{"id":41954,"date":"2024-09-19T16:00:00","date_gmt":"2024-09-19T14:00:00","guid":{"rendered":"https:\/\/ritme.com\/storm-reply-intel-oneapi\/"},"modified":"2024-09-20T11:24:28","modified_gmt":"2024-09-20T09:24:28","slug":"storm-reply-intel-oneapi","status":"publish","type":"post","link":"https:\/\/ritme.com\/it\/storm-reply-intel-oneapi\/","title":{"rendered":"Storm Reply migliora le prestazioni LLM con le istanze EC2 C7i e Intel\u00ae oneAPI"},"content":{"rendered":"\n

Storm Reply, leader nelle soluzioni cloud, ha scelto le istanze Amazon EC2 C7i, supportate dai processori Intel\u00ae Xeon\u00ae di quarta generazione, per ottimizzare i suoi grandi modelli linguistici (LLM). Sfruttando gli strumenti Intel\u00ae oneAPI, Storm Reply ha raggiunto prestazioni equivalenti a quelle delle soluzioni GPU, ottimizzando al contempo i costi.<\/strong><\/p>\n\n\n\n

Storm Reply \u00e8 specializzata nell’accompagnamento dei propri clienti nella distribuzione di soluzioni d\u2019intelligenza artificiale generativa e di grandi modelli linguistici (LLM). Per soddisfare le esigenze di una grande azienda del settore energetico, Storm Reply ha dovuto trovare una soluzione di hosting economica e ad alta disponibilit\u00e0 per i suoi carichi di lavoro LLM.<\/p>\n\n\n\n

<\/div>\n\n\n
\n
\"Storm<\/figure>\n<\/div>\n\n\n
<\/div>\n\n\n\n

Dopo un’analisi approfondita, Storm Reply ha optato per le istanze Amazon EC2 C7i, alimentate da processori Intel\u00ae Xeon\u00ae Scalable di quarta generazione. Questa infrastruttura si \u00e8 rivelata ideale per gli LLM, grazie all’integrazione delle librerie Intel e del framework Intel\u00ae GenAI.<\/p>\n\n\n\n

Grazie alle ottimizzazioni di Intel\u00ae Extension for PyTorch e oneAPI Toolkit<\/mark><\/a>, Storm Reply \u00e8 riuscita non solo a migliorare le prestazioni dei suoi modelli, ma anche a ridurre notevolmente i costi. I test hanno dimostrato che l’inferenza LLM con i processori scalabili Intel Xeon raggiunge un tempo di risposta di 92 secondi, rispetto ai 485 secondi senza le ottimizzazioni Intel. I risultati di Storm Reply dimostrano che questa soluzione CPU rivaleggia con gli ambienti GPU in termini di rapporto prezzo-prestazioni.<\/p>\n\n\n\n

Le istanze EC2 C7i consentono a Storm Reply di offrire ai clienti soluzioni IA robuste, garantendo al contempo l’ottimizzazione delle risorse e dei costi.<\/p>\n\n\n\n

<\/div>\n\n\n\n

Per vedere l’articolo completo,<\/em> clicca qui<\/mark><\/a>.<\/p>\n\n\n\n

<\/div>\n","protected":false},"excerpt":{"rendered":"

