{"id":313,"date":"2026-09-17T13:46:45","date_gmt":"2026-09-17T13:46:45","guid":{"rendered":"https:\/\/wordpress.nevatal.id\/2026\/09\/17\/crag-multihop-reasoning-engine-comparison-alternatives-2\/"},"modified":"2026-09-17T13:46:45","modified_gmt":"2026-09-17T13:46:45","slug":"crag-multihop-reasoning-engine-comparison-alternatives-2","status":"publish","type":"post","link":"https:\/\/wordpress.nevatal.id\/2026\/09\/17\/crag-multihop-reasoning-engine-comparison-alternatives-2\/","title":{"rendered":"CRAG MultiHop Reasoning Engine: A Comprehensive Comparison &#038; Alternatives Breakdown"},"content":{"rendered":"<h1>CRAG MultiHop Reasoning Engine: A Comprehensive Comparison &#038; Alternatives Breakdown<\/h1>\n<div class=\"callout\" style=\"background:#f0f9ff; border-left:4px solid #0284c7; padding:15px; margin:20px 0; border-radius:4px;\">\n<h3>Key Takeaways<\/h3>\n<ul>\n<li>The CRAG MultiHop Reasoning Engine solves complex multi-step queries by decomposing them into logical sub-queries.<\/li>\n<li>It features self-grading retrieval, ensuring only accurate and relevant context is used for answer generation.<\/li>\n<li>Hybrid retrieval combines dense vector and BM25 sparse search for optimal results.<\/li>\n<li>Real-time WebSocket streaming provides transparency into the pipeline&#8217;s progress.<\/li>\n<li>Explore the live project: <a href=\"https:\/\/crag.nevatal.tech\" target=\"_blank\" rel=\"noopener noreferrer\">https:\/\/crag.nevatal.tech<\/a><\/li>\n<\/ul>\n<\/div>\n<h2>The Challenge: Why CRAG MultiHop Reasoning Engine Was Built<\/h2>\n<p>Traditional Retrieval-Augmented Generation (RAG) systems often struggle with complex queries that require multi-step reasoning. These systems typically retrieve context in a single step, leading to inaccuracies when dealing with ambiguous or insufficient information. The CRAG MultiHop Reasoning Engine was developed to address these challenges by introducing advanced features like query decomposition, self-grading retrieval, and hybrid retrieval.<\/p>\n<h2>Core Architecture &#038; Technical Stack Deep-Dive<\/h2>\n<p>The CRAG MultiHop Reasoning Engine leverages a robust tech stack to deliver its advanced capabilities:<\/p>\n<ul>\n<li><strong>Backend:<\/strong> Django ASGI \/ Daphne for handling HTTP and WebSocket connections.<\/li>\n<li><strong>Frontend:<\/strong> React + Vite for a responsive and dynamic user interface.<\/li>\n<li><strong>Database:<\/strong> ChromaDB for vector storage, PostgreSQL for relational data, and Redis for task queuing.<\/li>\n<li><strong>Retrieval:<\/strong> Hybrid dense vector and BM25 sparse retrieval merged and ranked via Jina Reranker v3.<\/li>\n<li><strong>Language Models:<\/strong> Utilizes OpenRouter&#8217;s Qwen 30B for answer generation.<\/li>\n<\/ul>\n<h2>Key Features Breakdown &#038; Practical Benefits<\/h2>\n<h3>Sequential Multi-Hop Query Decomposition<\/h3>\n<p>The engine breaks down complex questions into logical sub-queries, enabling multi-step reasoning up to three hops. This ensures that the system can handle intricate queries that require connecting information from multiple documents.<\/p>\n<h3>Corrective RAG (CRAG) Self-Grading Evaluator<\/h3>\n<p>The self-grading evaluator classifies retrieved context as correct, ambiguous, or incorrect. For ambiguous or insufficient context, the system automatically falls back to live external search, ensuring that the generated answers are accurate and reliable.<\/p>\n<h3>Hybrid Retrieval &#038; Local Reranking<\/h3>\n<p>By combining dense vector search with BM25 sparse retrieval, the engine ensures comprehensive context retrieval. The local Cross-Encoder (jina-reranker-v3) then reranks the results, placing the most relevant chunks at the beginning of the context window.