En esta página, se muestra cómo instalar AlloyDB Omni y cómo integrar AlloyDB AI en él.
AlloyDB AI
es un paquete de funciones incluidas en AlloyDB Omni que te permiten
crear aplicaciones de IA generativa empresarial. Para obtener más información sobre la funcionalidad de AA de AlloyDB, consulta Compila aplicaciones de IA generativa.
AlloyDB Omni con AlloyDB AI te permite consultar modelos de AA remotos para trabajar con predicciones en línea y embeddings de texto generados a partir de modelos de AA. AlloyDB Omni con AlloyDB AI también puede procesar embeddings de vectores de otro contenido, como una imagen, por ejemplo, si usas la interfaz de google_ml.predict_row y realizas la traducción por tu cuenta en la búsqueda.
Según dónde quieras instalar AlloyDB Omni con AlloyDB AI, selecciona una de las siguientes opciones:
Verifica la instalación de AlloyDB Omni con AlloyDB AI
Para verificar que la instalación se realizó correctamente y que se usa la predicción del modelo, ingresa lo siguiente:
En la consulta anterior, la llamada a embedding() genera incorporaciones para el texto de entrada AlloyDB AI.
array_dims devuelve las dimensiones del array que devuelve embedding().
Dado que el modelo textembedding-gecko registrado previamente devuelve un resultado con 768 dimensiones, el resultado es [768].
[[["Fácil de comprender","easyToUnderstand","thumb-up"],["Resolvió mi problema","solvedMyProblem","thumb-up"],["Otro","otherUp","thumb-up"]],[["Difícil de entender","hardToUnderstand","thumb-down"],["Información o código de muestra incorrectos","incorrectInformationOrSampleCode","thumb-down"],["Faltan la información o los ejemplos que necesito","missingTheInformationSamplesINeed","thumb-down"],["Problema de traducción","translationIssue","thumb-down"],["Otro","otherDown","thumb-down"]],["Última actualización: 2025-09-04 (UTC)"],[[["\u003cp\u003eAlloyDB Omni, including AlloyDB AI, allows users to build enterprise generative AI applications by querying remote machine learning (ML) models for online predictions and text embeddings.\u003c/p\u003e\n"],["\u003cp\u003eUsers can install AlloyDB Omni with AlloyDB AI on single-server Kubernetes GDC air-gapped environments, and must have an existing agreement with Google governing Google Cloud offerings.\u003c/p\u003e\n"],["\u003cp\u003eSuccessful installation can be verified by creating the \u003ccode\u003egoogle_ml_integration\u003c/code\u003e extension and checking the output of the \u003ccode\u003eembedding()\u003c/code\u003e function, which should return dimensions of 768 when using the pre-registered \u003ccode\u003etextembedding-gecko\u003c/code\u003e model.\u003c/p\u003e\n"],["\u003cp\u003eAlloyDB Omni with AlloyDB AI can also process vector embeddings from various content like images using the \u003ccode\u003egoogle_ml.predict_row\u003c/code\u003e interface.\u003c/p\u003e\n"]]],[],null,["# Install AlloyDB Omni with AlloyDB AI\n\nSelect a documentation version: 15.5.5keyboard_arrow_down\n\n- [Current (16.8.0)](/alloydb/omni/current/docs/install-with-alloydb-ai)\n- [16.8.0](/alloydb/omni/16.8.0/docs/install-with-alloydb-ai)\n- [16.3.0](/alloydb/omni/16.3.0/docs/install-with-alloydb-ai)\n- [15.12.0](/alloydb/omni/15.12.0/docs/install-with-alloydb-ai)\n- [15.7.1](/alloydb/omni/15.7.1/docs/install-with-alloydb-ai)\n- [15.7.0](/alloydb/omni/15.7.0/docs/install-with-alloydb-ai)\n- [15.5.5](/alloydb/omni/15.5.5/docs/install-with-alloydb-ai)\n- [15.5.4](/alloydb/omni/15.5.4/docs/install-with-alloydb-ai)\n- [15.5.2](/alloydb/omni/15.5.2/docs/install-with-alloydb-ai)\n\n\u003cbr /\u003e\n\n\n| **Note:** Your use of AlloyDB Omni is subject to the agreement between you and Google that governs Google Cloud offerings. If you do not have a Google Cloud account, or have not otherwise entered into an agreement with Google that governs Google Cloud offerings, please do not proceed or download this software until you have done so. To create a Google Cloud account, see [the Google Cloud homepage](/docs/get-started).\n\n\u003cbr /\u003e\n\nThis page shows you how to install AlloyDB Omni and integrate\nAlloyDB AI in it.\n\n[AlloyDB AI](https://cloud.google.com/alloydb/ai)\nis a suite of features included with AlloyDB Omni that let you\nbuild enterprise generative AI applications. For more information about the ML functionality of AlloyDB, see\n[Build generative AI applications](/alloydb/docs/vertex-ai).\n\nAlloyDB Omni with AlloyDB AI lets you query remote ML models to work with online predictions and text embeddings generated from ML models. AlloyDB Omni with AlloyDB AI can also process vector embeddings from other content such as an image, for example, if you use the `google_ml.predict_row` interface and do the translation yourself in the query.\n\nBased on where you want to install AlloyDB Omni with AlloyDB AI, select one of the following options: \nSingle-server Kubernetes GDC air-gapped\n\nVerify AlloyDB Omni with AlloyDB AI installation\n------------------------------------------------\n\nTo verify your installation is successful and uses model prediction, enter the following: \n\n CREATE EXTENSION google_ml_integration CASCADE;\n\n SELECT array_dims(embedding( 'textembedding-gecko@001', 'AlloyDB AI')::real[]);\n array_dims\n\nThe output looks similar to the following: \n\n [1:768]\n (1 row)\n\nIn the previous query, the `embedding()` call generates embeddings for the input text `AlloyDB AI`.\n`array_dims` returns the dimensions of the array returned by `embedding()`.\nSince the pre-registered `textembedding-gecko` model returns an output with 768 dimensions, the output is `[768]`.\n\nWhat's next\n-----------\n\n- [Run and connect to AlloyDB Omni](/alloydb/omni/15.5.5/docs/run-connect)\n- [Manage AlloyDB Omni](/alloydb/omni/15.5.5/docs/manage)\n- [Build generative AI applications using AlloyDB AI](/alloydb/omni/15.5.5/docs/overview-ai)\n- [Register and call remote AI models](/alloydb/omni/15.5.5/docs/model-endpoint-register-model)"]]