{"id":61368,"date":"2024-03-08T11:58:57","date_gmt":"2024-03-08T11:58:57","guid":{"rendered":"https:\/\/developer.kore.ai\/v10-1\/?p=61368"},"modified":"2024-03-11T13:32:08","modified_gmt":"2024-03-11T13:32:08","slug":"llm-and-generative-ai-logs","status":"publish","type":"post","link":"https:\/\/developer.kore.ai\/v10-1\/docs\/bots\/analyzing-your-bot\/llm-and-generative-ai-logs\/","title":{"rendered":"LLM and Generative AI Logs"},"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><\/div><\/section><div class=\"vc_col-sm-12 wpb_column vc_column_container\"><div class=\"vc_column-inner\"><div class=\"wpb_wrapper\"><\/div><\/div><\/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>\r\n\n<p><span style=\"font-weight: 400;\">The LLM and Gen AI Logs on the XO Platform provide detailed information about requests sent to LLMs and the corresponding responses. The logs include data on features accessing the LLMs, response generation time, payload details, tokens used, and more. It enables bot designers to track and compare usage across various LLM features and refine prompts and settings to boost performance and user experience.<\/span><\/p>\n<p><span style=\"font-weight: 400;\">The log analysis focuses on the following key areas:<\/span><\/p>\n<ul>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><b>Request-response dynamics<\/b><span style=\"font-weight: 400;\">: Analysis of request-response dynamics between user prompts and model responses offers insights into prompt and model performance in specific scenarios.<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><b>Payload details<\/b><span style=\"font-weight: 400;\">: Analyzing the payload data exchanged during interactions allows for effective monitoring and optimization of advanced AI functionalities.<\/span><\/li>\n<\/ul>\n<p><span style=\"font-weight: 400;\">To access the logs, Go to <\/span><b>Analyze<\/b><span style=\"font-weight: 400;\"> &gt; <\/span><b>LLM and Gen AI Logs<\/b><span style=\"font-weight: 400;\">. <\/span><span style=\"font-weight: 400;\">Click any record to view the log summary and payload details.<\/span><\/p>\n<p><span style=\"font-weight: 400;\"><a ref=\"magnificPopup\" href=\"https:\/\/kore-wordpress.s3.us-east-2.amazonaws.com\/developer.kore.ai\/v10-1\/wp-content\/uploads\/sites\/35\/20240311112742\/2024-03-11_16-56-37.gif\"><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-61489\" src=\"https:\/\/kore-wordpress.s3.us-east-2.amazonaws.com\/developer.kore.ai\/v10-1\/wp-content\/uploads\/sites\/35\/20240311112742\/2024-03-11_16-56-37.gif\" alt=\"\" width=\"1910\" height=\"824\" \/><\/a><\/span><\/p>\n<h2><span class=\"ez-toc-section\" id=\"Field_Description\">Field Description<\/span><\/h2>\n<p><span style=\"font-weight: 400;\">You can sort the data by either Newest to Oldest or Oldest to Newest. Click the click to view the <\/span><b>Summary<\/b><span style=\"font-weight: 400;\"> and <\/span><b>Payload Details<\/b><span style=\"font-weight: 400;\">.<\/span><\/p>\n<table>\n<tbody>\n<tr>\n<th>Fields<\/th>\n<th>Description<\/th>\n<\/tr>\n<tr>\n<td><span style=\"font-weight: 400;\">Date &amp; Time<\/span><\/td>\n<td><span style=\"font-weight: 400;\">The timestamp of the call made to the LLM.\u00a0<\/span><\/td>\n<\/tr>\n<tr>\n<td><span style=\"font-weight: 400;\">User ID<\/span><\/td>\n<td><span style=\"font-weight: 400;\">The distinct identifier of the end user engaged in the conversation.<\/span><\/p>\n<p><span style=\"font-weight: 400;\">You can view the metrics based on the <\/span><b>Kore User id<\/b><span style=\"font-weight: 400;\"> or <\/span><b>Channel User Id<\/b><span style=\"font-weight: 400;\">.<\/span><\/p>\n<p><span style=\"font-weight: 400;\">Channel-specific ids are shown only for the users who have interacted with the VA during the selected period.<\/span><\/td>\n<\/tr>\n<tr>\n<td><span style=\"font-weight: 400;\">Feature<\/span><\/td>\n<td><span style=\"font-weight: 400;\">The XO Platform feature (Co-Pilot and Dynamic conversation features) is making calls to the LLM models.<\/span><\/td>\n<\/tr>\n<tr>\n<td><span style=\"font-weight: 400;\">Description<\/span><\/td>\n<td><span style=\"font-weight: 400;\">Extra details about the node and task name linked to the feature.<\/span><\/td>\n<\/tr>\n<tr>\n<td><span style=\"font-weight: 400;\">Model<\/span><\/td>\n<td><span style=\"font-weight: 400;\">The Large Language Model to which the request was made.<\/span><\/td>\n<\/tr>\n<tr>\n<td><span style=\"font-weight: 400;\">Language<\/span><\/td>\n<td><span style=\"font-weight: 400;\">The language in which the conversation occurred.<\/span><span style=\"font-weight: 400;\"><br \/>\n<\/span><span style=\"font-weight: 400;\">If it is a multi-lingual VA, you can select specific languages to filter the conversations that occurred in those languages. The page shows the conversations that happen in all enabled languages by default.<\/span><\/td>\n<\/tr>\n<tr>\n<td><span style=\"font-weight: 400;\">Time Taken<\/span><\/td>\n<td><span style=\"font-weight: 400;\">Time taken by the LLM to generate the response.