<\/p>\n<h2>Real-World Use Cases &#038; Applications<\/h2>\n<p>The CRAG MultiHop Reasoning Engine is ideal for:<\/p>\n<ul>\n<li>Complex research and multi-document intelligence investigations requiring multi-step deductions.<\/li>\n<li>Automated high-precision document QA with self-healing fallback mechanisms.<\/li>\n<li>Developer reference implementation for self-grading agentic RAG workflows.<\/li>\n<\/ul>\n<h2>How It Works: Step-by-Step Workflow<\/h2>\n<p>The engine processes queries through a structured pipeline:<\/p>\n<ol>\n<li><strong>Query Decomposition:<\/strong> Breaks down the query into logical sub-queries.<\/li>\n<li><strong>Hybrid Retrieval:<\/strong> Combines dense vector and BM25 sparse search.<\/li>\n<li><strong>Self-Grading:<\/strong> Evaluates the retrieved context for accuracy.<\/li>\n<li><strong>Reranking:<\/strong> Orders the results using a local Cross-Encoder.<\/li>\n<li><strong>Answer Generation:<\/strong> Synthesizes the final answer using Qwen 30B.<\/li>\n<\/ol>\n<h2>Comparison: CRAG MultiHop Reasoning Engine vs Traditional Approaches<\/h2>\n<table>\n<thead>\n<tr>\n<th>Feature<\/th>\n<th>CRAG MultiHop Reasoning Engine<\/th>\n<th>Traditional RAG Systems<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td>Query Handling<\/td>\n<td>Multi-step decomposition<\/td>\n<td>Single-step retrieval<\/td>\n<\/tr>\n<tr>\n<td>Context Evaluation<\/td>\n<td>Self-grading retrieval<\/td>\n<td>No evaluation<\/td>\n<\/tr>\n<tr>\n<td>Retrieval Method<\/td>\n<td>Hybrid dense + sparse<\/td>\n<td>Single method<\/td>\n<\/tr>\n<tr>\n<td>Transparency<\/td>\n<td>Real-time WebSocket streaming<\/td>\n<td>No progress tracking<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<h2>Frequently Asked Questions (FAQ)<\/h2>\n<h3>What is Corrective RAG (CRAG)?<\/h3>\n<p>Corrective RAG (CRAG) is a self-grading evaluator that classifies retrieved context as correct, ambiguous, or incorrect, ensuring accurate answer generation.<\/p>\n<h3>How does the engine handle ambiguous context?<\/h3>\n<p>For ambiguous context, the system refines the chunks and, if necessary, falls back to live external search to retrieve accurate information.<\/p>\n<h3>Can I upload my own documents?<\/h3>\n<p>Yes, the engine supports asynchronous document ingestion for PDF, TXT, and web URLs.<\/p>\n<h3>What is the maximum number of hops supported?<\/h3>\n<p>The engine supports up to three hops for query decomposition.<\/p>\n<h2>Conclusion &#038; Next Steps<\/h2>\n<p>The CRAG MultiHop Reasoning Engine represents a significant advancement in retrieval-augmented generation, offering robust solutions for complex queries and ensuring accurate, reliable answers. Explore the live project and see it in action at <a href=\"https:\/\/crag.nevatal.tech\" target=\"_blank\" rel=\"noopener noreferrer\">https:\/\/crag.nevatal.tech<\/a>.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Explore the CRAG MultiHop Reasoning Engine, a cutting-edge AI solution for complex multi-step queries, self-grading retrieval, and hybrid retrieval. Learn how it compares to traditional RAG systems.<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_yoast_wpseo_canonical":"","_yoast_wpseo_opengraph-title":"","_yoast_wpseo_opengraph-description":"","_yoast_wpseo_twitter-title":"","_yoast_wpseo_twitter-description":"","footnotes":""},"categories":[2],"tags":[67,61,63,64,69,26,66,62,65,68],"class_list":["post-313","post","type-post","status-publish","format-standard","hentry","category-artificial-intelligence-machine-learning","tag-celery","tag-chromadb","tag-corrective-rag","tag-crag","tag-django-asgi","tag-fastapi","tag-jina-reranker","tag-multi-hop-rag","tag-query-decomposition","tag-websockets"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v28.4 - https:\/\/yoast.com\/product\/yoast-seo-wordpress\/ -->\n<title>CRAG MultiHop Reasoning Engine: A Comprehensive Comparison &amp; Alternatives Breakdown<\/title>\n<meta name=\"description\" content=\"Discover how the CRAG MultiHop Reasoning Engine outperforms traditional RAG systems with self-grading retrieval, multi-step query decomposition, and hybrid retrieval. Learn more and explore the live project.