POST /v1/services/mlmodelServices

from metadata.generated.schema.entity.services.connections.metadata.openMetadataConnection import (
    AuthProvider,
    OpenMetadataConnection,
)
from metadata.generated.schema.security.client.openMetadataJWTClientConfig import (
    OpenMetadataJWTClientConfig,
)
from metadata.ingestion.ometa.ometa_api import OpenMetadata
from metadata.generated.schema.api.services.createMlModelService import CreateMlModelServiceRequest

metadata = OpenMetadata(
    OpenMetadataConnection(
        hostPort="https://your-company.getcollate.io/api",
        authProvider=AuthProvider.openmetadata,
        securityConfig=OpenMetadataJWTClientConfig(jwtToken="your-jwt-token"),
    )
)

request = CreateMlModelServiceRequest(
    name="mlflow_svc",
    displayName="MLflow Production",
    serviceType="Mlflow",
    description="Production MLflow tracking server",
    connection={
        "config": {
            "type": "Mlflow",
            "trackingUri": "http://localhost:8088",
            "registryUri": "http://localhost:8088",
            "supportsMetadataExtraction": True
        }
    }
)

service = metadata.create_or_update(request)
print(f"Created: {service.fullyQualifiedName.root}")

import org.openmetadata.schema.api.services.CreateMlModelService;
import org.openmetadata.schema.api.services.CreateMlModelService.MlModelServiceType;
import org.openmetadata.schema.entity.services.MlModelService;
import org.openmetadata.schema.services.connections.mlmodel.MlflowConnection;
import org.openmetadata.schema.type.MlModelConnection;
import org.openmetadata.sdk.fluent.MlModelServices;

// client is an initialized OpenMetadataClient.
MlModelServices.setDefaultClient(client);

CreateMlModelService request = new CreateMlModelService()
    .withName("mlflow_svc")
    .withServiceType(MlModelServiceType.Mlflow)
    .withConnection(new MlModelConnection().withConfig(
        new MlflowConnection()
            .withTrackingUri("http://localhost:8088")
            .withRegistryUri("http://localhost:8088")));

MlModelService service = MlModelServices.create(request);

curl -X POST "{base_url}/api/v1/services/mlmodelServices" \
  -H "Authorization: Bearer {access_token}" \
  -H "Content-Type: application/json" \
  -d '{
    "name": "mlflow_svc",
    "serviceType": "Mlflow",
    "description": "Production MLflow tracking server",
    "connection": {
      "config": {
        "type": "Mlflow",
        "trackingUri": "http://localhost:8088",
        "registryUri": "http://localhost:8088",
        "supportsMetadataExtraction": true
      }
    }
  }'

{
  "id": "ca22d46e-81b9-4e48-85b5-0adc44980da9",
  "name": "mlflow_svc",
  "fullyQualifiedName": "mlflow_svc",
  "serviceType": "Mlflow",
  "description": "Production MLflow tracking server",
  "version": 0.1,
  "updatedAt": 1769982621618,
  "updatedBy": "admin",
  "href": "http://localhost:8585/api/v1/services/mlmodelServices/ca22d46e-81b9-4e48-85b5-0adc44980da9",
  "connection": {
    "config": {
      "type": "Mlflow",
      "trackingUri": "http://localhost:8088",
      "registryUri": "http://localhost:8088",
      "supportsMetadataExtraction": true
    }
  },
  "owners": [],
  "tags": [],
  "deleted": false,
  "domains": []
}

POST

services

mlmodelServices

POST /v1/services/mlmodelServices

from metadata.generated.schema.entity.services.connections.metadata.openMetadataConnection import (
    AuthProvider,
    OpenMetadataConnection,
)
from metadata.generated.schema.security.client.openMetadataJWTClientConfig import (
    OpenMetadataJWTClientConfig,
)
from metadata.ingestion.ometa.ometa_api import OpenMetadata
from metadata.generated.schema.api.services.createMlModelService import CreateMlModelServiceRequest

metadata = OpenMetadata(
    OpenMetadataConnection(
        hostPort="https://your-company.getcollate.io/api",
        authProvider=AuthProvider.openmetadata,
        securityConfig=OpenMetadataJWTClientConfig(jwtToken="your-jwt-token"),
    )
)

request = CreateMlModelServiceRequest(
    name="mlflow_svc",
    displayName="MLflow Production",
    serviceType="Mlflow",
    description="Production MLflow tracking server",
    connection={
        "config": {
            "type": "Mlflow",
            "trackingUri": "http://localhost:8088",
            "registryUri": "http://localhost:8088",
            "supportsMetadataExtraction": True
        }
    }
)

service = metadata.create_or_update(request)
print(f"Created: {service.fullyQualifiedName.root}")

import org.openmetadata.schema.api.services.CreateMlModelService;
import org.openmetadata.schema.api.services.CreateMlModelService.MlModelServiceType;
import org.openmetadata.schema.entity.services.MlModelService;
import org.openmetadata.schema.services.connections.mlmodel.MlflowConnection;
import org.openmetadata.schema.type.MlModelConnection;
import org.openmetadata.sdk.fluent.MlModelServices;

