🌍 Join Neuralk-AI's tabular AI ecosystem!

---

💡 A Tabular Foundation Model for Industrial Applications

Neuralk-AI builds Seldon, a foundation model designed specifically for tabular classification on industrial data. The Neuralk SDK gives Python developers a scikit-learn compatible interface to Seldon, so it drops straight into existing ML pipelines.

What Seldon offers:

• Zero hyperparameter tuning — strong baseline performance out of the box
• Scikit-learn compatible — works with pipelines, cross-validation, and the familiar fit / predict interface
• Mixed feature types — handles numerical and categorical data natively
• Flexible deployment — Cloud API or on-premise server
• Multiple model sizes — seldon-flash (low latency), seldon-small (balanced), seldon-large (most accurate)

---

🚀 How to get started?

Install the SDK with pip (Python 3.11+):

pip install neuralk

Authenticate and set your API key:

neuralk login
export NEURALK_API_KEY=nk_live_your_api_key_here

Make your first prediction:

from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score
from neuralk import SeldonClassifier
from neuralk.datasets import two_moons

X, y = two_moons()
X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=42)

clf = SeldonClassifier()
clf.fit(X_train, y_train)
predictions = clf.predict(X_test)

print(f"Accuracy: {accuracy_score(y_test, predictions):.2%}")

---

📚 Learn more