I have served an mlflow model and am sending POST requests in this format:
curl -X POST -H "Content-Type:application/json; format=pandas-split"
--data '{"columns":["alcohol", "chlorides", "citric acid", "density",
"fixed acidity", "free sulfur dioxide", "pH", "residual sugar", "sulphates",
"total sulfur dioxide", "volatile acidity"],"data":[[12.8, 0.029, 0.48, 0.98,
6.2, 29, 3.33, 1.2, 0.39, 75, 0.66]]}'
http://127.0.0.1:1234/invocations
It is getting scored. However for my particular project, the input to rest api for scoring will always be multiple records in dataframe/csv format instead of a single record. Can someone point me to how to achieve this ?
To generate json use pandas: