{"id":111,"date":"2026-02-02T18:53:53","date_gmt":"2026-02-02T18:53:53","guid":{"rendered":"http:\/\/192.168.0.101\/blog\/?p=111"},"modified":"2026-02-04T20:31:49","modified_gmt":"2026-02-04T20:31:49","slug":"medtrac-knowledge-surface","status":"publish","type":"post","link":"http:\/\/netlite.community\/blog\/index.php\/2026\/02\/02\/medtrac-knowledge-surface\/","title":{"rendered":"MEDTRAC\u2122 &#8211; Knowledge Surface"},"content":{"rendered":"\n<p class=\"wp-block-paragraph\">20 January \u2014 MEDTRAC\u2122 has developed a proprietary knowledge-retention platform, the MEDTRAC\u2122 Knowledge Surface, designed to train the company\u2019s large language model and codify operational and analytical rules across its projects. The platform addresses the persistent \u201cWhere did I put that information?\u201d problem by routing all relevant data to a single, structured location and enabling high-speed search with typical retrieval times of&nbsp;0.2\u20130.5 seconds, combined with large-language-model\u2013based discovery. This approach removes the need to continually retrain models on locally stored data.<\/p>\n\n\n\n<figure class=\"wp-block-image size-full\"><img fetchpriority=\"high\" decoding=\"async\" width=\"882\" height=\"718\" src=\"http:\/\/192.168.0.101\/blog\/wp-content\/uploads\/2026\/02\/image-10.png\" alt=\"\" class=\"wp-image-115\" style=\"aspect-ratio:4\/3;object-fit:cover\" srcset=\"http:\/\/netlite.community\/blog\/wp-content\/uploads\/2026\/02\/image-10.png 882w, http:\/\/netlite.community\/blog\/wp-content\/uploads\/2026\/02\/image-10-300x244.png 300w, http:\/\/netlite.community\/blog\/wp-content\/uploads\/2026\/02\/image-10-768x625.png 768w\" sizes=\"(max-width: 882px) 100vw, 882px\" \/><\/figure>\n\n\n\n<p class=\"wp-block-paragraph\">The MEDTRAC\u2122 Knowledge Surface supports rapid publication of website content, ingestion and syndication of both internal and external knowledge sources, and fast retrieval via a high-performance search engine. It is fully integrated into the company\u2019s website to enable rapid publishing, SEO optimisation, and content syndication, and is intended to replace the company\u2019s use of OneNote, traditional file storage, and standalone chat systems.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">The platform enables secure ingestion and rapid search across both external and internal knowledge sources, including patient and product data, while remaining accessible to internal models and cloud-based large language models such as OpenAI, Anthropic, Grok, and Llama.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">The system is powered by the company\u2019s local LLM service hosted in Mellie\u0127a, which will be upgraded from a 7-billion-parameter model to a 20-billion-parameter model. The local LLM will be used for on-premise processing of low- to medium-complexity workloads, reducing typical LLM response times from approximately <strong>10\u201330 seconds<\/strong> to <strong>1\u20135 seconds<\/strong>.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>20 January \u2014 MEDTRAC\u2122 has developed a proprietary knowledge-retention platform, the MEDTRAC\u2122 Knowledge Surface, designed to train the company\u2019s large language model and codify operational and analytical rules across its projects. The platform addresses the persistent \u201cWhere did I put that information?\u201d problem by routing all relevant data to a single, structured location and enabling [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":115,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1],"tags":[],"class_list":["post-111","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-uncategorized"],"aioseo_notices":[],"_links":{"self":[{"href":"http:\/\/netlite.community\/blog\/index.php\/wp-json\/wp\/v2\/posts\/111","targetHints":{"allow":["GET"]}}],"collection":[{"href":"http:\/\/netlite.community\/blog\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"http:\/\/netlite.community\/blog\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"http:\/\/netlite.community\/blog\/index.php\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"http:\/\/netlite.community\/blog\/index.php\/wp-json\/wp\/v2\/comments?post=111"}],"version-history":[{"count":6,"href":"http:\/\/netlite.community\/blog\/index.php\/wp-json\/wp\/v2\/posts\/111\/revisions"}],"predecessor-version":[{"id":304,"href":"http:\/\/netlite.community\/blog\/index.php\/wp-json\/wp\/v2\/posts\/111\/revisions\/304"}],"wp:featuredmedia":[{"embeddable":true,"href":"http:\/\/netlite.community\/blog\/index.php\/wp-json\/wp\/v2\/media\/115"}],"wp:attachment":[{"href":"http:\/\/netlite.community\/blog\/index.php\/wp-json\/wp\/v2\/media?parent=111"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"http:\/\/netlite.community\/blog\/index.php\/wp-json\/wp\/v2\/categories?post=111"},{"taxonomy":"post_tag","embeddable":true,"href":"http:\/\/netlite.community\/blog\/index.php\/wp-json\/wp\/v2\/tags?post=111"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}