Creating a node

You can deploy an individual notebook cell or a third-party Docker image as an independent service using nodes.

If your project uses packages and libraries that are not included in the list of pre-installed software, first configure the node environment using a Docker image.

Node from a modelNode from a model

1. Select the relevant project in your community or on the DataSphere homepage in the Recent projects tab.

2. In the top-right corner, click Create resource. In the pop-up window, select Node.

3. Enter a name for the node in the Name field.

4. Under Type, specify the resource type: Model.

5. In the Models field, select the saved model and specify the input data if needed.

   Note

   When deploying PyTorch models, DataSphere cannot automatically provide the input and output parameters.

   If you are setting the input data, make sure to specify the output data as well. When the input data is set manually for any model type, DataSphere cannot automatically provide the output data.

   For XGBoost models and LightGBM models, the names and types of input and output parameters remain unchanged:

   • Input parameters: input__0 of the TYPE_FP32 type, vector length: [N]. For example, if N=32, specify [32] in the Tensor dimension field.
   • Output parameters: output__0 of the TYPE_FP32 type, scalar value. In the Tensor dimension field, specify [1].

   Tip

   To create a node from XGBoost and LightGBM models saved in DataSphere before April 8, 2024, re-save them to the model resource.

6. Under Folder, select the folder to create new resources in.

7. Under Provisioning, select the configuration of instance computing resources, the availability zone, and the ID of the subnet to host the instance in.

8. In the Maintenance limit field, specify how many of the node's instances can be stopped for maintenance at the same time.

9. Under Access control list (ACL), click Add ACL and specify the IDs of the folders to allow connections to the node from. By default, the ID of the folder owned by the user creating the node is specified.

10. Click Create.

To view all created nodes:

1. Select the relevant project in your community or on the DataSphere homepage in the Recent projects tab.

2. Under Project resources, select Node.

Node from a Docker imageNode from a Docker image

1. Select the relevant project in your community or on the DataSphere homepage in the Recent projects tab.

2. In the top-right corner, click Create resource. In the pop-up window, select Node.

3. Enter a name for the node in the Name field.

4. (Optional) In the Description field, enter a description of the node.

5. Under Type, select the resource to base your node on: Docker.

6. Under Docker image storage, select the container registry. You can select Container Registry or any other registry. For Container Registry, specify:

   • Docker image in the cr.yandex/<registry_ID>/<image_ID>:<tag> format.
   • Username will automatically get the json_key value.
   • Password secret: In the project settings, select the secret containing the file with the authorized key for the service account from the list.

   To use an image from another Docker image storage, select the Other type and fill the remaining fields with the values required for connection to your registry.

7. Optionally, under Docker image settings, set the disk size available in the Docker image.

8. Under Endpoint:

   • Type: Select the node connection protocol: HTTP (HTTP/2) or gRPC.
   • Port: Specify the port for connecting to the node.
   • Timeout: Set the session duration in seconds.
   • Idle timeout: Set the idle time before disconnecting from the node, in seconds.

9. (Optional) Under Telemetry:

   • Type: Select the telemetry service (Prometheus or Yandex Monitoring).
   • HTTP path: Specify the address to send telemetry data to.
   • Port: Specify the port to send telemetry data to.

10. (Optional) Under Healthcheck:

    • Type: Protocol to perform node health checks through (HTTP or gRPC).
    • Port: Port that node health checks are performed from.
    • Path: Path to the resource to check.
    • Timeout: Check duration in seconds.
    • Interval: Interval between checks in seconds.
    • Fails threshold: Allowed number of failed checks.
    • Passes threshold: Required number of successful checks.

11. (Optional) Under Docker image settings, set the total memory available in the Docker image.

12. Under Folder, select the folder to create new resources in.

13. Under Provisioning:

    • Instance configuration: Select a configuration of the instance's computing resources.
    • Distribution by zones: Add an availability zone and the ID of the subnet to host the instance in.
    • Maintenance limit: Specify how many of the node's instances can be stopped for maintenance at the same time.
    • Additional disk: Optionally, add an additional disk for the instance. If you selected multiple instances, a disk will be created for each one.

14. Under Access control list (ACL), click Add ACL and specify the IDs of the folders to allow connections to the node from. By default, the ID of the folder owned by the user creating the node is specified.

15. Click Create.

To view all created nodes:

1. Select the relevant project in your community or on the DataSphere homepage in the Recent projects tab.

2. Under Project resources, select Node.

See alsoSee also

• Configuring the environment for deploying a standalone service
• Updating a node
• Deleting a node
• Creating an alias
• Deploying a service based on a Docker image
• Deploying a service from an ONNX model