[[["이해하기 쉬움","easyToUnderstand","thumb-up"],["문제가 해결됨","solvedMyProblem","thumb-up"],["기타","otherUp","thumb-up"]],[["이해하기 어려움","hardToUnderstand","thumb-down"],["잘못된 정보 또는 샘플 코드","incorrectInformationOrSampleCode","thumb-down"],["필요한 정보/샘플이 없음","missingTheInformationSamplesINeed","thumb-down"],["번역 문제","translationIssue","thumb-down"],["기타","otherDown","thumb-down"]],["최종 업데이트: 2025-03-06(UTC)"],[[["AlloyDB can be used as a vector database by utilizing the `vector` extension, which includes `pgvector` functions and operators for storing embeddings."],["The `vector` extension, version `0.5.0.google-1` or later, is required to store embeddings as `vector` values, with this specific version having been optimized by Google for AlloyDB."],["To store embeddings, add a `vector[]` column to an existing AlloyDB table using an `ALTER TABLE` command, specifying the number of dimensions the model supports."],["You can copy vectors into the vector column from a CSV file, using the `COPY` command, after the column has been created."],["Once the embeddings are stored, you can further enhance query performance by creating indexes using the `vector` or `alloydb_scann` extensions."]]],[]]