topic Is Model Registry possible in Databricks Free Edition? in Get Started Discussions

Is Model Registry possible in Databricks Free Edition?

xyz999 — Wed, 23 Jul 2025 14:05:55 GMT

Has anyone registered a Model in Databricks Free Edition? It seems not working or not available in Free Edition.

Re: Is Model Registry possible in Databricks Free Edition?

Advika — Thu, 24 Jul 2025 10:44:50 GMT

Yes, this is a supported feature. You can register models in Databricks Free Edition using the MLflow Model Registry.

You can refer to the official documentation here:
https://docs.databricks.com/gcp/en/mlflow#model-registry-with-unity-catalog
https://docs.databricks.com/gcp/en/machine-learning/manage-model-lifecycle/

Re: Is Model Registry possible in Databricks Free Edition?

xyz999 — Fri, 25 Jul 2025 19:48:51 GMT

Hello Advika, I followed the documentation and had the following code/model, I keep getting this error ;
[CONFIG_NOT_AVAILABLE] Configuration spark.mlflow.modelRegistryUri is not available. SQLSTATE: 42K0I
Any help would be greatly appreciated.

MyCode:
# Import necessary libraries
import pandas as pd
from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import accuracy_score
import mlflow
import mlflow.sklearn

# Load the Iris dataset
iris = load_iris()
X = pd.DataFrame(iris.data, columns=iris.feature_names)
y = pd.Series(iris.target)

# Split the dataset
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42)

# Optional: Enable MLflow autologging
mlflow.sklearn.autolog()

# Start MLflow run
with mlflow.start_run() as run:
# Train model
clf = RandomForestClassifier(n_estimators=100, random_state=42)
clf.fit(X_train, y_train)

# Predict and evaluate
predictions = clf.predict(X_test)
acc = accuracy_score(y_test, predictions)
print(f"Accuracy: {acc}")

# Capture run ID
run_id = run.info.run_id
print(f"MLflow Run ID: {run_id}")

# Get model URI
model_uri = f"runs:/{run_id}/model"
model_name = "IrisClassifierModel"

# Register the model
mlflow.register_model(model_uri=model_uri, name=model_name)
print(f"Model registered as '{model_name}'")

# Done
print("Model training, logging, and registration complete.")

Re: Is Model Registry possible in Databricks Free Edition?

xyz999 — Tue, 29 Jul 2025 15:24:28 GMT

Does anyone have any input to this. It looks like S3 issue, model registry does not really work in Free Edition, documentation does not seem correct.

Re: Is Model Registry possible in Databricks Free Edition?

SP_6721 — Tue, 29 Jul 2025 21:20:16 GMT

Hi @xyz999

Have you tried to upgrade to models in Unity Catalog:

import mlflow
mlflow.set_registry_uri("databricks-uc")

Re: Is Model Registry possible in Databricks Free Edition?

xyz999 — Tue, 29 Jul 2025 21:37:01 GMT

Yes, if I use UC it gives this error:
MlflowException: The following failures occurred while uploading one or more artifacts to s3 … 'S3UploadFailedError(\'Failed to upload /local_disk0/repl_tmp_data …