{"id":254,"date":"2026-09-13T09:09:55","date_gmt":"2026-09-13T09:09:55","guid":{"rendered":"https:\/\/wordpress.nevatal.id\/2026\/09\/13\/ragreader-multi-llm-consensus-benchmark-architecture-performance\/"},"modified":"2026-09-13T09:09:55","modified_gmt":"2026-09-13T09:09:55","slug":"ragreader-multi-llm-consensus-benchmark-architecture-performance","status":"publish","type":"post","link":"https:\/\/wordpress.nevatal.id\/2026\/09\/13\/ragreader-multi-llm-consensus-benchmark-architecture-performance\/","title":{"rendered":"RagReader &#8211; Multi-LLM Consensus &#038; Benchmark: Architecture &#038; Performance Deep Dive"},"content":{"rendered":"<h1>RagReader &#8211; Multi-LLM Consensus &#038; Benchmark: Architecture &#038; Performance Deep Dive<\/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>9-way pipeline comparison: Evaluate dense\/sparse\/hybrid retrieval paired with GPT-4, Claude 3.5, and Gemini 2.0 in a single benchmark run<\/li>\n<li>Automated ground truth generation: Eliminates manual labeling via TREC-style Reciprocal Rank Fusion (RRF) candidate pooling<\/li>\n<li>Real-time evaluation metrics: Streams Precision@K, Recall@K, ROUGE-L, and LLM-judged scores (Faithfulness, Relevance, Coverage) via WebSocket<\/li>\n<li>Deterministic benchmarking: Combines algorithmic scoring (ROUGE-L) with LLM evaluation (Mistral Nemo) for comprehensive quality assessment<\/li>\n<\/ul>\n<div class=\"project-access-box\" style=\"background:#f0f9ff; border:1px solid #bae6fd; border-left:4px solid #0284c7; padding:12px 18px; margin:20px 0; border-radius:4px;\"><strong>Live Project Access:<\/strong> <a href=\"https:\/\/rag.nevatal.tech\" target=\"_blank\" rel=\"noopener noreferrer\">https:\/\/rag.nevatal.tech<\/a><\/div>\n<\/div>\n<h2>The Challenge: Why RagReader Was Built<\/h2>\n<p>AI engineers face a critical dilemma when implementing Retrieval-Augmented Generation (RAG) systems: selecting the optimal combination of retrieval method (dense vector, sparse keyword, or hybrid) and generative LLM (GPT, Claude, or Gemini) requires extensive trial-and-error testing. Traditional approaches suffer from:<\/p>\n<ul>\n<li><strong>Subjective evaluation:<\/strong> Manual assessment of answer quality is time-consuming and prone to bias<\/li>\n<li><strong>Incomplete metrics:<\/strong> Most tools measure either retrieval quality or generation quality, but not both holistically<\/li>\n<li><strong>Costly experimentation:<\/strong> Running sequential tests across multiple configurations wastes API credits and developer time<\/li>\n<\/ul>\n<p>RagReader solves this by executing a 3\u00d73 matrix of pipelines concurrently, providing objective comparisons through:<\/p>\n<pre><code>9 Concurrent Pipelines = \n  [Dense, Sparse, Hybrid Retrieval] \u00d7 [GPT-4, Claude 3.5, Gemini 2.0]<\/code><\/pre>\n<h2>Core Architecture &#038; Technical Stack<\/h2>\n<h3>System Topology<\/h3>\n<p>The Django ASGI backend orchestrates parallel execution through a WebSocket-powered streaming architecture:<\/p>\n<pre><code>React Dashboard \u2194 Django Channels (WebSocket) \u2194 \n  \u2502\n  \u251c\u2500 Dense Pipeline (ChromaDB + Cross-Encoder)\n  \u251c\u2500 Sparse Pipeline (BM25 Index)\n  \u2514\u2500 Hybrid Pipeline (RRF Fusion + Reranker)\n     \u2502\n     \u251c\u2500 GPT-4 Generator\n     \u251c\u2500 Claude Generator\n     \u2514\u2500 Gemini Generator<\/code><\/pre>\n<h3>Key Architectural Components<\/h3>\n<ul>\n<li><strong>Concurrent Execution:<\/strong> Django Channels manages WebSocket connections while Celery workers handle parallel pipeline execution<\/li>\n<li><strong>Automated Ground Truth:<\/strong> Reciprocal Rank Fusion combines results from all retrievers to create evaluation baselines without manual labeling<\/li>\n<li><strong>Metric Calculation:<\/strong> Real-time scoring of both deterministic (ROUGE-L) and LLM-evaluated (Faithfulness\/Relevance\/Coverage) metrics<\/li>\n<\/ul>\n<h2>Key Features &#038; Practical Benefits<\/h2>\n<h3>Automated RRF Candidate Pooling<\/h3>\n<p>The system implements TREC-style evaluation methodology:<\/p>\n<pre><code>def rrf_score(doc_rank):\n    return 1.0 \/ (60.0 + doc_rank)  # Standard TREC constant<\/code><\/pre>\n<p>By aggregating results from all retrieval methods, RagReader identifies consensus-relevant chunks with higher accuracy than any single approach.