{"id":139487,"date":"2026-09-19T13:01:50","date_gmt":"2026-09-19T07:31:50","guid":{"rendered":"https:\/\/www.guvi.in\/blog\/?p=139487"},"modified":"2026-09-19T13:01:53","modified_gmt":"2026-09-19T07:31:53","slug":"rag-and-vector-databases","status":"publish","type":"post","link":"https:\/\/www.guvi.in\/blog\/rag-and-vector-databases\/","title":{"rendered":"RAG and Vector Databases: A Forward Deployed Engineer&#8217;s Primer"},"content":{"rendered":"\n<p><strong>RAG and vector databases for forward deployed engineers<\/strong> are important technologies for building AI applications that can work with customer-specific information. Retrieval-Augmented Generation (RAG) allows an AI system to retrieve relevant information from external sources before generating a response, while vector databases help store and search the numerical representations of that information.<\/p>\n\n\n\n<p>For FDEs, these technologies are particularly useful when deploying AI solutions that need to work with private documents, internal knowledge bases, product information, or business data. Engineers may need to connect data sources, generate embeddings, build retrieval pipelines, evaluate responses, and integrate the system into an existing customer workflow.<\/p>\n\n\n\n<p>This article explains how RAG and vector databases work, why they matter for FDEs, the components involved, common use cases, and the practical skills engineers need to build reliable customer-facing AI solutions.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>TL;DR Summary<\/strong><\/h3>\n\n\n\n<ul>\n<li><strong>RAG and vector databases for forward deployed engineers<\/strong> enable AI applications to retrieve customer-specific information before generating responses.<\/li>\n\n\n\n<li>RAG combines information retrieval with generative AI to provide context to language models.<\/li>\n\n\n\n<li>Vector databases store embeddings and enable semantic similarity searches.<\/li>\n\n\n\n<li>FDEs may build pipelines covering document ingestion, chunking, embedding, retrieval, generation, and evaluation.<\/li>\n\n\n\n<li>Common use cases include enterprise search, AI assistants, support tools, and document question answering.<\/li>\n\n\n\n<li>FDEs should understand embeddings, metadata, retrieval, APIs, data pipelines, evaluation, and deployment.<\/li>\n<\/ul>\n\n\n\n<h2 class=\"wp-block-heading\"><strong>What Are RAG and Vector Databases?<\/strong><\/h2>\n\n\n\n<p><a href=\"https:\/\/www.guvi.in\/blog\/guide-for-retrieval-augmented-generation\/\" target=\"_blank\" rel=\"noreferrer noopener\">RAG<\/a> is an AI architecture that retrieves relevant information from an external knowledge source and provides it to a language model as context. This allows the model to generate responses using information that may not have been included in its original training data.<\/p>\n\n\n\n<p>A <a href=\"https:\/\/www.google.com\/aclk?sa=L&amp;pf=1&amp;ai=DChsSEwiZoczVhvCWAxWewzwCHXW4NtsYACICCAEQABoCc2Y&amp;co=1&amp;ase=2&amp;gclid=CjwKCAjw2aPVBhBkEiwA0Cptt3YFpua1WPCmafUzixYYj7mnprJewtVM8Cb-bkyEp5l9eP1Y02kj0RoC72UQAvD_BwE&amp;cid=CAASWuRoMREpFVj_TjB_WMMJbUxS26XdtgUzaIDdc4q9KQjyfJ8RBtJTlgezywzX_rJs_Ct8JCCxKAHtbwV7i9jONVCNdT4sg9kKKScrIMWQTrUtHoVVXacUXcw0Iw&amp;cce=2&amp;category=acrcp_v1_32&amp;sig=AOD64_3DDafm8yCET17wbAUvyJDBmfMPKg&amp;q&amp;nis=4&amp;adurl=https:\/\/aws.amazon.com\/marketplace\/build-learn\/vector-databases-for-ai?trk%3Dfa7e5851-0cc3-436a-b80c-6d80ff7394c2%26sc_channel%3Dps%26ef_id%3DCjwKCAjw2aPVBhBkEiwA0Cptt3YFpua1WPCmafUzixYYj7mnprJewtVM8Cb-bkyEp5l9eP1Y02kj0RoC72UQAvD_BwE:G:s%26gads_camp%3D23958044345%26gads_ag%3D198397576500%26gads_ad%3D813473147188%26gads_kw%3Dvector%2520database%26gads_matchtype%3De%26gads_network%3Dg%26gads_device%3Dc%26gads_geo%3D9061929%26gad_campaignid%3D23958044345%26gbraid%3D0AAAAADjHtp8gcvLb1CJbbtUASuSt166DA%26gclid%3DCjwKCAjw2aPVBhBkEiwA0Cptt3YFpua1WPCmafUzixYYj7mnprJewtVM8Cb-bkyEp5l9eP1Y02kj0RoC72UQAvD_BwE&amp;ved=2ahUKEwiXpMbVhvCWAxVdaHADHfRBIcoQ0Qx6BAgQEAE\" target=\"_blank\" rel=\"noreferrer