// client is an initialized OpenMetadataClient.
MlModelServices.setDefaultClient(client);

CreateMlModelService request = new CreateMlModelService()
    .withName("mlflow_svc")
    .withServiceType(MlModelServiceType.Mlflow)
    .withConnection(new MlModelConnection().withConfig(
        new MlflowConnection()
            .withTrackingUri("http://localhost:8088")
            .withRegistryUri("http://localhost:8088")));

MlModelService service = MlModelServices.create(request);

curl -X POST "{base_url}/api/v1/services/mlmodelServices" \
  -H "Authorization: Bearer {access_token}" \
  -H "Content-Type: application/json" \
  -d '{
    "name": "mlflow_svc",
    "serviceType": "Mlflow",
    "description": "Production MLflow tracking server",
    "connection": {
      "config": {
        "type": "Mlflow",
        "trackingUri": "http://localhost:8088",
        "registryUri": "http://localhost:8088",
        "supportsMetadataExtraction": true
      }
    }
  }'

{
  "id": "ca22d46e-81b9-4e48-85b5-0adc44980da9",
  "name": "mlflow_svc",
  "fullyQualifiedName": "mlflow_svc",
  "serviceType": "Mlflow",
  "description": "Production MLflow tracking server",
  "version": 0.1,
  "updatedAt": 1769982621618,
  "updatedBy": "admin",
  "href": "http://localhost:8585/api/v1/services/mlmodelServices/ca22d46e-81b9-4e48-85b5-0adc44980da9",
  "connection": {
    "config": {
      "type": "Mlflow",
      "trackingUri": "http://localhost:8088",
      "registryUri": "http://localhost:8088",
      "supportsMetadataExtraction": true
    }
  },
  "owners": [],
  "tags": [],
  "deleted": false,
  "domains": []
}

Create an ML Model Service

Create a new ML model service connection to a platform such as Mlflow, Sklearn, or SageMaker.

The Python examples on this page use the original client (metadata.ingestion.ometa.ometa_api.OpenMetadata). For more information, see Which Python SDK Should I Use?.

Body Parameters

string

required

Name of the ML model service. Must be unique across all ML model services.

string

required

Type of ML model service, for example Mlflow, Sklearn, SageMaker, CustomMlModel.

object

required

Connection configuration specific to the service type.

Show properties

object

Service-specific connection configuration, such as the trackingUri and registryUri fields for Mlflow.

string

Human-readable display name for the ML model service.

string

Description of the ML model service in Markdown format.

array

Array of owner references (users or teams) to assign to the service.

Show properties

string

UUID of the owner entity.

string

Type of owner entity, for example user, team.

string

Name of the owner entity.

array

Fully qualified names of the domains to assign for governance purposes.

array

Array of classification tags to apply to the ML model service.

Show properties

string

required

Fully qualified name of the tag.

string

Type of label, for example Manual, Derived, Propagated.

string

State of the tag, for example Suggested, Confirmed.

POST /v1/services/mlmodelServices

from metadata.generated.schema.entity.services.connections.metadata.openMetadataConnection import (
    AuthProvider,
    OpenMetadataConnection,
)
from metadata.generated.schema.security.client.openMetadataJWTClientConfig import (
    OpenMetadataJWTClientConfig,
)
from metadata.ingestion.ometa.ometa_api import OpenMetadata
from metadata.generated.schema.api.services.createMlModelService import CreateMlModelServiceRequest

metadata = OpenMetadata(
    OpenMetadataConnection(
        hostPort="https://your-company.getcollate.io/api",
        authProvider=AuthProvider.openmetadata,
        securityConfig=OpenMetadataJWTClientConfig(jwtToken="your-jwt-token"),
    )
)

request = CreateMlModelServiceRequest(
    name="mlflow_svc",
    displayName="MLflow Production",
    serviceType="Mlflow",
    description="Production MLflow tracking server",
    connection={
        "config": {
            "type": "Mlflow",
            "trackingUri": "http://localhost:8088",
            "registryUri": "http://localhost:8088",
            "supportsMetadataExtraction": True
        }
    }
)

service = metadata.create_or_update(request)
print(f"Created: {service.fullyQualifiedName.root}")

import org.openmetadata.schema.api.services.CreateMlModelService;
import org.openmetadata.schema.api.services.CreateMlModelService.MlModelServiceType;
import org.openmetadata.schema.entity.services.MlModelService;
import org.openmetadata.schema.services.connections.mlmodel.MlflowConnection;
import org.openmetadata.schema.type.MlModelConnection;
import org.openmetadata.sdk.fluent.MlModelServices;

// client is an initialized OpenMetadataClient.
MlModelServices.setDefaultClient(client);