\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/wordpress.nevatal.id\/2026\/09\/17\/crag-multihop-reasoning-engine-comparison-alternatives-2\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"CRAG MultiHop Reasoning Engine: A Comprehensive Comparison &amp; Alternatives Breakdown\" \/>\n<meta property=\"og:description\" content=\"Discover how the CRAG MultiHop Reasoning Engine outperforms traditional RAG systems with self-grading retrieval, multi-step query decomposition, and hybrid retrieval. Learn more and explore the live project.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/wordpress.nevatal.id\/2026\/09\/17\/crag-multihop-reasoning-engine-comparison-alternatives-2\/\" \/>\n<meta property=\"og:site_name\" content=\"Nevatal\" \/>\n<meta property=\"article:published_time\" content=\"2026-09-17T13:46:45+00:00\" \/>\n<meta name=\"author\" content=\"play258\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"play258\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"3 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\\\/\\\/wordpress.nevatal.id\\\/2026\\\/09\\\/17\\\/crag-multihop-reasoning-engine-comparison-alternatives-2\\\/#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/wordpress.nevatal.id\\\/2026\\\/09\\\/17\\\/crag-multihop-reasoning-engine-comparison-alternatives-2\\\/\"},\"author\":{\"name\":\"play258\",\"@id\":\"https:\\\/\\\/wordpress.nevatal.id\\\/#\\\/schema\\\/person\\\/d2821efbaf1c66c1392f012a520ebd73\"},\"headline\":\"CRAG MultiHop Reasoning Engine: A Comprehensive Comparison &#038; Alternatives Breakdown\",\"datePublished\":\"2026-09-17T13:46:45+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/wordpress.nevatal.id\\\/2026\\\/09\\\/17\\\/crag-multihop-reasoning-engine-comparison-alternatives-2\\\/\"},\"wordCount\":611,\"commentCount\":0,\"publisher\":{\"@id\":\"https:\\\/\\\/wordpress.nevatal.id\\\/#\\\/schema\\\/person\\\/d2821efbaf1c66c1392f012a520ebd73\"},\"keywords\":[\"Celery\",\"ChromaDB\",\"Corrective RAG\",\"CRAG\",\"Django ASGI\",\"FastAPI\",\"Jina Reranker\",\"Multi-Hop RAG\",\"Query Decomposition\",\"WebSockets\"],\"articleSection\":[\"Artificial Intelligence &amp; Machine Learning\"],\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"CommentAction\",\"name\":\"Comment\",\"target\":[\"https:\\\/\\\/wordpress.nevatal.id\\\/2026\\\/09\\\/17\\\/crag-multihop-reasoning-engine-comparison-alternatives-2\\\/#respond\"]}]},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/wordpress.nevatal.id\\\/2026\\\/09\\\/17\\\/crag-multihop-reasoning-engine-comparison-alternatives-2\\\/\",\"url\":\"https:\\\/\\\/wordpress.nevatal.id\\\/2026\\\/09\\\/17\\\/crag-multihop-reasoning-engine-comparison-alternatives-2\\\/\",\"name\":\"CRAG MultiHop Reasoning Engine: A Comprehensive Comparison & Alternatives Breakdown\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/wordpress.nevatal.id\\\/#website\"},\"datePublished\":\"2026-09-17T13:46:45+00:00\",\"description\":\"Discover how the CRAG MultiHop Reasoning Engine outperforms traditional RAG systems with self-grading retrieval, multi-step query decomposition, and hybrid retrieval. Learn more and explore the live project.