RESTful service for hosting machine learning models.
Project description
REST Model Service
RESTful service for hosting machine learning models.
Installation
The package can be installed from pypi:
pip install rest_model_service
To use the service you must first have a working model class that uses the MLModel base class from the ml_base package.
You can then set up a configuration file that points at the model class, the configuration file should look like this:
service_title: REST Model Service
models:
- qualified_name: iris_model
class_path: tests.mocks.IrisModel
create_endpoint: true
The config file should be YAML and be in the current working directory.
The qualified name of your model and the class path to your model class should be placed in the correct place in the configuration file. The create_endpoint option is there for cases when you might want to load a model but not create an endpoint for it.
Creating an OpenAPI Contract
An OpenAPI contract can be generated dynamically for your models as hosted within the REST model service. To create the contract and save it execute this command:
generate_openapi --output_file=example.yaml
The script should be able to find your configuration file, but if you did not place it in the current working directory you can point the script to the right path by setting an environment variable like this:
export REST_CONFIG=examples/rest_config.yaml
generate_openapi --output_file=example.yaml
An example rest_config.yaml file is provided in the examples of the project. It points at a model class in the tests package.
The OpenAPI contract should be in your current working directory.
If you get an error that says something about not being able to find a module, you might need to update your PYTHONPATH environment variable:
export PYTHONPATH=./
The service relies on being able to find the model class in the python environment to load it and instantiate it. If your python interpreter is not able to find the model class, then the script won't be able to create an OpenAPI contract for it.
Running the Service
To start the service in development mode, execute this command:
uvicorn rest_model_service.main:app --reload
The service should be able to find your configuration file, but if you did not place it in the current working directory you can point the service to the right path like this:
export REST_CONFIG='examples/rest_config.yaml'
uvicorn rest_model_service.main:app --reload
Downloading Code and Setting Up for Development
To download the code and set up a development environment use these instructions.
To download the source code execute this command:
git clone https://github.com/schmidtbri/rest-model-service
Then create a virtual environment and activate it:
cd rest-model-service
make venv
# on Macs
source venv/bin/activate
Install the dependencies:
make dependencies
Running the Unit Tests
To run the unit test suite execute these commands:
# first install the test dependencies
make test-dependencies
# run the test suite
make test
# clean up the unit tests
make clean-test
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Hashes for rest_model_service-0.1.0-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 7a972620e4c7e9ad808bd20a35fab4b454dfe4f8b214392554ef038fde57e674 |
|
MD5 | dfb592e0d6ba4ac8cefee00ed579f323 |
|
BLAKE2b-256 | d43da9224744d7631179e4e7214d845ca9ec7c7449c473f69d1b07b4fd07048e |