Stay organized with collections
Save and categorize content based on your preferences.
This document shows how to use AlloyDB Studio to register and call model
endpoints. You can then use the registered model endpoints to invoke predictions
or generate embeddings.
In the Explorer pane, expand google_ml, and then click Models.
Click more_vertView actions next to the pre-registered model, and then click Call model.
The SQL query to generate embeddings using the pre-registered model appears.
Enter your text for which you want to generate embedding, and then click Run.
For more information about other SQL queries using pre-registered embedding models, see Generate embeddings.
Register a model endpoint
You can use the template generated by the AlloyDB Studio to register a model endpoint. After registering the model endpoint, you can then start invoking predictions or generating embeddings.
In the Google Cloud console, open the AlloyDB page.
Click more_vertView actions next to Models, and then click Register model.
Modify required parameters based on the model endpoint provider. For more information about registering a model endpoint, see Register and call remote AI models.
In the Explorer pane, expand google_ml, and then click Models.
Click more_vertView actions next to the pre-registered model, and then click Alter model.
Click Run to save the model endpoint metadata.
You can run the google_ml.alter_model() function in the Editor tab of AlloyDB Studio to modify model metadata of other registered model endpoints. For more information, see Model endpoint management reference.
Delete a pre-registered model endpoint
In the Google Cloud console, open the AlloyDB page.
In the Explorer pane, expand google_ml, and then click Models.
Click more_vertView actions next to the pre-registered model, and then click Delete model.
Click Run to delete the model endpoint.
You can run the google_ml.drop_model() function in the Editor tab of AlloyDB Studio to delete other registered model endpoints. For more information, see Model endpoint management reference.
[[["Easy to understand","easyToUnderstand","thumb-up"],["Solved my problem","solvedMyProblem","thumb-up"],["Other","otherUp","thumb-up"]],[["Hard to understand","hardToUnderstand","thumb-down"],["Incorrect information or sample code","incorrectInformationOrSampleCode","thumb-down"],["Missing the information/samples I need","missingTheInformationSamplesINeed","thumb-down"],["Other","otherDown","thumb-down"]],["Last updated 2025-09-04 UTC."],[[["\u003cp\u003eAlloyDB Studio allows you to register and call model endpoints for generating predictions or embeddings.\u003c/p\u003e\n"],["\u003cp\u003ePre-registered embedding models, like textembedding-gecko, can be accessed and called directly from the \u003cstrong\u003eModels\u003c/strong\u003e section in the \u003cstrong\u003eExplorer\u003c/strong\u003e pane.\u003c/p\u003e\n"],["\u003cp\u003eYou can register custom model endpoints using a template provided by AlloyDB Studio, and then use them for generating predictions or embeddings.\u003c/p\u003e\n"],["\u003cp\u003eAlloyDB Studio enables the alteration of metadata for pre-registered model endpoints through the \u003cstrong\u003eAlter model\u003c/strong\u003e option and the \u003ccode\u003egoogle_ml.alter_model()\u003c/code\u003e function.\u003c/p\u003e\n"],["\u003cp\u003ePre-registered model endpoints can be deleted using the \u003cstrong\u003eDelete model\u003c/strong\u003e option or the \u003ccode\u003egoogle_ml.drop_model()\u003c/code\u003e function within AlloyDB Studio.\u003c/p\u003e\n"]]],[],null,["# Use model endpoint management in AlloyDB Studio\n\nThis document shows how to use AlloyDB Studio to register and call model\nendpoints. You can then use the registered model endpoints to invoke predictions\nor generate embeddings.\n\nFor more information about model endpoint management, see [Model endpoint management overview]().\n\nCall pre-registered embedding model endpoints\n---------------------------------------------\n\nThe supported pre-registered embedding models are listed in the **Explorer pane** of AlloyDB Studio.\n\n1. In the Google Cloud console, open the **AlloyDB** page.\n\n [Go to AlloyDB](https://console.cloud.google.com/alloydb)\n2. Select a cluster from the list.\n\n3. In the navigation menu, click **AlloyDB Studio**.\n\n4. In the **Explorer** pane, expand **google_ml** , and then click **Models**.\n\n5. Click more_vert **View actions** next to the pre-registered model, and then click **Call model**.\n\n The SQL query to generate embeddings using the pre-registered model appears.\n6. Enter your text for which you want to generate embedding, and then click **Run**.\n\nFor more information about other SQL queries using pre-registered embedding models, see [Generate embeddings]().\n\nRegister a model endpoint\n-------------------------\n\nYou can use the template generated by the AlloyDB Studio to register a model endpoint. After registering the model endpoint, you can then start invoking predictions or generating embeddings.\n| **Note:** Only pre-registered embedding models are listed in the **Models** menu of the **Explorer** pane.\n\n1. In the Google Cloud console, open the **AlloyDB** page.\n\n [Go to AlloyDB](https://console.cloud.google.com/alloydb)\n2. Select a cluster from the list.\n\n3. In the navigation menu, click **AlloyDB Studio**.\n\n4. In the **Explorer** pane, expand **google_ml**.\n\n5. Click more_vert **View actions** next to **Models** , and then click **Register model**.\n\n6. Modify required parameters based on the model endpoint provider. For more information about registering a model endpoint, see [Register and call remote AI models]().\n\n7. Click **Run** to register the model endpoint.\n\nFor more information about other SQL queries using registered model endpoints, see [Invoke predictions]() or [Generate embeddings]().\n\nAlter a pre-registered model endpoint\n-------------------------------------\n\nFor pre-registered model endpoints, you can alter the model metadata, if required.\n\n1. In the Google Cloud console, open the **AlloyDB** page.\n\n [Go to AlloyDB](https://console.cloud.google.com/alloydb)\n2. Select a cluster from the list.\n\n3. In the navigation menu, click **AlloyDB Studio**.\n\n4. In the **Explorer** pane, expand **google_ml** , and then click **Models**.\n\n5. Click more_vert **View actions** next to the pre-registered model, and then click **Alter model**.\n\n6. Click **Run** to save the model endpoint metadata.\n\nYou can run the `google_ml.alter_model()` function in the **Editor** tab of AlloyDB Studio to modify model metadata of other registered model endpoints. For more information, see [Model endpoint management reference]().\n\nDelete a pre-registered model endpoint\n--------------------------------------\n\n1. In the Google Cloud console, open the **AlloyDB** page.\n\n [Go to AlloyDB](https://console.cloud.google.com/alloydb)\n2. Select a cluster from the list.\n\n3. In the navigation menu, click **AlloyDB Studio**.\n\n4. In the **Explorer** pane, expand **google_ml** , and then click **Models**.\n\n5. Click more_vert **View actions** next to the pre-registered model, and then click **Delete model**.\n\n6. Click **Run** to delete the model endpoint.\n\nYou can run the `google_ml.drop_model()` function in the **Editor** tab of AlloyDB Studio to delete other registered model endpoints. For more information, see [Model endpoint management reference]().\n\nWhat's next\n-----------\n\n- [Learn more about model endpoint management]()\n- Use [sample templates for registering model endpoints]()"]]