Serving CatBoost models

Out of the box, mlserver supports the deployment and serving of catboost models. By default, it will assume that these models have been serialised using the save_model() method.

In this example, we will cover how we can train and serialise a simple model, to then serve it using mlserver.

Training

To test the CatBoost Server, first we need to generate a simple CatBoost model using Python.

import numpy as np
from catboost import CatBoostClassifier

train_data = np.random.randint(0, 100, size=(100, 10))
train_labels = np.random.randint(0, 2, size=(100))

model = CatBoostClassifier(iterations=2,
                           depth=2,
                           learning_rate=1,
                           loss_function='Logloss',
                           verbose=True)
model.fit(train_data, train_labels)
model.save_model('model.cbm')

Our model will be persisted as a file named model.cbm.

Serving

Now that we have trained and saved our model, the next step will be to serve it using mlserver. For that, we will need to create 2 configuration files:

  • settings.json: holds the configuration of our server (e.g. ports, log level, etc.).

  • model-settings.json: holds the configuration of our model (e.g. input type, runtime to use, etc.).

settings.json

%%writefile settings.json
{
    "debug": "true"
}

model-settings.json

%%writefile model-settings.json
{
    "name": "catboost",
    "implementation": "mlserver_catboost.CatboostModel",
    "parameters": {
        "uri": "./model.cbm",
        "version": "v0.1.0"
    }
}

Start serving our model

Now that we have our config in-place, we can start the server by running mlserver start .. This needs to either be ran from the same directory where our config files are or pointing to the folder where they are.

mlserver start .

Since this command will start the server and block the terminal, waiting for requests, this will need to be ran in the background on a separate terminal.

Send test inference request

We now have our model being served by mlserver. To make sure that everything is working as expected, let’s send a request from our test set.

For that, we can use the Python types that mlserver provides out of box, or we can build our request manually.

import requests
import numpy as np

test_data = np.random.randint(0, 100, size=(1, 10))

x_0 = test_data[0:1]
inference_request = {
    "inputs": [
        {
            "name": "predict-prob",
            "shape": x_0.shape,
            "datatype": "FP32",
            "data": x_0.tolist()
        }
    ]
}

endpoint = "http://localhost:8080/v2/models/catboost/versions/v0.1.0/infer"
response = requests.post(endpoint, json=inference_request)

print(response.json())