import os
from scale_gp_beta import SGPClient
client = SGPClient(
api_key=os.environ.get("SGP_API_KEY"),
)
inference_model = client.models.create(
name="name",
vendor_configuration={
"model_image": {
"command": ["string"],
"registry": "registry",
"repository": "repository",
"tag": "tag",
},
"model_infra": {},
},
)
print(inference_model.id)
{
"id": "id",
"created_at": "2019-12-27T18:11:19.117Z",
"created_by_user_id": "created_by_user_id",
"model_type": "generic",
"model_vendor": "openai",
"name": "name",
"status": "failed",
"model_metadata": {
"foo": "bar"
},
"object": "model",
"vendor_configuration": {
"model_image": {
"command": [
"string"
],
"registry": "registry",
"repository": "repository",
"tag": "tag",
"env_vars": {
"foo": "bar"
},
"healthcheck_route": "healthcheck_route",
"predict_route": "predict_route",
"readiness_delay": 0,
"request_schema": {
"foo": "bar"
},
"response_schema": {
"foo": "bar"
},
"streaming_command": [
"string"
],
"streaming_predict_route": "streaming_predict_route"
},
"model_infra": {
"cpus": "string",
"endpoint_type": "async",
"gpu_type": "nvidia-tesla-t4",
"gpus": 0,
"high_priority": true,
"labels": {
"foo": "string"
},
"max_workers": 0,
"memory": "memory",
"min_workers": 0,
"per_worker": 0,
"public_inference": true,
"storage": "storage"
}
}
}