Storm Reply, leader nelle soluzioni cloud, ha scelto le istanze Amazon EC2 C7i, supportate dai processori Intel\u00ae Xeon\u00ae di quarta generazione, per ottimizzare i suoi grandi modelli linguistici (LLM).<\/p>\n","protected":false},"author":3370,"featured_media":41963,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"inline_featured_image":false,"_uag_custom_page_level_css":"","footnotes":""},"categories":[55],"tags":[],"class_list":["post-41954","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-soluzioni-it"],"acf":[],"yoast_head":"\nStorm Reply migliora i suoi LLM con Intel oneAPI - RITME<\/title>\n<meta name=\"description\" content=\"Scoprite in questo articolo come Storm Reply, leader nelle soluzioni cloud, sta potenziando i suoi Large Language Models (LLM) con Intel oneAPI.\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/ritme.com\/it\/storm-reply-intel-oneapi\/\" \/>\n<meta property=\"og:locale\" content=\"it_IT\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Storm Reply migliora i suoi LLM con Intel oneAPI - RITME\" \/>\n<meta property=\"og:description\" content=\"Scoprite in questo articolo come Storm Reply, leader nelle soluzioni cloud, sta potenziando i suoi Large Language Models (LLM) con Intel oneAPI.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/ritme.com\/it\/storm-reply-intel-oneapi\/\" \/>\n<meta property=\"og:site_name\" content=\"RITME\" \/>\n<meta property=\"article:published_time\" content=\"2024-09-19T14:00:00+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2024-09-20T09:24:28+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/ritme.com\/wp-content\/uploads\/2024\/09\/IT_img_Intel-oneAPI_Q3-2024_mise-en-avant.png\" \/>\n\t<meta property=\"og:image:width\" content=\"674\" \/>\n\t<meta property=\"og:image:height\" content=\"477\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/png\" \/>\n<meta name=\"author\" content=\"Olivier Ritme\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Scritto da\" \/>\n\t<meta name=\"twitter:data1\" content=\"Olivier Ritme\" \/>\n\t<meta name=\"twitter:label2\" content=\"Tempo di lettura stimato\" \/>\n\t<meta name=\"twitter:data2\" content=\"2 minuti\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\\\/\\\/ritme.com\\\/it\\\/storm-reply-intel-oneapi\\\/#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/ritme.com\\\/it\\\/storm-reply-intel-oneapi\\\/\"},\"author\":{\"name\":\"Olivier Ritme\",\"@id\":\"https:\\\/\\\/ritme.com\\\/it\\\/#\\\/schema\\\/person\\\/ab075d31d4bf1d07c1b874a103afcb10\"},\"headline\":\"Storm Reply migliora le prestazioni LLM con le istanze EC2 C7i e Intel\u00ae oneAPI\",\"datePublished\":\"2024-09-19T14:00:00+00:00\",\"dateModified\":\"2024-09-20T09:24:28+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/ritme.com\\\/it\\\/storm-reply-intel-oneapi\\\/\"},\"wordCount\":274,\"publisher\":{\"@id\":\"https:\\\/\\\/ritme.com\\\/it\\\/#organization\"},\"image\":{\"@id\":\"https:\\\/\\\/ritme.com\\\/it\\\/storm-reply-intel-oneapi\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/ritme.com\\\/wp-content\\\/uploads\\\/2024\\\/09\\\/IT_img_Intel-oneAPI_Q3-2024_mise-en-avant.png\",\"articleSection\":[\"Soluzioni\"],\"inLanguage\":\"it-IT\"},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/ritme.com\\\/it\\\/storm-reply-intel-oneapi\\\/\",\"url\":\"https:\\\/\\\/ritme.com\\\/it\\\/storm-reply-intel-oneapi\\\/\",\"name\":\"Storm Reply migliora i suoi LLM con Intel oneAPI - RITME\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/ritme.com\\\/it\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/ritme.com\\\/it\\\/storm-reply-intel-oneapi\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/ritme.com\\\/it\\\/storm-reply-intel-oneapi\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/ritme.com\\\/wp-content\\\/uploads\\\/2024\\\/09\\\/IT_img_Intel-oneAPI_Q3-2024_mise-en-avant.png\",\"datePublished\":\"2024-09-19T14:00:00+00:00\",\"dateModified\":\"2024-09-20T09:24:28+00:00\",\"description\":\"Scoprite in questo articolo come Storm Reply, leader nelle soluzioni cloud, sta potenziando i suoi Large Language Models (LLM) con Intel oneAPI.