<\/span><\/td>\n<\/tr>\n<tr>\n<td><span style=\"font-weight: 400;\">Status<\/span><\/td>\n<td><span style=\"font-weight: 400;\">Status of a call made to the LLM. \u201cSuccess\u201d or \u201cFailure\u201d.<\/span><\/td>\n<\/tr>\n<tr>\n<td><span style=\"font-weight: 400;\">User<\/span><\/td>\n<td><span style=\"font-weight: 400;\">Bot designer or end user who made a call to the LLM.<\/span><\/td>\n<\/tr>\n<tr>\n<td><span style=\"font-weight: 400;\">Integration Type<\/span><\/td>\n<td><span style=\"font-weight: 400;\">Type of integration used (e.g. System\/Custom).<\/span><\/td>\n<\/tr>\n<tr>\n<td><span style=\"font-weight: 400;\">Prompt Name<\/span><\/td>\n<td><span style=\"font-weight: 400;\">Prompt used with the model and running at the node\/task level. The pre-built prompts are named &#8216;Default.<\/span><\/td>\n<\/tr>\n<tr>\n<td><span style=\"font-weight: 400;\">Channel<\/span><\/td>\n<td><span style=\"font-weight: 400;\">The communication channel or platform used for the interaction with LLM.<\/span><\/td>\n<\/tr>\n<tr>\n<td><span style=\"font-weight: 400;\">Session ID<\/span><\/td>\n<td><span style=\"font-weight: 400;\">Identifier for the session.<\/span><\/td>\n<\/tr>\n<tr>\n<td><span style=\"font-weight: 400;\">Request Payload<\/span><\/td>\n<td><span style=\"font-weight: 400;\">The request payload sent to a Large Language Model (LLM) is the user&#8217;s input or question, along with any extra details needed for the model to give a good response.\u00a0<\/span><\/td>\n<\/tr>\n<tr>\n<td><span style=\"font-weight: 400;\">Response Payload<\/span><\/td>\n<td><span style=\"font-weight: 400;\">The Large Language Model (LLM) produces a response payload as its answer to the input it receives. It&#8217;s in the text format and contains additional information required to present the response. This payload helps developers use the model&#8217;s output effectively.<\/span><\/td>\n<\/tr>\n<tr>\n<td><span style=\"font-weight: 400;\">Request Tokens<\/span><\/td>\n<td><span style=\"font-weight: 400;\">Request tokens for a Language Model (LLM) are the individual parts of input text, like words or punctuation, given to the model to create a response. These tokens are the basis for the model&#8217;s understanding and its output generation.<\/span><\/td>\n<\/tr>\n<tr>\n<td><span style=\"font-weight: 400;\">Response Tokens<\/span><\/td>\n<td><span style=\"font-weight: 400;\">Response tokens for a Large Language Model (LLM) are the pieces of generated output, like words or punctuation, showing the model&#8217;s response. These tokens make up the structured parts of the LLM&#8217;s text, making it easier to understand and analyze.<\/span><\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<h2><span class=\"ez-toc-section\" id=\"Filter_Criteria\">Filter Criteria<\/span><\/h2>\n<p><span style=\"font-weight: 400;\">The LLM and GenAI logs data can be viewed based on specific filter criteria that can be selected.<\/span><a href=\"https:\/\/developer.kore.ai\/v10-1\/docs\/bots\/analyzing-your-bot\/dashboard-filter-criteria\/\"> <span style=\"font-weight: 400;\">Learn more<\/span><\/a><span style=\"font-weight: 400;\">.<\/span><\/p>\n<p>&nbsp;<\/p>\n","protected":false},"excerpt":{"rendered":"<p>The LLM and Gen AI Logs on the XO Platform provide detailed information about requests sent to LLMs and the corresponding responses. The logs include data on features accessing the LLMs, response generation time, payload details, tokens used, and more. It enables bot designers to track and compare usage across various LLM features and refine&#8230;<\/p>\n","protected":false},"author":33,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[45],"tags":[],"class_list":["post-61368","post","type-post","status-publish","format-standard","hentry","category-analyzing-your-bot"],"_links":{"self":[{"href":"https:\/\/developer.kore.ai\/v10-1\/wp-json\/wp\/v2\/posts\/61368","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/developer.kore.ai\/v10-1\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/developer.kore.ai\/v10-1\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/developer.kore.ai\/v10-1\/wp-json\/wp\/v2\/users\/33"}],"replies":[{"embeddable":true,"href":"https:\/\/developer.kore.ai\/v10-1\/wp-json\/wp\/v2\/comments?post=61368"}],"version-history":[{"count":6,"href":"https:\/\/developer.kore.ai\/v10-1\/wp-json\/wp\/v2\/posts\/61368\/revisions"}],"predecessor-version":[{"id":61506,"href":"https:\/\/developer.kore.ai\/v10-1\/wp-json\/wp\/v2\/posts\/61368\/revisions\/61506"}],"wp:attachment":[{"href":"https:\/\/developer.kore.ai\/v10-1\/wp-json\/wp\/v2\/media?parent=61368"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/developer.kore.ai\/v10-1\/wp-json\/wp\/v2\/categories?post=61368"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/developer.kore.ai\/v10-1\/wp-json\/wp\/v2\/tags?post=61368"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}