\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/wordpress.nevatal.id\\\/2026\\\/09\\\/17\\\/crag-multihop-reasoning-engine-comparison-alternatives-2\\\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/wordpress.nevatal.id\\\/2026\\\/09\\\/17\\\/crag-multihop-reasoning-engine-comparison-alternatives-2\\\/\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/wordpress.nevatal.id\\\/2026\\\/09\\\/17\\\/crag-multihop-reasoning-engine-comparison-alternatives-2\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/wordpress.nevatal.id\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"CRAG MultiHop Reasoning Engine: A Comprehensive Comparison &#038; Alternatives Breakdown\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/wordpress.nevatal.id\\\/#website\",\"url\":\"https:\\\/\\\/wordpress.nevatal.id\\\/\",\"name\":\"Nevatal\",\"description\":\"\",\"publisher\":{\"@id\":\"https:\\\/\\\/wordpress.nevatal.id\\\/#\\\/schema\\\/person\\\/d2821efbaf1c66c1392f012a520ebd73\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/wordpress.nevatal.id\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"},{\"@type\":[\"Person\",\"Organization\"],\"@id\":\"https:\\\/\\\/wordpress.nevatal.id\\\/#\\\/schema\\\/person\\\/d2821efbaf1c66c1392f012a520ebd73\",\"name\":\"play258\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/wordpress.nevatal.id\\\/wp-content\\\/uploads\\\/2026\\\/08\\\/images-1.jpg\",\"url\":\"https:\\\/\\\/wordpress.nevatal.id\\\/wp-content\\\/uploads\\\/2026\\\/08\\\/images-1.jpg\",\"contentUrl\":\"https:\\\/\\\/wordpress.nevatal.id\\\/wp-content\\\/uploads\\\/2026\\\/08\\\/images-1.jpg\",\"width\":190,\"height\":266,\"caption\":\"play258\"},\"logo\":{\"@id\":\"https:\\\/\\\/wordpress.nevatal.id\\\/wp-content\\\/uploads\\\/2026\\\/08\\\/images-1.jpg\"},\"sameAs\":[\"https:\\\/\\\/wordpress.nevatal.id\"],\"url\":\"https:\\\/\\\/wordpress.nevatal.id\\\/author\\\/play258\\\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"CRAG MultiHop Reasoning Engine: A Comprehensive Comparison & Alternatives Breakdown","description":"Discover how the CRAG MultiHop Reasoning Engine outperforms traditional RAG systems with self-grading retrieval, multi-step query decomposition, and hybrid retrieval. Learn more and explore the live project.","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/wordpress.nevatal.id\/2026\/09\/17\/crag-multihop-reasoning-engine-comparison-alternatives-2\/","og_locale":"en_US","og_type":"article","og_title":"CRAG MultiHop Reasoning Engine: A Comprehensive Comparison & Alternatives Breakdown","og_description":"Discover how the CRAG MultiHop Reasoning Engine outperforms traditional RAG systems with self-grading retrieval, multi-step query decomposition, and hybrid retrieval. Learn more and explore the live project.","og_url":"https:\/\/wordpress.nevatal.id\/2026\/09\/17\/crag-multihop-reasoning-engine-comparison-alternatives-2\/","og_site_name":"Nevatal","article_published_time":"2026-09-17T13:46:45+00:00","author":"play258","twitter_card":"summary_large_image","twitter_misc":{"Written by":"play258","Est. reading time":"3 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/wordpress.nevatal.id\/2026\/09\/17\/crag-multihop-reasoning-engine-comparison-alternatives-2\/#article","isPartOf":{"@id":"https:\/\/wordpress.nevatal.id\/2026\/09\/17\/crag-multihop-reasoning-engine-comparison-alternatives-2\/"},"author":{"name":"play258","@id":"https:\/\/wordpress.nevatal.id\/#\/schema\/person\/d2821efbaf1c66c1392f012a520ebd73"},"headline":"CRAG MultiHop Reasoning Engine: A Comprehensive Comparison &#038; Alternatives Breakdown","datePublished":"2026-09-17T13:46:45+00:00","mainEntityOfPage":{"@id":"https:\/\/wordpress.nevatal.id\/2026\/09\/17\/crag-multihop-reasoning-engine-comparison-alternatives-2\/"},"wordCount":611,"commentCount":0,"publisher":{"@id":"https:\/\/wordpress.nevatal.id\/#\/schema\/person\/d2821efbaf1c66c1392f012a520ebd73"},"keywords":["Celery","ChromaDB","Corrective