https://github.com/ml-libs/mlserve

mlserve turns your python models into RESTful API, serves web page with form generated to match your input data.
https://github.com/ml-libs/mlserve

machine-learning mlserve model-deployment model-serving scikit-learn

Last synced: 22 days ago
JSON representation

mlserve turns your python models into RESTful API, serves web page with form generated to match your input data.

• Host: GitHub
• URL: https://github.com/ml-libs/mlserve
• Owner: ml-libs
• License: apache-2.0
• Created: 2018-07-28T10:48:59.000Z (over 6 years ago)
• Default Branch: master
• Last Pushed: 2022-12-08T18:56:19.000Z (almost 2 years ago)
• Last Synced: 2024-10-11T23:10:34.462Z (25 days ago)
• Topics: machine-learning, mlserve, model-deployment, model-serving, scikit-learn
• Language: Python
• Homepage: https://github.com/ml-libs/mlserve
• Size: 7.6 MB
• Stars: 27
• Watchers: 3
• Forks: 1
• Open Issues: 24
• Metadata Files:
  • Readme: README.rst
  • Changelog: CHANGES.txt
  • Contributing: CONTRIBUTING.rst
  • License: LICENSE

Awesome Lists containing this project

README

        
mlserve

=======

.. image:: https://travis-ci.com/ml-libs/mlserve.svg?branch=master

    :target: https://travis-ci.com/ml-libs/mlserve

.. image:: https://codecov.io/gh/ml-libs/mlserve/branch/master/graph/badge.svg

    :target: https://codecov.io/gh/ml-libs/mlserve

.. image:: https://api.codeclimate.com/v1/badges/1ff813d5cad2d702cbf1/maintainability

   :target: https://codeclimate.com/github/ml-libs/mlserve/maintainability

   :alt: Maintainability

.. image:: https://img.shields.io/pypi/v/mlserve.svg

    :target: https://pypi.python.org/pypi/mlserve

**mlserve** turns your python models into RESTful API, serves web page with

form generated to match your input data.

It may be useful if one wants to demonstrate created predictive model and

quickly integrate into existing application. Additionally UI is provided for

input data (based on training dataframe) and simple dashboard.

Project is not complete but already usable, so no any guaranties on API or UI

backward compatibility.

Online Demo

===========

Several models deployed online using ``heroku.com/free`` free dynos.

Free apps sleep automatically after 30 mins of inactivity so first request

may take some time.

* https://young-ridge-56019.herokuapp.com

Full source code and instructions available here: https://github.com/ml-libs/mlserve-demo

.. image:: https://raw.githubusercontent.com/ml-libs/mlserve/master/docs/_static/list_models.png

    :alt: mlserve models

.. image:: https://raw.githubusercontent.com/ml-libs/mlserve/master/docs/_static/one_model.png

    :alt: one model

Ideas

-----

**mlsserve** is small using following design based on following ideas:

- Simplicity and ease of use is primary objective.

- Application consists of two processes: IO process that runs HTTP server

  and responsible for fetching and sending data, as well as serve UI, other

  process (worker) is doing CPU intensive work related to predictions

  calculations.

Features

========

* Model predictions serving via RESTful API endpoint.

* Model predictions serving via generated UI.

* Web page to simplify models usage.

* Automatic UI generation to match your input data.

* Simple dashboard for monitoring purposes.

Installation

============

Installation process is simple, just::

    $ pip install git+https://github.com/ml-libs/mlserve.git

Example

=======

To deploy model just follow following simple steps:

Save your model into pickle file:

.. code:: python

    with open('boston_gbr.pkl', 'wb') as f:

        pickle.dump(clf, f)

Use `build_schema` function to build UI representation of pandas dataframe,

and save it as json file file:

.. code:: python

    import mlserve

    data_schema = mlserve.build_schema(df)

    with open('boston.json', 'wb') as f:

        json.dump(data_schema, f)

Create configuration file with following format::

    models:

      - name: "boston_regressor"  # url friendly name

        description: "Boston GBR"  # optional model description

        model_path: "boston_gbr.pkl"  # path to your saved model

        data_schema_path: "boston.json"  # path to data representation

        target: "target"  # name of the target column

Serve model::

    $ mlserve -c models.yaml

Thats it, model is available throw REST API, you can test is with curl command::

    $ curl --header "Content-Type: application/json" --request POST

    --data '[{"feature1": 1, "feature2": 2}]'

    http://127.0.0.1:9000/api/v1/models/boston_gradient_boosting_regressor/predict

UI is available via http://127.0.0.1:9000

Supported Frameworks

====================

* Scikit-Learn

* Keras (planning)

* PyTorch (planning)

Requirements

------------

* Python_ 3.6+

* aiohttp_

.. _PEP492: https://www.python.org/dev/peps/pep-0492/

.. _Python: https://www.python.org

.. _aiohttp: https://github.com/aio-libs/aiohttp

.. _asyncio: http://docs.python.org/3.6/library/asyncio.html

.. _uvloop: https://github.com/MagicStack/uvloop