Connect your models (SDK)

You can connect your models into the platform using Heartex SDK. Each model is expected to be publicly available through https. To add your model into the project, go to the project Settings and open the Machine Learning tab. There you need to enter the model URL and its title. Then you can select that model from the dropdown.

Obtaining an SDK

Visit SDK page on Github.

Here is what an example model may look like:

from htx.adapters.sklearn import serve

from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.linear_model import LogisticRegression
from sklearn.pipeline import make_pipeline

if __name__ == "__main__":
  # Creating sklearn-compatible model
  my_model = make_pipeline(TfidfVectorizer(), LogisticRegression())

  # Start serving this model
  serve(my_model)