Vertex AI: Node.js Client

Google Cloud Vertex AI is an integrated suite of machine learning tools and services for building and using ML models with AutoML or custom code. It offers both novices and experts the best workbench for the entire machine learning development lifecycle.

A comprehensive list of changes in each version may be found in the CHANGELOG.

• Vertex AI Node.js Client API Reference
• Vertex AI Documentation
• github.com/googleapis/nodejs-ai-platform

Read more about the client libraries for Cloud APIs, including the older Google APIs Client Libraries, in Client Libraries Explained.

Table of contents:

• Quickstart
  • Before you begin
  • Installing the client library
  • Using the client library
• Samples
• Versioning
• Contributing
• License

Quickstart

Before you begin

1. Select or create a Cloud Platform project.
2. Enable billing for your project.
3. Enable the Vertex AI API.
4. Set up authentication with a service account so you can access the API from your local workstation.

Installing the client library

npm install @google-cloud/aiplatform

Using the client library

const {DatasetServiceClient} = require('@google-cloud/aiplatform');
const client = new DatasetServiceClient();

// Do something with DatasetServiceClient.
console.info(client);

Samples

Samples are in the samples/ directory. Each sample's README.md has instructions for running its sample.

Sample	Source Code	Try it
Cancel-batch-prediction-job	source code
Cancel-custom-job	source code
Create-batch-prediction-job-text-classification	source code
Create-batch-prediction-job-text-entity-extraction	source code
Create-batch-prediction-job-text-sentiment-analysis	source code
Create-batch-prediction-job-video-action-recognition	source code
Create-batch-prediction-job-video-classification	source code
Create-batch-prediction-job-video-object-tracking	source code
Create-custom-job	source code
Create-dataset-image	source code
Create-dataset-tabular-bigquery	source code
Create-dataset-tabular-gcs	source code
Create-dataset-text	source code
Create-dataset-video	source code
Create-dataset	source code
Create-endpoint	source code
Create-hyperparameter-tuning-job	source code
Create-training-pipeline-image-classification	source code
Create-training-pipeline-image-object-detection	source code
Create-training-pipeline-tabular-classification	source code
Create-training-pipeline-tabular-regression	source code
Create-training-pipeline-text-classification	source code
Create-training-pipeline-text-entity-extraction	source code
Create-training-pipeline-text-sentiment-analysis	source code
Create-training-pipeline-video-action-recognition	source code
Create-training-pipeline-video-classification	source code
Create-training-pipeline-video-object-tracking	source code
Delete-batch-prediction-job	source code
Delete-custom-job	source code
Delete-dataset	source code
Delete-endpoint	source code
Delete-export-model	source code
Delete-model	source code
Deploy-model-custom-trained-model	source code
Deploy-model	source code
Export-model-tabular-classification	source code
Export-model	source code
Get-batch-prediction-job	source code
Get-custom-job	source code
Get-hyperparameter-tuning-job	source code
Get-model-evaluation-image-classification	source code
Get-model-evaluation-image-object-detection	source code
Get-model-evaluation-slice	source code
Get-model-evaluation-tabular-classification	source code
Get-model-evaluation-tabular-regression	source code
Get-model-evaluation-text-classification	source code
Get-model-evaluation-text-entity-extraction	source code
Get-model-evaluation-text-sentiment-analysis	source code
Get-model-evaluation-video-action-recognition	source code
Get-model-evaluation-video-classification	source code
Get-model-evaluation-video-object-tracking	source code
Get-model-evaluation	source code
Get-model	source code
Get-training-pipeline	source code
Import-data-image-classification	source code
Import-data-image-object-detection	source code
Import-data-text-classification-single-label	source code
Import-data-text-entity-extraction	source code
Import-data-text-sentiment-analysis	source code
Import-data-video-action-recognition	source code
Import-data-video-classification	source code
Import-data-video-object-tracking	source code
Import-data	source code
List-endpoints	source code
List-model-evaluation-slices	source code
Predict-custom-trained-model	source code
Predict-image-classification	source code
Predict-image-object-detection	source code
Predict-tabular-classification	source code
Predict-tabular-regression	source code
Predict-text-classification	source code
Predict-text-entity-extraction	source code
Predict-text-sentiment-analysis	source code
Quickstart	source code
Undeploy-model	source code
Upload-model	source code

The Vertex AI Node.js Client API Reference documentation also contains samples.

Supported Node.js Versions

Our client libraries follow the Node.js release schedule. Libraries are compatible with all current active and maintenance versions of Node.js. If you are using an end-of-life version of Node.js, we recommend that you update as soon as possible to an actively supported LTS version.

Google's client libraries support legacy versions of Node.js runtimes on a best-efforts basis with the following warnings:

• Legacy versions are not tested in continuous integration.
• Some security patches and features cannot be backported.
• Dependencies cannot be kept up-to-date.

Client libraries targeting some end-of-life versions of Node.js are available, and can be installed through npm dist-tags. The dist-tags follow the naming convention legacy-(version). For example, npm install @google-cloud/aiplatform@legacy-8 installs client libraries for versions compatible with Node.js 8.

Versioning

This library follows Semantic Versioning.

This library is considered to be stable. The code surface will not change in backwards-incompatible ways unless absolutely necessary (e.g. because of critical security issues) or with an extensive deprecation period. Issues and requests against stable libraries are addressed with the highest priority.

More Information: Google Cloud Platform Launch Stages

Contributing

Contributions welcome! See the Contributing Guide.

Please note that this README.md, the samples/README.md, and a variety of configuration files in this repository (including .nycrc and tsconfig.json) are generated from a central template. To edit one of these files, make an edit to its templates in directory.

License

Apache Version 2.0

See LICENSE