global19 / nodejs-automl

Node.js client for Google Cloud AutoML: Train high quality custom machine learning models with minimum effort and machine learning expertise.

Cloud AutoML: Node.js Client

Cloud AutoML API client for Node.js

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

• Cloud AutoML Node.js Client API Reference
• Cloud AutoML Documentation
• github.com/googleapis/nodejs-automl

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 Cloud AutoML 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/automl

Using the client library

const automl = require('@google-cloud/automl');
const fs = require('fs');

// Create client for prediction service.
const client = new automl.PredictionServiceClient();

/**
 * TODO(developer): Uncomment the following line before running the sample.
 */
// const projectId = `The GCLOUD_PROJECT string, e.g. "my-gcloud-project"`;
// const computeRegion = `region-name, e.g. "us-central1"`;
// const modelId = `id of the model, e.g. “ICN723541179344731436”`;
// const filePath = `local text file path of content to be classified, e.g. "./resources/flower.png"`;
// const scoreThreshold = `value between 0.0 and 1.0, e.g. "0.5"`;

// Get the full path of the model.
const modelFullId = client.modelPath(projectId, computeRegion, modelId);

// Read the file content for prediction.
const content = fs.readFileSync(filePath, 'base64');

const params = {};

if (scoreThreshold) {
  params.score_threshold = scoreThreshold;
}

// Set the payload by giving the content and type of the file.
const payload = {};
payload.image = {imageBytes: content};

// params is additional domain-specific parameters.
// currently there is no additional parameters supported.
const [response] = await client.predict({
  name: modelFullId,
  payload: payload,
  params: params,
});
console.log('Prediction results:');
response.payload.forEach(result => {
  console.log(`Predicted class name: ${result.displayName}`);
  console.log(`Predicted class score: ${result.classification.score}`);
});

Samples

Samples are in the samples/ directory. The samples' README.md has instructions for running the samples.

Sample	Source Code	Try it
Batch_predict	source code
Delete_dataset	source code
Delete_model	source code
Deploy_model	source code
Export_dataset	source code
Get_dataset	source code
Get_model	source code
Get_model_evaluation	source code
Get_operation_status	source code
Import_dataset	source code
Language_entity_extraction_create_dataset	source code
Language_entity_extraction_create_model	source code
Language_entity_extraction_predict	source code
Language_sentiment_analysis_create_dataset	source code
Language_sentiment_analysis_create_model	source code
Language_sentiment_analysis_predict	source code
Language_text_classification_create_dataset	source code
Language_text_classification_create_model	source code
Language_text_classification_predict	source code
List_datasets	source code
List_model_evaluations	source code
List_models	source code
List_operation_status	source code
Quickstart	source code
Translate_create_dataset	source code
Translate_create_model	source code
Translate_predict	source code
Undeploy_model	source code
Vision_classification_create_dataset	source code
Vision_classification_create_model	source code
Vision_classification_deploy_model_node_count	source code
Vision_classification_predict	source code
Vision_object_detection_create_dataset	source code
Vision_object_detection_create_model	source code
Vision_object_detection_deploy_model_node_count	source code
Vision_object_detection_predict	source code

The Cloud AutoML 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.

Client libraries targetting some end-of-life versions of Node.js are available, and can be installed via npm dist-tags. The dist-tags follow the naming convention legacy-(version).

Legacy Node.js versions are supported as a best effort:

• Legacy versions will not be tested in continuous integration.
• Some security patches may not be able to be backported.
• Dependencies will not be kept up-to-date, and features will not be backported.

Legacy tags available

• legacy-8: install client libraries from this dist-tag for versions compatible with Node.js 8.

Versioning

This library follows Semantic Versioning.

This library is considered to be General Availability (GA). This means it is 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 GA 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 template in this directory.

License

Apache Version 2.0

See LICENSE