noopener nofollow\">vector database<\/a> stores embeddings, which are numerical representations of text or other data. These embeddings allow systems to search for information based on semantic similarity rather than relying only on exact keyword matches.<\/p>\n\n\n\n<p>Together, RAG and vector databases can help create AI applications that understand and retrieve relevant customer information.<\/p>\n\n\n\n<p>Explore modern AI technologies with <strong>HCL GUVI&#8217;s <\/strong><a href=\"https:\/\/www.guvi.in\/mlp\/artificial-intelligence-and-machine-learning?utm_source=blog&amp;utm_medium=hyperlink&amp;utm_campaign=rag-vector-databases-forward-deployed-engineers\" target=\"_blank\" rel=\"noreferrer noopener\"><strong>Artificial Intelligence &amp; Machine Learning Course<\/strong><\/a>. Learn AI, machine learning, and practical application development through hands-on projects and industry-focused training.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\"><strong>How Does RAG Work?<\/strong><\/h2>\n\n\n\n<figure class=\"wp-block-image size-large\"><img decoding=\"async\" width=\"1200\" height=\"629\" src=\"https:\/\/www.guvi.in\/blog\/wp-content\/uploads\/2026\/09\/image-506-1200x629.png\" alt=\"How Does RAG Work?\" class=\"wp-image-139490\" srcset=\"https:\/\/www.guvi.in\/blog\/wp-content\/uploads\/2026\/09\/image-506-1200x629.png 1200w, https:\/\/www.guvi.in\/blog\/wp-content\/uploads\/2026\/09\/image-506-300x157.png 300w, https:\/\/www.guvi.in\/blog\/wp-content\/uploads\/2026\/09\/image-506-768x402.png 768w, https:\/\/www.guvi.in\/blog\/wp-content\/uploads\/2026\/09\/image-506-1536x805.png 1536w, https:\/\/www.guvi.in\/blog\/wp-content\/uploads\/2026\/09\/image-506-150x79.png 150w, https:\/\/www.guvi.in\/blog\/wp-content\/uploads\/2026\/09\/image-506.png 1733w\" sizes=\"(max-width: 1200px) 100vw, 1200px\" title=\"\"><\/figure>\n\n\n\n<p>A typical RAG system has two main stages: indexing and retrieval.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>1. Indexing<\/strong><\/h3>\n\n\n\n<p>Customer information is first prepared for searching.<\/p>\n\n\n\n<p>The process usually involves:<\/p>\n\n\n\n<ol>\n<li>Collecting documents or data.<\/li>\n\n\n\n<li>Splitting content into smaller chunks.<\/li>\n\n\n\n<li>Generating embeddings for each chunk.<\/li>\n\n\n\n<li>Storing embeddings and metadata in a vector database.<\/li>\n<\/ol>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>2. Retrieval and Generation<\/strong><\/h3>\n\n\n\n<p>When a user asks a question:<\/p>\n\n\n\n<ol>\n<li>The question is converted into an embedding.<\/li>\n\n\n\n<li>The system searches for similar content.<\/li>\n\n\n\n<li>Relevant chunks are retrieved.<\/li>\n\n\n\n<li>The retrieved information is added to the model&#8217;s context.<\/li>\n\n\n\n<li>The language model generates an answer using that context.<\/li>\n<\/ol>\n\n\n\n<p>This approach allows an AI application to work with changing or private information without requiring the underlying language model to be retrained for every update.