{"id":60537,"date":"2023-12-15T10:34:25","date_gmt":"2023-12-15T10:34:25","guid":{"rendered":"https:\/\/developer.kore.ai\/v10-2\/?p=60537"},"modified":"2024-06-04T07:34:37","modified_gmt":"2024-06-04T06:34:37","slug":"dynamic-conversations-features","status":"publish","type":"post","link":"https:\/\/developer.kore.ai\/v10-2\/docs\/bots\/nlp\/dynamic-conversations-features\/","title":{"rendered":"Dynamic Conversations Features"},"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-6ae8af510905d\" data-id=\"6ae8af510905d\" 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>\r\n\t<div class=\"wpb_text_column \">\r\n\t\t<div class=\"wpb_wrapper\">\r\n\t\t\t<p><span style=\"font-weight: 400;\">The Dynamic Conversations features boost your virtual assistant\u2019s performance with LLM-powered runtime features designed to streamline development and reduce time and effort. By default, all the features are disabled. To enable the feature, select the model, prompt, and toggle the status to enable it. You can select another supported model for a feature if you have configured multiple models. You can also change the model, its prompts, and its settings.<\/span><\/p>\n<p><span style=\"font-weight: 400;\">Steps to enable the feature:<\/span><\/p>\n<ol>\n<li><span style=\"font-weight: 400;\">Navigate to <\/span><b>Build <\/b>&gt;<b> Natural Language <\/b>&gt;<b> Generative AI &amp; LLM <\/b>&gt;<b> Dynamic Conversations<\/b>.<br \/>\n<a ref=\"magnificPopup\" href=\"https:\/\/kore-wordpress.s3.us-east-2.amazonaws.com\/developer.kore.ai\/v10-2\/wp-content\/uploads\/sites\/45\/20231220143133\/Dynamic1.jpg\"><img loading=\"lazy\" decoding=\"async\" class=\"alignnone wp-image-60905 size-full\" src=\"https:\/\/kore-wordpress.s3.us-east-2.amazonaws.com\/developer.kore.ai\/v10-2\/wp-content\/uploads\/sites\/45\/20231220143133\/Dynamic1.jpg\" alt=\"\" width=\"1918\" height=\"830\" srcset=\"https:\/\/kore-wordpress.s3.us-east-2.amazonaws.com\/developer.kore.ai\/v10-2\/wp-content\/uploads\/sites\/45\/20231220143133\/Dynamic1.jpg 1918w, https:\/\/kore-wordpress.s3.us-east-2.amazonaws.com\/developer.kore.ai\/v10-2\/wp-content\/uploads\/sites\/45\/20231220143133\/Dynamic1-300x130.jpg 300w, https:\/\/kore-wordpress.s3.us-east-2.amazonaws.com\/developer.kore.ai\/v10-2\/wp-content\/uploads\/sites\/45\/20231220143133\/Dynamic1-1024x443.jpg 1024w\" sizes=\"auto, (max-width: 1918px) 100vw, 1918px\" \/><\/a><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">Select the <\/span><span style=\"font-weight: 400;\"><strong>Model<\/strong> and the <strong>Prompt <\/strong><\/span><span style=\"font-weight: 400;\">from the drop-down list for a feature.<\/span><\/li>\n<li><span style=\"font-weight: 400;\">Turn on the <strong>Status<\/strong> toggle. The success message is displayed.<\/span><\/li>\n<\/ol>\n\r\n\t\t<\/div>\r\n\t<\/div>\r\n<div class=\"ult-spacer spacer-6ae8af51091fe\" data-id=\"6ae8af51091fe\" 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>\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=\"Change_Settings_for_a_Model\"><span style=\"font-weight: 400;\">Change Settings for a Model<\/span><\/span><\/h2>\n<p>Click the option below to see the steps:<\/p>\n\r\n\t\t<\/div>\r\n\t<\/div>\r\n<div class=\"w-tabs style_default switch_click accordion title_atleft icon_chevron iconpos_right \"><div class=\"w-tabs-list items_1\"><div class=\"w-tabs-list-h\"><div class=\"w-tabs-item\"><div class=\"w-tabs-item-h\"><span class=\"w-tabs-item-title\">Change Settings for a Pre-built Model<\/span><\/div><\/div><\/div><\/div><div class=\"w-tabs-sections\"><div class=\"w-tabs-sections-h\"><div class=\"w-tabs-section\" id=\"1703076206589-aa9fd0d2-44e2\"><a href=\"#1703076206589-aa9fd0d2-44e2\" class=\"w-tabs-section-header\"><div class=\"w-tabs-section-header-h\"><h3 class=\"w-tabs-section-title\"><span class=\"ez-toc-section\" id=\"Change_Settings_for_a_Pre-built_Model\">Change Settings for a Pre-built Model<\/span><\/h3><div class=\"w-tabs-section-control\"><\/div><\/div><\/a><div class=\"w-tabs-section-content\"><div class=\"w-tabs-section-content-h i-cf\">\r\n\t<div class=\"wpb_text_column \">\r\n\t\t<div class=\"wpb_wrapper\">\r\n\t\t\t<p><span style=\"font-weight: 400;\">You can change the selected model\u2019s settings if required. <\/span><b>In most cases<\/b>,<b> the default settings work fine<\/b><span style=\"font-weight: 400;\">.<\/span><\/p>\n<p><span style=\"font-weight: 400;\">Follow these steps:<\/span><\/p>\n<ol>\n<li aria-level=\"1\"><span style=\"font-weight: 400;\">Go to\u00a0<\/span><b>Build <\/b>&gt;<b> Natural Language <\/b>&gt;<b> Generative AI &amp; LLM\u00a0<\/b>&gt; <b>Dynamic Conversations<\/b><span style=\"font-weight: 400;\">.<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">Hover over the feature to view the <\/span><b>Advance Setting<\/b><span style=\"font-weight: 400;\"> (gear) icon.<br \/>\n<a ref=\"magnificPopup\" href=\"https:\/\/kore-wordpress.s3.us-east-2.amazonaws.com\/developer.kore.ai\/v10-2\/wp-content\/uploads\/sites\/45\/20231220143158\/Dynamic2.jpg\"><img loading=\"lazy\" decoding=\"async\" class=\"alignnone wp-image-60908 size-full\" src=\"https:\/\/kore-wordpress.s3.us-east-2.amazonaws.com\/developer.kore.ai\/v10-2\/wp-content\/uploads\/sites\/45\/20231220143158\/Dynamic2.jpg\" alt=\"\" width=\"1914\" height=\"817\" srcset=\"https:\/\/kore-wordpress.s3.us-east-2.amazonaws.com\/developer.kore.ai\/v10-2\/wp-content\/uploads\/sites\/45\/20231220143158\/Dynamic2.jpg 1914w, https:\/\/kore-wordpress.s3.us-east-2.amazonaws.com\/developer.kore.ai\/v10-2\/wp-content\/uploads\/sites\/45\/20231220143158\/Dynamic2-300x128.jpg 300w, https:\/\/kore-wordpress.s3.us-east-2.amazonaws.com\/developer.kore.ai\/v10-2\/wp-content\/uploads\/sites\/45\/20231220143158\/Dynamic2-1024x437.jpg 1024w\" sizes=\"auto, (max-width: 1914px) 100vw, 1914px\" \/><\/a><\/span><span style=\"font-weight: 400;\"><br \/>\n<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">Click the <\/span><b>Advance Setting<\/b><span style=\"font-weight: 400;\">. The <\/span><b>Advance Settings<\/b><span style=\"font-weight: 400;\"> dialog box is displayed.