When we are providing our API endpoint to frontend team we need to ensure that we don’t overwhelm them with preprocessing technicalities.We might not always have a Python backend server (eg. Node.js server) so using numpy and keras libraries, for preprocessing, might be a pain.If we are planning to serve multiple models then we will have to create multiple TensorFlow Serving servers and will have to add new URLs to our frontend code. But our Flask server would keep the domain URL same and we only need to add a new route (a function).Providing subscription-based access, exception handling and other tasks can be carried out in the Flask app.

The most common way to deploy a trained model is to save into the binary format of the tool of your choice, wrap it in a microservice (for example a Python Flask application) and use it for inference.

Here’s a table showing the tradeoffs:

flask_sqlalchemy.get_debug_queries()

session_options={"autoflush": False, "autocommit": False, "expire_on_commit": False}

The philosophy behind Flask is that it gives only the components you need to build an app so that you have the flexibility and control. In other words, it’s un-opinionated. Some features it offers are a build-int dev server, Restful request dispatching, Http request handling, and much more.

To use Gunicorn as your web server, it must be included in the requirements.txt file as an app dependency. It does not need to be installed in your virtual environment/host machine.

db.session.remove()

Werkzeug provides a development server: a simple web server that you can run with a single command and almost no configuration. When you do flask run (or werkzeug.serving.run_simple()), this development server is what you are getting

Flask-Sockets, another extension for Flask that makes the use of WebSocket accessible to Flask applications

Hmm. Definitely more http:// and a little more / than there needs to be. It seems like SERVER_NAME should be set to something more like localhost:5000. Let’s try.