{"id":13570,"date":"2024-06-20T09:26:57","date_gmt":"2024-06-20T01:26:57","guid":{"rendered":"https:\/\/www.1ai.net\/?p=13570"},"modified":"2024-06-20T09:26:57","modified_gmt":"2024-06-20T01:26:57","slug":"%e6%9c%88%e4%b9%8b%e6%9a%97%e9%9d%a2-kimi-%e5%bc%80%e6%94%be%e5%b9%b3%e5%8f%b0%e5%b0%86%e5%90%af%e5%8a%a8-context-caching-%e5%86%85%e6%b5%8b%ef%bc%9a%e6%8f%90%e4%be%9b%e9%a2%84%e8%ae%be%e5%86%85","status":"publish","type":"post","link":"https:\/\/www.1ai.net\/en\/13570.html","title":{"rendered":"Kimi Open Platform will launch Context Caching internal testing: provide preset content QA Bot, fixed document collection query"},"content":{"rendered":"<p data-vmark=\"f267\"><a href=\"https:\/\/www.1ai.net\/en\/tag\/%e6%9c%88%e4%b9%8b%e6%9a%97%e9%9d%a2\" title=\"[Sees articles with labels]\" target=\"_blank\" >Dark Side of the Moon<\/a>Official Announcement <a href=\"https:\/\/www.1ai.net\/en\/tag\/kimi\" title=\"[View articles tagged with [Kimi]]\" target=\"_blank\" >Kimi<\/a> The open platform Context Caching function will start internal testing.<strong>Supports long text and large models, and can implement context caching function<\/strong>.<\/p>\n<p data-vmark=\"ea32\"><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-13571\" title=\"44669580-79d2-402a-8487-e6e0266c144d.jpg@s_2w_820h_348\" src=\"https:\/\/www.1ai.net\/wp-content\/uploads\/2024\/06\/44669580-79d2-402a-8487-e6e0266c144d.jpg@s_2w_820h_348.jpg\" alt=\"44669580-79d2-402a-8487-e6e0266c144d.jpg@s_2w_820h_348\" width=\"820\" height=\"348\" \/><\/p>\n<p>\u25b2 Image source: Kimi Open Platform official public account, the same below<\/p>\n<p data-vmark=\"c189\">According to reports, Context Caching is an advanced feature provided by the Kimi open platform. It can reduce the cost of users requesting the same content by caching repeated Tokens content. The principle is as follows:<\/p>\n<p data-vmark=\"1783\"><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-13572\" title=\"e7d19b2a-3b65-492a-a94c-dcdfbb698ecf\" src=\"https:\/\/www.1ai.net\/wp-content\/uploads\/2024\/06\/e7d19b2a-3b65-492a-a94c-dcdfbb698ecf.png\" alt=\"e7d19b2a-3b65-492a-a94c-dcdfbb698ecf\" width=\"1080\" height=\"608\" \/><\/p>\n<p data-vmark=\"d311\">Officially, Context Caching\u00a0<strong>Can<\/strong><strong>Improve the API interface response speed<\/strong>(or first word return speed). In large-scale, high-repetition prompt scenarios, the benefits brought by the Context Caching function are greater.<\/p>\n<p data-vmark=\"bc68\">Context Caching is suitable for<strong>Frequent requests, repeated references to a large number of initial contexts<\/strong>In this case, reusing cached content can improve efficiency and reduce costs. The applicable business scenarios are as follows:<\/p>\n<ul class=\"small-size list-paddingleft-2\">\n<li>\n<p data-vmark=\"4c5a\">Provides a large number of QA Bots with preset content, such as Kimi API Assistant.<\/p>\n<\/li>\n<li>\n<p data-vmark=\"3b15\">Frequent queries on a fixed set of documents, such as a question-and-answer tool for information disclosure by listed companies.<\/p>\n<\/li>\n<li>\n<p data-vmark=\"b2f5\">Periodic analysis of static code bases or knowledge bases, such as various Copilot Agents.<\/p>\n<\/li>\n<li>\n<p data-vmark=\"9212\">Popular AI applications with huge instant traffic, such as Honghong Simulator and LLM Riddles.<\/p>\n<\/li>\n<li>\n<p data-vmark=\"411c\">Agent-type applications with complex interaction rules, such as Kimi+, a popular app.<\/p>\n<\/li>\n<\/ul>\n<p data-vmark=\"fbd6\">The official will release the best practices\/billing plans\/technical documents for the Context Caching function in the future. IT Home will keep an eye on it and bring relevant reports as soon as possible.<\/p>","protected":false},"excerpt":{"rendered":"<p>The Dark Side of the Moon has announced that the Kimi Open Platform Context Caching feature will be launched for internal testing, which will support large models of long text and enable context caching. \u25b2 Figure source Kimi open platform official public number, the same below According to the introduction, Context Caching (context caching) is a high-level function provided by the Kimi open platform, through the caching of duplicate Tokens content, to reduce the cost of the user in the request for the same content, the principle is as follows: official said Context Caching can improve the API interface Context Caching improves the API's interface response speed (or first-word return speed). Context Caching can improve the API interface response speed (or first-word return speed). In the scaled-up, highly repetitive prompt scenario, Context Caching<\/p>","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[146],"tags":[1814,1168],"collection":[],"class_list":["post-13570","post","type-post","status-publish","format-standard","hentry","category-news","tag-kimi","tag-1168"],"acf":[],"_links":{"self":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/13570","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=13570"}],"version-history":[{"count":0,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/13570\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/media?parent=13570"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/categories?post=13570"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/tags?post=13570"},{"taxonomy":"collection","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/collection?post=13570"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}