Export AutoML tabular models

This page describes how to use Vertex AI to export yourAutoML tabular model to Cloud Storage, download the model toan on-premises server or a server hosted by another cloud provider, and thenuse Docker to make the model available for predictions.

For information about exporting image and video Edge models, seeExport AutoML Edge models.

After exporting your tabular model, if you want to import it back intoVertex AI, seeImport models to Vertex AI.

Limitations

Exporting AutoML tabular models has the following limitations:

  • You can export AutoML tabular classification and regressionmodels only. Exporting AutoML tabular forecasting models isn'tsupported.

  • Vertex Explainable AI isn't available using exported tabular models. If you need touse Vertex Explainable AI, you must serve predictions from a model hosted byVertex AI.

  • The exported tabular model can run only on x86 architecture CPUs that supportAdvanced Vector Extensions (AVX) instruction sets.

Export process

The steps for exporting your model are:

  1. Set up your environment.
  2. Export the model.
  3. Pull and run the model server.
  4. Request predictions.

Before you begin

Before you can complete this task, you must have completed the following tasks:

Export the model

Console

  1. In the Google Cloud console, in the Vertex AI section, go totheModels page.

    Go to the Models page

  2. Click the tabular model you want to export to open its details page.

  3. ClickExport in the button bar to export your model.

  4. Select or create a Cloud Storage folder in the desiredlocation.

    The bucket must meet thebucket requirements.

    You cannot export a model to a top-level bucket. You must use at leastone level of folder.

    For best results, create a new, empty folder. You will copy the entirecontents of the folder in a later step.

  5. ClickExport.

    You will download the exported model to your server in the next section.

REST

You use themodels.export method to export a model toCloud Storage.

Before using any of the request data, make the following replacements:

  • LOCATION: Your region.
  • PROJECT: Yourproject ID.
  • MODEL_ID: the ID of the model you want to export.
  • GCS_DESTINATION : your destination folder in Cloud Storage. For example,gs://export-bucket/exports.

    You cannot export a model to a top-level bucket. You must use at least one level of folder.

    The folder must conform to thebucket requirements.

    For best results, create a new folder. You will copy the entire contents of the folder in a later step.

HTTP method and URL:

POST https://LOCATION-aiplatform.googleapis.com/v1/projects/PROJECT/locations/LOCATION/models/MODEL_ID:export

Request JSON body:

{  "outputConfig": {    "exportFormatId": "tf-saved-model",    "artifactDestination": {      "outputUriPrefix": "GCS_DESTINATION"    }  }}

To send your request, choose one of these options:

curl

Save the request body in a file namedrequest.json, and execute the following command:

curl -X POST \
     -H "Authorization: Bearer $(gcloud auth print-access-token)" \
     -H "Content-Type: application/json; charset=utf-8" \
     -d @request.json \
     "https://LOCATION-aiplatform.googleapis.com/v1/projects/PROJECT/locations/LOCATION/models/MODEL_ID:export"

PowerShell

Save the request body in a file namedrequest.json, and execute the following command:

$cred = gcloud auth print-access-token
$headers = @{ "Authorization" = "Bearer $cred" }

Invoke-WebRequest `
    -Method POST `
    -Headers $headers `
    -ContentType: "application/json; charset=utf-8" `
    -InFile request.json `
    -Uri "https://LOCATION-aiplatform.googleapis.com/v1/projects/PROJECT/locations/LOCATION/models/MODEL_ID:export" | Select-Object -Expand Content

You should receive a JSON response similar to the following:

{  "name": "projects/PROJECT_NUMBER/locations/LOCATION/models/MODEL_ID/operations/OPERATION_ID",  "metadata": {    "@type": "type.googleapis.com/google.cloud.aiplatform.v1.ExportModelOperationMetadata",    "genericMetadata": {      "createTime": "2020-10-12T20:53:40.130785Z",      "updateTime": "2020-10-12T20:53:40.130785Z"    },    "outputInfo": {      "artifactOutputUri": "gs://OUTPUT_BUCKET/model-MODEL_ID/EXPORT_FORMAT/YYYY-MM-DDThh:mm:ss.sssZ"    }  }}

Java

Before trying this sample, follow theJava setup instructions in theVertex AI quickstart using client libraries. For more information, see theVertex AIJava API reference documentation.

