Skip to main content

A Flask extension for running machine learning code

Project description

Flask-ML

codecov

Flask-ML helps users easily deploy their ML models as a web service. Flask-ML Server, similar to Flask, allows the user to specify web services using the decorator pattern. But Flask-ML allows users to specify the input schema being expected by the ML function and provides helper classes to form response objects for the outputs produced by the ML function. Furthermore, users can specify schemas for their inputs and outputs in order to expose their model via the frontend provided by RescueBox-Desktop.

Installation

To install Flask-ML

pip install flask-ml

Usage examples

Server

Refer simple_server.py, more_server_examples.py, and simple_cli.py

Client

Refer client_example.py

Development

Install both production and dev dependencies

pip install -e ".[dev]"

To re-generate the model classes, run

make generate-models

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

flask_ml-0.2.5.tar.gz (800.0 kB view details)

Uploaded Source

Built Distribution

flask_ml-0.2.5-py3-none-any.whl (20.6 kB view details)

Uploaded Python 3

File details

Details for the file flask_ml-0.2.5.tar.gz.

File metadata

  • Download URL: flask_ml-0.2.5.tar.gz
  • Upload date:
  • Size: 800.0 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/5.1.1 CPython/3.11.4

File hashes

Hashes for flask_ml-0.2.5.tar.gz
Algorithm Hash digest
SHA256 20169854c7bb70fe6f1b21f6065eab91374c98cc51a97a6f57147bd8eb165e78
MD5 4c4073204a9417c725e7b10e77424093
BLAKE2b-256 41d555f38788b44d9eba4f947235757a4d239f201fbb242e9d45eeb079754468

See more details on using hashes here.

File details

Details for the file flask_ml-0.2.5-py3-none-any.whl.

File metadata

  • Download URL: flask_ml-0.2.5-py3-none-any.whl
  • Upload date:
  • Size: 20.6 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/5.1.1 CPython/3.11.4

File hashes

Hashes for flask_ml-0.2.5-py3-none-any.whl
Algorithm Hash digest
SHA256 8dcf090060d49ccc5d9085e6cbc85f47ecc6e589c88fcbe6ad3dd3dd738cc414
MD5 0fb7adb6a714e829c650dd980e0d2c2b
BLAKE2b-256 9fa43f257e5a7c6cf6e045f1e9217297d00f3cecda8974c81668054c16caef82

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page