[[["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):2025-05-08。"],[[["This guide demonstrates how to utilize AlloyDB as a vector database by leveraging the `vector` extension, which incorporates `pgvector` functions for storing embeddings."],["You must use the `vector` extension, specifically version `0.5.0.google-1` or later, which includes Google-optimized `pgvector` functionalities for storing embeddings as `vector` values."],["To store embeddings, create a `vector[]` column in your database table with the correct dimensions supported by your chosen model, for example, 768 for text-embedding-005."],["Embeddings can be copied to the newly created vector column using the `COPY` command from a CSV file that stores your vectors."],["After storing embeddings, you can enhance query performance by creating indexes with either the `vector` or `alloydb_scann` extension."]]],[]]