{"id":23,"date":"2026-08-30T03:47:39","date_gmt":"2026-08-30T03:47:39","guid":{"rendered":"https:\/\/wordpress.nevatal.id\/2026\/08\/30\/crag-multihop-reasoning-engine-guide\/"},"modified":"2026-09-06T08:42:02","modified_gmt":"2026-09-06T08:42:02","slug":"crag-multihop-reasoning-engine-guide","status":"publish","type":"post","link":"https:\/\/wordpress.nevatal.id\/2026\/08\/30\/crag-multihop-reasoning-engine-guide\/","title":{"rendered":"CRAG MultiHop Reasoning Engine: Self-Grading RAG with Query Decomposition"},"content":{"rendered":"<h1>CRAG MultiHop Reasoning Engine: Self-Grading RAG with Query Decomposition<\/h1>\n<div class=\"callout\" style=\"background:#f0f9ff; border-left:4px solid #0284c7; padding:15px; margin:20px 0; border-radius:4px;\">\n<h3 style=\"margin-top:0;\">Key Takeaways<\/h3>\n<ul>\n<li><strong>Multi-hop reasoning<\/strong> decomposes complex questions into logical sub-queries (up to 3 hops)<\/li>\n<li><strong>Self-grading retrieval<\/strong> classifies context as correct\/ambiguous\/incorrect with automated fallback<\/li>\n<li><strong>Hybrid search pipeline<\/strong> merges dense vectors (ChromaDB) + sparse BM25 with Jina reranker<\/li>\n<li><strong>WebSocket UI<\/strong> visualizes real-time pipeline progress from retrieval to generation<\/li>\n<li><strong>Graceful degradation<\/strong> maintains functionality when components fail (e.g., falls back to BM25 if vector search fails)<\/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 face two critical limitations:<\/p>\n<ol>\n<li><strong>The Multi-Hop Problem:<\/strong> Complex research questions often require chaining multiple information retrieval steps. A single query cannot directly answer &#8220;What were the economic impacts of the 2021 Suez Canal obstruction on European manufacturing?&#8221;\u2014it needs sequential searches about the obstruction timeline, affected shipping routes, then regional economic data.<\/li>\n<li><strong>Garbage-In, Garbage-Out Retrieval:<\/strong> Standard retrievers frequently return noisy or irrelevant chunks. When LLMs generate answers from these weak contexts, hallucinations and inaccuracies propagate.<\/li>\n<\/ol>\n<p>CRAG MultiHop Reasoning Engine addresses both through its <strong>query decomposition<\/strong> and <strong>self-correcting retrieval<\/strong> architecture.<\/p>\n<h2>Core Architecture &#038; Technical Stack Deep-Dive<\/h2>\n<h3>System Topology<\/h3>\n<p>The containerized deployment runs:<\/p>\n<ul>\n<li><strong>Frontend:<\/strong> React + Vite with WebSocket event streaming<\/li>\n<li><strong>Backend:<\/strong> Django ASGI (Daphne) handling HTTP\/WS routes<\/li>\n<li><strong>Workers:<\/strong> Celery + Redis for async document ingestion<\/li>\n<li><strong>Datastores:<\/strong> ChromaDB (vectors), PostgreSQL (metadata), BM25 (sparse)<\/li>\n<li><strong>Models:<\/strong> Hybrid local\/cloud execution (Jina reranker + OpenRouter LLMs)<\/li>\n<\/ul>\n<h3>Pipeline Models<\/h3>\n<table>\n<thead>\n<tr>\n<th>Role<\/th>\n<th>Model<\/th>\n<th>Execution<\/th>\n<th>Purpose<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td>Embeddings<\/td>\n<td>Multilingual-E5<\/td>\n<td>Local CPU<\/td>\n<td>Chunk vectorization<\/td>\n<\/tr>\n<tr>\n<td>Reranker<\/td>\n<td>Jina-Reranker-v3<\/td>\n<td>Local CPU<\/td>\n<td>Hybrid result ordering<\/td>\n<\/tr>\n<tr>\n<td>CRAG Evaluator<\/td>\n<td>Multilingual-E5<\/td>\n<td>Local CPU<\/td>\n<td>Retrieval self-grading<\/td>\n<\/tr>\n<tr>\n<td>Generator<\/td>\n<td>Qwen-30B<\/td>\n<td>Cloud (OpenRouter)<\/td>\n<td>Answer synthesis<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<h2>Key Features Breakdown &#038; Practical Benefits<\/h2>\n<h3>1. Query Decomposition Engine<\/h3>\n<p>For multi-hop questions like &#8220;How did Tesla&#8217;s 2023 price cuts affect BYD&#8217;s Q2 sales in Germany?