<\/p>\n\n\n\n<div style=\"background-color: #099f4e; border: 3px solid #110053; border-radius: 12px; padding: 18px 22px; color: #FFFFFF; font-size: 18px; font-family: Montserrat, Helvetica, sans-serif; line-height: 1.6; box-shadow: 0 4px 12px rgba(0, 0, 0, 0.15); max-width: 750px;\"> \n  <strong style=\"font-size: 22px; color: #FFFFFF;\">\ud83d\udca1 Did You Know?<\/strong> \n  <br \/><br \/> \n  RAG can reduce the need to put an organization&#8217;s entire knowledge base directly into a model prompt. Instead, the system retrieves only information relevant to the current query.\n<\/div>\n\n\n\n<h2 class=\"wp-block-heading\"><strong>Why Do FDEs Need RAG and Vector Databases?<\/strong><\/h2>\n\n\n\n<p>FDEs often build AI solutions around customer-specific data. Generic AI models may not have access to a customer&#8217;s internal documentation, policies, product information, or operational knowledge.<\/p>\n\n\n\n<p>RAG can help solve this problem by connecting the model to the customer&#8217;s existing information sources.<\/p>\n\n\n\n<p>For example, an FDE working with a company could build an internal AI assistant that answers questions about:<\/p>\n\n\n\n<ul>\n<li>Company policies<\/li>\n\n\n\n<li>Product documentation<\/li>\n\n\n\n<li>Technical manuals<\/li>\n\n\n\n<li>Support knowledge bases<\/li>\n\n\n\n<li>Internal procedures<\/li>\n\n\n\n<li>Customer records<\/li>\n<\/ul>\n\n\n\n<p>The engineer must do more than connect a language model. They need to understand where the data comes from, how it should be indexed, who can access it, and how the system should behave when information is missing.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\"><strong>How Do Vector Databases Support RAG?<\/strong><\/h2>\n\n\n\n<p><a href=\"https:\/\/www.guvi.in\/blog\/what-is-a-vector-database-in-ai\/\" target=\"_blank\" rel=\"noreferrer noopener\">Vector databases<\/a> provide the search layer of many RAG systems.<\/p>\n\n\n\n<p>Traditional databases are excellent for structured queries such as finding a customer by ID. Vector search is useful when the system needs to find content that is conceptually similar to a query.<\/p>\n\n\n\n<p>A vector database can store:<\/p>\n\n\n\n<ul>\n<li>Embeddings<\/li>\n\n\n\n<li>Original text or references<\/li>\n\n\n\n<li>Metadata<\/li>\n\n\n\n<li>Document identifiers<\/li>\n\n\n\n<li>Access information<\/li>\n<\/ul>\n\n\n\n<p>Metadata can help filter results based on attributes such as department, document type, date, or user permissions.<\/p>\n\n\n\n<p>Popular vector database technologies include purpose-built vector databases as well as traditional databases that support vector search.<\/p>\n\n\n\n<p>The important skill for an FDE is understanding the underlying concepts rather than memorizing one particular product.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\"><strong>What Does a RAG Workflow Look Like?<\/strong><\/h2>\n\n\n\n<p>A practical customer deployment might follow this workflow:<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code><strong>Customer Data \u2192 Ingestion \u2192 Chunking \u2192 Embeddings \u2192 Vector Storage \u2192 Retrieval \u2192 LLM \u2192 Response<\/strong><\/code><\/pre>\n\n\n\n<p>Consider a customer with thousands of technical documents.<\/p>\n\n\n\n<p>An FDE could create a pipeline that:<\/p>\n\n\n\n<ul>\n<li>Collects documents from existing systems.<\/li>\n\n\n\n<li>Extracts and cleans their content.<\/li>\n\n\n\n<li>Splits documents into useful chunks.<\/li>\n\n\n\n<li>Generates embeddings.<\/li>\n\n\n\n<li>Stores them with metadata.<\/li>\n\n\n\n<li>Retrieves relevant content for each question.<\/li>\n\n\n\n<li>Sends the retrieved context to an LLM.