Delete an ML Model Service

Delete an ML model service by ID or name, with soft/hard delete options

DELETE /v1/services/mlmodelServices/{id}

DELETE /v1/services/mlmodelServices/{id}

Python

from metadata.sdk import configure
from metadata.sdk.entities import MlModelServices

configure(
    host="https://your-company.open-metadata.org/api",
    jwt_token="your-jwt-token"
)

# Soft delete by ID
MlModelServices.delete("ca22d46e-81b9-4e48-85b5-0adc44980da9")

# Hard delete
MlModelServices.delete(
    "ca22d46e-81b9-4e48-85b5-0adc44980da9",
    hard_delete=True
)

# Delete by name
MlModelServices.delete_by_name("mlflow_svc")

# Delete by name with options
MlModelServices.delete_by_name(
    "mlflow_svc",
    hard_delete=True,
    recursive=True
)

# Restore a soft-deleted ML model service
MlModelServices.restore("ca22d46e-81b9-4e48-85b5-0adc44980da9")

Response (Soft Delete)

{
  "id": "ca22d46e-81b9-4e48-85b5-0adc44980da9",
  "name": "mlflow_svc",
  "fullyQualifiedName": "mlflow_svc",
  "serviceType": "Mlflow",
  "version": 0.2,
  "updatedAt": 1769982621618,
  "updatedBy": "admin",
  "connection": {
    "config": {
      "type": "Mlflow",
      "trackingUri": "http://localhost:8088",
      "registryUri": "http://localhost:8088",
      "supportsMetadataExtraction": true
    }
  },
  "owners": [],
  "tags": [],
  "deleted": true,
  "domains": []
}

Delete an ML Model Service

Delete an ML model service by ID or fully qualified name. Supports soft delete (default), hard delete, and restore operations.

Delete by ID

id · string · required

UUID of the ML model service to delete.

recursive · boolean · default: "false"

Recursively delete child entities (ML models).

hardDelete · boolean · default: "false"

Permanently delete the ML model service. If false, the service is soft-deleted and can be restored.

Delete by Name

Use DELETE /v1/services/mlmodelServices/name/{fqn} to delete by fully qualified name.

fqn · string · required

Fully qualified name of the ML model service (e.g., mlflow_svc).

recursive · boolean · default: "false"

Recursively delete child entities.

hardDelete · boolean · default: "false"

Permanently delete the ML model service.

Restore a Soft-Deleted ML Model Service

Use PUT /v1/services/mlmodelServices/restore to restore a soft-deleted ML model service.

id · string · required

UUID of the soft-deleted ML model service to restore.

DELETE /v1/services/mlmodelServices/{id}

Python

from metadata.sdk import configure
from metadata.sdk.entities import MlModelServices

configure(
    host="https://your-company.open-metadata.org/api",
    jwt_token="your-jwt-token"
)

# Soft delete by ID
MlModelServices.delete("ca22d46e-81b9-4e48-85b5-0adc44980da9")

# Hard delete
MlModelServices.delete(
    "ca22d46e-81b9-4e48-85b5-0adc44980da9",
    hard_delete=True
)

# Delete by name
MlModelServices.delete_by_name("mlflow_svc")

# Delete by name with options
MlModelServices.delete_by_name(
    "mlflow_svc",
    hard_delete=True,
    recursive=True
)

# Restore a soft-deleted ML model service
MlModelServices.restore("ca22d46e-81b9-4e48-85b5-0adc44980da9")

Response (Soft Delete)

{
  "id": "ca22d46e-81b9-4e48-85b5-0adc44980da9",
  "name": "mlflow_svc",
  "fullyQualifiedName": "mlflow_svc",
  "serviceType": "Mlflow",
  "version": 0.2,
  "updatedAt": 1769982621618,
  "updatedBy": "admin",
  "connection": {
    "config": {
      "type": "Mlflow",
      "trackingUri": "http://localhost:8088",
      "registryUri": "http://localhost:8088",
      "supportsMetadataExtraction": true
    }
  },
  "owners": [],
  "tags": [],
  "deleted": true,
  "domains": []
}

---

Returns

Soft delete returns the ML model service object with deleted: true. Hard delete returns no content (204). Restore returns the restored ML model service object.

---

Error Handling

Code	Error Type	Description
401	UNAUTHORIZED	Invalid or missing authentication token
403	FORBIDDEN	User lacks permission to delete this ML model service
404	NOT_FOUND	ML model service with given ID or FQN does not exist