[[["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):2025-08-22。"],[[["\u003cp\u003eThis page provides instructions on how to generate embeddings by utilizing registered model endpoints.\u003c/p\u003e\n"],["\u003cp\u003eThe \u003ccode\u003egoogle_ml.embedding()\u003c/code\u003e SQL function is used to interact with the registered model endpoint, specifically for text embedding models.\u003c/p\u003e\n"],["\u003cp\u003eTo call the model, you must define the \u003ccode\u003eMODEL_ID\u003c/code\u003e and the \u003ccode\u003eCONTENT\u003c/code\u003e you wish to process in a SQL query.\u003c/p\u003e\n"],["\u003cp\u003eThe page provides examples of generating embeddings for \u003ccode\u003etext-embedding-005\u003c/code\u003e, \u003ccode\u003etext-embedding-ada-002\u003c/code\u003e, \u003ccode\u003etext-embedding-3-small\u003c/code\u003e, and \u003ccode\u003etext-embedding-3-large\u003c/code\u003e model endpoints.\u003c/p\u003e\n"]]],[],null,["# Generate vector embeddings with model endpoint management\n\nSelect a documentation version: Current (16.8.0)keyboard_arrow_down\n\n- [Current (16.8.0)](/alloydb/omni/current/docs/ai/model-endpoint-embeddings)\n- [16.8.0](/alloydb/omni/16.8.0/docs/ai/model-endpoint-embeddings)\n- [16.3.0](/alloydb/omni/16.3.0/docs/ai/model-endpoint-embeddings)\n- [15.12.0](/alloydb/omni/15.12.0/docs/ai/model-endpoint-embeddings)\n- [15.7.1](/alloydb/omni/15.7.1/docs/ai/model-endpoint-embeddings)\n- [15.7.0](/alloydb/omni/15.7.0/docs/ai/model-endpoint-embeddings)\n\n\u003cbr /\u003e"]]