samuelbernardolip/deepaas

A REST API to serve machine learning and deep learning models

DEEPaaS

DEEP as a Service API (DEEPaaS API) is a REST API built on aiohttp that allows to provide easy access to machine learning, deep learning and artificial intelligence models. By using the DEEPaaS API users can easily run a REST API in front of their model, thus accessing its functionality via HTTP calls. DEEPaaS API leverages the OpenAPI specification.

Documentation

The DEEPaaS documentation is hosted on Read the Docs.

Quickstart

The best way to quickly try the DEEPaaS API is through:

make run

This command will install a virtualenv (in the virtualenv directory) with DEEPaaS and all its dependencies and will run the DEEPaaS REST API, listening on 127.0.0.1:5000. If you browse to http://127.0.0.1:5000 you will get the Swagger documentation page (i.e. the Swagger web UI).

Develop mode

If you want to run the code in develop mode (i.e. pip install -e), you can issue the following command before:

make develop

Citing

If you are using this software and want to cite it in any work, please use the following:

Lopez Garcia, A. "DEEPaaS API: a REST API for Machine Learning and Deep Learning models". In: Journal of Open Source Software 4(42) (2019), pp. 1517. ISSN: 2475-9066. DOI: 10.21105/joss.01517

You can also use the following BibTeX entry:

@article{Lopez2019DEEPaaS,
    journal = {Journal of Open Source Software},
    doi = {10.21105/joss.01517},
    issn = {2475-9066},
    number = {42},
    publisher = {The Open Journal},
    title = {DEEPaaS API: a REST API for Machine Learning and Deep Learning models},
    url = {http://dx.doi.org/10.21105/joss.01517},
    volume = {4},
    author = {L{\'o}pez Garc{\'i}a, {\'A}lvaro},
    pages = {1517},
    date = {2019-10-25},
    year = {2019},
    month = {10},
    day = {25},}

Acknowledgements

This software has been developed within the DEEP-Hybrid-DataCloud (Designing and Enabling E-infrastructures for intensive Processing in a Hybrid DataCloud) project that has received funding from the European Union's Horizon 2020 research and innovation programme under grant agreement No 777435.