RAG","CRAG","Django ASGI","FastAPI","Jina Reranker","Multi-Hop RAG","Query Decomposition","WebSockets"],"articleSection":["Artificial Intelligence &amp; Machine Learning"],"inLanguage":"en-US","potentialAction":[{"@type":"CommentAction","name":"Comment","target":["https:\/\/wordpress.nevatal.id\/2026\/09\/17\/crag-multihop-reasoning-engine-comparison-alternatives-2\/#respond"]}]},{"@type":"WebPage","@id":"https:\/\/wordpress.nevatal.id\/2026\/09\/17\/crag-multihop-reasoning-engine-comparison-alternatives-2\/","url":"https:\/\/wordpress.nevatal.id\/2026\/09\/17\/crag-multihop-reasoning-engine-comparison-alternatives-2\/","name":"CRAG MultiHop Reasoning Engine: A Comprehensive Comparison & Alternatives Breakdown","isPartOf":{"@id":"https:\/\/wordpress.nevatal.id\/#website"},"datePublished":"2026-09-17T13:46:45+00:00","description":"Discover how the CRAG MultiHop Reasoning Engine outperforms traditional RAG systems with self-grading retrieval, multi-step query decomposition, and hybrid retrieval. Learn more and explore the live project.","breadcrumb":{"@id":"https:\/\/wordpress.nevatal.id\/2026\/09\/17\/crag-multihop-reasoning-engine-comparison-alternatives-2\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/wordpress.nevatal.id\/2026\/09\/17\/crag-multihop-reasoning-engine-comparison-alternatives-2\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/wordpress.nevatal.id\/2026\/09\/17\/crag-multihop-reasoning-engine-comparison-alternatives-2\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/wordpress.nevatal.id\/"},{"@type":"ListItem","position":2,"name":"CRAG MultiHop Reasoning Engine: A Comprehensive Comparison &#038; Alternatives Breakdown"}]},{"@type":"WebSite","@id":"https:\/\/wordpress.nevatal.id\/#website","url":"https:\/\/wordpress.nevatal.id\/","name":"Nevatal","description":"","publisher":{"@id":"https:\/\/wordpress.nevatal.id\/#\/schema\/person\/d2821efbaf1c66c1392f012a520ebd73"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/wordpress.nevatal.id\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":["Person","Organization"],"@id":"https:\/\/wordpress.nevatal.id\/#\/schema\/person\/d2821efbaf1c66c1392f012a520ebd73","name":"play258","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/wordpress.nevatal.id\/wp-content\/uploads\/2026\/08\/images-1.jpg","url":"https:\/\/wordpress.nevatal.id\/wp-content\/uploads\/2026\/08\/images-1.jpg","contentUrl":"https:\/\/wordpress.nevatal.id\/wp-content\/uploads\/2026\/08\/images-1.jpg","width":190,"height":266,"caption":"play258"},"logo":{"@id":"https:\/\/wordpress.nevatal.id\/wp-content\/uploads\/2026\/08\/images-1.jpg"},"sameAs":["https:\/\/wordpress.nevatal.id"],"url":"https:\/\/wordpress.nevatal.id\/author\/play258\/"}]}},"_links":{"self":[{"href":"https:\/\/wordpress.nevatal.id\/wp-json\/wp\/v2\/posts\/313","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/wordpress.nevatal.id\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/wordpress.nevatal.id\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/wordpress.nevatal.id\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/wordpress.nevatal.id\/wp-json\/wp\/v2\/comments?post=313"}],"version-history":[{"count":0,"href":"https:\/\/wordpress.nevatal.id\/wp-json\/wp\/v2\/posts\/313\/revisions"}],"wp:attachment":[{"href":"https:\/\/wordpress.nevatal.id\/wp-json\/wp\/v2\/media?parent=313"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/wordpress.nevatal.id\/wp-json\/wp\/v2\/categories?post=313"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/wordpress.nevatal.id\/wp-json\/wp\/v2\/tags?post=313"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}