This repository contains a basic example of MLOps
This project aims to run a classification application using:
- MLFLow
- Hyperparametrization
- Ray
- FastApi
The application is running locally. How to run it?
-
Check the requirements.txt to install the required libraries to run the app (not all libraries are required).
-
The version of Python is Python 3.10.12
-
Start mlflow ´mlflow server --host 127.0.0.1 --port 8001´
-
In scenario 1 folder, execute 'python3 train_serve_iris.py'
-
uvicorn will be ready to receive requests to predict iris specieis
-
Send a request using curl
curl --location 'http://127.0.0.1:8004/predict' \ --header 'Content-Type: application/json' \ --data '{ "sepal_length": 5.1, "sepal_width": 3.5, "petal_length": 1.4, "petal_width": 0.2 }'
Response will be
{"species":"setosa"}
-
In scenario 2 folder, execute 'python3 ray_hypB_FA.py'
-
Uvicorn will be ready to receive requests to predict patient's diagnosis
-
Open another terminal and execute the curl (from curl.txt)
