/templates/save
Create a new template
curl --request POST \
--url https://api.shadeform.ai/v1/templates/save \
--header 'Content-Type: application/json' \
--header 'X-API-KEY: <api-key>' \
--data '{
"name": "My Template",
"description": "A template for ML workloads",
"public": true,
"launch_configuration": {
"type": "docker",
"docker_configuration": {
"image": "vllm/vllm-openai:latest",
"args": "--model mistralai/Mistral-7B-v0.1",
"shared_memory_in_gb": 8,
"envs": [
{
"name": "HUGGING_FACE_HUB_TOKEN",
"value": "hugging_face_api_token"
}
],
"port_mappings": [
{
"host_port": 80,
"container_port": 8000
}
],
"volume_mounts": [
{
"host_path": "~/.cache/huggingface",
"container_path": "/root/.cache/huggingface"
}
]
},
"script_configuration": {
"base64_script": "IyEvYmluL2Jhc2gKCiMgRW5kbGVzcyBsb29wCndoaWxlIHRydWUKZG8KICAgICMgRmV0Y2ggYSBjYXQgZmFjdCB3aXRoIGEgbWF4aW11bSBsZW5ndGggb2YgMTQwIGNoYXJhY3RlcnMKICAgIGN1cmwgLS1uby1wcm9ncmVzcy1tZXRlciBodHRwczovL2NhdGZhY3QubmluamEvZmFjdD9tYXhfbGVuZ3RoPTE0MAoKICAgICMgUHJpbnQgYSBuZXdsaW5lIGZvciByZWFkYWJpbGl0eQogICAgZWNobwoKICAgICMgU2xlZXAgZm9yIDMgc2Vjb25kcyBiZWZvcmUgdGhlIG5leHQgaXRlcmF0aW9uCiAgICBzbGVlcCAzCmRvbmUKCgo="
}
},
"auto_delete": {
"date_threshold": "2006-01-02T15:04:05-07:00",
"spend_threshold": "3.14"
},
"alert": {
"date_threshold": "2006-01-02T15:04:05-07:00",
"spend_threshold": "3.14"
},
"volume_mount": {
"auto": true
},
"tags": [
"ml",
"pytorch"
],
"envs": [
{
"name": "HUGGING_FACE_HUB_TOKEN",
"value": "hugging_face_api_token"
}
],
"networking": {
"ufw_rules": [
{
"rule": "allow",
"from_ip": "192.168.1.0/24",
"to_ip": "10.0.0.0/8",
"port": "80",
"proto": "tcp"
}
]
}
}'{
"id": "d290f1ee-6c54-4b01-90e6-d701748f0851"
}Authorizations
Body
Name of the template
"My Template"
Description of the template
"A template for ML workloads"
Whether the template is publicly available
true
Defines automatic actions after the instance becomes active.
Specifies the type of launch configuration. See Launch Configuration for more details.
docker, script "docker"
May only be used if launch_configuration.type is 'docker'. Use docker_configuration to automatically pull and run a docker image. See this tutorial for examples.
Specifies the docker image to be pulled and run on the instance at startup.
"vllm/vllm-openai:latest"
Specifies the container arguments passed into the image at runtime.
"--model mistralai/Mistral-7B-v0.1"
Describes the amount of shared memory allocated for the container. Equivalent to using the --shm-size flag in the docker cli. If shared_memory_in_gb is not specified, then the container will use the host namespace which is the equivalent of --ipc=host.
8
List of environment variable name-value pairs that will be passed to the docker container.
Environment variables for the container image.
List of port mappings between the host instance and the docker container. Equivalent of -p flag for docker run command.
Maps the public instance port to a port on the container.
List of volume mounts between the host instance and the docker container. Equivalent of -v flag for docker run command.
Mounts the host volume to a container file path.
May only be used if launch_configuration.type is 'script'. Configures a startup script to be run automatically after the instance is active. See this [tutorial]/guides/startupscript) for examples.
A startup script that is base64 encoded.
