[[["易于理解","easyToUnderstand","thumb-up"],["解决了我的问题","solvedMyProblem","thumb-up"],["其他","otherUp","thumb-up"]],[["很难理解","hardToUnderstand","thumb-down"],["信息或示例代码不正确","incorrectInformationOrSampleCode","thumb-down"],["没有我需要的信息/示例","missingTheInformationSamplesINeed","thumb-down"],["翻译问题","translationIssue","thumb-down"],["其他","otherDown","thumb-down"]],["最后更新时间 (UTC):2025-04-11。"],[[["\u003cp\u003eThis page provides detailed reference information regarding the tuning parameters for the ScaNN Index.\u003c/p\u003e\n"],["\u003cp\u003eThe \u003ccode\u003emax_num_levels\u003c/code\u003e, \u003ccode\u003enum_leaves\u003c/code\u003e, and \u003ccode\u003equantizer\u003c/code\u003e parameters are used during index creation and can be adjusted for optimal performance based on the size of the vector dataset.\u003c/p\u003e\n"],["\u003cp\u003eThe \u003ccode\u003escann.enable_pca\u003c/code\u003e parameter, enabled by default, uses Principal Component Analysis to reduce embedding size, but can be disabled if recall deteriorates.\u003c/p\u003e\n"],["\u003cp\u003e\u003ccode\u003escann.num_leaves_to_search\u003c/code\u003e, \u003ccode\u003escann.pre_reordering_num_neighbors\u003c/code\u003e, and \u003ccode\u003escann.num_search_threads\u003c/code\u003e are query runtime parameters that impact the trade-off between recall and QPS, and can be adjusted based on application requirements.\u003c/p\u003e\n"],["\u003cp\u003eAdjusting the \u003ccode\u003enum_leaves\u003c/code\u003e parameter when creating an index can create a more fine-grained index, improving recall and query performance at the cost of longer index creation times.\u003c/p\u003e\n"]]],[],null,[]]