0

Hi and thank you for looking into this.

(Disclaimer: I have little-to-no technical background and would like to find the least complex solution. Ideally, only "connecting" different out-of-the-box components and no coding.)

HIGH-LEVEL PROBLEM: I have trained a model for text classification using Google AutoML. I want to make this model available on a website, ie I want to enable visitors to enter their text and to receive the model's predicted class.

CONSIDERATIONS SO FAR: AutoML allows us to deploy the model via REST API and I understand that what I want are the API's PUT and GET function (right?). Ideally, I would use some form of plug-in or script to create an input field for the user which accepts the PUT and then delivers the GET.

Are you aware of any services for this? I'm also happy to host the website in an content management system like WordPress.

I'm very open regarding other approaches to solving my problem and highly appreciate any constructive input.

Many thanks!

AutoML Documentation https://cloud.google.com/natural-language/automl/docs/predict

EDIT Jan 10 There is another question related to this and a depo is shared which supposedly provided a solution. I'm not able to access the depo but the question might help you to understand my issue. Is there a way to use Googles AutoML with JavaScript?

EDIT Jan 16 I have learned that in order to provide the input to the model the POST function could be used instead of the PUT.

Philipp H
  • 1
  • 1
  • If I understand well, you don't want that the end user use directly your model, you simply want to plug your backend (Wordpress for example) to this AutoML module to use it. Am I right? And you look for a module/plugin that request easily for you the AutoML deployed model? – guillaume blaquiere Jan 10 '20 at 10:19
  • @guillaumeblaquiere many thanks for getting back and sorry for my late response. You understood correctly. The user should interact with the model which is hosted in the Google Cloud via a webpage. They should be able to provide the input text on this webpage and recieve the model's output. – Philipp H Jan 16 '20 at 12:43
  • And ideally, the technical complexity of the solution should be minimal. – Philipp H Jan 16 '20 at 12:46
  • The minimal integration is hard. You have to call your model with a JWT token. This JWT is generated thanks to a service account hosted by your Backend. By the way, the user call your backend, the backend create the security token and call AutoML model, and you have to process the response. Nothing is magic, there is these minimal things to do. – guillaume blaquiere Jan 16 '20 at 16:12

0 Answers0