CreateMlModelService request = new CreateMlModelService()
    .withName("mlflow_svc")
    .withServiceType(MlModelServiceType.Mlflow)
    .withConnection(new MlModelConnection().withConfig(
        new MlflowConnection()
            .withTrackingUri("http://localhost:8088")
            .withRegistryUri("http://localhost:8088")));

MlModelService service = MlModelServices.create(request);

curl -X POST "{base_url}/api/v1/services/mlmodelServices" \
  -H "Authorization: Bearer {access_token}" \
  -H "Content-Type: application/json" \
  -d '{
    "name": "mlflow_svc",
    "serviceType": "Mlflow",
    "description": "Production MLflow tracking server",
    "connection": {
      "config": {
        "type": "Mlflow",
        "trackingUri": "http://localhost:8088",
        "registryUri": "http://localhost:8088",
        "supportsMetadataExtraction": true
      }
    }
  }'

{
  "id": "ca22d46e-81b9-4e48-85b5-0adc44980da9",
  "name": "mlflow_svc",
  "fullyQualifiedName": "mlflow_svc",
  "serviceType": "Mlflow",
  "description": "Production MLflow tracking server",
  "version": 0.1,
  "updatedAt": 1769982621618,
  "updatedBy": "admin",
  "href": "http://localhost:8585/api/v1/services/mlmodelServices/ca22d46e-81b9-4e48-85b5-0adc44980da9",
  "connection": {
    "config": {
      "type": "Mlflow",
      "trackingUri": "http://localhost:8088",
      "registryUri": "http://localhost:8088",
      "supportsMetadataExtraction": true
    }
  },
  "owners": [],
  "tags": [],
  "deleted": false,
  "domains": []
}

Returns

Returns the created ML model service object with all specified properties and system-generated fields.

Response

string

Unique identifier for the ML model service (UUID format).

string

ML model service name.

string

Fully qualified name of the service.

string

Human-readable display name.

string

Description of the ML model service in Markdown format.

string

Type of ML model service, for example Mlflow, Sklearn, SageMaker, CustomMlModel.

object

Connection configuration for the service.

Show properties

object

Service-specific connection configuration.

array

List of owners assigned to the ML model service.

Show properties

string

UUID of the owner entity.

string

Type of owner entity, for example user, team.

string

Name of the owner entity.

array

Fully qualified names of the assigned domains.

array

Classification tags applied to the ML model service.

Show properties

string

Fully qualified name of the tag.

string

Type of label, for example Manual, Derived, Propagated.

string

State of the tag, for example Suggested, Confirmed.

number

Version number for the entity (starts at 0.1).

Create or Update (PUT)

Use PUT /v1/services/mlmodelServices instead of POST to perform an upsert. If an ML model service with the same fullyQualifiedName already exists, it will be updated; otherwise, a new service is created. The request body is the same as POST.

curl -X PUT "{base_url}/api/v1/services/mlmodelServices" \
  -H "Authorization: Bearer {access_token}" \
  -H "Content-Type: application/json" \
  -d '{ ... same body as POST ... }'

Note: PUT will not return a 409 conflict error if the entity already exists — it will update the existing entity instead. However, for certain fields (such as description, tags, owners, and custom properties), PUT preserves an already-populated value instead of overwriting it with an empty or omitted one — the exact behavior depends on the field and the calling user or bot’s permissions, not a blanket rule. See Entity Update Behavior for the full preserve/merge rules. Use PATCH to intentionally replace an existing value.

Bulk Create or Update (PUT)

Use PUT /v1/services/mlmodelServices/bulk to create or update multiple ML model services in a single request. The request body is an array of create request objects.

curl -X PUT "{base_url}/api/v1/services/mlmodelServices/bulk" \
  -H "Authorization: Bearer {access_token}" \
  -H "Content-Type: application/json" \
  -d '[
    { "name": "mlflow_prod", "serviceType": "Mlflow", "connection": { "config": { "type": "Mlflow", "trackingUri": "http://mlflow-prod:8088" } } },
    { "name": "sagemaker_prod", "serviceType": "SageMaker", "connection": { "config": { "type": "SageMaker" } } }
  ]'

Error Handling

Code	Error Type	Description
`400`	`BAD_REQUEST`	Invalid request body or missing required fields
`401`	`UNAUTHORIZED`	Invalid or missing authentication token
`403`	`FORBIDDEN`	User lacks permission to create ML model services
`409`	`ENTITY_ALREADY_EXISTS`	ML model service with same name already exists (POST only)

API Reference

SDK

API

Data Assets

AI Assets

Discovery

Lineage

Data Contracts

Teams & Users

Data Governance

Data Quality

Alerts

Incidents

Billing

Query Runner

Context Plugins

Standards

Create an ML Model Service

Create an ML Model Service

Body Parameters

Returns

Response

Create or Update (PUT)

Bulk Create or Update (PUT)

Error Handling