[[["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\u003eAlloyDB AI provides machine learning capabilities to AlloyDB for PostgreSQL and AlloyDB Omni, allowing users to apply ML models to their data.\u003c/p\u003e\n"],["\u003cp\u003eThe \u003ccode\u003evector\u003c/code\u003e extension, a customized version of \u003ccode\u003epgvector\u003c/code\u003e, is available for storing embeddings, and supports scalar quantization features as well as \u003ccode\u003eIVFFlat\u003c/code\u003e and \u003ccode\u003eHSNW\u003c/code\u003e indexes.\u003c/p\u003e\n"],["\u003cp\u003eAlloyDB includes the \u003ccode\u003ealloydb_scann\u003c/code\u003e extension, which implements a highly efficient nearest-neighbor index using the ScaNN algorithm, and is usable with PostgreSQL 15.\u003c/p\u003e\n"],["\u003cp\u003eThe \u003ccode\u003egoogle_ml_integration\u003c/code\u003e extension lets users utilize the \u003ccode\u003eInvoke predictions\u003c/code\u003e to call a model within a SQL transaction, or \u003ccode\u003eGenerate embeddings\u003c/code\u003e functions to use an LLM to translate text prompts into numerical vectors.\u003c/p\u003e\n"],["\u003cp\u003eAlloyDB Omni integrates with Vertex AI, enabling applications to invoke predictions using models from the Vertex AI Model Garden and generate embeddings using \u003ccode\u003etext-embedding-005\u003c/code\u003e LLM.\u003c/p\u003e\n"]]],[],null,[]]