FastAPI Model Server Skeleton
Serving machine learning models production-ready, fast, easy and secure powered by the great FastAPI by Sebastián Ramírez](https://github.com/tiangolo).
This repository contains a skeleton app which can be used to speed-up your next machine learning project. The code is fully tested and provides a preconfigured tox
to quickly expand this sample code.
To experiment and get a feeling on how to use this skeleton, a sample regression model for house price prediction is included in this project. Follow the installation and setup instructions to run the sample model and serve it aso RESTful API.
Requirements
Python 3.6+
Installation
Install the required packages in your local environment (ideally virtualenv, conda, etc.).
pip install -r requirements
Setup
-
Duplicate the
.env.example
file and rename it to.env
-
In the
.env
file configure theAPI_KEY
entry. The key is used for authenticating our API.
A sample API key can be generated using Python REPL:
import uuid
print(str(uuid.uuid4()))
Run It
- Start your app with:
uvicorn fastapi_skeleton.main:app
-
Go to http://localhost:8000/docs.
-
Click
Authorize
and enter the API key as created in the Setup step. -
You can use the sample payload from the
docs/sample_payload.json
file when trying out the house price prediction model using the API.
Run Tests
If you're not using tox
, please install with:
pip install tox
Run your tests with:
tox
This runs tests and coverage for Python 3.6 and Flake8, Autopep8, Bandit.