שימוש בנתיבים שרירותיים בהתאמה אישית בפריסה יחידה

from google.cloud import aiplatform

invoke_enabled_model = aiplatform.Model.upload(
    display_name="invoke-enabled-model",
    serving_container_image_uri=IMAGE_URI,
    serving_container_invoke_route_prefix="/*",
    serving_container_health_route=HEALTH_ROUTE,
    serving_container_environment_variables={"KEY": "VALUE"},
    serving_container_args=[],
    sync=True,
)

dedicated_endpoint = aiplatform.Endpoint.create(
    display_name="dedicated-endpoint-for-invoke-enabled-model",
    dedicated_endpoint_enabled=True,
    sync=True,
)

dedicated_endpoint.deploy(
    model=invoke_enabled_model,
    traffic_percentage=100,
    machine_type=MACHINE_TYPE,
    accelerator_type=ACCELERATOR_TYPE,
    accelerator_count=1,
    max_replica_count=1,
)

def invoke_tabular_sample(
    project: str,
    location: str,
    endpoint_id: str,
    request_path: str,
    http_request_body: Dict[str, Any],
    stream: bool = False,
):
    aiplatform.init(project=project, location=location)

    dedicated_endpoint = aiplatform.Endpoint(endpoint_id)
    if stream:
        for chunk in dedicated_endpoint.invoke(
            request_path=request_path,
            body=json.dumps(http_request_body).encode("utf-8"),
            headers={"Content-Type": "application/json"},
            stream=True,
        ):
            print(chunk)
    else:
        response = dedicated_endpoint.invoke(
            request_path=request_path,
            body=json.dumps(http_request_body).encode("utf-8"),
            headers={"Content-Type": "application/json"},
        )
        print(response)

def invoke_direct_deployed_model_inference_tabular_sample(
    project: str,
    location: str,
    endpoint_id: str,
    request_path: str,
    http_request_body: Dict[str, Any],
    deployed_model_id: str,
    stream: bool = False,
):
    aiplatform.init(project=project, location=location)

    dedicated_endpoint = aiplatform.Endpoint(endpoint_id)
    if stream:
        for chunk in dedicated_endpoint.invoke(
            request_path=request_path,
            body=json.dumps(http_request_body).encode("utf-8"),
            headers={"Content-Type": "application/json"},
            deployed_model_id=deployed_model_id,
            stream=True,
        ):
            print(chunk)
    else:
        response = dedicated_endpoint.invoke(
            request_path=request_path,
            body=json.dumps(http_request_body).encode("utf-8"),
            headers={"Content-Type": "application/json"},
            deployed_model_id=deployed_model_id,
        )
        print(response)