<br \/>\n<\/span><span style=\"font-weight: 400;\"><a ref=\"magnificPopup\" href=\"https:\/\/kore-wordpress.s3.us-east-2.amazonaws.com\/developer.kore.ai\/v10-2\/wp-content\/uploads\/sites\/45\/20231220071114\/Advance_Settings.png\"><img loading=\"lazy\" decoding=\"async\" class=\"alignnone wp-image-60879\" src=\"https:\/\/kore-wordpress.s3.us-east-2.amazonaws.com\/developer.kore.ai\/v10-2\/wp-content\/uploads\/sites\/45\/20231220071114\/Advance_Settings-350x350.png\" alt=\"\" width=\"500\" height=\"569\" srcset=\"https:\/\/kore-wordpress.s3.us-east-2.amazonaws.com\/developer.kore.ai\/v10-2\/wp-content\/uploads\/sites\/45\/20231220071114\/Advance_Settings-264x300.png 264w, https:\/\/kore-wordpress.s3.us-east-2.amazonaws.com\/developer.kore.ai\/v10-2\/wp-content\/uploads\/sites\/45\/20231220071114\/Advance_Settings.png 660w\" sizes=\"auto, (max-width: 500px) 100vw, 500px\" \/><\/a><\/span><a ref=\"magnificPopup\" href=\"https:\/\/kore-wordpress.s3.us-east-2.amazonaws.com\/developer.kore.ai\/v10-2\/wp-content\/uploads\/sites\/45\/20230626144938\/advanced-model-settings.png\"> <span style=\"font-weight: 400;\"><br \/>\n<\/span><\/a><span style=\"font-weight: 400;\">Adjusting the settings allows you to fine-tune the model\u2019s behavior to meet your needs. The default settings work fine for most cases. You can tweak the settings and find the right balance for your use case. A few settings are common in the features, and a few are feature-specific:<\/span><\/li>\n<\/ol>\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li style=\"font-weight: 400;\" aria-level=\"2\"><b>Model<\/b><span style=\"font-weight: 400;\">: The selected model for which the settings are displayed.<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"2\"><b>Instructions or Context<\/b><span style=\"font-weight: 400;\">: Add feature\/use case-specific instructions or context to guide the model.<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"2\"><b>Temperature<\/b><span style=\"font-weight: 400;\">: The setting controls the randomness of the model\u2019s output. A higher temperature, like 0.8 or above, can result in unexpected, creative, and less relevant responses. On the other hand, a lower temperature, like 0.5 or below, makes the output more focused and relevant.<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"2\"><b>Max Tokens<\/b><span style=\"font-weight: 400;\">: It indicates the total number of tokens used in the API call to the model. It affects the cost and the time taken to receive a response. A token can be as short as one character or as long as one word, depending on the text.<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"2\"><b>Number of Previous User Inputs<\/b><span style=\"font-weight: 400;\">: Indicates how many previous user messages should be sent to the model as context for rephrasing the response sent through the respective node. For example, 5 means that the previous 5 responses are sent as context.<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"2\"><b>Additional Instructions<\/b><span style=\"font-weight: 400;\">: Add specific instructions on how prompts should be rephrased. You can create a persona, ask it to rephrase in a particular tone, etc.<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"2\"><b>Similarity Threshold<\/b><span style=\"font-weight: 400;\">: The Similarity Threshold is applicable for the Answer from Docs feature. This threshold refers to the similarity between the user utterance and the document chunks. The platform shortlists all chunks that are above the threshold and sends these chunks to the LLMs to auto-generate the responses. Define a suitable threshold that works best for your use case. Setting a higher threshold limits the number of chunks and may not generate any result. Setting a lower threshold might qualify too many chunks and might dilute the response.<\/span><\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<div class=\"ult-spacer spacer-6ae8af5109820\" data-id=\"6ae8af5109820\" data-height=\"28\" data-height-mobile=\"28\" data-height-tab=\"28\" 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\r\n\t\t<\/div>\r\n\t<\/div>\n<p>&nbsp;<\/p>\n\r\n\t\t<\/div>\r\n\t<\/div>\r\n<\/div><\/div><\/div><\/div><\/div><\/div><div class=\"w-tabs style_default switch_click accordion title_atleft icon_chevron iconpos_right \"><div class=\"w-tabs-list items_1\"><div class=\"w-tabs-list-h\"><div class=\"w-tabs-item\"><div class=\"w-tabs-item-h\"><span class=\"w-tabs-item-title\">Change Settings for a Custom Model<\/span><\/div><\/div><\/div><\/div><div class=\"w-tabs-sections\"><div class=\"w-tabs-sections-h\"><div class=\"w-tabs-section\" id=\"1703082550738-84909343-0e74\"><a href=\"#1703082550738-84909343-0e74\" class=\"w-tabs-section-header\"><div class=\"w-tabs-section-header-h\"><h3 class=\"w-tabs-section-title\"><span class=\"ez-toc-section\" id=\"Change_Settings_for_a_Custom_Model\">Change Settings for a Custom Model<\/span><\/h3><div class=\"w-tabs-section-control\"><\/div><\/div><\/a><div class=\"w-tabs-section-content\"><div class=\"w-tabs-section-content-h i-cf\">\r\n\t<div class=\"wpb_text_column \">\r\n\t\t<div class=\"wpb_wrapper\">\r\n\t\t\t<p><span style=\"font-weight: 400;\">For a custom model, you can only change the post-processor script to adjust the actual response with the expected response.