&#8221;, the system:<\/p>\n<ol>\n<li>Identifies required sub-queries (Tesla&#8217;s price cuts \u2192 BYD&#8217;s Germany market share \u2192 Q2 sales reports)<\/li>\n<li>Executes retrievals sequentially, feeding prior results into subsequent hops<\/li>\n<li>Merges evidence chains for final generation<\/li>\n<\/ol>\n<h3>2. Self-Grading Retrieval (CRAG)<\/h3>\n<p>Before passing chunks to the LLM, the pipeline evaluates their relevance:<\/p>\n<ul>\n<li><strong>Correct:<\/strong> High similarity to query \u2192 Proceeds to reranking<\/li>\n<li><strong>Ambiguous:<\/strong> Moderate match \u2192 Triggers query expansion with atomic terms<\/li>\n<li><strong>Incorrect:<\/strong> Low relevance \u2192 Fallback to external web search<\/li>\n<\/ul>\n<h2>Real-World Use Cases &#038; Applications<\/h2>\n<ul>\n<li><strong>Cross-Document Intelligence:<\/strong> Investigative research connecting disparate sources<\/li>\n<li><strong>Technical Documentation QA:<\/strong> Precise answers from API docs, RFCs, or manuals<\/li>\n<li><strong>Academic Literature Reviews:<\/strong> Synthesizing findings across multiple papers<\/li>\n<\/ul>\n<h2>How It Works: Step-by-Step Workflow<\/h2>\n<ol>\n<li><strong>User Query:<\/strong> Submits complex question via WebSocket<\/li>\n<li><strong>Multi-Hop Split:<\/strong> Qwen-30B decomposes into sub-queries<\/li>\n<li><strong>Hybrid Retrieval:<\/strong> Concurrent BM25 + vector search<\/li>\n<li><strong>CRAG Grading:<\/strong> E5 model scores chunk relevance<\/li>\n<li><strong>Reranking:<\/strong> Jina model orders top candidates<\/li>\n<li><strong>Generation:<\/strong> Qwen-30B synthesizes final answer<\/li>\n<\/ol>\n<h2>Comparison: CRAG vs Traditional RAG<\/h2>\n<table>\n<thead>\n<tr>\n<th>Feature<\/th>\n<th>Traditional RAG<\/th>\n<th>CRAG MultiHop<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td>Query Handling<\/td>\n<td>Single-step retrieval<\/td>\n<td>Multi-hop decomposition<\/td>\n<\/tr>\n<tr>\n<td>Retrieval QA<\/td>\n<td>No self-assessment<\/td>\n<td>Grades as correct\/ambiguous\/incorrect<\/td>\n<\/tr>\n<tr>\n<td>Fallback<\/td>\n<td>None<\/td>\n<td>External search on weak retrievals<\/td>\n<\/tr>\n<tr>\n<td>Pipeline Visibility<\/td>\n<td>Black box<\/td>\n<td>Real-time WebSocket events<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<h2>Frequently Asked Questions (FAQ)<\/h2>\n<h3>How many hops can CRAG process?<\/h3>\n<p>Default maximum of 3 hops to balance depth and latency. Configurable via UI settings.<\/p>\n<h3>What file formats are supported for uploads?<\/h3>\n<p>PDF, plain text (TXT), and web URLs with automated background parsing.<\/p>\n<h3>Does it work without GPU acceleration?<\/h3>\n<p>Yes\u2014Jina reranker and E5 evaluator run efficiently on CPU-only environments.<\/p>\n<h3>How is this different from LangChain agents?<\/h3>\n<p>CRAG specializes in self-grading retrieval with corrective actions, whereas LangChain offers broader agent tooling without built-in retrieval QA.<\/p>\n<h2>Conclusion &#038; Next Steps<\/h2>\n<p>CRAG MultiHop Reasoning Engine sets a new standard for reliable, multi-step question answering. Its self-correcting architecture and real-time pipeline transparency make it ideal for research-intensive domains.<\/p>\n<p><strong>Ready to test it?<\/strong> Experience the live demo at <a href=\"https:\/\/crag.nevatal.tech\">crag.nevatal.tech<\/a> or explore the architecture diagrams for implementation insights.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>The CRAG MultiHop Reasoning Engine combines multi-step query decomposition with self-grading retrieval and hybrid search to solve complex research questions. Its corrective mechanisms automatically detect and fix weak context retrieval.