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';
[[["์ดํดํ๊ธฐ ์ฌ์","easyToUnderstand","thumb-up"],["๋ฌธ์ ๊ฐ ํด๊ฒฐ๋จ","solvedMyProblem","thumb-up"],["๊ธฐํ","otherUp","thumb-up"]],[["์ดํดํ๊ธฐ ์ด๋ ค์","hardToUnderstand","thumb-down"],["์๋ชป๋ ์ ๋ณด ๋๋ ์ํ ์ฝ๋","incorrectInformationOrSampleCode","thumb-down"],["ํ์ํ ์ ๋ณด/์ํ์ด ์์","missingTheInformationSamplesINeed","thumb-down"],["๋ฒ์ญ ๋ฌธ์ ","translationIssue","thumb-down"],["๊ธฐํ","otherDown","thumb-down"]],["์ต์ข ์ ๋ฐ์ดํธ: 2025-08-13(UTC)"],[],[],null,["| **Preview**\n|\n|\n| This product is\n|\n| subject to the \"Pre-GA Offerings Terms\" in the General Service Terms section of the\n| [Service Specific Terms](/terms/service-terms#1).\n|\n| Pre-GA products 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\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n[MySQL](/sql/docs/mysql/model-endpoint-predictions \"View this page for the MySQL database engine\") \\| PostgreSQL \\| SQL Server\n\n\u003cbr /\u003e\n\nThis page describes model endpoint management. Model endpoint management lets you experiment with registering an AI model endpoint and invoking predictions.\n\nTo use AI models in\nproduction environments, see [Build generative AI applications using\nCloud SQL](/sql/docs/postgres/ai-overview) and [Invoke online predictions from Cloud SQL instances](/sql/docs/postgres/invoke-online-predictions).\n\n\nAfter the model endpoints are added and registered in model endpoint management, you can\nreference them using the model ID to invoke predictions.\n\nBefore you begin\n\nMake sure that you complete the following actions:\n\n- Register your model endpoint with model endpoint management. For more information, see [Register and call remote AI models using model endpoint management](/sql/docs/postgres/model-endpoint-register-model).\n- Create or update your Cloud SQL instance so that the instance can integrate with Vertex AI. For more information, see [Enable database integration with Vertex AI](/sql/docs/postgres/integrate-cloud-sql-with-vertex-ai#enable-database-integration-with-vertex-ai).\n\nInvoke predictions for generic models\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\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';"]]