\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/ritme.com\\\/it\\\/storm-reply-intel-oneapi\\\/#breadcrumb\"},\"inLanguage\":\"it-IT\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/ritme.com\\\/it\\\/storm-reply-intel-oneapi\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"it-IT\",\"@id\":\"https:\\\/\\\/ritme.com\\\/it\\\/storm-reply-intel-oneapi\\\/#primaryimage\",\"url\":\"https:\\\/\\\/ritme.com\\\/wp-content\\\/uploads\\\/2024\\\/09\\\/IT_img_Intel-oneAPI_Q3-2024_mise-en-avant.png\",\"contentUrl\":\"https:\\\/\\\/ritme.com\\\/wp-content\\\/uploads\\\/2024\\\/09\\\/IT_img_Intel-oneAPI_Q3-2024_mise-en-avant.png\",\"width\":674,\"height\":477,\"caption\":\"Storm Reply migliora le prestazioni LLM con le istanze EC2 C7i e Intel\u00ae oneAPI\"},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/ritme.com\\\/it\\\/storm-reply-intel-oneapi\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/ritme.com\\\/it\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Soluzioni\",\"item\":\"https:\\\/\\\/ritme.com\\\/it\\\/categoria\\\/soluzioni-it\\\/\"},{\"@type\":\"ListItem\",\"position\":3,\"name\":\"Storm Reply migliora le prestazioni LLM con le istanze EC2 C7i e Intel\u00ae oneAPI\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/ritme.com\\\/it\\\/#website\",\"url\":\"https:\\\/\\\/ritme.com\\\/it\\\/\",\"name\":\"RITME\",\"description\":\"Il partner strategico dei team di ricerca\",\"publisher\":{\"@id\":\"https:\\\/\\\/ritme.com\\\/it\\\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/ritme.com\\\/it\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"it-IT\"},{\"@type\":\"Organization\",\"@id\":\"https:\\\/\\\/ritme.com\\\/it\\\/#organization\",\"name\":\"RITME\",\"url\":\"https:\\\/\\\/ritme.com\\\/it\\\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"it-IT\",\"@id\":\"https:\\\/\\\/ritme.com\\\/it\\\/#\\\/schema\\\/logo\\\/image\\\/\",\"url\":\"https:\\\/\\\/ritme.com\\\/wp-content\\\/uploads\\\/2021\\\/06\\\/Ritme_200x86.svg\",\"contentUrl\":\"https:\\\/\\\/ritme.com\\\/wp-content\\\/uploads\\\/2021\\\/06\\\/Ritme_200x86.svg\",\"caption\":\"RITME\"},\"image\":{\"@id\":\"https:\\\/\\\/ritme.com\\\/it\\\/#\\\/schema\\\/logo\\\/image\\\/\"}},{\"@type\":\"Person\",\"@id\":\"https:\\\/\\\/ritme.com\\\/it\\\/#\\\/schema\\\/person\\\/ab075d31d4bf1d07c1b874a103afcb10\",\"name\":\"Olivier Ritme\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"it-IT\",\"@id\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/5e766af435a9d437904f33762395f31273c9bfbb003cd5e2a6b1c2536fa1f594?s=96&d=mm&r=g\",\"url\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/5e766af435a9d437904f33762395f31273c9bfbb003cd5e2a6b1c2536fa1f594?s=96&d=mm&r=g\",\"contentUrl\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/5e766af435a9d437904f33762395f31273c9bfbb003cd5e2a6b1c2536fa1f594?s=96&d=mm&r=g\",\"caption\":\"Olivier Ritme\"},\"sameAs\":[\"http:\\\/\\\/adminRitme\"],\"url\":\"https:\\\/\\\/ritme.com\\\/it\\\/author\\\/olivier\\\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Storm Reply migliora i suoi LLM con Intel oneAPI - RITME","description":"Scoprite in questo articolo come Storm Reply, leader nelle soluzioni cloud, sta potenziando i suoi Large Language Models (LLM) con Intel