SELECTjson_array_elements(google_ml.predict_row(model_id=>'gemini-pro',request_body=>'{ "contents": [ { "role": "user", "parts": [ { "text": "For TPCH database schema as mentioned here https://www.tpc.org/TPC_Documents_Current_Versions/pdf/TPC-H_v3.0.1.pdf , generate a SQL query to find all supplier names which are located in the India nation." } ] } ] }'))->'candidates'->0->'content'->'parts'->0->'text';
如需为 Hugging Face 上的已注册 facebook/bart-large-mnli 模型端点生成预测,请运行以下语句:
SELECTgoogle_ml.predict_row(model_id=>'facebook/bart-large-mnli',request_body=>
'{ "inputs": "Hi, I recently bought a device from your company but it is not working as advertised and I would like to get reimbursed!", "parameters": {"candidate_labels": ["refund", "legal", "faq"]} }');
[[["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):2025-09-04。"],[[["\u003cp\u003eModel endpoint management is a preview feature that allows you to experiment with registering AI model endpoints and invoking predictions, subject to Pre-GA Offerings Terms.\u003c/p\u003e\n"],["\u003cp\u003eRegistered model endpoints can be referenced by their model ID to invoke predictions.\u003c/p\u003e\n"],["\u003cp\u003eThe \u003ccode\u003egoogle_ml.predict_row()\u003c/code\u003e SQL function is used to call registered model endpoints for predictions and can be used with any model type.\u003c/p\u003e\n"],["\u003cp\u003eExamples are provided for invoking predictions using registered \u003ccode\u003egemini-pro\u003c/code\u003e and \u003ccode\u003efacebook/bart-large-mnli\u003c/code\u003e model endpoints.\u003c/p\u003e\n"]]],[],null,["# Invoke predictions with model endpoint management\n\nSelect a documentation version: 15.5.4keyboard_arrow_down\n\n- [15.5.5](/alloydb/omni/15.5.5/docs/model-endpoint-predictions)\n- [15.5.4](/alloydb/omni/15.5.4/docs/model-endpoint-predictions)\n- [15.5.2](/alloydb/omni/15.5.2/docs/model-endpoint-predictions)\n\n\u003cbr /\u003e\n\n|\n| **Preview\n| --- Model endpoint management**\n|\n|\n| This feature is subject to the \"Pre-GA Offerings Terms\" in the General Service Terms section\n| of the [Service Specific Terms](/terms/service-terms#1).\n|\n| Pre-GA features are available \"as is\" and might have limited support.\n|\n| For more information, see the\n| [launch stage descriptions](/products#product-launch-stages).\n\nThis page describes a preview that lets you experiment with registering an AI model endpoint\nand invoking predictions with Model endpoint management. For using AI models in\nproduction environments, see [Build generative AI applications using\nAlloyDB AI](/alloydb/docs/ai).\n\nAfter the model endpoints are added and registered in the Model endpoint management, you can\nreference them using the model ID to invoke predictions.\n\nBefore you begin\n----------------\n\nMake sure that you have registered your model endpoint with Model endpoint management. For more information, see [Register a model endpoint with model endpoint management](/alloydb/omni/15.5.4/docs/model-endpoint-register-model)\n\nInvoke predictions for generic models\n-------------------------------------\n\nUse the `google_ml.predict_row()` SQL function to call a registered generic model endpoint to invoke\npredictions. You can use `google_ml.predict_row()` function with any model type. \n\n SELECT\n google_ml.predict_row(\n model_id =\u003e '\u003cvar translate=\"no\"\u003eMODEL_ID\u003c/var\u003e',\n request_body =\u003e '\u003cvar translate=\"no\"\u003eREQUEST_BODY\u003c/var\u003e');\n\nReplace the following:\n\n- \u003cvar translate=\"no\"\u003eMODEL_ID\u003c/var\u003e: the model ID you defined when registering the model endpoint.\n- \u003cvar translate=\"no\"\u003eREQUEST_BODY\u003c/var\u003e: the parameters to the prediction function, in JSON format.\n\nExamples\n--------\n\nSome examples for invoking predictions using registered model endpoints are listed in this section.\n\nTo generate predictions for a registered `gemini-pro` model endpoint, run the following statement: \n\n SELECT\n json_array_elements(\n google_ml.predict_row(\n model_id =\u003e 'gemini-pro',\n request_body =\u003e '{\n \"contents\": [\n {\n \"role\": \"user\",\n \"parts\": [\n {\n \"text\": \"For TPCH database schema as mentioned here https://www.tpc.org/TPC_Documents_Current_Versions/pdf/TPC-H_v3.0.1.pdf , generate a SQL query to find all supplier names which are located in the India nation.\"\n }\n ]\n }\n ]\n }'))-\u003e 'candidates' -\u003e 0 -\u003e 'content' -\u003e 'parts' -\u003e 0 -\u003e 'text';\n\nTo generate predictions for a registered `facebook/bart-large-mnli` model endpoint on Hugging Face, run the following statement: \n\n SELECT\n google_ml.predict_row(\n model_id =\u003e 'facebook/bart-large-mnli',\n request_body =\u003e\n '{\n \"inputs\": \"Hi, I recently bought a device from your company but it is not working as advertised and I would like to get reimbursed!\",\n \"parameters\": {\"candidate_labels\": [\"refund\", \"legal\", \"faq\"]}\n }'\n );"]]