[[["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 to store embeddings as vector values."],["To use this feature, ensure you install the `vector` extension, version `0.5.0.google-1` or later, optimized for AlloyDB, by running `CREATE EXTENSION IF NOT EXISTS vector;`."],["You can store embeddings in an existing AlloyDB table by adding a `vector[]` column, specifying the number of dimensions supported by the model being used, and copying the vectors into this column from a CSV file or using `AlloyDBVectorStore` for LangChain integration."],["After storing vector data, consider creating indexes using the `vector` or `alloydb_scann` extension for enhanced query performance."],["The AlloyDB ScaNN index is currently in preview and subject to Pre-GA Offerings Terms, with features available \"as is\" and having potentially limited support."]]],[]]