<\/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":[1],"tags":[67,61,63,64,69,26,66,62,65,68],"class_list":["post-23","post","type-post","status-publish","format-standard","hentry","category-uncategorized","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: Self-Grading RAG with Query Decomposition<\/title>\n<meta name=\"description\" content=\"Explore CRAG MultiHop Reasoning Engine - a self-grading RAG system with query decomposition, hybrid retrieval, and real-time pipeline visualization. Ideal for complex research.\" \/>\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\/08\/30\/crag-multihop-reasoning-engine-guide\/\" \/>\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: Self-Grading RAG with Query Decomposition\" \/>\n<meta property=\"og:description\" content=\"Explore CRAG MultiHop Reasoning Engine - a self-grading RAG system with query decomposition, hybrid retrieval, and real-time pipeline visualization. Ideal for complex research.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/wordpress.nevatal.id\/2026\/08\/30\/crag-multihop-reasoning-engine-guide\/\" \/>\n<meta property=\"og:site_name\" content=\"Nevatal\" \/>\n<meta property=\"article:published_time\" content=\"2026-08-30T03:47:39+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2026-09-06T08:42:02+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\\\/08\\\/30\\\/crag-multihop-reasoning-engine-guide\\\/#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/wordpress.nevatal.id\\\/2026\\\/08\\\/30\\\/crag-multihop-reasoning-engine-guide\\\/\"},\"author\":{\"name\":\"play258\",\"@id\":\"https:\\\/\\\/wordpress.nevatal.id\\\/#\\\/schema\\\/person\\\/d2821efbaf1c66c1392f012a520ebd73\"},\"headline\":\"CRAG MultiHop Reasoning Engine: Self-Grading RAG with Query Decomposition\",\"datePublished\":\"2026-08-30T03:47:39+00:00\",\"dateModified\":\"2026-09-06T08:42:02+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/wordpress.nevatal.id\\\/2026\\\/08\\\/30\\\/crag-multihop-reasoning-engine-guide\\\/\"},\"wordCount\":606,\"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\"],\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"CommentAction\",\"name\":\"Comment\",\"target\":[\"https:\\\/\\\/wordpress.nevatal.id\\\/2026\\\/08\\\/30\\\/crag-multihop-reasoning-engine-guide\\\/#respond\"]}]},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/wordpress.nevatal.id\\\/2026\\\/08\\\/30\\\/crag-multihop-reasoning-engine-guide\\\/\",\"url\":\"https:\\\/\\\/wordpress.nevatal.id\\\/2026\\\/08\\\/30\\\/crag-multihop-reasoning-engine-guide\\\/\",\"name\":\"CRAG MultiHop Reasoning Engine: Self-Grading RAG with Query Decomposition\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/wordpress.nevatal.id\\\/#website\"},\"datePublished\":\"2026-08-30T03:47:39+00:00\",\"dateModified\":\"2026-09-06T08:42:02+00:00\",\"description\":\"Explore CRAG MultiHop Reasoning Engine - a self-grading RAG system with query decomposition, hybrid retrieval, and real-time pipeline visualization. Ideal for complex research.\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/wordpress.nevatal.id\\\/2026\\\/08\\\/30\\\/crag-multihop-reasoning-engine-guide\\\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/wordpress.nevatal.id\\\/2026\\\/08\\\/30\\\/crag-multihop-reasoning-engine-guide\\\/\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/wordpress.nevatal.id\\\/2026\\\/08\\\/30\\\/crag-multihop-reasoning-engine-guide\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/wordpress.nevatal.id\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"CRAG MultiHop Reasoning Engine: Self-Grading RAG with Query