<\/span><\/p>\n<p><span style=\"font-weight: 400;\">In the case of GenAI Node only, you can change the Exit Scenario Key-Value<\/span><b>,<\/b><span style=\"font-weight: 400;\"> Virtual Assistance Response Key, and a post-processor script.<\/span><\/p>\n<p><span style=\"font-weight: 400;\">Follow these steps:<\/span><\/p>\n<ol>\n<li aria-level=\"1\"><span style=\"font-weight: 400;\">Go to\u00a0<\/span><b>Build <\/b>&gt;<b> Natural Language <\/b>&gt;<b> Generative AI &amp; LLM\u00a0<\/b>&gt; <b>Dynamic Conversations<\/b><span style=\"font-weight: 400;\">.<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">Hover over the feature to view the <\/span><b>Setting<\/b><span style=\"font-weight: 400;\"> (gear) icon.<br \/>\n<\/span><span style=\"font-weight: 400;\"><a ref=\"magnificPopup\" href=\"https:\/\/kore-wordpress.s3.us-east-2.amazonaws.com\/developer.kore.ai\/v10-2\/wp-content\/uploads\/sites\/45\/20240212104554\/image4-3-4.png\"><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-61166\" src=\"https:\/\/kore-wordpress.s3.us-east-2.amazonaws.com\/developer.kore.ai\/v10-2\/wp-content\/uploads\/sites\/45\/20240212104554\/image4-3-4.png\" alt=\"\" width=\"1579\" height=\"553\" srcset=\"https:\/\/kore-wordpress.s3.us-east-2.amazonaws.com\/developer.kore.ai\/v10-2\/wp-content\/uploads\/sites\/45\/20240212104554\/image4-3-4.png 1579w, https:\/\/kore-wordpress.s3.us-east-2.amazonaws.com\/developer.kore.ai\/v10-2\/wp-content\/uploads\/sites\/45\/20240212104554\/image4-3-4-300x105.png 300w, https:\/\/kore-wordpress.s3.us-east-2.amazonaws.com\/developer.kore.ai\/v10-2\/wp-content\/uploads\/sites\/45\/20240212104554\/image4-3-4-1024x359.png 1024w\" sizes=\"auto, (max-width: 1579px) 100vw, 1579px\" \/><\/a><\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">Click <\/span><b>Edit<\/b><span style=\"font-weight: 400;\">. The Actual Response is displayed.<br \/>\n<a ref=\"magnificPopup\" href=\"https:\/\/kore-wordpress.s3.us-east-2.amazonaws.com\/developer.kore.ai\/v10-2\/wp-content\/uploads\/sites\/45\/20231215114027\/image6-2.png\"><img loading=\"lazy\" decoding=\"async\" class=\"alignnone wp-image-60568 size-full\" src=\"https:\/\/kore-wordpress.s3.us-east-2.amazonaws.com\/developer.kore.ai\/v10-2\/wp-content\/uploads\/sites\/45\/20231215114027\/image6-2.png\" alt=\"\" width=\"1884\" height=\"663\" srcset=\"https:\/\/kore-wordpress.s3.us-east-2.amazonaws.com\/developer.kore.ai\/v10-2\/wp-content\/uploads\/sites\/45\/20231215114027\/image6-2.png 1884w, https:\/\/kore-wordpress.s3.us-east-2.amazonaws.com\/developer.kore.ai\/v10-2\/wp-content\/uploads\/sites\/45\/20231215114027\/image6-2-300x106.png 300w, https:\/\/kore-wordpress.s3.us-east-2.amazonaws.com\/developer.kore.ai\/v10-2\/wp-content\/uploads\/sites\/45\/20231215114027\/image6-2-1024x360.png 1024w\" sizes=\"auto, (max-width: 1884px) 100vw, 1884px\" \/><\/a><\/span><span style=\"font-weight: 400;\"><br \/>\n<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">Click <\/span><b>Configure<\/b><span style=\"font-weight: 400;\">. The Post Processor Script is displayed.<br \/>\n<a ref=\"magnificPopup\" href=\"https:\/\/kore-wordpress.s3.us-east-2.amazonaws.com\/developer.kore.ai\/v10-2\/wp-content\/uploads\/sites\/45\/20231215114116\/image12-2.png\"><img loading=\"lazy\" decoding=\"async\" class=\"alignnone wp-image-60571 size-full\" src=\"https:\/\/kore-wordpress.s3.us-east-2.amazonaws.com\/developer.kore.ai\/v10-2\/wp-content\/uploads\/sites\/45\/20231215114116\/image12-2.png\" alt=\"\" width=\"1536\" height=\"847\" srcset=\"https:\/\/kore-wordpress.s3.us-east-2.amazonaws.com\/developer.kore.ai\/v10-2\/wp-content\/uploads\/sites\/45\/20231215114116\/image12-2.png 1536w, https:\/\/kore-wordpress.s3.us-east-2.amazonaws.com\/developer.kore.ai\/v10-2\/wp-content\/uploads\/sites\/45\/20231215114116\/image12-2-300x165.png 300w, https:\/\/kore-wordpress.s3.us-east-2.amazonaws.com\/developer.kore.ai\/v10-2\/wp-content\/uploads\/sites\/45\/20231215114116\/image12-2-1024x565.png 1024w\" sizes=\"auto, (max-width: 1536px) 100vw, 1536px\" \/><\/a><\/span><span style=\"font-weight: 400;\"><br \/>\n<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">Modify the script and click <\/span><b>Save &amp; Test<\/b><span style=\"font-weight: 400;\">. The Response is displayed.<br \/>\n<a ref=\"magnificPopup\" href=\"https:\/\/kore-wordpress.s3.us-east-2.amazonaws.com\/developer.kore.ai\/v10-2\/wp-content\/uploads\/sites\/45\/20231215114219\/image11-2.png\"><img loading=\"lazy\" decoding=\"async\" class=\"alignnone wp-image-60574 size-full\" src=\"https:\/\/kore-wordpress.s3.us-east-2.amazonaws.com\/developer.kore.ai\/v10-2\/wp-content\/uploads\/sites\/45\/20231215114219\/image11-2.png\" alt=\"\" width=\"1533\" height=\"838\" srcset=\"https:\/\/kore-wordpress.s3.us-east-2.amazonaws.com\/developer.kore.ai\/v10-2\/wp-content\/uploads\/sites\/45\/20231215114219\/image11-2.png 1533w, https:\/\/kore-wordpress.s3.us-east-2.amazonaws.com\/developer.kore.ai\/v10-2\/wp-content\/uploads\/sites\/45\/20231215114219\/image11-2-300x164.png 300w, https:\/\/kore-wordpress.s3.us-east-2.amazonaws.com\/developer.kore.ai\/v10-2\/wp-content\/uploads\/sites\/45\/20231215114219\/image11-2-1024x560.png 1024w\" sizes=\"auto, (max-width: 1533px) 100vw, 1533px\" \/><\/a><\/span><span style=\"font-weight: 400;\"><br \/>\n<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">Click <\/span><b>Save<\/b><span style=\"font-weight: 400;\">.