Metadata-Version: 2.4
Name: aqueduct
Version: 1.12.0
Summary: Builder for performance-efficient prediction.
Home-page: https://github.com/avito-tech/aqueduct
Download-URL: https://github.com/avito-tech/aqueduct/archive/refs/heads/main.zip
Author: Data Science SWAT
Author-email: UnitDataScienceSwat@avito.ru
License: MIT
Keywords: datascience,learning
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Developers
Classifier: Topic :: Scientific/Engineering
Classifier: Topic :: Software Development :: Build Tools
Classifier: Topic :: Software Development :: Libraries :: Python Modules
Classifier: Topic :: Software Development :: Libraries :: Python Modules
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3.8
Classifier: Operating System :: MacOS
Classifier: Operating System :: Microsoft :: Windows
Classifier: Operating System :: POSIX
Classifier: Operating System :: Unix
Classifier: Operating System :: OS Independent
Requires-Python: >=3.8
Description-Content-Type: text/x-rst
Requires-Dist: psutil==5.9.4
Provides-Extra: aiohttp
Requires-Dist: aiohttp; extra == "aiohttp"
Provides-Extra: numpy
Requires-Dist: numpy; extra == "numpy"
Dynamic: author
Dynamic: author-email
Dynamic: classifier
Dynamic: description
Dynamic: description-content-type
Dynamic: download-url
Dynamic: home-page
Dynamic: keywords
Dynamic: license
Dynamic: provides-extra
Dynamic: requires-dist
Dynamic: requires-python
Dynamic: summary

========
Aqueduct
========

Framework to make youre prediction performance-efficient and scalable.

Key Benefits
============

- Increases the throughput of your machine learning-based service
- Uses shared memory for instantaneous transfer of large amounts of data between processes
- All optimizations in one library
- Supports multiple frameworks

Documentation
=============

- `Videos about aqueduct <docs/video.rst>`_
- Getting started
- - `Fundamentals <docs/fundamentals.rst>`_
- - `Example <docs/example.rst>`_
- `Batching <docs/batching.rst>`_
- `Logging <docs/logging.rst>`_
- `Metrics <docs/metrics.rst>`_
- `F.A.Q. <docs/faq.rst>`_
- Additional features
- - `Sentry support <docs/sentry.rst>`_

Examples
========

- `Aiohttp <examples/aiohttp/>`_
- `Flask <examples/flask/>`_

Installation
=============

Install using ``pip``:

.. code-block:: shell

    pip install aqueduct

Moreover, aqueduct has "optional extras"

- ``numpy`` - support types from numpy in shared memory
- ``aiohttp`` - extension for aiohttp support(see more in examples)

.. code-block:: shell

    pip install aqueduct[numpy,aiohttp]


Contact Us
==========

Feel free to ask questions in Telegram: `t.me/avito-ml <https://t.me/avito_ml>`_
