as ChatGPT and Microsoft Copilot may appear to understand normal human language, but underneath they are working with tokens, numbers, vectors, attention, and probabilities. The basic process is: Text \u2192 Tokens \u2192 Token &#8230; <a title=\"How Large Language Models Work: 7 Powerful Steps\" class=\"read-more\" href=\"https:\/\/www.techpolaju.com\/blog\/ai\/how-large-language-models-work\/\" aria-label=\"Read more about How Large Language Models Work: 7 Powerful Steps\">Read more<\/a><\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[14],"tags":[],"class_list":["post-1224","post","type-post","status-publish","format-standard","hentry","category-ai"],"_links":{"self":[{"href":"https:\/\/www.techpolaju.com\/blog\/wp-json\/wp\/v2\/posts\/1224","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.techpolaju.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.techpolaju.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.techpolaju.com\/blog\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.techpolaju.com\/blog\/wp-json\/wp\/v2\/comments?post=1224"}],"version-history":[{"count":10,"href":"https:\/\/www.techpolaju.com\/blog\/wp-json\/wp\/v2\/posts\/1224\/revisions"}],"predecessor-version":[{"id":1235,"href":"https:\/\/www.techpolaju.com\/blog\/wp-json\/wp\/v2\/posts\/1224\/revisions\/1235"}],"wp:attachment":[{"href":"https:\/\/www.techpolaju.com\/blog\/wp-json\/wp\/v2\/media?parent=1224"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.techpolaju.com\/blog\/wp-json\/wp\/v2\/categories?post=1224"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.techpolaju.com\/blog\/wp-json\/wp\/v2\/tags?post=1224"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}