<\/li>\n\n\n\n<li>Returns an answer to the user.<\/li>\n<\/ul>\n\n\n\n<p>The engineer would then evaluate retrieval quality and response accuracy before deploying the application.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\"><strong>What Skills Should FDEs Learn?<\/strong><\/h2>\n\n\n\n<p>FDEs working with RAG systems should develop skills across several areas.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>1. Programming and APIs<\/strong><\/h3>\n\n\n\n<p><a href=\"https:\/\/www.guvi.in\/hub\/python\/\" target=\"_blank\" rel=\"noreferrer noopener\">Python<\/a> is particularly useful for building ingestion pipelines, retrieval services, and integrations. Knowledge of <a href=\"https:\/\/www.guvi.in\/blog\/what-is-rest-api\/\" target=\"_blank\" rel=\"noreferrer noopener\">REST APIs <\/a>helps connect the RAG application to customer systems.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>2. Embeddings and Retrieval<\/strong><\/h3>\n\n\n\n<p>Understand:<\/p>\n\n\n\n<ul>\n<li>What embeddings represent<\/li>\n\n\n\n<li>How similarity search works<\/li>\n\n\n\n<li>Chunking strategies<\/li>\n\n\n\n<li>Metadata filtering<\/li>\n\n\n\n<li>Retrieval ranking<\/li>\n<\/ul>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>3. Databases<\/strong><\/h3>\n\n\n\n<p>Basic <a href=\"https:\/\/www.guvi.in\/blog\/guide-on-sql-for-data-science\/\" target=\"_blank\" rel=\"noreferrer noopener\">SQL <\/a>and database concepts remain valuable even when using vector search because customer data often exists across multiple storage systems.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>4. AI and LLMs<\/strong><\/h3>\n\n\n\n<p>Learn how language models use context, prompts, tokens, and retrieved information. FDEs should also understand the limitations of <a href=\"https:\/\/www.guvi.in\/blog\/guide-to-large-language-models\/\" target=\"_blank\" rel=\"noreferrer noopener\">LLM<\/a>-generated responses.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>5. Deployment and Monitoring<\/strong><\/h3>\n\n\n\n<p>Customer-facing RAG applications need reliable deployment, logging, monitoring, access control, and error handling.<\/p>\n\n\n\n<figure class=\"wp-block-pullquote\"><blockquote><p><strong>Pro Tip:<\/strong> Build a small document-question-answering project using Python, embeddings, a vector database, and an LLM. Then add metadata filtering and evaluation to make the project more representative of an enterprise deployment.<\/p><\/blockquote><\/figure>\n\n\n\n<figure class=\"wp-block-embed is-type-video is-provider-youtube wp-block-embed-youtube\"><div class=\"wp-block-embed__wrapper\">\n<div class=\"container-lazyload preview-lazyload container-youtube js-lazyload--not-loaded\"><a href=\"https:\/\/www.youtube.com\/watch?v=wAnoNodsIFE&#038;pp=0gcJCSQMAYcqIYzv\" class=\"lazy-load-youtube preview-lazyload preview-youtube\" data-video-title=\"Generative AI Engineering: Foundations, RAG &amp; Deployment - Workshop | HCL GUVI\" title=\"Play video &quot;Generative AI Engineering: Foundations, RAG &amp; Deployment - Workshop | HCL GUVI&quot;\" target=\"_blank\" rel=\"noopener\">https:\/\/www.youtube.com\/watch?v=wAnoNodsIFE&#038;pp=0gcJCSQMAYcqIYzv<\/a><noscript>Video can&#8217;t be loaded because JavaScript is disabled: <a href=\"https:\/\/www.youtube.com\/watch?v=wAnoNodsIFE&#038;pp=0gcJCSQMAYcqIYzv\" title=\"Generative AI Engineering: Foundations, RAG &amp; Deployment - Workshop | HCL GUVI\" target=\"_blank\" rel=\"noopener\">Generative AI Engineering: Foundations, RAG &amp; Deployment &#8211; Workshop | HCL GUVI (https:\/\/www.youtube.com\/watch?v=wAnoNodsIFE&#038;pp=0gcJCSQMAYcqIYzv)<\/a><\/noscript><\/div>\n<\/div><\/figure>\n\n\n\n<h2 class=\"wp-block-heading\"><strong>What Challenges Do FDEs Face With RAG?