{"id":61684,"date":"2024-04-29T12:53:54","date_gmt":"2024-04-29T11:53:54","guid":{"rendered":"https:\/\/developer.kore.ai\/v10-3\/?p=61684"},"modified":"2024-04-30T09:28:07","modified_gmt":"2024-04-30T08:28:07","slug":"whats-new-in-this-release","status":"publish","type":"post","link":"https:\/\/developer.kore.ai\/v10-3\/docs\/bots\/whats-new\/whats-new-in-this-release\/","title":{"rendered":"What&#8217;s New"},"content":{"rendered":"<section class=\"l-section wpb_row height_auto\"><div class=\"l-section-h i-cf\"><div class=\"g-cols vc_row type_default valign_top\"><div class=\"vc_col-sm-12 wpb_column vc_column_container\"><div class=\"vc_column-inner\"><div class=\"wpb_wrapper\"><div class=\"ult-spacer spacer-6ae8c68c96d59\" data-id=\"6ae8c68c96d59\" data-height=\"\" data-height-mobile=\"\" data-height-tab=\"\" data-height-tab-portrait=\"\" data-height-mobile-landscape=\"\" style=\"clear:both;display:block;\"><\/div>\r\n\t<div class=\"wpb_text_column \">\r\n\t\t<div class=\"wpb_wrapper\">\r\n\t\t\t<p>Learn about the new features and enhancements included in Kore.ai Experience Optimization Platform v10.2, released on April 27, 2024.<\/p>\n<p><span style=\"font-weight: 400;\">Key features and enhancements included in this release are summarized below.<\/span><\/p>\n\r\n\t\t<\/div>\r\n\t<\/div>\r\n<div class=\"ult-spacer spacer-6ae8c68c96e08\" data-id=\"6ae8c68c96e08\" data-height=\"10\" data-height-mobile=\"10\" data-height-tab=\"10\" data-height-tab-portrait=\"\" data-height-mobile-landscape=\"\" style=\"clear:both;display:block;\"><\/div><\/div><\/div><\/div><\/div><\/div><\/section><section class=\"l-section wpb_row height_auto\"><div class=\"l-section-h i-cf\"><div class=\"g-cols vc_row type_default valign_top\"><div class=\"vc_col-sm-12 wpb_column vc_column_container\"><div class=\"vc_column-inner\"><div class=\"wpb_wrapper\">\r\n\t<div class=\"wpb_text_column \">\r\n\t\t<div class=\"wpb_wrapper\">\r\n\t\t\t<h2><span class=\"ez-toc-section\" id=\"LLM_and_Generative_AI\"><span style=\"font-weight: 400;\">LLM and Generative AI<\/span><\/span><\/h2>\n<h3><span class=\"ez-toc-section\" id=\"Custom_LLM_Integration_Support_for_Rephrase_Dialog_Responses\"><span style=\"font-weight: 400;\">Custom LLM Integration Support for Rephrase Dialog Responses<\/span><\/span><\/h3>\n<p><span style=\"font-weight: 400;\">Rephrase Dialog Responses now supports Custom LLMs in addition to commercial LLMs. This allows platform users to use the rephrasing feature with their own custom-trained language models and create customized prompts tailored to their specific use cases, models, and linguistic contexts, providing greater flexibility and control over the rephrasing process and conversational experiences. <a href=\"https:\/\/developer.kore.ai\/v10-3\/docs\/bots\/nlp\/dynamic-conversations-features\/\" target=\"_blank\" rel=\"noopener noreferrer\">Learn more<\/a>.<\/span><\/p>\n<h2><span class=\"ez-toc-section\" id=\"NLP\">NLP<\/span><\/h2>\n<h3><span class=\"ez-toc-section\" id=\"New_Pre-trained_MPNet_Few-shot_Model_for_Intent_Detection\"><span style=\"font-weight: 400;\">New Pre-trained MPNet Few-shot Model for Intent Detection<\/span><\/span><\/h3>\n<p><span style=\"font-weight: 400;\">The few-shot model now supports the Pre-trained MPNet embedding model for intent detection. <\/span><span style=\"font-weight: 400;\">The Pre-trained MPNet model is the advanced version of MPNet. It has been pre-trained and fine-tuned for superior accuracy and precision in intent identification compared to MPNet. <a href=\"https:\/\/developer.kore.ai\/v10-3\/docs\/bots\/nlp\/user-utterances\/\" target=\"_blank\" rel=\"noopener noreferrer\">Learn more<\/a>.<\/span><\/p>\n<p><span style=\"font-weight: 400;\">Advantages of using the Pre-trained MPNet Model:<\/span><\/p>\n<ul>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><b>Understanding Negations<\/b><span style=\"font-weight: 400;\">: Pre-trained models get negations like &#8220;not&#8221; or &#8220;don&#8217;t&#8221; easily, unlike MPNet, which might mix things up. So, when you say, &#8220;I want to transfer funds,&#8221; and &#8220;I do not want to transfer funds,&#8221; pre-trained models know the difference, making them better at understanding what you really mean.<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><b>Clear Intent Differentiation<\/b><span style=\"font-weight: 400;\">: Pre-trained models are great at telling apart similar things, which can be tricky for MPNet. For example, if you say, &#8220;I want to unblock a card,&#8221; or &#8220;I want to block a card,&#8221; pre-trained models can confidently tell the difference between wanting to block or unblock a card, unlike MPNet, which might get confused.<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><b>Staying on Topic<\/b><span style=\"font-weight: 400;\">: Pre-trained models are good at sticking to the topic at hand. So, if you talk about increasing your credit card limit, they won&#8217;t start suggesting things unrelated to credit cards, unlike MPNet, which might go off track.