General Forecast

General Forecast is a easy-to-use unified inference and deployment engine for structured data foundation models (SDFMs). It provides low-latency, high-throughput in-context learning predictions for live tabular and time-series data through high-level APIs and a Python SDK.

• Website: https://generalforecast.com
• Docs: https://docs.generalforecast.com/

Quickstart

uv venv --python 3.12
source .venv/bin/activate

uv pip install "generalforecast[sklearn]"

Predict locally in Python with the scikit-learn API:

import generalforecast as gf
from sklearn.datasets import load_breast_cancer
from sklearn.model_selection import train_test_split

X, y = load_breast_cancer(return_X_y=True)
X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=0)

classifier = gf.Classifier(
    "general-forecast/tabicl-v2-classifier",
    allow_downloads=True,
).fit(X_train, y_train)

print("accuracy:", classifier.score(X_test, y_test))
print("probabilities:\n", classifier.predict_proba(X_test[:3]).round(3))

Serve models locally with a prediction package:

# Create a classifier as shown above

# Creates a declarative package directory with gf.yaml, context.arrow, gf.lock
package = classifier.to_package("./breast-cancer-pkg", name="breast-cancer")
print("locked digest:", package.lock.package_digest)

gf serve ./breast-cancer-pkg --port 8000

Contributing

We welcome and value any contributions and collaborations. For more specific questions, please contact hello@generalforecast.com.

License

Licensed under the Apache License 2.0.

If you use General Forecast, please cite our work:

@misc{generalforecast2026,
    title={General Forecast: A unified high-throughput inference engine for structured data foundation models},
    author={Tejas Prabhune and Ayushi Batwara and Joseph E. Gonzalez},
    year={2026},
    publisher={GitHub},
    howpublished={\url{https://github.com/generalforecast/gf}}
}