AryaXAI SDK Documentation | Build & Integrate Explainable AI and Alignment Tools

Upon creating a new project, AryaXAI automatically trains a default AutoML model, 'XGBoost_default', for default prediction and explainability. However, users have the option to utilize their own model for explainability through:

1. Uploading own model. (Tensorflow supported for DL models)

For Image projects:

2. Training a model using AryaXAI's built-in modelling techniques, which include:

XGBoost
LGBoost
CatBoost
RandomForest
SGD (Stochastic Gradient Descent)
Logistic Regression
Linear Regression
GaussianNaiveBayes

Users can fine-tune these models and adjust the hyperparameters according to their requirements.

Uploading own Deep Learning model

Before uploading a model, ensure that the corresponding features have already been uploaded through the data upload process.

Select the tag in which your model is trained on. Also, you can define the test data when you are uploading the model

For tabular project:


project.upload_model(
    model_path='',               # e.g., 'model.h5' or 'model.pkl'
    model_name='',                       # e.g., 'Credit Risk Classifier'
    model_data_tags=['', ''],            # e.g., ['training'], ['v1.0', 'baseline']
    model_test_tags=['', ''],            # e.g., ['validation'], ['test', '2025']
    model_type='',                   # e.g., 'tensorflow', 'pytorch', 'sklearn'
    model_architecture='',       # e.g., 'deep_learning', 'random_forest'
    instance_type='',         # e.g., 'small', 'medium', 'gpu-large'
    explainability_method=['', ''],# e.g., ['shap'], ['lime', 'ig']
    feature_list=[
        '', '', '', # Replace with your dataset's feature names
        # ...
        ''
    ]
)

Help on method upload_model in module aryaxai.core.project


help(project.upload_model)

To activate model.:


project.activate_model('DL Model')

For image project:


project.upload_model(model_path='/content/cifar10epoch100 (Copy).h5',
                     model_name = 'cifar2',
                     model_data_tags = ['testing'],
                     model_test_tags = ['testing'],
                     model_type='tensorflow',
                     model_architecture='deep_learning',
                     instance_type='small')

Supported models in Tabular project

Following are the models that you can upload to AryaXAI:


project.upload_model_types()

{'model_architecture': {'machine_learning': ['Xgboost',
   'Lgboost',
   'CatBoost',
   'Random_forest',
   'Linear_Regression',
   'Logistic_Regression',
   'Gaussian_NaiveBayes',
   'SGD'],
  'deep_learning': ['tensorflow', 'pytorch']},
 'prediction_type': ['classification', 'regression']}

‍

To view uploaded model info


project.models()

Delete uploaded file


project.delete_file('file name')

‍

Example H2

Example H3