To authenticate to Vertex AI, set up Application Default Credentials. For more information, seeSet up authentication for a local development environment.

importcom.google.api.gax.longrunning.OperationFuture;importcom.google.cloud.aiplatform.v1.ExportModelOperationMetadata;importcom.google.cloud.aiplatform.v1.ExportModelRequest;importcom.google.cloud.aiplatform.v1.ExportModelResponse;importcom.google.cloud.aiplatform.v1.GcsDestination;importcom.google.cloud.aiplatform.v1.ModelName;importcom.google.cloud.aiplatform.v1.ModelServiceClient;importcom.google.cloud.aiplatform.v1.ModelServiceSettings;importjava.io.IOException;importjava.util.concurrent.ExecutionException;importjava.util.concurrent.TimeUnit;importjava.util.concurrent.TimeoutException;publicclassExportModelTabularClassificationSample{publicstaticvoidmain(String[]args)throwsInterruptedException,ExecutionException,TimeoutException,IOException{// TODO(developer): Replace these variables before running the sample.StringgcsDestinationOutputUriPrefix="gs://your-gcs-bucket/destination_path";Stringproject="YOUR_PROJECT_ID";StringmodelId="YOUR_MODEL_ID";exportModelTableClassification(gcsDestinationOutputUriPrefix,project,modelId);}staticvoidexportModelTableClassification(StringgcsDestinationOutputUriPrefix,Stringproject,StringmodelId)throwsIOException,ExecutionException,InterruptedException,TimeoutException{ModelServiceSettingsmodelServiceSettings=ModelServiceSettings.newBuilder().setEndpoint("us-central1-aiplatform.googleapis.com:443").build();// Initialize client that will be used to send requests. This client only needs to be created// once, and can be reused for multiple requests. After completing all of your requests, call// the "close" method on the client to safely clean up any remaining background resources.try(ModelServiceClientmodelServiceClient=ModelServiceClient.create(modelServiceSettings)){Stringlocation="us-central1";ModelNamemodelName=ModelName.of(project,location,modelId);GcsDestination.BuildergcsDestination=GcsDestination.newBuilder();gcsDestination.setOutputUriPrefix(gcsDestinationOutputUriPrefix);ExportModelRequest.OutputConfigoutputConfig=ExportModelRequest.OutputConfig.newBuilder().setExportFormatId("tf-saved-model").setArtifactDestination(gcsDestination).build();OperationFuture<ExportModelResponse,ExportModelOperationMetadata>exportModelResponseFuture=modelServiceClient.exportModelAsync(modelName,outputConfig);System.out.format("Operation name: %s\n",exportModelResponseFuture.getInitialFuture().get().getName());System.out.println("Waiting for operation to finish...");ExportModelResponseexportModelResponse=exportModelResponseFuture.get(300,TimeUnit.SECONDS);System.out.format("Export Model Tabular Classification Response: %s",exportModelResponse.toString());}}}

Node.js

Before trying this sample, follow theNode.js setup instructions in theVertex AI quickstart using client libraries. For more information, see theVertex AINode.js API reference documentation.

To authenticate to Vertex AI, set up Application Default Credentials. For more information, seeSet up authentication for a local development environment.