<\/span><\/li>\n<li aria-level=\"1\"><span style=\"font-weight: 400;\">(Only for GenAI Node) <\/span><span style=\"font-weight: 400;\">Enter the <\/span><b>Exit Scenario Key-Value<\/b><span style=\"font-weight: 400;\"> and <\/span><b>Virtual Assistance Response Key<\/b> fields. Click<span style=\"font-weight: 400;\">\u00a0<\/span><b>Save<\/b><span style=\"font-weight: 400;\">.<\/span><span style=\"font-weight: 400;\"><br \/>\n<\/span><span style=\"font-weight: 400;\">The Exit Scenario Key-Value fields help identify when to end the interaction with the GenAI model and return to the dialog flow. A Virtual Assistance Response Key is available in the response payload to display the VA\u2019s response to the user.<br \/>\n<a ref=\"magnificPopup\" href=\"https:\/\/kore-wordpress.s3.us-east-2.amazonaws.com\/developer.kore.ai\/v10-2\/wp-content\/uploads\/sites\/45\/20240212102036\/image1-8.png\"><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-61163\" src=\"https:\/\/kore-wordpress.s3.us-east-2.amazonaws.com\/developer.kore.ai\/v10-2\/wp-content\/uploads\/sites\/45\/20240212102036\/image1-8.png\" alt=\"\" width=\"1904\" height=\"696\" srcset=\"https:\/\/kore-wordpress.s3.us-east-2.amazonaws.com\/developer.kore.ai\/v10-2\/wp-content\/uploads\/sites\/45\/20240212102036\/image1-8.png 1904w, https:\/\/kore-wordpress.s3.us-east-2.amazonaws.com\/developer.kore.ai\/v10-2\/wp-content\/uploads\/sites\/45\/20240212102036\/image1-8-300x110.png 300w, https:\/\/kore-wordpress.s3.us-east-2.amazonaws.com\/developer.kore.ai\/v10-2\/wp-content\/uploads\/sites\/45\/20240212102036\/image1-8-1024x374.png 1024w\" sizes=\"auto, (max-width: 1904px) 100vw, 1904px\" \/><\/a><br \/>\n<\/span><\/li>\n<\/ol>\n\r\n\t\t<\/div>\r\n\t<\/div>\r\n<\/div><\/div><\/div><\/div><\/div><\/div><div class=\"ult-spacer spacer-6ae8af5109e02\" data-id=\"6ae8af5109e02\" data-height=\"28\" data-height-mobile=\"28\" data-height-tab=\"28\" 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<h2><span class=\"ez-toc-section\" id=\"Model_and_Feature_Support_Matrix\"><span style=\"font-weight: 400;\">Model and Feature Support Matrix<\/span><\/span><\/h2>\n<p><span style=\"font-weight: 400;\">The following table displays the Dynamic Conversation features and the supported models.\u00a0<\/span><\/p>\n<p>(<span style=\"font-weight: 400;\">\u2705 Supported | <\/span><span style=\"font-weight: 400;\">\u274c Not Supported)<\/span><\/p>\n<table>\n<tbody>\n<tr>\n<td><b>Model<\/b><\/td>\n<td><span style=\"font-weight: 400;\">GenAI Node<\/span><\/td>\n<td><span style=\"font-weight: 400;\">Answer From Documents<\/span><\/td>\n<td><span style=\"font-weight: 400;\">GenAI Prompt<\/span><\/td>\n<td><span style=\"font-weight: 400;\">Rephrase Dialog Responses<\/span><\/td>\n<td><span style=\"font-weight: 400;\">Zero-shot ML Model<\/span><\/td>\n<td><span style=\"font-weight: 400;\">Repeat Responses<\/span><\/td>\n<td><span style=\"font-weight: 400;\">Rephrase User Query<\/span><\/td>\n<\/tr>\n<tr>\n<td><span style=\"font-weight: 400;\">Azure OpenAI \u2013 GPT 3.5 Turbo<\/span><\/td>\n<td><span style=\"font-weight: 400;\">\u2705<\/span><\/td>\n<td><span style=\"font-weight: 400;\">\u2705<\/span><\/td>\n<td><span style=\"font-weight: 400;\">\u2705<\/span><\/td>\n<td><span style=\"font-weight: 400;\">\u2705<\/span><\/td>\n<td><span style=\"font-weight: 400;\">\u2705<\/span><\/td>\n<td><span style=\"font-weight: 400;\">\u2705<\/span><\/td>\n<td><span style=\"font-weight: 400;\">\u274c<\/span><\/td>\n<\/tr>\n<tr>\n<td><span style=\"font-weight: 400;\">Azure OpenAI \u2013 GPT 4<\/span><\/td>\n<td><span style=\"font-weight: 400;\">\u2705<\/span><\/td>\n<td><span style=\"font-weight: 400;\">\u2705<\/span><\/td>\n<td><span style=\"font-weight: 400;\">\u2705<\/span><\/td>\n<td><span style=\"font-weight: 400;\">\u2705<\/span><\/td>\n<td><span style=\"font-weight: 400;\">\u2705*<\/span><\/td>\n<td><span style=\"font-weight: 400;\">\u2705<\/span><\/td>\n<td><span style=\"font-weight: 400;\">\u274c<\/span><\/td>\n<\/tr>\n<tr>\n<td><span style=\"font-weight: 400;\">OpenAI \u2013 GPT 3.5 Turbo<\/span><\/td>\n<td><span style=\"font-weight: 400;\">\u2705<\/span><\/td>\n<td><span style=\"font-weight: 400;\">\u2705<\/span><\/td>\n<td><span style=\"font-weight: 400;\">\u2705<\/span><\/td>\n<td><span style=\"font-weight: 400;\">\u2705<\/span><\/td>\n<td><span style=\"font-weight: 400;\">\u2705<\/span><\/td>\n<td><span style=\"font-weight: 400;\">\u2705<\/span><\/td>\n<td><span style=\"font-weight: 400;\">\u274c<\/span><\/td>\n<\/tr>\n<tr>\n<td><span style=\"font-weight: 400;\">OpenAI \u2013 GPT 4<\/span><\/td>\n<td><span style=\"font-weight: 400;\">\u2705<\/span><\/td>\n<td><span style=\"font-weight: 400;\">\u2705<\/span><\/td>\n<td><span style=\"font-weight: 400;\">\u2705<\/span><\/td>\n<td><span style=\"font-weight: 400;\">\u2705<\/span><\/td>\n<td><span style=\"font-weight: 400;\">\u2705*<\/span><\/td>\n<td><span style=\"font-weight: 400;\">\u2705<\/span><\/td>\n<td><span style=\"font-weight: 400;\">\u274c<\/span><\/td>\n<\/tr>\n<tr>\n<td><span style=\"font-weight: 400;\">Anthropic \u2013 Claude Instant<\/span><\/td>\n<td><span style=\"font-weight: 400;\">\u274c<\/span><\/td>\n<td><span style=\"font-weight: 400;\">\u274c<\/span><\/td>\n<td><span style=\"font-weight: 400;\">\u2705<\/span><\/td>\n<td><span style=\"font-weight: 400;\">\u2705<\/span><\/td>\n<td><span style=\"font-weight: 400;\">\u274c<\/span><\/td>\n<td><span style=\"font-weight: 400;\">\u2705<\/span><\/td>\n<td><span style=\"font-weight: 400;\">\u274c<\/span><\/td>\n<\/tr>\n<tr>\n<td><span style=\"font-weight: 400;\">Anthropic \u2013 