"IyEvYmluL2Jhc2gKCiMgRW5kbGVzcyBsb29wCndoaWxlIHRydWUKZG8KICAgICMgRmV0Y2ggYSBjYXQgZmFjdCB3aXRoIGEgbWF4aW11bSBsZW5ndGggb2YgMTQwIGNoYXJhY3RlcnMKICAgIGN1cmwgLS1uby1wcm9ncmVzcy1tZXRlciBodHRwczovL2NhdGZhY3QubmluamEvZmFjdD9tYXhfbGVuZ3RoPTE0MAoKICAgICMgUHJpbnQgYSBuZXdsaW5lIGZvciByZWFkYWJpbGl0eQogICAgZWNobwoKICAgICMgU2xlZXAgZm9yIDMgc2Vjb25kcyBiZWZvcmUgdGhlIG5leHQgaXRlcmF0aW9uCiAgICBzbGVlcCAzCmRvbmUKCgo="
Volume mount configuration
Set to true to automatically mount unmounted disks to a default filesystem.
Tags associated with the template
["ml", "pytorch"]
Network and firewall configuration
List of UFW (Uncomplicated Firewall) rules
Uncomplicated Firewall rule configuration
The UFW rule action
"allow"
Source IP address or CIDR range
"192.168.1.0/24"
Destination IP address or CIDR range
"10.0.0.0/8"
Port number or range (e.g. '80' or '8000:8999')
"80"
Protocol (e.g. tcp, udp)
"tcp"
Response
Response of the /templates/save API call
The unique identifier for the instance. Used in the instances for the /instances/{id}/info and /instances/{id}/delete APIs.
"d290f1ee-6c54-4b01-90e6-d701748f0851"
curl --request POST \
--url https://api.shadeform.ai/v1/templates/save \
--header 'Content-Type: application/json' \
--header 'X-API-KEY: <api-key>' \
--data '{
"name": "My Template",
"description": "A template for ML workloads",
"public": true,
"launch_configuration": {
"type": "docker",
"docker_configuration": {
"image": "vllm/vllm-openai:latest",
"args": "--model mistralai/Mistral-7B-v0.1",
"shared_memory_in_gb": 8,
"envs": [
{
"name": "HUGGING_FACE_HUB_TOKEN",
"value": "hugging_face_api_token"
}
],
"port_mappings": [
{
"host_port": 80,
"container_port": 8000
}
],
"volume_mounts": [
{
"host_path": "~/.cache/huggingface",
"container_path": "/root/.cache/huggingface"
}
]
},
"script_configuration": {
"base64_script": "IyEvYmluL2Jhc2gKCiMgRW5kbGVzcyBsb29wCndoaWxlIHRydWUKZG8KICAgICMgRmV0Y2ggYSBjYXQgZmFjdCB3aXRoIGEgbWF4aW11bSBsZW5ndGggb2YgMTQwIGNoYXJhY3RlcnMKICAgIGN1cmwgLS1uby1wcm9ncmVzcy1tZXRlciBodHRwczovL2NhdGZhY3QubmluamEvZmFjdD9tYXhfbGVuZ3RoPTE0MAoKICAgICMgUHJpbnQgYSBuZXdsaW5lIGZvciByZWFkYWJpbGl0eQogICAgZWNobwoKICAgICMgU2xlZXAgZm9yIDMgc2Vjb25kcyBiZWZvcmUgdGhlIG5leHQgaXRlcmF0aW9uCiAgICBzbGVlcCAzCmRvbmUKCgo="
}
},
"auto_delete": {
"date_threshold": "2006-01-02T15:04:05-07:00",
"spend_threshold": "3.14"
},
"alert": {
"date_threshold": "2006-01-02T15:04:05-07:00",
"spend_threshold": "3.14"
},
"volume_mount": {
"auto": true
},
"tags": [
"ml",
"pytorch"
],
"envs": [
{
"name": "HUGGING_FACE_HUB_TOKEN",
"value": "hugging_face_api_token"
}
],
"networking": {
"ufw_rules": [
{
"rule": "allow",
"from_ip": "192.168.1.0/24",
"to_ip": "10.0.0.0/8",
"port": "80",
"proto": "tcp"
}
]
}
}'{
"id": "d290f1ee-6c54-4b01-90e6-d701748f0851"
}