<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><b>Easier Training<\/b><span style=\"font-weight: 400;\">: Pre-trained models need less training data compared to MPNet. This means the model can learn the same things with fewer examples, making the training process faster and simpler.<\/span><\/li>\n<\/ul>\n<h2><span class=\"ez-toc-section\" id=\"Channels\"><span style=\"font-weight: 400;\">Channels<\/span><\/span><\/h2>\n<h3><span class=\"ez-toc-section\" id=\"Support_for_Thread_Handling_for_Virtual_Assistants_in_Slack_Channels\"><span style=\"font-weight: 400;\">Support for Thread Handling for Virtual Assistants in Slack Channels<\/span><\/span><\/h3>\n<p><span style=\"font-weight: 400;\">The Platform now offers native support for threaded conversations in the Slack channel. Users can initiate a new thread from any message within a Slack channel or direct message group.<\/span><\/p>\n<p><span style=\"font-weight: 400;\">Additionally, the platform provides extended functionality for developers. It can automatically create a new thread whenever a user @mentions the virtual assistant in a Slack channel. This behavior is configurable, giving developers control over this feature.<br \/>\n<\/span><span style=\"font-weight: 400;\"><a ref=\"magnificPopup\" href=\"https:\/\/kore-wordpress.s3.us-east-2.amazonaws.com\/developer.kore.ai\/v10-3\/wp-content\/uploads\/sites\/43\/20240429135832\/slack-channel-customize-.png\"><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-61701\" src=\"https:\/\/kore-wordpress.s3.us-east-2.amazonaws.com\/developer.kore.ai\/v10-3\/wp-content\/uploads\/sites\/43\/20240429135832\/slack-channel-customize-.png\" alt=\"\" width=\"976\" height=\"229\" srcset=\"https:\/\/kore-wordpress.s3.us-east-2.amazonaws.com\/developer.kore.ai\/v10-3\/wp-content\/uploads\/sites\/43\/20240429135832\/slack-channel-customize-.png 976w, https:\/\/kore-wordpress.s3.us-east-2.amazonaws.com\/developer.kore.ai\/v10-3\/wp-content\/uploads\/sites\/43\/20240429135832\/slack-channel-customize--300x70.png 300w\" sizes=\"auto, (max-width: 976px) 100vw, 976px\" \/><\/a><\/span><\/p>\n<h2><span class=\"ez-toc-section\" id=\"Digital_Forms\"><span style=\"font-weight: 400;\">Digital Forms<\/span><\/span><\/h2>\n<ul>\n<li><span style=\"font-weight: 400;\">Enable the &#8220;Off-the-Record Information&#8221; Flag for Digital Forms: <\/span><span style=\"font-weight: 400;\">On a digital form, when the field\u2019s \u201cOff the record\u201d flag is enabled, the field data is cleared at the end of the user session and not stored in databases or logs.<\/span><\/li>\n<li><span style=\"font-weight: 400;\">Digital Forms Date Picker Supports Japanese:\u00a0<\/span><span style=\"font-weight: 400;\">The digital form\u2019s Date Picker now supports the Japanese language if the bot language is Japanese.<\/span><\/li>\n<\/ul>\n\r\n\t\t<\/div>\r\n\t<\/div>\r\n<div class=\"ult-spacer spacer-6ae8c68c97888\" data-id=\"6ae8c68c97888\" data-height=\"20\" data-height-mobile=\"20\" data-height-tab=\"20\" data-height-tab-portrait=\"\" data-height-mobile-landscape=\"\" style=\"clear:both;display:block;\"><\/div><\/div><\/div><\/div><\/div><\/div><\/section>\n","protected":false},"excerpt":{"rendered":"Learn about the new features and enhancements included in Kore.ai Experience Optimization Platform v10.2, released on April 27, 2024. Key features and enhancements included in this release are summarized below. LLM and Generative AI Custom LLM Integration Support for Rephrase Dialog Responses Rephrase Dialog Responses now supports Custom LLMs in addition to commercial LLMs. This...","protected":false},"author":26,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[13],"tags":[],"class_list":["post-61684","post","type-post","status-publish","format-standard","hentry","category-whats-new"],"_links":{"self":[{"href":"https:\/\/developer.kore.ai\/v10-3\/wp-json\/wp\/v2\/posts\/61684","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/developer.kore.ai\/v10-3\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/developer.kore.ai\/v10-3\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/developer.kore.ai\/v10-3\/wp-json\/wp\/v2\/users\/26"}],"replies":[{"embeddable":true,"href":"https:\/\/developer.kore.ai\/v10-3\/wp-json\/wp\/v2\/comments?post=61684"}],"version-history":[{"count":9,"href":"https:\/\/developer.kore.ai\/v10-3\/wp-json\/wp\/v2\/posts\/61684\/revisions"}],"predecessor-version":[{"id":61711,"href":"https:\/\/developer.kore.ai\/v10-3\/wp-json\/wp\/v2\/posts\/61684\/revisions\/61711"}],"wp:attachment":[{"href":"https:\/\/developer.kore.ai\/v10-3\/wp-json\/wp\/v2\/media?parent=61684"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/developer.kore.ai\/v10-3\/wp-json\/wp\/v2\/categories?post=61684"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/developer.kore.ai\/v10-3\/wp-json\/wp\/v2\/tags?post=61684"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}