Claude<\/span><\/td>\n<td><span style=\"font-weight: 400;\">\u274c<\/span><\/td>\n<td><span style=\"font-weight: 400;\">\u274c<\/span><\/td>\n<td><span style=\"font-weight: 400;\">\u2705<\/span><\/td>\n<td><span style=\"font-weight: 400;\">\u2705<\/span><\/td>\n<td><span style=\"font-weight: 400;\">\u274c<\/span><\/td>\n<td><span style=\"font-weight: 400;\">\u2705<\/span><\/td>\n<td><span style=\"font-weight: 400;\">\u274c<\/span><\/td>\n<\/tr>\n<tr>\n<td><span style=\"font-weight: 400;\">Custom LLM<\/span><\/td>\n<td><span style=\"font-weight: 400;\">\u2705<\/span><\/td>\n<td><span style=\"font-weight: 400;\">\u274c<\/span><\/td>\n<td><span style=\"font-weight: 400;\">\u2705<\/span><\/td>\n<td><span style=\"font-weight: 400;\">\u2705<\/span><\/td>\n<td><span style=\"font-weight: 400;\">\u274c<\/span><\/td>\n<td><span style=\"font-weight: 400;\">\u274c<\/span><\/td>\n<td><span style=\"font-weight: 400;\">\u274c<\/span><\/td>\n<\/tr>\n<tr>\n<td><span style=\"font-weight: 400;\">Kore.ai XO GPT<\/span><\/td>\n<td><span style=\"font-weight: 400;\">\u274c<\/span><\/td>\n<td><span style=\"font-weight: 400;\">\u274c<\/span><\/td>\n<td><span style=\"font-weight: 400;\">\u274c<\/span><\/td>\n<td><span style=\"font-weight: 400;\">\u2705<\/span><\/td>\n<td><span style=\"font-weight: 400;\">\u274c<\/span><\/td>\n<td><span style=\"font-weight: 400;\">\u274c<\/span><\/td>\n<td><span style=\"font-weight: 400;\">\u2705<\/span><\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<p>&nbsp;<\/p>\n<p><span style=\"font-weight: 400;\">*<\/span><span style=\"font-weight: 400;\">\u00a0 Currently, the Zero-shot ML Model does not support batch testing when using GPT 4.<\/span><\/p>\n<div class=\"alert alert-info\"><b>Note<\/b>: Azure OpenAI and OpenAI have officially ended support for their GPT-3 model on January 4, 2024. We recommend selecting a higher or alternate model for supported features as soon as possible. <a href=\"https:\/\/platform.openai.com\/docs\/deprecations\" target=\"_blank\" rel=\"noopener noreferrer\">Learn more<\/a>.<\/div>\n<h2><span class=\"ez-toc-section\" id=\"Feature_Details\"><span style=\"font-weight: 400;\">Feature Details<\/span><\/span><\/h2>\n<h3><span class=\"ez-toc-section\" id=\"GenAI_Node\">GenAI Node<\/span><\/h3>\n<p>When enabled, this feature lets you add an GenAI Node to Dialog Tasks. This node allows you to collect Entities from end-users in a free-flowing conversation (in the selected English\/Non-English Bot Language) using LLM and Generative AI in the background. You can define the entities to be collected as well as rules &amp; scenarios in English and Non-English Bot languages. You can configure node properties just like any other node. You can also use the GenAI Node across Dialog Tasks.<\/p>\n<p><a ref=\"magnificPopup\" href=\"https:\/\/kore-wordpress.s3.us-east-2.amazonaws.com\/developer.kore.ai\/v10-2\/wp-content\/uploads\/sites\/45\/20230903083238\/GeanAI-Botactionnode-1.png\"><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-59048\" src=\"https:\/\/kore-wordpress.s3.us-east-2.amazonaws.com\/developer.kore.ai\/v10-2\/wp-content\/uploads\/sites\/45\/20230903083238\/GeanAI-Botactionnode-1.png\" alt=\"\" width=\"750\" height=\"500\" \/><\/a><\/p>\n<p><b>Usage<\/b><\/p>\n<p>When creating or editing a Dialog Task that\u2019s created manually or <a href=\"https:\/\/developer.kore.ai\/v10-2\/docs\/bots\/chatbot-overview\/using-the-dialog-builder-tool\/#Auto-Generated_Dialog_Tasks\">auto-generated<\/a>, you can find a node called GenAI Node within your nodes list.<br \/>\nWhen this feature is disabled, the node is unavailable within the Dialog Builder. <a href=\"https:\/\/developer.kore.ai\/v10-2\/docs\/bots\/bot-builder-tool\/dialog-task\/genai-node\/\">Learn more<\/a>.<\/p>\n<h3><span class=\"ez-toc-section\" id=\"Answer_From_Documents\">Answer From Documents<\/span><\/h3>\n<p><span style=\"font-weight: 400;\">This feature leverages a Large Language Model (LLM) and Generative AI models from OpenAI to generate answers for FAQs by processing uploaded documents in an unstructured PDF format and user queries.<\/span><\/p>\n<p><a ref=\"magnificPopup\" href=\"https:\/\/kore-wordpress.s3.us-east-2.amazonaws.com\/developer.kore.ai\/v10-2\/wp-content\/uploads\/sites\/45\/20230731110104\/answer-from-docs.png\"><img loading=\"lazy\" decoding=\"async\" class=\"alignnone wp-image-58465\" src=\"https:\/\/kore-wordpress.s3.us-east-2.amazonaws.com\/developer.kore.ai\/v10-2\/wp-content\/uploads\/sites\/45\/20230731110104\/answer-from-docs.png\" alt=\"\" width=\"869\" height=\"352\" srcset=\"https:\/\/kore-wordpress.s3.us-east-2.amazonaws.com\/developer.kore.ai\/v10-2\/wp-content\/uploads\/sites\/45\/20230731110104\/answer-from-docs.png 953w, https:\/\/kore-wordpress.s3.us-east-2.amazonaws.com\/developer.kore.ai\/v10-2\/wp-content\/uploads\/sites\/45\/20230731110104\/answer-from-docs-300x122.png 300w\" sizes=\"auto, (max-width: 869px) 100vw, 869px\" \/><\/a><\/p>\n<p><b>Usage<\/b><\/p>\n<p><span style=\"font-weight: 400;\">After redacting personally identifiable information, the uploaded documents and the end-user queries are shared with OpenAI to curate the answers.<\/span><\/p>\n<p><span style=\"font-weight: 400;\">Once you meet the prerequisites and enable the feature:<\/span><\/p>\n<ol>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">You should <\/span><a href=\"https:\/\/developer.kore.ai\/v10-2\/v10\/docs\/bots\/bot-builder-tool\/knowledge-task\/answer-from-documents\/#Upload_PDF_Documents\"><span style=\"font-weight: 400;\">upload the PDF document(s)<\/span><\/a><span style=\"font-weight: 400;\"> to be shared with the third-party system (OpenAI). You can upload a maximum of 10 documents with a size of not more than 5 MB.