[[["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):2025-03-06。"],[[["AlloyDB AI provides machine learning capabilities to AlloyDB for PostgreSQL and AlloyDB Omni, allowing users to apply ML models to their data."],["The `vector` extension, a customized version of `pgvector`, is available for storing embeddings, and supports scalar quantization features as well as `IVFFlat` and `HSNW` indexes."],["AlloyDB includes the `alloydb_scann` extension, which implements a highly efficient nearest-neighbor index using the ScaNN algorithm, and is usable with PostgreSQL 15."],["The `google_ml_integration` extension lets users utilize the `Invoke predictions` to call a model within a SQL transaction, or `Generate embeddings` functions to use an LLM to translate text prompts into numerical vectors."],["AlloyDB Omni integrates with Vertex AI, enabling applications to invoke predictions using models from the Vertex AI Model Garden and generate embeddings using `text-embedding-005` LLM."]]],[]]