/** * TODO(developer): Uncomment these variables before running the sample.\ * (Not necessary if passing values as arguments) */// const gcsDestinationOutputUriPrefix ='YOUR_GCS_DESTINATION_\// OUTPUT_URI_PREFIX'; eg. "gs://<your-gcs-bucket>/destination_path"// const modelId = 'YOUR_MODEL_ID';// const project = 'YOUR_PROJECT_ID';// const location = 'YOUR_PROJECT_LOCATION';// Imports the Google Cloud Model Service Client libraryconst{ModelServiceClient}=require('@google-cloud/aiplatform');// Specifies the location of the api endpointconstclientOptions={apiEndpoint:'us-central1-aiplatform.googleapis.com',};// Instantiates a clientconstmodelServiceClient=newModelServiceClient(clientOptions);asyncfunctionexportModelTabularClassification(){// Configure the name resourcesconstname=`projects/${project}/locations/${location}/models/${modelId}`;// Configure the outputConfig resourcesconstoutputConfig={exportFormatId:'tf-saved-model',artifactDestination:{outputUriPrefix:gcsDestinationOutputUriPrefix,},};constrequest={name,outputConfig,};// Export Model requestconst[response]=awaitmodelServiceClient.exportModel(request);console.log(`Long running operation :${response.name}`);// Wait for operation to completeawaitresponse.promise();console.log(`Export model response :${JSON.stringify(response.result)}`);}exportModelTabularClassification();

Python

To learn how to install or update the Vertex AI SDK for Python, seeInstall the Vertex AI SDK for Python. For more information, see thePython API reference documentation.

fromgoogle.cloudimportaiplatform_v1beta1defexport_model_tabular_classification_sample(project:str,model_id:str,gcs_destination_output_uri_prefix:str,location:str="us-central1",api_endpoint:str="us-central1-aiplatform.googleapis.com",timeout:int=300,):# The AI Platform services require regional API endpoints.client_options={"api_endpoint":api_endpoint}# Initialize client that will be used to create and send requests.# This client only needs to be created once, and can be reused for multiple requests.client=aiplatform_v1beta1.ModelServiceClient(client_options=client_options)gcs_destination={"output_uri_prefix":gcs_destination_output_uri_prefix}output_config={"artifact_destination":gcs_destination,"export_format_id":"tf-saved-model",}name=client.model_path(project=project,location=location,model=model_id)response=client.export_model(name=name,output_config=output_config)print("Long running operation:",response.operation.name)print("output_info:",response.metadata.output_info)export_model_response=response.result(timeout=timeout)print("export_model_response:",export_model_response)

Get the status of an export operation

Some requests start long-running operations that require time to complete. Theserequests return an operation name, which you can use to view the operation'sstatus or cancel the operation. Vertex AI provides helper methodsto make calls against long-running operations. For more information, seeWorking with long-runningoperations.

Pull and run the model server

In this task, you will download your exported model from Cloud Storageand start the Docker container, so your model is ready to receive predictionrequests.

To pull and run the model server:

  1. On the machine where you will run the model, change to the directory whereyou want to save the exported model.

  2. Download the exported model:

    gcloudstoragecp<var>gcs-destination</var>.--recursive

    Wheregcs-destination is the path to the location of the exportedmodel in Cloud Storage.

    The model is copied to your current directory, under the following path:

    ./model-<model-id>/tf-saved-model/<export-timestamp>

    The path may contain eithertf-saved-model orcustom-trained.

  3. Rename the directory so the timestamp is removed.

    mvmodel-<model-id>/tf-saved-model/<export-timestamp>model-<model-id>/tf-saved-model/<new-dir-name>

    The timestamp makes the directory invalid for Docker.

  4. Pull the model server Docker image.

    sudo docker pullMODEL_SERVER_IMAGE

    The model server image to pull is located in theenvironment.json file inexported model directory. It should have the following path:

    ./model-<model-id>/tf-saved-model/<new-dir-name>/environment.json

    If no environment.json file is present, use:

    MULTI_REGION-docker.pkg.dev/vertex-ai/automl-tabular/prediction-server-v1

    ReplaceMULTI_REGION withus,europe, orasia to select which Dockerrepository you want to pull the Docker image from. Each repository provides thesame Docker image, but choosing theArtifact Registrymulti-region closest tothe machine where you are running Docker might reduce latency.