Decomposition\"}]},{\"@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: Self-Grading RAG with Query Decomposition","description":"Explore CRAG MultiHop Reasoning Engine - a self-grading RAG system with query decomposition, hybrid retrieval, and real-time pipeline visualization. Ideal for complex research.","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\/08\/30\/crag-multihop-reasoning-engine-guide\/","og_locale":"en_US","og_type":"article","og_title":"CRAG MultiHop Reasoning Engine: Self-Grading RAG with Query Decomposition","og_description":"Explore CRAG MultiHop Reasoning Engine - a self-grading RAG system with query decomposition, hybrid retrieval, and real-time pipeline visualization. Ideal for complex research.","og_url":"https:\/\/wordpress.nevatal.id\/2026\/08\/30\/crag-multihop-reasoning-engine-guide\/","og_site_name":"Nevatal","article_published_time":"2026-08-30T03:47:39+00:00","article_modified_time":"2026-09-06T08:42:02+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\/08\/30\/crag-multihop-reasoning-engine-guide\/#article","isPartOf":{"@id":"https:\/\/wordpress.nevatal.id\/2026\/08\/30\/crag-multihop-reasoning-engine-guide\/"},"author":{"name":"play258","@id":"https:\/\/wordpress.nevatal.id\/#\/schema\/person\/d2821efbaf1c66c1392f012a520ebd73"},"headline":"CRAG MultiHop Reasoning Engine: Self-Grading RAG with Query Decomposition","datePublished":"2026-08-30T03:47:39+00:00","dateModified":"2026-09-06T08:42:02+00:00","mainEntityOfPage":{"@id":"https:\/\/wordpress.nevatal.id\/2026\/08\/30\/crag-multihop-reasoning-engine-guide\/"},"wordCount":606,"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"],"inLanguage":"en-US","potentialAction":[{"@type":"CommentAction","name":"Comment","target":["https:\/\/wordpress.nevatal.id\/2026\/08\/30\/crag-multihop-reasoning-engine-guide\/#respond"]}]},{"@type":"WebPage","@id":"https:\/\/wordpress.nevatal.id\/2026\/08\/30\/crag-multihop-reasoning-engine-guide\/","url":"https:\/\/wordpress.nevatal.id\/2026\/08\/30\/crag-multihop-reasoning-engine-guide\/","name":"CRAG MultiHop Reasoning Engine: Self-Grading RAG with Query Decomposition","isPartOf":{"@id":"https:\/\/wordpress.nevatal.id\/#website"},"datePublished":"2026-08-30T03:47:39+00:00","dateModified":"2026-09-06T08:42:02+00:00","description":"Explore CRAG MultiHop Reasoning Engine - a self-grading RAG system with query decomposition, hybrid retrieval, and real-time pipeline visualization. Ideal for complex research.","breadcrumb":{"@id":"https:\/\/wordpress.nevatal.id\/2026\/08\/30\/crag-multihop-reasoning-engine-guide\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/wordpress.nevatal.id\/2026\/08\/30\/crag-multihop-reasoning-engine-guide\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/wordpress.nevatal.id\/2026\/08\/30\/crag-multihop-reasoning-engine-guide\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/wordpress.nevatal.id\/"},{"@type":"ListItem","position":2,"name":"CRAG MultiHop Reasoning Engine: Self-Grading RAG with Query Decomposition"}]},{"@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\/23","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=23"}],"version-history":[{"count":1,"href":"https:\/\/wordpress.nevatal.id\/wp-json\/wp\/v2\/posts\/23\/revisions"}],"predecessor-version":[{"id":78,"href":"https:\/\/wordpress.nevatal.id\/wp-json\/wp\/v2\/posts\/23\/revisions\/78"}],"wp:attachment":[{"href":"https:\/\/wordpress.nevatal.id\/wp-json\/wp\/v2\/media?parent=23"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/wordpress.nevatal.id\/wp-json\/wp\/v2\/categories?post=23"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/wordpress.nevatal.id\/wp-json\/wp\/v2\/tags?post=23"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}