<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">The uploaded documents <\/span><span style=\"font-weight: 400;\">are listed under the <\/span><b>Answer from Documents<\/b><span style=\"font-weight: 400;\"> section with the following details:<\/span><\/li>\n<\/ol>\n<ul>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">Upload Name<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">Uploaded by<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">Uploaded on<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">Status (Active\/Inactive)<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">Actions (View and Delete File)<\/span><\/li>\n<\/ul>\n<ol start=\"3\">\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">A good practice is to test the answer generation by asking the VA a question directly related to the contents of your uploaded documents. <\/span><a href=\"https:\/\/developer.kore.ai\/v10-2\/v10\/docs\/bots\/bot-builder-tool\/knowledge-task\/answer-from-documents\/#Test_Answer_Generation\"><span style=\"font-weight: 400;\">Learn more<\/span><\/a><span style=\"font-weight: 400;\">.<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">You can view, delete, and disable the uploaded documents.<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">The VA provides answers only from uploaded documents that are active, whereas disabled documents are ignored.<\/span><\/li>\n<\/ol>\n<p><span style=\"font-weight: 400;\">If the feature is disabled, you won\u2019t be able <\/span><span style=\"font-weight: 400;\">to send queries to LLMs as a fallback. <\/span><a href=\"https:\/\/developer.kore.ai\/v10-2\/docs\/bots\/bot-builder-tool\/knowledge-task\/answer-from-documents\/#Disable_Answer_from_Documents\"><span style=\"font-weight: 400;\">Learn more<\/span><\/a><span style=\"font-weight: 400;\">.<\/span><\/p>\n<h3 style=\"margin-bottom: 18.0pt;\"><span class=\"ez-toc-section\" id=\"GenAI_Prompt\"><span lang=\"EN\" style=\"color: #073763;\">GenAI Prompt<\/span><\/span><\/h3>\n<p>This feature lets you define custom user prompts based on the conversation context and the response from the LLMs. You can define the subsequent conversation flow by selecting a specific AI model, tweaking its settings, and previewing the response for the prompt.<\/p>\n<p>&nbsp;<\/p>\n<p><strong>Usage<\/strong><\/p>\n<ol>\n<li><strong>\u00a0<\/strong>When building the Dialog Flow, click the <strong>\u201c+\u201d <\/strong>button, and select the <strong>GenAI Prompt <\/strong>node.<br \/>\n<a ref=\"magnificPopup\" href=\"https:\/\/kore-wordpress.s3.us-east-2.amazonaws.com\/developer.kore.ai\/v10-2\/wp-content\/uploads\/sites\/45\/20230903084030\/GenAI-promptnode.png\"><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-59051\" src=\"https:\/\/kore-wordpress.s3.us-east-2.amazonaws.com\/developer.kore.ai\/v10-2\/wp-content\/uploads\/sites\/45\/20230903084030\/GenAI-promptnode.png\" alt=\"\" width=\"700\" height=\"500\" \/><\/a><\/li>\n<li>Configuring the Component Properties in the following sections helps set up the node:<\/li>\n<\/ol>\n<ul>\n<li><strong>General Settings<\/strong>: Provide<strong> Name<\/strong> and <strong>Display Name<\/strong> for the node and write your own OpenAI Prompt.<\/li>\n<li><strong>Advanced Settings: <\/strong>Fine-tune the model\u2019s behavior and tweak its settings as required for the following:\n<ul>\n<li>Model<\/li>\n<li>System Context<\/li>\n<li>Temperature<\/li>\n<li>Max Tokens<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<ol start=\"3\">\n<li><strong>Advanced<\/strong> <strong>Controls<\/strong>: Select the maximum wait time (<strong>Timeout)<\/strong> to receive a response from the LLM and the bot\u2019s response (Timeout Error Handling) when a timeout error occurs.<\/li>\n<li>When you add custom tags to the <strong>current message<\/strong>, <strong>user profile<\/strong>, and <strong>session <\/strong>under <strong>Instance Properties, <\/strong>you can build custom profiles for the bot conversation. .<\/li>\n<li>Configuring node connections on an instance lets you define the connection rules for the conversation using transition conditions. This lets the conversation follow specific paths based on the user\u2019s input.<\/li>\n<\/ol>\n<p>If this feature is disabled, you cannot configure the ML model to build custom prompts using OpenAI for different use cases. <a href=\"https:\/\/developer.kore.ai\/v10-2\/docs\/bots\/bot-builder-tool\/dialog-task\/genai-prompt\/\" target=\"_blank\" rel=\"noopener noreferrer\">Learn more<\/a>.<\/p>\n<h3><span class=\"ez-toc-section\" id=\"Rephrase_Dialog_Responses\">Rephrase Dialog Responses<\/span><\/h3>\n<p><span style=\"font-weight: 400;\">This feature sends all User Prompts, Error Prompts, and Bot Responses to the Generative AI along with the conversation context, which depends on the configured number of user inputs. Responses are rephrased in English or the selected Non-English Bot Language based on the context and user emotion, providing a more empathetic, natural, and contextual conversation experience to the end-user.\u00a0You can give instructions (additional instructions) in English or any other bot language you select.