AlloyDB AI 是 AlloyDB Omni 中包含的一套功能,可让您构建企业生成式 AI 应用。如需详细了解 AlloyDB 的 AI/ML 功能,请参阅构建生成式 AI 应用。
借助具有 AlloyDB AI 的 AlloyDB Omni,您可以查询远程机器学习模型,以使用从机器学习模型生成的在线预测和文本嵌入。具有 AlloyDB AI 的 AlloyDB Omni 还可以处理来自其他内容(例如图片)的向量嵌入,例如,如果您使用 google_ml.predict_row 接口并自行在查询中进行转换。
根据您要在其中安装具有 AlloyDB AI 的 AlloyDB Omni 的位置,选择以下选项之一:
[[["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):2025-04-21。"],[[["AlloyDB Omni with AlloyDB AI enables users to build enterprise generative AI applications and query remote ML models for online predictions and text embeddings."],["Installation of AlloyDB Omni with AlloyDB AI can be done through a single-server Kubernetes GDC air-gapped environment."],["Users can verify the successful installation and use of model prediction by creating the `google_ml_integration` extension and using the `embedding()` function to generate text embeddings."],["The `embedding()` function, demonstrated with the `text-embedding-005` model, returns an output with 768 dimensions, as shown in the verification example."],["Vertex AI model support and stability are subject to Vertex AI's model versioning and lifecycle guidelines."]]],[]]