  5. Start the Docker container, using the directory name you just created:

    dockerrun-v`pwd`/model-<model-id>/tf-saved-model/<new-dir-name>:/models/default-p8080:8080-itMODEL_SERVER_IMAGE

You can stop the model server at any time by usingCtrl-C.

Update the model server docker container

Because you download the model server Docker container when you export themodel, you must explicitly update the model server to getupdates and bug fixes. You should update the model server periodically,using the following command:

dockerpullMODEL_SERVER_IMAGE

Make sure the Docker image URI matches the URI of the Docker image thatyou pulled previously.

Get predictions from the exported model

The model server in the Vertex AI image container handlesprediction requests and returns prediction results.

Batch prediction is not available for exported models.

Prediction data format

You provide the data (payload field) for your prediction request the followingJSON format:

{ "instances": [ { "column_name_1": value, "column_name_2": value, … } , … ] }
Note: Exported Vertex AI models do not validate the data formatof prediction requests. This means that an otherwise well-formed predictionrequest with missing columns, errors in the column names, or even a request fora completely different model returns a (flawed or potentially meaningless)prediction. Make sure your prediction requests to exported models are correct.

The following example shows a request with three columns: a categorical column,a numeric array, and a struct. The request includes two rows.

{  "instances": [    {      "categorical_col": "mouse",      "num_array_col": [        1,        2,        3      ],      "struct_col": {        "foo": "piano",        "bar": "2019-05-17T23:56:09.05Z"      }    },    {      "categorical_col": "dog",      "num_array_col": [        5,        6,        7      ],      "struct_col": {        "foo": "guitar",        "bar": "2019-06-17T23:56:09.05Z"      }    }  ]}

Make the prediction request

  1. Put your request data into a text file, for example,tmp/request.json.

    The number of rows of data in the prediction request, called themini-batchsize, affects the prediction latency and throughput. The larger the mini-batch size, the higher the latency and throughput. For reduced latency, use asmaller mini-batch size. For increased throughput, increase the mini-batchsize. The most commonly used mini-batch sizes are 1, 32, 64, 128, 256, 512,and 1024.

  2. Request the prediction:

    curl -X POST --data @/tmp/request.json http://localhost:8080/predict

Prediction results format

The format of your results depends on your model objective.

Classification model results

Prediction results for classification models (binary and multi-class) returna probability score for each potential value of the target column. You mustdetermine how you want to use the scores. For example, to get a binaryclassification from the provided scores, you would identify a threshold value.If there are two classes, "A" and "B", you should classify the example as "A"if the score for "A" is greater than the chosen threshold, and "B" otherwise.For imbalanced datasets, the threshold might approach 100% or 0%.

The results payload for a classification model look similar to this example:

{  "predictions": [    {      "scores": [        0.539999994635582,        0.2599999845027924,        0.2000000208627896      ],      "classes": [        "apple",        "orange",        "grape"      ]    },    {      "scores": [        0.23999999463558197,        0.35999998450279236,        0.40000002086278963      ],      "classes": [        "apple",        "orange",        "grape"      ]    }  ]}

Regression model results

A predicted value is returned for each valid row of the prediction request.Prediction intervals are not returned for exported models.

The results payload for a regression model look similar to this example:

{  "predictions": [    {      "value": -304.3663330078125,      "lower_bound": -56.32196807861328,      "upper_bound": 126.51904296875    },    {      "value": -112.3663330078125,      "lower_bound": 16.32196807861328,      "upper_bound": 255.51904296875    }  ]}

What's next

Except as otherwise noted, the content of this page is licensed under theCreative Commons Attribution 4.0 License, and code samples are licensed under theApache 2.0 License. For details, see theGoogle Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates.

Last updated 2025-12-15 UTC.