{"id":111103,"date":"2023-10-26T15:10:31","date_gmt":"2023-10-26T13:10:31","guid":{"rendered":"https:\/\/prohoster.info\/blog\/novosti-interneta\/otkryt-kod-jina-embedding-modeli-dlya-vektornogo-predstavleniya-smysla-teksta"},"modified":"2023-10-26T15:10:31","modified_gmt":"2023-10-26T13:10:31","slug":"otkryt-kod-jina-embedding-modeli-dlya-vektornogo-predstavleniya-smysla-teksta","status":"publish","type":"post","link":"https:\/\/prohoster.info\/cs\/blog\/news\/otkryt-kod-jina-embedding-modeli-dlya-vektornogo-predstavleniya-smysla-teksta","title":{"rendered":"Otev\u0159en\u00fd k\u00f3d Jina Embedding, model pro vektorov\u00e9 vyj\u00e1d\u0159en\u00ed v\u00fdznamu textu","gt_translate_keys":[{"key":"rendered","format":"text"}]},"content":{"rendered":"<p>Spole\u010dnost Jina uvedla pod licenc\u00ed Apache 2.0 model strojov\u00e9ho u\u010den\u00ed pro vektorov\u00e9 zastoupen\u00ed textu \u2014 jina-embeddings-v2. Tento model umo\u017e\u0148uje p\u0159ev\u00e9st libovoln\u00fd text, kter\u00fd obsahuje a\u017e 8192 znak\u016f, na malou sekvenci re\u00e1ln\u00fdch \u010d\u00edsel tvo\u0159\u00edc\u00edch vektor, kter\u00fd odpov\u00edd\u00e1 p\u016fvodn\u00edmu textu a reprodukuje jeho s\u00e9mantiku. Jina Embedding se stala prvn\u00edm otev\u0159en\u00fdm modelem strojov\u00e9ho u\u010den\u00ed, kter\u00fd m\u00e1 vlastnosti, je\u017e se vyrovnaj\u00ed propriet\u00e1rn\u00edmu modelu vektorizace textu od projektu OpenAI (text-embedding-ada-002), a tak\u00e9 dok\u00e1\u017ee zpracov\u00e1vat texty o d\u00e9lce a\u017e 8192 token\u016f.      <\/p>\n<p>Vzd\u00e1lenost mezi dv\u011bma utvo\u0159en\u00fdmi vektory lze pou\u017e\u00edt k ur\u010den\u00ed v\u00fdznamov\u00e9 souvislosti p\u016fvodn\u00edch text\u016f. V praxi mohou utvo\u0159en\u00e9 vektory slou\u017eit k anal\u00fdze podobnosti text\u016f, organizaci vyhled\u00e1v\u00e1n\u00ed materi\u00e1l\u016f p\u0159\u00edbuzn\u00e9ho t\u00e9matu (\u0159azen\u00ed v\u00fdsledk\u016f podle s\u00e9mantick\u00e9 bl\u00edzkosti), skupinov\u00e1n\u00ed text\u016f dle v\u00fdznamu, vytv\u00e1\u0159en\u00ed doporu\u010den\u00ed (nab\u00eddka seznamu podobn\u00fdch textov\u00fdch \u0159et\u011bzc\u016f), identifikaci anom\u00e1li\u00ed, ur\u010dov\u00e1n\u00ed plagi\u00e1torstv\u00ed a klasifikaci test\u016f. Mezi p\u0159\u00edklady pou\u017eit\u00ed se zmi\u0148uje vyu\u017eit\u00ed modelu pro anal\u00fdzu pr\u00e1vn\u00edch dokument\u016f, pro obchodn\u00ed analytiku, ve zdravotnick\u00e9m v\u00fdzkumu pro zpracov\u00e1n\u00ed v\u011bdeck\u00fdch \u010dl\u00e1nk\u016f, v liter\u00e1rn\u00ed kritice, pro anal\u00fdzu finan\u010dn\u00edch zpr\u00e1v a pro zlep\u0161en\u00ed kvality zpracov\u00e1n\u00ed slo\u017eit\u00fdch dotaz\u016f chatovac\u00edmi boty.        <\/p>\n<p>K dispozici jsou dv\u011b varianty modelu jina-embeddings (z\u00e1kladn\u00ed \u2014 0.27 GB a zkr\u00e1cen\u00e1 \u2014 0.07 GB), vy\u0161kolen\u00e9 na 400 milionech p\u00e1r\u016f textov\u00fdch sekvenc\u00ed v anglick\u00e9m jazyce pokr\u00fdvaj\u00edc\u00edch r\u016fzn\u00e9 oblasti znalost\u00ed. P\u0159i tr\u00e9nov\u00e1n\u00ed byly pou\u017eity sekvence o velikosti 512 token\u016f, kter\u00e9 byly extrapolov\u00e1ny na velikost 8192 pomoc\u00ed metody ALiBi (Attention with Linear Biases).     <\/p>\n<p>Z\u00e1kladn\u00ed model obsahuje 137 milion\u016f parametr\u016f a je ur\u010den pro pou\u017eit\u00ed na stoln\u00edch syst\u00e9mech s GPU. Zkr\u00e1cen\u00e1 verze zahrnuje 33 milion\u016f parametr\u016f, poskytuje ni\u017e\u0161\u00ed p\u0159esnost a je ur\u010dena pro aplikace na mobiln\u00edch za\u0159\u00edzen\u00edch a syst\u00e9mech s omezenou pam\u011bt\u00ed. V bl\u00edzk\u00e9 budoucnosti se pl\u00e1nuje tak\u00e9 publikace velk\u00e9ho modelu, kter\u00fd pokryje 435 milion\u016f parametr\u016f. V p\u0159\u00edprav\u011b je tak\u00e9 v\u00edcejazy\u010dn\u00e1 verze tohoto modelu, kter\u00e1 se v sou\u010dasnosti zam\u011b\u0159uje na podporu n\u011bm\u010diny a \u0161pan\u011bl\u0161tiny. Samostatn\u011b byl vyvinut plugin pro pou\u017eit\u00ed modelu jina-embeddings prost\u0159ednictv\u00edm n\u00e1stroje LLM.<br \/>\n<br \/>Zdroj: <a content=\"nofollow\" rel=\"nofollow\" href=\"https:\/\/www.opennet.ru\/opennews\/art.shtml?num=59996\">opennet.ru<\/a> <\/p>","protected":false,"gt_translate_keys":[{"key":"rendered","format":"html"}]},"excerpt":{"rendered":"<p>\u041a\u043e\u043c\u043f\u0430\u043d\u0438\u044f Jina \u043e\u0442\u043a\u0440\u044b\u043b\u0430 \u043f\u043e\u0434 \u043b\u0438\u0446\u0435\u043d\u0437\u0438\u0435\u0439 Apache 2.0 \u043c\u043e\u0434\u0435\u043b\u044c \u043c\u0430\u0448\u0438\u043d\u043d\u043e\u0433\u043e \u043e\u0431\u0443\u0447\u0435\u043d\u0438\u044f \u0434\u043b\u044f \u0432\u0435\u043a\u0442\u043e\u0440\u043d\u043e\u0433\u043e \u043f\u0440\u0435\u0434\u0441\u0442\u0430\u0432\u043b\u0435\u043d\u0438\u044f \u0442\u0435\u043a\u0441\u0442\u0430 &#8212; jina-embeddings-v2. \u041c\u043e\u0434\u0435\u043b\u044c \u043f\u043e\u0437\u0432\u043e\u043b\u044f\u0435\u0442 \u043f\u0440\u0435\u043e\u0431\u0440\u0430\u0437\u043e\u0432\u0430\u0442\u044c \u043f\u0440\u043e\u0438\u0437\u0432\u043e\u043b\u044c\u043d\u044b\u0439 \u0442\u0435\u043a\u0441\u0442, \u0432\u043a\u043b\u044e\u0447\u0430\u044e\u0449\u0438\u0439 \u0434\u043e 8192 \u0437\u043d\u0430\u043a\u043e\u0432, \u0432 \u043d\u0435\u0431\u043e\u043b\u044c\u0448\u0443\u044e \u043f\u043e\u0441\u043b\u0435\u0434\u043e\u0432\u0430\u0442\u0435\u043b\u044c\u043d\u043e\u0441\u0442\u044c \u0432\u0435\u0449\u0435\u0441\u0442\u0432\u0435\u043d\u043d\u044b\u0445 \u0447\u0438\u0441\u0435\u043b, \u043e\u0431\u0440\u0430\u0437\u0443\u044e\u0449\u0438\u0445 \u0432\u0435\u043a\u0442\u043e\u0440, \u0441\u043e\u043f\u043e\u0441\u0442\u0430\u0432\u043b\u0435\u043d\u043d\u044b\u0439 \u0441 \u0438\u0441\u0445\u043e\u0434\u043d\u044b\u043c \u0442\u0435\u043a\u0441\u0442\u043e\u043c \u0438 \u0432\u043e\u0441\u043f\u0440\u043e\u0438\u0437\u0432\u043e\u0434\u044f\u0449\u0438\u0439 \u0435\u0433\u043e \u0441\u0435\u043c\u0430\u043d\u0442\u0438\u043a\u0443 (\u0441\u043c\u044b\u0441\u043b). Jina Embedding \u0441\u0442\u0430\u043b\u0430 \u043f\u0435\u0440\u0432\u043e\u0439 \u043e\u0442\u043a\u0440\u044b\u0442\u043e\u0439 \u043c\u043e\u0434\u0435\u043b\u044c\u044e \u043c\u0430\u0448\u0438\u043d\u043d\u043e\u0433\u043e \u043e\u0431\u0443\u0447\u0435\u043d\u0438\u044f, \u043e\u0431\u043b\u0430\u0434\u0430\u044e\u0449\u0435\u0439 \u0445\u0430\u0440\u0430\u043a\u0442\u0435\u0440\u0438\u0441\u0442\u0438\u043a\u0430\u043c\u0438, \u043d\u0435 \u0443\u0441\u0442\u0443\u043f\u0430\u044e\u0449\u0438\u043c\u0438 \u043f\u0440\u043e\u043f\u0440\u0438\u0435\u0442\u0430\u0440\u043d\u043e\u0439 \u043c\u043e\u0434\u0435\u043b\u0438 [&hellip;]<\/p>\n","protected":false,"gt_translate_keys":[{"key":"rendered","format":"html"}]},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[702],"tags":[],"class_list":["post-111103","post","type-post","status-publish","format-standard","hentry","category-news"],"aioseo_notices":[],"aioseo_head":"\n\t\t<!-- All in One SEO 5.0.3 - aioseo.com -->\n\t<meta name=\"description\" content=\"\u041a\u043e\u043c\u043f\u0430\u043d\u0438\u044f Jina \u043e\u0442\u043a\u0440\u044b\u043b\u0430 \u043f\u043e\u0434 \u043b\u0438\u0446\u0435\u043d\u0437\u0438\u0435\u0439 Apache 2.0 \u043c\u043e\u0434\u0435\u043b\u044c \u043c\u0430\u0448\u0438\u043d\u043d\u043e\u0433\u043e \u043e\u0431\u0443\u0447\u0435\u043d\u0438\u044f \u0434\u043b\u044f \u0432\u0435\u043a\u0442\u043e\u0440\u043d\u043e\u0433\u043e \u043f\u0440\u0435\u0434\u0441\u0442\u0430\u0432\u043b\u0435\u043d\u0438\u044f \u0442\u0435\u043a\u0441\u0442\u0430 - jina-embeddings-v2.\" \/>\n\t<meta name=\"robots\" content=\"max-image-preview:large\" \/>\n\t<meta name=\"author\" content=\"Yuri Gagarin\"\/>\n\t<link rel=\"canonical\" href=\"https:\/\/prohoster.info\/cs\/blog\/news\/otkryt-kod-jina-embedding-modeli-dlya-vektornogo-predstavleniya-smysla-teksta\" \/>\n\t\t<meta name=\"generator\" content=\"All in One SEO (AIOSEO) 5.0.3\" \/>\n\t\t<meta property=\"og:locale\" content=\"cs_CZ\" \/>\n\t\t<meta property=\"og:site_name\" content=\"ProHoster | \u041a\u0443\u043f\u0438\u0442\u044c \u043d\u0430\u0434\u0435\u0436\u043d\u044b\u0439 \u0445\u043e\u0441\u0442\u0438\u043d\u0433 \u0434\u043b\u044f \u0441\u0430\u0439\u0442\u043e\u0432 \u0441 \u0437\u0430\u0449\u0438\u0442\u043e\u0439 \u043e\u0442 DDoS, VPS VDS \u0441\u0435\u0440\u0432\u0435\u0440\u044b\" \/>\n\t\t<meta property=\"og:type\" content=\"article\" \/>\n\t\t<meta property=\"og:title\" content=\"\ud83e\udd47\u041e\u0442\u043a\u0440\u044b\u0442 \u043a\u043e\u0434 Jina Embedding, \u043c\u043e\u0434\u0435\u043b\u0438 \u0434\u043b\u044f \u0432\u0435\u043a\u0442\u043e\u0440\u043d\u043e\u0433\u043e \u043f\u0440\u0435\u0434\u0441\u0442\u0430\u0432\u043b\u0435\u043d\u0438\u044f \u0441\u043c\u044b\u0441\u043b\u0430 \u0442\u0435\u043a\u0441\u0442\u0430 | ProHoster\" \/>\n\t\t<meta property=\"og:description\" content=\"\u041a\u043e\u043c\u043f\u0430\u043d\u0438\u044f Jina \u043e\u0442\u043a\u0440\u044b\u043b\u0430 \u043f\u043e\u0434 \u043b\u0438\u0446\u0435\u043d\u0437\u0438\u0435\u0439 Apache 2.0 \u043c\u043e\u0434\u0435\u043b\u044c \u043c\u0430\u0448\u0438\u043d\u043d\u043e\u0433\u043e \u043e\u0431\u0443\u0447\u0435\u043d\u0438\u044f \u0434\u043b\u044f \u0432\u0435\u043a\u0442\u043e\u0440\u043d\u043e\u0433\u043e \u043f\u0440\u0435\u0434\u0441\u0442\u0430\u0432\u043b\u0435\u043d\u0438\u044f \u0442\u0435\u043a\u0441\u0442\u0430 - jina-embeddings-v2.\" \/>\n\t\t<meta property=\"og:url\" content=\"https:\/\/prohoster.info\/cs\/blog\/news\/otkryt-kod-jina-embedding-modeli-dlya-vektornogo-predstavleniya-smysla-teksta\" \/>\n\t\t<meta property=\"og:image\" content=\"https:\/\/prohoster.info\/wp-content\/uploads\/2021\/11\/logo-350.jpg\" \/>\n\t\t<meta property=\"og:image:secure_url\" content=\"https:\/\/prohoster.info\/wp-content\/uploads\/2021\/11\/logo-350.jpg\" \/>\n\t\t<meta property=\"og:image:width\" content=\"350\" \/>\n\t\t<meta property=\"og:image:height\" content=\"350\" \/>\n\t\t<meta property=\"article:published_time\" content=\"2023-10-26T13:10:31+00:00\" \/>\n\t\t<meta property=\"article:modified_time\" content=\"2023-10-26T13:10:31+00:00\" \/>\n\t\t<meta property=\"article:publisher\" content=\"https:\/\/www.facebook.com\/prohoster\" \/>\n\t\t<meta property=\"article:author\" content=\"https:\/\/www.facebook.com\/prohoster\" \/>\n\t\t<!-- All in One SEO -->\n\n","aioseo_head_json":{"title":"\ud83e\udd47Otev\u0159en\u00fd k\u00f3d Jina Embedding, model pro vektorov\u00e9 zastoupen\u00ed v\u00fdznamu textu | ProHoster","description":"Spole\u010dnost Jina otev\u0159ela pod licenc\u00ed Apache 2.0 model strojov\u00e9ho u\u010den\u00ed pro vektorov\u00e9 reprezentace textu - jina-embeddings-v2.","canonical_url":"https:\/\/prohoster.info\/cs\/blog\/news\/otkryt-kod-jina-embedding-modeli-dlya-vektornogo-predstavleniya-smysla-teksta","robots":"max-image-preview:large","keywords":"","webmasterTools":{"miscellaneous":""},"schema":null,"og:locale":"cs_CZ","og:site_name":"ProHoster | \u041a\u0443\u043f\u0438\u0442\u044c \u043d\u0430\u0434\u0435\u0436\u043d\u044b\u0439 \u0445\u043e\u0441\u0442\u0438\u043d\u0433 \u0434\u043b\u044f \u0441\u0430\u0439\u0442\u043e\u0432 \u0441 \u0437\u0430\u0449\u0438\u0442\u043e\u0439 \u043e\u0442 DDoS, VPS VDS \u0441\u0435\u0440\u0432\u0435\u0440\u044b","og:type":"article","og:title":"\ud83e\udd47\u041e\u0442\u043a\u0440\u044b\u0442 \u043a\u043e\u0434 Jina Embedding, \u043c\u043e\u0434\u0435\u043b\u0438 \u0434\u043b\u044f \u0432\u0435\u043a\u0442\u043e\u0440\u043d\u043e\u0433\u043e \u043f\u0440\u0435\u0434\u0441\u0442\u0430\u0432\u043b\u0435\u043d\u0438\u044f \u0441\u043c\u044b\u0441\u043b\u0430 \u0442\u0435\u043a\u0441\u0442\u0430 | ProHoster","og:description":"\u041a\u043e\u043c\u043f\u0430\u043d\u0438\u044f Jina \u043e\u0442\u043a\u0440\u044b\u043b\u0430 \u043f\u043e\u0434 \u043b\u0438\u0446\u0435\u043d\u0437\u0438\u0435\u0439 Apache 2.0 \u043c\u043e\u0434\u0435\u043b\u044c \u043c\u0430\u0448\u0438\u043d\u043d\u043e\u0433\u043e \u043e\u0431\u0443\u0447\u0435\u043d\u0438\u044f \u0434\u043b\u044f \u0432\u0435\u043a\u0442\u043e\u0440\u043d\u043e\u0433\u043e \u043f\u0440\u0435\u0434\u0441\u0442\u0430\u0432\u043b\u0435\u043d\u0438\u044f \u0442\u0435\u043a\u0441\u0442\u0430 - jina-embeddings-v2.","og:url":"https:\/\/prohoster.info\/cs\/blog\/news\/otkryt-kod-jina-embedding-modeli-dlya-vektornogo-predstavleniya-smysla-teksta","og:image":"https:\/\/prohoster.info\/wp-content\/uploads\/2021\/11\/logo-350.jpg","og:image:secure_url":"https:\/\/prohoster.info\/wp-content\/uploads\/2021\/11\/logo-350.jpg","og:image:width":350,"og:image:height":350,"article:published_time":"2023-10-26T13:10:31+00:00","article:modified_time":"2023-10-26T13:10:31+00:00","article:publisher":"https:\/\/www.facebook.com\/prohoster","article:author":"https:\/\/www.facebook.com\/prohoster"},"aioseo_meta_data":[],"gt_translate_keys":[{"key":"link","format":"url"}],"_links":{"self":[{"href":"https:\/\/prohoster.info\/cs\/wp-json\/wp\/v2\/posts\/111103","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/prohoster.info\/cs\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/prohoster.info\/cs\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/prohoster.info\/cs\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/prohoster.info\/cs\/wp-json\/wp\/v2\/comments?post=111103"}],"version-history":[{"count":0,"href":"https:\/\/prohoster.info\/cs\/wp-json\/wp\/v2\/posts\/111103\/revisions"}],"wp:attachment":[{"href":"https:\/\/prohoster.info\/cs\/wp-json\/wp\/v2\/media?parent=111103"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/prohoster.info\/cs\/wp-json\/wp\/v2\/categories?post=111103"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/prohoster.info\/cs\/wp-json\/wp\/v2\/tags?post=111103"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}