<\/strong><\/h2>\n\n\n\n<p>RAG systems can produce poor results even when the language model itself is capable.<\/p>\n\n\n\n<p>Common challenges include:<\/p>\n\n\n\n<ul>\n<li>Poor-quality source documents<\/li>\n\n\n\n<li>Incorrect chunk sizes<\/li>\n\n\n\n<li>Weak retrieval results<\/li>\n\n\n\n<li>Outdated information<\/li>\n\n\n\n<li>Duplicate content<\/li>\n\n\n\n<li>Missing metadata<\/li>\n\n\n\n<li>Access-control problems<\/li>\n\n\n\n<li>High latency<\/li>\n\n\n\n<li>Incorrect model responses<\/li>\n<\/ul>\n\n\n\n<figure class=\"wp-block-pullquote\"><blockquote><p><strong>Warning:<\/strong> Adding a vector database does not automatically make an AI application accurate. Retrieval quality, source data, permissions, evaluation, and prompt design all affect the final result.<\/p><\/blockquote><\/figure>\n\n\n\n<p>FDEs should test the system using realistic customer questions and continuously improve the retrieval pipeline based on observed failures.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\"><strong>Start Your Learning Journey with HCL GUVI<\/strong><\/h2>\n\n\n\n<p>Explore modern AI technologies with <strong>HCL GUVI&#8217;s <\/strong><a href=\"https:\/\/www.guvi.in\/mlp\/artificial-intelligence-and-machine-learning?utm_source=blog&amp;utm_medium=hyperlink&amp;utm_campaign=rag-vector-databases-forward-deployed-engineers\" target=\"_blank\" rel=\"noreferrer noopener\"><strong>Artificial Intelligence &amp; Machine Learning Course<\/strong><\/a>. Learn AI, machine learning, and practical application development through hands-on projects and industry-focused training.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\"><strong>Conclusion<\/strong><\/h2>\n\n\n\n<p>Understanding <strong>RAG and vector databases for forward deployed engineers<\/strong> can help FDEs build practical AI solutions that work with real customer data. RAG provides the architecture for retrieving relevant information, while vector databases provide an efficient way to search that information using embeddings.<\/p>\n\n\n\n<p>For FDEs, the most important skill is not simply knowing how to connect an LLM to a vector database. It is understanding the complete workflow from customer data ingestion to retrieval, generation, evaluation, security, and deployment. Building practical RAG projects is a strong way to develop these skills and prepare for customer-focused AI engineering roles.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\"><strong>FAQs<\/strong><\/h2>\n\n\n<div id=\"rank-math-faq\" class=\"rank-math-block\">\n<div class=\"rank-math-list \">\n<div id=\"faq-question-1789711373709\" class=\"rank-math-list-item\">\n<h3 class=\"rank-math-question \"><strong>What is RAG for Forward Deployed Engineers?<\/strong><\/h3>\n<div class=\"rank-math-answer \">\n\n<p>RAG is an architecture that allows an AI application to retrieve relevant external information before generating a response. FDEs can use it to build AI solutions around customer-specific knowledge.<\/p>\n\n<\/div>\n<\/div>\n<div id=\"faq-question-1789711378046\" class=\"rank-math-list-item\">\n<h3 class=\"rank-math-question \"><strong>Why are vector databases used in RAG?<\/strong><\/h3>\n<div class=\"rank-math-answer \">\n\n<p>Vector databases store embeddings and enable semantic similarity searches. This helps a RAG system retrieve information that is conceptually relevant to a user&#8217;s question.