Amplify Framework Adds Predictions Category

The Amplify Framework is an open source project for building cloud-enabled mobile and web applications.

Starting today, the Amplify Framework has added a new category called “Predictions” that makes it easy for developers to add and configure AI/ML based use cases in their web and mobile applications using few lines of code. No previous machine learning experience is required. Developers can accomplish these uses cases with the Amplify CLI and either the Amplify JavaScript library (using a new Predictions category) or the generated iOS and Android SDKs for Amazon AI/ML services.

The Amplify CLI enables developers to easily set up the backend and orchestrate advanced use cases such as on-demand indexing of images to auto-update a collection in Amazon Rekognition for entity recognition. The actual image bytes are not stored by Amazon Rekognition. For example, this enables developers to securely upload an image using an Amplify storage object at run time which triggers an auto-update of the collection. The application can then make inference calls using the predictions library to identify the entities that match the previously uploaded image. In addition, you can setup or import a SageMaker endpoint from the Amplify CLI.

Web developers can use the Amplify JavaScript library with the new Predictions category to add AI/ML uses cases such as text translation, speech to text generation, image recognition, text to speech, and insights from text to their web application. The supported use cases leverage services such as Amazon Rekognition, Amazon Translate, Amazon Polly, Amazon Transcribe, Amazon Comprehend, and Amazon Textract.

Mobile developers can use the new iOS and Android SDK for SageMaker to make inference requests on their custom models hosted on SageMaker via an HTTPS endpoint. The Android SDK also includes support for Amazon Textract that allows developers to extract text and data from scanned documents. These services add to the list of existing AI services supported in iOS and Android SDKs.

For more details on how to use the Predictions category, refer to our blog post. To learn more about Amplify Framework, please visit our documentation.