<\/p>\n<h3>Multi-Dimensional Evaluation<\/h3>\n<table>\n<thead>\n<tr>\n<th>Metric Type<\/th>\n<th>Measures<\/th>\n<th>Calculation Method<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td>Retrieval Quality<\/td>\n<td>Precision@K, Recall@K, F1@K<\/td>\n<td>Ground-truth vs. retrieved chunks<\/td>\n<\/tr>\n<tr>\n<td>Text Overlap<\/td>\n<td>ROUGE-L F1<\/td>\n<td>Longest common subsequence algorithm<\/td>\n<\/tr>\n<tr>\n<td>Semantic Quality<\/td>\n<td>Faithfulness, Relevance, Coverage<\/td>\n<td>Mistral Nemo LLM evaluation (1-5 scale)<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<h2>Real-World Use Cases<\/h2>\n<ul>\n<li><strong>Enterprise RAG Optimization:<\/strong> Compare retrieval\/generation combinations before production deployment<\/li>\n<li><strong>LLM Performance Benchmarking:<\/strong> Objectively evaluate GPT\/Claude\/Gemini on proprietary documents<\/li>\n<li><strong>Automated Dataset Creation:<\/strong> Generate labeled evaluation sets without manual annotation<\/li>\n<\/ul>\n<h2>How It Works: Step-by-Step Workflow<\/h2>\n<ol>\n<li>Upload documents or connect to existing vector database<\/li>\n<li>Submit a test query and select evaluation method (Manual or RRF)<\/li>\n<li>Review automatically generated ground truth or adjust manually<\/li>\n<li>Launch Deep Dive analysis to execute all 9 pipelines<\/li>\n<li>Compare real-time metrics in streaming dashboard<\/li>\n<\/ol>\n<h2>Comparison: RagReader vs Traditional Approaches<\/h2>\n<table>\n<thead>\n<tr>\n<th>Feature<\/th>\n<th>RagReader<\/th>\n<th>Traditional Testing<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td>Parallel Evaluation<\/td>\n<td>9 concurrent pipelines<\/td>\n<td>Sequential testing<\/td>\n<\/tr>\n<tr>\n<td>Ground Truth<\/td>\n<td>Automated RRF pooling<\/td>\n<td>Manual labeling<\/td>\n<\/tr>\n<tr>\n<td>Metrics<\/td>\n<td>Precision@K + ROUGE-L + LLM eval<\/td>\n<td>Single metric focus<\/td>\n<\/tr>\n<tr>\n<td>Cost<\/td>\n<td>Single test run<\/td>\n<td>Multiple API calls<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<h2>Frequently Asked Questions<\/h2>\n<h3>1. How does automated ground truth generation work?<\/h3>\n<p>RagReader uses Reciprocal Rank Fusion to combine results from all three retrieval methods (dense, sparse, hybrid). The top consensus chunks become the evaluation baseline.<\/p>\n<h3>2. What&#8217;s the advantage of WebSocket streaming?<\/h3>\n<p>Real-time updates let developers spot performance differences immediately, rather than waiting for all pipelines to complete.<\/p>\n<h3>3. How does the LLM evaluation work?<\/h3>\n<p>Mistral Nemo scores each answer on three dimensions: Faithfulness (factual consistency), Relevance (query alignment), and Coverage (information completeness).<\/p>\n<h3>4. Can I use custom LLMs or retrievers?<\/h3>\n<p>The current version supports predefined configurations, but the architecture allows for extension through Django&#8217;s plugin system.<\/p>\n<h2>Conclusion &#038; Next Steps<\/h2>\n<p>RagReader provides AI developers with an unprecedented capability to objectively compare RAG configurations through its 9-way parallel execution engine and multi-dimensional evaluation methodology. By combining algorithmic scoring with LLM judgment, it delivers comprehensive insights into both retrieval effectiveness and generation quality.<\/p>\n<p>To experience the benchmark dashboard firsthand, visit the live project at <a href=\"https:\/\/rag.nevatal.tech\">https:\/\/rag.nevatal.tech<\/a> and run your own comparative analysis.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>RagReader is a diagnostic platform that benchmarks 9 concurrent RAG configurations (Dense\/Sparse\/Hybrid \u00d7 GPT\/Claude\/Gemini) with automated ground-truth generation and real-time performance metrics. This technical deep dive explores its architecture, evaluation methodology, and enterprise use cases.