ML Model Service Versions

List and retrieve historical versions of an ML model service

GET /v1/services/mlmodelServices/{id}/versions

GET /v1/services/mlmodelServices/{id}/versions

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"
)

# List all versions
versions = MlModelServices.get_versions("ca22d46e-81b9-4e48-85b5-0adc44980da9")
for v in versions:
    print(f"Version {v.version}: {v.description}")

# Get a specific version
svc_v1 = MlModelServices.get_specific_version(
    "ca22d46e-81b9-4e48-85b5-0adc44980da9",
    "0.1"
)
print(f"Original description: {svc_v1.description}")

Response (List Versions)

{
  "entityType": "mlmodelService",
  "versions": [
    "{\"id\":\"ca22d46e-81b9-4e48-85b5-0adc44980da9\",\"name\":\"mlflow_svc\",\"fullyQualifiedName\":\"mlflow_svc\",\"version\":0.2,\"description\":\"Updated: Production MLflow tracking server\",\"serviceType\":\"Mlflow\"}",
    "{\"id\":\"ca22d46e-81b9-4e48-85b5-0adc44980da9\",\"name\":\"mlflow_svc\",\"fullyQualifiedName\":\"mlflow_svc\",\"version\":0.1,\"serviceType\":\"Mlflow\"}"
  ]
}

ML Model Service Versions

Every change to an ML model service entity creates a new version. Use these endpoints to view the version history and retrieve specific versions.

List Versions

id · string · required

UUID of the ML model service.

Get Specific Version

Use GET /v1/services/mlmodelServices/{id}/versions/{version} to retrieve a specific version.

id · string · required

UUID of the ML model service.

version · string · required

Version number to retrieve (e.g., 0.2).

GET /v1/services/mlmodelServices/{id}/versions

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"
)

# List all versions
versions = MlModelServices.get_versions("ca22d46e-81b9-4e48-85b5-0adc44980da9")
for v in versions:
    print(f"Version {v.version}: {v.description}")

# Get a specific version
svc_v1 = MlModelServices.get_specific_version(
    "ca22d46e-81b9-4e48-85b5-0adc44980da9",
    "0.1"
)
print(f"Original description: {svc_v1.description}")

Response (List Versions)

{
  "entityType": "mlmodelService",
  "versions": [
    "{\"id\":\"ca22d46e-81b9-4e48-85b5-0adc44980da9\",\"name\":\"mlflow_svc\",\"fullyQualifiedName\":\"mlflow_svc\",\"version\":0.2,\"description\":\"Updated: Production MLflow tracking server\",\"serviceType\":\"Mlflow\"}",
    "{\"id\":\"ca22d46e-81b9-4e48-85b5-0adc44980da9\",\"name\":\"mlflow_svc\",\"fullyQualifiedName\":\"mlflow_svc\",\"version\":0.1,\"serviceType\":\"Mlflow\"}"
  ]
}

---

Returns

List versions returns an object with entityType and a versions array of serialized entity snapshots (newest first).

Get specific version returns the full ML model service object as it existed at that version.

---

Error Handling

Code	Error Type	Description
401	UNAUTHORIZED	Invalid or missing authentication token
404	NOT_FOUND	ML model service or version does not exist