{"id":3905,"date":"2024-02-14T20:51:33","date_gmt":"2024-02-14T12:51:33","guid":{"rendered":"https:\/\/www.1ai.net\/?p=3905"},"modified":"2024-02-14T20:51:33","modified_gmt":"2024-02-14T12:51:33","slug":"%e8%8b%b1%e4%bc%9f%e8%be%be%e6%8e%a8%e5%87%ba-rtx-%e8%81%8a%e5%a4%a9%e6%9c%ba%e5%99%a8%e4%ba%ba%ef%bc%8c%e5%8f%af%e5%9c%a8-rtx-30-%e5%92%8c-40-gpu-%e4%b8%8a%e5%85%8d%e8%b4%b9%e4%bd%bf%e7%94%a8","status":"publish","type":"post","link":"https:\/\/www.1ai.net\/en\/3905.html","title":{"rendered":"Nvidia launches RTX Chatbot, free to use on RTX 30 and 40 GPUs"},"content":{"rendered":"<p data-vmark=\"f44a\"><a href=\"https:\/\/www.1ai.net\/en\/tag\/%e8%8b%b1%e4%bc%9f%e8%be%be\" title=\"Look at the article with the label\" target=\"_blank\" >Nvidia<\/a>Today marks the release of the \"Chat with RTX\" application, a Windows PC-based<a href=\"https:\/\/www.1ai.net\/en\/tag\/%e8%81%8a%e5%a4%a9%e6%9c%ba%e5%99%a8%e4%ba%ba\" title=\"[View articles tagged with [chatbot]]\" target=\"_blank\" >Chatbots<\/a>, powered by TensorRT-LLM.<\/p>\n<p data-vmark=\"7335\"><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-3906\" title=\"bfe41a2a-c38f-464b-87fe-d6345cefc8d0\" src=\"https:\/\/www.1ai.net\/wp-content\/uploads\/2024\/02\/bfe41a2a-c38f-464b-87fe-d6345cefc8d0.png\" alt=\"bfe41a2a-c38f-464b-87fe-d6345cefc8d0\" width=\"731\" height=\"484\" \/><\/p>\n<p data-vmark=\"e07f\">The \"Chat with RTX\" chatbot is designed as a localized system that users can use without the need for Internet access, and the application is supported by all GeForce RTX 30 and 40 GPUs with at least 8 GB of video memory.<\/p>\n<p data-vmark=\"e311\"><span class=\"accentTextColor\">Chat with RTX supports a wide range of file formats including text, pdf, doc \/ docx and xml.<\/span>. Simply point the app to the folder containing the files and it will load them into the library in seconds. Additionally, users can provide the URL of a YouTube playlist and the app will load transcriptions of the videos in the playlist, enabling users to look up what they cover.<\/p>\n<p data-vmark=\"295c\">From the official description, users can use Chat With RTX in the same way as they use ChatGPT, through different queries.<span class=\"accentTextColor\">However, the results generated will be based solely on the specific dataset<\/span>, which seems to be better suited for operations such as generating summaries, quickly searching documents, and so on.<\/p>\n<p data-vmark=\"37f6\">Having an RTX GPU that supports TensorRT-LLM means users will use all data and projects locally rather than keeping them in the cloud, which saves time and provides more accurate results.<\/p>\n<p data-vmark=\"f653\">NVIDIA says that TensorRT-LLM v0.6.0, which boosts performance by 5x, will be available later this month. It will also support other LLMs such as Mistral 7B and Nemotron 3 8B.<\/p>","protected":false},"excerpt":{"rendered":"<p>Young Weida launched the Chat with RTX today, a chat robot for Windows PC supported by TensorRT-LLLM. The Chat with RTX chat robot is designed as a localised system that can be used by users without Internet access, and is supported by all GeForce RTX 30 and 40 GPUs with at least 8 GB. Chat with RTX supports multiple file formats, including text, pdf, doc\/ docx and xml. Just point the application to the folder that contains the file, it loads them into the library within seconds<\/p>","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[146],"tags":[275,239],"collection":[],"class_list":["post-3905","post","type-post","status-publish","format-standard","hentry","category-news","tag-275","tag-239"],"acf":[],"_links":{"self":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/3905","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/comments?post=3905"}],"version-history":[{"count":0,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/3905\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/media?parent=3905"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/categories?post=3905"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/tags?post=3905"},{"taxonomy":"collection","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/collection?post=3905"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}