Create ModelDeployment

POST

https://host.com/apis/models/v2/workspaces/:workspace/deployments

POST

/apis/models/v2/workspaces/:workspace/deployments

$ curl -X POST https://host.com/apis/models/v2/workspaces/workspace/deployments \
>      -H "Content-Type: application/json" \
>      -d '{
>   "name": "llama-deploy-v1",
>   "config": "llama-config-v2"
> }'

1 {
2   "name": "llama-3.1-8b",
3   "workspace": "research-team",
4   "created_at": "2024-01-15T09:30:00Z",
5   "updated_at": "2024-01-15T09:30:00Z",
6   "entity_version": 1,
7   "config": "llama-config-v2",
8   "config_version": 3,
9   "id": "deploy-1234abcd",
10   "project": "project/nlp/llama",
11   "status": "PENDING",
12   "status_message": "Deployment is being initialized",
13   "status_history": [
14     {
15       "timestamp": "2024-01-15T09:30:00Z",
16       "status": "PENDING",
17       "status_message": "Deployment is being initialized"
18     }
19   ],
20   "model_provider_id": "provider-ai/llama",
21   "auth_context": {
22     "principal_id": "user-7890",
23     "principal_email": "alice@example.com",
24     "principal_groups": [
25       "ml-engineers",
26       "researchers"
27     ],
28     "principal_on_behalf_of": "user-4567",
29     "principal_on_behalf_of_groups": [
30       "team-leads"
31     ],
32     "principal_on_behalf_of_email": "bob@example.com"
33   }
34 }

Create a new ModelDeployment (version 1).

Path parameters

workspacestringRequired

Request

This endpoint expects an object.

namestringRequiredformat: "^[\w\-.]+$"<=255 characters

Name of the deployment. Allowed characters: letters (a-z, A-Z), digits (0-9), underscores, hyphens, and dots.

configstringRequired<=255 characters

Reference to the ModelDeploymentConfig name

projectstringOptionalformat: "^[\w\-./]+$"<=255 characters

The URN of the project associated with this deployment

config_versionintegerOptional

Reference to a specific ModelDeploymentConfig version. If not specified, uses latest.

Response

Create a new model deployment

namestringformat: "^[\w\-.]+$"<=255 characters

Name of the entity. Name/workspace combo must be unique across all entities. Allowed characters: letters (a-z, A-Z), digits (0-9), underscores, hyphens, and dots.

workspacestringformat: "^[\w\-.]+$"<=255 characters

The workspace of the entity. Allowed characters: letters (a-z, A-Z), digits (0-9), underscores, hyphens, and dots.

created_atdatetime

The timestamp of model entity creation

updated_atdatetime

The timestamp of the last model entity update

entity_versioninteger

Version of this deployment. Automatically managed.

configstring<=255 characters

Reference to the ModelDeploymentConfig name

config_versioninteger

Reference to the specific ModelDeploymentConfig version

idstring

Unique identifier for the deployment

projectstringformat: "^[\w\-./]+$"<=255 characters

The URN of the project associated with this entity.

statusenumDefaults to UNKNOWN

Current status of the deployment, populated by models controller

status_messagestring<=1000 charactersDefaults to

Detailed status message, populated by models controller

status_historylist of objects

History of status changes, ordered chronologically (oldest first)

model_provider_idstring<=255 characters

Optional reference to the auto-created ModelProvider workspace/name (format: workspace/name)

auth_contextobject

Auth context captured at deployment creation.

Errors

422

Unprocessable Entity Error