<\/span><\/p>\n<p><a ref=\"magnificPopup\" href=\"https:\/\/docs.kore.ai\/smartassist\/wp-content\/uploads\/sites\/45\/sites\/3\/2023\/04\/rephrase-response.gif\"><img decoding=\"async\" class=\"alignnone wp-image-10532\" src=\"https:\/\/docs.kore.ai\/smartassist\/wp-content\/uploads\/sites\/45\/sites\/3\/2023\/04\/rephrase-response.gif\" \/><\/a><\/p>\n<p><b>Usage<\/b><\/p>\n<p><span style=\"font-weight: 400;\">When configuring a <\/span><a href=\"https:\/\/developer.kore.ai\/v10-2\/docs\/bots\/bot-builder-tool\/dialog-task\/working-with-the-message-nodes\/#Component_Properties\"><span style=\"font-weight: 400;\">Message<\/span><\/a><span style=\"font-weight: 400;\">, <\/span><a href=\"https:\/\/developer.kore.ai\/v10-2\/docs\/bots\/bot-builder-tool\/dialog-task\/working-with-the-entity-node\/#Component_Properties\"><span style=\"font-weight: 400;\">Entity<\/span><\/a><span style=\"font-weight: 400;\">, or <\/span><a href=\"https:\/\/developer.kore.ai\/v10-2\/docs\/bots\/bot-builder-tool\/dialog-task\/working-with-the-confirmation-nodes\/#Component_Properties\"><span style=\"font-weight: 400;\">Confirmation <\/span><\/a><span style=\"font-weight: 400;\">node, you can enable the <\/span><b>Rephrase Response <\/b><span style=\"font-weight: 400;\">feature (disabled by default). This lets you set the number of user inputs sent to OpenAI\/Anthropic Claude-1 based on the selected model as context for rephrasing the response sent through the node. You can choose between 0 and 5, where 0 means that no previous input is considered, while 5 means that the previous. 5 responses are sent as context.<\/span><\/p>\n<p><span style=\"font-weight: 400;\">When this feature is disabled, the Rephrase Response section is not visible within your node\u2019s Component Properties.<\/span><\/p>\n<p><span style=\"font-weight: 400;\"><a ref=\"magnificPopup\" href=\"https:\/\/docs.kore.ai\/smartassist\/wp-content\/uploads\/sites\/45\/sites\/3\/2023\/04\/rephrase-response.png\"><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-10535\" src=\"https:\/\/docs.kore.ai\/smartassist\/wp-content\/uploads\/sites\/45\/sites\/3\/2023\/04\/rephrase-response.png\" alt=\"\" width=\"388\" height=\"269\" \/><\/a><\/span><\/p>\n<h3><span class=\"ez-toc-section\" id=\"Zero-shot_ML_Model\">Zero-shot ML Model<\/span><\/h3>\n<p>This feature uses a Azure OpenAI or OpenAI LLM models to help the ML Engine identify the relevant intents from user utterances based on semantic similarity. By identifying the logical intent during run time, this feature eliminates the need for training data. The Zero-shot ML model requires well-defined intents to work well. This training approach is well-suited for virtual assistants with relatively fewer intents and distinct use cases.<\/p>\n<div class=\"alert alert-info\"><b>Note:<\/b> The Zero-shot model is production-ready in English but experimental in other languages. We advise caution before using it in production for non-English languages.<\/div>\n<p><strong>Usage\u00a0<\/strong><\/p>\n<p>Before performing utterance testing, the user selects the <strong>Zero-shot Model with OpenAI<\/strong> Network Type. During utterance testing, the user provides a more descriptive input with a subject, object, and nouns. Once the test runs, the system identifies the most logical intent as the definitive match by comparing the following:<\/p>\n<ul>\n<li>User utterance input<\/li>\n<li>Intent names<\/li>\n<\/ul>\n<p>The identified intent is then displayed as the matched intent.<\/p>\n<p>If this feature is disabled, the system won\u2019t identify and display the logical and matched intent during utterance testing. <a href=\"https:\/\/developer.kore.ai\/v10-2\/v10\/docs\/bots\/nlp\/user-utterances\/#Zero-Shot_Learning_Model_with_OpenAI\">Learn more<\/a>.<\/p>\n<h3><span class=\"ez-toc-section\" id=\"Repeat_Responses\">Repeat Responses<\/span><\/h3>\n<p><span style=\"font-weight: 400;\">This feature uses LLM to reiterate the recent bot responses when the Repeat Response event is triggered. Bot developers can enable the event and customize the trigger conditions. This empowers end-users to ask the bot to repeat its recent responses at any point during the conversation. Currently, this event is supported for IVR, Audiocodes, and Twilio Voice channels. <a href=\"https:\/\/developer.kore.ai\/v10-2\/docs\/bots\/bot-intelligence\/event-based-bot-actions\/#Repeat_Bot_Response_Event\">Learn more<\/a>.<\/span><\/p>\n<h3><span class=\"ez-toc-section\" id=\"Rephrase_User_Query\">Rephrase User Query<\/span><\/h3>\n<p>This feature uses the <a href=\"https:\/\/developer.kore.ai\/v10-2\/docs\/bots\/nlp\/kore-xo-gpt-model\/\" target=\"_blank\" rel=\"noopener noreferrer\">Kore.ai XO GPT Model<\/a>. This model helps improve intent detection and entity extraction by enriching the user query with relevant details from the ongoing user conversation.<\/p>\n<p>When a user intent and entity are split across multiple utterances or through the conversation, the feature enriches the user query by rephrasing the user\u2019s multiple queries during runtime. This enriched user query contains all the conversation details so the bot can understand the actual meaning behind a user\u2019s utterance. This enriched user query is fed to the natural language, improving accuracy by improving intent identification and entity extraction.<\/p>\n<p><strong>Usage<\/strong><\/p>\n<p>The LLM rephrases the query using one of the following methods depending on the scenario:<\/p>\n<p><strong>Completeness<\/strong>: The user query should be complete based on the conversation context so that the NLP can identify the right intent. If the user query is incomplete, the system urges the user to rephrase with more information.<\/p>\n<p>For example:<br \/>\nUser: What is the weather forecast for New York tomorrow?<br \/>\nBot: It will be Sunny, with temperature ranging between 30 &#8211; 35 degrees Celsius.<br \/>\nUser: How about Orlando?