<\/p>\n\n<\/div>\n<\/div>\n<div id=\"faq-question-1789711385627\" class=\"rank-math-list-item\">\n<h3 class=\"rank-math-question \"><strong>Do FDEs need to know vector databases?<\/strong><\/h3>\n<div class=\"rank-math-answer \">\n\n<p>AI-focused FDEs can benefit significantly from understanding vector databases, embeddings, indexing, similarity search, and metadata filtering.<\/p>\n\n<\/div>\n<\/div>\n<div id=\"faq-question-1789711394044\" class=\"rank-math-list-item\">\n<h3 class=\"rank-math-question \"><strong>Is Python useful for building RAG applications?<\/strong><\/h3>\n<div class=\"rank-math-answer \">\n\n<p>Yes. Python is commonly useful for building data ingestion pipelines, API integrations, retrieval workflows, and AI applications.<\/p>\n\n<\/div>\n<\/div>\n<div id=\"faq-question-1789711401750\" class=\"rank-math-list-item\">\n<h3 class=\"rank-math-question \"><strong>What are common RAG problems?<\/strong><\/h3>\n<div class=\"rank-math-answer \">\n\n<p>Common issues include poor source data, ineffective chunking, weak retrieval, outdated information, access-control issues, latency, and inaccurate generated responses.<\/p>\n\n<\/div>\n<\/div>\n<div id=\"faq-question-1789711411584\" class=\"rank-math-list-item\">\n<h3 class=\"rank-math-question \"><strong>How can I learn RAG as a Forward Deployed Engineer?<\/strong><\/h3>\n<div class=\"rank-math-answer \">\n\n<p>Start by learning embeddings and retrieval concepts, then build a small document-question-answering application. Add APIs, metadata filtering, evaluation, logging, and deployment to make the project closer to a real customer solution.<\/p>\n\n<\/div>\n<\/div>\n<\/div>\n<\/div>","protected":false},"excerpt":{"rendered":"<p>RAG and vector databases for forward deployed engineers are important technologies for building AI applications that can work with customer-specific information. Retrieval-Augmented Generation (RAG) allows an AI system to retrieve relevant information from external sources before generating a response, while vector databases help store and search the numerical representations of that information. For FDEs, these [&hellip;]<\/p>\n","protected":false},"author":7,"featured_media":139491,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1043],"tags":[],"views":"27","authorinfo":{"name":"HCL GUVI","url":"https:\/\/www.guvi.in\/blog\/author\/guvipr\/"},"thumbnailURL":"https:\/\/www.guvi.in\/blog\/wp-content\/uploads\/2026\/09\/RAG-and-Vector-Databases-A-Forward-Deployed-Engineers-Primer-300x116.webp","_links":{"self":[{"href":"https:\/\/www.guvi.in\/blog\/wp-json\/wp\/v2\/posts\/139487"}],"collection":[{"href":"https:\/\/www.guvi.in\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.guvi.in\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.guvi.in\/blog\/wp-json\/wp\/v2\/users\/7"}],"replies":[{"embeddable":true,"href":"https:\/\/www.guvi.in\/blog\/wp-json\/wp\/v2\/comments?post=139487"}],"version-history":[{"count":6,"href":"https:\/\/www.guvi.in\/blog\/wp-json\/wp\/v2\/posts\/139487\/revisions"}],"predecessor-version":[{"id":139549,"href":"https:\/\/www.guvi.in\/blog\/wp-json\/wp\/v2\/posts\/139487\/revisions\/139549"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.guvi.in\/blog\/wp-json\/wp\/v2\/media\/139491"}],"wp:attachment":[{"href":"https:\/\/www.guvi.in\/blog\/wp-json\/wp\/v2\/media?parent=139487"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.guvi.in\/blog\/wp-json\/wp\/v2\/categories?post=139487"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.guvi.in\/blog\/wp-json\/wp\/v2\/tags?post=139487"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}