oneAPI.","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:\/\/ritme.com\/it\/storm-reply-intel-oneapi\/","og_locale":"it_IT","og_type":"article","og_title":"Storm Reply migliora i suoi LLM con Intel oneAPI - RITME","og_description":"Scoprite in questo articolo come Storm Reply, leader nelle soluzioni cloud, sta potenziando i suoi Large Language Models (LLM) con Intel oneAPI.","og_url":"https:\/\/ritme.com\/it\/storm-reply-intel-oneapi\/","og_site_name":"RITME","article_published_time":"2024-09-19T14:00:00+00:00","article_modified_time":"2024-09-20T09:24:28+00:00","og_image":[{"width":674,"height":477,"url":"https:\/\/ritme.com\/wp-content\/uploads\/2024\/09\/IT_img_Intel-oneAPI_Q3-2024_mise-en-avant.png","type":"image\/png"}],"author":"Olivier Ritme","twitter_card":"summary_large_image","twitter_misc":{"Scritto da":"Olivier Ritme","Tempo di lettura stimato":"2 minuti"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/ritme.com\/it\/storm-reply-intel-oneapi\/#article","isPartOf":{"@id":"https:\/\/ritme.com\/it\/storm-reply-intel-oneapi\/"},"author":{"name":"Olivier Ritme","@id":"https:\/\/ritme.com\/it\/#\/schema\/person\/ab075d31d4bf1d07c1b874a103afcb10"},"headline":"Storm Reply migliora le prestazioni LLM con le istanze EC2 C7i e Intel\u00ae oneAPI","datePublished":"2024-09-19T14:00:00+00:00","dateModified":"2024-09-20T09:24:28+00:00","mainEntityOfPage":{"@id":"https:\/\/ritme.com\/it\/storm-reply-intel-oneapi\/"},"wordCount":274,"publisher":{"@id":"https:\/\/ritme.com\/it\/#organization"},"image":{"@id":"https:\/\/ritme.com\/it\/storm-reply-intel-oneapi\/#primaryimage"},"thumbnailUrl":"https:\/\/ritme.com\/wp-content\/uploads\/2024\/09\/IT_img_Intel-oneAPI_Q3-2024_mise-en-avant.png","articleSection":["Soluzioni"],"inLanguage":"it-IT"},{"@type":"WebPage","@id":"https:\/\/ritme.com\/it\/storm-reply-intel-oneapi\/","url":"https:\/\/ritme.com\/it\/storm-reply-intel-oneapi\/","name":"Storm Reply migliora i suoi LLM con Intel oneAPI - RITME","isPartOf":{"@id":"https:\/\/ritme.com\/it\/#website"},"primaryImageOfPage":{"@id":"https:\/\/ritme.com\/it\/storm-reply-intel-oneapi\/#primaryimage"},"image":{"@id":"https:\/\/ritme.com\/it\/storm-reply-intel-oneapi\/#primaryimage"},"thumbnailUrl":"https:\/\/ritme.com\/wp-content\/uploads\/2024\/09\/IT_img_Intel-oneAPI_Q3-2024_mise-en-avant.png","datePublished":"2024-09-19T14:00:00+00:00","dateModified":"2024-09-20T09:24:28+00:00","description":"Scoprite in questo articolo come Storm Reply, leader nelle soluzioni cloud, sta potenziando i suoi Large Language Models (LLM) con Intel oneAPI.","breadcrumb":{"@id":"https:\/\/ritme.com\/it\/storm-reply-intel-oneapi\/#breadcrumb"},"inLanguage":"it-IT","potentialAction":[{"@type":"ReadAction","target":["https:\/\/ritme.com\/it\/storm-reply-intel-oneapi\/"]}]},{"@type":"ImageObject","inLanguage":"it-IT","@id":"https:\/\/ritme.com\/it\/storm-reply-intel-oneapi\/#primaryimage","url":"https:\/\/ritme.com\/wp-content\/uploads\/2024\/09\/IT_img_Intel-oneAPI_Q3-2024_mise-en-avant.png","contentUrl":"https:\/\/ritme.com\/wp-content\/uploads\/2024\/09\/IT_img_Intel-oneAPI_Q3-2024_mise-en-avant.png","width":674,"height":477,"caption":"Storm Reply migliora le prestazioni LLM con le istanze EC2 C7i e Intel\u00ae oneAPI"},{"@type":"BreadcrumbList","@id":"https:\/\/ritme.com\/it\/storm-reply-intel-oneapi\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/ritme.com\/it\/"},{"@type":"ListItem","position":2,"name":"Soluzioni","item":"https:\/\/ritme.com\/it\/categoria\/soluzioni-it\/"},{"@type":"ListItem","position":3,"name":"Storm Reply migliora le prestazioni LLM con le istanze EC2 C7i e Intel\u00ae oneAPI"}]},{"@type":"WebSite","@id":"https:\/\/ritme.com\/it\/#website","url":"https:\/\/ritme.com\/it\/","name":"RITME","description":"Il partner strategico