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.
NICL (Neuralk In-Context Learning)¶
NICL is our foundation model designed for tabular prediction tasks. 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¶
There are 2 different ways to use NICL, through a familiar interface compatible with scikit-learn.
Use NICLClassifier with your API key:
from neuralk import NICLClassifier
clf = NICLClassifier(api_key="nk_live_xxx")
clf.fit(X_train, y_train)
predictions = clf.predict(X_test)
Use NICLClassifier with the host parameter:
from neuralk import NICLClassifier
clf = NICLClassifier(host="http://your-server:8000")
clf.fit(X_train, y_train)
predictions = clf.predict(X_test)
→ 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 NICL and In-Context Learning