<\/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":[70],"tags":[77,73,75,72,71,76,74,68],"class_list":["post-254","post","type-post","status-publish","format-standard","hentry","category-artificial-intelligence-developer-tools","tag-django-channels","tag-evaluation-metrics","tag-faithfulness-scoring","tag-multi-llm-consensus","tag-rag-benchmark","tag-reciprocal-rank-fusion","tag-rouge-l","tag-websockets"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v28.4 - https:\/\/yoast.com\/product\/yoast-seo-wordpress\/ -->\n<title>RagReader - Multi-LLM Consensus &amp; Benchmark: Architecture &amp; Performance Deep Dive<\/title>\n<meta name=\"description\" content=\"Discover RagReader&#039;s architecture for comparing 9 RAG pipelines with automated benchmarking. Optimize your AI QA system with precision metrics, RRF candidate pooling, and multi-LLM evaluation.\" \/>\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\/13\/ragreader-multi-llm-consensus-benchmark-architecture-performance\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"RagReader - Multi-LLM Consensus &amp; Benchmark: Architecture &amp; Performance Deep Dive\" \/>\n<meta property=\"og:description\" content=\"Discover RagReader&#039;s architecture for comparing 9 RAG pipelines with automated benchmarking. Optimize your AI QA system with precision metrics, RRF candidate pooling, and multi-LLM evaluation.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/wordpress.nevatal.id\/2026\/09\/13\/ragreader-multi-llm-consensus-benchmark-architecture-performance\/\" \/>\n<meta property=\"og:site_name\" content=\"Nevatal\" \/>\n<meta property=\"article:published_time\" content=\"2026-09-13T09:09:55+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\\\/13\\\/ragreader-multi-llm-consensus-benchmark-architecture-performance\\\/#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/wordpress.nevatal.id\\\/2026\\\/09\\\/13\\\/ragreader-multi-llm-consensus-benchmark-architecture-performance\\\/\"},\"author\":{\"name\":\"play258\",\"@id\":\"https:\\\/\\\/wordpress.nevatal.id\\\/#\\\/schema\\\/person\\\/d2821efbaf1c66c1392f012a520ebd73\"},\"headline\":\"RagReader &#8211; Multi-LLM Consensus &#038; Benchmark: Architecture &#038; Performance Deep Dive\",\"datePublished\":\"2026-09-13T09:09:55+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/wordpress.nevatal.id\\\/2026\\\/09\\\/13\\\/ragreader-multi-llm-consensus-benchmark-architecture-performance\\\/\"},\"wordCount\":620,\"commentCount\":0,\"publisher\":{\"@id\":\"https:\\\/\\\/wordpress.nevatal.id\\\/#\\\/schema\\\/person\\\/d2821efbaf1c66c1392f012a520ebd73\"},\"keywords\":[\"Django Channels\",\"Evaluation Metrics\",\"Faithfulness Scoring\",\"Multi-LLM Consensus\",\"RAG Benchmark\",\"Reciprocal Rank Fusion\",\"ROUGE-L\",\"WebSockets\"],\"articleSection\":[\"Artificial Intelligence &amp; Developer Tools\"],\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"CommentAction\",\"name\":\"Comment\",\"target\":[\"https:\\\/\\\/wordpress.nevatal.id\\\/2026\\\/09\\\/13\\\/ragreader-multi-llm-consensus-benchmark-architecture-performance\\\/#respond\"]}]},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/wordpress.nevatal.id\\\/2026\\\/09\\\/13\\\/ragreader-multi-llm-consensus-benchmark-architecture-performance\\\/\",\"url\":\"https:\\\/\\\/wordpress.nevatal.id\\\/2026\\\/09\\\/13\\\/ragreader-multi-llm-consensus-benchmark-architecture-performance\\\/\",\"name\":\"RagReader - Multi-LLM Consensus & Benchmark: Architecture & Performance Deep Dive\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/wordpress.nevatal.id\\\/#website\"},\"datePublished\":\"2026-09-13T09:09:55+00:00\",\"description\":\"Discover RagReader's architecture for comparing 9 RAG pipelines with automated benchmarking. Optimize your AI QA system with precision metrics, RRF candidate pooling, and multi-LLM evaluation.\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/wordpress.nevatal.id\\\/2026\\\/09\\\/13\\\/ragreader-multi-llm-consensus-benchmark-architecture-performance\\\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/wordpress.nevatal.id\\\/2026\\\/09\\\/13\\\/ragreader-multi-llm-consensus-benchmark-architecture-performance\\\/\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/wordpress.nevatal.id\\\/2026\\\/09\\\/13\\\/ragreader-multi-llm-consensus-benchmark-architecture-performance\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/wordpress.nevatal.id\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"RagReader &#8211; Multi-LLM Consensus &#038; Benchmark: Architecture &#038; Performance Deep Dive\"}]},{\"@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":"RagReader - Multi-LLM Consensus & Benchmark: Architecture & Performance Deep Dive","description":"Discover RagReader's architecture for comparing 9 RAG pipelines with automated benchmarking. Optimize your AI QA system with precision metrics, RRF candidate pooling, and multi-LLM evaluation.","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\/13\/ragreader-multi-llm-consensus-benchmark-architecture-performance\/","og_locale":"en_US","og_type":"article","og_title":"RagReader - Multi-LLM Consensus & Benchmark: Architecture & Performance Deep Dive","og_description":"Discover RagReader's architecture for comparing 9 RAG pipelines with automated benchmarking. Optimize your AI QA system with precision metrics, RRF candidate pooling, and multi-LLM evaluation.","og_url":"https:\/\/wordpress.nevatal.id\/2026\/09\/13\/ragreader-multi-llm-consensus-benchmark-architecture-performance\/","og_site_name":"Nevatal","article_published_time":"2026-09-13T09:09:55+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\/13\/ragreader-multi-llm-consensus-benchmark-architecture-performance\/#article","isPartOf":{"@id":"https:\/\/wordpress.nevatal.id\/2026\/09\/13\/ragreader-multi-llm-consensus-benchmark-architecture-performance\/"},"author":{"name":"play258","@id":"https:\/\/wordpress.nevatal.id\/#\/schema\/person\/d2821efbaf1c66c1392f012a520ebd73"},"headline":"RagReader &#8211; Multi-LLM Consensus &#038; Benchmark: Architecture &#038; Performance Deep Dive","datePublished":"2026-09-13T09:09:55+00:00","mainEntityOfPage":{"@id":"https:\/\/wordpress.nevatal.id\/2026\/09\/13\/ragreader-multi-llm-consensus-benchmark-architecture-performance\/"},"wordCount":620,"commentCount":0,"publisher":{"@id":"https:\/\/wordpress.nevatal.id\/#\/schema\/person\/d2821efbaf1c66c1392f012a520ebd73"},"keywords":["Django Channels","Evaluation Metrics","Faithfulness Scoring","Multi-LLM Consensus","RAG Benchmark","Reciprocal Rank Fusion","ROUGE-L","WebSockets"],"articleSection":["Artificial Intelligence &amp; Developer Tools"],"inLanguage":"en-US","potentialAction":[{"@type":"CommentAction","name":"Comment","target":["https:\/\/wordpress.nevatal.id\/2026\/09\/13\/ragreader-multi-llm-consensus-benchmark-architecture-performance\/#respond"]}]},{"@type":"WebPage","@id":"https:\/\/wordpress.nevatal.id\/2026\/09\/13\/ragreader-multi-llm-consensus-benchmark-architecture-performance\/","url":"https:\/\/wordpress.nevatal.id\/2026\/09\/13\/ragreader-multi-llm-consensus-benchmark-architecture-performance\/","name":"RagReader - Multi-LLM Consensus & Benchmark: Architecture & Performance Deep Dive","isPartOf":{"@id":"https:\/\/wordpress.nevatal.id\/#website"},"datePublished":"2026-09-13T09:09:55+00:00","description":"Discover RagReader's architecture for comparing 9 RAG pipelines with automated benchmarking. Optimize your AI QA system with precision metrics, RRF candidate pooling, and multi-LLM evaluation.","breadcrumb":{"@id":"https:\/\/wordpress.nevatal.id\/2026\/09\/13\/ragreader-multi-llm-consensus-benchmark-architecture-performance\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/wordpress.nevatal.id\/2026\/09\/13\/ragreader-multi-llm-consensus-benchmark-architecture-performance\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/wordpress.nevatal.id\/2026\/09\/13\/ragreader-multi-llm-consensus-benchmark-architecture-performance\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/wordpress.nevatal.id\/"},{"@type":"ListItem","position":2,"name":"RagReader &#8211; Multi-LLM Consensus &#038; Benchmark: Architecture &#038; Performance Deep Dive"}]},{"@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\/254","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=254"}],"version-history":[{"count":0,"href":"https:\/\/wordpress.nevatal.id\/wp-json\/wp\/v2\/posts\/254\/revisions"}],"wp:attachment":[{"href":"https:\/\/wordpress.nevatal.id\/wp-json\/wp\/v2\/media?parent=254"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/wordpress.nevatal.id\/wp-json\/wp\/v2\/categories?post=254"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/wordpress.nevatal.id\/wp-json\/wp\/v2\/tags?post=254"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}