dei team di ricerca","publisher":{"@id":"https:\/\/ritme.com\/it\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/ritme.com\/it\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"it-IT"},{"@type":"Organization","@id":"https:\/\/ritme.com\/it\/#organization","name":"RITME","url":"https:\/\/ritme.com\/it\/","logo":{"@type":"ImageObject","inLanguage":"it-IT","@id":"https:\/\/ritme.com\/it\/#\/schema\/logo\/image\/","url":"https:\/\/ritme.com\/wp-content\/uploads\/2021\/06\/Ritme_200x86.svg","contentUrl":"https:\/\/ritme.com\/wp-content\/uploads\/2021\/06\/Ritme_200x86.svg","caption":"RITME"},"image":{"@id":"https:\/\/ritme.com\/it\/#\/schema\/logo\/image\/"}},{"@type":"Person","@id":"https:\/\/ritme.com\/it\/#\/schema\/person\/ab075d31d4bf1d07c1b874a103afcb10","name":"Olivier Ritme","image":{"@type":"ImageObject","inLanguage":"it-IT","@id":"https:\/\/secure.gravatar.com\/avatar\/5e766af435a9d437904f33762395f31273c9bfbb003cd5e2a6b1c2536fa1f594?s=96&d=mm&r=g","url":"https:\/\/secure.gravatar.com\/avatar\/5e766af435a9d437904f33762395f31273c9bfbb003cd5e2a6b1c2536fa1f594?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/5e766af435a9d437904f33762395f31273c9bfbb003cd5e2a6b1c2536fa1f594?s=96&d=mm&r=g","caption":"Olivier Ritme"},"sameAs":["http:\/\/adminRitme"],"url":"https:\/\/ritme.com\/it\/author\/olivier\/"}]}},"uagb_featured_image_src":{"full":["https:\/\/ritme.com\/wp-content\/uploads\/2024\/09\/IT_img_Intel-oneAPI_Q3-2024_mise-en-avant.png",674,477,false],"thumbnail":["https:\/\/ritme.com\/wp-content\/uploads\/2024\/09\/IT_img_Intel-oneAPI_Q3-2024_mise-en-avant-300x300.png",300,300,true],"medium":["https:\/\/ritme.com\/wp-content\/uploads\/2024\/09\/IT_img_Intel-oneAPI_Q3-2024_mise-en-avant-500x354.png",500,354,true],"medium_large":["https:\/\/ritme.com\/wp-content\/uploads\/2024\/09\/IT_img_Intel-oneAPI_Q3-2024_mise-en-avant.png",674,477,false],"large":["https:\/\/ritme.com\/wp-content\/uploads\/2024\/09\/IT_img_Intel-oneAPI_Q3-2024_mise-en-avant.png",674,477,false],"1536x1536":["https:\/\/ritme.com\/wp-content\/uploads\/2024\/09\/IT_img_Intel-oneAPI_Q3-2024_mise-en-avant.png",674,477,false],"2048x2048":["https:\/\/ritme.com\/wp-content\/uploads\/2024\/09\/IT_img_Intel-oneAPI_Q3-2024_mise-en-avant.png",674,477,false]},"uagb_author_info":{"display_name":"Olivier Ritme","author_link":"https:\/\/ritme.com\/it\/author\/olivier\/"},"uagb_comment_info":0,"uagb_excerpt":"Storm Reply, leader nelle soluzioni cloud, ha scelto le istanze Amazon EC2 C7i, supportate dai processori Intel\u00ae Xeon\u00ae di quarta generazione, per ottimizzare i suoi grandi modelli linguistici (LLM).","_links":{"self":[{"href":"https:\/\/ritme.com\/it\/wp-json\/wp\/v2\/posts\/41954","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/ritme.com\/it\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/ritme.com\/it\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/ritme.com\/it\/wp-json\/wp\/v2\/users\/3370"}],"replies":[{"embeddable":true,"href":"https:\/\/ritme.com\/it\/wp-json\/wp\/v2\/comments?post=41954"}],"version-history":[{"count":3,"href":"https:\/\/ritme.com\/it\/wp-json\/wp\/v2\/posts\/41954\/revisions"}],"predecessor-version":[{"id":41967,"href":"https:\/\/ritme.com\/it\/wp-json\/wp\/v2\/posts\/41954\/revisions\/41967"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/ritme.com\/it\/wp-json\/wp\/v2\/media\/41963"}],"wp:attachment":[{"href":"https:\/\/ritme.com\/it\/wp-json\/wp\/v2\/media?parent=41954"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/ritme.com\/it\/wp-json\/wp\/v2\/categories?post=41954"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/ritme.com\/it\/wp-json\/wp\/v2\/tags?post=41954"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}