Introduction¶
Neuralk AI develops powerful Tabular Foundation Models (TFMs) purpose-built for industry applications, delivering state-of-the-art accuracy on real-world ML tasks across commerce, finance, healthcare and beyond.
Seldon¶
Seldon is our foundation model designed for tabular prediction tasks (classification and regression). It uses In-Context Learning to make predictions based on examples you provide, without requiring traditional model training or hyperparameter tuning.
No hyperparameter tuning needed. Strong baseline performance out of the box.
Explore new datasets quickly. Adapt to changing data without retraining.
Familiar fit/predict interface. Works with pipelines and cross-validation.
Cloud API or on-premise. Same SDK, same interface.
Using the Model¶
Use Seldon with your API key. The task type (classification or regression) is automatically detected from the target variable.
Pass discrete labels to fit():
from neuralk import Seldon
model = Seldon(api_key="nk_live_xxx")
model.fit(X_train, y_train) # y_train has discrete labels
predictions = model.predict(X_test)
Pass continuous values to fit():
from neuralk import Seldon
model = Seldon(api_key="nk_live_xxx")
model.fit(X_train, y_train) # y_train has continuous values
predictions = model.predict(X_test)
Use the host parameter instead of an API key:
from neuralk import Seldon
model = Seldon(host="http://your-server:8000")
→ Learn more about On-Premise Deployment
Getting Started¶
Install the SDK:
pip install neuralkGet your API key: Run
neuralk loginMake predictions: See Quickstart
Learn More¶
Quickstart - First prediction in 5 minutes
Advanced Configuration - Data preparation and pipeline examples
Built-in selection of the most informative context - Advanced context selection strategies
Frequently Asked Questions - Common questions about Seldon and In-Context Learning