<br \/>\nBot: Sorry, I cannot understand. Can you please rephrase?<\/p>\n<p>The query should be completed as \u201cHow about the weather forecast in Orlando tomorrow?\u201d.<\/p>\n<p><strong>Co-referencing<\/strong>: Coreference arises when multiple expressions or queries within text pertain to a common entity. In cases where a user&#8217;s query demonstrates incomplete coreference, the system prompts the user to rephrase the query with additional information. This enhances NLP&#8217;s ability to discern the correct intent and entities involved.<\/p>\n<p>For example:<br \/>\nUser: I&#8217;ve been experiencing a persistent headache for the past week.<br \/>\nBot: I&#8217;m sorry to hear that. Have you been taking any medication for it?<br \/>\nUser: Yes, I&#8217;ve been taking ibuprofen, but it doesn&#8217;t seem to help much.<br \/>\nBot: I see. How often do you take ibuprofen?<br \/>\nUser: I take it every six hours<br \/>\nBot: I don\u2019t understand. Can you tell me how often you take ibuprofen?<\/p>\n<p>The co-reference in the user query should be expanded for NLP to identify the right intent and entities. The co-reference should be expanded as \u201cI take ibuprofen every six hours\u201d.<\/p>\n<p><strong>Completeness and Co-referencing<\/strong>: The following example illustrates completeness and co-referencing issues with the user\u2019s input which triggers rephrasing.<\/p>\n<p>For example:<br \/>\nUser: I want to apply for a personal loan.<br \/>\nBot: Sure, I can help you. You&#8217;re eligible to take a personal loan of up to 20,000$.<br \/>\nUser: How about a Home loan?<br \/>\nBot: You&#8217;re eligible to apply for a home loan as well. You can avail up to 100,000$.<br \/>\nUser: What about the interest rates of both loans?<\/p>\n<p>The co-reference and the query have to be completed as \u201cWhat is the interest rate of personal loan and home loan?<\/p>\n<h3><span class=\"ez-toc-section\" id=\"Few-shot_ML_Model\"><span style=\"font-weight: 400;\">Few-shot ML Model<\/span><\/span><\/h3>\n<p>The Few-shot model uses Kore Ai\u2019s hosted embeddings to train virtual assistants based on intent names and training utterances. The model identifies the intents based on semantic similarity between user and training utterances.<\/p>\n<div class=\"alert alert-info\"><b>Note:<\/b> The Few-shot model is production-ready in English but experimental in other languages. We advise caution before using it in production for non-English languages.<\/div>\n<p><b>Usage\u00a0<\/b><\/p>\n<p><span style=\"font-weight: 400;\">Before performing utterance testing, the user selects the <\/span><b>Few-Shot Model (Kore.ai Hosted Embeddings) <\/b><span style=\"font-weight: 400;\">network type.\u00a0<\/span><\/p>\n<p><span style=\"font-weight: 400;\">During utterance testing, the user provides a more descriptive intent name with a subject, object, and nouns, as well as the training utterances. Once the test runs, the system identifies the most logical intent as the definitive match based on the following:<\/span><\/p>\n<ul>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">The default configuration settings<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">User utterance input<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">Intent names<\/span><\/li>\n<\/ul>\n<p><span style=\"font-weight: 400;\">If this feature is disabled, the system won\u2019t identify and display the logically matched intent during utterance testing. <\/span><a href=\"https:\/\/developer.kore.ai\/v10-2\/docs\/bots\/nlp\/user-utterances\/#Few-Shot_Model_Koreai_Hosted_Embeddings\"><span style=\"font-weight: 400;\">Learn more<\/span><\/a><span style=\"font-weight: 400;\">.<\/span><\/p>\n<p>&nbsp;<\/p>\n\r\n\t\t<\/div>\r\n\t<\/div>\r\n<div class=\"ult-spacer spacer-6ae8af510aa92\" data-id=\"6ae8af510aa92\" 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>\n","protected":false},"excerpt":{"rendered":"The Dynamic Conversations features boost your virtual assistant\u2019s performance with LLM-powered runtime features designed to streamline development and reduce time and effort. By default, all the features are disabled. To enable the feature, select the model, prompt, and toggle the status to enable it. You can select another supported model for a feature if you...","protected":false},"author":33,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[203,6],"tags":[],"class_list":["post-60537","post","type-post","status-publish","format-standard","hentry","category-llm-and-generative-ai","category-nlp"],"_links":{"self":[{"href":"https:\/\/developer.kore.ai\/v10-2\/wp-json\/wp\/v2\/posts\/60537","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/developer.kore.ai\/v10-2\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/developer.kore.ai\/v10-2\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/developer.kore.ai\/v10-2\/wp-json\/wp\/v2\/users\/33"}],"replies":[{"embeddable":true,"href":"https:\/\/developer.kore.ai\/v10-2\/wp-json\/wp\/v2\/comments?post=60537"}],"version-history":[{"count":30,"href":"https:\/\/developer.kore.ai\/v10-2\/wp-json\/wp\/v2\/posts\/60537\/revisions"}],"predecessor-version":[{"id":61817,"href":"https:\/\/developer.kore.ai\/v10-2\/wp-json\/wp\/v2\/posts\/60537\/revisions\/61817"}],"wp:attachment":[{"href":"https:\/\/developer.kore.ai\/v10-2\/wp-json\/wp\/v2\/media?parent=60537"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/developer.kore.ai\/v10-2\/wp-json\/wp\/v2\/categories?post=60537"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/developer.kore.ai\/v10-2\/wp-json\/wp\/v2\/tags?post=60537"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}